WO2014148077A1 - 情報端末、行動推定方法、及びプログラム - Google Patents
情報端末、行動推定方法、及びプログラム Download PDFInfo
- Publication number
- WO2014148077A1 WO2014148077A1 PCT/JP2014/050766 JP2014050766W WO2014148077A1 WO 2014148077 A1 WO2014148077 A1 WO 2014148077A1 JP 2014050766 W JP2014050766 W JP 2014050766W WO 2014148077 A1 WO2014148077 A1 WO 2014148077A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- change frequency
- user
- unit
- index data
- behavior
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0251—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity
- H04W52/0254—Power saving arrangements in terminal devices using monitoring of local events, e.g. events related to user activity detecting a user operation or a tactile contact or a motion of the device
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
- H04W4/027—Services making use of location information using location based information parameters using movement velocity, acceleration information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/005—Routing actions in the presence of nodes in sleep or doze mode
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2101/00—Indexing scheme associated with group H04L61/00
- H04L2101/60—Types of network addresses
- H04L2101/681—Types of network addresses using addresses for wireless personal area networks or wireless sensor networks, e.g. Zigbee addresses
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
- H04W88/08—Access point devices
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Definitions
- the present invention relates to an information terminal, a behavior estimation method, and a program for estimating the behavior and state of a user and an object.
- Patent Document 1 a specific area indicating a place where the user stays for a long time (for example, work or home) is set in advance, and the user stays in the communication area of the base station including the specific area.
- a technique for reducing the power consumption of the user terminal by suppressing the number of activations of a GPS (Global Positioning System) sensor built in the user terminal is disclosed.
- the acceleration of the object and the vibration applied to the object are acquired from the acceleration sensor of the control device, and the GPS receiver of the control device is operated based on the acquired acceleration and vibration change.
- a technique for reducing the power consumption of the control device by changing the period to be performed is disclosed.
- the place where the user stays for a long time may vary depending on the user's behavior and situation.
- the technique described in Patent Document 2 reduces the position information of the target object by reducing the execution cycle of the process for acquiring the position information of the target object in the vicinity of the destination to which the target object is transferred. Get well.
- the technique described in Patent Document 2 reduces the power consumption by increasing the execution cycle of the process of acquiring the position information of the target object at a place other than the destination. For this reason, in the method described in Patent Document 2, the accuracy of grasping the behavior state of the target is lowered in most of the areas other than the vicinity of the destination.
- the present invention has been made in view of such circumstances, and provides a technique for accurately estimating the behavior state of a target while suppressing power consumption.
- the first aspect relates to information terminals.
- the information terminal according to the first aspect includes an extraction unit that extracts at least one of the change frequency of the index data and the change frequency of the user behavior state indicated by the acquired index data as change frequency information, A setting unit that sets a rule for controlling the sleep state of the estimation unit that estimates the behavior state based on the extracted change frequency information, and a control unit that controls the sleep state of the estimation unit based on the set rule Have.
- the second aspect relates to a behavior estimation method executed by an information terminal (computer).
- the computer extracts at least one of the change frequency of the index data and the change frequency of the user's behavior state indicated by the acquired index data as change frequency information, and the user
- a rule for controlling the sleep state of the estimation unit for estimating the behavior state of the estimation unit is set based on the extracted change frequency information, and the sleep state of the estimation unit is controlled based on the set rule.
- a program that causes an information terminal to realize the configuration of each aspect described above may be used, or a computer-readable recording medium that records such a program may be used.
- This recording medium includes a non-transitory tangible medium.
- FIG. 1 is a diagram conceptually illustrating a hardware configuration example of the information terminal 1 in the first embodiment.
- the information terminal 1 includes a CPU (Central Processing Unit) 11, a memory 12, an input / output interface (I / F) 13, a communication device 14, and the like. Each of these units is connected to the bus 15, for example.
- the memory 12 is a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk, a portable storage medium, or the like.
- the input / output I / F 13 is connected to various sensors such as an atmospheric pressure sensor and an acceleration sensor, and an input / output device such as a GPS device.
- the communication device 14 communicates with other devices located outside by wireless or wired.
- the information terminal 1 is a mobile terminal such as a so-called mobile phone or PDA (Personal Digital Assistant), and may include a display device such as a display, a device that inputs and outputs sound, and the like.
- a display device such as a display, a device that inputs and outputs sound, and the like.
- FIG. 2 is a diagram conceptually illustrating a processing configuration example of the information terminal 1 in the first embodiment.
- FIG. 2 shows only the configuration related to the behavior estimation method executed by the information terminal 1 in the present embodiment. Therefore, the information terminal 1 has a large number of processing units other than the processing units illustrated.
- the information terminal 1 includes an extraction unit 101, a setting unit 102, a control unit 103, an estimation unit 104, and the like. Each of these processing units is realized, for example, by executing a program stored in the memory 12 by the CPU 11. In addition, the program is installed from a portable recording medium such as a CD (Compact Disc) or a memory card or another device via the input / output I / F 13 or the communication device 14 and stored in the memory 12. Also good.
- a portable recording medium such as a CD (Compact Disc) or a memory card or another device via the input / output I / F 13 or the communication device 14 and stored in the memory 12. Also good.
- the estimation unit 104 executes behavior estimation processing for estimating a user's behavior state based on information obtained from an acceleration sensor or a GPS receiver.
- the “behavioral state” refers to an action related to the movement of the user among various actions that the user can take.
- Examples of the user's behavior state include "stop” indicating a state where the user is stopped on the spot, a state where the user is walking, a state where the user is running, or a state where the user is climbing up and down the stairs. “Walking / running / staircase” shown, “automobile” showing a state where the user is on a car, “train” showing a state where the user is on a train, and the like.
- a user's action state is not limited to these.
- the action state of “walking / running / staircase” may be distinguished from “walking”, “running”, and “staircase”.
- the behavior estimation process can be realized using a known technique. Further, the estimation unit 104 is switched to the sleep state or the operation state under the control of the control unit 103.
- the extraction unit 101 acquires index data via the memory 12, the input / output I / F 13, and the communication device 14. Then, the extraction unit 101 extracts at least one of the change frequency of the index data and the change frequency of the user's behavior state indicated by the acquired index data as change frequency information. Then, the extraction unit 101 transmits the change frequency information extracted from the index data to the setting unit 102.
- the extraction unit 101 will be described in detail.
- index is information that can indicate the change frequency of the user's behavior state
- index data is data including this index.
- the index data includes, for example, a base station ID of a communication base station, a Wi-Fi (Wireless Fidelity) access point SSID (Service Set Identifier), a barometric pressure acquired by a barometric sensor, and the information terminal 1 The user's schedule information and the like.
- the extraction unit 101 extracts the change frequency of the index data from the acquired index data.
- the extraction unit 101 can extract the change frequency of the index data from the base station ID of the communication base station, the SSID of the Wi-Fi access point, and the atmospheric pressure.
- the extraction unit 101 can extract the presence / absence of a change in the base station ID within a predetermined time, the number of changes in the base station ID within a predetermined time, and the like as the change frequency of the index data.
- the extraction unit 101 can extract, for example, the difference in the SSID list of Wi-Fi access points acquired every predetermined time as the change frequency of the index data.
- the extraction unit 101 can extract, for example, the change amount of the atmospheric pressure measured every predetermined time as the change frequency of the index data.
- the change frequency of the user's behavior state can be estimated from the change frequency of the index data. For example, if the base station ID, the SSID of the Wi-Fi access point, and the atmospheric pressure acquired by the extraction unit 101 change frequently, that is, if the index data changes frequently, the user is moving Probability is high. When the user is moving, the user may perform various actions such as using various moving means. For this reason, when the change frequency of the index data is large, it can be estimated that the time during which a certain behavior state is maintained is short, and the user's behavior state is likely to change (the change frequency is large).
