JP7601258B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

Conventionally, technologies have been developed to confirm whether operations using a mobile terminal or launching of an application are based on the user's will. For example, Patent Literature 1 discloses an information processing device that includes an identity authentication unit that compares acquired static biometric information with preregistered static biometric information to authenticate the identity of the user, a status determination unit that compares acquired dynamic biometric information with preregistered dynamic biometric information to determine the user's status, and an application launch unit that limits application software to be launched depending on the user's status determined by the status determination unit.

International Publication No. WO2015/189967A1

The information processing device described in Patent Document 1 uses biometric information such as fingerprints, veins, face, iris, and retina as static biometric information for personal authentication. However, there is a problem in that such biometric information requires a dedicated reading device and cannot necessarily be used on the terminal.

One aspect of the present invention has been made in consideration of the above problems, and one example of the objective thereof is to provide technology that identifies whether an operation on a terminal is based on the operator's will, based on personal authentication information input by the operator and the operator's biometric information.

An information processing device according to one aspect of the present invention comprises: an identity verification information acquisition means for acquiring identity verification information input from a terminal; a biometric information acquisition means for acquiring biometric information of an operator of the terminal; and an identification means for executing an identification process for identifying whether or not the operation is being performed of the individual's will by referring to one or more biometric information models trained using the operator's normal biometric information, the biometric information acquired by the biometric information acquisition means, and the identity verification information acquired by the identity verification information acquisition means.

An information processing method according to one aspect of the present invention includes at least one processor acquiring personal identification information input from a terminal, acquiring biometric information of an operator of the terminal, and identifying whether or not the operation is being performed of the operator's own will by referring to one or more biometric information models trained using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information.

An information processing program according to one aspect of the present invention causes a computer to execute the following processes: acquiring personal identification information input from a terminal; acquiring biometric information of an operator of the terminal; and identifying whether or not the operation is being performed of the operator's own volition by referring to one or more biometric information models learned using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information.

According to one aspect of the present invention, a technology can be provided that identifies whether an operation on a terminal is based on the operator's will, based on the identity authentication information input by the operator and the operator's biometric information.

1 is a block diagram showing a configuration of an information processing device according to a first exemplary embodiment of the present invention; 4 is a flowchart showing a flow of an information processing method according to the first exemplary embodiment. FIG. 11 is a block diagram showing a configuration of an information processing device according to an exemplary embodiment 2 of the present invention. FIG. 11 is a flow diagram showing an outline of the flow of information processing performed by an information processing device according to an exemplary embodiment 2. FIG. 11 is a conceptual diagram showing that the bioinformation model includes a plurality of models. 11 is a table showing a method of using different models depending on the importance or purpose of the operation contents. FIG. 13 is a conceptual diagram showing an example of a method in which some of multiple pieces of biometric information are combined and the model compares the features of the biometric information. FIG. 11 is a block diagram showing a configuration of an information processing device according to an exemplary embodiment 3 of the present invention. FIG. 11 is a flow diagram showing an outline of the flow of information processing performed by an information processing device according to an exemplary embodiment 3. 13 is a flowchart showing the flow of an information processing method according to an exemplary embodiment 3. FIG. 11 is a block diagram showing a configuration of an information processing device according to an exemplary embodiment 4 of the present invention. 13 is an example of warning information displayed on a display unit. FIG. 1 is a configuration diagram for implementing an information processing device using software.

[Example embodiment 1]
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A first exemplary embodiment of the present invention will be described in detail with reference to the accompanying drawings. This exemplary embodiment is a basic form of the exemplary embodiments described below.

(Configuration of information processing device)
The configuration of an information processing device 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. The information processing device 1 is a device that identifies whether or not an operation of a user (operator) 40 who operates a terminal 30 was performed based on the user's will. In this exemplary embodiment, the user refers to the user identified by personal identification information, which will be described later.

As shown in Fig. 1, the information processing device 1 includes an identity verification information acquisition unit 11, a biometric information acquisition unit 12, and an identification unit 13. The identity verification information acquisition unit 11, the biometric information acquisition unit 12, and the identification unit 13 are each a form of identity verification information acquisition means, a biometric information acquisition means, and an identification means described in the claims.

