Determination device, determination system, determination method, and recording medium

Abstract

This determination device comprises: a signal information acquisition means that acquires signal information from an RFID tag provided on a product carried by a customer when reading product identification information in the RFID tag by means of a reading device provided at a gate through which the customer passes; a determination means that uses a plurality of trained models set in accordance with the conditions of the environment in which the reading device is installed to acquire a determination result that indicates, on the basis of the signal information, whether or not the product was purchased by the customer; and an output control means that causes the determination result to be outputted.

Description

Determination device, determination system, determination method, and recording medium

[0001] The present disclosure relates to a determination device, a determination system, a determination method, and a recording medium.

[0002] There are devices that obtain information about products purchased by customers by reading items in a shopping cart with a determination device installed at the gate. Such devices can sometimes lose accuracy in reading product information due to changes in the store environment. There is a demand for them to maintain a certain level of reading accuracy even when the store environment changes.

[0003] For example, Patent Document 1 discloses that when the layout of a store is changed, the judgment criteria of a classifier are retrained in accordance with the environment in which the product is placed.

[0004] Japanese Patent Application Laid-Open No. 2021-47723

[0005] However, if re-learning is performed every time the environment changes, as in the invention described in Patent Document 1, it takes time to re-learn.

[0006] An example of an object of the present disclosure is to provide a determination device that can improve the accuracy of determining whether or not a customer who has passed through a gate has purchased an item, without taking time for relearning.

[0007] A determination device in one aspect of the present disclosure includes a signal information acquisition means for acquiring signal information from an RFID tag when a reading device installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product held by the customer; a determination means for obtaining a determination result as to whether or not the product is purchased by the customer based on the signal information using a plurality of trained models set according to the environmental conditions in which the reading device is installed; and an output control means for outputting the determination result.

[0008] In one aspect of the present disclosure, a determination method involves a computer acquiring signal information from an RFID tag attached to a product held by a customer when the computer uses a reading device installed at a gate through which the customer passes to read product identification information in the RFID tag, and using multiple trained models configured according to the environmental conditions in which the reading device is installed, obtaining a determination result as to whether the product is purchased by the customer based on the signal information, and outputting the determination result.

[0009] In one aspect of the present disclosure, a recording medium acquires signal information from the RFID tag when a reading device installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product carried by the customer, and obtains a determination result as to whether the product is purchased by the customer based on the signal information using multiple trained models configured according to the environmental conditions in which the reading device is installed, and outputs the determination result.

[0010] According to the present disclosure, it is possible to provide a determination device that can improve the accuracy of determining whether or not a product is purchased by a customer who has passed through a gate, without taking time for relearning.

[0011] FIG. 1 is a block diagram showing an example configuration of a determination system according to the present disclosure. FIG. 2 is a schematic diagram showing an example of a gate according to the present disclosure. FIG. 3 is a diagram showing a hardware configuration in which a determination device according to the present disclosure is realized by a computer device and its peripheral devices. FIG. 4 is a diagram for explaining a trained model trained for each environmental condition of a reading device according to the present disclosure. FIG. 5 is a diagram for explaining a trained model trained for each environmental condition of a reading device according to the present disclosure. FIG. 6 is a flowchart showing a determination operation according to the present disclosure. FIG. 7 is a block diagram showing an example configuration of a determination system according to the present disclosure. FIG. 8 is a flowchart showing a determination operation according to the present disclosure.

[0012] Hereinafter, embodiments of a determination device, a determination system, a determination method, and a non-transitory recording medium for recording a program according to the present disclosure will be described in detail with reference to the drawings. The disclosed technology is not limited to these embodiments.

[0013] 1 is a block diagram showing an example of a configuration including a determination device 100 according to the present disclosure. As shown in Fig. 1, in the determination system 10, the determination device 100 is connected to a reading device 200 and an output device 300 via a network.

[0014] The determination device 100 is a device that determines whether or not a customer will purchase a product based on product identification information in an RFID (Radio Frequency Identification) tag attached to the product read by the reading device 200. The reading device 200 is a sensor for reading product identification information of a product to be purchased by a customer passing through a gate. The output device 300 is a device that outputs information on a product determined to be purchased by the customer, and is, for example, a display installed near the exit of the gate or a display on the customer's terminal. The store in the present disclosure is, for example, a retail store that sells clothing, food, etc.

