Selection device and information processing system

Abstract

To improve the accuracy of determining the location of wireless tags. [Solution] The selection device of the embodiment includes an acquisition unit and a selection unit. The acquisition unit acquires tag data of a reference radio tag at multiple positions of the antenna measured by a communication device equipped with an antenna. The selection unit selects a trained model from multiple trained models based on the tag data of the reference radio tag. The multiple trained models are models that are appropriate to the environment of the communication device and are models generated by machine learning based on multiple training data. The multiple training data includes tag data of multiple radio tags to be trained and data indicating the range in which each of the multiple radio tags to be trained exists.

Description

Technical Field

[0006] , , , ,

[0005] , , , ,

[0001] Embodiments of the present invention relate to a selective communication device and an information processing system.

Background Art

[0002] There is a device that determines whether a wireless tag is within a predetermined range or outside the predetermined range by receiving radio waves transmitted from a wireless tag attached to an article with an antenna. Such a device moves an antenna to measure the phase of the wireless tag. The device determines whether the wireless tag is within a predetermined range or outside the predetermined range based on the phase difference, which is the amount of change in the measured phase. The device needs to set the phase difference corresponding to the boundary of the predetermined range as a threshold value.

[0003] When a predetermined fixed threshold value is used for the determination process, the determination accuracy may decrease due to the influence of the environment such as disturbance.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

[0007] [Figure 1] Figure 1 is a block diagram showing an example of the configuration of a communication system according to an embodiment. [Figure 2] Figure 2 is a block diagram showing an example of the configuration of a reading device according to an embodiment. [Figure 3] Figure 3 shows an example of a data structure that constitutes measurement data according to the embodiment. [Figure 4] Figure 4 is a block diagram showing an example of the configuration of a drive device according to this embodiment. [Figure 5] Figure 5 is a schematic diagram illustrating the drive device according to the embodiment. [Figure 6] Figure 6 is a block diagram showing an example of the configuration of a terminal according to the embodiment. [Figure 7] Figure 7 is a schematic diagram illustrating the first and second ranges according to the embodiment. [Figure 8] Figure 8 is a diagram illustrating comparative reference tag data for a communication device according to an embodiment, depending on the environment in which metal is placed. [Figure 9] Figure 9 is a diagram illustrating comparative reference tag data for a communication device according to an embodiment, depending on the environment in which metal is placed. [Figure 10] Figure 10 is a flowchart showing an example of the process by which the processor of the reader according to the embodiment acquires reference tag data. [Figure 11] Figure 11 is a flowchart showing an example of selection processing by the processor of a terminal according to this embodiment. [Figure 12] Figure 12 is a flowchart showing an example of the process by which the processor of the reader according to the embodiment acquires determination tag data. [Figure 13] Figure 13 is a flowchart showing an example of the determination process performed by the terminal processor according to this embodiment. [Figure 14] Figure 14 shows an example of the arrangement of multiple wireless tags to be used for learning according to the embodiment. [Figure 15] Figure 15 is a graph showing an example of training tag data according to the embodiment. [Figure 16] Figure 16 is a graph showing another example of training tag data according to the embodiment. [Figure 17] Figure 17 is a graph showing yet another example of training tag data according to the embodiment. [Figure 18] Figure 18 is a flowchart showing an example of the process by which the terminal processor according to this embodiment generates a trained model. [Modes for carrying out the invention]

[0008] The communication system according to the embodiment will be described below with reference to the drawings. Note that the scale of the parts in the drawings used in the description of the embodiment below may have been changed as appropriate. Also, for illustrative purposes, some components may be omitted from the drawings used in the description of the embodiment below.

[0009] Figure 1 is a block diagram showing an example of the configuration of a communication system 1 according to an embodiment. The communication system 1 includes a communication device 10, a terminal 400, and a plurality of wireless tags 600 attached to a plurality of articles 500. Although FIG. 1 shows one wireless tag 600 attached to one article 500, the communication system 1 includes a plurality of wireless tags 600 attached to a plurality of articles 500. Note that the communication system 1 includes the communication device 10 and the terminal 400, but may not include the plurality of articles 500. The communication system 1 is an example of an information processing system.

[0010] The communication device 10 is a device that reads information from the wireless tag 600. The communication device 10 can be used for inspection in a warehouse or the like, but it may also be a store, and the application examples of the communication device 10 are not limited to this. The communication device 10 includes a reading device 100, a driving device 200, and an antenna 300.

[0011] The reading device 100 is a device that controls the driving device 200 and the antenna 300 to read information from the wireless tag 600. Configuration examples of the reading device 100 will be described later. The driving device 200 is a device that moves the antenna 300. Configuration examples of the driving device 200 will be described later. The antenna 300 transmits and receives radio waves to and from the wireless tag 600. The antenna 300 converts the radio waves received from the wireless tag 600 into a high-frequency signal and outputs the high-frequency signal to the reading device 100.

[0012] The terminal 400 is a device that processes the information read from the wireless tag 600 by the reading device 100. The terminal 400 is a PC (personal computer) or the like, but any device that can process information is acceptable and is not limited to this. Configuration examples of the terminal 400 will be described later. The terminal 400 is an example of a selection device.

[0013] The article 500 is a commodity or the like. The wireless tag 600 is typically an RFID (radio frequency identification) tag. However, the wireless tag 600 may be any other type of wireless tag. The wireless tag 600 is a passive wireless tag that operates using predetermined radio waves emitted from the antenna 300 as an energy source. The wireless tag 600 transmits a signal containing information stored in the wireless tag 600 by performing backscatter modulation on an unmodulated signal. The information stored in the wireless tag 600 may include uniquely identifiable identification information. The information stored in the wireless tag 600 may also include information about the item 500 to which the wireless tag 600 is attached.

[0014] The reading device 100 will be explained using Figure 2. Figure 2 is a block diagram showing an example of the configuration of the reading device 100. The reading device 100 includes a processor 101, a ROM (read-only memory) 102, a RAM (random-access memory) 103, a first connection interface 104, a second connection interface 105, a high-frequency front-end unit 106, a digital amplitude modulation unit 107, a DA (digital to analog) conversion unit 108, an AD (analog to digital) conversion unit 109, a demodulation unit 110, and a storage device 111. Each part of the reading device 100 is connected by a bus 112, etc.

[0015] The processor 101 corresponds to the central part of the computer that performs calculations and control necessary for the operation of the reader 100. The processor 101 loads various programs stored in the ROM 102 or storage device 111, etc., into the RAM 103. By executing the programs loaded into the RAM 103, the processor 101 realizes the various parts described later and performs various operations.

[0016] The processor 101 may be a CPU (central processing unit), MPU (microprocessing unit), SoC (system on a chip), DSP (digital signal processor), GPU (graphics processing unit), ASIC (application specific integrated circuit), PLD (programmable logic device), or FPGA (field-programmable gate array), etc. The processor 101 may be a combination of several of these.

[0017] ROM 102 corresponds to the main memory of a computer centered around processor 101. ROM 102 is a non-volatile memory used exclusively for reading data. ROM 102 stores the above-mentioned program. Furthermore, ROM 102 stores data or various setting values ​​used by processor 101 in performing various processes.

[0018] RAM103 corresponds to the main memory of a computer centered around processor 101. RAM103 is memory used for reading and writing data. RAM103 is a work area that stores data temporarily used by processor 101 when performing various processes.

[0019] The first connection interface 104 is an interface for the reader 100 to communicate with the drive unit 200.

[0020] The second connection interface 105 is an interface for the reader 100 to communicate with the terminal 400.

[0021] The high-frequency front-end unit 106 outputs a high-frequency signal to the antenna 300. The high-frequency front-end unit 106 receives a high-frequency signal from the antenna 300.

[0022] The digital amplitude modulation unit 107 is a circuit that adds information to be transmitted to the wireless tag 600 to the carrier wave transmitted to the wireless tag 600.

