Mediation support device, mediation support method, and mediation support program
The intermediation support device uses AI and language models to mediate calls, assess fraud risks, and manage connections, addressing limitations in existing fraud prevention services by enhancing call management and fraud detection.
Patent Information
- Application Number
- JP2024083023
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-05-22
- Publication Date
- 2025-12-05
- Estimated Expiration
- 2044-05-22
AI Technical Summary
Existing fraud prevention services are limited in their ability to manage calls between terminals, assuming a direct connection and lacking flexibility in handling potential fraud risks.
An intermediation support device and method utilizing generative AI and large-scale language models to mediate calls, assess fraud risks, and control call connections based on voice information input, including risk level evaluation and flexible call management.
Provides convenient and flexible intermediation support for call transmission and reception, enhancing fraud detection and prevention by assessing and managing call risks through intermediation.
Smart Images

Figure 2025176752000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an intermediation support device, an intermediation support method, and an intermediation support program. [Background technology]
[0002] Non-Patent Document 1 describes a special fraud prevention service that is part of efforts to prevent special fraud crimes. In this special fraud prevention service, call recording data recorded on a device with a call recording function (special fraud prevention adapter) is transferred to the cloud and analyzed on a server (special fraud analysis server). If the analysis reveals suspicion of special fraud, a warning is sent to the individual or their relatives via a pre-registered phone number or email address. This enables the individual or their relatives to sense the risk of fraud. [Prior art documents] [Non-patent literature]
[0003] [Non-Patent Document 1] "Special fraud prevention service" in conjunction with efforts to prevent special fraud crimes: https: / / web116.jp / shop / benri / tokusyu / tokusyu_00.html Summary of the Invention [Problem to be solved by the invention]
[0004] However, the special fraud prevention service in Non-Patent Document 1 has room for improvement in that it is a technology that aims to prevent special fraud crimes based on recorded call data, assuming that the calling terminal (caller) and the receiving terminal (recipient) are connected.
[0005] The present invention has been made based on the above-mentioned awareness of the problem, and aims to provide an intermediation support device, an intermediation support method, and an intermediation support program that can provide convenient and flexible intermediation support for calling and receiving between a calling terminal and a called terminal. [Means for solving the problem]
[0006] The intermediation support device of this embodiment is an intermediation support device that supports intermediation of calls made and received between a calling terminal and a called terminal, and is characterized by having an intermediation reception unit that mediates and accepts calls from the calling terminal, a judgment unit that judges whether the call from the calling terminal satisfies the direct connection conditions, a first acquisition unit that acquires first voice information input from the calling terminal when the call from the calling terminal does not satisfy the direct connection conditions, the first voice information including at least the caller and call requirements, a second acquisition unit that makes an intermediary call to the called terminal and conveys the first voice information to the called terminal, and acquires second operation information including whether the call from the calling terminal is to be received at the called terminal, and a control unit that controls whether the call from the calling terminal is to be received at the called terminal according to the second operation information. [Effects of the Invention]
[0007] According to the present invention, it is possible to provide an intermediation support device, an intermediation support method, and an intermediation support program that can provide convenient and flexible intermediation support for transmission and reception between a calling terminal and a called terminal. [Brief explanation of the drawings]
[0008] [Figure 1] 1 is a diagram illustrating an example of a schematic configuration of an intermediation support device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing an example of the internal configuration of an intermediation support server according to the present embodiment. [Figure 3] FIG. 10 is a diagram showing an example of first voice information to which a risk level is assigned. [Figure 4] 10 is a diagram showing an example of first voice information transmitted in an intermediate call to a receiving terminal. FIG. [Figure 5] 10 is a flowchart illustrating an example of an intermediation support process according to the present embodiment. [Figure 6] FIG. 2 is a diagram illustrating an example of the functional configuration of a calling terminal, a called terminal, and an intermediation support server. [Figure 7]FIG. 2 is a diagram illustrating an example of the hardware configuration of a calling terminal, a called terminal, and an intermediation support server. DETAILED DESCRIPTION OF THE INVENTION
[0009] The intermediation support device, the intermediation support method, and the intermediation support program according to the present embodiment will be described below.
[0010] The call system equipped with the intermediary support device, intermediary support method, and intermediary support program of this embodiment realizes the "next-generation telephone answering function Shin Denwaban (tentative name)" as a new telephone answering machine function as a "Reiwa-era automatic telephone."
[0011] "Shin Denwaban (provisional name)" does not unconditionally connect the calling terminal (caller) and the receiving terminal (received party). Instead, it mediates and accepts a call from the calling terminal (caller) and determines whether it is permissible to immediately connect the call to the receiving terminal (received party), i.e., whether the direct connection conditions are met. If the determination indicates a risk of special fraud or other fraud in the call from the calling terminal (caller), i.e., if the direct connection conditions are not met, the calling terminal (caller) is prompted to input first voice information including at least the caller and the call requirements, and the first voice information is acquired. Next, an intermediate call is made to the receiving terminal (received party), and the first voice information is transmitted to the receiving terminal (received party). At the same time, the second voice information (second operation information) including whether the call from the calling terminal (caller) should be received at the receiving terminal (received party) is prompted to input second voice information (second operation information) including whether the call from the calling terminal (caller) should be received at the receiving terminal (received party). Then, depending on the second voice information (second operation information), it is controlled whether the call from the calling terminal (caller) should be received at the receiving terminal (received party).
[0012] "Shin Denwaban (tentative name)" utilizes generative AI (artificial intelligence) and large-scale language models to provide convenient and flexible mediation support for calls between a calling terminal (caller) and a called terminal (received party). For example, by improving the accuracy of analysis of the first voice information, which includes at least the caller and the calling requirements input from the calling terminal (caller), it is possible to detect the risk level of calls from the calling terminal (caller) in stages and take flexible measures according to the risk level. Furthermore, it is possible to apply modifications, including summarization, correction, and deletion processes, to the first voice information, which includes at least the caller and the calling requirements input from the calling terminal (caller).