[0015] (Gate) FIG. 2 is a schematic diagram illustrating an example of a gate in the present disclosure. Gate 1 as shown in FIG. 2 is provided, for example, near the exit of a store. Gate 1 is provided with a reading device 200. Reading device 200 has an RFID reader 201 and an antenna 202. The gate shown in FIG. 2 is a walk-through gate in which, as a customer walks through aisle A within gate 1, reading device 200 reads product identification information stored in an RFID tag attached to a product P carried by the customer. Note that, in the example gate shown in FIG. 2, two antennas 202 are provided on each side of aisle A near the center of the gate in the direction of travel, but the number of antennas 202 is not limited to the example configuration shown in FIG. 2.

[0016] The RFID reader 201 of the reading device 200 is a control circuit that communicates with an RFID tag via an antenna 202 in accordance with a predetermined communication protocol and reads the product identification information stored in the RFID tag. The antenna 202 is installed in a position where it can transmit and receive radio waves to and from an RFID tag passing through the gate 1, and transmits radio waves to the RFID tag and receives radio waves transmitted from the RFID tag. The antenna 202 may be provided as a separate antenna for transmission and a separate antenna for reception.

[0017] In the example of gate 1 in FIG. 2 , output device 300 may be provided near the exit of gate 1 and configured to output a list of products determined to be purchased. Purchased products are products that a customer passing through gate 1 is carrying and intends to purchase. Furthermore, a configuration may be provided in which, when it is detected that a customer has exited gate 1, payment processing for products determined to be purchased is performed using pre-registered payment information. Furthermore, a determination device 100 may be provided at gate 1. In this case, the determination result can be output without communication between gate 1 and determination device 100 via a network.

[0018] Returning to FIG. 1 , the determination device 100 includes a signal information acquisition unit 101, a determination unit 102, and an output control unit 103. FIG. 3 is a diagram illustrating an example of a hardware configuration in which the determination device 100 according to the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 3 , the determination device 100 includes a CPU (Central Processing Unit) 501, memories such as a ROM (Read Only Memory) 502 and a RAM (Random Access Memory) 503, a storage device 505 such as a hard disk for storing a program 504, a communication interface 508 for network connection, and an input / output interface 509 for inputting and outputting data. The determination device 100 is also connected to each component via a bus 510. The determination device 100 shown in FIG. 1 can also be configured using cloud computing or the like.

[0019] The CPU 501 runs an operating system to control the entire determination device 100 according to the present disclosure. The CPU 501 also reads programs and data into memory from a recording medium 506 mounted in, for example, a drive device 507. The CPU 501 also functions as the signal information acquisition unit 101, the determination unit 102, and the output control unit 103 according to the present disclosure, or as part of these, and executes processing or commands in the flowchart shown in FIG. 6, which will be described later, based on the program.

[0020] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. The semiconductor memory or the like that is part of the recording medium is a non-volatile storage device that stores the program. The program may also be downloaded from an external computer (not shown) that is connected to a communication network.

[0021] As described above, the first embodiment shown in Fig. 1 is realized by the computer hardware shown in Fig. 3. However, the means for realizing each component included in the determination device 100 in Fig. 1 is not limited to the configuration described above. The determination device 100 may be realized by a single physically coupled device, or may be realized by a system consisting of two or more physically separated devices connected by wire or wirelessly.

[0022] The signal information acquisition unit 101 is a means for acquiring signal information from an RFID tag when a reader 200 installed at a gate 1 through which a customer passes reads commodity identification information stored in an RFID tag attached to a commodity carried by a customer. The signal information is information related to the state of the signal at the time of reading. The signal information acquisition unit 101 acquires signal strength by measuring the received signal strength indicator (RSSI) value from the RFID tag received by the antenna 202 at the timing when the reader 200 reads the commodity identification information. While the present specification describes a case where the signal information is an RSSI value, the signal information is not limited to the RSSI value and may also include a maximum RSSI value, a minimum RSSI value, etc. Furthermore, the signal information may also include the number of times the reader 200 reads each unit of commodity identification information, the reading time, and the number of antennas 202 that have successfully read the EPC (Electronic Product Code) stored in the RFID tag.

[0023] The determination unit 102 is a means for obtaining a determination result as to whether or not a product is purchased by a customer based on signal information, using multiple trained models set according to the environmental conditions in which the reading device 200 is installed. In the determination device 100 of the present disclosure, multiple trained models tuned under the environmental conditions in which the reading device 200 is installed are stored in advance in the storage device 505. Tuning refers to selecting a trained model and setting a usage method for the selected multiple trained models so that the determination results are consistent under the environmental conditions in which the reading device 200 is installed. Setting the usage method refers to integrating results calculated using multiple trained models according to the environmental conditions, or preparing an integrated model that integrates parameters of multiple trained models according to the environmental conditions.