[0023] The DA conversion unit 108 is a circuit that converts a digital signal to an analog signal. The DA conversion unit 108 converts the digital signal modulated by the digital amplitude modulation unit 107 into an analog signal. The DA conversion unit 108 outputs a high-frequency signal to the antenna 300 via the high-frequency front-end unit 106.

[0024] The AD conversion unit 109 is a circuit that converts an analog signal into a digital signal. The AD conversion unit 109 converts the high-frequency signal input from the antenna 300 into a digital signal via the high-frequency front-end unit 106.

[0025] The demodulation unit 110 is a circuit that extracts various information from radio waves received from the wireless tag 600. For example, the demodulation unit 110 extracts a unique identification code stored in the wireless tag 600 from the digital signal converted by the AD conversion unit 109. Also, using known technology, when the antenna 300 receives the radio waves from the wireless tag 600, the demodulation unit 110 outputs tag data of the wireless tag 600 in time series from the digital signal converted by the AD conversion unit 109. The tag data is time series data based on the radio waves from the wireless tag 600 received by the antenna 300. The tag data includes phase data. The phase data is data indicating the phase of the radio waves from the wireless tag 600. The tag data includes received signal strength indicator (RSSI) data. The received signal strength data is data indicating the received strength of the radio waves from the wireless tag 600. The tag data includes at least one of the phase data and the received signal strength data. Furthermore, each wireless tag 600 may store radio wave reception strength data in its own memory when it receives radio waves transmitted from the antenna 300. In this example, the demodulation unit 110 may extract the radio wave reception strength data stored in the wireless tag 600 in a time series from the digital signal converted by the AD conversion unit 109. The demodulation unit 110 is an example of a detection unit that detects the tag data of each wireless tag 600 in a time series based on the radio waves from each wireless tag 600.

[0026] The storage device 111 is a device composed of non-volatile memory for storing data and programs. The storage device 111 is composed of an HDD (Hard Disk Drive) or an SSD (Solid State Drive), but is not limited to these. The storage device 111 is an example of a storage unit.

[0027] The storage device 111 includes a reference tag data storage area 1111. The reference tag data storage area 1111 stores a reference tag dataset of a reference radio tag. The reference tag dataset is a collection of multiple tag data from a reference radio tag measured by the communication device 10. Hereinafter, the tag data of the reference radio tag associated with the reference tag dataset will also be referred to as reference tag data. The reference tag dataset includes multiple reference tag data from the reference radio tag at multiple locations on the antenna 300. Each of the multiple locations on the antenna 300 is a measurement location for the tag data. The communication device 10 may be able to measure reference tag data at all of the multiple locations on the antenna 300. In this example, the reference tag dataset includes reference tag data associated with each of the multiple locations on the antenna 300. The communication device 10 may only be able to measure reference tag data at some of the multiple locations on the antenna 300. In this example, the reference tag dataset includes reference tag data associated with each of the some locations on the antenna 300. The reference tag dataset is an example of reference tag data for the reference radio tag at multiple locations on the antenna 300.

[0028] A reference wireless tag is a wireless tag placed in a predetermined location. The reference wireless tag may be placed in a predetermined location on the counter stand 700, which will be described later. The reference wireless tag only needs to be placeable in a predetermined location and may be detachable from the counter stand 700. The reference wireless tag may include one wireless tag or multiple wireless tags. If the reference wireless tag includes multiple wireless tags, the multiple wireless tags may be placed in different locations on the counter stand 700. The reference wireless tag is an example of a wireless tag. The reference tag dataset may be updated based on measurements by the communication device 10.

[0029] The memory device 111 includes a measurement data storage area 1112. The measurement data storage area 1112 stores measurement data. The measurement data includes multiple determination tag datasets. Each determination tag dataset is a dataset for each wireless tag 600 to be determined. The determination tag dataset is a collection of multiple tag data for the wireless tag 600 to be determined, measured by the communication device 10. Hereinafter, the tag data of the wireless tag 600 to be determined that is associated with the determination tag dataset will also be referred to as determination tag data. The determination tag dataset includes multiple determination tag data for the wireless tag 600 to be determined at multiple locations on the antenna 300. Depending on the wireless tag 600 to be determined, the communication device 10 may be able to measure determination tag data at all of the multiple locations on the antenna 300. In this example, the determination tag dataset includes determination tag data associated with each of the multiple locations on the antenna 300. Depending on the wireless tag 600 to be determined, the communication device 10 may only be able to measure determination tag data at some of the multiple locations on the antenna 300. In this example, the determination tag dataset includes determination tag data associated with each of the some locations on the antenna 300. The multiple identification tag datasets are examples of identification tag data for each wireless tag 600 to be identified at multiple locations on the antenna 300.

[0030] The wireless tag 600 to be determined is a wireless tag whose range of existence is to be determined. The wireless tag 600 to be determined is an example of a wireless tag to be measured. A wireless tag to be measured is also called a wireless tag to be measured. The wireless tag 600 to be determined is an example of a wireless tag. Multiple wireless tags 600 to be determined are a collection of wireless tags whose tag data is measured by a common measurement process by the communication device 10. The measurement process is a process of measuring tag data. The measurement process is a process that involves the movement of the antenna 300. For example, one measurement process is a process that involves the movement of the antenna 300 within the scanning range of the antenna 300. The object to determine the range of existence of the wireless tag 600 includes an object to determine whether the position of the wireless tag 600 is included in the first range or the second range. The first range and the second range are different ranges that do not overlap with each other. For example, the first range and the second range are three-dimensional regions. Examples of the first range and the second range will be described later. The measurement data may be updated based on the measurement by the communication device 10. An example of the structure of the measurement data will be described later.

[0031] Bus 112 includes a control bus, an address bus, and a data bus, etc. Bus 112 transmits signals exchanged between the various parts of the reader 100.

[0032] The hardware configuration of the reading device 100 is not limited to the configuration described above. The reading device 100 may be modified or have its components omitted or changed as appropriate, and new components added as needed.

[0033] The various components implemented by processor 101 will now be described. The processor 101 implements the movement control unit 1011, the communication control unit 1012, the acquisition unit 1013, and the output unit 1014. Each part implemented by the processor 101 can also be called a function. Each part implemented by the processor 101 can also be said to be implemented by a control unit including the processor 101, ROM 102, and RAM 103.

[0034] The movement control unit 1011 controls the movement of the antenna 300 by controlling the drive unit 200.

[0035] The communication control unit 1012 controls the transmission of radio waves from the antenna 300.

[0036] The acquisition unit 1013 acquires a reference tag dataset corresponding to the environment of the communication device 10. The acquisition unit 1013 acquires multiple determination tag datasets.

[0037] The output unit 1014 outputs data to the terminal 400 via the second connection interface 105. In one example, the output unit 1014 outputs a reference tag dataset to the terminal 400. In another example, the output unit 1014 outputs multiple determination tag datasets to the terminal 400.

[0038] Figure 3 shows an example of a data structure that makes up measurement data. The antenna 300 moves back and forth in one direction based on control by the drive unit 200. The scanning range of the antenna 300 is a unidirectional range from position 0, which corresponds to the home position, to position L. Position L can be set as appropriate.

[0039] The measurement data includes a determination tag dataset for each wireless tag 600 to be determined. The determination tag dataset includes multiple determination tag data for the wireless tag 600 to be determined at multiple locations on the antenna 300. For example, the multiple locations on the antenna 300 include locations at a fixed interval a between location 0 and location L. The value of the fixed interval a can be set as appropriate. Depending on the wireless tag 600 to be determined, the communication device 10 may be able to measure determination tag data at all locations at a fixed interval a between location 0 and location L. Depending on the wireless tag 600 to be determined, the communication device 10 may only be able to measure determination tag data at some of the locations at a fixed interval a between location 0 and location L. The multiple locations on the antenna 300 may include one or more locations different from the locations at a fixed interval a between location 0 and location L.

