Terminal management device and terminal management method

Abstract

This terminal management device comprises: an acquisition unit that acquires one or more pieces of probe request information respectively based on one or more probe requests that are transmitted from one or more user terminals positioned in a first area; a classification unit that classifies, for each of the acquired one or more pieces of probe request information, to which of a plurality of types the user terminal that transmitted the corresponding probe request belongs; and a first determination unit that determines an active rate, which is the ratio of user terminals in a screen-on state among the one or more user terminals, on the basis of the acquisition timings of the one or more pieces of probe request information acquired by the acquisition unit, the classification result of the classification unit, and the number of the one or more user terminals.

Description

Terminal management device and terminal management method

[0001] The present invention relates to a terminal management device and a terminal management method.

[0002] It has been known for some time that the number of people in an area can be determined using Wi-Fi® probe requests transmitted from terminals such as smartphones. For example, Patent Document 1 discloses a waiting time estimation system that estimates the waiting time for an attraction based on congestion detection information, which includes the MAC address that identifies each mobile terminal detected by a congestion detection terminal.

[0003] Japanese Patent Publication No. 2017-37477

[0004] With the widespread adoption of mobile devices such as smartphones, there is a growing need to understand the activity rate, which is the percentage of mobile devices in an active state among multiple mobile devices within a specific area. However, the waiting time estimation system described in Patent Document 1 has the problem of being unable to determine whether a mobile device is in an active state or a sleep state.

[0005] This invention was made to solve the above-mentioned problems and aims to understand the activity rate of user terminals within a specific area.

[0006] A terminal management device according to a preferred embodiment of the present invention includes: an acquisition unit that acquires one or more probe request pieces of information based on one or more probe requests transmitted from one or more user terminals located in a first area; a classification unit that classifies, for each of the acquired one or more probe request pieces of information, which of a plurality of types the user terminal that transmitted the corresponding probe request belongs to; and a first determination unit that determines the active rate, which is the percentage of user terminals that are in a screen-on state among the one or more user terminals, based on the acquisition timing of the one or more probe request pieces of information acquired by the acquisition unit, the classification result of the classification unit, and the number of the one or more user terminals.

[0007] A terminal management method according to a preferred embodiment of the present invention is performed by a computer and acquires one or more probe request pieces of information based on one or more probe requests transmitted from one or more user terminals located in a first area; for each of the acquired probe request pieces of information, it classifies which of a plurality of types the user terminal that transmitted the corresponding probe request belongs to; and based on the timing of acquisition of the acquired probe request pieces of information, the classification result, and the number of the one or more user terminals, it determines the active rate, which is the percentage of the one or more user terminals that are in a screen-on state.

[0008] According to the terminal management device and terminal management method of the present invention, it is possible to grasp the activity rate of user terminals within a specific area.

[0009] This figure shows the overall configuration of a terminal management system including a terminal management device according to the first embodiment. This is a block diagram showing an example configuration of the terminal device in Figure 1. This figure shows the relationship between the number of probe request transmissions and the probe interval when the screen of a first type terminal device is on. This figure shows the relationship between the number of probe request transmissions and the probe interval when the screen of a first type terminal device is off. This is a block diagram showing an example configuration of the wireless signal detection device in Figure 1. This is a block diagram showing an example configuration of the human detection device in Figure 1. This is a block diagram showing an example configuration of the terminal management device in Figure 1. This is a schematic diagram showing an example of a neural network model applied to the third learning model according to the first embodiment. This figure shows an example of a repetition pattern of screen on and screen off during a first period for three terminal devices classified as type 1. This is a diagram of Figure 9 with the timing of probe request transmissions added. This is a diagram of the probe request transmission timings of the three terminal devices in Figure 10 superimposed. This is a schematic diagram of a specific area when test terminal devices are placed inside and outside the specific area as a preliminary preparation. This figure shows an example of a first signal strength database according to the first embodiment. This figure shows an example of the display of the active rate. This is a flowchart showing an example of the operation of the processing device in Figure 7. This is a flowchart showing an example of the operation of the subroutine in Figure 15. This is a block diagram showing an example configuration of a terminal management device according to the second embodiment. This is a flowchart showing an example of the operation of the processing device in Figure 17. This is a schematic diagram to explain tripoint positioning. This is a schematic diagram to explain dupoint positioning.

[0010] 1. The configuration of the terminal management device according to the first embodiment of the present invention will be described below with reference to Figures 1 to 16.

[0011] 1.1. Configuration of the First Embodiment 1.1.1. Configuration Figure 1 of the terminal management system is a diagram showing the overall configuration of the terminal management system 1, including the terminal management device 40 according to the first embodiment. The terminal management system 1 includes a wireless signal detection device 20, a human detection device 30, a terminal management device 40, and a communication network NET. Figure 1 shows three wireless signal detection devices 20[1], 20[2], and 20[3] and two human detection devices 30[1] and 30[2].

[0012] The terminal management system 1 determines the activity rate of terminal devices 10 located within a specific area based on the number of terminal devices 10 located within that area and probe requests transmitted from the terminal devices 10 located within that area, and notifies the administrator of the determined activity rate. The specific area includes public spaces such as commercial facilities, concert halls, and conference rooms, as well as private spaces such as offices and classrooms. The specific area is an example of the first area. The activity rate is the percentage of terminal devices 10 located within the specific area that are in a screen-on state.

[0013] Terminal device 10 includes n terminal devices 10[1], 10[2], ..., 10[k], ..., 10[n], where n is any natural number and k is any natural number smaller than n. In this embodiment, the configurations of terminal devices 10[1] to 10[n] are identical to each other. Note that terminal device 10 may include terminal devices with different configurations. Terminal device 10 is located within or outside a specific area.

[0014] A user using terminal device 10[1] is user U[1], a user using terminal device 10[2] is user U[2], a user using terminal device 10[k] is user U[k], and a user using terminal device 10[n] is user U[n]. When referring to an unspecified number of users or all users, user is also written as user U.

[0015] In Figure 1, there is a one-to-one correspondence between n terminal devices 10 and n users U, but a single user may possess multiple terminal devices. Also, Figure 1 assumes that all terminal devices 10 are active, i.e., powered on, but each terminal device 10[k] may be inactive, i.e., powered off. Furthermore, users U can move between a specific area and an area outside that specific area.

[0016] The terminal device 10 includes personal computers, tablet devices, smartphones, smartwatches, etc.

[0017] The communication network NET is a telecommunication line such as a mobile communication network managed by a telecommunications carrier that provides communication services. The communication network NET includes one or both of a wired communication network and a wireless communication network. For example, the communication network NET may be connected via the Internet to another network (not shown) managed by another telecommunications carrier.

[0018] In the terminal management system 1, the radio signal detection devices 20[1], 20[2], 20[3], the person detection devices 30[1], 30[2], and the terminal management device 40 are communicatively connected to each other via the communication network NET. Note that the radio signal detection devices 20[1], 20[2], 20[3], and the person detection devices 30[1] and 30[2] may be directly connected to the terminal management device 40 without going through the communication network NET.

[0019] The radio signal detection device 20 is a device that detects a probe request transmitted from the terminal device 10[k]. The configurations of the three radio signal detection devices 20[1], 20[2], and 20[3] are the same as each other. In the present embodiment, the three radio signal detection devices 20[1], 20[2], and 20[3] are arranged at different positions from each other.

[0020] In the present embodiment, three radio signal detection devices 20[1], 20[2], and 20[3] are exemplified, but this number is merely an example, and the terminal management system 1 can include any number of two or more radio signal detection devices 20. Note that when there is only one radio signal detection device 20, it is difficult to determine the position of the terminal device 10. The radio signal detection device 20 may include detection devices whose configurations are not identical to each other.

[0021] 1.1.2. Configuration of Terminal Device FIG. 2 is a block diagram showing a configuration example of the terminal device 10[k] in FIG. 1. As shown in FIG. 2, the terminal device 10[k] includes a processing device 11, a storage device 12, a communication device 13, a display device 14, and an input device 15. Each element included in the terminal device 10[1] is mutually connected by a single bus or a plurality of buses for communicating information. The terminal device 10[k] is an example of a user terminal.

[0022] The processing unit 11 is a processor that controls the entire terminal device 10[k], and is configured, for example, using one or more chips. The processing unit 11 is configured using a central processing unit (CPU) that includes, for example, interfaces with peripheral devices, arithmetic units, registers, etc. Some or all of the functions of the processing unit 11 may be implemented by hardware such as a DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), FPGA (Field Programmable Gate Array). The processing unit 11 executes various processes in parallel or sequentially.

[0023] The storage device 12 is a recording medium that can be read from and written to by the processing device 11. The storage device 12 includes, for example, non-volatile memory and volatile memory. Non-volatile memory includes, for example, ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory), and EEPROM (Electrically Erasable Programmable Read Only Memory). Volatile memory includes, for example, RAM (Random Access Memory).

[0024] The storage device 12 stores multiple programs, including the control program PR1, which is executed by the processing device 11. The storage device 12 also functions as a work area for the processing device 11. The control program PR1 is a program that controls the entire processing device 11.

[0025] The communication device 13 is hardware serving as a transmission / reception device for communicating with other devices. The communication device 13 is also called, for example, a network device, a network controller, a network card, a communication module, or the like. The communication device 13 may include a connector for wired connection, and may include an interface circuit corresponding to the connector. Further, the communication device 13 may include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products compliant with wired LAN, IEEE 1394, and USB. Further, examples of the wireless communication interface include products compliant with Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like.

[0026] The display device 14 is a device that displays image and character information. The display device 14 displays various images based on control by the processing device 11. For example, various display panels such as a liquid crystal panel and an organic EL (Electro Luminescence) panel are suitably used as the display device 14.

[0027] The input device 15 receives an operation from a user U[1]. For example, the input device 15 is configured to include a pointing device such as a keyboard, a touch pad, a touch panel, and a mouse. Here, when the input device 15 is configured to include a touch panel, it may also serve as the display device 14.

[0028] The processing device 11 functions as an accepting unit 111, a transmitting unit 112, an acquiring unit 113, and a display control unit 114 by, for example, reading and executing the control program PR1 from the storage device 12.

[0029] The accepting unit 111 accepts an operation of a user U[k] on the input device 15. The operation by the user U[k] is, for example, a tap operation on a touch panel that is the input device 15.

[0030] The transmitting unit 112 transmits a probe request to an access point (not shown) at a predetermined timing via the communication device 13.

[0031] A probe request is a signal transmitted from the terminal device 10[k] to search for access points in its vicinity before the terminal device 10[k] connects to a Wi-Fi® access point. When a nearby access point receives a probe request from the terminal device 10[k], it transmits a probe response to the terminal device 10[k]. The terminal device 10[k] transmits probe requests at predetermined intervals until a Wi-Fi® connection is established with an access point.