- the base station ID, the SSID of the Wi-Fi access point, and the atmospheric pressure do not change much, that is, if the change frequency of the index data is small, the user is likely to stay in a predetermined area. .
- the time during which a certain behavior state (particularly “stop”, etc.) is maintained tends to be relatively longer than when the user is moving. Therefore, when the change frequency of index data is small, it can be estimated that a user's action state is hard to change (change frequency is small).
- the extraction unit 101 may be able to extract the change frequency of the user's behavior state from the acquired index data.
- the extraction unit 101 can extract the change frequency of the user's behavior state from the schedule information.
- the extraction unit 101 represents a user's action schedule at that time, such as “meeting”, “moving”, and “present”. Identify keywords.
- the change frequency of the user's behavioral state can be estimated.
- the change frequency of the user's behavior state is small from a keyword such as “conference” or “attended” that is estimated to have a long time for the user to maintain a certain behavior state.
- the change frequency of a user's action state is large from the keyword estimated that the time for which a user maintains a certain action state is short, such as "movement”. Then, by preparing a list in which these keywords are associated with the change frequency of the user's behavior state in a storage area such as the memory 12 of the information terminal 1 or the storage of the external device, the extraction unit 101 Using the identified keyword, the change frequency of the user's behavior state can be extracted from the list.
- the setting unit 102 sets a rule (control rule) for controlling the sleep state of the estimation unit 104 based on the change frequency information extracted by the extraction unit 101.
- the control rule includes at least a condition for causing the estimation unit 104 to sleep and a sleep time corresponding to the condition.
- the setting unit 102 sets a control rule in the information terminal 1 such that the sleep time is shorter than when the change frequency indicated by the change frequency information is small.
- the setting unit 102 sets a control rule in the information terminal 1 such that the sleep time is longer than when the change frequency indicated by the change frequency information is large.
- This control rule is realized, for example, as a plurality of tables with different setting values such as sleep time.
- the setting unit 102 selects one of the tables according to the change frequency information extracted by the extraction unit 101, and causes the control unit 103 to refer to the selected table.
- the control rule may be realized as a function that generates a longer sleep time as the change frequency indicated by the change frequency information is smaller.
- the setting unit 102 may cause the control unit 103 to refer to a control rule generated by substituting the quantitative change frequency information extracted by the extraction unit 101 into the function.
- the setting of the control rule by the setting unit 102 means that another processing unit (the control unit 103 or the like) is operated based on the control rule.
- FIG. 3 illustrates two different tables (sleep time setting tables) that define how to control the sleep state.
- FIG. 3A is a sleep time setting table applied when the change frequency indicated by the change frequency information is high, that is, when the change frequency of the user's action state is high.
- FIG. 3B is a sleep time setting table applied when the change frequency indicated by the change frequency information is small, that is, when the change frequency of the user's action state is small.
- Each record of the sleep time setting table includes an estimation unit when an action state such as “stop” indicated in the “behavior state” column is continuously estimated for the time indicated in the “behavior state continuation threshold time” column.
- the uppermost record in the sleep time setting table of FIG. 3A shows that when the estimation unit 104 estimates that the user's behavior state is “stopped” for 120 seconds, the estimation unit 104 is set to 60. It means to sleep for a second.
- the behavior state continuation threshold time and sleep time set in the sleep time setting table are set to values that are empirically grasped from sample data and the like. In the sleep time setting table of FIG. 3A, the action state continuation threshold time is set longer and the sleep time is set shorter than the sleep time setting table of FIG. This is because the situation in which the table of FIG.
- the setting unit 102 determines to use any sleep time setting table based on whether or not the change frequency information extracted by the extraction unit 101 is equal to or greater than a predetermined threshold. For example, when the change frequency information extracted by the extraction unit 101 is equal to or greater than a predetermined threshold, the setting unit 102 determines that “the change frequency of the user's behavior state is large”, and as a control rule, FIG. To use the sleep time setting table. On the other hand, when the change frequency information extracted by the extraction unit 101 is less than the predetermined threshold, the setting unit 102 determines that “the change frequency of the user's behavior state is small”, and as a control rule, FIG. To use the sleep time setting table.
- control rules such as the sleep time setting table are stored in a storage unit (not shown), and the setting unit 102 determines whether the change frequency information extracted by the extraction unit 101 is equal to or greater than a predetermined threshold. Based on this, any sleep time setting table may be read from the storage unit. Further, the storage unit in which the control rules such as the sleep time setting table are stored may be built in the information terminal 1 or may be built in another device located outside the information terminal 1. .
- the control unit 103 controls the sleep state of the estimation unit 104 based on the control rule set by the setting unit 102.
- control the sleep state of the estimation unit 104 means a sleep state where the estimation unit 104 cannot execute the behavior estimation process (sleeps), and the estimation unit 104 can execute the behavior estimation process It means switching between operating states (not sleeping).
- the operation of the control unit 103 will be described by taking as an example the case where a control rule as shown in FIG. 3 is used. In this case, the control unit 103 determines whether to put the estimation unit 104 to sleep based on the duration of the user's behavior state estimated by the estimation unit 104.
- the control unit 103 receives the user behavior state estimated by the estimation unit 104, and determines whether or not the estimated duration of the user behavior state satisfies a condition set in the control rule. judge. When the condition set in the control rule is satisfied, the control unit 103 causes the estimation unit 104 to sleep until the sleep time associated with the condition elapses. Further, if the estimation unit 104 is executing the behavior estimation process at a predetermined interval (for example, every 10 seconds), the control unit 103 sets the number of times the user's behavior state estimated by the estimation unit 104 is continued. As described above, the sleep state of the estimation unit 104 can be controlled.
- the control unit 103 is associated with the condition.
- the estimation unit 104 is caused to sleep until the sleep time elapses.
- FIG. 4 is a flowchart illustrating a flow in which the information terminal 1 according to the first embodiment sets a control rule for the estimation unit 104.
- FIG. 5 is a flowchart illustrating a flow in which the information terminal 1 in the first embodiment controls the sleep state of the estimation unit 104.
- the flow in which the information terminal 1 sets the control rule of the estimation unit 104 will be described with reference to FIG.
- a case where the information terminal 1 acquires a base station ID as index data will be described as an example.
- the information terminal 1 acquires a base station ID as index data (S102). Then, the information terminal 1 extracts the change frequency of the base station ID acquired in S102 as change frequency information (S104). And the information terminal 1 sets the control rule of the estimation part 104 based on the change frequency information extracted by S104 (S106). For example, the information terminal 1 acquires the current base station ID every predetermined time (for example, 10 minutes), and checks whether the base station ID has changed. And the information terminal 1 extracts the frequency
- the information terminal 1 determines that the change frequency indicated by the change frequency information is large, and the change frequency information A control rule is set such that the sleep time is shorter than when the change frequency indicated by is small.
- the change frequency information is less than the predetermined threshold, the information terminal 1 determines that the change frequency indicated by the change frequency information is small, and the sleep time is longer than when the change frequency indicated by the change frequency information is large.
- the information terminal 1 estimates a user's action state by the estimation part 104 (S202). For example, the estimation unit 104 calculates a moving speed of the user based on information acquired from an acceleration sensor or the like or GPS information, and estimates the current behavior state of the user. Then, the information terminal 1 calculates the duration of the behavior state estimated in S202 (S204). The information terminal 1 can calculate the duration of the behavior state by, for example, counting the time from when a certain behavior state is estimated until a different behavior state is estimated. Then, the information terminal 1 determines whether or not the behavior state estimated in S202 has continued for a predetermined time (S206). The predetermined time is determined based on the control rule set in S106. For example, if the sleep time setting table of FIG.
- the predetermined time used in S206 is “120 seconds”.
