Determination apparatus, determination method, and determination program
Patent Information
- Application Number
- JP2023074697
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-28
- Publication Date
- 2024-11-08
AI Technical Summary
【0008】 本発明の一態様によれば、特殊詐欺のリスクを高精度に検知することができる。
Smart Images

Figure 2024158998000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a determination device, a determination method, and a determination program. [Background technology]
[0002] Even if a store clerk witnesses a customer's actions suspected of being a victim of a specialized fraud, such as purchasing a high-value prepaid card at a convenience store or operating an ATM (Asynchronous Transfer Mode) while talking on the phone, the clerk often hesitates to speak to the customer so as not to mistake it for a specialized fraud or not listen to the customer. As a technology for detecting the risk of specialized fraud, for example, a technology for detecting the risk of specialized fraud using the telephone (see Patent Document 1, for example) and a technology for detecting the risk of specialized fraud by an automated transaction device such as an ATM, which recognizes emotions such as confusion or impatience, detects the risk of specialized fraud and outputs a message on the screen to warn of transfer fraud (see Patent Document 2, for example). In addition, a technology for generating emotions of a robot (see Patent Documents 3 to 5, for example) and a technology for recognizing the user's emotions (see Patent Documents 6 to 7, for example) are known. [Prior art documents] [Non-patent literature]
[0003] [Patent Document 1] JP 2019-153961 A [Patent Document 2] Patent Publication No. 2021-092952 [Patent Document 3] Patent No. 6273314 [Patent Document 4] Patent No. 6273313 [Patent Document 5] Patent No. 6199927 [Patent Document 6] Patent No. 3676969 [Patent Document 7] Patent No. 4704952 Summary of the Invention [Problem to be solved by the invention]
[0004] However, the conventional technology may not be able to accurately detect the risk of special fraud. For example, when the conventional technology determines that the risk is high, it may erroneously detect the risk because it notifies the customer of the risk determination result without confirming with the customer. [Means for solving the problem]
[0005] A determination device according to one embodiment of the present invention has an acquisition unit that acquires at least one of imaging data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation between the customer, a determination unit that determines a risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition unit, and a conversation unit that has a conversation with the customer about the risk determined by the determination unit.
[0006] A determination method according to one embodiment of the present invention is a determination method executed by a determination device, and includes an acquisition step of acquiring at least one of imaging data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation between the customer, a determination step of determining a risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition step, and a conversation step of having a conversation with the customer about the risk determined by the determination step.
[0007] A judgment program according to one embodiment of the present invention causes a computer to execute the following steps: an acquisition step of acquiring at least one of imaging data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation between the customer; a judgment step of judging a risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition step; and a conversation step of having a conversation with the customer about the risk judged by the judgment step. Effect of the Invention
[0008] According to one aspect of the present invention, the risk of specialized fraud can be detected with high accuracy. [Brief description of the drawings]
[0009] [Figure 1] 1 is a block diagram showing an example of a configuration of a determination device 10. FIG. [Diagram 2] FIG. 2 is a diagram for explaining an example of a determination device 10. [Diagram 3] 4 is a flowchart showing an example of a process flow of the determination device 10. [Figure 4] 1 is a diagram illustrating an example of a hardware configuration of a determination device 10. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, an embodiment for carrying out a determination device and a determination method according to an aspect of the present invention will be described in detail with reference to the drawings, but the determination device and the determination method according to an aspect of the present invention are not limited to this embodiment. In the following embodiments, the same components are given the same reference numerals, and duplicated descriptions are omitted.
[0011] (Embodiment) [1. Judgment device] An example of a determination device 10 according to an embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram showing an example of the configuration of the determination device 10. The determination device 10 determines the risk of special fraud for a customer and has a conversation with the customer about the risk. The determination device 10 is realized by, for example, an AI (Artificial Intelligence) humanoid robot capable of recognizing emotions, such as Pepper (registered trademark), and a microphone, and is installed near an ATM (Asynchronous Transfer Mode) or a prepaid card sales point in a bank, a convenience store, or other store. In the example shown in FIG. 1, the determination device 10 has an acquisition unit 11, a control unit 12, a conversation unit 13, and a storage unit 14.