[0040] The drive unit 200 will be explained using Figures 4 and 5. Figure 4 is a block diagram showing an example of the configuration of the drive unit 200. The drive unit 200 includes a processor 201, ROM 202, RAM 203, connection interface 204, drive unit 205, and home position sensor 206. The components included in the drive unit 200 are connected by a bus 208, etc.

[0041] The processor 201 corresponds to the central part of the computer that performs calculations and control necessary for the operation of the drive unit 200. The processor 201 loads various programs stored in ROM 202, etc., into RAM 203. The processor 201 performs various operations by executing the programs loaded into RAM 203. The processor 201 can be a CPU, MPU, SoC, DSP, GPU, ASIC, PLD, or FPGA, etc. The processor 201 may be a combination of several of these.

[0042] ROM202 corresponds to the main memory of a computer centered around processor 201. ROM202 is a non-volatile memory used exclusively for reading data. ROM202 stores the above-mentioned program. ROM202 also stores data or various setting values ​​used by processor 201 in performing various processes.

[0043] RAM203 corresponds to the main memory of a computer centered around processor 201. RAM203 is memory used for reading and writing data. RAM203 is a work area that stores data temporarily used by processor 201 when performing various processes.

[0044] The connection interface 204 is an interface for the drive unit 200 to connect with the reader unit 100.

[0045] The drive unit 205 moves the antenna 300. For example, the drive unit 205 is a stepping motor.

[0046] The home position sensor 206 is a sensor that detects whether or not the moving stage 213, which will be described later, is in the home position.

[0047] Bus 208 includes a control bus, an address bus, and a data bus, etc. Bus 208 transmits signals exchanged between various parts of the drive unit 200.

[0048] Figure 5 is a schematic diagram illustrating the drive unit 200. The drive unit 200 includes a rotating shaft 211, a rail 212, and a moving stage 213.

[0049] As illustrated in Figure 5, the drive unit 200 and the antenna 300 are located below the counter base 700. The counter base 700 is a platform having a horizontal surface on which the article 500 with the wireless tag 600 attached is placed. The counter base 700 is an example of a mounting section. The counter base 700 may be included in the communication system 1 or the communication device 10.

[0050] The rotating shaft 211 transmits the driving force of the drive unit 205. Screw grooves are formed on the rotating shaft 211 and the rail 212. The screw grooves are opposite each other and connected. Therefore, when the drive unit 205 is driven to rotate, the rotating shaft 211 rotates and the rail 212 moves. A moving stage 213 on which the antenna 300 is mounted is attached to the rail 212.

[0051] The moving stage 213 is equipped with a ball screw nut, and moves horizontally when the rail 212 rotates due to the ball screw nut. That is, the moving stage 213 moves in the direction along the x-axis as shown in Figure 5. Also, if the rotation direction of the rail 212 is reversed, the moving stage 213 moves in the opposite direction. In this way, the drive device 200 moves the antenna 300 back and forth along the rail 212 in one direction along the x-axis.

[0052] The hardware configuration of the drive unit 200 is not limited to the configuration described above. The drive unit 200 may be modified or have the above-described components omitted or changed, and new components added as appropriate.

[0053] Terminal 400 will be explained using Figure 6. Figure 6 is a block diagram showing an example of the configuration of terminal 400. Terminal 400 includes a processor 401, ROM 402, RAM 403, connection interface 404, and storage device 405. The components of terminal 400 are connected by a bus 406, etc.

[0054] The processor 401 corresponds to the central part of the computer that performs calculations and control processing necessary for the operation of the terminal 400. The processor 401 loads various programs stored in the ROM 402 or memory device 405, etc., into the RAM 403. By executing the programs loaded into the RAM 403, the processor 401 realizes the various parts described later and performs various operations. The processor 401 is a CPU, MPU, SoC, DSP, GPU, ASIC, PLD, or FPGA, etc. The processor 401 may be a combination of several of these.

[0055] ROM402 corresponds to the main memory of a computer centered around processor 401. ROM402 is a non-volatile memory used exclusively for reading data. ROM402 stores the above-mentioned program. ROM402 also stores data or various setting values ​​used by processor 401 in performing various processes.

[0056] RAM403 corresponds to the main memory of a computer centered around processor 401. RAM403 is memory used for reading and writing data. RAM403 is a work area that stores data temporarily used by processor 401 when performing various processes.

[0057] The connection interface 404 is an interface for the terminal 400 to communicate with the reader 100 or other devices.

[0058] The storage device 405 is a device composed of non-volatile memory for storing data and programs. The storage device 405 is composed of, but is not limited to, an HDD or an SSD. The storage device 405 is an example of a storage unit.

[0059] The storage device 405 includes a reference tag data storage area 4051. The reference tag data storage area 4051 stores a reference tag dataset acquired from the reader 100 by the terminal 400. The reference tag dataset stored in the reference tag data storage area 4051 corresponds to the reference tag dataset stored in the reference tag data storage area 1111. The reference tag dataset stored in the reference tag data storage area 4051 can be updated each time the terminal 400 acquires a reference tag dataset from the reader 100.

[0060] The storage device 405 includes a comparison reference tag data storage area 4052. The comparison reference tag data storage area 4052 stores multiple comparison reference tag datasets.

[0061] The comparison reference tag dataset is a collection of multiple tag data from reference radio tags pre-measured by a communication device. Hereinafter, the tag data of reference radio tags related to the comparison reference tag dataset will also be referred to as comparison reference tag data. For the sake of simplicity, the communication device that pre-measures the comparison reference tag data will be described as communication device 10, but it may be one or more communication devices of the same type as communication device 10. The comparison reference tag dataset includes multiple comparison reference tag data from reference radio tags at multiple locations on the antenna 300. Communication device 10 may be able to measure comparison reference tag data at all of the multiple locations on the antenna 300. In this example, the comparison reference tag dataset includes comparison reference tag data associated with each of all locations on the antenna 300. Communication device 10 may only be able to measure comparison reference tag data at some of the multiple locations on the antenna 300. In this example, the comparison reference tag dataset includes comparison reference tag data associated with each of the some locations on the antenna 300. The reference wireless tag used in measuring the comparative reference tag data is a tag placed in the same predetermined location as the reference wireless tag used in measuring the reference tag data. Multiple comparative reference tag datasets are examples of multiple comparative tag data sets used for comparison with the reference tag dataset.

[0062] Multiple comparison reference tag datasets are datasets that correspond to the environment of the communication device 10. In other words, multiple comparison reference tag datasets are different datasets that correspond to the environment of the communication device 10. The environment of the communication device 10 is the environment that affects the tag data. The environment of the communication device 10 includes the arrangement of metals relative to the communication device 10. For example, the arrangement of metals relative to the communication device 10 is the arrangement of metals around the communication device 10. Metals are elements containing metal, such as metal plates or metal shelves, but are not limited to these.

[0063] The arrangement of metal is the arrangement of metal that affects the tag data. The arrangement of metal includes the presence or absence of metal relative to the communication device 10. The arrangement of metal may also include the distance between the communication device 10 and the metal. It may also include the position of the metal relative to the communication device 10. Multiple comparison reference tag datasets may include comparison reference tag datasets corresponding to environments where no metal is placed relative to the communication device 10. Multiple comparison reference tag datasets may include comparison reference tag datasets corresponding to environments where metal is placed relative to the communication device 10. Multiple comparison reference tag datasets may include multiple comparison reference tag data corresponding to the distance between the communication device 10 and the metal in an environment where metal is placed relative to the communication device 10. Multiple comparison reference tag datasets may include multiple comparison reference tag datasets corresponding to the position of the metal relative to the communication device 10 in an environment where metal is placed relative to the communication device 10. Note that the arrangement of metal is not limited to the presence or absence of metal, distance, and position. The arrangement of metal may also include the shape, size, and number of metals, etc.

[0064] Multiple comparison reference tag datasets are associated with multiple trained models, as described later. In other words, each of the multiple comparison reference tag datasets is associated with each of the multiple trained models for each environment of the communication device 10. The multiple comparison reference tag datasets can be updated as needed.

