Estimation system and estimation method

Abstract

A position estimation system 1 includes: a first acquisition unit 11 for acquiring a plurality of items of radio wave information for learning, in which position information and access point information including information for identifying an access point and information indicating radio wave intensity from the access point are associated with each other; a determination unit 12 for determining whether or not each of the plurality of items of radio wave information for learning, acquired by the first acquisition unit 11, is radio wave information related to a permanent access point on the basis of the access point information; and a model creation unit 13 for creating a position estimation model for estimating position information on the basis of the access point information by using, as learning data, only the radio wave information for learning determined to be the radio wave information related to a permanent access point by the determination unit 12.

Description

Estimation system and estimation method

[0001] One aspect of the present invention relates to an estimation system and an estimation method.

[0002] Patent Document 1 discloses a location estimation model construction device that includes an information acquisition unit that acquires wireless LAN information consisting of received signal strength for each access point, and a location estimation model learning unit that uses a set of pairs of wireless LAN information associated with location information and the location information, and the wireless LAN information acquired by the information acquisition unit as learning data, to learn a location estimation model that estimates location information from wireless LAN information.

[0003] Japanese Patent Application Laid-Open No. 2023-129115

[0004] Here, in a system that estimates location based on wireless LAN information (received signal strength for each access point) as described above, a problem arises in that Wi-Fi temporarily present in the environment, such as smartphone tethering or a mobile Wi-Fi router, becomes noise, deteriorating the accuracy of location estimation.

[0005] One aspect of the present invention has been made in consideration of the above-described circumstances, and relates to an estimation system and an estimation method that can improve the accuracy of position estimation using information from a wireless LAN.

[0006] An estimation system according to one embodiment of the present invention includes a first acquisition unit that acquires multiple pieces of learning radio wave information linked to location information and access point information including information that identifies an access point and information indicating radio wave strength from the access point; a determination unit that determines, for each of the multiple pieces of learning radio wave information acquired by the first acquisition unit, based on the access point information, whether the information is radio wave information relating to a permanent access point; and a model creation unit that uses only the learning radio wave information determined by the determination unit to be radio wave information relating to a permanent access point as learning data to create a location estimation model that estimates location information based on the access point information.

[0007] In an estimation system according to one aspect of the present invention, when creating a location estimation model that estimates location information based on access point information, only the learning radio wave information determined to be related to a permanent access point is used as training data among multiple pieces of learning radio wave information linked to location information and access point information. This results in radio wave information related to non-permanent access points, i.e., access points with inconsistent location information, being excluded from the training data used to create the location estimation model. This allows only radio wave information related to access points with inconsistent location information to be learned to create a location estimation model, thereby enabling the creation of a location estimation model with high location estimation accuracy. As described above, the estimation system according to one aspect of the present invention can improve the accuracy of location estimation using wireless LAN information.

[0008] According to one aspect of the present invention, it is possible to improve the accuracy of position estimation in position estimation using information from a wireless LAN.

[0009] FIG. 1 is a diagram illustrating an overview of indoor position estimation based on radio wave information from an access point. FIG. 2 is a diagram schematically illustrating a system configuration of a position estimation system according to an embodiment. FIG. 3 is a block diagram illustrating a functional configuration of a processing server included in the position estimation system illustrated in FIG. 2. FIG. 4 is a table illustrating an example of learning radio wave information. FIG. 5 is a flowchart illustrating a learning data determination process executed by the position estimation system according to an embodiment. FIG. 6 is a flowchart illustrating a position estimation process executed by the position estimation system according to an embodiment. FIG. 7 is a diagram illustrating a hardware configuration of a processing server.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] First, an overview of indoor position estimation according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram illustrating an overview of indoor position estimation based on radio wave information from an access point. As shown in Fig. 1, in indoor position estimation according to this embodiment, "IV. Indoor position estimation" is performed after "I. Spatial data collection," "II. Space reconstruction," and "III. Radio wave environment estimation," which are prerequisites for the processing, are performed.