[0024] The selection or use of a trained model may use a rule set derived from past tuning cases using generative AI (artificial intelligence) technology. More specifically, a hypothesis for a combination of multiple rules is output by inputting, as a prompt for an existing trained model, text information regarding multiple rule combinations and environmental conditions suitable for the combinations, and an instruction text for outputting a combination of multiple rules that matches the current environmental conditions. If the hypothesis is appropriate, the obtained combination of multiple rules is selected as the trained model to be used for judgment. If multiple appropriate trained models are obtained, an integrated model is created by integrating parameters of the multiple trained models for data after a change in environmental conditions occurs, and a trained model with a judgment result accuracy above a predetermined level is selected.

[0025] (Trained Model) The trained model in the present disclosure is a model generated by machine learning the correlation between the characteristics of signal information from an RFID tag when the reading device 200 reads product identification information under specified environmental conditions and whether the product is purchased or not, and is expressed, for example, by a mathematical formula using the signal information from the RFID tag as an explanatory variable. Furthermore, each of the multiple trained models is a model that learns the correlation by inputting multiple sets of training data sets including signal information obtained under different environmental conditions of the reading device 200 and results of whether the product is purchased or not. The trained model may be a black-box model using deep learning, or a white-box model such as a single decision tree and decision rule or a combination thereof.

[0026] The signal information includes an RSSI value indicating the signal strength of the read product identification information, the number of times the product identification information has been read, the reading time, the number of antennas 202 that have read the EPC stored in the RFID tag, attribute information of the product to which the RFID tag is attached, etc. The trained model may be a model expressed as a mathematical formula using multiple pieces of signal information from the above-mentioned signal information.

[0027] Examples of environmental conditions include the store environment where the reading device 200 is installed, the weather, and the radio wave environment. Examples of the store environment include the store location (e.g., a street store or a store in a mall), the store ceiling height, the material of the store floor or ceiling, the layout of the product shelves, or how crowded the store is. Examples of the radio wave environment include the position of the antenna inside the gate, the number of antennas, the material of the shopping cart, or the material of the product to which the RFID tag is attached.

[0028] The trained model is generated by a learning means of the determination device 100 or a device other than the determination device 100. The learning algorithm may be any machine learning method such as a neural network, a support vector machine (SVM), or logistic regression.

[0029] The signal information received from the RFID tag when reading the product identification information stored in the RFID tag varies depending on the environmental conditions of the reader 200. Using FIGS. 4 and 5 , we will explain the trained models trained for each environmental condition of the reader 200. FIG. 4 shows a graph of the evolution of RSSI values ​​when a customer passes through gate 1 when a trained model trained under the environmental conditions of the reader 200 is used. FIG. 5 shows a graph of the evolution of RSSI values ​​when a customer passes through gate 1 when a trained model similar to that of FIG. 4 is used under different environmental conditions. As shown in FIG. 4 , when a trained model trained under the environmental conditions of the reader 200 is used, it is easy to distinguish between the graphs of RSSI values ​​for tag A inside gate 1 and tag B outside gate 1. In contrast, when a trained model not trained under the environmental conditions of the reader 220 is used, as shown in FIG. 5 , it is difficult to distinguish between the graphs of RSSI values ​​for tag A inside gate 1 and tag B outside gate 1. Similarly, even in a trained model using signal information other than RSSI values, tuning the trained model by training it for each environmental condition of the reader 200 makes it easier to distinguish between signal information when an RFID tag inside a gate and signal information when an RFID tag outside a gate is read. However, in the actual installation environment of the reader 200, the determination result is affected by multiple environmental conditions such as weather and radio wave conditions. For this reason, the determination device 100 of the present disclosure assembles trained models trained under different environmental conditions to improve the accuracy of the determination result of whether or not a product is purchased.