[0032] According to the inventor's findings, the probe request transmission interval, which is the time interval at which probe requests are sent from the terminal device 10[k], differs depending on the model of the terminal device 10[k]. The model can also be referred to as the type. The trend in the probe request transmission interval can be broadly classified according to the manufacturer of the terminal device 10[k] and the type of OS (Operating System) incorporated into the terminal device 10[k]. According to the inventor's research, commercially available smartphones can be broadly classified into three types, Type 1, Type 2, and Type 3, based on the trend in the probe request transmission interval. The probe request transmission interval will also be referred to as the probe interval below.

[0033] The trend in probe spacing will be explained below with reference to Figures 3 and 4. In the following explanation, the first type terminal device 10[k], the second type terminal device 10[k], and the third type terminal device 10[k] may be referred to as type A, type S, and type G, respectively. In this embodiment, the terminal device 10[k] has been broadly classified into three types for explanation, but the number of types used to classify the terminal device 10[k] is not limited to three.

[0034] Figure 3 shows the relationship between the transmission of a probe request and the probe interval when the screen of the first type terminal device 10[k] is on. "Screen on" means that the display device 14 of the terminal device 10[k] is lit. Generally, when the display device 14 of the terminal device 10[k] is lit, it can be said that it is in an active state.

[0035] In Figure 3, the horizontal axis of the graph indicates the number of probe requests since the start of one set of measurements. The vertical axis of the graph indicates the probe interval. Multiple probe requests are sent in one set. The circular plots show the results of the first set of measurements, and the square plots show the results of the second set of measurements. For example, in the first set of measurements, a total of 19 probe requests were sent. In the first set of measurements, when the first probe request is sent, the probe interval is 5 seconds. This means that the next probe request was sent 5 seconds after the previous probe request. For example, when the second probe request is sent, the probe interval is 6 seconds. For example, when the twelfth probe request is sent, the probe interval is 60 seconds.

[0036] As shown in Figure 3, in both the first and second measurement sets, when the screen is turned on, the probe interval is approximately 5 seconds at the beginning of sending probe requests, but there is a tendency for the probe interval to gradually increase with each probe request sent.

[0037] Figure 4 shows the relationship between the transmission of probe requests and the probe interval when the screen of the first type terminal device 10[k] is off. "Screen off" means that the display device 14 of the terminal device 10[k] is turned off. Generally, the state in which the display device 14 of the terminal device 10[k] is turned off can be said to be a sleep state.

[0038] In sleep mode, power consumption in the terminal device 10[k] is reduced, and user U[k] errors, unintended malfunctions, etc., are prevented. When the input device 15 is operated by user U[k] in sleep mode, the display device 14 lights up, and the terminal device 10[k] wakes up from sleep mode. In addition, if a phone call is received or a push notification is received while in sleep mode, the terminal device 10[k] will also wake up from sleep mode to active mode.

[0039] In Figure 4, as in Figure 3, the horizontal axis of the graph indicates the number of probe requests since the start of one set of measurements. The vertical axis of the graph indicates the probe interval. The circular plots show the results of the first set of measurements, and the square plots show the results of the second set of measurements. For example, in the first set of measurements, a total of 10 probe requests were sent. In the first set of measurements, when the first probe request was sent, the probe interval was 100 seconds. When the second probe request was sent, the probe interval was 3 seconds. When the third probe request was sent, the probe interval was 3 seconds. When the fourth probe request was sent, the probe interval was 270 seconds.

[0040] As shown in Figure 4, in both the first and second measurement sets, when the screen is off, there is a tendency for the probe interval to alternate irregularly between a few seconds and 100 seconds or more.

[0041] Therefore, as can be seen from Figures 3 and 4, even with the same terminal device 10[k], the trend in the probe interval pattern when the screen is on and the trend in the probe interval pattern when the screen is off are different. In other words, the timing of sending probe requests differs between the sleep state and the active state of the terminal device 10[k].

[0042] Although not shown in the diagram, the probe interval of the S-type device when the screen is on tends to change regularly. For example, the probe interval of the S-type device when the screen is on changes to 15 seconds the first time, 30 seconds the second time, and 60 seconds the third time. The probe interval of the S-type device when the screen is off is different from the probe interval of the same type device when the screen is on. Also, the probe interval of the S-type device when the screen is off tends to be longer than the probe interval of the A-type device when the screen is off.

[0043] Furthermore, although a detailed explanation will be omitted, the probe spacing of the G-type device when the screen is on is different from the probe spacing of the A-type device and the S-type device when the screen is on. The probe spacing of the G-type device when the screen is off is also different from the probe spacing of the A-type device when the screen is off.

[0044] Referring again to Figure 2, the acquisition unit 113 acquires a probe response from the access point via the communication device 13. The probe response is the access point's response to the probe request. If the ESSID (Extended Service Set Identifier) ​​included in the probe request matches its own ESSID, the access point sends the probe response to the terminal device 10[k].

[0045] The display control unit 114 displays various information on the display device 14 based on the various information acquired by the acquisition unit 113. When the screen is off, if the reception unit 111 receives a tap operation on the input device 15 from user U[k], the display control unit 114 changes the state of the display device 14 from the screen off state to the screen on state. When the screen is on, if the reception unit 111 does not receive a tap operation on the input device 15 from user U[k] for a certain period of time, the display control unit 114 changes the state of the display device 14 from the screen on state to the screen off state.

[0046] 1.1.3. Configuration of the Wireless Signal Detection Device Figure 5 is a block diagram showing an example configuration of the wireless signal detection device 20 shown in Figure 1. As shown in Figure 5, the wireless signal detection device 20 comprises a processing unit 21, a storage device 22, a communication device 23, and a receiving device 24. Each element of the wireless signal detection device 20 is interconnected by one or more buses for communicating information.

[0047] The processing unit 21 is a processor that controls the entire wireless signal detection device 20, and is configured, for example, using one or more chips. The processing unit 21 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and registers. Some or all of the functions of the processing unit 21 may be implemented by hardware such as a DSP, ASIC, PLD, FPGA, etc. The processing unit 21 executes various processes in parallel or sequentially.

[0048] The storage device 22 is a recording medium that can be read from and written to by the processing device 21. The storage device 22 includes, for example, non-volatile memory and volatile memory. The non-volatile memory is, for example, ROM, EPROM, and EEPROM. The volatile memory is, for example, RAM.

[0049] The storage device 22 stores multiple programs, including the control program PR2, which is executed by the processing device 21. The storage device 22 also functions as a work area for the processing device 21.

[0050] The communication device 23 is hardware that acts as a transmitting and receiving device for communicating with other devices. The communication device 23 is also called, for example, a network device, network controller, network card, communication module, etc. The communication device 23 may be equipped with a connector for wired connection and an interface circuit corresponding to the connector. The communication device 23 may also be equipped with a wireless communication interface. Examples of connectors and interface circuits for wired connection include products compliant with wired LAN, IEEE 1394, and USB. Examples of wireless communication interfaces include products compliant with Wi-Fi® and Bluetooth®.

[0051] The receiving device 24 receives a modulated wave including a probe request. The modulated wave can also be called a radio signal. The receiving device 24 demodulates the received modulated wave into an analog signal, then converts it into a digital signal and outputs it to the processing device 21 as a probe request signal. The receiving device 24 measures the received intensity of the received modulated wave and outputs the measured value to the processing device 21.

[0052] The processing unit 21 functions as an acquisition unit 211, a hashing unit 212, and a transmission unit 213 by, for example, reading and executing the control program PR2 from the storage device 22.

[0053] The acquisition unit 211 acquires a probe request signal from the receiving device 24. The probe request includes the MAC (Media Access Control) address of the terminal device 10[k] that sends the probe request, among one or more terminal devices 10.

[0054] The hashing unit 212 generates a hash value from the MAC address included in the probe request obtained by the acquisition unit 211 according to a certain calculation procedure. The hashing unit 212 replaces the MAC address with the generated hash value. Therefore, the probe request information does not include the MAC address of terminal device 10[k], but includes information in which the MAC address of terminal device 10[k] has been hashed. MAC addresses include fixed MAC addresses and random MAC addresses, but the hashing unit 212 uniformly replaces them with a hash value regardless of whether they are fixed MAC addresses or random MAC addresses.

[0055] The transmitting unit 213 transmits probe request information, in which the MAC address has been replaced with a hash value, to the terminal management device 40, along with RSSI (Received Signal Strength Indication) information including the measured value of the received signal strength. Note that hashing the MAC address protects the privacy of user U.

[0056] 1.1.4. Human Detection Device Configuration Figure 6 is a block diagram showing an example configuration of the human detection device 30 shown in Figure 1. As shown in Figure 6, the human detection device 30 comprises a processing unit 31, a storage device 32, a communication device 33, a light-emitting device 34, and a light-receiving device 35. Each element of the human detection device 30 is interconnected by one or more buses for communicating information.

[0057] The processing unit 31 is a processor that controls the entire human detection device 30, and is configured, for example, using one or more chips. The processing unit 31 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and registers. Some or all of the functions of the processing unit 31 may be implemented by hardware such as a DSP, ASIC, PLD, FPGA, etc. The processing unit 31 executes various processes in parallel or sequentially.

[0058] The storage device 32 is a recording medium that can be read from and written to by the processing device 31. The storage device 32 includes, for example, non-volatile memory and volatile memory. The non-volatile memory is, for example, ROM, EPROM, and EEPROM. The volatile memory is, for example, RAM.

[0059] The storage device 32 stores multiple programs, including the control program PR3, which is executed by the processing unit 31. The storage device 32 also functions as a work area for the processing unit 31. The control program PR3 is a program that controls the entire processing unit 31.

[0060] The communication device 33 is hardware that acts as a transmitting and receiving device for communicating with other devices. The communication device 33 is also called, for example, a network device, network controller, network card, communication module, etc. The communication device 33 may be equipped with a connector for wired connection and an interface circuit corresponding to the connector. The communication device 33 may also be equipped with a wireless communication interface. Examples of connectors and interface circuits for wired connection include products compliant with wired LAN, IEEE 1394, and USB. Examples of wireless communication interfaces include products compliant with Wi-Fi® and Bluetooth®.

[0061] The light-emitting device 34 includes a light-emitting device that irradiates infrared light of a specific wavelength to the outside of the device, and a drive circuit that drives the light-emitting device. An infrared LED (Light Emitting Diode) or a laser diode is used as the light-emitting device in the light-emitting device 34.