[0012] In "I. Spatial data collection," for example, a user (or a mobile robot, etc.) carrying a sensor such as a lidar or a camera and a terminal capable of measuring the radio wave environment moves through an indoor space, and data such as images of the indoor space and data on the radio wave environment (radio wave intensity, etc.) are collected.

[0013] In "II. Spatial Reconstruction," a highly accurate 3D map (environmental map) is constructed based on data such as images of indoor spaces using a technology such as SLAM (Simultaneous Localization and Mapping). SLAM is a technology that uses cameras, various sensors, encoders, etc. to estimate the vehicle's position and create an environmental map in parallel. A specific example of SLAM is Visual SLAM, which uses images captured by a camera.

[0014] In "III. Radio wave environment estimation," the constructed 3D map is linked to the data on the radio wave environment collected at the same time. Specifically, at least coordinates on the 3D map, information identifying the access point, and information indicating the radio wave intensity from the access point are linked. This allows the radio wave environment at each location to be reflected in the 3D map. In this embodiment, a position estimation model is created that takes such a 3D map into consideration.

[0015] In "IV. Indoor Position Estimation," the indoor position of a mobile communication terminal, such as a smartphone, is estimated from radio wave environment data acquired by the mobile communication terminal and the above-mentioned 3D map. In this embodiment, the data on the radio wave environment acquired by the smartphone or the like is input into a position estimation model, thereby performing position estimation taking the 3D map into consideration. Note that, in indoor position estimation, corrections using mobile spatial statistics or linkage with an outdoor map may be performed, particularly in congested situations.

[0016] Fig. 2 is a diagram schematically illustrating the system configuration of a position estimation system 1 according to an embodiment. As shown in Fig. 2, the position estimation system 1 (estimation system) includes a processing server 10, a radio wave environment measuring device 20, and a DB 30. Fig. 2 illustrates a flow of creating a position estimation model required for performing the indoor position estimation described above.

[0017] The radio wave environment measuring device 20 is a device that collects data on the radio wave environment (such as radio wave intensity) in "I. Spatial Data Collection" described above. The radio wave environment measuring device 20 measures (collects) at least data on the radio wave environment, and may also simultaneously acquire data such as images of indoor spaces. Various access points are considered as the access points related to the radio wave environment collected by the radio wave environment measuring device 20. Possible access points include, for example, a smartphone 40 in tethering, a temporarily located mobile Wi-Fi router 50, a permanently installed mobile Wi-Fi router 60, and a fixed router 70 (home router). The radio wave environment measuring device 20 transmits the collected data on the radio wave environment (radio wave information) to the processing server 10.

[0018] The processing server 10 extracts only radio wave information related to permanently installed access points from the multiple pieces of radio wave information acquired from the radio wave environment measuring device 20 and transmits the extracted information to the DB 30. The DB 30 stores the radio wave information related to the permanently installed access points. The processing server 10 uses only the radio wave information related to the permanently installed access points as training data to create a location estimation model that estimates location information based on the access point information. In other words, the processing server 10 creates a location estimation model based only on the information about the permanently installed access points. The processing server 10 then uses the created location estimation model to perform location estimation based on radio wave information acquired by a mobile communication terminal (not shown), such as a smartphone.

[0019] Fig. 3 is a block diagram showing the functional configuration of the processing server 10 included in the position estimation system 1 shown in Fig. 2. The functions of the processing server 10 will be described in detail below.

[0020] The processing server 10 includes a first acquisition unit 11 , a determination unit 12 , a model creation unit 13 , a second acquisition unit 14 , and a position estimation unit 15 .

[0021] The first acquisition unit 11 acquires multiple pieces of learning radio wave information, each piece of which is linked to location information and access point information including information identifying an access point and information indicating radio wave intensity from the access point. The first acquisition unit 11 acquires the learning radio wave information, for example, only from the radio wave environment measuring device 20. In this case, the radio wave environment measuring device 20 collects data such as images of indoor spaces corresponding to the location information in association with the access point information. Alternatively, the first acquisition unit 11 may acquire, for example, only the access point information in the learning radio wave information from the radio wave environment measuring device 20 and acquire data such as images of indoor spaces corresponding to the location information from another communication terminal (e.g., a mobile communication terminal such as a smartphone). Even when the pieces of information included in the learning radio wave information are acquired from different terminals in this way, the first acquisition unit 11 can acquire the learning radio wave information in which the location information and the access point information are linked by associating the pieces of information with each other using information such as time.