[0030] The determination unit 102 is a means for obtaining a determination result as to whether or not an item is a purchased item for a customer based on signal information, using multiple trained models configured according to the environmental conditions in which the reading device 200 is installed. The determination unit 102 obtains a determination result, for example, by integrating the results of determining whether or not an item is a purchased item using each of the multiple trained models according to the environmental conditions. In this case, the determination unit 102 integrates the results calculated by each trained model. The method for integrating the results output by each trained model is not particularly limited, and the determination result may be obtained by, for example, simple averaging or weighted averaging. In this case, the determination unit 102 determines whether or not an item is a purchased item based on whether the average output exceeds a predetermined threshold. Furthermore, the determination result may be obtained by majority voting or weighted majority voting on the determination results of the multiple trained models.

[0031] The determination unit 102 may use an integrated model in which parameters of multiple trained models are integrated according to environmental conditions to obtain a determination result of whether or not the product is purchased by the customer based on the signal information. In this case, the determination unit 102 uses an integrated model in which parameters of multiple trained models are integrated. A known method can be used to integrate the parameters. For example, when integrating, the weights of the parameters corresponding to each trained model may be changed depending on the characteristics of each trained model.

[0032] The output control unit 103 is a means for outputting the determination result. The output control unit 103 may output a screen listing the products determined to be purchased by the customer. The output control unit 103 outputs the list of purchased products to, for example, the output device 300 or the customer's mobile terminal.

[0033] 6 is a flowchart showing an outline of the operation of the determination device 100 according to the present disclosure. The processing according to this flowchart may be executed based on program control by the processor described above. The determination device 100 may start the flow according to this flowchart, for example, when the signal information received from the reading device 200 is equal to or greater than a predetermined value.

[0034] As shown in Fig. 6, first, the traffic light information acquisition unit 101 acquires traffic light information from the RFID tag when the reader 200 installed at the gate 1 through which the customer passes reads the product identification information stored in the RFID tag attached to the product carried by the customer (step S101). Next, the determination unit 102 acquires a determination result as to whether the product is the one purchased by the customer based on the traffic light information, using multiple trained models configured according to the environmental conditions in which the reader 200 is installed (step S102). Finally, the output control unit 103 outputs the determination result (step S103). This concludes the flow of the determination device 100.

[0035] In the determination device 100 of this embodiment, the determination unit 102 obtains a determination result as to whether or not a product has been purchased by a customer based on traffic light information, using multiple trained models set according to the environmental conditions in which the reading device 200 is installed. This allows for determination using, for example, multiple trained models set in advance according to the environmental conditions. This makes it possible to improve the accuracy of determining whether or not a product has been purchased by a customer who has passed through gate 1, without taking time for re-learning.

[0036] [Second Embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Fig. 7 is a block diagram showing a determination system 11 according to the present disclosure. In the determination system 11, similar to the determination system 10, a determination device 110 is connected to a reading device 210 and an output device 310 via a network.

[0037] In the following, the description of the present embodiment will be omitted to the extent that the description thereof does not become unclear. The functions of each component in each embodiment of the present disclosure can be realized not only by hardware but also by a computer device or software under program control, similar to the computer device shown in FIG.

[0038] 7, the determination device 110 includes a signal information acquisition unit 111, an environmental condition acquisition unit 112, a setting unit 113, a determination unit 114, and an output control unit 115. The determination unit 114 and the output control unit 115 are similar to the corresponding components in the first embodiment, and therefore description thereof will be omitted.

[0039] The configuration of the signal information acquisition unit 111 is basically the same as the corresponding configuration in the first embodiment, but the signal information acquisition unit 111 outputs the acquired signal information to the environmental condition acquisition unit 112 and the determination unit 114 .

[0040] The environmental condition acquisition unit 112 is a means for acquiring the environmental conditions in which the reading device 210 is installed. In the present disclosure, for example, the gate 1 is equipped with a sensor for acquiring the environmental conditions. Examples of the sensor include a temperature sensor, a humidity sensor, and a distance sensor that measures the height to the ceiling. Signal information received by the reading device 210 may be used as the sensor. The sensor is not limited to these, as long as it is a sensor that can measure the environmental conditions of the store. The environmental conditions input by a store clerk may also be acquired. The environmental condition acquisition unit 112 outputs the acquired environmental conditions to the setting unit 123.

[0041] The setting unit 113 is a means for setting multiple trained models according to environmental conditions. The setting method is the same as that of the first embodiment. That is, the setting unit 113 selects a trained model and sets a usage method for the selected multiple trained models so that the determination results are consistent under the environmental conditions in which the reading device 210 is installed. Setting the usage method means integrating results calculated using multiple trained models according to the environmental conditions, or preparing an integrated model that integrates parameters of multiple trained models according to the environmental conditions. The setting unit 113 may set the selection or usage method for the multiple trained models selected by the generation AI.