[0013] The "Shin" in "Shin Denwaban (tentative name)" may mean at least one of the following: "new era," "friendly," "aiming to truly solve problems," "synchronizing with customers," and "in-house efforts with conviction."
[0014] 1 is a diagram showing an example of the schematic configuration of an intermediation support device 1 of this embodiment. The intermediation support device 1 may be read as an "intermediation support system" (the two may be synonymous). The intermediation support method and intermediation support program of this embodiment are realized by a computer (CPU: Central Processing Unit) included in the intermediation support device 1 executing (causing) various processing steps.
[0015] As shown in FIG. 1, the intermediation support device 1 includes a transmitting terminal 10, a receiving terminal 20, an intermediation support server 30, and a large-scale language model 40. The transmitting terminal 10, the receiving terminal 20, the intermediation support server 30, and the large-scale language model 40 are communicably connected to each other via a network NW. In FIG. 1, the transmitting terminal 10, the receiving terminal 20, the intermediation support server 30, and the large-scale language model 40 are each depicted as a simplified single block for the sake of convenience. In reality, the transmitting terminal 10, the receiving terminal 20, the intermediation support server 30, and the large-scale language model 40 may have a more complex configuration than that depicted in FIG. 1, both in terms of hardware and software. For example, the intermediation support server 30 may be configured to include multiple servers, databases, and the like. Furthermore, the large-scale language model 40 may constitute a part of the intermediation support server 30 (the intermediation support server 30 may be used as a concept including the large-scale language model 40).
[0016] The intermediation support device (intermediation support system) 1 may be understood as a configuration including the calling terminal 10, the called terminal 20, the intermediation support server 30, and the large-scale language model 40, or as a configuration including only the intermediation support server 30 without including the calling terminal 10, the called terminal 20, and the large-scale language model 40. In other words, in the intermediation support device (intermediation support system) 1, the intermediation support server 30 is an essential component, but the calling terminal 10, the called terminal 20, and the large-scale language model 40 are not essential components.
[0017] The transmitting terminal 10 and the receiving terminal 20 are configured, for example, by a personal computer, telephone, smartphone, tablet terminal, or the like equipped with a function for executing voice calls. The transmitting terminal 10 and the receiving terminal 20 may be either a fixed type or a mobile (portable) type. The transmitting terminal 10 and the receiving terminal 20 may be the same (common) device.
[0018] The calling terminal 10 and the called terminal 20 may be communication devices capable of performing various types of communication with the intermediation support server 30. The calling terminal 10 and the called terminal 20 may communicate with a network (such as the Internet) via, for example, wired and / or wireless (e.g., Long Term Evolution (LTE), 5th Generation New Radio (5G NR), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.). The calling terminal 10 and the called terminal 20 may execute a browser and various other applications in response to a user operation.
[0019] In this embodiment, the calling terminal 10 and the called terminal 20 (particularly the called terminal 20) can receive highly convenient and flexible intermediation support for making and receiving calls between the calling terminal 10 and the called terminal 20 by using an intermediation support service (for example, "Shin Denwaban (tentative name)") provided by the intermediation support server 30. An application for receiving the intermediation support service (for example, "Shin Denwaban (tentative name)") provided by the intermediation support server 30 may be downloaded (installed) to the calling terminal 10 and the called terminal 20 (particularly the called terminal 20). Hereinafter, this application may be referred to as the intermediation support application "Shin Denwaban (tentative name)".
[0020] The intermediation support server 30 may be any communication device capable of performing various communications (including intermediary reception and intermediary outgoing communications) between the calling terminal 10 and the called terminal 20, and may be interpreted as a device, circuit, etc. The intermediation support server 30 controls and executes various processes for providing convenient and flexible intermediation support for outgoing and incoming communications between the calling terminal 10 and the called terminal 20. The intermediation support server 30 may be realized as a function on the cloud.
[0021] 2 is a block diagram showing an example of the internal configuration of the intermediation support server 30 of this embodiment. The intermediation support server 30, which supports intermediation of calls between the calling terminal 10 and the called terminal 20, has an intermediation reception unit 31, a determination unit 32, a first acquisition unit 33, a risk assessment unit 34, a second acquisition unit 35, a control unit 36, and a forwarding unit 37. In the following explanation, it is assumed that a call is made from the calling terminal 10 to the called terminal 20.
[0022] The intermediary reception unit 31 mediates and accepts calls from the calling terminal 10. The intermediary reception unit 31 does not connect the call from the calling terminal 10 to the called terminal 20, but temporarily places the call on hold on the intermediary support server 30 side. At this time, a voice message such as "This is the intermediary support service 'Shin Denwaban (tentative name)'" may be played from the output unit (e.g., telephone or speaker) of the calling terminal 10. Please note that the contents of the call will be recorded in order to increase customer satisfaction through improved service and strengthen compliance." The contents of the subsequent call may then be recorded.
[0023] The determination unit 32 determines whether or not the call from the calling terminal 10 satisfies the direct connection conditions. The direct connection conditions refer to the conditions for canceling (suspending) the intermediary reception by the intermediary reception unit 31 and connecting the call from the calling terminal 10 to the receiving terminal 20.
[0024] The determination unit 32 determines that the direct connection condition is satisfied when the calling number of the calling terminal 10 is a pre-registered call candidate number and a pre-defined password is input from the calling terminal 10, and otherwise determines that the direct connection condition is not satisfied.
[0025] The intermediation support application "Shin Denwaban (tentative name)" is equipped with a telephone directory function corresponding to the receiving terminal 20, and the intermediation support server 30 is provided with a storage device (memory) that collectively stores telephone numbers of family, friends, acquaintances, business associates, restaurants, business partners, etc. that are registered corresponding to the receiving terminal 20. The determination unit 32 then determines whether or not the calling number of the calling terminal 10 is included in the telephone numbers registered corresponding to the receiving terminal 20, that is, whether or not "the calling number of the calling terminal 10 is a pre-registered call candidate number." This may be called the first condition of the direct connection condition.