(Personal Identification Information Acquisition Department)
The personal identification information acquisition unit 11 acquires personal identification information of the operator input by the operator from the terminal. In this exemplary embodiment, the personal identification information is information that proves the identity of the operator, and is, for example, information that only the operator knows, or information contained in something that is considered to be owned only by the operator. Examples of personal identification information include My Number, information recorded on a My Number card, information recorded on a card with an integrated IC chip (such as a credit card or cash card), a PIN, account information, a password, a face image, a fingerprint, and the like.

The terminal is a terminal through which an operator performs input operations. Examples of terminals include personal computers, mobile terminals such as smartphones or mobile tablets, various wearable devices, ATMs (Automatic Teller Machines) at financial institutions, input terminals at public institutions, etc. However, the type of terminal is not limited to the above examples, and the form is not limited as long as it is a terminal with information and communication functions configured to enable an operator to perform operations for a desired procedure. The information processing device 1 may be connected to the terminal via an information and communication network such as the Internet.

A wearable device is a device that is worn by a person on a part of their body. Examples of wearable devices include wristwatches, glasses, headphones, or earphones. In this exemplary embodiment, however, the term refers to wearable devices that, in addition to the original functions of these devices, have the ability to acquire biometric information, particularly the pulse rate and body temperature, of the wearer.

The identity verification information to be input may be any one of the pieces of information that can be input from the terminal, or a combination of these. Typically, identity verification information can be input using a keyboard, touch panel, various information reading devices, etc., provided on the terminal. For example, the My Number, account (account number), PIN, password, etc. can be input from a touch panel provided on a personal computer or mobile terminal. If the personal computer or mobile terminal is equipped with a card reading device, the My Number card can be read. In the case of an ATM of a financial institution, etc., a financial institution card reading device is attached. If the personal computer, mobile terminal, ATM, etc. is equipped with a camera, an image of the face may be sent as identity verification information.

(Biometric information acquisition unit)
The biometric information acquisition unit 12 acquires biometric information of the operator of the terminal. In this exemplary embodiment, the biometric information is physical information or physiological information. Specifically, the biometric information includes, as an example, at least one of keystrokes on a keyboard or a touch panel, pulse, body temperature, and facial expression. In this exemplary embodiment, keystrokes, which are physical information, refer to the overall characteristics of key operation on a keyboard or a touch panel. As an example, keystrokes include the speed at which a key is typed, the pattern or frequency of typos, differences in input speed depending on the type of character string, and the like. Such information on keystrokes is information that is likely to reveal input habits that differ from person to person.

Physiological information such as pulse rate or body temperature can be acquired by a wearable device equipped with a pulse meter or thermometer when the operator is wearing the wearable device. Furthermore, facial expressions can be acquired by a camera when the operator is operating a terminal equipped with a camera. By comparing the pulse rate, body temperature, facial expressions, etc. with normal times, it is possible to identify whether the operator is operating in an unusual mental state.

Such biometric information is acquired by equipment that is generally provided in the terminal. Also, if the operator is wearing a wearable device, the biometric information may be acquired by the wearable device. In other words, there is no need to install new equipment dedicated to acquiring biometric information.

(Identification unit)
The identification unit 13 performs an identification process to identify whether or not the operation by the operator 40 is being performed of the operator's own will, by referring to one or more biometric information models learned using the operator's 40's normal biometric information, the biometric information acquired by the biometric information acquisition unit 12, and the personal identification information acquired by the personal identification information acquisition unit 11.

The biometric information model is a machine learning model constructed by learning the operator's biometric information under normal circumstances. In other words, the biometric information model calculates the degree to which the biometric information acquired by the biometric information acquisition unit 12 matches the biometric information under normal circumstances of the person (hereinafter also referred to as the "person") identified by the identity verification information acquired by the identity verification information acquisition unit 11, and performs an identification process to identify whether or not the operation performed on the terminal is performed at the person's will. The method of constructing the biometric information model will be described later.