[0065] The storage device 405 includes a measurement data storage area 4053. The measurement data storage area 4053 stores measurement data. The measurement data includes multiple determination tag datasets acquired from the reader 100 by the terminal 400. The measurement data stored in the measurement data storage area 4053 corresponds to the measurement data stored in the measurement data storage area 1112. The measurement data stored in the measurement data storage area 4053 can be updated each time the terminal 400 acquires multiple determination tag datasets from the reader 100.

[0066] The memory device 405 includes a training data storage area 4054. The training data storage area 4054 stores multiple training data. The training data includes data that has been pre-measured by a communication device. For the sake of simplicity, the communication device that pre-measures the data included in the training data is assumed to be communication device 10, but it may be one or more communication devices of the same type as communication device 10. The training data is data used for machine learning. Multiple training data sets are data that corresponds to the environment of communication device 10. In other words, multiple training data sets are data that are different from each other, depending on the environment of communication device 10.

[0067] Multiple training data sets include training tag datasets. Each training tag dataset contains multiple datasets for multiple target wireless tags 600. These multiple target wireless tags 600 are a collection of wireless tags whose tag data is measured by a common measurement process performed by the communication device 10. The dataset for each target wireless tag 600 includes multiple tag data for the target wireless tag 600 at multiple locations on the antenna 300. Hereinafter, the tag data of the target wireless tag 600 associated with the training tag dataset will also be referred to as training tag data. Depending on the target wireless tag 600, the communication device 10 may be able to measure training tag data at all of the multiple locations on the antenna 300. In this example, the dataset for the target wireless tag 600 includes training tag data associated with each of the multiple locations on the antenna 300. Depending on the target wireless tag 600, the communication device 10 may only be able to measure training tag data at some of the multiple locations on the antenna 300. In this example, the dataset for the wireless tag 600 to be trained includes training tag data associated with each of several locations on the antenna 300. The dataset for the wireless tag 600 to be trained is an example of training tag data for the wireless tag 600 to be trained. The training tag dataset is an example of training tag data for multiple wireless tags 600 to be trained. The wireless tag 600 to be trained is an example of a wireless tag.

[0068] Multiple training data sets include data indicating the range in which each of the multiple wireless tags 600 to be trained exists. Hereafter, the data indicating the range in which each of the multiple wireless tags 600 to be trained exists will also be referred to as the ground truth data. The ground truth data includes data indicating whether each of the multiple wireless tags 600 to be trained is included in the first range or the second range. The notation "each of the multiple wireless tags 600 to be trained" may be read as "the location of each of the multiple wireless tags 600 to be trained". The ground truth data is data entered by the user. Multiple training data sets can be updated.

[0069] The memory device 405 includes a trained model memory area 4055. The trained model memory area 4055 stores multiple trained models. The multiple pre-trained models are models adapted to the environment of the communication device 10, and are models generated by machine learning based on multiple training data. In other words, each of the multiple pre-trained models is a model adapted to the environment of the communication device 10, generated by machine learning based on each of the multiple training data. The term "generated" includes not only newly created models but also updated models. The multiple pre-trained models are used to determine the range in which the wireless tag 600 to be judged exists.

[0070] The trained model outputs decision output data based on the input decision input data. The decision input data consists of the multiple decision tag datasets described above. The decision output data indicates the range in which each wireless tag 600 to be determined exists. The data indicating the range in which each wireless tag 600 to be determined exists includes data indicating whether each wireless tag 600 to be determined belongs to the first range or the second range. The data indicating which range each wireless tag 600 belongs to includes data indicating which range the location of each wireless tag 600 belongs to. Each wireless tag 600 to be determined is associated with either the first range or the second range.

[0071] Bus 406 includes a control bus, an address bus, and a data bus, etc. Bus 406 transmits signals exchanged between various parts of terminal 400.

[0072] The hardware configuration of terminal 400 is not limited to the configuration described above. Terminal 400 may be modified or have its components omitted or changed as appropriate, and new components added as needed.

[0073] The various components implemented by processor 401 will be described below. The processor 401 implements a first acquisition unit 4011, an input unit 4012, a second acquisition unit 4013, an output unit 4014, a model processing unit 4015, and a selection unit 4016. Each part implemented by the processor 401 can also be called a function. Each part implemented by the processor 401 can also be said to be implemented by a control unit including the processor 401, ROM 402, and RAM 403.

[0074] The first acquisition unit 4011 acquires data from the reader device 100 via the connection interface 404. In one example, the first acquisition unit 4011 acquires a reference tag dataset from the reader device 100 according to the environment of the communication device 10. In another example, the first acquisition unit 4011 acquires multiple determination tag datasets from the reader device 100. The acquisition of data from the reader device 100 by the first acquisition unit 4011 is an example of the acquisition of data from the communication device 10 by the first acquisition unit 4011. The first acquisition unit 4011 is an example of an acquisition unit.

[0075] The input unit 4012 inputs the judgment input data to a pre-trained model selected from multiple pre-trained models according to the environment of the communication device 10. The judgment input data consists of multiple judgment tag datasets acquired by the first acquisition unit 4011.

[0076] The second acquisition unit 4013 acquires judgment output data from the trained model based on the input of judgment input data to the trained model by the input unit 4012.

[0077] The output unit 4014 outputs the determination result to another device. The determination result includes data indicating the range in which each wireless tag 600 to be determined exists, which was acquired as determination output data by the second acquisition unit 4013.

[0078] The model processing unit 4015 generates a trained model.

[0079] The selection unit 4016 selects one trained model from among multiple trained models stored in the trained model memory area 4055. For example, the selection unit 4016 selects a trained model from among multiple trained models depending on the environment of the communication device 10.

[0080] The first and second scopes will be explained below. Figure 7 is a schematic diagram illustrating the first range 81 and the second range 82, and is a plan view of the countertop 700 seen from above.

[0081] The first range 81 and the second range 82 are horizontally separated ranges. The first range 81 is the range set in the central part of the horizontal plane of the counter base 700. The second range 82 is the range set in the outer periphery of the horizontal plane of the counter base 700 and the range set horizontally outside the counter base 700. The second range 82 is set to surround the first range 81. In Figure 7, the second range 82 is set with a gap between it and the first range 81, but is not limited to this. The second range 82 may be adjacent to the first range 81.

[0082] The settings of the first range 81 and the second range 82 are not limited to these. The first range 81 may be a range set in the central part of the horizontal plane of the counter base 700, and the second range 82 may be a range set in the outer periphery of the horizontal plane of the counter base 700. The first range 81 may be a range set across the entire horizontal plane of the counter base 700, and the second range 82 may be a range set horizontally outside the counter base 700. The second range 82 is not limited to a range set to surround the first range 81.

[0083] The first range 81 and the second range 82 may be different ranges that do not overlap with each other, and are not limited to ranges separated horizontally. The first range 81 and the second range 82 may also be ranges separated vertically.

[0084] Next, we will explain an example of standard tag data. Figure 8 is a diagram illustrating the reference tag data for the communication device 10 according to the environment in which metal is placed.

[0085] The left side of Figure 8 shows an example of the arrangement of the reference wireless tag 800, and is a plan view of the counter stand 700 seen from above. The reference wireless tag 800 is positioned at a predetermined location on the counter base 700. For example, the predetermined location may be within a first range 81 and at the center position L / 2 of the scanning range of the antenna 300. The predetermined location may also be within a second range 82. The predetermined location can be set as appropriate.

[0086] This section explains the reference tag dataset. Here, phase data is used as an example of reference tag data. The graph on the right side of Figure 8 shows an example of multiple reference tag data for the reference radio tag 800 at multiple locations of the antenna 300 included in the reference tag dataset. The horizontal axis represents the position of antenna 300. Position L is assumed to be 600 mm. The vertical axis represents the phase. The graph shows the phase at each position a at a constant interval between position 0 and position L. The phase of the reference radio tag 800 changes as the position of the antenna 300 changes. This is because the distance between the antenna 300 and the reference radio tag 800 changes as the antenna 300 moves.