[0026] The intermediation support application "Shin Denwaban (tentative name)" is equipped with a function for approving a password corresponding to the receiving terminal 20, and the intermediation support server 30 is provided with a storage device (memory) that stores the password registered corresponding to the receiving terminal 20. The determination unit 32 plays a voice message such as "Please input the password by voice before connecting the call. Beep" from the output unit (e.g., telephone or speaker) of the calling terminal 10. Then, it determines whether the password input by the caller from the input unit (e.g., telephone or microphone) of the calling terminal 10 matches the password registered corresponding to the receiving terminal 20, i.e., whether "a predetermined password was input from the calling terminal 10." This may be called the second condition of the direct connection condition.
[0027] Here, in the storage device (memory) of the intermediation support server 30, the telephone number registered in correspondence with the receiving terminal 20 and the password registered in correspondence with the receiving terminal 20 can be updated as needed by adding, correcting, changing, etc. These update processes can be executed, for example, through operations on the intermediation support application "Shin Denwaban (tentative name)" on the receiving terminal 20.
[0028] If the determination by the determination unit 32 shows that the call from the calling terminal 10 satisfies the direct connection conditions, the call from the calling terminal 10 is connected to the called terminal 20, allowing a call between the two. If the determination by the determination unit 32 shows that the call from the calling terminal 10 does not satisfy the direct connection conditions, the process proceeds to subsequent processing by the first acquisition unit 33, the risk assessment unit 34, the second acquisition unit 35, the control unit 36, and the transfer unit 37.
[0029] If the call from the calling terminal 10 does not satisfy the direct connection conditions (for example, if the calling number of the calling terminal 10 is not a pre-registered call candidate number and / or if a pre-defined password is not input from the calling terminal 10), the first acquisition unit 33 outputs a voice such as "Excuse me, but please input the caller's name, company name, and business by voice. Beep." from an output unit (for example, a telephone or a speaker) of the calling terminal 10. Then, the first acquisition unit 33 acquires first voice information input by the caller from an input unit (for example, a telephone or a microphone) of the calling terminal 10, the first voice information including at least the caller and the call requirements. Note that if the input of the first voice information is not executed and the first acquisition unit 33 cannot acquire the first voice information, the connection may be cut off without connecting the call from the calling terminal 10 to the called terminal 20. At that time, a voice message such as "We are sorry, but we will have to disconnect the connection because we were unable to receive voice input of the caller's name, company name, and business purpose from the output unit (e.g., telephone mouth or speaker) of the calling terminal 10 may be output. In addition, the flow from the intermediation acceptance of the call from the calling terminal 10 to the disconnection of the connection may be stored as an intermediation support history.
[0030] The first acquisition unit 33 may perform modifications, including summarization, correction, and deletion, on the first voice information acquired by itself, which includes at least the sender and the transmission requirements. The summarization process refers to, for example, a process of briefly summarizing the gist and main points of the first voice information input by the sender through an input unit (e.g., a telephone or microphone) of the transmitting terminal 10. The correction process refers to, for example, a process of correcting an obvious mistake in the first voice information input by the sender through an input unit (e.g., a telephone or microphone) of the transmitting terminal 10, or a process of overwriting (updating) the earlier content of a recorded message with the later content if the latter content is restated later. The deletion process refers to, for example, a process of ignoring and not including (discarding) content that has become unnecessary as a result of the summarization process or correction process described above in the first voice information input by the sender through an input unit (e.g., a telephone or microphone) of the transmitting terminal 10. Furthermore, the deletion process means, for example, ignoring and not including (cutting out) content such as "eh," "ah," or "so," which the sender unconsciously utters.
[0031] The risk assessment unit 34 evaluates the risk of the first voice information acquired by the first acquisition unit 33, the first voice information including at least the caller and the calling requirements. That is, the risk assessment unit 34 evaluates the risk level of the call from the calling terminal 10. Recently, there has been an increase in cases where special frauds, suspicious door-to-door sales, and the like are triggered by unknown calls from unknown numbers. The risk assessment unit 34 analyzes the first voice information acquired by the first acquisition unit 33, the first voice information including at least the caller and the calling requirements, and evaluates the risk level of the first voice information (call from the calling terminal 10). For example, the risk assessment unit 34 may assign at least one of high risk, medium risk, and low risk as the risk level of the first voice information (call from the calling terminal 10). Of course, the risk assessment unit 34 may evaluate the risk level of the first voice information (call from the calling terminal 10) in two or more stages.
[0032] Currently, special fraud methods are classified into the following 10 types. (1) "It's me" fraud This method involves perpetrators claiming to be relatives or other relatives and saying things like, "I left my bag behind. There was a check inside. I need money," in order to trick (or extort) the victim out of cash. (2) Deposit fraud They claim to be police officers or bank association employees and say, "Your account has been used for criminal purposes. You will need to apply for a replacement cash card." They also claim to be government officials and say, "You have overpaid medical expenses, etc. We will process the necessary paperwork and then come and collect your card," in order to obtain your PIN and trick (or extort) you into handing over your cash card or other items. (3) Fictitious billing fraud This is a method of defrauding (threatening) people of money by saying things like, "You have unpaid fees for paid sites or consumption fees. If you don't pay by today, you will be taken to court," or by using the cost of computer virus protection support as an excuse. (4) Refund fraud The method involves telling the victim, "You have a refund due, so please go ahead and complete the necessary paperwork" regarding medical expenses, taxes, insurance premiums, etc., and then getting the victim to operate an ATM and transfer money from the victim's account to the criminal's account. (5) Loan guarantee fraud This is a method in which people are tricked into believing that they can easily obtain a loan, even though in reality they do not provide the loan, and then they are tricked (or threatened) into giving up money by telling people who wish to apply for a loan that a "guarantee deposit" is required. (6) Financial product fraud This method involves giving false information about completely worthless unlisted stocks or expensive items, leading people to believe they will make a profit if they purchase them, and then deceiving (extorting) them into giving them money as payment for the purchase. (7) Gambling fraud This is a method in which they trick people into signing up as members under the pretense of "looking for pachinko players," and then make them pay registration and information fees, thereby defrauding (extorting) them of money. (8) Dating fraud This is a method in which people who want to be introduced to women are tricked (or extorted) into paying money as membership registration fees or security deposits by claiming to be able to "introduce women." (9) Cash card fraud (theft) The perpetrators claim to be police officers, employees of a banking association, or a major department store, and tell victims that their cash cards have been used fraudulently and that they will be made unusable. They then wait for an opportunity to steal the cards by switching them with point cards or other items. (10) Other special frauds This refers to special frauds that do not fall into the categories listed above.