In this exemplary embodiment, normal times refer to, for example, a state in which the person does not feel anxiety, fear, worry, or the like, or a state in which the person is mentally stable. In addition, in consideration of the problem that this exemplary embodiment is intended to solve, normal times may be rephrased as a state in which the person performs operations based on his or her original will. Original will is, for example, the will to perform operations voluntarily in a state in which the person is not threatened or coerced by others, or is not confronted with fraud, or the like.

In the exemplary embodiment 1, an example has been described in which the personal identification information acquisition unit 11, the biometric information acquisition unit 12, and the identification unit 13 are integrated into one information processing device 1, but these units do not need to be integrated into one location. In other words, some or all of these units may be distributed and located in different locations. Also, some or all of these units may be distributed and located on the cloud. This also applies to the following exemplary embodiments.

(Effects of information processing device 1)
As described above, the information processing device 1 according to this exemplary embodiment is configured to include an identity verification information acquisition unit 11 that acquires identity verification information input from the terminal 30, a biometric information acquisition unit 12 that acquires biometric information of the operator 40 of the terminal 30, and an identification unit 13 that executes an identification process to identify whether or not the operation is performed at the operator's will, by referring to one or more biometric information models learned using the operator's normal biometric information, the biometric information acquired by the biometric information acquisition unit 12, and the identity verification information acquired by the identity verification information acquisition unit 11. Therefore, the information processing device 1 according to this exemplary embodiment has an effect of being able to identify whether or not an operation on the terminal is an operation based on the operator's will, based on the identity authentication information input by the operator and the operator's biometric information.

(Flow of information processing method)
Next, the flow of the information processing method according to this exemplary embodiment will be described with reference to the drawings. Fig. 2 is a flowchart showing the flow of the information processing method S1.

As shown in the figure, the information processing method S1 includes the following steps. In step S11, at least one processor (e.g., personal identification information acquisition unit 11) acquires personal identification information input from the terminal. In addition, in step S12, at least one processor (e.g., biometric information acquisition unit 12) acquires biometric information of the operator of the terminal. In addition, in step S13, at least one processor (e.g., identification unit 13) refers to one or more biometric information models learned using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information, and identifies whether the operation is performed at the user's will. The contents of the personal identification information, biometric information, and biometric learning model are as described above.

(Effects of information processing method S1)
As described above, in the information processing method S1 according to this exemplary embodiment, a configuration is adopted in which at least one processor acquires personal identification information input from a terminal, acquires biometric information of an operator of the terminal, and identifies whether or not the operation is being performed of the person's will by referring to one or more biometric information models trained using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information.

Therefore, according to the information processing method S1 of this exemplary embodiment, it is possible to obtain the effect of identifying whether an operation on a terminal is an operation based on the operator's will, based on the personal authentication information input by the operator and the operator's biometric information.

Exemplary embodiment 2
Next, a second exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first exemplary embodiment are given the same reference numerals, and the description thereof will be omitted as appropriate.

(Information processing device 1A)
3 is a block diagram showing the configuration of an information processing device 1A according to this exemplary embodiment. As shown in the figure, the information processing device 1A includes a control unit 10, a communication unit 15, and a memory 16.

The control unit 10 includes a personal identification information acquisition unit 11, a biometric information acquisition unit 12, and an identification unit 13. The functions of the personal identification information acquisition unit 11, the biometric information acquisition unit 12, and the identification unit 13 are as described in exemplary embodiment 1. As an example, the memory 16 stores one or more programs in a read only memory (ROM), and the functions of each unit of the control unit 10 are realized by appropriately expanding the programs into a random access memory (RAM) and executing them.

The information processing device 1A is connected to the terminal 30 via the communication unit 15 so as to be able to communicate information via an information communication network N such as the Internet. The terminal 30 is a terminal operated by an operator 40, and a specific example thereof is as described in the exemplary embodiment 1.

Note that the operations performed by the operator 40 using the terminal 30 do not refer to operations performed on the information processing device 1A, but rather to personal transactions such as financial transactions and commercial transactions, or administrative procedures instructed or requested by the executive branch based on laws, regulations, etc. (procedures related to resident registration cards and family registers, electronic tax payment, electronic voting, etc.).