- the sleep time setting table of FIG. 3B is set in S106, and the user's action state is estimated as “stopped” in S202, the predetermined time used in S206 is “90 seconds”.
- the information terminal 1 continues the behavior estimation process (S202).
- the behavior state estimated in S202 continues for a predetermined time or more (S206: YES)
- the information terminal 1 sleeps corresponding to the behavior state estimated in S202 based on the set control rule.
- the estimation unit 104 is put to sleep for the time (S208). For example, assume that the sleep setting table shown in FIG. 3A is set in S106. In this state, when the estimation unit 104 estimates that the user's behavior state is “stopped” for 120 seconds, the information terminal 1 causes the estimation unit 104 to sleep for 60 seconds. When the estimation unit 104 estimates that the user's behavior state is “walking / running / staircase” for 20 seconds, the information terminal 1 causes the estimation unit 104 to sleep for 60 seconds. When the estimation unit 104 estimates that the user's behavior state is “automobile” for 20 seconds, the information terminal 1 causes the estimation unit 104 to sleep for 50 seconds.
- the information terminal 1 when the estimation unit 104 continuously estimates that the user's behavior state is “train” for 20 seconds, the information terminal 1 causes the estimation unit 104 to sleep for 50 seconds. Then, after a predetermined sleep time has elapsed, the information terminal 1 cancels the sleep state of the estimation unit 104 (S210), and causes the estimation unit 104 to resume the behavior estimation process (S202).
- the above is the processing flow of the information terminal 1 in the first embodiment. Note that the processes shown in FIGS. 4 and 5 are executed independently.
- the control rule used in S206 is dynamically switched according to the change frequency information acquired in S104.
- the control rule for controlling the sleep state of the estimation unit 104 is set in the information terminal 1 from the change frequency information extracted from the index data. Then, based on the set control rule, the sleep state of the estimation unit 104 is controlled. Thereby, according to this embodiment, the sleep state of the estimation part 104 can be controlled according to the change frequency of a user's action state. Specifically, when the change frequency indicated by the change frequency information extracted from the index data is large, that is, when the change frequency of the user behavior state is large, the sleep time is longer than when the change frequency indicated by the change frequency information is small. Is set in the information terminal 1, and the sleep state of the estimation unit 104 is controlled according to the control rule.
- the sleep time becomes longer than when the change frequency indicated by the change frequency information is large.
- the information terminal 1 can raise the execution frequency of the action estimation process by the estimation part 104 in the situation where a user's action state is easy to change, and can improve the estimation precision of a target action state.
- the information terminal 1 suppresses execution of useless behavior estimation processing by the estimation unit 104 in a situation where the user's behavior state is unlikely to change, and power consumed by the behavior estimation processing. Can be reduced.
- the change frequency of the user's behavior state described above can be determined by using the estimation result of the behavior estimation process without using the change frequency information extracted from the index data.
- the behavior estimation process has a larger calculation amount than the process of extracting change frequency information from the index data.
- the information terminal 1 according to the present invention can reduce power consumption more efficiently than the case where the estimation result of the behavior estimation process is used.
- control rule set by the setting unit 102 is not limited to FIG.
- the setting unit 102 may set a control rule that controls the sleep state based on the behavior state change pattern estimated by the estimation unit 104.
- FIG. 6 is a diagram illustrating another example of the control rule set based on the change frequency information.
- the information terminal 1 controls the sleep state of the estimation unit 104 according to the change pattern of the user behavior state estimated by the estimation unit 104.
- the information terminal 1 causes the estimation unit 104 to sleep for the time indicated by the “sleep time” associated with the “previous behavior state” and the “current behavior state”.
- FIG. 6 does not show any action state change pattern related to “stop”, but “walk / run / staircase”, “car”, “train”, and the like similarly show change patterns of each action state.
- the sleep time is set accordingly.
- what the behavior state change pattern means may change depending on the change frequency of the user behavior state. As an example, consider a case where the user behavior state estimated by the estimation unit 104 changes from “walking” to “stop”.
- this change pattern is a temporary stop of the user, such as when the user stops outdoors with a red light, and the “stop” state does not continue so long. It can be judged.
- this change pattern is a case in which the user has stopped for a long time, such as when sitting at his / her seat in the workplace, and the “stop” state continues for a long time after that. it can. Therefore, even in this case, the above-described effects can be obtained.
- the information terminal 1 in this embodiment converts each change frequency information extracted from a plurality of types of index data each having a different index into unified change frequency information (sleep degree) having a unified index, and A control rule is set based on the unified change frequency information.
- the information terminal 1 in the second embodiment will be described focusing on the content different from the first embodiment. In the following description, the same contents as those in the first embodiment are omitted as appropriate.
- FIG. 7 is a diagram conceptually illustrating a processing configuration example of the information terminal 1 in the second embodiment. As shown in FIG. 7, the information terminal 1 in this embodiment further includes a conversion unit 105.
- the extraction unit 101 acquires a plurality of types of index data each having a different index. Then, the extraction unit 101 extracts change frequency information from each index data.
- the conversion part 105 converts each change frequency information extracted by the extraction part 101 into a sleep degree.
- the sleep degree is a unified index that makes it possible to equally handle change frequency information extracted from a plurality of types of index data each having a different index.
- the conversion unit 105 converts the change frequency information respectively extracted from a plurality of types of index data into sleep degrees as follows. For example, when the base station ID is acquired as index data, the conversion unit 105 determines whether or not the base station ID acquired this time has changed from the previously acquired base station ID. As a result of the determination, when the base station ID acquired this time has not changed from the previously acquired base station ID, the conversion unit 105 adds a predetermined value (for example, “1” or the like) to the sleep degree.
- a predetermined value for example, “1” or the like
- the conversion unit 105 when the base station ID acquired this time has changed from the previously acquired base station ID, the conversion unit 105 resets the sleep degree to zero. Not limited to this, the conversion unit 105 may subtract a predetermined value from the sleep degree when the base station ID acquired this time has changed from the base station ID acquired last time.
- the conversion unit 105 converts keywords such as “meeting”, “attended”, and “movement” into a sleep degree. Generally, if the keyword acquired from the schedule information is “meeting” or “attended”, it can be determined that the change frequency information is small. Conversely, if the keyword acquired from the schedule information is “move”, it can be determined that the change frequency information is large. Therefore, for example, the conversion unit 105 prepares a list indicating the correspondence between each keyword acquired from the schedule information and the sleep degree in the storage unit or the like, and refers to the list, thereby converting the schedule information to the sleep degree. Convert.
- the conversion unit 105 converts each change frequency information extracted from the index data having different indexes, such as “base station ID” and “schedule information”, into a unified index “sleep degree”.
- the setting unit 102 can treat each change frequency information equally.
- the setting part 102 sets a control rule based on the sleep degree converted from the change frequency information of each parameter
- the setting unit 102 sets a control rule including a sleep start timing (sleep start line) and a sleep time based on the sleep degree. Specifically, the setting unit 102 determines a change frequency that comprehensively considers each index data from the sleep degree.
- the setting unit 102 sets a sleep start line or a sleep time according to a change frequency that comprehensively considers each index data, that is, a change frequency of the user's action state.
- the sleep start line is a so-called threshold value
- the control unit 103 causes the estimation unit 104 to sleep when the sleep degree exceeds the sleep start line.
- the setting unit 102 resets the sleep degree. And if the sleep state of the estimation part 104 is cancelled
- the setting unit 102 can determine the change frequency of the user's action state by checking the inclination of the sleep degree. For example, if the sleep degree is abruptly increased, the setting unit 102 can determine that the change frequency of the user behavior state indicated by the change frequency information of each index data is small. Therefore, when the sleep degree is rapidly increased, the setting unit 102 extends the time during which the estimation unit 104 is in the sleep state by lowering the sleep start line or setting the sleep time longer.