[0033] There are manuals for each type of special fraud described above, and groups of special fraud perpetrators often make initiating calls according to these manuals. In this embodiment, the intermediary support server 30 and the large-scale language model 40 work together to learn and accumulate actual examples of special fraud cases that have actually occurred in the past and those currently in progress, and compare them with the first voice information (transmission from the calling terminal 10) to evaluate the risk level of the first voice information (transmission from the calling terminal 10). The Metropolitan Police Department's database stores information such as actual examples of special fraud cases that have actually occurred in the past and those currently in progress, as well as information on the special fraud eradication action program, efforts to prevent special fraud victims, and public relations data for preventing special fraud victims. It is preferable to regularly update the intermediary support server 30 and the large-scale language model 40 with this information.
[0034] As described above, intermediary support server 30 may operate by appropriately referring to large-scale language model 40. Large-scale language model 40 may be interpreted as generative AI (Artificial Intelligence), and may cooperate with intermediary support server 30 to fulfill the functions of each block of intermediary support server 30 (intermediation reception unit 31, determination unit 32, first acquisition unit 33, risk assessment unit 34, second acquisition unit 35, control unit 36, and transfer unit 37, especially risk assessment unit 34).
[0035] The large-scale language model 40 stores, for example, specific information from the individual domain database (e.g., risk level information based on selective evaluation patterns) and common information from the common domain database (e.g., risk level information based on mandatory evaluation patterns) normalized into a unified data format so that they can be adapted to the training of language models for natural language processing. Furthermore, by combining one or more types of natural language processing based on the individual domain database and the common domain database, training and adjustment of language models specialized for generating risk level information based on selective evaluation patterns and risk level information based on mandatory evaluation patterns can be performed. Support information for assisting in the generation of risk level information can be generated by using the language model according to the content of the prompt. The language model may be stored on a cloud computer, which enables training of large datasets and training using high-performance computing resources.
[0036] Here, "natural language processing" refers to a process that enables a computer to understand text and audio data written in natural language and execute processing appropriate to the purpose. Specifically, examples include morphological analysis, which breaks natural language down into "morphemes," the smallest units that make up the language, and assigns information such as parts of speech; syntactic analysis, which analyzes the grammatical structure of natural language to clarify the structure and meaning of a sentence; semantic analysis, which analyzes the meaning of natural language to understand the meaning of words and sentences and make logical judgments and inferences; contextual analysis, which understands natural language while taking into account the context before and after a sentence; and intention analysis, which extracts the intention of a speaker or writer from a conversation or sentence using natural language. Thus, "natural language processing" processes natural language by combining processes such as morphological analysis, syntactic analysis, semantic analysis, contextual analysis, and intention analysis, thereby enabling the intermediation support process (e.g., risk level evaluation by the risk assessment unit 34) related to the intermediation support of this embodiment.
[0037] A "language model" is a type of probabilistic model used in natural language processing, and is a model that probabilistically predicts how likely a given word or sentence is to occur in natural language. Specifically, a language model calculates the occurrence probability of a given word sequence or sentence, or compares the occurrence probabilities of multiple word sequences or sentences, making it possible to automatically generate the most likely word or sentence based on the context when predicting the next word or sentence.
[0038] In the field of natural language processing, the term "language model" refers to a mathematical model that learns language patterns, grammatical rules, etc., and generates and understands natural language. For example, the language model used in the risk assessment unit 34's risk level assessment is trained specifically for the risk assessment unit 34's risk level assessment, and is used to assess the risk level by the risk assessment unit 34 according to the content of the prompt.
[0039] "Normalized into a unified data format" means that when handling large amounts of data such as individual area databases and common area databases, the data is converted into a common format and organized in a unified manner. When the risk assessment unit 34 performs machine learning to evaluate risk levels, it is possible to improve the efficiency and accuracy of processing by using normalized specific information, common information, system overview, and other information as input. "Normalization" is a processing method for organizing and structuring data in database tables according to certain rules, eliminating data redundancy and maintaining data consistency and integrity.
[0040] "Prompt" is information that displays to the user what to input, how to operate, etc., and allows the user to give instructions. "Information to support information indicating the risk level assessment by the risk assessment unit 34" is information that makes the risk level assessment by the risk assessment unit 34 more efficient and enables more effective mediation support to be implemented.
[0041] In addition, in addition to / instead of the large-scale language model 40, the intermediation support server 30 may be configured to hold and refer to a dictionary database and a vocabulary database for executing processing by each block of the intermediation support server 30 (the intermediation reception unit 31, the judgment unit 32, the first acquisition unit 33, the risk assessment unit 34, the second acquisition unit 35, the control unit 36, and the transfer unit 37, particularly the risk assessment unit 34).