The information processing device 1A is connected to the bioinformation model 20 via the communication unit 15 so as to be capable of communicating information with the bioinformation model 20. The functions of the bioinformation model 20 are as described in exemplary embodiment 1.

Note that the personal identification information acquisition unit 11, biometric information acquisition unit 12, identification unit 13, communication unit 15, and memory 16 do not need to be integrated in one location as one information processing device 1A. In other words, some or all of these may be distributed and located in different locations. Also, some or all of these may be distributed and located on the cloud. Also, the biometric information model 20 may be located in a location different from the above-mentioned units, or may be located on the cloud.

(Biometric Information Model 20)
As described above, the biometric information model 20 is a machine learning model constructed by learning the operator's biometric information in normal times. The biometric information model 20 acquires the operator's biometric information in advance and learns the operator's biometric information pattern in normal times. When the identification unit 13 inputs the operator 40's personal identification information and biometric information, the biometric information model 20 derives an evaluation index indicating the degree to which the biometric information matches the operator's biometric information in normal times and outputs the evaluation index to the identification unit 13.

(Flow of information processing by information processing device 1A)
The flow of information processing performed by the information processing device 1A will be described with reference to the drawings. FIG. 4 is a flow diagram showing an outline of the flow of information processing performed by the information processing device 1A. In step 1, the information processing device 1A acquires personal identification information and biometric information of the operator. Specifically, the personal identification information acquisition unit 11 acquires personal identification information input by the operator 40 from the terminal 30. The biometric information acquisition unit 12 acquires the biometric information of the operator 40 via the terminal 30 or a wearable device worn by the operator 40. The biometric information acquired via the wearable device can be confirmed to be the biometric information of the operator 40 by the biometric information acquisition unit 12 acquiring identification information (such as a MAC address) of the wearable device together with the information.

Next, in step 2, the information processing device 1A performs an identification process using the identification model. Specifically, the identification unit 13 uses the biometric information model 20 to perform an identification process for identifying whether or not an operation performed by an operator 40 was performed according to the operator's original intention.

Next, in step 3, the information processing device 1A may perform processing according to the identification result. If the identification result is normal, that is, if the operation is identified as having been performed with the person's original intention, the information processing device 1A does not perform any processing. On the other hand, if the identification result is abnormal, that is, if the operation is identified as not having been performed with the person's original intention, the information processing device 1A may perform some processing.

As an example, if the result of the identification process identifies that an operation was not performed by the operator's will, the identification unit 13 may record the acquired biometric information of the operator 40 as operation information at the time of an abnormality. An abnormality is when a certain operation is identified as not being performed by the operator's will. Operation information confirmed as abnormal can be used for learning the model. This can further improve the evaluation accuracy of the model.

Alternatively, in the event of an abnormality, the identification unit 13 may send some kind of warning to the security department of the operation destination. Alternatively, in the event of an abnormality, the identification unit 13 may send a message to the police or the like informing them that there is a possibility of an abnormal operation.

The biometric information model 20 pre-learns one or more biometric information characteristics under normal conditions for each of multiple operators 40.

For example, if the operator 40 operates the terminal 30 against his or her will due to intimidation, coercion, fraud, or the like, it is believed that the mental state will be different from normal and that the biometric information obtained during operation will be different from the biometric information obtained during normal operation. For example, if the operator becomes nervous due to intimidation or coercion, the pulse rate will be higher than normal and the body temperature will often be higher than normal. In addition, it is expected that facial expressions will change from normal, with a tense expression and more frequent blinking. If the electrical conductivity of the skin could be measured with a wearable device, it is expected that a conductivity different from normal would be obtained. The same is true in cases where the operator 40 believes that he or she must perform an emergency operation due to a transfer fraud, etc.

It is also expected that keystrokes when typing will differ from normal. For example, it is expected that there will be a higher rate of input errors for familiar character strings (such as one's name or password) that one normally does not make input errors with. It is also expected that the speed at which characters are typed will become noticeably slower, and there will be an overall increase in input errors.