- the setting unit 102 can determine that the change frequency of the user's action state indicated by each index data is large. Therefore, when the sleep degree is slowly increasing or decreasing, the setting unit 102 sets the time during which the estimation unit 104 is in the sleep state by increasing the sleep start line or setting the sleep time short. shorten.
- the amount of change in the sleep start line and sleep time adjusted by the setting unit 102 may be a predetermined value or a value calculated according to the slope of the sleep degree. . Note that whether the slope of the sleep degree is steep or not can be determined based on, for example, whether the slope of the sleep degree is equal to or greater than a predetermined threshold.
- the conversion unit 105 may add the sleep degree when the index data changes, and reset or subtract the sleep degree when the index data does not change.
- the setting unit 102 can determine that the change frequency of the user's action state is high. Therefore, when the sleep degree is abruptly increased, the setting unit 102 shortens the time during which the estimation unit 104 is in the sleep state by raising the sleep start line or setting the sleep time short.
- the setting unit 102 can determine that the change frequency of the user's behavior state is small. Therefore, when the sleep degree is slowly increasing or decreasing, the setting unit 102 sets the time for the estimation unit 104 to enter the sleep state by lowering the sleep start line or setting the sleep time longer. Lengthen.
- the conversion unit 105 may convert the change amount of the index data such as the number of changes of the base station ID within a predetermined time, not the presence / absence of the change of the index data, into the sleep degree. In this case, for example, the conversion unit 105 may add or subtract the sleep degree as described above depending on whether or not the change amount of the index data is equal to or greater than a predetermined threshold, or replace the change amount of the index data as it is with the sleep degree. May be.
- FIG. 8 is a flowchart showing the flow of processing of the information terminal 1 in the second embodiment.
- the information terminal 1 acquires a plurality of types of index data (S302). Then, the information terminal 1 extracts change frequency information of each index data acquired in S302 (S304). Then, the information terminal 1 converts each change frequency information extracted in S304 into a sleep degree (S306). And the information terminal 1 sets the control rule of the estimation part 104 based on the sleep degree each converted by S306 (S308).
- FIG. 9 is a diagram illustrating a transition example of the sleep degree.
- the extraction unit 101 acquires the base station ID, the atmospheric pressure, and the schedule information as index data, and the setting unit 102 adjusts only the sleep time according to the inclination of the sleep degree. To do.
- Three graphs shown on the left side of FIG. 9 are graphs showing temporal changes in the sleep degrees of the base station ID, the atmospheric pressure, and the schedule information. The graph shown on the right side of FIG.
- FIG. 9 is a graph showing the temporal change in the sleep degree when these three graphs are integrated.
- the sleep degree exceeds the sleep start line at time t 1 .
- the setting unit 102 sets the sleep time according to the slope of the sleep degree.
- the setting unit 102 determines time t 1 to time t 2 as the sleep time. Note that, as described above, the setting unit 102 adjusts the section determined from the time t 1 to the time t 2 according to the slope of the sleep degree when the sleep start line is exceeded.
- the setting unit 102 determines the interval determined from the time t 1 to the time t 2 as compared with the case where the slope of the sleep degree is less than the predetermined slope. Set a longer time.
- the setting unit 102 determines from time t 1 to time t 2 as compared to the case where the slope of the sleep degree is greater than or equal to the predetermined slope. Set the interval to be shortened. Then, the control unit 103 causes the estimation unit 104 to sleep until the sleep time indicated by the section from the time t 1 to the time t 2 determined by the setting unit 102 elapses.
- the processing unit such as the extraction unit 101 is also put to sleep.
- the processing unit such as the extraction unit 101 may be kept in the sleep mode without causing the processing unit to sleep. By doing in this way, it becomes possible to extend or shorten the sleep time of the estimation unit 104 based on the change in the sleep degree acquired while the estimation unit 104 is sleeping.
- the sleep state can be controlled.
- change frequency information extracted from a plurality of types of index data having different indices is converted into a sleep degree.
- a sleep state control rule of the estimation unit 104 is set.
- the information terminal 1 in the present embodiment learns change frequency information related to specific index data from the history of index data acquired by the information terminal 1.
- the specific index data is index data in which one change frequency information can be specified by one index data without depending on the history among the index data acquired by the information terminal 1.
- a base station ID (index data) that tends to be connected for a long time statistically longer than a predetermined threshold is learned as specific index data, and information indicating that the change frequency is small is learned as the change frequency information.
- the And the information terminal 1 extracts the change frequency information regarding the learned specific index data as the change frequency information of the acquired index data.
- the information terminal 1 in the third embodiment will be described focusing on the contents different from those in the first and second embodiments. In the following description, the same contents as those in the first and second embodiments are omitted as appropriate.
- FIG. 10 is a diagram conceptually illustrating a processing configuration example of the information terminal 1 in the third embodiment. As illustrated in FIG. 10, the information terminal 1 in the present embodiment further includes a learning unit 106 and a storage unit 200.
- the learning unit 106 learns the change frequency information of each index data based on the index data history acquired by the information terminal 1.
- the “index data history” is, for example, index data acquired in a predetermined period (for example, one week or one month).
- the history of index data may be stored in the storage area of the information terminal 1 or may be stored in the storage area of another device located outside the server or the like.
- it is assumed that the history of index data acquired by the extraction unit 101 is stored in the storage unit 200 included in the information terminal 1.
- the learning unit 106 can extract change frequency information corresponding to specific index data from the history of index data acquired in a predetermined period, which is stored in the storage unit 200.
- a base station ID that is continuously connected for a predetermined threshold time that is, whose change frequency is small
- a base station ID or Wi-Fi access point history acquired during a predetermined period.
- the learning unit 106 stores an identifier indicating specific index data, such as a base station ID or an SSID of a Wi-Fi access point, and change frequency information obtained from the history of the index data in association with each other in the storage unit 200.
- FIG. 11 is a diagram illustrating an example of a correspondence relationship between the specific index data stored in the storage unit 200 and the change frequency information.
- a correspondence relationship between an index data ID that is an identifier for identifying specific index data and change frequency information corresponding to the specific index data is stored.
- the extraction unit 101 refers to the storage unit 200 using the acquired index data, and extracts change frequency information related to the specific index data stored in the storage unit 200.
- Information indicating the correspondence between the specific index data and the change frequency information may be stored in a storage area of another device located outside the server or the like. In this case, the extraction unit 101 refers to a storage area of another device located outside using the acquired index data, and extracts change frequency information regarding specific index data stored in the storage area.
- FIG. 12 is a flowchart showing the flow of processing of the information terminal 1 in the third embodiment.
- the information terminal 1 extracts change frequency information corresponding to the index data by referring to the storage unit 200 using the index data acquired in S102 (S402). For example, it is assumed that index data indicating “base station ID 001” is acquired in S102 when the storage unit 200 stores information as illustrated in FIG. In this case, the information terminal 1 extracts, from the storage unit 200, information indicating that the change frequency is large, which is associated with the “base station ID001”. And the information terminal 1 sets a control rule as demonstrated in 1st Embodiment based on the change frequency information acquired by S402 (S106).
- the change frequency information of specific index data which is grasped from the history of index data acquired in the past, is stored in the storage unit 200. And the change frequency information corresponding to the said index data is extracted by referring the memory
- FIG. As a result, according to the present embodiment, for specific index data, the change frequency information can be acquired from a single piece of data only by referring to the storage unit 200 without calculating the change frequency information from the history of a plurality of data. be able to. Therefore, the calculation amount in the information terminal 1 can be reduced, and the power consumption can be further reduced.
- the information terminal 1 in the present embodiment controls the sleep state of the estimation unit 104 using the change frequency information of the index data extracted in the information terminal used by another user.
- the information terminal 1 in the fourth embodiment will be described focusing on the contents different from those in the first to third embodiments. In the following description, the same contents as those in the first to third embodiments are omitted as appropriate.