[0042] The first acquisition unit 33 may add to the first voice information the risk level of the first voice information (transmission from the transmitting terminal 10) evaluated by the risk evaluation unit 34. That is, the first voice information may be obtained by appropriately modifying the sender and the transmission requirements, including summarizing, correcting, and deleting, and adding the risk level of the transmission from the transmitting terminal 10 to the modified information.
[0043] 3A, 3B, and 3C are diagrams showing examples of first voice information to which a risk level has been assigned. Fig. 3A illustrates the first voice information when the risk level is low, Fig. 3B illustrates the first voice information when the risk level is medium, and Fig. 3C illustrates the first voice information when the risk level is high.
[0044] In Fig. 3A, the first voice information includes the following message: "This is △△ from ○○ Preparatory School. □□-kun did not come to class today and we did not receive any notice of absence, so we are contacting you just in case." Since there is nothing suspicious about the message in Fig. 3A, the risk level of the first voice information in Fig. 3A may be evaluated as low.
[0045] In Figure 3B, the first voice information includes the message, "This is XX from XX Bank. I am contacting you regarding the new mortgage that you recently came to consult with us about." Because it is not possible to fully determine whether the facts in the message in Figure 3B are correct and because it is a call from a bank, it can be determined that the possibility that the call is from a specialized fraudster cannot be completely ruled out, and the risk level of the first voice information in Figure 3B can be evaluated as medium.
[0046] In Figure 3C, the first voice information has the following message: "This is △△ from ○○ Securities. We have recently introduced high-quality unlisted stocks to Mr. / Ms. □□. We are confident that we can offer great deals with full principal guarantee and absolutely no losses, so please allow us to explain." The message in Figure 3C contains words that could be considered typical of special frauds, such as "high-quality unlisted stocks," "full principal guarantee," and "absolutely no losses," so it is highly likely that the call is from a special fraud perpetrator, and the risk level of the first voice information in Figure 3C can be evaluated as high.
[0047] The second acquisition unit 35 makes an intermediary call to the receiving terminal 20 and transmits the first voice information with the assigned risk level to the receiving party. When making an intermediary call to the receiving terminal 20, the second acquisition unit 35 does not notify the calling number of the calling terminal 10, but notifies the intermediary calling number of the intermediary support device 1 (intermediary support server 30). This makes it impossible for the receiving party to call back (call back) the calling terminal 10 by tracing the call history of the receiving terminal 20, and makes it possible to prevent the damage from spreading even if the call is from a specialized fraudster.
[0048] In this embodiment, both the calling terminal 10 (calling side) and the called terminal 20 (called side) are notified of only the intermediary calling number (for example, a cloud phone number) of the intermediary support device 1 (intermediary support server 30) (the calling side and called side's telephone numbers are not notified of each other). This is effective in preventing the caller from creating a list of victims and in preventing secondary damage caused by the called side calling back.
[0049] Figures 4A, 4B, and 4C are diagrams showing examples of first voice information transmitted in an intermediate call to the receiving terminal 20. Figures 4A, 4B, and 4C correspond to Figures 3A, 3B, and 3C, respectively, but are not simply recordings, and have been modified to make it easier for the receiving party to understand the outline. That is, Figures 3A to 3C exemplify the first voice information itself input by the caller to the calling terminal 10, while Figures 4A to 4C depict modified versions of the first voice information input by the caller to the calling terminal 10.
[0050] In FIG. 4A, the output unit (e.g., the telephone or speaker) of the receiving terminal 20 outputs the first audio information, such as "The danger level is low. Mr. / Ms. △△ from ○○ Preparatory School has contacted you to inform you that Mr. / Ms. □□ has not attended school. Do you want to connect this call? Please answer "yes" or "no." Beep."
[0051] In FIG. 4B, the output unit (e.g., telephone or speaker) of the receiving terminal 20 outputs the first audio information, such as "Risk level is medium. You have received a call from Mr. / Ms. XX of XX Bank regarding a new mortgage. Do you want to connect this call? Please answer "yes" or "no." Beep."
[0052] In FIG. 4C, the output unit (e.g., telephone or speaker) of the receiving terminal 20 outputs the first audio information, such as "The risk level is high. Mr. / Ms. XX of XX Securities is contacting you to sell unlisted stocks, but we recommend that you do not connect the call due to the high risk of special fraud. Would you like to connect this call? Please answer "yes" or "no." Beep."
[0053] The recipient who has heard the first voice information replies "yes" or "no" via an input unit (for example, a telephone or microphone) of the recipient terminal 20. In this way, the second acquisition unit 35 acquires second voice information including whether or not the call from the calling terminal 10 is to be received at the recipient terminal 20. In other words, the answer "yes" or "no" corresponds to the second voice information.
[0054] The control unit 36 controls whether or not to receive the call from the calling terminal 10 at the receiving terminal 20, depending on the second voice information, i.e., the answer of "yes" or "no." For example, if the answer from the recipient of the receiving terminal 20 is "yes," the call from the calling terminal 10 is received at the receiving terminal 20. On the other hand, if the answer from the recipient of the receiving terminal 20 is "no," the call from the calling terminal 10 is not received at the receiving terminal 20, and the connection is cut off.
[0055] Instead of using a response of "yes" or "no" as the "second voice information," performing a predetermined operation of the dial keys may be used as the "second operation information." For example, the callee who hears the first voice information may press "1" if he / she wishes to connect the call, or "2" if he / she wishes not to connect the call, and this operation may be used as the "second operation information." In other words, the "second operation information" is used as a concept that includes both responding "yes" or "no" and performing a predetermined operation of the dial keys.