In this way, the biometric information model 20 can compare the characteristics of the operator's normal biometric information acquired via the terminal 30 or wearable device with the characteristics of the biometric information acquired during a certain operation, and output an evaluation index indicating the degree to which the biometric information during a certain operation matches (or differs from) the operator's normal biometric information during the operation.

(Types of bioinformation models)
Furthermore, the bioinformation model 20 may have a plurality of bioinformation models (hereinafter, simply referred to as "models"). Fig. 5 is a conceptual diagram showing that the bioinformation model 20 has a plurality of models. As shown in the figure, the bioinformation model 20 has a model 20A (model A), a model 20B (model B), and a model 20C (model C). Note that the bioinformation model 20 may have more models.

It is expected that the biometric information under normal circumstances will vary depending on the importance or purpose of the operation. Therefore, the identification unit 13 may acquire information indicating the importance of the operation of the terminal 30, select one of a plurality of biometric information models according to the acquired information indicating the importance, and perform the identification process using the selected biometric information model.

Alternatively, the identification unit 13 may acquire information indicating the purpose of the operation of the terminal 30, select one of a plurality of biometric information models depending on the acquired information indicating the purpose of the operation, and perform the identification process using the selected biometric information model.

Figure 6 is a table showing a method of using different models depending on the importance or purpose of the operation. For example, the identification unit 13 may use different models depending on the importance of the operation (e.g. the amount of money involved in the operation). Operations involving transactions of large amounts are considered to cause greater tension than operations involving small amounts. Thus, the identification unit 13 may select the model to use depending on the amount of the operation.

Table 601 is a table in which different models are used depending on the importance. As shown in Table 601, as an example, Model A is a model used when the importance of an operation is high. For example, assuming that importance is the amount of money, when the amount input in a certain operation is equal to or greater than a first threshold (corresponding to high importance), the identification unit 13 performs an identification process using Model A that has been trained using biometric information obtained during operations in which the operation amount is equal to or greater than the first threshold under normal circumstances.

Similarly, when the amount input in a certain operation is equal to or greater than the second threshold and less than the first threshold (corresponding to medium importance), the identification unit 13 performs the identification process using model B trained using biometric information obtained during operations in which the operation amount is equal to or greater than the second threshold and less than the first threshold under normal circumstances. Also, when the amount input in a certain operation is less than the second threshold (corresponding to low importance), the identification unit 13 performs the identification process using model C trained using biometric information obtained during operations in which the operation amount is less than the second threshold under normal circumstances.

The importance of an operation is not limited to the amount of money involved. For example, the importance of an operation may include at least one of the type of financial transaction, the amount of the financial transaction, the type of commercial transaction, the amount of the commercial transaction, the counterparty of the operation, and the frequency of operations performed on the counterparty in the past.

The identification unit 13 may also use different models depending on the purpose of the operation. For example, depositing and withdrawing money at a bank ATM is a frequent operation and is considered to be familiar to the user. Meanwhile, administrative procedures are considered to be infrequent operations and are considered to be unfamiliar. Unfamiliar operations are considered to have different levels of tension and input speed, etc., compared to familiar operations. Thus, the identification unit 13 may use different models depending on the purpose of the operation.

Table 602 is a table in which different models are used depending on the purpose. As shown in Table 602, as an example, Model A is a model used when the purpose of the operation is for purposes that are considered to be relatively frequent, such as financial transactions and commercial transactions. Model B is a model used when the purpose of the operation is electronic voting, electronic tax payment, etc. Model C is a model used when the purpose of the operation is administrative procedures other than electronic voting, electronic tax payment, etc. Furthermore, the biometric information model 20 may be equipped with both models of Table 601 and Table 602 in Figure 6.

As described above, classification accuracy can be further improved by using a model that best suits a given condition from multiple models trained according to various conditions.