[0087] The processor 101 of the reading device 100 sequentially acquires reference tag data of the reference radio tag 800 at multiple locations on the antenna 300. For example, the multiple locations on the antenna 300 include locations a at a fixed interval between location 0 and location L, as described above. The multiple locations on the antenna 300 may also include one or more locations different from the locations a at a fixed interval between location 0 and location L. The processor 101 stores the acquired reference tag data in the reference tag data storage area 1111. The multiple reference tag data of the reference radio tag 800 at multiple locations on the antenna 300 constitute a reference tag dataset.

[0088] Figure 9 is a diagram illustrating the reference tag data for the communication device 10 according to the environment in which metal is placed. The left side of Figure 9 shows an example of the arrangement of the reference wireless tag 800, and is a plan view of the counter stand 700 seen from above. The reference wireless tag 800 is positioned in a predetermined location on the counter base 700, similar to the example in Figure 8. The two metal plates 900 are arranged around the communication device 10.

[0089] This section explains the reference tag dataset. Here, phase data is used as an example of reference tag data. The graph on the right side of Figure 9 shows an example of multiple reference tag data for the reference radio tag 800 at multiple locations of the antenna 300 included in the reference tag dataset. The horizontal axis represents the position of antenna 300. Position L is assumed to be 600 mm. The vertical axis represents the phase. The graph shows the phase at each position a at a constant interval between position 0 and position L. Comparing Figure 8 and Figure 9, the pattern of the reference tag dataset differs due to the influence of the metal plate 900. Thus, since the reference tag dataset is measured by the communication device 10, it differs depending on the environment of the communication device 10. For example, the reference tag dataset differs depending on the presence or absence of metal relative to the communication device 10. Even in an environment where metal is placed relative to the communication device 10, the reference tag dataset differs depending on the distance between the communication device 10 and the metal. Even in an environment where metal is placed relative to the communication device 10, the reference tag dataset differs depending on the position of the metal relative to the communication device 10.

[0090] Next, we will explain the process of acquiring reference tag data by the processor 101 of the reading device 100 configured as described above.

[0091] Figure 10 is a flowchart showing an example of the process by which the processor 101 of the reading device 100 acquires reference tag data. The processing procedure described below is merely an example, and each process may be modified as much as possible. Furthermore, depending on the embodiment, steps in the processing procedure described below may be omitted, replaced, or added as appropriate.

[0092] For example, a reference wireless tag 800 is assumed to be placed in a predetermined position on the counter base 700. The processor 101 of the reader 100 may start the reference tag data acquisition process based on the acquisition of a reference tag data start instruction entered by the user at the terminal 400. The user can input a reference tag data acquisition start instruction at the terminal 400 at any time. The user may input a reference tag data acquisition start instruction at the terminal 400 when the communication device 10 is installed. The user may input a reference tag data acquisition start instruction at the terminal 400 when there is a change in the environment of the communication device 10, such as the installation of the metal plate 900.

[0093] The movement control unit 1011 controls the movement of the antenna 300 (ACT1). In ACT1, for example, the movement control unit 1011 transmits a movement instruction to the drive unit 200. The movement instruction is an instruction to move the antenna 300 in one direction from position 0, which corresponds to the home position, to position L.

[0094] The processor 201 of the drive unit 200 receives a movement instruction from the reader 100. Based on the movement instruction, the processor 201 uses the home position sensor 206 to determine whether the antenna 300 is in the home position. If the antenna 300 is not in the home position, the processor 201 controls the drive unit 205 to move the antenna 300 to the home position. Based on the control by the processor 201, the drive unit 205 moves the antenna 300 to the home position. The processor 201 controls the drive unit 205 to start moving the antenna 300 from position 0, which corresponds to the home position. Based on the control by the processor 201, the drive unit 205 starts moving the antenna 300 from position 0. The processor 201 controls the drive unit 205 to move the antenna 300 in one direction from position 0 to position L. Based on the control by the processor 201, the drive unit 205 moves the antenna 300 in one direction from position 0 to position L.

[0095] The communication control unit 1012 controls the start of radio wave transmission from the antenna 300 (ACT2). In ACT2, for example, the communication control unit 1012 controls the start of radio wave transmission from the antenna 300 based on the start of movement of the antenna 300 from position 0. The communication control unit 1012 may also control the start of radio wave transmission from the antenna 300 based on a movement start notification from the drive unit 200. The movement start notification may indicate that the antenna 300 has started moving from position 0. The antenna 300 starts transmitting radio waves.

[0096] The acquisition unit 1013 acquires the reference tag data of the reference radio tag 800 (ACT3). In ACT3, the acquisition unit 1013 acquires the reference tag data of the reference radio tag 800 detected by the demodulation unit 110. If the acquisition unit 1013 acquires the reference tag data (ACT3, YES), the process transitions from ACT3 to ACT4. If the acquisition unit 1013 does not acquire the reference tag data (ACT3, NO), the process transitions from ACT3 to ACT5.

[0097] Based on the acquisition of reference tag data from the reference wireless tag 800, the acquisition unit 1013 stores the reference tag data in the reference tag data storage area 1111 (ACT4).

[0098] The communication control unit 1012 determines whether the movement of the antenna 300 has finished (ACT5). In ACT5, for example, the communication control unit 1012 determines whether the movement of the antenna 300 from position 0 to position L has finished. The communication control unit 1012 may also determine that the movement of the antenna 300 has finished based on a movement completion notification from the drive unit 200. The movement completion notification may indicate that the movement of the antenna 300 has finished upon reaching position L. If the movement of the antenna 300 has finished (ACT5, YES), the process transitions from ACT5 to ACT6. If the movement of the antenna 300 has not finished (ACT5, NO), the process transitions from ACT5 to ACT3.

[0099] The acquisition unit 1013 repeats the processes of ACT3 and ACT4 from the time the antenna 300 starts moving at position 0 until it finishes moving at position L. The movement of the antenna 300 from position 0 to position L is an example of the movement of the antenna 300 that is associated with one measurement process.

[0100] The acquisition unit 1013 acquires a reference tag dataset according to the environment of the communication device 10 by repeating the processing of ACT3. For example, the acquisition unit 1013 sequentially acquires reference tag data for the reference wireless tag 800 at some or all of the multiple positions of the antenna 300. The acquisition unit 1013 may also acquire reference tag data for the reference wireless tag 800 at some or all of the positions at a fixed interval a between position 0 and position L. The acquisition unit 1013 can acquire the position of the antenna 300 in cooperation with the drive unit 200.

[0101] The acquisition unit 1013 stores the reference tag dataset in the reference tag data storage area 1111 by repeating the processing of ACT4. For example, for the reference radio tag 800, the acquisition unit 1013 stores the reference tag data in the reference tag data storage area 1111 each time reference tag data is acquired. The acquisition unit 1013 stores the reference tag data in the reference tag data storage area 1111 in association with the position of the antenna 300. The acquisition unit 1013 may also store the reference tag data in the reference tag data storage area 1111 at some or all of the positions at a fixed interval a between position 0 and position L.

[0102] The communication control unit 1012 controls the termination of radio wave transmission from the antenna 300 (ACT6). In ACT6, for example, the communication control unit 1012 controls the termination of radio wave transmission from the antenna 300 based on the completion of the movement of the antenna 300 from position 0 to position L. The antenna 300 terminates radio wave transmission.

[0103] The output unit 1014 outputs the reference tag dataset to the terminal 400 (ACT7). In ACT7, for example, the output unit 1014 obtains the reference tag dataset from the reference tag data storage area 1111. The output unit 1014 outputs the reference tag dataset to the terminal 400 via the second connection interface 105.

[0104] Next, the selection process performed by the terminal 400 processor 401 configured as described above will be explained. The selection process is the process of selecting one trained model from multiple trained models according to the environment of the communication device 10.