[0056] The forwarding unit 37 forwards the intermediation support history of incoming and outgoing calls between the calling terminal 10 and the called terminal 20 to a pre-registered forwarding destination terminal. The intermediation support server 30 is provided with a storage device (memory) that stores contact information (such as addresses of family / relative terminals) of particularly close family members, friends, and acquaintances registered in correspondence with the called terminal 20 (for example, if the owner of the called terminal 20 is an elderly person living alone, the owner's son, daughter, home helper, etc.), and is capable of forwarding messages via an interface such as email, an app like LINE ("LINE" is a registered trademark of LINE Corporation of Japan), or a chat format. Furthermore, the forwarding of the intermediation support history is not limited to forwarding by text information, and may also be forwarding by audio information or a combination of text information and audio information.
[0057] Here, the intermediation support history may include, for example, the time of the call made by the calling terminal 10, a determination result indicating whether the call from the calling terminal 10 satisfied the direct connection conditions, first voice information (including an evaluation of the risk level) input from the calling terminal 10 when the call from the calling terminal 10 did not satisfy the direct connection conditions, second voice information (second operation information) including whether the call from the calling terminal 10 was received at the receiving terminal 20, information indicating whether the call from the calling terminal 10 was received at the receiving terminal 20 according to the second voice information (second operation information), and call record information between the calling terminal 10 and the receiving terminal 20.
[0058] The transfer unit 37 may transfer the intermediation support history of the call origination and reception between the originating terminal 10 and the receiving terminal 20 to a different transfer destination terminal according to the risk level of the first voice information (call originated from the originating terminal 10).
[0059] For example, assume that the risk level of the first voice information (transmission from the transmitting terminal 10) includes at least high risk, medium risk, and low risk, as shown in Figures 3 and 4. In this case, the transfer unit 37 may transfer the intermediation support history to a police terminal if the risk level is high risk, transfer the intermediation support history to an operator terminal of the intermediation support device 1 (intermediation support server 30) if the risk level is medium risk, and transfer the intermediation support history to a pre-registered family / relative terminal if the risk level is low risk.
[0060] When the danger level is high, transferring the intermediary support history to a police terminal can lead to the emergency arrest of a special fraudster, and even if the calling terminal 10 and the called terminal 20 are connected and the caller and the called terminal talk, the police can immediately contact the called terminal 20 (the called terminal) and both parties can cooperate to carry out a so-called "play duped" operation that leads to the arrest of a special fraudster.
[0061] When the danger level is medium danger, the intermediation support history is transferred to the operator terminal of the intermediation support device 1 (intermediation support server 30), allowing the operator to examine the details and, if necessary, make an emergency call to the police or contact the receiving terminal 20 (the recipient) for confirmation, thereby enabling flexible responses.
[0062] By transferring the intermediation support history to a pre-registered family / relative terminal when the risk level is low, for example, family / relatives living in a distant location can check the safety of the caller and get an overview of regular communication via telephone, thereby realizing a so-called monitoring function.
[0063] In addition, when the intermediation support history is transferred to the police terminal when the danger level is high danger, or when the intermediation support history is transferred to the operator terminal of the intermediation support device 1 (intermediation support server 30) when the danger level is medium danger, the intermediation support history may also be transferred to a pre-registered family / relative terminal.
[0064] FIG. 5 is a flowchart showing an example of the intermediation support process of this embodiment.
[0065] In step ST1, a call from the calling terminal 10 is intermediary-accepted. In step ST2, it is determined whether the calling number of the calling terminal 10 is a pre-registered call candidate number. In step ST3, it is determined whether a predetermined password has been input from the calling terminal 10. If the calling number of the calling terminal 10 is a pre-registered call candidate number (step ST2: Yes) and the predetermined password has been input from the calling terminal 10 (step ST3: Yes), it is determined that the direct connection condition is satisfied, and the process proceeds to step ST4, where the calling terminal 10 and the receiving terminal 20 are connected to enable conversation, and the process ends. Note that the processes of steps ST2 and ST3 do not necessarily have to be performed in this order, and may be performed simultaneously.
[0066] If the calling number of the calling terminal 10 is not a pre-registered call candidate number (step ST2: No) and / or a predetermined password is not input from the calling terminal 10 (step ST3: No), it is determined that the direct connection condition is not satisfied, and the process proceeds to step ST5, where first voice information including at least the caller and calling requirements input from the calling terminal 10 is acquired. In step ST6, the acquired first voice information is modified by performing summarization, correction, and deletion processes, and an evaluation of a risk level is assigned (linked). In step ST7, an intermediary call is made to the called terminal 20, and the first voice information (modified and assigned a risk level) in step ST6 is conveyed to the called party, and second operation information (for example, second voice information that is a voice response of "yes" or "no") including whether the call from the calling terminal 10 is to be received at the called terminal 20 is acquired. When an intermediary call is made to the called terminal 20, the calling number of the calling terminal 10 is not notified, but the intermediary call number of the intermediary support device 1 (intermediary support server 30) is notified.
[0067] In step ST8, it is determined whether the second operation information indicates a desire to connect with the calling terminal 10. If the second operation information indicates a desire to connect with the calling terminal 10 (step ST8: Yes), the process proceeds to step ST9, where the calling terminal 10 and the called terminal 20 are connected to enable conversation, and the process ends. If the second operation information indicates a desire not to connect with the calling terminal 10 (step ST8: No), the process proceeds to step ST10, where the calling terminal 10 and the called terminal 20 are not connected, but the connection is cut off, and the process ends.
[0068] 5 is completed (step ST4 → end, step ST9 → end, step ST10 → end), a transfer process of the intermediary support history is performed. In particular, when the processes of steps ST5 to ST10 are performed, a transfer process of the intermediary support history may be performed according to the risk level of the first voice information (transmission from the transmitting terminal 10). For example, if the risk level is high, the intermediary support history may be transferred to a police terminal, if the risk level is medium, the intermediary support history may be transferred to an operator terminal of the intermediary support device 1 (intermediary support server 30), and if the risk level is low, the intermediary support history may be transferred to a pre-registered family / relative terminal.