[0062] The light-receiving device 35 includes a light-receiving device that detects infrared light reflected by an object and a receiving circuit that demodulates the received signal. A photodiode, phototransistor, or the like can be used as the light-receiving device in the light-receiving device 35. The light-receiving device 35 converts the infrared light into an electrical signal using the light-receiving device, and the receiving circuit demodulates the received signal for output.

[0063] The processing unit 31 functions as a device that performs the following processes, for example, by reading and executing the control program PR3 from the storage device 32.

[0064] The processing unit 31 generates a drive signal for the light-emitting device and transmits it to the light-emitting device 34. The processing unit 31 acquires the demodulated received signal from the light-receiving device 35. The processing unit 31 transmits the acquired received signal as passage information to the terminal management device 40 via the communication device 33. The passage information is information that changes over time in response to the passage of user U.

[0065] In this embodiment, the case described is one in which a detection device is applied in which the reflected infrared light emitted by the light-emitting device 34 is detected by the light-receiving device 35. However, the human detection device 30 may be a device that detects infrared radiation emitted by a person. In the case of a device that detects infrared radiation emitted by a person, a light-emitting device is not required for the human detection device.

[0066] 1.1.5. Diagram 7 of the terminal management device configuration is a block diagram showing an example configuration of the terminal management device 40 shown in Figure 1. As shown in Figure 7, the terminal management device 40 comprises a processing unit 41, a storage device 42, a communication device 43, and a display device 44. Each element of the terminal management device 40 is interconnected by one or more buses for communicating information.

[0067] The processing unit 41 is a processor that controls the entire terminal management device 40, and is configured, for example, using one or more chips. The processing unit 41 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and registers. Some or all of the functions of the processing unit 41 may be implemented by hardware such as a DSP, ASIC, PLD, FPGA, etc. The processing unit 41 executes various processes in parallel or sequentially.

[0068] The storage device 42 is a recording medium that can be read from and written to by the processing device 41. The storage device 42 includes, for example, non-volatile memory and volatile memory. The non-volatile memory is, for example, ROM, EPROM, and EEPROM. The volatile memory is, for example, RAM.

[0069] The storage device 42 stores multiple programs, including the control program PR4 for execution by the processing device 41, the first signal strength database DB1, the third learning model LM3, and the first learning model LM1. The storage device 42 also functions as a work area for the processing device 41. The third learning model LM3 and the first learning model LM1 will be described below. The third learning model LM3 and the first learning model LM1 are generated in the learning unit 418, which will be described later.

[0070] The third learning model LM3 is a model that, upon inputting acquired probe request information, classifies which of three predetermined categories the terminal device 10[k] that sent the corresponding probe request belongs to.

[0071] The probe request information includes the length of the probe request frame, i.e., the packet length of the probe request. The packet length of the probe request tends to differ for each of the three types of terminal devices 10[k], type 1, type 2, and type 3, with the exception of some models. Therefore, the three types of terminal devices 10[k] can be classified to some extent by the packet length of the probe request.

[0072] Furthermore, the probe request information includes information about the corresponding radio frequency, manufacturer-specific information for each terminal device 10[k], etc. Therefore, the three types of terminal devices 10[k] can be classified more accurately based on the signal length of the probe request, information about the corresponding radio frequency, manufacturer-specific information, etc.

[0073] For example, the third learning model LM3 uses a machine learning model capable of multi-class classification. This multi-class classification machine learning model is trained using methods such as neural network models, logistic regression, and support vector machines. Below, we will explain a machine learning method using a neural network model as an example.

[0074] Figure 8 is a schematic diagram showing an example of a neural network model 90 applied to the third learning model LM3 according to the first embodiment.

[0075] The neural network model 90 receives probe request information as input data.

[0076] The neural network model 90 is composed of convolutional neural networks, recurrent neural networks, and the like.

[0077] The neural network model 90 outputs output data that includes the type of terminal device 10[k].

[0078] When training data is input to the neural network model 90, the neural network model 90 learns the correlation between the input data, which is the probe request information for learning, and the output data, which is the type of terminal device 10[k]. The input data and output data that constitute the training data are also referred to as explanatory variables and target variables, respectively.

[0079] More specifically, the probe request information, which is an explanatory variable, is input to the neural network model 90 as input data.

[0080] An evaluation function is used to compare the output data output as an inference result from the neural network model 90, i.e., the type of terminal device 10[k], with the output data that constitutes the training data, i.e., the correct label of the type of terminal device 10[k]. The weights associated with each synapse are repeatedly adjusted so that the value of the evaluation function becomes small. This adjustment of the weights associated with each synapse is called backpropagation. In this way, a third learning model LM3 is trained to perform multi-class classification in which probe request information is classified into three types included in the correct label, i.e., type 1, type 2, and type 3.

[0081] When predetermined learning termination conditions are met, machine learning is terminated, and the neural network model 90 at that point is stored in the memory device 42 as the trained third learning model LM3. The predetermined learning termination conditions include, for example, the number of iterations of the above series of machine learning processes reaching a predetermined number, or the value of the evaluation function becoming smaller than an acceptable value.

[0082] The method for generating the first learning model LM1 according to the first embodiment will be described below with reference to Figures 9 to 11. The first learning model LM1 is a model that has already learned the relationship between the activity rate of the learning terminal device, the acquisition timing of the learning probe request information for each type, and the number of learning terminal devices for each type. The first learning model LM1 is prepared for each type.

[0083] The first learning model LM1 for Type A devices outputs the number of Type A devices based on the active rate and the timing of acquiring probe request information transmitted from Type A devices. The first learning model LM1 for Type S devices outputs the number of Type S devices based on the active rate and the timing of acquiring probe request information transmitted from Type S devices. The first learning model LM1 for Type G devices outputs the number of Type G devices based on the active rate and the timing of acquiring probe request information transmitted from Type G devices.

[0084] The first learning model LM1, like the third learning model LM3, is trained using machine learning models such as neural network models, logistic regression, and support vector machines.

[0085] Figure 9 shows an example of the repeated screen-on and screen-off patterns during the first period T1 for three terminal devices classified as Type 1. In Figure 9, the three terminal devices are indicated as "Terminal Device #1", "Terminal Device #2", and "Terminal Device #3".

[0086] As mentioned above, even with the same terminal device, the probe interval when the screen is on and when the screen is off differ from each other. Therefore, it is preferable to consider both the probe interval when the screen is on and the probe interval when the screen is off when generating the first learning model LM1.

[0087] Therefore, in this embodiment, during the first period T1, the first learning model LM1 is trained using a pattern in which three terminal devices alternately turn their screens on and off at different timings. When the screen is off, the terminal device 10[k] is in a sleep state. When the terminal device 10[k] is in the sleep state, if there is an operation by user U[k], an incoming call, a push notification, etc., the terminal device 10[k] wakes up from the sleep state and turns its screen on. Note that the repeating pattern shown in Figure 9 is merely an example, and the repetition does not always occur at the timings shown in Figure 9. The first period T1 is, for example, 10 minutes.

[0088] Since the three terminal devices repeatedly turn their screens on and off at different times, the activity rate changes over time during the first period T1. For example, during the period from time t0 to time t1, terminal device #1 is in the screen-on state, while terminal devices #2 and #3 are in the screen-off state. Therefore, during the period from time t0 to time t1, one of the three terminal devices is in the active state, resulting in an activity rate of 33.3%.

[0089] During the period from time t1 to time t2, terminal devices #1 and #2 were in the screen-on state, while terminal device #3 was in the screen-off state. Therefore, during the period from time t1 to time t2, two out of the three terminal devices were active, resulting in an activity rate of 66.7%.

[0090] Similarly, the activity rate for the period from time t2 to time t3 is 33.3%, the activity rate for the period from time t3 to time t4 is 66.7%, the activity rate for the period from time t4 to time t5 is 33.3%, and the activity rate for the period from time t5 to time t6 is 0%. The activity rate for the period from time t6 to time t7 is 33.3%, the activity rate for the period from time t7 to time t8 is 0%, the activity rate for the period from time t8 to time t9 is 33.3%, and the activity rate for the period from time t9 to time t10 is 0%.

[0091] In other words, the periods with an activity rate of 0% are from time t5 to time t6, from time t7 to time t8, and from time t9 to time t10. The periods with an activity rate of 33.3% are from time t0 to time t1, from time t2 to time t3, from time t4 to time t5, from time t6 to time t7, and from time t8 to time t9. The periods with an activity rate of 66.7% are from time t1 to time t2 and from time t3 to time t4.

[0092] The period with an activity rate of 0% accounts for 60% of the first period T1, the period with an activity rate of 33.3% accounts for 30% of the first period T1, and the period with an activity rate of 66.7% accounts for 10% of the first period T1. Therefore, the average activity rate for the first period T1 is 40%.

[0093] Figure 10 is a diagram of Figure 9 with the probe request transmission timing added. The probe request transmission timing is indicated by an oval mark. As mentioned above, even for terminal devices of the same type, the probe request transmission timing may differ depending on the manufacturer of the terminal device. Also, the interval for sending probe requests when the screen is on is shorter than the interval for sending probe requests when the screen is off.

[0094] Figure 11 is a diagram showing the overlaid probe request transmission timings of the three terminal devices in Figure 10. The probe request transmission timings in the first period T1 shown in Figure 11 correspond to the learning log when the activity rate of the three terminal devices classified as Type 1 is 40%. For the sake of simplicity, the explanation uses the transmission timing of probe requests transmitted by each of the three terminal devices, but in reality, the timing used as the learning log is the acquisition timing of the probe request information acquired by the acquisition unit 411 described later in the first period T1. The acquisition timing of the probe request information is substantially equal to the transmission timing of the probe request.

[0095] The learning unit 418 creates 1100 training logs, for example, combining the number of terminal devices classified as Type 1, i.e., Type A devices, from 1 to 100, and the active rates of 0%, 10%, 20%, ..., 100%. The learning unit 418 uses these 1100 training logs, each associated with the number of terminal devices and the active rate, to machine-learn the relationship between the number of Type A devices, the active rate, and the training logs. The machine learning model is trained using methods such as a neural network model or logistic regression. Below, a machine learning method using a neural network model will be described as an example.

[0096] In this embodiment, 1100 learning logs are used, but the number of learning logs is not particularly limited. The number of Type A devices does not need to be limited to 1 to 100, and can be determined appropriately according to the size of the specific area. The active rate does not need to be limited to 10% increments, and may be less than or greater than 10%. In addition, two or more learning logs with the same number of terminal devices and active rate conditions may be prepared.