(Method of comparison)
The method of comparing and evaluating the characteristics of the bioinformation in normal times and the characteristics of the bioinformation during a certain operation is not limited. As an example, the bioinformation model 20 may digitize the characteristics for each piece of bioinformation and output them. Since pulse and body temperature are expected to change significantly between normal times and abnormal times, the identification unit 13 may set a threshold value in advance for each of the pulse and body temperature. The bioinformation model 20 may output the difference between these values acquired during the operation and the normal values to the identification unit 13. Then, the identification unit 13 may compare the output difference with a preset threshold value to identify whether the operation was performed by the person's will. The bioinformation model 20 may also digitize and output the characteristics of a combination of some of the multiple pieces of bioinformation. The bioinformation model 20 may also digitize and output the characteristics of a combination of all of the multiple pieces of bioinformation. Then, the identification unit 13 may compare the output value with a threshold value. The method of digitizing the features is not limited.

Figure 7 is a conceptual diagram showing an example of a method in which some of multiple pieces of biometric information are combined and the model compares the features of the biometric information. As shown in the figure, the biometric information model 20 may be trained using combined biometric information that combines multiple pieces of biometric information under normal circumstances. The identification unit 13 may then use the biometric information model 20 to perform an identification process to determine whether or not an operation is being performed of the person's own volition. This allows the identification unit 13 to more accurately identify whether or not a certain operation is being performed of the person's own volition.

The illustrated example shows a case where two of four pieces of biometric information are combined to compare normal and operating conditions. Specifically, the model derives the characteristics of the two pieces of combined biometric information (the combination of two pieces of biometric information connected by a straight line in the figure) from the four pieces of biometric information: keystrokes, pulse, body temperature, and facial expression. The characteristics of the two pieces of combined biometric information are, for example, characteristics that have a correlation (high positive correlation or high negative correlation) such that when one is high, the other is also high, and when one is high, the other is low. Also, if the correlation between the two pieces of biometric information is low, the combination does not need to be used.

In this way, the biometric information model 20 learns in advance the degree of correlation between two combinations of biometric information under normal circumstances. Then, an evaluation index (such as a degree of agreement) indicating to what extent the degree of correlation between two combinations of biometric information obtained during a certain operation matches the degree of correlation under normal circumstances may be calculated and output. The identification unit 13 may then compare the output degree of agreement with a preset threshold value to identify whether or not the operation is being performed at the person's will.

The biometric information may include at least one of keystrokes input via a keyboard or touch panel, pulse, body temperature, facial expression, and gaze, and may also include other biometric information. However, it is preferable to use biometric information acquired by devices that are typically provided in terminals or owned by many operators. This is because it is possible to obtain biometric information from many operators and efficiently build a model.

(Average model)
It is preferable that the biometric information model 20 acquires and learns biometric information for each operator under normal circumstances. However, due to its nature, it is difficult to acquire a large amount of biometric information under normal circumstances for each operator, and it may be difficult to build a highly accurate model for each operator. Therefore, it is preferable that the biometric information model 20 learns biometric information of an unspecified number of operators under normal circumstances. This makes it possible to build an average biometric information model of the operator under normal circumstances.

(Individual model)
In addition, an average biometric information model 20 trained using biometric information of an unspecified number of operators in normal times may be trained with biometric information of an individual operator in normal times to construct a model dedicated to the individual operator by modifying the average model. When identifying an operation, the identification unit 13 uses a model dedicated to the operator (the person himself/herself) of that operation to identify whether the operation is performed by the operator's will. By constructing an individual model in this manner, a model with relatively high evaluation accuracy can be constructed even if the amount of biometric information for each operator is small.

The identification unit 13 may also set the threshold value referenced to identify whether an operation is being performed of the individual's own volition according to the amount of information in the acquired biometric information of the operator under normal circumstances. In other words, the threshold value may be changed according to the evaluation accuracy of the model. When the amount of information in normal biometric information acquired for each individual is small, the evaluation accuracy of the model for each individual is expected to be low. In such cases, the frequency of erroneous identification as abnormal can be reduced by setting a relatively generous threshold value (a threshold value with a high hurdle for determining abnormality). Then, as the amount of information in normal biometric information acquired for each individual increases, the threshold value may be changed to one that allows for more accurate identification of normal and abnormal conditions.