[0069] Thus, the intermediation support device of this embodiment is an intermediation support device that supports intermediation of calls made and received between a calling terminal and a called terminal, and includes an intermediation reception unit that mediates and accepts calls from the calling terminal, a determination unit that determines whether the call from the calling terminal satisfies the direct connection conditions, a first acquisition unit that acquires first voice information including at least the caller and call requirements input from the calling terminal when the call from the calling terminal does not satisfy the direct connection conditions, a second acquisition unit that makes an intermediary call to the called terminal and conveys the first voice information to the called terminal, and acquires second operation information including whether the call from the calling terminal is to be received at the called terminal, and a control unit that controls whether the call from the calling terminal is to be received at the called terminal according to the second operation information.
[0070] This allows for convenient and flexible mediation support for calls between a calling terminal and a called terminal. Furthermore, as in the above-mentioned Non-Patent Document 1, it is not necessary for users (for example, elderly people) to install a dedicated terminal with a call recording function (special fraud prevention adapter) (the hurdle is low), and a service that can prevent special frauds can be realized on the cloud.
[0071] Fig. 6 is a diagram showing an example of the functional configuration of the calling terminal 10, the called terminal 20, and the intermediation support server 30. As shown in Fig. 6, the calling terminal 10, the called terminal 20, and the intermediation support server 30 each have a control unit 110, a storage unit 120, a communication unit 130, an input unit 140, and an output unit 150. Note that Fig. 6 shows an example of the functional blocks of the calling terminal 10, the called terminal 20, and the intermediation support server 30, and they may have other functional blocks not shown in Fig. 6. Furthermore, they may be configured not to include some of the functional blocks.
[0072] The control unit 110 controls the calling terminal 10, the called terminal 20, and the intermediation support server 30. The control unit 110 can be configured by a controller, a control circuit, or a control device that is explained based on common understanding in the technical field related to the present invention.
[0073] The storage unit 120 stores information used by the calling terminal 10, the called terminal 20, and the intermediation support server 30. The storage unit 120 can be configured, for example, by a memory, storage, storage device, or the like that is explained based on common understanding in the technical field related to the present invention.
[0074] The communication unit 130 performs communication (e.g., mutual communication) between the calling terminal 10, the called terminal 20, and the intermediation support server 30. The communication unit 130 can be configured by a transmitter / receiver, a transmitting / receiving circuit, or a transmitting / receiving device that is explained based on common understanding in the technical field related to the present invention. Note that the communication unit 130 may be configured by a transmitting unit and a receiving unit.
[0075] The input unit 140 accepts inputs from the calling terminal 10, the called terminal 20, and the intermediation support server 30. The input unit 140 may also be connected to a predetermined device, storage medium, etc., and accept data input. The input unit 140 may output the input results to, for example, the control unit 110. The input unit 140 may be configured with input devices such as a keyboard, a mouse, and buttons, input / output terminals, input / output circuits, etc., which are explained based on common understanding in the technical field related to the present invention. The input unit 140 may also be configured as an integrated unit with a display unit (for example, a touch panel).
[0076] The output unit 150 performs output at the calling terminal 10, the called terminal 20, and the intermediation support server 30. For example, the output unit 150 may be configured to include a display unit that displays images, an audio output unit that outputs audio, and the like. The display unit may be configured, for example, by a display device such as a monitor or the like that is described based on common understanding in the technical field related to the present invention. Furthermore, the audio output unit may be configured by an output device such as a speaker that is described based on common understanding in the technical field related to the present invention.
[0077] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by a single physically coupled device, or may be realized by two or more physically separate devices connected by wire or wirelessly.
[0078] For example, the devices in one embodiment of the present disclosure (the calling terminal 10, the called terminal 20, and the intermediation support server 30) may function as a computer that performs the intermediation support processing of the present disclosure. Fig. 7 is a diagram showing an example of the hardware configuration of the calling terminal 10, the called terminal 20, and the intermediation support server 30. The calling terminal 10, the called terminal 20, and the intermediation support server 30 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.
[0079] In this disclosure, terms such as apparatus, circuit, device, unit, and server may be interchangeable. The hardware configurations of the calling terminal 10, the called terminal 20, and the intermediation support server 30 may be configured to include one or more of the devices shown in the drawings, or may be configured to exclude some of the devices.
[0080] For example, although only one processor 1001 is shown, there may be multiple processors. Furthermore, processing may be performed by one processor, or processing may be performed by two or more processors simultaneously, serially, or in other ways. Furthermore, processor 1001 may be implemented by one or more chips.
[0081] Each function of the calling terminal 10, the called terminal 20, and the intermediation support server 30 is realized by loading predetermined software (programs) onto hardware such as a processor 1001, a memory 1002, etc., so that the processor 1001 performs calculations and controls communication by a communication device 1004, reading and / or writing of data in the memory 1002 and storage 1003, etc.
[0082] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Note that each unit such as the control unit 110 described above may be realized by the processor 1001.
[0083] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the control unit 110 may be realized by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks.
[0084] The memory 1002 is a computer-readable recording medium and may be configured by at least one of, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically EEPROM (EEPROM), a random access memory (RAM), or other suitable storage medium. The memory 1002 may also be referred to as a register, a cache, a main memory, or the like. The memory 1002 may store executable programs (program codes), software modules, and the like for implementing a method according to one embodiment.
[0085] Storage 1003 is a computer-readable recording medium, and may be configured by at least one of, for example, a flexible disk, a floppy disk, a magneto-optical disk (e.g., a compact disk (CD-ROM (Compact Disc ROM)), a digital versatile disk, a Blu-ray (registered trademark) disk), a removable disk, a hard disk drive, a smart card, a flash memory device (e.g., a card, a stick, a key drive), a magnetic stripe, a database, a server, or other suitable storage medium. Storage 1003 may also be called an auxiliary storage device. Note that the above-mentioned storage unit 120 may be realized by memory 1002 and / or storage 1003.