- FIG. 13 is a diagram conceptually illustrating a processing configuration example of the behavior estimation system in the fourth exemplary embodiment.
- the behavior estimation system in this embodiment includes a user information terminal 1, another user information terminal 1 ′, and a shared information storage unit 300. There may be a plurality of other user terminals 1 ′.
- the other user terminal 1 ′ has at least the same configuration as the information terminal 1.
- the extraction unit 101 ′ performs the same processing as the extraction unit 101 of the above-described embodiment.
- the learning unit 106 ′ learns the change frequency information of each index data based on the acquired history of index data, and the learning result is the shared information storage unit 300, similarly to the learning unit 106 of the embodiment described above.
- the shared information storage unit 300 is included in another device located outside the information terminal 1 such as a server. Similar to the storage unit 200 of the third embodiment, the shared information storage unit 300 stores the correspondence between specific index data and change frequency information as shown in FIG.
- the shared information storage unit 300 calculates an average value or an intermediate value of each change frequency information, etc. Thus, a value comprehensively determined from a plurality of change frequency information is stored.
- FIG. 14 is a flowchart showing the flow of processing of the information terminal 1 in the fourth embodiment.
- the information terminal 1 refers to the shared information storage unit 300 using the index data acquired in S102, thereby extracting change frequency information corresponding to the index data (S502). And the information terminal 1 sets a control rule as demonstrated in 1st Embodiment based on the change frequency information acquired by S502 (S106).
- the change frequency information extracted by the information terminal 1 ′ of another user is extracted based on the index data acquired by the information terminal 1.
- ascertained by information terminal 1 'of another user can be controlled accurately.
- the information terminal 1 in the present embodiment further improves the accuracy of the behavior estimation process of the estimation unit 104 using the change frequency of the index data.
- the information terminal 1 in the fifth embodiment will be described focusing on the contents different from those in the first to fourth embodiments. In the following description, the same contents as those in the first to fourth embodiments are omitted as appropriate.
- FIG. 15 is a diagram conceptually illustrating a processing configuration example of the information terminal 1 in the fifth embodiment. As shown in FIG. 15, the information terminal 1 in the present embodiment further includes a correction unit 107.
- the correction unit 107 corrects the estimation result of the estimation unit 104 based on the change frequency information extracted by the extraction unit 101. For example, when the same base station ID is continuously acquired, it is assumed that the estimation unit 104 has estimated the user's behavior state as “car” or “train”. Here, if the user is really moving using a car or a train, the base station ID and the like should change frequently. Then, in the present situation where the same base station ID is continuously acquired, it is considered that the possibility that the user is on a car or a train is low. That is, it can be determined that the estimation by the estimation unit 104 is likely to be erroneous. Therefore, the correction unit 107 corrects the estimation result by the estimation unit 104 to “stop” or the like in view of the situation where the same base station ID is continuously acquired.
- FIG. 16 is a flowchart showing a flow in which the information terminal 1 in the fifth embodiment corrects the estimation result.
- the information terminal 1 compares the change frequency information extracted from the index data by the extraction unit 101 with the behavior state estimated by the estimation unit 104 (S602). Then, the information terminal 1 determines whether or not the change frequency information extracted from the index data contradicts the behavior state estimated by the estimation unit 104. When it is determined that the change frequency information extracted from the index data and the behavior state estimated by the estimation unit 104 are inconsistent (S604: YES), the information terminal 1 displays the behavior state estimated by the estimation unit 104. The correction is made based on the change frequency information extracted by the extraction unit 101.
- the estimation unit 104 determines that the cause There is a high possibility that an incorrect estimation result is output. In this case, the information terminal 1 determines that the change frequency of the index data is inconsistent with the estimated action state. Then, the information terminal 1 corrects the behavior state to “stop” or the like based on the change frequency information “not changed” (S606). On the other hand, when it is determined that the change frequency information extracted from the index data is consistent with the behavior state estimated by the estimation unit 104 (S604: NO), the information terminal 1 performs the behavior state estimated by the estimation unit 104. Do not correct.
- the information terminal 1 adjusts at least the sleep time set in the control rule using the behavior tendency information extracted from the history of the user behavior state estimated by the estimation unit 104.
- the behavior tendency information is information indicating the tendency of each behavior state regarding a certain user and the trend.
- the information terminal 1 in the sixth embodiment will be described focusing on the contents different from those in the first to fifth embodiments. In the following description, the same contents as those in the first to fifth embodiments are omitted as appropriate.
- FIG. 17 is a diagram conceptually illustrating a processing configuration example of the information terminal 1 in the sixth embodiment.
- the information terminal 1 in this embodiment extracts behavior tendency information from the history of the user's behavior state estimated by the estimation unit 104 and stores it in the behavior tendency storage unit 400. And the information terminal 1 adjusts the action state continuation threshold time and sleep time set to the control rule as shown in FIG. 3 based on the stored action tendency information.
- the information terminal 1 extracts behavior tendency information from the history of the behavior state of the user estimated by the estimation unit 104.
- the estimation unit 104 calculates an average value or an intermediate value of the duration of each behavior state from the history of the user behavior state estimated by the estimation unit 104, and associates the behavior tendency information with the behavior state information. To do.
- the estimation unit 104 determines whether or not the change frequency of the current user behavior state is large based on the control rule set in the information terminal 1. Then, the estimation unit 104 associates the extracted behavior tendency information with the change frequency of the user's behavior state, and stores it in the behavior tendency storage unit 400.
- FIG. 18 is a diagram illustrating an example of information stored in the behavior tendency storage unit 400.
- the behavior trend information stored in the behavior trend storage unit 400 is updated each time information is received from the estimation unit 104.
- the setting unit 102 acquires behavior trend information from the behavior trend storage unit 400 using the change frequency information acquired by the extraction unit 101.
- the setting part 102 calculates the action state continuation threshold time of each action state and the sleep time corresponding to it from the acquired action tendency information, and sets it to a control rule.
- the setting unit 102 divides the duration of each behavior state included in the behavior trend information by a predetermined ratio, for example, and sets the behavior state duration threshold time of each behavior state and the corresponding sleep time. Is calculated.
- the behavior tendency storage unit 400 may be included in another device located outside the server, for example. In this case, the behavior tendency storage unit 400 further includes information for identifying each user such as a user ID, and the information terminal 1 uses the user ID of the information terminal 1 from the behavior tendency storage unit 400 to the information terminal 1. Action tendency information corresponding to the user is acquired.
- FIG. 19 is a flowchart showing a process flow of the information terminal 1 in the sixth embodiment.
- the information terminal 1 acquires the user's behavior state estimated by the estimation unit 104 and its duration (S702).
- the information terminal 1 can calculate the duration of the behavior state by, for example, counting the time from when a certain behavior state is estimated until a different behavior state is estimated.
- the information terminal 1 confirms the currently set control rule, and acquires the current user behavior state change frequency (S704).
- the information terminal 1 acquires behavior trend information corresponding to the behavior status acquired in S702 and the change frequency of the user behavior status acquired in S704 from the behavior trend storage unit 400 (S706).
- the information terminal 1 reads the behavior trend information from the behavior trend storage unit 400 using the change frequency information extracted by the extraction unit 101. Then, the information terminal 1 adjusts the sleep time based on the duration of each action state included in the read action tendency information (S710). For example, the information terminal 1 calculates the behavior state continuation threshold time of each behavior state and the corresponding sleep time by dividing the duration of each behavior state included in the behavior trend information by a predetermined ratio. Moreover, the information terminal 1 may use the read duration of each action state as it is, or may use it after correcting it using arbitrary constants.
- this embodiment can also be applied to the sleep time setting table shown in FIG.
- the duration of each behavior state in a certain user is grasped.