[0097] Referring again to Figure 7, the communication device 43 is hardware that acts as a transmitting and receiving device for communicating with other devices. The communication device 43 is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 43 may be equipped with a connector for wired connection and an interface circuit corresponding to the connector. The communication device 43 may also be equipped with a wireless communication interface. Examples of connectors and interface circuits for wired connection include products compliant with wired LAN, IEEE 1394, and USB. Examples of wireless communication interfaces include products compliant with Wi-Fi® and Bluetooth®.

[0098] The display device 44 is a device that displays images and text information. The display device 44 displays various images based on control by the processing device 41. For example, various display panels such as liquid crystal panels and organic EL panels are preferably used as the display device 44.

[0099] The processing unit 41 functions as an acquisition unit 411, an analysis unit 412, a classification unit 413, a position determination unit 414, a first determination unit 415, a second determination unit 416, a display control unit 417, and a learning unit 418, for example, by reading and executing the control program PR4 from the storage device 42. Furthermore, the first determination unit 415 functions as an extraction unit 4151, a number determination unit 4152, and a difference determination unit 4153.

[0100] The acquisition unit 411 acquires probe request information and signal strength information from the wireless signal detection device 20 via the communication device 43. The probe request information is information based on one or more probe requests transmitted from one or more terminal devices 10 located in a specific area. As mentioned above, the MAC addresses included in the probe request information are hashed. The timing for acquiring probe request information for probe requests transmitted from terminal devices 10[k] in a sleep state is different from the timing for acquiring probe request information for probe requests transmitted from terminal devices 10[k] in an active state (not in a sleep state).

[0101] Furthermore, the acquisition unit 411 acquires passage information from the person detection device 30.

[0102] The analysis unit 412 determines the number of users U located in a specific area SA based on the acquired passage information. The human detection devices 30[1] and 30[2] are arranged at an appropriate distance from each other in the horizontal direction. When a user U passes in front of the human detection devices 30[1] and 30[2], a time difference occurs between the change in passage information acquired from human detection device 30[1] and the change in passage information acquired from human detection device 30[2]. Therefore, the analysis unit 412 can determine the direction in which the user U is moving from the acquired passage information.

[0103] The analysis unit 412 determines the number of people entering a specific service area (SA) at a predetermined time and the number of people leaving the specific service area (SA) at a predetermined time. If the specific service area (SA) is one floor of a commercial facility, the analysis unit 412 can determine the number of people located in the specific service area at a predetermined time by setting the initial value of the number of people in the specific service area (SA) at opening time in the morning to zero and increasing or decreasing the number of people entering and leaving at predetermined time intervals.

[0104] If 10 people enter a specific service area (SA) during a specified time period, and 5 people leave the SA during the same time period, then the number of people in the SA during that time period will have increased by 5. If the number of users U located in the SA during the previous period was 25, then the number of users U located in the SA during the current period will be determined to be 30.

[0105] The classification unit 413 classifies, for each of the one or more acquired probe request pieces of information, which of the multiple types the terminal device 10[k] that sent the corresponding probe request belongs to, that is, whether it belongs to type 1, type 2, or type 3. The classification unit 413 inputs the acquired probe request information into the third learning model LM3 to classify which of the predetermined types 1, type 2, or type 3 the terminal device 10[k] that sent the corresponding probe request belongs to.

[0106] The position determination unit 414 determines whether the classified terminal device 10 is located in a specific area SA based on the information stored in the first signal strength database DB1 and the RSSI information included in the probe request information acquired by the acquisition unit 411. The method for determining whether each of the one or more terminal devices 10 is located in a specific area SA will be described below with reference to Figure 12.

[0107] Figure 12 is a schematic diagram of the designated area SA when test terminal devices TT are placed inside and outside the designated area SA as a preliminary preparation. The test terminal devices TT are devices that transmit probe requests. As shown in Figure 12, nine measurement areas are set up inside and outside the designated area SA. The nine measurement areas are referred to as the first measurement area MA1 to the ninth measurement area MA9. The first measurement area MA1 to the fourth measurement area MA4 are areas inside the designated area SA, and the fifth measurement area MA5 to the ninth measurement area MA9 are areas outside the designated area SA.

[0108] Within the designated area SA, three wireless signal detection devices 20[1], 20[2], and 20[3] are arranged at different locations. Preferably, the three wireless signal detection devices 20[1], 20[2], and 20[3] are arranged on the ceiling of a building, for example. In the example shown in Figure 12, the three wireless signal detection devices 20[1], 20[2], and 20[3] are arranged within the designated area SA, but they may also be arranged outside the designated area SA, as long as they are within range of being able to receive probe requests from terminal devices 10 located at any location within the designated area SA.

[0109] First, the tester places the test terminal device TT in the center of the first measurement area MA1, and the first measurement is performed. In the first measurement, the probe request transmitted from the test terminal device TT placed in the center of the first measurement area MA1 is received by three wireless signal detection devices 20[1], 20[2], and 20[3], respectively.

[0110] The received signal strength obtained by receiving the probe request signal with the wireless signal detection device 20[1], the received signal strength obtained by receiving the probe request with the wireless signal detection device 20[2], and the received signal strength obtained by receiving the probe request with the wireless signal detection device 20[3] are associated with the first measurement area MA1 and stored in the storage device 42 as the first signal strength database DB1.

[0111] Next, the tester places the test terminal device TT in the center of the second measurement area MA2, and the second measurement is performed. In the second measurement, the probe request transmitted from the test terminal device TT placed in the center of the second measurement area MA2 is received by three wireless signal detection devices 20[1], 20[2], and 20[3], respectively.

[0112] The received signal strength obtained by receiving the probe request with the wireless signal detection device 20[1], the received signal strength obtained by receiving the probe request with the wireless signal detection device 20[2], and the received signal strength obtained by receiving the probe request with the wireless signal detection device 20[3] are associated with the second measurement area MA2 and stored in the storage device 42 as the first signal strength database DB1.

[0113] Similarly, the third measurement, performed with the test terminal device TT positioned in the third measurement area MA3, is followed by the ninth measurement, performed with the test terminal device TT positioned in the ninth measurement area MA9. The three received signal strengths obtained in the mth measurement are associated with the mth measurement area MAm and stored in the memory device 42. Here, m is an integer from 3 to 9. The received signal strength obtained by receiving the probe request transmitted from the test terminal device TT with the wireless signal detection device 20 is hereinafter also referred to as the "reference signal strength".

[0114] Figure 12 shows how user Uin, moving from the outside to a specific area SA, and user Uout, moving from the specific area SA to the outside, pass through gate GA. Human detection devices 30[1] and 30[2] are arranged at gate GA. Since human detection devices 30[1] and 30[2] are arranged at a predetermined distance from each other in the horizontal direction, when a user passes in front of human detection devices 30[1] and 30[2], a time difference occurs between the time ta when human detection device 30[1] detects user U and the time tb when human detection device 30[2] detects user U. If time ta is later than time tb, the detected person is user Uin, moving from the outside to a specific area SA; if time ta is earlier than time tb, the detected person is user Uout, moving from the specific area SA to the outside.

[0115] Figure 13 shows an example of a first signal strength database DB1 according to the first embodiment. The first signal strength database DB1 stores the measurement results of the reference signal strength in association with the measurement area MA. The reference signal strength includes a first reference signal strength obtained by receiving the radio signal transmitted from the test terminal device TT with the radio signal detection device 20[1], a second reference signal strength obtained by receiving it with the radio signal detection device 20[2], and a third reference signal strength obtained by receiving it with the radio signal detection device 20[3].

[0116] In this example, measurements were performed with the test terminal device TT positioned in the center of each measurement area MA. However, the test terminal device TT does not necessarily have to be positioned in the center of each individual area. Also, in this example, measurements were performed at one location in each individual area. However, measurements may be performed at multiple locations within each individual area.

[0117] The position determination unit 414 determines which of the first measurement area MA1 to the ninth measurement area MA9 the terminal device that sent the probe request is closest to, based on information showing the relationship between the reference signal strength and the measurement area MA where the test terminal device TT is located, and the measurement signal strength. If the terminal device that sent the probe request is closest to any of the first measurement area MA1 to the fourth measurement area MA4, the position determination unit 414 determines that the terminal device is located in the specific area SA. On the other hand, if the terminal device that sent the probe request information acquisition timing request is closest to any of the fifth measurement area MA5 to the ninth measurement area MA9, the position determination unit 414 determines that the terminal device is not located in the specific area SA.

[0118] The measured signal strength is the three received signal strengths obtained by receiving the wireless signals transmitted from one or more terminal devices 10 using three wireless signal detection devices 20. The three received signal strengths may be corrected for each type, taking into account the error in the received signal strength for each type. The classification unit 413 excludes terminal devices that are determined not to be located in a specific area SA from subsequent processing for determining the active rate.

[0119] The closest measurement area to the terminal device that sent the probe request is determined, for example, as follows: The first reference signal strength, second reference signal strength, and third reference signal strength obtained by placing the test terminal device TT in the first measurement area MA1 are denoted as Pref_a1, Pref_b1, and Pref_c1, respectively. The first measurement signal strength, second measurement signal strength, and third measurement signal strength of the terminal device 10[k] are denoted as Pma, Pmb, and Pmc, respectively. Q1 is the sum of the squares of the differences between the first reference signal strength Pref_a1 and the first measurement signal strength Pma, the squares of the differences between the second reference signal strength Pref_b1 and the second measurement signal strength Pmb, and the squares of the differences between the third reference signal strength Pref_c1 and the third measurement signal strength Pmc. That is, the sum of the squares of the differences Q1 is expressed by the following equation (1).

[0120] Q1 = (Pref_a1 - Pma) 2 +(Pref_b1-Pmb) 2 +(Pref_c1 - Pmc) 2...(1)

[0121] Let a first reference signal strength, a second reference signal strength, and a third reference signal strength obtained by arranging the test terminal device TT in a second measurement area MA2 be Pref_a2, Pref_b2, and Pref_c2, respectively. Let Q2 be the sum of the square of the difference between the first reference signal strength Pref_a2 and the first measurement signal strength Pma, the square of the difference between the second reference signal strength Pref_b2 and the second measurement signal strength Pmb, and the square of the difference between the third reference signal strength Pref_c2 and the third measurement signal strength Pmc. That is, the sum of squared differences Q2 is expressed by the following formula (2).

[0122] Q2 = (Pref_a2 - Pma) 2 + (Pref_b2 - Pmb) 2 + (Pref_c2 - Pmc) 2                                  ...(2)

[0123] Similarly, for the third measurement area MA3 to the ninth measurement area MA9, the sums of squared differences Q3 to Q9 are calculated. That is, the sums of squared differences Q3 and Q9 are expressed by the following formulas (3) and (4), respectively.