[0012] (Acquisition part 11) The acquisition unit 11 acquires at least one of imaging data of a customer in a store, attribute data on attributes of the customer, and conversation data on a conversation of the customer. For example, the acquisition unit 11 acquires these data in the vicinity of an ATM or a prepaid card sales point of a bank, a convenience store, or other store. Specifically, the acquisition unit 11 acquires video data of a customer captured by a camera installed in the vicinity of an ATM in the store as imaging data, and acquires conversation data of the customer by a microphone installed in the vicinity of the ATM in the store. The acquisition unit 11 may acquire attribute data on at least one of the age and sex of the customer. In the example shown in FIG. 1, the acquisition unit 11 further acquires risk data on risks, emotion data on the emotion of the customer, and reaction data on the reaction of the customer to the conversation about risks by the conversation unit 13. For example, the acquisition unit 11 acquires emotion data recognized based on at least one of the imaging data and the conversation data. In addition, the acquisition unit 11 acquires reaction data on the emotion of the customer when receiving feedback from the customer about whether the conversation about risks by the conversation unit 13 was correct. The acquisition unit 11 may acquire emotion data and reaction data by recognizing the emotion of the customer, or may acquire emotion data and reaction data whose emotion has been recognized in advance. The emotion recognition method is similar to the methods described in Patent Documents 3 to 7, and therefore a detailed description thereof will be omitted. The emotion recognition method is not limited to these methods, and other known methods may be used.
[0013] (Control unit 12) The control unit 12 controls the entire determination device 10. As an example, the control unit 12 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the determination device 10 using a RAM as a working area. As another example, the control unit 12 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). In the example shown in FIG. 1, the control unit 12 has a trained model generation unit 121 and a determination unit 122.
[0014] (Trained model generation unit 121) The trained model generation unit 121 uses at least one of the imaging data, attribute data, and conversation data acquired by the acquisition unit 11 and risk data to generate a trained model 141 that outputs risk data when at least one of the imaging data, attribute data, and conversation data is input. For example, the trained model generation unit 121 uses the imaging data, attribute data, conversation data, and risk data acquired by the acquisition unit 11 as teacher data to generate a sentence generation model having a dialogue function including the trained model 141 that outputs risk data when the imaging data, attribute data, and conversation data are input.
[0015] Further, the trained model generation unit 121 uses the emotion data acquired by the acquisition unit 11 and the conversation data on the conversation about the risk to generate a trained model 142 in which conversation data on the risk is output when emotion data is input. For example, the trained model generation unit 121 uses the emotion data acquired by the acquisition unit 11 and the conversation data on the risk as teacher data to generate a sentence generation model having a dialogue function including the trained model 142 in which conversation data on the risk is output when emotion data is input. The trained model generation unit 121 may retrain the trained model 142 using the conversation data on the risk and reaction data on the customer's reaction to the conversation about the risk. For example, the trained model generation unit 121 retrains the trained model 142 using the conversation data on the risk and the reaction data on the customer's emotion acquired by the acquisition unit 11 when receiving feedback from the customer about whether the conversation about the risk was correct as teacher data. The sentence generation model having a dialogue function is realized by, for example, ChatGPT (Chat Generative Pre-trained Transformer) or the like.
[0016] (Judgment unit 122) The determination unit 122 determines the risk of special fraud for a customer based on at least one of the imaging data, attribute data, and conversation data acquired by the acquisition unit 11. The determination unit 122 may determine the risk using the trained model 141 that outputs risk data related to the risk when at least one of the imaging data, attribute data, and conversation data acquired by the acquisition unit 11 is input. The determination unit 122 may determine the risk based on at least one of the customer's facial expression and emotion. For example, the determination unit 122 determines the risk based on at least one of the customer's facial expression recognized based on the imaging data acquired by the acquisition unit 11 and the customer's emotion recognized based on at least one of the imaging data and the conversation data. When determining the risk based on the customer's facial expression, the determination unit 122 may determine the risk by recognizing the customer's facial expression from the imaging data, or may determine the risk based on the customer's facial expression recognized in advance by a facial expression recognition camera or the like. When determining the risk based on the customer's emotion, the determination unit 122 may determine the risk by recognizing the customer's emotion from at least one of the imaging data and the conversation data, or may determine the risk based on the customer's emotion recognized in advance.