[0022] The location information is represented by data such as an image of an indoor space, and is converted into coordinates (X, Y, Z) in the indoor space according to a 3D map. Information identifying an access point is, for example, a service set identifier (SSID) that can uniquely identify the access point (wireless LAN). The information identifying the access point may also be a basic service set identifier (BSSID), i.e., a MAC address. When the radio wave environment measuring device 20 collects access point information, information on two or more access points (radio waves from two or more access points) may be collected simultaneously. In this case, the learning radio wave information associates the location information (X, Y, Z) with the access point information associated with SSID: 1 and the access point information associated with SSID: 2 (see FIG. 4 ). In the learning radio wave information shown in FIG. 4 , the location information (X, Y, Z) is associated with the access point information associated with SSID: 1 and the access point information associated with SSID: 2.

[0023] The determination unit 12 determines, for each of the plurality of pieces of learning radio wave information acquired by the first acquisition unit 11, whether or not the information is radio wave information relating to a permanent access point, based on the access point information.

[0024] When the information identifying an access point includes information related to a mobile communication terminal (e.g., a smartphone), the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point. For example, when the SSID includes a smartphone brand name or the like, the determination unit 12 determines that the wireless LAN indicated by the SSID is related to smartphone tethering and is in a temporary environment, and determines that the learning radio wave information related to the SSID is not radio wave information related to a permanent access point and excludes it from the learning data.

[0025] When the information identifying an access point includes information related to a mobile router, the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point. For example, when the SSID includes a model number of a mobile router sold by a telecommunications carrier (carrier), the determination unit 12 determines that the wireless LAN indicated by the SSID is related to a mobile router and is in a temporary environment, and determines that the learning radio wave information related to the SSID is not radio wave information related to a permanent access point and excludes it from the learning data.

[0026] When the information identifying an access point includes information related to a frequency band used only indoors, the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. For example, when the SSID includes information on W52 (5.2 GHz band) or W53 (5.3 GHz band) which are used only indoors, the determination unit 12 determines that the wireless LAN indicated by the SSID is used only indoors, determines that the learning radio wave information related to the SSID is radio wave information related to a permanent access point, and sets it as learning data.

[0027] When the information identifying an access point includes information indicating a pre-registered facility name, the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. The registered facility name here is, for example, the name of a facility in an indoor space.

[0028] When the information identifying an access point includes information related to a pre-registered home router, the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. Here, the home router is, for example, a fixed router installed corresponding to a facility in an indoor space. For example, when the SSID includes the name or manufacturer name of the fixed router, the determination unit 12 determines that the wireless LAN indicated by the SSID is for indoor use only, and determines that the learning radio wave information related to the SSID is radio wave information related to a permanent access point and sets it as learning data.

[0029] When the information identifying an access point appears a predetermined number of times or more in a predetermined period of time, the determination unit 12 determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. For example, the determination unit 12 determines that the learning radio wave information related to an SSID that has appeared a predetermined number of times or more in the most recent predetermined period of time is radio wave information related to a permanent access point, and determines it to be learning data.

[0030] The determining unit 12 determines that the learning radio wave information is related to a permanent access point and stores the learning radio wave information determined as learning data in the DB 30 .

[0031] The model creation unit 13 uses only the learning radio wave information determined by the determination unit 12 to be radio wave information related to permanent access points as learning data to create a location estimation model that estimates location information based on access point information. The model creation unit 13 acquires multiple pieces of learning radio wave information (learning radio wave information determined to be radio wave information related to permanent access points) by referring to the DB 30, and creates a location estimation model using the multiple pieces of learning radio wave information as learning data. For example, when using the learning radio wave information shown in FIG. 4 as learning data, the model creation unit 13 performs machine learning using the radio wave strengths of SSID: 1 and SSID: 2 as explanatory variables and the location information (X, Y, Z) as a target variable to create a location estimation model. As described above, a BSSID may be used instead of an SSID. Because the BSSID is likely to remain constant, it is advantageous as a learning target.