[0042] The determination unit 114 uses the multiple trained models that have been set to obtain a determination result as to whether or not the product is purchased by the customer based on the signal information.

[0043] In the present disclosure, the environmental condition acquisition unit 112 acquires the environmental conditions in which the reading device 210 is installed. Then, the setting unit 113 sets multiple trained models according to the environmental conditions, and the determination unit 114 uses the set multiple trained models to obtain a determination result on whether or not the product is a purchase by the customer based on the signal information. This makes it possible to use multiple trained models set according to the environmental conditions after the environmental conditions have changed. This improves the accuracy of the determination.

[0044] Furthermore, in the present disclosure, when the signal information input from the signal information acquisition unit 111 is less than a predetermined threshold, the environmental condition acquisition unit 112 may acquire the environmental conditions in which the reading device 210 is installed. The threshold is a value for determining the read commodity identification information, which is set according to the environmental conditions or the specifications of the RFID tag. As a result, when a certain level of accuracy in reading the commodity identification information is ensured, the multiple trained models can be used as is without changing the settings.

[0045] 8 is a flowchart showing an outline of the operation of the determination device 110 according to the present disclosure. The processing according to this flowchart may be executed based on program control by the processor described above. The determination device 110 may start the flow according to this flowchart, for example, when the signal information received from the reading device 210 is equal to or greater than a predetermined value.

[0046] As shown in FIG. 8 , first, the traffic light information acquisition unit 111 acquires traffic light information from the RFID tag when the reader 210 installed at the gate 1 through which the customer passes reads the product identification information stored in the RFID tag attached to the product carried by the customer (step S201). Next, if the traffic light information is less than a predetermined threshold (YES in step S202), the environmental condition acquisition unit 112 acquires the environmental conditions in which the reader 210 is installed (step S203). Next, the setting unit 113 sets multiple trained models according to the environmental conditions (step S204). Next, the determination unit 114 acquires a determination result of whether the product is the one purchased by the customer based on the traffic light information using the multiple trained models set according to the environmental conditions in which the reader 210 is installed (step S205). Finally, the output control unit 115 outputs the determination result (step S206). On the other hand, if the signal information is not less than the predetermined threshold (S202; NO), the environmental condition acquisition unit 112 acquires the determination result without changing the settings of the multiple trained models (step S207), and the output control unit 115 outputs the determination result (step S206).

[0047] Although the present disclosure has been described above with reference to various embodiments, the present disclosure is not limited to the above embodiments. The configurations and details of each of the present disclosures include embodiments to which various modifications that would be understood and acquired by those skilled in the art within the scope of the present disclosure are applied. The present disclosure also includes embodiments in which the matters described herein are appropriately combined or substituted as necessary. For example, matters described using a specific embodiment may also be applied to other embodiments to the extent that no contradiction occurs. For example, although multiple operations are described in sequence in the form of a flowchart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed as long as it does not interfere with the content.

[0048] Some or all of the above-described embodiments can be described as follows: However, some or all of the above-described embodiments are not limited to the following.

[0049] (Supplementary Note 1) A determination device comprising: a signal information acquisition means for acquiring signal information from an RFID tag when a reading device installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product held by the customer; a determination means for obtaining a determination result as to whether the product is a purchase of the customer based on the signal information using a plurality of trained models set according to the environmental conditions in which the reading device is installed; and an output control means for outputting the determination result.

[0050] (Supplementary Note 2) The determination device according to Supplementary Note 1, wherein the determination means acquires a determination result by integrating results of determining whether or not the product is a purchase product using each of a plurality of trained models in accordance with the environmental conditions.

[0051] (Supplementary Note 3) The determination device according to Supplementary Note 1, wherein the determination means obtains a determination result as to whether the product is a purchased product of the customer based on the signal information using an integrated model that integrates parameters of multiple trained models according to the environmental conditions.

[0052] (Supplementary Note 4) The determination device according to any one of Supplementary Note 1 to Supplementary Note 3, wherein the environmental conditions include at least one of a store environment in which the reading device is installed, weather, and a radio wave environment of the reading device.

[0053] (Supplementary Note 5) The determination device according to any one of Supplementary Notes 1 to 4, wherein the trained models are models generated by machine learning the correlation between the characteristics of the signal information and whether the product is a purchased product under different environmental conditions of the reading device.