[0105] Figure 11 is a flowchart showing an example of the selection process performed by the processor 401 of terminal 400. The processing procedure described below is merely an example, and each process may be modified as much as possible. Furthermore, depending on the embodiment, steps in the processing procedure described below may be omitted, replaced, or added as appropriate.

[0106] The processor 401 of terminal 400 may start the selection process based on the acquisition of a selection process start instruction entered by the user at terminal 400. The user can enter a selection process start instruction at terminal 400 at any time. The processor 401 of terminal 400 may start the selection process in conjunction with the reference tag data acquisition process described above. In this example, the reference tag data acquisition process start instruction may include the selection process start instruction.

[0107] The first acquisition unit 4011 acquires a reference tag dataset from the reader 100 according to the environment of the communication device 10 (ACT10). In ACT10, for example, the first acquisition unit 4011 acquires the reference tag dataset from the reader 100 via the connection interface 404. The first acquisition unit 4011 stores the reference tag dataset in the reference tag data storage area 4051.

[0108] The selection unit 4016 compares the reference tag dataset with multiple comparison reference tag datasets (ACT11). In ACT11, for example, the selection unit 4016 retrieves the reference tag dataset from the reference tag data storage area 4051. The selection unit 4016 compares the reference tag dataset with multiple comparison reference tag datasets stored in the comparison reference tag data storage area 4052.

[0109] The selection unit 4016 selects one comparison reference tag dataset from multiple comparison reference tag datasets based on the comparison. Selecting a comparison reference dataset based on the comparison is one example of selecting a comparison reference dataset based on a reference tag dataset. For example, the selection unit 4016 selects a comparison reference tag dataset associated with the environment of the communication device 10 that is closest to the environment of the communication device 10 associated with the reference tag dataset. The environment of the communication device 10 associated with the reference tag dataset is the environment of the communication device 10 that measured the multiple reference tag data included in the reference tag dataset. The environment of the communication device 10 associated with the comparison reference tag dataset is the environment of the communication device 10 that measured the multiple comparison reference tag data included in the comparison reference tag dataset. The selection unit 4016 may also select the comparison reference tag dataset that has the highest correlation with the reference tag dataset from multiple comparison reference tag datasets. The environment of the communication device 10 associated with the comparison reference tag dataset that has the highest correlation with the reference tag dataset is closest to the environment of the communication device 10 associated with the reference tag dataset.

[0110] The selection unit 4016 selects a trained model from a group of trained models according to the environment of the communication device 10 (ACT12). In ACT12, for example, the selection unit 4016 selects a trained model associated with the selected comparison reference tag dataset from the group of trained models. The selection unit 4016 sets the selected trained model as the trained model to be used.

[0111] As described above, the selection unit 4016 selects a comparison reference tag dataset based on a comparison between the reference tag dataset and multiple comparison reference tag datasets. Therefore, selecting a trained model associated with the selected comparison reference tag dataset is an example of selecting a trained model based on comparison. In this example, the selection unit 4016 selects a trained model from multiple trained models based on a comparison between the reference tag dataset and multiple comparison reference tag datasets.

[0112] As described above, selecting a reference dataset for comparison based on comparison is one example of selecting a reference dataset for comparison based on a reference tag dataset. Therefore, selecting a trained model based on comparison is one example of selecting a trained model based on a reference tag dataset. In this example, the selection unit 4016 selects a trained model from multiple trained models based on the reference tag dataset.

[0113] As described above, the reference tag dataset differs depending on the environment of the communication device 10. Therefore, selecting a trained model based on the reference tag dataset is an example of selecting a trained model according to the environment of the communication device 10 related to the reference tag dataset. In this example, the selection unit 4016 selects a trained model from multiple trained models according to the environment of the communication device 10.

[0114] Next, we will explain the process by which the processor 101 of the reading device 100 configured as described above acquires the tag data for determination.

[0115] Figure 12 is a flowchart showing an example of the process by which the processor 101 of the reading device 100 acquires tag data for determination. The processing procedure described below is merely an example, and each process may be modified as much as possible. Furthermore, depending on the embodiment, steps in the processing procedure described below may be omitted, replaced, or added as appropriate.

[0116] For example, suppose that an item 500, whose information stored in a wireless tag 600 is to be read, is placed on a counter stand 700. A wireless tag 600 attached to an item 500 placed on the counter stand 700 can be a wireless tag 600 to be determined. There may also be items in the vicinity of the counter stand 700 that are not to be read from the wireless tag 600. A wireless tag 600 attached to an item in the vicinity of the counter stand 700 can be a wireless tag 600 to be determined.

[0117] The processor 101 of the reading device 100 may start the process of acquiring judgment tag data based on the acquisition of an instruction to start the process of acquiring judgment tag data entered by the user at the terminal 400.

[0118] The movement control unit 1011 controls the movement of the antenna 300 (ACT20). The processing of ACT20 may be the same as the processing of ACT1.

[0119] The communication control unit 1012 controls the start of radio wave transmission from the antenna 300 (ACT21). The processing of ACT21 may be the same as the processing of ACT2.

[0120] The acquisition unit 1013 acquires the determination tag data for each wireless tag 600 to be determined (ACT22). In ACT22, the acquisition unit 1013 acquires the determination tag data for each wireless tag 600 to be determined, as detected by the demodulation unit 110. If the acquisition unit 1013 acquires the determination tag data (ACT22, YES), the process transitions from ACT22 to ACT23. If the acquisition unit 1013 does not acquire the determination tag data (ACT22, NO), the process transitions from ACT22 to ACT24.

[0121] The acquisition unit 1013 stores the determination tag data in the measurement data storage area 1112 based on the acquisition of determination tag data for each wireless tag 600 to be determined (ACT23).

[0122] The communication control unit 1012 determines whether the movement of the antenna 300 has finished (ACT24). The processing of ACT24 may be the same as the processing of ACT5. If the movement of the antenna 300 has finished (ACT24, YES), the process transitions from ACT24 to ACT25. If the movement of the antenna 300 has not finished (ACT24, NO), the process transitions from ACT24 to ACT22.

[0123] The acquisition unit 1013 repeats the processes of ACT22 and ACT23 from the time the antenna 300 starts moving at position 0 until it finishes moving at position L.

[0124] The acquisition unit 1013 acquires multiple determination tag datasets by repeating the processing of ACT22. For example, the acquisition unit 1013 sequentially acquires determination tag data at some or all of the multiple positions of the antenna 300 for each wireless tag 600 to be determined. The acquisition unit 1013 may also sequentially acquire determination tag data at some or all of the positions at a fixed interval a between position 0 and position L. The number of positions of the determination tag data measured by the communication device 10 may be the same or different for each wireless tag 600 to be determined. The acquisition unit 1013 can acquire the position of the antenna 300 in cooperation with the drive device 200.

[0125] The acquisition unit 1013 stores multiple determination tag datasets in the measurement data storage area 1112 by repeating the processing of ACT23. For example, the acquisition unit 1013 stores the determination tag data in the measurement data storage area 1112 each time it acquires determination tag data for each wireless tag 600 to be determined. The acquisition unit 1013 stores the determination tag data in the measurement data storage area 1112 in association with the position of the antenna 300. The acquisition unit 1013 may also store determination tag data in the measurement data storage area 1112 at some or all of the positions at a fixed interval a between position 0 and position L.

[0126] The communication control unit 1012 controls the termination of radio wave transmission from the antenna 300 (ACT25). The processing of ACT25 may be the same as the processing of ACT6.

[0127] The output unit 1014 outputs multiple judgment tag datasets to the terminal 400 (ACT26). In ACT26, for example, the output unit 1014 obtains multiple judgment tag datasets from the measurement data storage area 1112. The output unit 1014 outputs multiple judgment tag datasets to the terminal 400 via the second connection interface 105.

[0128] Next, the determination process performed by the processor 401 of the terminal 400 configured as described above will be explained. The determination process is the process of acquiring data indicating the range in which each wireless tag 600 to be determined exists.