[0032] The second acquisition unit 14 acquires positioning radio wave information including access point information. The second acquisition unit 14 acquires, for example, data on the radio wave environment (positioning radio wave information) collected by a mobile communication terminal 90 (such as a smartphone) for which positioning is desired. The positioning radio wave information includes access point information including information identifying an access point and information indicating the radio wave intensity from the access point. The second acquisition unit 14 may acquire positioning radio wave information including information on a plurality of access points.

[0033] The location estimation unit 15 performs location estimation by inputting the access point information of the positioning radio wave information acquired by the second acquisition unit 14 into the location estimation model created by the model creation unit 13. The location estimation unit 15 may perform location positioning by inputting only access point information, among the multiple access point information of the positioning radio wave information, whose access point identification information (SSID) is for a predetermined location positioning, into the location positioning model. Here, the predetermined access point information for location positioning is, for example, access point information (access point information related to permanent access points) used as learning data when the location estimation model was created. The location estimation unit 15 may perform detailed location positioning by combining the coordinates (X, Y, Z) of the indoor space output from the location estimation model with the latitude and longitude of the building related to the indoor space.

[0034] Next, a learning data determination process executed by the position estimation system 1 will be described with reference to Fig. 5. The learning data determination process is a process for determining whether or not data is to be used as learning data in model creation. Fig. 5 is a flowchart showing the learning data determination process executed by the position estimation system 1 according to the embodiment.

[0035] 5, data on the radio wave environment (such as radio wave intensity) is collected (step S1) by, for example, the radio wave environment measuring device 20. The collected data on the radio wave environment (radio wave information) is recorded as a list of previously existing wireless LANs, including the SSIDs and MAC addresses of access points (step S2).

[0036] Next, based on the information transmitted from the radio wave environment measuring device 20, the processing server 10 acquires multiple pieces of learning radio wave information linked to location information and access point information, and performs the judgment processing of steps S3 to S8.

[0037] In step S3, the processing server 10 determines whether the SSID that identifies the access point includes the brand name of the mobile communication terminal (for example, a smartphone) or the like.

[0038] If it is determined in step S3 that the SSID does not include the radio wave information, the processing server 10 determines whether the SSID that identifies the access point includes the model number of a mobile router sold by a telecommunications carrier (step S4).If it is determined in step S4 that the SSID does not include the radio wave information, the processing server 10 determines that the radio wave information is related to a permanent access point (wireless LAN) (step S9).

[0039] On the other hand, if it is determined in step S3 or S4 that the SSID identifying the access point contains information related to a frequency band that is used exclusively indoors (W52 (5.2 GHz band) or W53 (5.3 GHz band)) (step S5). If it is determined in step S5 that the SSID contains information, it is determined that the radio wave information is related to a permanent access point (wireless LAN) (step S9).

[0040] If it is determined in step S5 that the SSID identifying the access point does not contain information indicating a pre-registered facility (store) name, it is determined (step S6) whether the SSID identifying the access point contains information indicating a pre-registered facility (store) name. If it is determined in step S6 that the SSID contains information, it is determined that the radio wave information is related to a permanent access point (wireless LAN) (step S9).

[0041] If it is determined in step S6 that the SSID identifying the access point does not include information indicating a name or manufacturer name commonly used for pre-registered fixed routers, it is determined (step S7).If it is determined in step S7 that the SSID does include information, it is determined that the radio wave information is related to a permanent access point (wireless LAN) (step S9).

[0042] If it is determined in step S7 that the SSID identifying the access point is not included, it is determined whether the SSID has appeared in each of the most recent several scans (step S8). If it is determined in step S8 that the SSID has appeared in each scan, it is determined that the radio wave information relates to a permanent access point (wireless LAN) (step S9). On the other hand, if it is determined in step S8 that the SSID has not appeared in each scan, it is determined that the radio wave information relates to a temporarily existing access point (wireless LAN) (step S10). This completes the learning data determination process. After only the radio wave information relating to permanent access points is extracted through this process, the radio wave information is used as learning data to create a location estimation model.