[0124] Q3 = (Pref_a3 - Pma) 2 + (Pref_b3 - Pmb) 2 + (Pref_c3 - Pmc) 2                                  ...(3)      ...    Q9 = (Pref_a9 - Pma) 2 + (Pref_b9 - Pmb) 2 + (Pref_c9 - Pmc) 2                                  ...(4)

[0125] A position determination unit 414 calculates the sums of squared differences Q1 to Q9, and determines that the terminal device 10[k] is located in the measurement area MAx corresponding to the minimum sum of squared differences Qx among the sums of squared differences Q1 to Q9.

[0126] Referring again to Figure 7, the first determination unit 415 determines the active rate, which is the percentage of terminal devices 10 that are in a screen-on state among the terminal devices 10, based on the acquisition timing of one or more probe request information acquired by the acquisition unit 411, the classification result of the classification unit 413, and the number of one or more terminal devices 10.

[0127] The first determination unit 415 comprises an extraction unit 4151, a unit number determination unit 4152, and a difference determination unit 4153.

[0128] Based on the classification results of the classification unit 413, the extraction unit 4151 extracts the acquisition timing of one or more probe request information acquired by the acquisition unit 411 for each classified type, and outputs the acquisition timing of probe request information for each type.

[0129] The unit number determination unit 4152 determines the number of terminal devices 10 for each type by inputting the activity rate of the terminal devices 10 and the acquisition timing of the extracted probe request information for each type into the first learning model LM1, which is prepared for each type. As mentioned above, the first learning model LM1 is a model that has learned the relationship between the activity rate of the learning terminal devices, the acquisition timing of the learning probe request information for each type, and the number of learning terminal devices for each type.

[0130] The difference determination unit 4153 determines the difference between the total number of terminal devices 10 for each type determined by the number determination unit 4152 and the number of one or more terminal devices 10. The number determination unit 4152 determines multiple numbers of terminal devices 10 for each type by changing the active rate of the terminal devices 10. The difference determination unit 4153 determines multiple differences in accordance with the change in the active rate of the terminal devices 10 by the number determination unit 4152.

[0131] More specifically, the unit number determination unit 4152 determines the first total value S1 by inputting the second active rate Ra2, which is the active rate of the terminal devices 10, and the timing for acquiring probe request information for each type of terminal device 10 to the first learning model LM1. The first total value S1 is the sum of the number of terminal devices 10 for each type. In this embodiment, the first total value S1 is the sum of the number output from the first learning model LM1 for type A devices, the number output from the first learning model LM1 for type S devices, and the number output from the first learning model LM1 for type G devices.

[0132] Furthermore, the previously determined active rate is used for the second active rate Ra2. In the initial state where the previously determined active rate does not exist, the initial value of the second active rate Ra2 is set to, for example, 50%. Note that the initial value of the second active rate Ra2 is not limited to 50%.

[0133] The difference determination unit 4153 determines the difference between the first total value S1 and the number of terminal devices 10 (NT) as the first difference value D1. If the first total value S1 is less than the number of terminal devices 10 (NT), that is, if the first difference value D1 is negative, the number determination unit 4152 determines the second total value S2, which is the sum of the number of terminal devices 10 for each type, by inputting a third active rate Ra3 lower than the second active rate Ra2 and the timing for acquiring probe request information for each type of terminal device 10 to the first learning model LM1.

[0134] The difference determination unit 4153 determines the difference between the second total value S2 and the number of terminal devices 10 (one or more) as the second difference value D2. The second difference value D2 is expressed by the following equation (5).

[0135] D2=S2-NT...(5)

[0136] The first determination unit 415 determines the second active rate Ra2 to be the active rate Ra0 of one or more terminal devices 10 if the first total value S1 is closer to the number of terminal devices 10 NT (one or more) than the second total value S2. Here, the fact that the first total value S1 is closer to the number of terminal devices 10 NT (one or more) than the second total value S2 is equivalent to the second difference value D2 being larger than the first difference value D1, i.e., |D1| < |D2|.

[0137] On the other hand, if the first total value S1 is greater than the number NT of terminal devices 10 (one or more), that is, if the first difference value D1 is positive, the number determination unit 4152 inputs a fourth active rate Ra4, which is higher than the second active rate Ra2, and the timing for acquiring probe request information for each type of terminal device 10 to the first learning model LM1, thereby determining a third total value S3, which is the sum of the number of terminal devices 10 for each type.

[0138] The difference determination unit 4153 determines the difference between the third total value S3 and the number NT of one or more terminal devices 10 as the third difference value D3. The third difference value D3 is expressed by the following equation (6).

[0139] D3=S3-NT...(6)

[0140] The first determination unit 415 determines the second active rate Ra2 to be the active rate Ra0 of one or more terminal devices 10 if the first total value S1 is closer to the number of terminal devices 10 NT (one or more) than the third total value S3. Here, the fact that the first total value S1 is closer to the number of terminal devices 10 NT (one or more) than the third total value S3 is equivalent to the fact that the magnitude of the third difference value D3 is greater than the magnitude of the first difference value D1, i.e., |D1| < |D3|.

[0141] Looking at a single terminal device, the probe interval when the screen is on is shorter than the probe interval when the screen is off. In other words, the frequency of acquiring probe request information when the screen is on is higher than the frequency of acquiring probe request information when the screen is off. Therefore, if the number of terminal devices 10 is constant, an increase in the activity rate will increase the frequency of acquiring probe request information. Here, under the condition that the timing of acquiring probe request information is constant, increasing the activity rate will decrease the number of terminal devices 10.

[0142] Therefore, if the first total value S1 is less than the number of terminal devices 10 (NT), the number determination unit 4152 changes the active rate in a direction that increases the first total value S1. In other words, in this case, the number determination unit 4152 decreases the active rate. Consequently, the second total value S2 becomes greater than the first total value S1. If the second total value S2 is closer to the number of terminal devices 10 (NT) than the first total value S1, there is room to further decrease the active rate in order to bring the total value closer to the number of terminal devices 10 (NT). Conversely, if the first total value S1 is closer to the number of terminal devices 10 (NT) than the second total value S2, then the second total value S2 exceeds the number of terminal devices 10 (NT).

[0143] Therefore, in this case, the first determination unit 415 determines the second active rate Ra2 to be the active rate of one or more terminal devices 10.

[0144] On the other hand, if the first total value S1 is greater than the number of terminal devices 10 (NT), the number determination unit 4152 changes the active rate in a direction that decreases the first total value S1. In other words, in this case, the number determination unit 4152 increases the active rate. Therefore, the second total value S2 becomes smaller than the first total value S1. If the second total value S2 is closer to the number of terminal devices 10 (NT) than the first total value S1, there is room to further increase the active rate in order to bring the total value closer to the number of terminal devices 10 (NT). Conversely, if the first total value S1 is closer to the number of terminal devices 10 (NT) than the second total value S2, then the second total value S2 is less than the number of terminal devices 10 (NT).

[0145] Therefore, in this case, the first determination unit 415 determines the second active rate Ra2 to be the active rate of one or more terminal devices 10.

[0146] The second decision unit 416 determines the number NT of one or more terminal devices 10 based on the number of users U located in a specific area SA.

[0147] The number of users U located in a specific area SA is determined by the analysis unit 412 based on passage information output from a person detection device 30 installed at the entrance and exit of the specific area SA, which detects people passing through the entrance and exit. In this example, if the specific area SA is a single floor, the entrance and exit include the elevator hall, stairs, escalator entrance, and escalator exit.

[0148] The human detection device 30 distinguishes and detects people moving from the outside to a specific area SA and people moving from the specific area SA to the outside. Non-contact human detection devices 30 can include, for example, infrared sensors, ultrasonic sensors, radar sensors, LiDAR (Light Detection and Ranging), video cameras, and acoustic sensors. Contact-type human detection devices 30 can include, for example, pressure sensors and turnstile gates.

[0149] Infrared sensors can detect the direction of movement of a passing person by arranging at least two sensors horizontally at appropriate intervals. Video cameras can detect the direction of movement of a person by tracking their movements using video analysis software. Video analysis can utilize technologies such as facial recognition and motion detection algorithms. Acoustic sensors can detect the direction of movement of a person, for example, by using echolocation technology. Pressure sensors can detect a person's walking and movement direction by being embedded in the floor.

[0150] In this embodiment, the case in which multiple infrared sensors are used as the human detection device 30 will be described as an example. Note that the human detection device 30 is not limited to the example sensors. Furthermore, several types of sensors may be combined. Combining several types of sensors improves the accuracy of human detection.

[0151] The second determination unit 416 determines a correction coefficient α as the ratio of the number of terminal devices to the number of people located in the specific area SA by referring to information that records the ownership status of terminal devices of people who have visited the specific area SA in the past. The correction coefficient α may be constant, or it may be determined by referring to information limited to the same day of the week as the present, information limited to the same time period as the present, etc.

[0152] The display control unit 417 displays the active rate of one or more terminal devices 10 on the display device 44. Figure 14 shows an example of the active rate display. As shown in Figure 14, in addition to the active rate Ra, the estimated number of devices, the number of users U located in the specific area SA at the time of the previous measurement: "previous number", the number of people entering the specific area SA: "inflow number", the number of people leaving the specific area SA: "outflow number", and the number of users U located in the specific area SA at the time of the current measurement: "current number". Note that the display shown in Figure 14 may also display the number of terminal devices 10 for each type.

[0153] The learning unit 418 generates the first learning model LM1 and the third learning model LM3. Note that the terminal management device 40 does not necessarily have to include the learning unit 418. The first learning model LM1 and the third learning model LM3 may be learned offline.

[0154] 1.2. Operation of the terminal management device according to the first embodiment 1.2.1. Operation of the processing device 41 Figure 15 is a flowchart illustrating an example of the operation of the processing device 41 in Figure 7. The operation of the processing device 41 will be described below with reference to Figure 15. The routine in Figure 15 is started, for example, when the processing device 41 is started up, and is executed at regular intervals.

[0155] In step S11, the processing unit 41 functions as an acquisition unit 411 to acquire probe request information from the wireless signal detection device 20.

[0156] In step S12, the processing unit 41 functions as an acquisition unit 411 to acquire passage information from the person detection device 30.

[0157] In step S13, the processing unit 41 functions as a classification unit 413 and classifies the terminal devices 10 that sent the probe request into three types based on the probe request information. More specifically, the processing unit 41 inputs the acquired probe request information into the third learning model LM3 and classifies which of the three types the terminal device 10[k] that sent the corresponding probe request belongs to.

[0158] In step S14, the processing unit 41 determines the number NT of terminal devices 10 located in the specific area SA based on the passage information. More specifically, the processing unit 41 determines the number of users U located in the specific area SA based on the passage information, and then determines the number NT of terminal devices 10 located in the specific area SA by multiplying the determined number of users U by a correction coefficient α.