[0017] The determination unit 122 may determine that the risk is higher when the customer's emotion is negative than when the customer's emotion is positive. The determination unit 122 may determine that the risk is higher when the customer's emotion is at least one of impatience, worry, and anxiety than when the customer's emotion is not impatient, worried, or anxious. For example, the determination unit 122 quantifies the magnitude of risk from 0 to 10, and when the customer's emotion is at least one of impatience, worry, and anxiety, the determination unit 122 determines the risk value to be 2 to 4, and when the customer's emotion is not worried or anxious, the determination unit 122 determines the risk value to be 0 to 1. Similarly, the determination unit 122 determines the risk value to be 2 to 4 when the risk is determined to be high. Furthermore, when there are multiple factors that determine the risk to be high, the determination unit 122 determines the total risk value by adding up the risk values determined according to each of the multiple factors.
[0018] The determination unit 122 may determine the risk based on at least one of the customer's movements and posture in the imaging data acquired by the acquisition unit 11. For example, when the customer's movements recognized from the imaging data of the customer are operating the ATM while talking, the determination unit 122 determines that the risk is higher than when the customer operates the ATM silently. The method of determining the risk based on at least one of the customer's movements and posture in the imaging data by the determination unit 122 is described in the reference literature (Internet search<URL:https: / / www.itmedia.co.jp / news / articles / 2212 / 07 / news077.html> ), so detailed description thereof will be omitted. The determination unit 122 may determine the risk based on at least one of the age and sex of the customer indicated by the attribute data acquired by the acquisition unit 11. This allows the determination unit 122 to detect the risk with higher accuracy. For example, when the attribute of the customer indicated by the attribute data acquired by the acquisition unit 11 is at least one of elderly and female, the determination unit 122 determines that the risk is higher than when the attribute of the customer is neither elderly nor female. This allows the determination unit 122 to detect the risk with higher accuracy. The determination unit 122 may determine the risk based on keywords included in the conversation data. For example, when the conversation data contains keywords related to special fraud such as "transfer money", "had an accident", and "urgent", the determination unit 122 determines that the risk is higher than when the keywords are not contained.
[0019] The determination unit 122 may determine the content of the conversation about risk based on the customer's emotions, and have the conversation unit 13 conduct the conversation about risk of the content. For example, when the customer's emotions are impatient, the determination unit 122 determines the content of the conversation about risk to be the content of the conversation about risk that will temporarily calm the customer. In this way, the determination unit 122 can have the conversation unit 13 conduct a conversation that matches the customer's emotions. The determination unit 122 may determine the content of the conversation about risk using the trained model 142 that outputs conversation data about risk related to a conversation about risk when emotion data related to emotions is input, and have the conversation unit 13 conduct a conversation about risk of the content. In this way, the determination unit 122 can brush up the content of the conversation about risk prepared in advance, such as a talk script that is an initial setting, by learning the trained model 142.
[0020] The determination unit 122 may determine the content of the conversation about risk using the trained model 142 retrained using the conversation data about risk and the reaction data about the customer's reaction to the conversation about risk, and have the conversation unit 13 have the conversation about the risk of the content. For example, the determination unit 122 may determine the content of the conversation about risk using the trained model 142 retrained using the conversation data about risk and the reaction data about the customer's emotion acquired by the acquisition unit 11 when receiving feedback from the customer about whether the conversation about risk was correct, and have the conversation unit 13 have the conversation about the risk of the content. This allows the determination unit 122 to brush up the content of the conversation about risk according to the customer's reaction prepared in advance, such as a talk script that is an initial setting, by learning the trained model 142. The determination unit 122 may determine the content of the conversation about risk using a sentence generation model having a dialogue function including the trained model 142, and have the conversation about the risk of the content. This enables the determination unit 122 to have the conversation unit 13 carry out a more polished conversation.