[0043] Next, the position estimation process executed by the position estimation system 1 will be described with reference to Fig. 6. The position estimation process is a process for estimating the position of a mobile communication terminal 90 (such as a smartphone) for which positioning is desired, using the created position estimation model. Fig. 6 is a flowchart showing the position estimation process executed by the position estimation system 1 according to the embodiment.

[0044] As shown in FIG. 6, the processing server 10 acquires data on the radio wave environment (radio wave information for positioning) from the mobile communication terminal 90 for which positioning is desired (step S101).

[0045] Next, from among the plurality of access point information in the positioning radio wave information, only access point information in which information identifying the access point (SSID) is for predetermined positioning is extracted (step S102).

[0046] The extracted access point information is then input to the position estimation model, thereby estimating the position of the mobile communication terminal 90 to be positioned (step S103). This completes the position estimation process.

[0047] Next, the effects of the position estimation system 1 according to this embodiment will be described.

[0048] The location estimation system 1 according to this embodiment includes a first acquisition unit 11 that acquires multiple pieces of learning radio wave information linked to location information and access point information including information for identifying an access point and information indicating radio wave intensity from the access point; a determination unit 12 that determines whether each of the multiple pieces of learning radio wave information acquired by the first acquisition unit 11 is radio wave information relating to a permanent access point based on the access point information; and a model creation unit 13 that uses only the learning radio wave information determined by the determination unit 12 to be radio wave information relating to a permanent access point as learning data to create a location estimation model that estimates location information based on the access point information.

[0049] In the position estimation system 1 according to the present embodiment, when creating a position estimation model that estimates position information based on access point information, only the training radio wave information determined to be radio wave information related to a permanent access point is used as training data among multiple pieces of training radio wave information that are linked to position information and access point information. This results in radio wave information related to non-permanent access points, i.e., access points whose position information is not constant, being excluded from the training data used to create the position estimation model. This allows only radio wave information related to access points whose position information is constant to be learned to create a position estimation model, thereby enabling the creation of a position estimation model with high position estimation accuracy. As described above, the position estimation system 1 according to the present embodiment can improve the accuracy of position estimation using wireless LAN information.

[0050] The position estimation system may further include a second acquisition unit 14 that acquires positioning radio wave information including access point information, and a position estimation unit 15 that performs position estimation by inputting the access point information of the positioning radio wave information acquired by the second acquisition unit 14 into a position estimation model. With this configuration, position estimation can be performed with high accuracy using the above-mentioned position estimation model.

[0051] When the information identifying an access point includes information related to a mobile communication terminal (such as a smartphone), the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point. With this configuration, information related to non-permanent access points such as a smartphone that performs tethering is excluded from the learning data, thereby improving the estimation accuracy of the location estimation model.

[0052] When the information for identifying an access point includes information related to a mobile router, the determination unit 12 may determine that the learning radio wave information related to the information for identifying the access point is not radio wave information related to a permanent access point. With this configuration, information about non-permanently installed mobile routers is excluded from the learning data, thereby improving the estimation accuracy of the location estimation model.

[0053] When the information identifying an access point includes information related to a frequency band that is used exclusively indoors, the determination unit 12 may determine that the training radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. With this configuration, the information related to the permanent access point can be appropriately used as training data, thereby improving the estimation accuracy of the location estimation model.

[0054] When the information identifying an access point includes information indicating a pre-registered facility name, the determination unit 12 may determine that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point. With this configuration, information related to permanent access points can be registered in advance and the information can be appropriately used as learning data, thereby improving the estimation accuracy of the location estimation model.

[0055] When the information for identifying an access point includes information related to a pre-registered home router, the determination unit 12 may determine that the learning radio wave information related to the information for identifying the access point is radio wave information related to a permanent access point. With this configuration, information related to a permanent access point is registered in advance, and the information can be appropriately used as learning data, thereby improving the estimation accuracy of the location estimation model.