- the sleep time of the estimation part 104 is adjusted based on the grasped
- the example in which the sleep process operation setting is divided into two stages of when the index data change frequency is large and small is shown.
- the operation setting for sleep processing may be divided into three or more stages by classifying more finely.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephone Function (AREA)
Abstract
Description
〔装置構成〕
図1は、第1実施形態における情報端末1のハードウェア構成例を概念的に示す図である。図1に示されるように、情報端末1は、CPU(Central Processing Unit)11、メモリ12、入出力インタフェース(I/F)13、通信装置14等を有する。これら各ユニットは、例えばバス15に接続される。メモリ12は、RAM(Random Access Memory)、ROM(Read Only Memory)、ハードディスク、可搬型記憶媒体等である。入出力I/F13は、気圧センサや加速度センサといった各種センサ、及びGPS装置等の入出力装置と接続される。通信装置14は、無線又は有線で、外部に位置する他の装置と通信を行う。
図2は、第1実施形態における情報端末1の処理構成例を概念的に示す図である。また、図2には、本実施形態における情報端末1により実行される行動推定方法に関する構成のみが示されている。そのため、情報端末1は、図示される各処理部以外の多数の処理部を有する。
以下、第1実施形態における情報端末1の処理の流れについて、図4及び図5を用いて説明する。図4は、第1実施形態における情報端末1が推定部104の制御ルールを設定する流れを示すフローチャートである。図5は、第1実施形態における情報端末1が推定部104のスリープ状態を制御する流れを示すフローチャートである。
以上、本実施形態では、指標データから抽出された変化頻度情報から、推定部104のスリープ状態を制御する制御ルールが情報端末1に設定される。そして、設定された制御ルールに基づいて、推定部104のスリープ状態が制御される。これにより、本実施形態によれば、ユーザの行動状態の変化頻度に合わせて、推定部104のスリープ状態を制御することができる。具体的には、指標データから抽出された変化頻度情報が示す変化頻度が大きい場合、すなわち、ユーザの行動状態の変化頻度が大きい場合は、変化頻度情報が示す変化頻度が小さいときよりもスリープ時間が短くなるような制御ルールが情報端末1に設定され、当該制御ルールに従って、推定部104のスリープ状態が制御される。一方、指標データから抽出された変化頻度情報が示す変化頻度が小さい場合、すなわち、ユーザの行動状態の変化頻度が小さい場合は、変化頻度情報が示す変化頻度が大きいときよりもスリープ時間が長くなるような制御ルールが設定され、当該制御ルールに従って、推定部104のスリープ状態が制御される。このようにすることで、情報端末1は、ユーザの行動状態が変わりやすい状況では、推定部104による行動推定処理の実行頻度を上げ、対象の行動状態の推定精度を向上させることができる。また、このようにすることで、情報端末1は、ユーザの行動状態が変わりにくい状況では、推定部104で無駄な行動推定処理が実行されることを抑制し、行動推定処理で消費される電力を低減させることができる。
本実施形態における情報端末1は、各々が異なる指標を有する複数種の指標データから抽出されるそれぞれの変化頻度情報を、統一された指標を有する統一変化頻度情報(スリープ度)に変換し、当該統一変化頻度情報に基づいて、制御ルールを設定する。以下、第2実施形態における情報端末1について、第1実施形態と異なる内容を中心に説明する。以下の説明では、第1実施形態と同様の内容については適宜省略する。
図7は、第2実施形態における情報端末1の処理構成例を概念的に示す図である。図7に示されるように、本実施形態における情報端末1は変換部105を更に有する。
以下、第2実施形態における情報端末1の処理の流れについて、図8を用いて説明する。図8は、第2実施形態における情報端末1の処理の流れを示すフローチャートである。
以上、本実施形態では、基地局IDや気圧等、各々の指標が異なる複数種の指標データから抽出される変化頻度情報が、スリープ度に変換される。そして、スリープ度に変換された各変化頻度情報に基づいて、推定部104のスリープ状態の制御ルールが設定される。これにより、本実施形態によれば、指標が異なる各指標データを、"スリープ度"として統一して判断することが可能となり、スリープの開始タイミングやスリープ時間といった、スリープ状態を制御する制御ルールをより細やかに設定することができる。
本実施形態における情報端末1は、当該情報端末1で取得された指標データの履歴から、特定指標データに関する変化頻度情報を学習する。ここで、特定指標データとは、当該情報端末1で取得された指標データの中で、履歴に頼らず、1つの指標データにより、1つの変化頻度情報を特定し得る指標データである。例えば、統計的に所定閾値以上の長い時間接続され続ける傾向にある基地局ID(指標データ)が特定指標データとして学習され、かつ、その変化頻度情報として変化頻度が小さいことを示す情報が学習される。そして、情報端末1は、当該学習された特定指標データに関する変化頻度情報を、取得された指標データの変化頻度情報として抽出する。以下、第3実施形態における情報端末1について、第1及び第2実施形態と異なる内容を中心に説明する。以下の説明では、第1及び第2実施形態と同様の内容については適宜省略する。
図10は、第3実施形態における情報端末1の処理構成例を概念的に示す図である。図10に示されるように、本実施形態における情報端末1は、学習部106と記憶部200とを更に有する。
以下、第3実施形態における情報端末1の処理の流れについて、図12を用いて説明する。図12は、第3実施形態における情報端末1の処理の流れを示すフローチャートである。
以上、本実施形態では、過去に取得された指標データの履歴から把握される、特定の指標データの変化頻度情報が記憶部200に記憶される。そして、抽出部101により取得された指標データを用いて記憶部200を参照することにより、当該指標データに対応する変化頻度情報が抽出される。これにより、本実施形態によれば、特定指標データについては、複数のデータの履歴からその変化頻度情報を算出しなくとも、記憶部200を参照するだけで1つのデータにより変化頻度情報を取得することができる。よって、情報端末1での演算量を減らし、その消費電力を更に低減できる。
本実施形態における情報端末1は、他のユーザが使用する情報端末において抽出された指標データの変化頻度情報を用いて、推定部104のスリープ状態を制御する。以下、第4実施形態における情報端末1について、第1から第3実施形態と異なる内容を中心に説明する。以下の説明では、第1から第3実施形態と同様の内容については適宜省略する。
図13は、第4実施形態における行動推定システムの処理構成例を概念的に示す図である。本実施形態における行動推定システムは、ユーザの情報端末1、他のユーザの情報端末1'、及び共有情報記憶部300で構成される。なお、他のユーザ端末1'は複数存在していてもよい。
以下、第4実施形態における情報端末1の処理の流れについて、図14を用いて説明する。図14は、第4実施形態における情報端末1の処理の流れを示すフローチャートである。
以上、本実施形態では、他のユーザの情報端末1'で抽出された変化頻度情報が、情報端末1で取得された指標データに基づいて抽出される。これにより、本実施形態によれば、他のユーザの情報端末1'で統計的に把握される指標データの変化頻度情報に従って、推定部104のスリープ状態を精度よく制御できる。
本実施形態における情報端末1は、指標データの変化頻度を用いて、推定部104の行動推定処理の精度をさらに向上させる。以下、第5実施形態における情報端末1について、第1から第4実施形態と異なる内容を中心に説明する。以下の説明では、第1から第4実施形態と同様の内容については適宜省略する。
図15は、第5実施形態における情報端末1の処理構成例を概念的に示す図である。図15に示されるように、本実施形態における情報端末1は修正部107を更に有する。
以下、第5実施形態における情報端末1の処理の流れについて、図16を用いて説明する。図16は、第5実施形態における情報端末1が推定結果を修正する流れを示すフローチャートである。
以上、本実施形態では、抽出部101で指標データから抽出された変化頻度情報と、推定部104で推定された行動状態が矛盾するか否かが判断される。そして、両者が矛盾する結果を示していた場合は、指標データから抽出された変化頻度情報を基準として、推定部104で推定された行動状態が修正される。これにより、本実施形態によれば、推定部104の推定の誤りを抑制し、ユーザの行動状態の推定精度を向上させることができる。
本実施形態における情報端末1は、推定部104で推定されたユーザの行動状態の履歴から抽出される行動傾向情報を用いて、制御ルールに設定される少なくともスリープ時間を調整する。ここで、行動傾向情報とは、あるユーザに関して、各行動状態がどの程度継続するか、その傾向を示す情報である。以下、第6実施形態における情報端末1について、第1から第5実施形態と異なる内容を中心に説明する。以下の説明では、第1から第5実施形態と同様の内容については適宜省略する。