[0129] Figure 13 is a flowchart showing an example of the determination process performed by the processor 401 of terminal 400. The processing procedure described below is merely an example, and each process may be modified as much as possible. Furthermore, depending on the embodiment, steps in the processing procedure described below may be omitted, replaced, or added as appropriate.

[0130] The processor 401 of terminal 400 may start the determination process based on the acquisition of a determination process start instruction entered by the user at terminal 400. The user can input a determination process start instruction at terminal 400 at any time. The processor 401 of terminal 400 may start the determination process in conjunction with the determination tag data acquisition process described above. In this example, the determination tag data acquisition process start instruction described above may include the determination process start instruction.

[0131] The first acquisition unit 4011 acquires multiple determination tag datasets from the reader 100 (ACT30). In ACT30, for example, the first acquisition unit 4011 acquires multiple determination tag datasets from the reader 100 via the connection interface 404. The first acquisition unit 4011 stores the multiple determination tag datasets in the measurement data storage area 4053.

[0132] The input unit 4012 inputs the judgment input data to the trained model selected by the selection unit 4016 from among multiple trained models according to the environment of the communication device 10 (ACT31). In ACT31, for example, the input unit 4012 acquires the judgment input data based on the measurement data stored in the measurement data storage area 4053. The input unit 4012 inputs the acquired judgment input data to the trained model selected by the selection unit 4016.

[0133] The second acquisition unit 4013 acquires judgment output data from the trained model based on the input of judgment input data to the trained model by the input unit 4012 (ACT32).

[0134] The output unit 4014 outputs the determination result, including the determination output data acquired by the second acquisition unit 4013, to another device (ACT33). The determination result may include information stored in each wireless tag 600 to be determined, which has been read by the reader 100. The other device may process the information stored in each wireless tag 600 to be determined, depending on whether each wireless tag 600 to be determined falls within the first range or the second range. The other device may process the information stored in each wireless tag 600 to be determined that falls within the first range. The other device does not have to process the information stored in each wireless tag 600 to be determined that falls within the second range. The terminal 400 may process the information stored in each wireless tag 600 to be determined, depending on whether each wireless tag 600 falls within the first range or the second range, instead of the other device. In this example, the processing in ACT33 may be omitted.

[0135] This section describes an example of measuring training tag data included in the training data used to generate a trained model. Here, we describe an example of measuring training tag data included in the training data corresponding to an environment where no metal is placed around the communication device 10. Similar examples may be used for training tag data included in other training data sets, and their explanations are omitted.

[0136] Figure 14 shows an example of the arrangement of multiple wireless tags 601-615 for learning purposes, and is a plan view of the counter stand 700 seen from above. The multiple wireless tags 601-615 for learning purposes are examples of wireless tag 600.

[0137] The wireless tags 601-615 are positioned on a virtual plane including the horizontal plane of the counter base 700, parallel to the vertical direction in which the antenna 300 moves. The wireless tags 601-605 are positioned at different locations from each other, and are included in the first range 81. The wireless tags 601-605 are positioned sequentially, moving away from position 0. As the antenna 300 moves from position 0 to position L, it passes through the wireless tags 601-605 in order, corresponding to each wireless tag.

[0138] The radio tags 606-610 are positioned at different locations from each other, but within the second range 82. The radio tags 606-610 are arranged in order, approaching position 0. Antenna 300 moves away from radio tags 606-610 while moving from position 0 to position L.

[0139] The radio tags 611-615 are positioned at different locations from each other, but within the second range 82. The radio tags 611-615 are positioned in order away from position L. The antenna 300 moves closer to the radio tags 611-615 as it moves from position 0 to position L.

[0140] Note that the number and arrangement of wireless tags for multiple learning targets are not limited to the example shown in Figure 14. It is sufficient if some of the wireless tags for multiple learning targets are placed in the first range 81 and the remaining wireless tags for multiple learning targets are placed in the second range 82.

[0141] This section describes multiple training tag data for wireless tags 601-615 at multiple locations on antenna 300. Here, phase data is used as an example of training tag data.

[0142] Figure 15 is a graph showing an example of multiple training tag data for wireless tags 601-605 at multiple locations on antenna 300. The horizontal axis represents the position of antenna 300. Position L is assumed to be 600 mm. The vertical axis represents the phase. The graph shows the phase for each of the wireless tags 601 to 605 at a fixed interval 'a' between position 0 and position L.

[0143] The phases of each of the wireless tags 601-605 change as the position of antenna 300 changes. This is because the distance between antenna 300 and each of the wireless tags 601-605 changes as antenna 300 moves. Regardless of the position of antenna 300, the phases of each of the wireless tags 601-605 are different. This is because the distance between antenna 300 and each of the wireless tags 601-605 is different.

[0144] Figure 16 is a graph showing an example of multiple training tag data for wireless tags 606-610 at multiple locations on antenna 300. The horizontal axis represents the position of antenna 300. Position L is assumed to be 600 mm. The vertical axis represents the phase. The graph shows the phase for each of the wireless tags 606 to 610 at a fixed interval 'a' between position 0 and position L.

[0145] The phases of each wireless tag 606-610 change as the position of antenna 300 changes. Regardless of the position of antenna 300, the phases of each wireless tag 606-610 are different.

[0146] Figure 17 is a graph showing an example of multiple training tag data for wireless tags 611-615 at multiple locations on antenna 300. The horizontal axis represents the position of antenna 300. Position L is assumed to be 600 mm. The vertical axis represents the phase. The graph shows the phase for each of the wireless tags 610 to 615 at a fixed interval 'a' between position 0 and position L.

[0147] The phases of each of the wireless tags 611-615 change as the position of antenna 300 changes. Regardless of the position of antenna 300, the phases of each of the wireless tags 611-615 are different.

[0148] We have explained the characteristics of phase data, and the same applies to the characteristics of radio wave reception strength data. The radio wave reception strength of each of the wireless tags 601 to 615 changes as the position of antenna 300 changes. This is because the distance between antenna 300 and each of the wireless tags 601 to 615 changes as antenna 300 moves. Regardless of the position of antenna 300, the radio wave reception strength of each of the wireless tags 601 to 615 will be different. This is because the distance between antenna 300 and each of the wireless tags 601 to 615 is different.

[0149] As described above, the processor 101 of the reader 100 acquires multiple training tag data for multiple wireless tags 600 to be trained at multiple locations on the antenna 300. This allows the processor 101 of the reader 100 to acquire multiple data sets for multiple wireless tags 600 to be trained. For example, the multiple locations on the antenna 300 include locations a at a fixed interval between location 0 and location L, as described above. The multiple locations on the antenna 300 may also include one or more locations different from the locations a at a fixed interval between location 0 and location L.

[0150] Figure 18 is a flowchart showing an example of the process by which the processor 401 of terminal 400 generates a trained model. This section describes an example of generating a trained model based on training data corresponding to an environment where no metal is placed around the communication device 10, among several trained models. Other trained model generation examples may be similar, and their explanations are omitted. The processing procedure described below is merely an example, and each process may be modified as much as possible. Furthermore, depending on the embodiment, steps in the processing procedure described below may be omitted, replaced, or added as appropriate.

[0151] The model processing unit 4015 may start the process of generating a trained model at any time and create a new trained model. The model processing unit 4015 may also start the process of generating a trained model at any time and update the trained model.

[0152] The model processing unit 4015 acquires training data (step S40). In step S40, the model processing unit 4015 acquires training data from the training data storage area 4054.

[0153] The model processing unit 4015 generates a trained model using machine learning based on the training data (step S41). In step S41, for example, the model processing unit 4015 trains the training data using machine learning. The model processing unit 4015 estimates the relationship between multiple datasets for multiple target wireless tags 600 and ground truth data indicating the range in which each of the target wireless tags 600 exists. Based on the estimation, the model processing unit 4015 generates a trained model. Machine learning is, but is not limited to, neural networks.