[0086] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may include a SIM card. Note that the above-mentioned communication unit 130 may be realized by the communication device 1004.
[0087] The input device 1005 is an input device (for example, a keyboard, a mouse, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one unit (for example, a touch panel). The above-mentioned input unit 140 and output unit 150 may be realized by the input device 1005 and the output device 1006, respectively.
[0088] Furthermore, each device such as the processor 1001 and the memory 1002 is connected by a bus 1008 for communicating information. The bus 1008 may be configured as a single bus, or may be configured as different buses between the devices.
[0089] Furthermore, the transmitting terminal 10, the receiving terminal 20, and the intermediation support server 30 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.
[0090] (Variation) In addition, terms explained in this disclosure and / or terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.
[0091] The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values from a predetermined value, or other corresponding information. Furthermore, the names used for parameters, etc. in this disclosure are not limiting in any way.
[0092] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.
[0093] Information, signals, etc. may be input / output via multiple network nodes. The input / output information, signals, etc. may be stored in a specific location (e.g., memory) or may be managed using a table. The input / output information, signals, etc. may be overwritten, updated, or added. Output information, signals, etc. may be deleted. Input information, signals, etc. may be transmitted to another device.
[0094] Furthermore, notification of specified information (e.g., notification that "it is X") is not limited to explicit notification, but may be made implicitly (e.g., by not notifying the specified information or by notifying other information).
[0095] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.
[0096] Software, instructions, information, etc. may also be transmitted and received via a transmission medium and / or signal waveform. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.
[0097] As used in this disclosure, the terms "system" and "network" may be used interchangeably.
[0098] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, the order of the processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the specific order presented.
[0099] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."
[0100] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.
[0101] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.
[0102] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.
[0103] Although the invention according to the present disclosure has been described in detail above, it is clear to those skilled in the art that the invention according to the present disclosure is not limited to the embodiments described in the present disclosure. The invention according to the present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the invention as defined by the description of the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not impose any limiting meaning on the invention according to the present disclosure. [Explanation of symbols]
[0104] 1. Intermediary support device (intermediary support system) 10. Calling terminal 20 Calling terminal 30 Intermediary support server 31 Intermediary Reception Department 32 Judgment section 33 First acquisition part 34 Risk Assessment Department 35 Second acquisition part 36 Control Unit 37 Transfer Unit 40 Large-scale language models NW Network
Claims
1. An intermediation support device that supports intermediation of calls made and received between a calling terminal and a called terminal, an intermediary reception unit that mediates and receives calls from the calling terminal; a determination unit that determines whether a call from the calling terminal satisfies a direct connection condition; a first acquisition unit that acquires first voice information input from the calling terminal when the call from the calling terminal does not satisfy the direct connection condition, the first voice information including at least the caller and the call requirement; a second acquisition unit that performs an intermediate call to the receiving terminal, transmits the first voice information to the receiving party, and acquires second operation information including whether or not the call from the calling terminal is to be received at the receiving terminal; a control unit that controls whether or not the call from the calling terminal is to be received by the called terminal in accordance with the second operation information; An intermediation support device comprising:
2. the determination unit determines that a direct connection condition is satisfied when the calling number of the calling terminal is a pre-registered call candidate number and a pre-defined password is input from the calling terminal, and otherwise determines that the direct connection condition is not satisfied; 2. The intermediation support device according to claim 1.
3. the first acquisition unit applies modifications to the first voice information, including summarization, correction, and deletion, and adds a risk level of the call from the calling terminal to the first voice information.
2. The intermediation support device according to claim 1.
4. the second acquisition unit, when making an intermediary call to the receiving terminal, does not notify the calling number of the calling terminal, but notifies the intermediary call number of the intermediation support device.
2. The intermediation support device according to claim 1.
5. a transfer unit that transfers the intermediation support history of the call between the calling terminal and the called terminal to a pre-registered transfer destination terminal; 2. The intermediation support device according to claim 1.
6. a transfer unit that transfers the intermediation support history of the call between the calling terminal and the called terminal to a different transfer destination terminal according to a risk level of the call from the calling terminal; 2. The intermediation support device according to claim 1.
7. The risk level includes at least high risk, medium risk, and low risk, the transfer unit transfers the intermediation support history to a police terminal when the risk level is the high risk, transfers the intermediation support history to an operator terminal of the intermediation support device when the risk level is the medium risk, and transfers the intermediation support history to a pre-registered family / relative terminal when the risk level is the low risk.
7. The intermediation support device according to claim 6.
8. An intermediation support method using an intermediation support device that supports intermediation of transmission and reception between a calling terminal and a called terminal, comprising: a step of mediating and accepting a call from the calling terminal; determining whether a call from the calling terminal satisfies a direct connection condition; When the call from the calling terminal does not satisfy the direct connection condition, acquiring first voice information input from the calling terminal, the first voice information including at least the caller and the call requirement; a step of making an intermediate call to the receiving terminal, transmitting the first voice information to the receiving party, and acquiring second operation information including whether or not the call from the calling terminal is to be received at the receiving terminal; controlling whether or not the call from the calling terminal is to be received by the called terminal in accordance with the second operation information; The method for mediation support is characterized in that the method is executed by a computer.
9. An intermediation support program used in an intermediation support device that supports intermediation of transmission and reception between a calling terminal and a called terminal, a step of mediating and accepting a call from the calling terminal; determining whether a call from the calling terminal satisfies a direct connection condition; When the call from the calling terminal does not satisfy the direct connection condition, acquiring first voice information input from the calling terminal, the first voice information including at least the caller and the call requirement; a step of making an intermediate call to the receiving terminal, transmitting the first voice information to the receiving party, and acquiring second operation information including whether or not the call from the calling terminal is to be received at the receiving terminal; controlling whether or not the call from the calling terminal is to be received by the called terminal in accordance with the second operation information; An intermediation support program characterized by causing a computer to execute the above.