[0021] (Conversation Section 13) The conversation unit 13 has a conversation with the customer about the risk determined by the determination unit 122. For example, the conversation unit 13 has a conversation with the customer about the risk that includes at least one of an explanation of the risk, persuasion, and questioning. Hereinafter, an example of a conversation by the conversation unit 13 will be described with reference to FIG. 2. FIG. 2 is a diagram for explaining an example of the determination device 10. In the example shown in FIG. 2, the determination device 10 is a robot such as Pepper, and is installed around an ATM 20 in a bank, a convenience store, or other store. The determination device 10 may be realized by the ATM 20 or other equipment. When the conversation data includes keywords such as "transfer", "had an accident", and "urgent", the conversation unit 13 has a conversation with the customer 30 about the risk that includes questions to confirm the situation such as "why are you transferring money", "did someone ask you to do it", and "how much do you need", as well as an explanation of the suspicion of a special fraud such as "there is a suspicion of a special fraud", as shown in FIG. 2. As a result, unlike the conventional technology that simply notifies the customer 30 when it is determined that the risk is high without checking with the customer 30, the conversation unit 13 can grasp the situation and identify risk factors, and therefore can detect risk with high accuracy. As a result, the conversation unit 13 can increase the possibility of preventing damage from specialized fraud and reduce damage from specialized fraud.
[0022] Returning to the description of FIG. 1, the conversation unit 13 may take a measure based on the risk determined by the determination unit 122. For example, the conversation unit 13 takes a different measure each time the value of the risk quantified by the determination unit 122 exceeds a threshold. As an example, when the value of the risk quantified by the determination unit 122 is 0 to 1, the conversation unit 13 does not take any particular measures against the risk in the conversation about the risk. When the value of the risk quantified by the determination unit 122 is 2 to 4, the conversation unit 13 calls out to the customer and conducts a hearing. In this case, the determination unit 122 may further determine the risk. When the value of the risk quantified by the determination unit 122 is 5 to 8, the conversation unit 13 notifies the store clerk. When the value of the risk quantified by the determination unit 122 is 9 to 10, the conversation unit 13 reports to the police. The method of conversation, notification, and reporting by the conversation unit 13 is not particularly limited, and for example, if the conversation unit 13 is an audio output unit, the conversation, notification, and report may be made by outputting audio, if the conversation unit 13 is a display unit such as a tablet, the conversation, notification, and report may be made by displaying letters, symbols, etc., or in the case of reporting to the police, the report may be made via communication.
[0023] (Storage unit 14) The storage unit 14 stores various data and various programs such as imaging data, attribute data, conversation data, risk data, trained model 141, trained model 142, etc. The storage unit 14 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.
[0024] [2. Judgment method] Next, an example of processing by the determination device 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an example of the flow of processing by the determination device 10.
[0025] In step S1, the acquisition unit 11 acquires at least one of imaging data of a customer in a store, attribute data related to attributes of the customer, and conversation data related to a conversation between the customer. For example, when a customer is located near an ATM or a prepaid card sales point in a bank, a convenience store, or other store, the acquisition unit 11 acquires at least one of imaging data, customer data, and conversation data.
[0026] In step S2, the determination unit 122 determines the risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition unit 11.
[0027] In step S3, the conversation unit 13 has a conversation with the customer about the risk determined by the determination unit 122. For example, when the conversation data contains keywords such as "transfer money," "had an accident," and "urgent," the conversation unit 13 has a conversation with the customer about the risk that includes questions to confirm the situation such as "why are you transferring money," "did someone ask you to do this," and "how much do you need," as well as an explanation of the suspicion of specialized fraud, such as "suspected of specialized fraud."
[0028] [3. Hardware Configuration] 4 is a diagram showing an example of a hardware configuration of the determination device 10. A program installed in the computer 1200 functioning as the determination device 10 can cause the computer 1200 to function as one or more "parts" of the device according to the embodiment, or to execute an operation or one or more "parts" associated with the device, and can cause the computer 1200 to execute a process or a step of a process according to the embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.
[0029] The computer 1200 according to the embodiment includes a CPU 1212, a RAM 1214, and a graphic controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.