Note that the normal biometric information is acquired via the terminal 30 or a wearable device worn by the operator 40. In this case, it is preferable to acquire the biometric information with the consent of the operator 40. Alternatively, the operator 40 may be requested to simulate a situation that mimics an operation and the data acquired as normal biometric information. This allows more data to be acquired during normal times.

(Spoofing operation)
In the present exemplary embodiment, the explanation is given on the assumption that the operator 40 is the person identified by the identity verification information acquired by the identity verification information acquisition unit 11. However, the operator 40 may be a person who has acquired identity verification information of another person by some means and has performed an operation while impersonating that person. Even in this case, the information processing device 1A can identify whether or not the operation was performed by the will of the person identified by the identity verification information.

Specifically, if an operation is performed by a person impersonating the person identified by the identity verification information, the biometric information of the person (impersonator) acquired by the biometric information acquisition unit 12 differs from the person's normal biometric information. Therefore, the biometric information model 20 outputs an evaluation index indicating that the information is different from normal biometric information. Therefore, the identification unit 13 can identify that the operation was not performed by the person's will.

In addition, even if the principal willingly requests an agent to perform an operation, the agent's operation will be mistakenly identified as not being performed by the principal. In order to prevent such misidentification, the agent's normal biometric information may be learned in advance in biometric information model 20, and biometric information model 20 may compare the normal biometric information of the principal or agent and output an evaluation result.

(Protection of Privacy)
As mentioned above, since biometric information is personal information, it is preferable to obtain the information with the consent of the operator 40. From the viewpoint of privacy protection, it is preferable to encrypt the obtained biometric information when transmitting it. Furthermore, for images of a face, etc., only feature data may be transmitted, and the image itself may not be transmitted. Furthermore, it is preferable that the transmitted biometric information is processed in an encoded state within the information processing device 1A and cannot be decoded. By processing in this manner, it is guaranteed that even an administrator of the information processing device cannot access the biometric information itself, and the privacy of the operator can be secured.

(Effects of information processing device 1A)
As described above, in the information processing device 1A according to the present exemplary embodiment, the identification unit 13 acquires information indicating the importance or purpose of the operation of the terminal, selects one of the multiple biometric information models 20A, 20B, and 20C according to the information indicating the importance or purpose, and executes the identification process using the selected biometric information model. Therefore, according to the information processing device 1A according to the present exemplary embodiment, in addition to the effects of the information processing device 1 according to the exemplary embodiment 1, it is possible to more accurately identify whether the operation on the terminal is an operation based on the intention of the operator. In this way, if it becomes possible to accurately identify whether the operation on the terminal is performed by the person's intention, the safety of various transactions is improved. In addition, it is expected that procedures such as electronic voting and electronic tax payment, which are currently not widely used due to the high risk of impersonation, will gradually become more widespread.

Exemplary embodiment 3
A third exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first or second exemplary embodiment are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

(Configuration and Functions of Information Processing Device 1B)
8 is a block diagram showing the configuration of an information processing device 1B according to an exemplary embodiment 3 of the present invention. As shown in the figure, the information processing device 1B includes a control unit 10A, a communication unit 15, and a memory 16. The configurations of the communication unit 15 and the memory 16 are as described in the exemplary embodiment 1. The information processing device 1B generates an average biometric information model 20 or an individual biometric information model 20 of a plurality of operators 40 from the biometric information of the plurality of operators 40 in normal times.

The information processing device 1B is connected to the terminal 30 via an information communication network N such as the Internet by the communication unit 15 so as to be able to communicate with the terminal 30. The terminal 30 is a terminal operated by an operator 40. The information processing device 1B is also connected to the bioinformation model 20 via the communication unit 15 so as to be able to communicate with the terminal 30.

The control unit 10A includes a personal identification information acquisition unit 11, a biometric information acquisition unit 12, and a model construction unit 14. The configurations of the personal identification information acquisition unit 11 and the biometric information acquisition unit 12 are as described in exemplary embodiment 1. The model construction unit 14 constructs a biometric information model of the operator under normal circumstances from the operator's biometric information under normal circumstances.