[0159] In step S15, the processing unit 41 functions as a first determination unit 415 and determines the active rate based on the timing of acquiring probe request information, the classification result, and the number NT of terminal devices located in a specific area SA. The detailed processing in step S15 will be described later with reference to Figure 16.

[0160] In step S16, the processing unit 41 functions as a display control unit 417 to display the active rate Ra on the display device 44, and then terminates this routine.

[0161] 1.2.2. Operation of Processing Unit 41 (Subroutine Operation) Figure 16 is a flowchart showing an example of the operation of the subroutine in Figure 15. The operation of the subroutine in step S15 will be explained below with reference to Figure 16.

[0162] In step S151, the processing unit 41 functions as an extraction unit 4151 and, based on the classification results of the classification unit 413, extracts the acquisition timing of the probe request information acquired by the acquisition unit 411 for each classified type, thereby outputting the acquisition timing of the probe request information for each type.

[0163] In step S152, the processing unit 41, functioning as a unit number determination unit 4152, inputs the active rate Ra of the terminal devices 10 and the timing for acquiring probe request information for each type to the first learning model LM1, thereby determining the number of terminal devices 10 for each type.

[0164] In step S153, the processing unit 41 functions as a difference determination unit 4153 to determine the difference between the total number of terminal devices 10 for each type and the number of terminal devices 10 in a specific area SA.

[0165] In step S154, the processing unit 41 functions as a unit number determination unit 4152 and determines a number of terminal devices 10 for each type by changing the active rate Ra of the terminal devices 10.

[0166] In step S155, the processing unit 41 functions as a difference determination unit 4153 and determines multiple differences in accordance with the change in the active rate Ra of the terminal device 10 by the number determination unit 4152.

[0167] In step S156, the processing unit 41 functions as the first determination unit 415 and determines the active rate of the terminal device 10 corresponding to the smallest difference among the multiple differences determined by the difference determination unit 4153 as the active rate of the terminal device 10 in the specific area SA, and then terminates this subroutine.

[0168] 1.3. Effects of the First Embodiment As described above, the terminal management device 40 according to the first embodiment comprises an acquisition unit 411, a classification unit 413, and a first determination unit 415. The acquisition unit 411 acquires one or more probe request pieces of information based on one or more probe requests transmitted from one or more terminal devices 10 located in a specific area. The classification unit 413 classifies, for each of the acquired one or more probe request pieces of information, which of the three types the terminal device 10 [k] that transmitted the corresponding probe request belongs to. The first determination unit 415 determines the active rate, which is the percentage of terminal devices 10 that are in a screen-on state among the one or more terminal devices 10, based on the acquisition timing of the one or more probe request pieces of information acquired by the acquisition unit 411, the classification result of the classification unit 413, and the number of one or more terminal devices 10.

[0169] According to this embodiment, the activity rate of terminal devices 10 within a specific service area (SA) can be determined. Therefore, in areas where smartphone operation while walking is restricted, if the activity rate exceeds a threshold, a notification can be issued stating that using a smartphone while walking is dangerous. Furthermore, by understanding the activity rate for each area, services tailored to each area can be provided.

[0170] Furthermore, the first determination unit 415 includes an extraction unit 4151, a number determination unit 4152, and a difference determination unit 4153. The extraction unit 4151 outputs the acquisition timing of probe request information for each type by extracting the acquisition timing of one or more probe request information acquired by the acquisition unit 411 for each classified type, based on the classification result of the classification unit 413. The number determination unit 4152 determines the number of terminal devices 10 for each type by inputting the activity rate of the terminal devices 10 and the extracted acquisition timing of probe request information for each type into the first learning model LM1 prepared for each type. The first learning model LM1 is a model that has learned the relationship between the activity rate of the learning terminal devices, the acquisition timing when learning probe request information for each type is acquired, and the number of learning terminal devices for each type.

[0171] The difference determination unit 4153 determines the difference between the total number of terminal devices of each type determined by the number determination unit 4152 and the number of one or more terminal devices. The number determination unit 4152 determines multiple numbers of terminal devices 10 of each type by changing the active rate of the terminal devices 10. The difference determination unit 4153 determines multiple differences in accordance with the change in the active rate of the terminal devices 10 by the number determination unit 4152. The first determination unit 415 determines the active rate of the terminal device 10 corresponding to the smallest difference among the multiple differences determined by the difference determination unit 4153 to be the active rate of one or more terminal devices 10.

[0172] According to this embodiment, the active rate of one or more terminal devices 10 in a specific area can be determined by determining the active rate such that the difference between the total number of terminal devices of each type, estimated based on the active rate and the timing of acquiring probe request information, and the number of one or more terminal devices 10 is minimized.

[0173] Furthermore, the unit number determination unit 4152 determines the first total value S1 by inputting the second active rate Ra2, which is the active rate of the terminal devices 10, and the timing for acquiring probe request information for each type of terminal device 10, into the first learning model LM1. The first total value S1 is the sum of the number of terminal devices 10 for each type. The difference determination unit 4153 determines the difference between the first total value S1 and the number NT of one or more terminal devices 10 as the first difference value D1. If the first total value S1 is less than the number of one or more terminal devices 10, the unit number determination unit 4152 determines the second total value S2, which is the sum of the number of terminal devices 10 for each type, by inputting the third active rate Ra3, which is lower than the second active rate Ra2, and the timing for acquiring probe request information for each type of terminal device 10, into the first learning model LM1.

[0174] The difference determination unit 4153 determines the difference between the second total value S2 and the number of terminal devices 10 (one or more) as the second difference value D2. The first determination unit 415 determines the second active rate Ra2 to be the active rate Ra0 of one or more terminal devices 10 if the first total value S1 is closer to the number of terminal devices 10 NT (one or more) than the second total value S2.

[0175] On the other hand, if the first total value S1 is greater than the number of terminal devices 10 (NT) of one or more devices, the number determination unit 4152 determines the third total value S3, which is the sum of the number of terminal devices 10 for each type, by inputting to the first learning model LM1 a fourth active rate Ra4 that is higher than the second active rate Ra2 and the timing for acquiring probe request information for each type of terminal device 10. The difference determination unit 4153 determines the difference between the third total value S3 and the number of terminal devices 10 (NT) of one or more devices as the third difference value D3. If the first total value S1 is closer to the number of terminal devices 10 (NT) of one or more devices than the third total value S3, the first determination unit 415 determines the second active rate Ra2 to the active rate Ra0 of one or more terminal devices 10.

[0176] According to this embodiment, the direction in which the active rate should be changed can be determined from the relationship between the active rate, the timing of acquiring probe request information, and the number of terminal devices, thus enabling the active rate to be determined earlier.

[0177] Furthermore, the terminal management device 40 according to the first embodiment further includes a second determination unit 416. The second determination unit 416 determines the number of one or more terminal devices 10 based on the number of people located in a specific area SA.

[0178] If the MAC addresses included in the probe request are randomized, it is difficult to identify each terminal device from the probe request, making it difficult to determine the number of terminal devices 10 located in a specific area SA. However, according to this embodiment, the number of one or more terminal devices 10 is determined based on the number of people located in a specific area SA, making it easier to determine the number of one or more terminal devices 10.

[0179] Furthermore, the terminal management device 40 according to the first embodiment further includes a display control unit 417. The display control unit 417 displays the activity rate of one or more terminal devices 10 on the display device 44.

[0180] According to this embodiment, the system administrator can easily find out the activity rate of one or more terminal devices 10 located in a specific area.

[0181] Furthermore, the terminal number determination method according to the first embodiment acquires one or more probe request information based on one or more probe requests transmitted from one or more terminal devices 10 located in a specific area, classifies each of the acquired probe request information to determine which of a plurality of types the terminal device 10 that transmitted the corresponding probe request belongs to, and determines the active rate Ra, which is the percentage of terminal devices 10 that are in a screen-on state among the one or more terminal devices 10. This terminal management method is executed by a computer.

[0182] According to this embodiment, the activity rate of terminal devices 10 within a specific service area (SA) can be determined.

[0183] 2. In the terminal management device 40A according to the second embodiment, the configuration of the first determination unit 415A differs from the configuration of the first determination unit 415 of the terminal management device 40 according to the first embodiment. Since the configurations of the terminal device 10, wireless signal detection device 20, and human detection device 30 according to the second embodiment are the same as those of the terminal device 10, wireless signal detection device 20, and human detection device 30 according to the first embodiment, the terminal management device 40A will be described below.

[0184] 2.1. Configuration of the Second Embodiment 2.1.1. Configuration of the Terminal Management Device Figure 17 is a block diagram showing an example configuration of the terminal management device 40A according to the second embodiment. As shown in Figure 17, the terminal management device 40A includes a processing unit 41A, a storage device 42A, a communication device 43, and a display device 44. Each element of the terminal management device 40A is interconnected by one or more buses for communicating information.

[0185] The processing unit 41A is a processor that controls the entire terminal management device 40A, and is configured, for example, using one or more chips. The processing unit 41A is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and registers. Some or all of the functions of the processing unit 41A may be implemented by hardware such as a DSP, ASIC, PLD, FPGA, etc. The processing unit 41A executes various processes in parallel or sequentially.

[0186] The storage device 42A is a recording medium that can be read from and written to by the processing device 41A. The storage device 42A includes, for example, non-volatile memory and volatile memory. The non-volatile memory is, for example, ROM, EPROM, and EEPROM. The volatile memory is, for example, RAM.

[0187] The storage device 42A stores a plurality of programs, including a control program PR4A for execution by the processing device 41A, a first signal strength database DB1, a third learning model LM3, and a second learning model LM2. The storage device 42A also functions as a work area for the processing device 41A. In this embodiment, the first signal strength database DB1 is the same as the first signal strength database DB1 in the first embodiment, and the third learning model LM3 is the same as the third learning model LM3 in the first embodiment.

[0188] The second learning model LM2 is a model that has already learned the relationship between the number of learning terminal devices of the first type, the activity rate of the learning terminal devices, and the timing at which probe request information of the first type of learning is acquired. The second learning model LM2 is trained using machine learning models such as neural network models, logistic regression, and support vector machines.

[0189] Since the configurations of the communication device 43 and the display device 44 are the same as those of the communication device 43 and the display device 44 according to the first embodiment, a description of the communication device 43 and the display device 44 will be omitted.

[0190] The processing unit 41A functions as an acquisition unit 411, an analysis unit 412, a classification unit 413, a position determination unit 414, a first determination unit 415A, a second determination unit 416, a display control unit 417, and a learning unit 418, for example, by reading and executing the control program PR4A from the storage device 42A. Furthermore, the first determination unit 415A functions as an extraction unit 4151A, a number determination unit 4152A, and an active rate determination unit 4154.