[0054] (Supplementary Note 6) The determination device according to Supplementary Note 5, wherein each of the trained models is a model that re-learns the correlation by inputting a plurality of sets of training data sets including the signal information obtained under different environmental conditions of the reading device and the results of whether the product is a purchased product.

[0055] (Supplementary Note 7) A determination device as described in any of Supplementary Notes 1 to 6, further comprising: an environmental condition acquisition means for acquiring the environmental conditions in which the reading device is installed; and a setting means for setting a plurality of trained models according to the environmental conditions, wherein the determination means uses the set plurality of trained models to obtain a determination result as to whether or not the product is a purchased product of the customer based on the signal information.

[0056] (Supplementary Note 8) The determination device according to Supplementary Note 7, wherein the environmental condition acquisition means acquires an environmental condition in which the reading device is installed when the signal information is less than a predetermined threshold value.

[0057] (Supplementary Note 9) The determination device according to any one of Supplementary Note 1 to Supplementary Note 8, wherein the output control means further outputs a screen showing a list of products determined to be purchased by the customer.

[0058] (Supplementary Note 10) A determination system comprising: a gate through which a customer passes; and a determination device according to any one of Supplementary Note 1 to Supplementary Note 9, which is provided at the gate.

[0059] (Supplementary Note 11) A determination method in which a computer acquires signal information from an RFID tag when a reading device installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product held by the customer, and obtains a determination result as to whether the product is a purchase of the customer based on the signal information using a plurality of trained models set according to the environmental conditions in which the reading device is installed, and outputs the determination result.

[0060] (Supplementary Note 12) The determination method according to claim 11, wherein the determination result is obtained by integrating results of determining whether or not the product is a purchase product using each of a plurality of trained models according to the environmental conditions.

[0061] (Supplementary Note 13) The determination method according to Supplementary Note 11, wherein a determination result as to whether or not the product is a purchased product of the customer is obtained based on the signal information using an integrated model in which parameters of multiple trained models are integrated according to the environmental conditions.

[0062] (Supplementary Note 14) The determination method according to any one of Supplementary Note 11 to Supplementary Note 13, wherein the environmental conditions include at least one of a store environment in which the reading device is installed, weather, and a radio wave environment of the reading device.

[0063] (Supplementary Note 15) The determination method according to any one of Supplementary Notes 11 to 14, wherein the trained models are models generated by machine learning the correlation between the characteristics of the signal information and whether or not the product is a purchased product under different environmental conditions of the reading device.

[0064] (Supplementary Note 16) The determination method according to Supplementary Note 15, wherein each of the trained models is a model that re-learns the correlation by inputting a plurality of sets of training datasets including the signal information obtained under different environmental conditions of the reading device and the results of whether the product is a purchased product.

[0065] (Supplementary Note 17) The determination method described in any one of Supplementary Notes 11 to 16 further includes acquiring environmental conditions in which the reading device is installed, setting multiple trained models according to the environmental conditions, and using the set multiple trained models, obtaining a determination result as to whether the product is a purchased product of the customer based on the signal information.

[0066] (Supplementary Note 18) The determination method according to Supplementary Note 17, further comprising acquiring an environmental condition in which the reading device is installed if the signal information is less than a predetermined threshold.

[0067] (Supplementary Note 19) The determination method according to any one of claims 11 to 18, further comprising outputting a screen showing a list of products determined to be purchased by the customer.

[0068] (Supplementary Note 20) A recording medium storing a program that causes a computer to execute the following process: when a reading device installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product held by the customer, acquires signal information from the RFID tag; uses a plurality of trained models set according to the environmental conditions in which the reading device is installed to acquire a determination result as to whether the product is a purchase of the customer based on the signal information; and outputs the determination result.

[0069] Some or all of the configurations described in Supplements 2 to 9 that are dependent on Supplement 1 described above are also dependent on Supplement 11 and Supplement 20 in the same dependent relationship as Supplements 2 to 9. Not limited to Supplements 1, 11, and 20, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording devices for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0070] 10, 11 Determination system 100, 110 Determination device 101, 111 Signal information acquisition unit 102, 114 Determination unit 103, 115 Output control unit 112 Environmental condition acquisition unit 113 Setting unit 200, 210 Reading device 300, 310 Output device 500 Computer device 501 CPU 502 ROM 503 RAM 504 Program 505 Storage device 506 Recording medium 507 Drive device 508 Communication interface 509 Input / output interface 510 Bus

Claims

1. A determination device comprising: a signal information acquisition means for acquiring signal information from an RFID tag when a reader installed at a gate through which a customer passes reads product identification information stored in an RFID tag attached to a product held by the customer; a determination means for obtaining a determination result as to whether or not the product is a purchase of the customer based on the signal information using a plurality of trained models set according to the environmental conditions in which the reader is installed; and an output control means for outputting the determination result.