図17は、第6実施形態における情報端末1の処理構成例を概念的に示す図である。本実施形態における情報端末1は、推定部104で推定されたユーザの行動状態の履歴から行動傾向情報を抽出し行動傾向記憶部400に記憶する。そして、情報端末1は、記憶された行動傾向情報に基づいて、図3に示されるような制御ルールに設定される、行動状態継続閾値時間及びスリープ時間を調整する。
以下、第6実施形態における情報端末1の処理の流れについて、図19を用いて説明する。図19は、第6実施形態における情報端末1の処理の流れを示すフローチャートである。
以上、本実施形態では、推定部104で推定された行動状態の履歴に基づき、あるユーザにおける、各行動状態の継続時間が把握される。そして、把握された各行動状態の継続時間に基づいて、推定部104のスリープ時間が調整される。これにより、本実施形態によれば、各ユーザの行動状態の継続時間の傾向等を情報端末1にフィードバックさせて、精度よく推定部104のスリープ状態を制御することができる。
以上、図面を参照して本発明の実施形態について述べたが、これらは本発明の例示であり、上記以外の様々な構成を採用することもできる。
Claims (19)
- 取得された指標データにより示される、前記指標データの変化頻度及びユーザの行動状態の変化頻度のうち、少なくとも一方を変化頻度情報として抽出する抽出部と、
ユーザの行動状態を推定する推定部のスリープ状態を制御するルールを、前記抽出された変化頻度情報に基づいて設定する設定部と、
前記設定されたルールに基づいて、前記推定部のスリープ状態を制御する制御部と、
を有する情報端末。 - 前記設定部は、前記抽出部により抽出された変化頻度情報に対応する前記ルールであって、前記推定部により推定され得るユーザの行動状態毎の、該行動状態の継続時間、及び該行動状態の継続回数のいずれか一方と、スリープ時間との対応関係を示す前記ルールを設定し、
前記制御部は、前記推定部により推定されるユーザの行動状態の継続時間、及び前記推定部により推定されるユーザの行動状態の継続回数の少なくともいずれか一方に基づいて、前記ルールからスリープ時間を決定し、該決定されたスリープ時間分、前記推定部をスリープさせる、
請求項1に記載の情報端末。 - 前記設定部は、前記抽出部により抽出された変化頻度情報に対応する前記ルールであって、前記推定部により推定され得るユーザの行動状態の変化パターンと、スリープ時間との対応関係を示す前記ルールを設定し、
前記制御部は、前記推定部により推定されるユーザの行動状態の変化パターンに基づいて、前記ルールからスリープ時間を決定し、該決定されたスリープ時間分、前記推定部をスリープさせる、
請求項1または2に記載の情報端末。 - 前記設定部は、前記推定部により推定されたユーザの行動状態の履歴から抽出される、各行動状態の継続傾向情報を取得し、該取得された継続傾向情報を用いて前記ルールの少なくともスリープ時間を調整する、
請求項1から3のいずれか1項に記載の情報端末。 - 複数種の前記指標データからそれぞれ抽出される複数の前記変化頻度情報を、統一変化頻度情報に変換する変換部を更に有し、
前記設定部は、前記統一変化頻度情報に基づいて、前記ルールを設定する、
請求項1に記載の情報端末。 - 当該情報端末で取得された前記指標データの履歴から抽出される、特定指標データに関する前記変化頻度情報を記憶部に記憶させる学習部を更に有し、
前記抽出部は、前記取得された指標データに基づいて特定される前記特定指標データに関する変化頻度情報を、前記取得された指標データの変化頻度情報として用いる、
請求項1から5のいずれか1項に記載の情報端末。 - 前記抽出部は、他のユーザの情報端末で抽出された前記変化頻度情報を記憶する記憶部から、前記取得された指標データに基づいて特定される前記他のユーザの情報端末で抽出された変化頻度情報を取得し、該取得された変化頻度情報を前記取得された指標データの変化頻度として用いる、
請求項1から6のいずれか1項に記載の情報端末。 - 前記推定部により推定されたユーザの行動状態と、前記取得された指標データの変化頻度情報との比較結果に基づいて、前記推定されたユーザの行動状態を修正する修正部を更に有する、
請求項1から7のいずれか1項に記載の情報端末。 - 前記抽出部は、通信基地局の基地局ID、Wi-Fi(Wireless Fidelity)アクセスポイントのSSID(Service Set Identifier)、気圧、及び前記ユーザのスケジュールが記憶されたスケジュール情報のうち、少なくともいずれか1つを前記指標データとして取得する、
請求項1から8のいずれか1項に記載の情報端末。 - コンピュータが、
取得された指標データにより示される、前記指標データの変化頻度及びユーザの行動状態の変化頻度のうち、少なくとも一方を変化頻度情報として抽出し、
ユーザの行動状態を推定する推定部のスリープ状態を制御するルールを、前記抽出された変化頻度情報に基づいて設定し、
前記設定されたルールに基づいて、前記推定部のスリープ状態を制御する、
ことを含む行動推定方法。 - 前記コンピュータが、
前記抽出された変化頻度情報に対応する前記ルールであって、前記推定部により推定され得るユーザの行動状態毎の、該行動状態の継続時間、及び該行動状態の継続回数のいずれか一方と、スリープ時間との対応関係を示す前記ルールを設定し、
前記推定部により推定されるユーザの行動状態の継続時間、及び前記推定部により推定されるユーザの行動状態の継続回数の少なくともいずれか一方に基づいて、前記ルールからスリープ時間を決定し、該決定されたスリープ時間分、前記推定部をスリープさせる、
ことを含む請求項10に記載の行動推定方法。 - 前記コンピュータが、
前記抽出された変化頻度情報に対応する前記ルールであって、前記推定部により推定され得るユーザの行動状態の変化パターンと、スリープ時間との対応関係を示す前記ルールを設定し、
前記推定部により推定されるユーザの行動状態の変化パターンに基づいて、前記ルールからスリープ時間を決定し、該決定されたスリープ時間分、前記推定部をスリープさせる、
ことを含む請求項10または11に記載の行動推定方法。 - 前記コンピュータが、
前記推定部により推定されたユーザの行動状態の履歴から抽出される、各行動状態の継続傾向情報を取得し、該取得された継続傾向情報を用いて前記ルールの少なくともスリープ時間を調整する、
ことを含む請求項10から12のいずれか1項に記載の行動推定方法。 - 前記コンピュータが、
複数種の前記指標データからそれぞれ抽出される複数の前記変化頻度情報を、統一変化頻度情報に変換し、
前記統一変化頻度情報に基づいて、前記ルールを設定する、
ことを含む請求項10に記載の行動推定方法。 - 前記コンピュータが、
当該コンピュータで取得された前記指標データの履歴から抽出される、特定指標データに関する前記変化頻度情報を記憶部に記憶させ、
前記取得された指標データに基づいて特定される前記特定指標データに関する変化頻度情報を、前記取得された指標データの変化頻度情報として用いる、
ことを含む請求項10から14のいずれか1項に記載の行動推定方法。 - 前記コンピュータが、
他のユーザのコンピュータで抽出された前記変化頻度情報を記憶する記憶部から、前記取得された指標データに基づいて特定される前記他のユーザの情報端末で抽出された変化頻度情報を取得し、該取得された変化頻度情報を前記取得された指標データの変化頻度として用いる、
ことを含む請求項10から15のいずれか1項に記載の行動推定方法。 - 前記コンピュータが、
前記推定部により推定されたユーザの行動状態と、前記取得された指標データの変化頻度情報との比較結果に基づいて、前記推定されたユーザの行動状態を修正する、
ことを含む請求項10から16のいずれか1項に記載の行動推定方法。 - 前記コンピュータが、
通信基地局の基地局ID、Wi-Fi(Wireless Fidelity)アクセスポイントのSSID(Service Set Identifier)、気圧、及び前記ユーザのスケジュールが記憶されたスケジュール情報のうち、少なくともいずれか1つを前記指標データとして取得する、
ことを含む請求項10から17のいずれか1項に記載の行動推定方法。 - コンピュータに、
取得された指標データにより示される、前記指標データの変化頻度及びユーザの行動状態の変化頻度のうち、少なくとも一方を変化頻度情報として抽出する抽出部と、
ユーザの行動状態を推定する推定部のスリープ状態を制御するルールを、前記抽出された変化頻度情報に基づいて設定する設定部と、
前記設定されたルールに基づいて、前記推定部のスリープ状態を制御する制御部と、
を実現させるプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015506625A JP6311701B2 (ja) | 2013-03-22 | 2014-01-17 | 情報端末、行動推定方法、及びプログラム |
US14/777,577 US20160295514A1 (en) | 2013-03-22 | 2014-01-17 | Information terminal, movement estimation method, and storage medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013060455 | 2013-03-22 | ||
JP2013-060455 | 2013-03-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014148077A1 true WO2014148077A1 (ja) | 2014-09-25 |
Family