[0056] The determination unit 12 may determine that the learning radio wave information related to the information identifying an access point is radio wave information related to a permanent access point when the information identifying the access point appears a predetermined number of times or more in determinations within a predetermined period. With this configuration, information related to an access point that appears frequently, i.e., that is likely to be permanent, can be appropriately used as learning data, thereby improving the estimation accuracy of the location estimation model.

[0057] The second acquisition unit 14 may acquire positioning radio wave information including information on a plurality of access points, and the position estimation unit 15 may perform position estimation by inputting only access point information, among the plurality of access point information in the positioning radio wave information, in which information identifying the access point is for predetermined position positioning, into the position estimation model. With this configuration, it is possible to perform position estimation with higher accuracy by using, for example, information related to permanent access points only.

[0058] Next, the hardware configuration of the processing server 10 included in the above-described location estimation system will be described with reference to Fig. 7. The processing server 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0059] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of each apparatus may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0060] Each function in each device is realized by loading specified software (programs) onto hardware such as processor 1001 and memory 1002, causing processor 1001 to perform calculations and control communication via communication device 1004 and reading and / or writing of data in memory 1002 and storage 1003.

[0061] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, a register, etc. For example, the control function of the first acquisition unit 11, etc. may be realized by the processor 1001.

[0062] The processor 1001 also reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above embodiments.

[0063] For example, the control functions of the first acquisition unit 11 and the like may be realized by a control program stored in the memory 1002 and running on the processor 1001, and similar functions may be realized for other functional blocks. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The program may be transmitted from a network via a telecommunications line.

[0064] The memory 1002 is a computer-readable recording medium and may be composed of at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to one embodiment of the present invention.

[0065] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including memory 1002 and / or storage 1003.

[0066] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0067] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0068] Furthermore, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.

[0069] Each device may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.

[0070] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0071] Each aspect / embodiment described herein may be applied to systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA, GSM, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth, or other suitable systems and / or next generation systems enhanced thereon.

[0072] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described herein may be rearranged unless it is consistent. For example, the methods described herein present elements of various steps in an example order, and are not limited to the particular order presented.

[0073] Input and output information may be stored in a specific location (for example, memory) or managed in a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0074] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0075] The aspects / embodiments described herein may be used alone or in combination, or may be switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0076] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0077] Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0078] The information, signals, etc. described herein may be represented using any one of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0079] It should be noted that terms explained in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0080] Furthermore, the information, parameters, etc. described in this specification may be expressed as absolute values, as relative values ​​from a predetermined value, or as corresponding other information.

[0081] A communications terminal may also be referred to by those skilled in the art as a mobile communications terminal, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communications device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0082] As used herein, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0083] When designations such as "first," "second," etc. are used herein, any reference to such elements does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0084] To the extent that the terms "include," "including," and variations thereof are used herein or in the claims, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used herein or in the claims, is not intended to be an exclusive or.

[0085] In this specification, a plurality of devices is also included unless the context or the technology clearly indicates that only one device exists.

[0086] Throughout this disclosure, the plural is intended to be included unless the singular is clearly indicated by the context.

[0087] Finally, various exemplary embodiments included in the present disclosure are described below in [E1] to [E10].

[0088] [E1] An estimation system comprising: a first acquisition unit that acquires multiple pieces of learning radio wave information linked to location information and access point information including information that identifies an access point and information indicating radio wave intensity from the access point; a determination unit that determines, for each of the multiple pieces of learning radio wave information acquired by the first acquisition unit, based on the access point information, whether the information is radio wave information related to a permanent access point; and a model creation unit that creates a location estimation model that estimates location information based on the access point information, using only the learning radio wave information determined by the determination unit to be radio wave information related to the permanent access point as learning data.

[0089] [E2] The estimation system according to [E1], further comprising: a second acquisition unit that acquires positioning radio wave information including the access point information; and a position estimation unit that performs position estimation by inputting the access point information of the positioning radio wave information acquired by the second acquisition unit into the position estimation model.

[0090] [E3] An estimation system according to [E1] or [E2], wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point when the information identifying the access point includes information related to a mobile communication terminal.