2. The determination device according to claim 1, wherein the determination means obtains a determination result by integrating the results of determining whether or not a product is a purchase product using each of a plurality of trained models in accordance with the environmental conditions.

3. The determination device according to claim 1, wherein the determination means uses an integrated model that integrates parameters of multiple trained models according to the environmental conditions to obtain a determination result as to whether or not the product is purchased by the customer based on the signal information.

4. A determination device according to any one of claims 1 to 3, wherein the environmental conditions include at least one of the store environment in which the reading device is installed, the weather, and the radio wave environment of the reading device.

5. A determination device as claimed in any one of claims 1 to 4, wherein the trained models are models generated by machine learning the correlation between the characteristics of the signal information and whether or not the product is a purchased product under different environmental conditions of the reading device.

6. The determination device described in claim 5, wherein each of the trained models is a model that re-learns the correlation by inputting multiple sets of training data sets including the signal information obtained under different environmental conditions of the reading device and the results of whether the product is purchased or not.

7. A determination device as described in any one of claims 1 to 6, further comprising: an environmental condition acquisition means for acquiring the environmental conditions in which the reading device is installed; and a setting means for setting a plurality of trained models according to the environmental conditions, wherein the determination means uses the plurality of trained models that have been set to obtain a determination result as to whether or not the product is a purchased product of the customer based on the signal information.

8. The determination device according to claim 7, wherein said environmental condition acquisition means acquires the environmental conditions in which said reading device is installed when said signal information is less than a predetermined threshold value.

9. The determination device according to any one of claims 1 to 8, wherein the output control means further outputs a screen showing a list of products determined to be purchased by the customer.

10. A determination system comprising a gate through which customers pass and a determination device according to any one of claims 1 to 9 provided at the gate.

11. A determination method in which a computer acquires signal information from an RFID tag when the product identification information in an RFID tag attached to a product held by a customer is read by a reading device installed at a gate through which the customer passes, and obtains a determination result as to whether the product is the one purchased by the customer based on the signal information using multiple trained models set according to the environmental conditions in which the reading device is installed, and outputs the determination result.

12. The determination method according to claim 11, wherein the determination result is obtained by integrating the results of determining whether or not a product is a purchase product using each of a plurality of trained models in accordance with the environmental conditions.

13. The determination method described in claim 11, wherein a determination result as to whether or not the product is purchased by the customer is obtained based on the signal information using an integrated model in which parameters of multiple trained models are integrated according to the environmental conditions.

14. A determination method according to any one of claims 11 to 13, wherein the environmental conditions include at least one of the store environment in which the reading device is installed, the weather, and the radio wave environment of the reading device.

15. A determination method according to any one of claims 11 to 14, wherein the trained models are models generated by machine learning the correlation between the signal information and whether or not the product is a purchased product under different environmental conditions of the reading device.

16. The determination method described in claim 15, wherein each of the trained models is a model that re-learns the correlation by inputting multiple sets of training datasets including the signal information obtained under different environmental conditions of the reading device and the results of whether the product is a purchased product or not.

17. A determination method according to any one of claims 11 to 16, further comprising: acquiring environmental conditions in which the reading device is installed; setting multiple trained models according to the environmental conditions; and using the set multiple trained models, obtaining a determination result as to whether or not the product is a purchased product of the customer based on the signal information.

18. The determination method according to claim 17, further comprising acquiring an environmental condition in which the reading device is installed if the signal information is less than a predetermined threshold.

19. The determination method according to any one of claims 11 to 18, further comprising outputting a screen showing a list of products determined to be purchased by the customer.

20. A recording medium storing a program that causes a computer to execute the following process: when a reader installed at a gate through which a customer passes reads product identification information in an RFID tag attached to a product held by said customer, acquires signal information from said RFID tag, and, using multiple trained models set according to the environmental conditions in which said reader is installed, obtains a determination result as to whether or not the product is the one purchased by said customer based on said signal information, and outputs the determination result.

Images