[0030] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.
[0031] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides the programs or data to the storage device 1224. The IC card drive reads programs and data from an IC card and writes the programs and data to the IC card.
[0032] The ROM 1230 stores therein programs that depend on the hardware of the computer 1200, such as a boot program that is executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.
[0033] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing an operation or processing of information according to the use of the computer 1200.
[0034] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, the DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.
[0035] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive 1226 (DVD-ROM 1227), or an IC card to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.
[0036] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search, replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and writes back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.
[0037] The above-mentioned programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.
[0038] The blocks in the flowcharts and block diagrams may represent stages of a process in which operations are performed or "parts" of apparatus responsible for performing the operations. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable storage medium, or a processor provided with computer readable instructions stored on a computer readable storage medium. Dedicated circuitry may include digital or analog hardware circuitry, and may include integrated circuits (ICs) or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs).
[0039] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.
[0040] The computer readable instructions may include either source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, JAVA, C++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
[0041] Computer readable instructions may be provided locally or over a local area network (LAN), a wide area network (WAN) such as the Internet, to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, such that the processor or programmable circuit executes the computer readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.
[0042] Although one aspect of the present invention has been described above using an embodiment, the technical scope of the present invention is not limited to the scope described in the above embodiment. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiment. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.
[0043] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and that the process may be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, it does not mean that the process must be performed in this order. [Explanation of symbols]
[0044] 10 Judgment device 11 Acquisition Department 12 Control section 13 Conversation Section 14 Storage section 121 Trained model generation unit 122 Judgment section 141, 142 Trained Model
Claims
1. an acquisition unit that acquires at least one of image data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation of the customer; a determination unit that determines a risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition unit; a conversation unit that has a conversation with the customer about the risk determined by the determination unit; A determination device comprising:
2. The determination unit determines the content of the conversation about the risk based on the customer's feelings, and causes the conversation unit to conduct the conversation about the risk having the determined content. The determination device according to claim 1 .
3. The determination unit determines the content of the conversation about the risk using a trained model that outputs conversation data about the risk when emotion data about the emotion is input, and causes the conversation unit to have a conversation about the risk with the determined content. The determination device according to claim 2 .
4. The determination unit determines the content of the conversation about the risk using the trained model that has been retrained using the conversation data about the risk and the reaction data regarding the customer's reaction to the conversation about the risk, and causes the conversation unit to have a conversation about the risk with the determined content. The determination device according to claim 3 .
5. The determination unit determines the content of the conversation about the risk using a sentence generation model having a dialogue function including the trained model, and causes the conversation unit to have a conversation about the risk of the determined content. The determination device according to claim 3 or 4.
6. The acquisition unit acquires the attribute data relating to at least one of the age and the gender of the customer, the determination unit determines the risk based on at least one of the age and the sex of the customer indicated by the attribute data acquired by the acquisition unit; The determination device according to claim 1 .
7. the determination unit determines that the risk is higher when the attribute of the customer indicated by the attribute data acquired by the acquisition unit is at least one of an elderly person and a female person, compared to when the attribute of the customer is neither an elderly person nor a female person; The determination device according to claim 6.
8. A determination method executed by a determination device, comprising: an acquisition step of acquiring at least one of image data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation of the customer; a determination step of determining a risk of specialized fraud for the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition step; a conversation step of having a conversation with the customer about the risk determined by the determination step; A method for determining whether or not a particular
9. An acquisition step of acquiring at least one of image data of a customer in a store, attribute data relating to attributes of the customer, and conversation data relating to a conversation of the customer; a determination step of determining a risk of specialized fraud against the customer based on at least one of the imaging data, the attribute data, and the conversation data acquired by the acquisition step; a conversation step of having a conversation with the customer about the risk determined by the determination step; A determination program that causes a computer to execute the above steps.
Citation Information
Patent Citations
Magnetic recording medium
JP1986099927A
Current limiter for temperature regulator
JP1987073313A
Ac signal supply controller
JP1987073314A
Information processing system, information processing apparatus, information processing method, and program
JP2019153961A
Automated transaction device
JP2021092952A