[0154] The training tag data for the target wireless tag 600, whether phase data or radio wave reception strength data, changes depending on the distance between the antenna 300 and the target wireless tag 600. The pattern of the dataset for the target wireless tag 600 differs for each location of the target wireless tag 600. There may be a certain correlation between the dataset for the target wireless tag 600 and the location of the wireless tag 600.

[0155] The model processing unit 4015 saves the generated trained model to the trained model memory area 4055 (step S42).

[0156] According to this embodiment, the selection device includes an acquisition unit that acquires tag data of a reference radio tag at multiple positions of the antenna measured by a communication device equipped with an antenna. The selection device includes a selection unit that selects a trained model from multiple trained models based on the tag data of the reference radio tag. The multiple trained models are models that are appropriate to the environment of the communication device and are models generated by machine learning based on multiple training data. The multiple training data includes tag data of multiple radio tags to be trained and data indicating the range in which each of the multiple radio tags to be trained exists. The selection device can improve the selection accuracy of the trained model according to the environment of the communication device by using the tag data of a reference wireless tag. Therefore, the selection device can improve the accuracy of the data indicating the range in which each wireless tag exists. In this way, the selection device can provide a technology that improves the accuracy of determining the location of wireless tags.

[0157] The selection unit selects a trained model from among several trained models based on a comparison between the tag data of a reference radio tag and multiple comparison tag data associated with multiple trained models. The selection device can improve the accuracy of selecting a trained model according to the communication device environment by using multiple comparison tag data associated with multiple trained models. Therefore, the selection device can improve the accuracy of data indicating the range in which each wireless tag exists.

[0158] The environment of the communication device includes the arrangement of metals relative to the communication device. The selection device can select a trained model according to the arrangement of metal relative to the communication device. Therefore, the selection device can improve the accuracy of the data indicating the range in which each wireless tag is located.

[0159] The tag data includes at least one of the following: phase data and radio wave reception intensity data. The selection device can improve the accuracy of the data indicating the range in which each wireless tag is located by using at least one of either phase data or radio wave reception intensity data.

[0160] The information processing system comprises a communication device and a selection device. The communication device comprises an antenna. The communication device comprises a drive unit for moving the position of the antenna. The communication device comprises an acquisition unit for acquiring tag data of a reference radio tag at multiple positions of the antenna. The communication device comprises an output unit for outputting the tag data of the reference radio tag to the selection device. The selection device comprises a first acquisition unit for acquiring the tag data of the reference radio tag from the communication device. The selection device comprises a selection unit for selecting a trained model from multiple trained models based on the tag data of the reference radio tag. The multiple trained models are models adapted to the environment of the communication device and are models generated by machine learning based on multiple training data. The multiple training data includes tag data of multiple radio tags and data indicating the range in which each of the multiple radio tags exists. The selection device can improve the selection accuracy of a trained model tailored to the communication device environment by using tag data from a reference wireless tag. Therefore, the selection device can improve the accuracy of data indicating the range in which each wireless tag exists. In this way, the information processing system can provide a technology that improves the accuracy of determining the location of wireless tags.

[0161] Modifications of this embodiment will now be described. An example has been described in which the processor 401 of terminal 400 implements a model processing unit 4015 that generates a trained model, but the example is not limited to this. The generation of the trained model may be implemented by a device other than terminal 400.

[0162] An example has been described in which the memory device 405 of terminal 400 stores multiple reference tag data, multiple training data, and multiple trained models, but it is not limited to this example. The multiple reference tag data, multiple training data, and multiple trained models may be stored in one or more devices different from terminal 400.

[0163] An example has been described in which the processor 401 of terminal 400 acquires decision output data through software processing, but it is not limited to this example. The communication system 1 may include an inference unit using a trained model. In this example, the input unit 4012 of the processor 401 inputs decision input data to the inference unit. Inputting decision input data from terminal 400 to the trained model includes transmitting the decision input data from terminal 400 to the inference unit. The second acquisition unit 4013 of the processor 401 acquires decision output data from the trained model based on the input of decision input data to the trained model. Acquiring decision output data from the trained model by terminal 400 includes receiving decision output data from the inference unit.

[0164] The communication device may be implemented using multiple devices as described in the example above, or it may be implemented using a single device that integrates the functions of multiple devices. The reader, drive device, and antenna may be implemented using a single device that integrates their functions. The reader may be implemented using multiple devices with distributed functions. The selection device may be implemented using a single device as described in the example above, or it may be implemented using multiple devices with distributed functions.

[0165] The program may be transferred while stored in the device according to the embodiment, or it may be transferred without being stored in the device. In the latter case, the program may be transferred via a network, or it may be transferred while recorded on a recording medium. The recording medium is a non-temporary tangible medium. The recording medium is a computer-readable medium. The recording medium can be any medium that is capable of storing a program and is readable by a computer, such as a CD-ROM or memory card, and its form is not limited.

[0166] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0167] 1...Communication system, 10...Communication device, 81...First range, 82...Second range, 100...Reader, 101...Processor, 102...ROM, 103...RAM, 104...First connection interface, 105...Second connection interface, 106...High frequency front end, 107...Digital amplitude modulation unit, 108...DA conversion unit, 109...AD conversion unit, 110...Demodulation unit, 111...Storage device, 112...Bus, 200...Drive unit, 201...Processor, 202...ROM, 203...RAM, 204...Connection interface, 205...Drive unit, 206...Home position sensor, 208...Bus, 211...Rotation axis, 212...Rail, 213...Moving stage, 300...Antenna, 400...Terminal, 401...Processor, 40 2...ROM, 403...RAM, 404...Connection interface, 405...Storage device, 406...Bus, 500...Item, 600...Wireless tag, 601~615...Wireless tag, 700...Counter stand, 800...Reference wireless tag, 900...Metal plate, 1011...Movement control unit, 1012...Communication control unit, 1013...Acquisition unit, 1014...Output unit, 1111...Reference tag data storage area, 1112...Measurement data storage area, 4011...First acquisition unit, 4012...Input unit, 4013...Second acquisition unit, 4014...Output unit, 4015...Model processing unit, 4016...Selection unit, 4051...Reference tag data storage area, 4052...Comparison reference tag data storage area, 4053...Measurement data storage area, 4054...Training data storage area, 4055...Trained model storage area.

Claims

1. An acquisition unit that acquires tag data of reference radio tags at multiple positions of the antenna measured by a communication device equipped with an antenna, A selection unit that selects a trained model from a plurality of trained models based on the tag data of the aforementioned reference wireless tag, Equipped with, The aforementioned multiple trained models are models adapted to the environment of the communication device, and are models generated by machine learning based on multiple training data. The aforementioned plurality of training data includes tag data of multiple wireless tags to be trained and data indicating the range in which each of the plurality of wireless tags to be trained exists. Selection device.

2. The selection device according to claim 1, wherein the selection unit selects a trained model from the plurality of trained models based on a comparison between the tag data of the reference wireless tag and a plurality of comparison tag data associated with the plurality of trained models.

3. The selection device according to claim 1 or 2, wherein the environment of the communication device includes the arrangement of metal relative to the communication device.

4. The selection device according to any one of claims 1 to 3, wherein the tag data includes at least one of phase data and radio wave reception intensity data.

5. An information processing system comprising a communication device and a selection device, The aforementioned communication device is Antenna and, A drive unit for moving the position of the aforementioned antenna, An acquisition unit that acquires tag data of reference radio tags at multiple positions of the antenna; and an output unit that outputs the tag data of the reference radio tags to the selection device. Equipped with, The aforementioned selection device is A first acquisition unit that acquires tag data of the aforementioned reference wireless tag from the communication device, A selection unit that selects a trained model from a plurality of trained models based on the tag data of the aforementioned reference wireless tag, Equipped with, The aforementioned multiple trained models are models adapted to the environment of the communication device, and are models generated by machine learning based on multiple training data. The aforementioned plurality of training data includes tag data of multiple wireless tags to be trained and data indicating the range in which each of the plurality of wireless tags to be trained exists. Information processing system.

Images