[0191] The acquisition unit 411, analysis unit 412, classification unit 413, and position determination unit 414 have the same configuration as the acquisition unit 411, analysis unit 412, classification unit 413, and position determination unit 414 according to the first embodiment, so a detailed explanation is omitted. Also, the second determination unit 416, display control unit 417, and learning unit 418 have the same configuration as the second determination unit 416, display control unit 417, and learning unit 418 according to the first embodiment, so a detailed explanation is omitted.

[0192] The first determination unit 415A determines the active rate based on the acquisition timing of one or more probe request information acquired by the acquisition unit 411, the classification result of the classification unit 413, and the number of one or more terminal devices 10.

[0193] The first determination unit 415A includes an extraction unit 4151A, a unit number determination unit 4152A, and an active rate determination unit 4154.

[0194] Based on the classification result of the classification unit 413, the extraction unit 4151A outputs the acquisition timing among the acquisition timings of one or more probe request information acquired by the acquisition unit 411 that corresponds to the first type of terminal device 10 that sent the probe request. Here, the terminal device 10 that corresponds to the first type is the first type of terminal device 10[k], that is, a Type A device.

[0195] The unit number determination unit 4152A determines the number of Type A devices in a specific area SA based on the number of users U located in the specific area SA and the statistical ratio of the number of Type A devices to the total number of terminal devices. The statistical ratio is, for example, the market share of Type A devices.

[0196] The active rate determination unit 4154 determines the first active rate Ra1, which is the active rate of Type A devices in the specific area SA, by inputting the number of Type A devices in the specific area SA and the timing of acquisition of extracted probe request information into the second learning model LM2. The active rate determination unit 4154 then determines the first active rate Ra1 as the active rate Ra of the terminal devices 10 in the specific area SA.

[0197] 2.2. Operation of the terminal management device according to the second embodiment 2.2.1. Operation of the processing device 41A Diagram 18 is a flowchart illustrating an example of the operation of the processing device 41A in Figure 17. The operation of the processing device 41A will be described below with reference to Figure 18. The routine in Figure 18 is a subroutine of step S15 in Figure 15. Therefore, the operation of the processing device 41A of the terminal management device 40A according to the second embodiment differs from the operation of the processing device 41 of the terminal management device 40 according to the first embodiment only in the processing of step S15.

[0198] In step S151A, the processing unit 41A functions as an extraction unit 4151A and, based on the classification result of the classification unit 413, outputs an acquisition timing among the acquisition timings of one or more probe request information acquired by the acquisition unit 411 that corresponds to an A-type device for the terminal device 10 that sent the probe request.

[0199] In step S152A, the processing unit 41A functions as a unit number determination unit 4152A to determine the number of Type A devices in a specific area SA based on the number of users U located in the specific area SA and the statistical ratio of the number of Type A devices to the total number of terminal devices.

[0200] In step S153A, the processing unit 41A, functioning as an active rate determination unit 4154, inputs the number of Type A devices in a specific area SA and the timing of acquiring extracted probe request information to the second learning model LM2, thereby determining the first active rate Ra1, which is the active rate of Type A devices in a specific area SA.

[0201] In step S154A, the processing unit 41A, functioning as an active rate determination unit 4154, determines the first active rate Ra1 to be the active rate Ra of the terminal device 10 in the specific area SA, and then terminates this subroutine.

[0202] 2.3. Effects of the Second Embodiment In the terminal management device 40A according to the second embodiment, the first determination unit 415A includes an extraction unit 4151A, a number determination unit 4152A, and an active rate determination unit 4154. Based on the classification result of the classification unit 413, the extraction unit 4151A outputs the acquisition timing of one or more probe request information acquired by the acquisition unit 411 that corresponds to the first type of terminal device 10 that sent the probe request. The number determination unit 4152A determines the number of terminal devices 10 of the first type in a specific area SA based on the number of users located in the specific area SA and the statistical ratio of the number of terminal devices belonging to the first type to the total number of terminal devices.

[0203] The active rate determination unit 4154 inputs the number of terminal devices 10 of the first type in a specific area SA and the acquisition timing of the extracted probe request information into a second learning model LM2 that has already learned the relationship between the number of terminal devices of the first type for learning, the active rate of the terminal devices for learning, and the acquisition timing when probe request information of the first type for learning is acquired. This input determines the first active rate Ra1, which is the active rate of the terminal devices 10 of the first type in a specific area SA, and sets the first active rate Ra1 to be the active rate of one or more terminal devices 10.

[0204] According to this embodiment, since the active rate of a first type of terminal device only needs to be determined on behalf of multiple types of terminal devices, the computational load is reduced and the active rate can be determined more easily.

[0205] 3. Modifications This disclosure is not limited to the embodiments illustrated above. Specific examples of modifications are given below. Two or more embodiments may be arbitrarily selected from the following examples and combined. Furthermore, the embodiments of the above embodiments and the modifications below can be combined arbitrarily as long as they do not contradict each other.

[0206] 3.1. Modification 1 In the first embodiment, a method for classifying the type of terminal device 10[k] using the third learning model LM3 was disclosed. However, a lookup table in which the relationship between the signal length and corresponding frequency of the probe request and the type of terminal device 10[k] is predetermined may be used. In this case, the classification unit 413 can classify the type of terminal device 10[k] by inputting the signal length and corresponding frequency of the probe request output from the probe request information into the lookup table.

[0207] 3.2. Modification 2 The first learning model LM1, the second learning model LM2, and the third learning model LM3 may be updated when new models are released by each manufacturer, when the OS of the terminal device is updated to a new version, or several times a year.

[0208] 3.3. Modification 3 In the first embodiment, the first learning model LM1 was prepared for each type, but the first learning model LM1 may be constructed as a single learning model by adding the type to the explanatory variables during training.

[0209] 3.4. Modification 4 In the first embodiment, it was explained that whether or not the terminal device 10[k] is located in a specific area SA is determined based on the information stored in the first signal strength database DB1 and the measured received signal strength. However, whether or not the terminal device 10[k] is located in a specific area SA may be determined using a learning model.

[0210] The input data constituting the training data for machine learning is a combination of measured values ​​of received signal strength when three wireless signal detection devices 20[1], 20[2], and 20[3] receive a probe request from a test terminal device TT located at an arbitrary location. The output data is information indicating the measurement area MA where the test terminal device TT is located.

[0211] In the terminal management device 40 according to Modification 3, the position determination unit 414 determines whether each of the one or more terminal devices 10 is located in a specific area SA by inputting three received signal strengths obtained by receiving wireless signals transmitted from one or more terminal devices 10 by three wireless signal detection devices 20[1], 20[2], and 20[3], which are obtained by receiving probe requests transmitted from one test terminal device TT with three wireless signal detection devices 20[1], 20[2], and 20[3], and the relationship between the three received signal strengths obtained by receiving wireless signals transmitted from one or more terminal devices 10 by three wireless signal detection devices 20[1], 20[2], and 20[3], and the measurement area MA where the test terminal device TT is located, into a learning model which has been trained using learning data acquired multiple times by changing the position of one test terminal device TT at least for each measurement area, and inputting three received signal strengths obtained by receiving wireless signals transmitted from one or more terminal devices 10 by three wireless signal detection devices 20[1], 20[2], and 20[3].

[0212] According to this embodiment, it is possible to easily determine whether or not each of the one or more terminal devices 10 is located in a specific area SA.

[0213] 3.5. Modification 5 In the first embodiment, in the processing of the first decision unit 415, under the condition that the timing of acquiring probe request information is constant, the direction in which to change the active rate was determined based on the relationship that increasing the active rate reduces the number of terminal devices 10. However, the first decision unit 415 may not determine the direction in which to change the active rate, but instead input multiple patterns in which the active rate is changed to the first learning model LM1, and calculate the number of terminal devices of each type for the multiple patterns. The first decision unit 415 may find the active rate from among the multiple patterns that minimizes the difference between the total value and the number of terminal devices 10 (NT) of 1 or more.

[0214] 3.6. Modification 6 In the above embodiment, the active rate of the terminal device was determined using Wi-Fi® wireless signals, but Bluetooth® wireless signals may also be used. With Bluetooth® wireless signals, an advertisement signal is transmitted at predetermined intervals until a connection with the BLE gateway is established. Therefore, the advertisement signal corresponds to a probe request.

[0215] 3.7. Modification 7 In each of the above embodiments, it has been explained that the location of the terminal device 10[k] in each individual area is determined by "mapping". However, the location of the terminal device 10[k] in each individual area may also be determined by tripoint positioning.

[0216] Tripoint positioning is a method for determining the position of terminal device 10[k] based on the received signal strength (RSSI) when a radio signal transmitted from terminal device 10[k] is received by three radio signal detection devices 20[1], 20[2], and 20[3]. In this modified example, terminal device 10[k] is an example of a fourth user terminal.

[0217] Figure 19 is a schematic diagram illustrating tripoint positioning. As shown in Figure 19, in tripoint positioning, the distance r1 between the wireless signal detection device 20[1] and the terminal device 10[k], the distance r2 between the wireless signal detection device 20[2] and the terminal device 10[k], and the distance r3 between the wireless signal detection device 20[3] and the terminal device 10[k] are measured.

[0218] More specifically, the three distances r1, r2, and r3 are the received signal strengths received by the three wireless signal detection devices 20[1], 20[2], and 20[3],

[0219] The position of terminal device 10[k] can be determined in the same manner as finding the internal or external division point of a triangle whose vertices are the positions of the three wireless signal detection devices 20. If the ratio of the distance r1 between wireless signal detection device 20[1] and terminal device 10[k], the distance r2 between wireless signal detection device 20[2] and terminal device 10[k], and the distance r3 between wireless signal detection device 20[3] and terminal device 10[k] is a:b:c, then a, b, and c are each expressed by the following equation (7).

[0220] a=10(RSSI1 / -10n) b=10(RSSI2 / -10n) ...(7) c=10(RSSI3 / -10n)

[0221] However, n is the propagation index. In this example, we assume n = 2. Let the position of the wireless signal detection device 20[1] be point A, and let the coordinates of point A be (x Ａ , y Ａ Let the position of the wireless signal detection device 20[2] be point B, and the coordinates of point B be (x Ｂ , y Ｂ Let the position of the wireless signal detection device 20[3] be point C, and the coordinates of point C be (x Ｃ , y Ｃ )

[0222] If point P is the location of terminal device 10[k], then when point P is located inside triangle ABC and is at a distance from points A, B, and C in the ratio of a, b, and c respectively, its coordinates (x Ｐ , y Ｐ ) is expressed by equations (8) and (9) below.