ID=51579774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/050766 WO2014148077A1 (ja) | 2013-03-22 | 2014-01-17 | 情報端末、行動推定方法、及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US20160295514A1 (ja) |
JP (1) | JP6311701B2 (ja) |
WO (1) | WO2014148077A1 (ja) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11313370A (ja) * | 1998-04-28 | 1999-11-09 | Toshiba Corp | 移動パケット通信システムとそのデータ通信装置、基地局装置及び移動端末装置 |
JP2002528009A (ja) * | 1998-10-15 | 2002-08-27 | テレフオンアクチーボラゲット エル エム エリクソン(パブル) | 移動通信ネットワークにおける移動局用の可変スリープモード |
JP2005079895A (ja) * | 2003-08-29 | 2005-03-24 | Toshiba Corp | 情報端末 |
JP2010028168A (ja) * | 2008-07-15 | 2010-02-04 | Fuji Electric Systems Co Ltd | 無線通信ネットワークシステム、無線端末、無線通信方法、無線通信プログラム |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008147778A (ja) * | 2006-12-06 | 2008-06-26 | Matsushita Electric Ind Co Ltd | 移動体通信システムおよび移動体通信端末装置 |
US8467804B2 (en) * | 2007-10-16 | 2013-06-18 | Sony Corporation | Mobile terminals and methods for regulating power-on/off of a GPS positioning circuit |
EP2215494A1 (en) * | 2007-11-30 | 2010-08-11 | Nokia Corporation | Controlling operation of a positioning module |
US8996332B2 (en) * | 2008-06-24 | 2015-03-31 | Dp Technologies, Inc. | Program setting adjustments based on activity identification |
JP2010033174A (ja) * | 2008-07-25 | 2010-02-12 | Toshiba Corp | 携帯型電子機器 |
US7679553B1 (en) * | 2008-08-01 | 2010-03-16 | Microsoft Corporation | Adjusting GPS communication with a wireless device |
US8682342B2 (en) * | 2009-05-13 | 2014-03-25 | Microsoft Corporation | Constraint-based scheduling for delivery of location information |
US9188451B2 (en) * | 2013-02-28 | 2015-11-17 | Here Global B.V. | Method and apparatus for minimizing power consumption in a navigation system |
-
2014
- 2014-01-17 US US14/777,577 patent/US20160295514A1/en not_active Abandoned
- 2014-01-17 JP JP2015506625A patent/JP6311701B2/ja not_active Expired - Fee Related
- 2014-01-17 WO PCT/JP2014/050766 patent/WO2014148077A1/ja active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11313370A (ja) * | 1998-04-28 | 1999-11-09 | Toshiba Corp | 移動パケット通信システムとそのデータ通信装置、基地局装置及び移動端末装置 |
JP2002528009A (ja) * | 1998-10-15 | 2002-08-27 | テレフオンアクチーボラゲット エル エム エリクソン(パブル) | 移動通信ネットワークにおける移動局用の可変スリープモード |
JP2005079895A (ja) * | 2003-08-29 | 2005-03-24 | Toshiba Corp | 情報端末 |
JP2010028168A (ja) * | 2008-07-15 | 2010-02-04 | Fuji Electric Systems Co Ltd | 無線通信ネットワークシステム、無線端末、無線通信方法、無線通信プログラム |
Also Published As
Publication number | Publication date |
---|---|
JP6311701B2 (ja) | 2018-04-18 |
US20160295514A1 (en) | 2016-10-06 |
JPWO2014148077A1 (ja) | 2017-02-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6316963B2 (ja) | 垂直アクセス領域と予測される垂直移動モデルとを備える支援データを生成するための装置および方法 | |
JP6363239B2 (ja) | パワー効率のよいコンテキストアウェア推定のための適応型センササンプリング | |
JP6641498B2 (ja) | 状況認識触覚アラート | |
US20160321564A1 (en) | Operational parameter value learning device, operational parameter value learning method, and controller for learning device | |
CN110602399A (zh) | 摄像头升降障碍的处理方法、装置及移动终端 | |
US8666693B2 (en) | Low average velocity pedestrial motion identification | |
JP2018070301A (ja) | エレベータ用空調制御装置およびエレベータ用空調制御システム | |
CN113453122B (zh) | 佩戴检测方法、装置、设备及计算机可读存储介质 | |
US20200189617A1 (en) | Vehicle Control Device | |
WO2018230654A1 (ja) | インタラクション装置、インタラクション方法、およびプログラム | |
WO2013157332A1 (ja) | 行動識別装置、行動識別システム及び行動識別プログラム | |
US9756600B2 (en) | Information processing apparatus, information process method and program | |
CN111816178A (zh) | 语音设备的控制方法、装置和设备 | |
JP6311701B2 (ja) | 情報端末、行動推定方法、及びプログラム | |
JP6198188B2 (ja) | 移動管理システム、移動管理装置、およびユーザ端末 | |
KR101676176B1 (ko) | 사용자 행위를 인식하기 위한 센싱 방법 및 장치 | |
KR102301397B1 (ko) | 이동 단말의 대기전력을 제어하는 장치 및 방법 | |
JP4138820B2 (ja) | 携帯端末 | |
KR20200002097A (ko) | 배뇨에 관한 설문을 수행하는 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 | |
KR101625304B1 (ko) | 음향 정보에 기초한 사용자 다수 행위 인식 방법 | |
CN110134361B (zh) | 设备的音量调节方法、计算机设备及计算机可读存储介质 | |
JP2010078509A (ja) | 赤外線センサを用いた計測装置並びにキャリブレーション方法 | |
JP6123791B2 (ja) | 情報処理システム、サーバ、端末、情報処理方法及びプログラム | |
JP2021148723A (ja) | 歩行判別システム、モバイル装置、処理装置、およびコンピュータプログラム | |
WO2015098214A1 (ja) | 情報処理装置、情報処理方法およびプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14768439 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14777577 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2015506625 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14768439 Country of ref document: EP Kind code of ref document: A1 |