[0091] [E4] An estimation system described in any one of [E1] to [E3], wherein, when the information identifying the access point includes information related to a mobile router, the determination unit determines that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point.

[0092] [E5] An estimation system according to any one of [E1] to [E4], wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information related to a frequency band that is used exclusively indoors.

[0093] [E6] An estimation system described in any one of [E1] to [E5], wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information indicating a pre-registered facility name.

[0094] [E7] An estimation system described in any one of [E1] to [E6], wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information related to a pre-registered home router.

[0095] [E8] An estimation system described in any one of [E1] to [E7], wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point appears a predetermined number of times or more in determinations within a predetermined period.

[0096] [E9] The estimation system described in [E2], wherein the second acquisition unit acquires the positioning radio wave information including information on a plurality of the access points, and the position estimation unit performs position estimation by inputting only the access point information, of the plurality of access point information in the positioning radio wave information, in which information identifying the access point is for a predetermined position positioning, into the position estimation model.

[0097] [E10] An estimation method executed by an estimation system, comprising: acquiring a plurality of pieces of learning radio wave information linked to location information and access point information including information for identifying an access point and information indicating radio wave intensity from the access point; determining, for each of the plurality of pieces of learning radio wave information, based on the access point information, whether the piece of learning radio wave information is radio wave information relating to a permanent access point; and using only the learning radio wave information determined to be radio wave information relating to the permanent access point as learning data, creating a location estimation model that estimates location information based on the access point information.

[0098] 1...position estimation system, 11...first acquisition unit, 12...determination unit, 13...model creation unit, 14...second acquisition unit, 15...position estimation unit.

Claims

1. An estimation system comprising: a first acquisition unit that acquires multiple pieces of learning radio wave information linked to location information and access point information including information that identifies an access point and information indicating the radio wave strength from the access point; a determination unit that determines whether each of the multiple pieces of learning radio wave information acquired by the first acquisition unit is radio wave information related to a permanent access point based on the access point information; and a model creation unit that uses only the learning radio wave information determined by the determination unit to be radio wave information related to the permanent access point as learning data to create a location estimation model that estimates location information based on the access point information.

2. The estimation system of claim 1, further comprising: a second acquisition unit that acquires positioning radio wave information including the access point information; and a position estimation unit that performs position estimation by inputting the access point information of the positioning radio wave information acquired by the second acquisition unit into the position estimation model.

3. An estimation system as described in claim 1 or 2, wherein, when the information identifying the access point includes information related to a mobile communication terminal, the determination unit determines that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point.

4. An estimation system as described in claim 1 or 2, wherein, when the information identifying the access point includes information related to a mobile router, the determination unit determines that the learning radio wave information related to the information identifying the access point is not radio wave information related to a permanent access point.

5. An estimation system as described in claim 1 or 2, wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information related to a frequency band that is used exclusively indoors.

6. An estimation system as described in claim 1 or 2, wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information indicating a pre-registered facility name.

7. An estimation system as described in claim 1 or 2, wherein the determination unit determines that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point when the information identifying the access point includes information related to a pre-registered home router.

8. An estimation system as described in claim 1 or 2, wherein the judgment unit judges that the learning radio wave information related to the information identifying the access point is radio wave information related to a permanent access point if the information identifying the access point appears a predetermined number of times or more in judgments within a predetermined period.

9. The estimation system of claim 2, wherein the second acquisition unit acquires the positioning radio wave information including a plurality of pieces of access point information, and the position estimation unit performs position estimation by inputting into the position estimation model only the access point information, of the plurality of access point information in the positioning radio wave information, where the information identifying the access point is for a predetermined position positioning purpose.

10. An estimation method executed by an estimation system, comprising: acquiring a plurality of pieces of learning radio wave information linked to location information and access point information including information for identifying an access point and information indicating radio wave strength from the access point; determining, for each of the plurality of pieces of learning radio wave information, based on the access point information, whether the information is radio wave information relating to a permanent access point; and using only the learning radio wave information determined to be radio wave information relating to the permanent access point as learning data, creating a location estimation model that estimates location information based on the access point information.

Images