[0223] x Ｐ = (a・x Ａ + b * x Ｂ + c・x ｃ ) / (a+b+c)...(8) y Ｐ = (a・y Ａ +by Ｂ+c・y ｃ ) / (a+b+c)...(9)

[0224] Furthermore, when point P is outside triangle ABC and is located at distances from points A, B, and C in the ratios a, b, and c respectively, its coordinates (x Ｐ , y Ｐ ) is expressed by equations (10) and (11) below.

[0225] x Ｐ = (-a * x) Ａ + b * x Ｂ + c・x ｃ ) / (-a+b+c)...(10) y Ｐ = (-a・y Ａ +by Ｂ +c・y ｃ ) / (-a+b+c)...(11)

[0226] Based on equations (8) to (11) above, point P(x Ｐ , y Ｐ ) can be found. Therefore, point P(x Ｐ , y Ｐ This determines which individual area each item is located in.

[0227] In the terminal management device 40 according to Modification 3, the position determination unit 414 determines the distance between each of the three wireless signal detection devices 20[1], 20[2], and 20[3] and the terminal device 10[k] based on the received signal strength detected by the three wireless signal detection devices 20[1], 20[2], and 20[3] in response to the probe request sent from the terminal device 10[k]. Based on these distances, the position determination unit 414 determines which of the multiple individual area IAs the terminal device 10[k] is located in.

[0228] According to this embodiment, it is not necessary to measure the received signal strength in advance using the test terminal device TT.

[0229] Note that the probe request does not include information about the transmitted signal strength, but the advertised signal does include information about the transmitted signal strength TxPower. Therefore, in Bluetooth® communication, the distance between the second wireless signal detection device 20b and the terminal device 10[k] can be determined with greater accuracy using the received signal strength and the transmitted signal strength.

[0230] 3.8. Modification 8 In Modification 6, it was explained that the location of the terminal device 10[k] in each individual area may be determined by triplicate positioning. However, the location of the terminal device 10[k] in each individual area may also be determined by duodenal positioning.

[0231] Two-point positioning is a method of determining the position of a terminal device 10[k] based on the direction of arrival of radio signals transmitted from the terminal device 10[k], which are measured by two radio signal detection devices 20[1] and 20[2], respectively.

[0232] Figure 20 is a schematic diagram illustrating two-point positioning. As shown in Figure 20, in two-point positioning, the azimuth angles φ1 and φ2 of the terminal device 10[k] are measured by the wireless signal detection device 20[1] and the wireless signal detection device 20[2]. The intersection of the two azimuth lines AL1 and AL2 is the position of the terminal device 10[k], i.e., point P(x Ｐ , y Ｐ It is estimated that point P(x Ｐ , y Ｐ This determines which individual area each item is located in.

[0233] In order to measure the azimuth angles φ1 and φ2, it is necessary to have multiple antennas on a single wireless signal detection device 20, and to detect the phase difference of signals received by the multiple antennas.

[0234] 4. Other (1) In the embodiments described above, the storage devices 12, 22, 32, 42, and 42A are exemplified by ROM and RAM, but they can also be flexible disks, magneto-optical disks (e.g., compact disks, digital multipurpose disks, Blu-ray® disks), smart cards, flash memory devices (e.g., cards, sticks, key drives), CD-ROMs (Compact Disc-ROMs), registers, removable disks, hard disks, floppy® disks, magnetic strips, databases, servers, and other suitable storage media. The program may also be transmitted from a network via a telecommunications line. The program may also be transmitted from a communication network NET via a telecommunications line.

[0235] (2) In the embodiments described above, the information, signals, etc. may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0236] (3) In the embodiments described above, the input and output information may be stored in a specific location (e.g., memory) or managed using a management table. The input and output information may be overwritten, updated, or appended to. The output information may be deleted. The input information may be transmitted to other devices.

[0237] (4) In the embodiments described above, the determination may be made by a value represented using one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0238] (5) The processing procedures, sequences, flowcharts, etc., exemplified in the embodiments described above may be rearranged in order, as long as there is no contradiction. For example, the methods described in this disclosure present various step elements using an exemplary order and are not limited to the specific order presented.

[0239] (6) Each function illustrated in Figures 1 to 20 is realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each function block is not particularly limited. That is, each function block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired, wireless, etc.). A function block may also be realized by combining the above one device or the above multiple devices with software.

[0240] (7) The programs illustrated in the embodiments described above should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether they are called software, firmware, middleware, microcode, hardware description languages ​​or by other names.

[0241] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0242] (8) In each of the above-mentioned forms, the terms “system” and “network” shall be used interchangeably.

[0243] (9) The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information.

[0244] (10) In the embodiments described above, the terminal device 10 may be a mobile station (MS). A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or several other appropriate terms. In this disclosure, terms such as “mobile station,” “user terminal,” “user equipment (UE),” and “terminal” may be used interchangeably.

[0245] (11) In the embodiments described above, the terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be a physical coupling or connection, a logical coupling or connection, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain and optical (both visible and invisible) domain.

[0246] (12) In the embodiments described above, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on".

[0247] (13) The terms “determining” and “determining” as used in this disclosure may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0248] (14) In the embodiments described above, where “include,” “including,” and variations thereof are used, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR.

[0249] (15) In the present disclosure, if articles are added by translation, such as a, an, and the in English, the present disclosure may include the fact that the noun following these articles is plural.

[0250] (16) In this disclosure, the term “A and B are different” may mean “A and B are different from each other.” The term may also mean “A and B are each different from C.” Terms such as “separate” and “combine” may be interpreted in the same way as “different.”

[0251] (17) Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of the specified information (e.g., notification that "it is X") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0252] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not restrictive in any way.

[0253] 10, 10[1], 10[2], 10, [k], 10[n]... Terminal device, 20... Detection device, 40... Terminal management device, 411... Acquisition unit, 413... Classification unit, 415... First determination unit, 314... Estimation unit, 4151, 4151A... Extraction unit, 4152, 4152A... Number of units determination unit, 4153... Difference determination unit, 4154... Active rate determination unit, D1... First difference value, D2... Second difference value, D3... Third difference value, LM1... First learning model, LM2... Second learning model, Ra... Active rate, Ra2... Second active rate, Ra3... Third active rate, Ra4... Fourth active rate, S1... First total value, S2... Second total value, S3... Third total value, U... User.

Claims

1. A terminal management device comprising: an acquisition unit that acquires one or more probe request information based on one or more probe requests transmitted from one or more user terminals located in a first area; a classification unit that classifies, for each of the acquired one or more probe request information, which of a plurality of types the user terminal that transmitted the corresponding probe request belongs to; and a first determination unit that determines the active rate, which is the percentage of user terminals that are in a screen-on state among the one or more user terminals, based on the acquisition timing of the one or more probe request information acquired by the acquisition unit, the classification result of the classification unit, and the number of the one or more user terminals.

2. The first determination unit comprises: an extraction unit that outputs the acquisition timing of probe request information for each type by extracting the acquisition timing of one or more probe request information acquired by the acquisition unit based on the classification result of the classification unit for each classified type; a number determination unit that determines the number of user terminals for each type by inputting the user terminal activity rate and the extracted acquisition timing of probe request information for each type into the first learning model, which is prepared for each type and has learned the relationship between the activity rate of user terminals for learning, the acquisition timing when the probe request information for learning for each type is acquired and the number of user terminals for learning for each type; a difference determination unit that determines the difference between the total number of user terminals for each type determined by the number determination unit and the number of one or more user terminals; the number determination unit determines multiple numbers of user terminals for each type by changing the activity rate of the user terminals; and the difference determination unit determines multiple differences in accordance with the change in the activity rate of the user terminals by the number determination unit. The terminal management device according to claim 1, wherein the active rate of the user terminal corresponding to the smallest difference among the multiple differences determined by the difference determination unit is determined to be the active rate of the one or more user terminals.

3. The number determination unit determines a first total value, which is the sum of the number of user terminals for each type, by inputting a second active rate as the activity rate of the user terminals and the timing for acquiring probe request information for each type of user terminal to the first learning model; the difference determination unit determines the difference between the first total value and the number of one or more user terminals as the first difference value; if the first total value is less than the number of one or more user terminals, the number determination unit determines a second total value, which is the sum of the number of user terminals for each type, by inputting a third active rate lower than the second active rate and the timing for acquiring probe request information for each type of user terminal to the first learning model; the difference determination unit determines the difference between the second total value and the number of one or more user terminals as the second difference value; and if the first total value is closer to the number of one or more user terminals than the second total value, the first determination unit determines the second active rate to the activity rate of one or more user terminals. If the first total value is greater than the number of one or more user terminals, the terminal number determination unit determines a third total value, which is the sum of the number of user terminals for each type, by inputting a fourth active rate higher than the second active rate and the timing for acquiring probe request information for each type of user terminal to the first learning model; the difference determination unit determines the difference between the third total value and the number of one or more user terminals as the third difference value; and if the first total value is closer to the number of one or more user terminals than the third total value, the first determination unit determines the second active rate to the active rate of one or more user terminals, according to claim 2.

4. The terminal management device according to claim 1, comprising: an extraction unit that outputs an acquisition timing among the acquisition timings of one or more probe request information acquired by the acquisition unit that corresponds to a first type, based on the classification result of the classification unit; a number determination unit that determines the number of user terminals of the first type in the first area based on the number of people located in the first area and the statistical ratio of the number of user terminals belonging to the first type to the total number of user terminals; and an activity rate determination unit that determines a first activity rate, which is the activity rate of user terminals of the first type in the first area, by inputting the number of user terminals of the first type in the first area and the acquisition timing of the extracted probe request information into a second learning model that has learned the relationship between the number of learning user terminals of the first type, the activity rate of learning user terminals, and the acquisition timing in which learning probe request information of the first type was acquired, and determines the first activity rate to be the activity rate of the one or more user terminals.

5. The terminal management device according to claim 1, further comprising a second determination unit that determines the number of one or more user terminals based on the number of people located in the first area.

6. The terminal management device according to claim 1, further comprising a display control unit that displays the activity rate of one or more user terminals on a display device.

7. A terminal management method performed by a computer, comprising: acquiring one or more probe request pieces of information based on one or more probe requests transmitted from one or more user terminals located in a first area; classifying each of the acquired probe request pieces of information to determine which of a plurality of types the user terminal that transmitted the corresponding probe request belongs to; and determining the active rate, which is the percentage of the one or more user terminals that are in a screen-on state, based on the timing of acquisition of the acquired probe request pieces of information, the classification result, and the number of the one or more user terminals.

Images