(Flow of information processing of information processing device 1B)
9 is a flow diagram showing an outline of the flow of information processing performed by the information processing device 1B. As shown in the figure, in step 1, the model construction unit 14 inputs the personal identification information of the operator 40 acquired by the personal identification information acquisition unit 11 and the normal biometric information of the operator 40 acquired by the biometric information acquisition unit 12 to the biometric information model 20. Next, in step 2, the biometric information model 20 digitizes or mathematically converts the characteristics of the normal biometric information of the operator 40 from the received personal identification information of the operator 40 and the normal biometric information of the operator (person) 40, and stores the digitized or mathematically converted characteristics. The method of digitizing or mathematically converting the characteristics is not limited.

(Learning Example 1)
For example, as described in the exemplary embodiment 2, the bioinformation model 20 may learn information in which the features of each of the multiple pieces of bioinformation are quantified. For example, the bioinformation model 20 may learn the average value and standard deviation of the values of the pulse or body temperature. The bioinformation model 20 may also learn and store features that combine several pieces of multiple pieces of bioinformation. For example, if there is a correlation between two pieces of bioinformation, the correlation may be expressed as a formula and stored. The bioinformation model 20 may also learn and store features that combine all of the multiple pieces of bioinformation, quantified or expressed as a formula.

(Learning Example 2)
Furthermore, the biometric information model 20 may learn two or more pieces of biometric information that are in an invariant relationship among the multiple pieces of biometric information. The invariant pieces of biometric information are pieces of biometric information that always have a specific interlocking relationship, such as when one piece increases, the other piece also increases, or when one piece increases, the other piece decreases.

The biometric information model 20 learns combinations of biometric information data that have such invariant relationships among the biometric information data input from the model construction unit 14, and creates a relational equation. There may be multiple relational equations for invariant relationships. The relational equations can be generated by learning using machine learning.

The biometric information model 20, which has learned the relational equation, can output, as an example, an evaluation value indicating to what extent the biometric information acquired during an operation matches the previously learned relational equation. The identification unit 13 can comprehensively compare these multiple evaluation values with a predetermined threshold value to identify whether the operation was performed of the person's own will.

(Learning Example 3)
The bioinformation model 20 can learn using bioinformation data in normal times and data in abnormal times (or data simulating abnormal times). That is, the bioinformation model 20 may learn bioinformation in normal times and abnormal times from training bioinformation data labeled as normal times and training bioinformation data labeled as abnormal times, which are input from the model construction unit 14. Learning using labeled data can be performed by machine learning using a neural network or the like.

As an example, the trained biometric information model 20 can output the probability that the biometric information acquired during an operation is normal and the probability that it is abnormal. The identification unit 13 can compare this probability with a predetermined threshold value to identify whether the operation was performed willingly by the person in question.

It is preferable that the biometric information model 20 is constructed for each operator 40. However, it is difficult to obtain a large amount of biometric information for each operator 40. Therefore, as described in exemplary embodiment 2, the information processing device 1B may construct an average biometric information model of the operator 40 under normal circumstances using all the biometric information of the multiple operators 40. Then, the information processing device 1B may add the biometric information of each operator 40 to the average biometric information model to construct a model for each operator 40 individually.

(Effects of information processing device 1B)
As described above, in the information processing device 1B according to the present exemplary embodiment, the personal identification information acquisition unit 11 acquires personal identification information input from the terminal 30, the biometric information acquisition unit 12 acquires biometric information of the operator 40 of the terminal 30, and the model construction unit 14 constructs a biometric information model of the operator at normal times from the biometric information of the operator 40 at normal times. Therefore, according to the information processing device 1B according to the present exemplary embodiment, it is possible to acquire biometric information at normal times of the person (operator) identified by the input personal identification information, and construct a biometric information model that stores the characteristics of the person. Therefore, it is possible to obtain an effect that, when an operation using a terminal is performed, a biometric information model that can identify whether the operation was performed by the operator's intention or not can be constructed.

(Flow of information processing method)
Next, the flow of the information processing method according to this exemplary embodiment will be described with reference to the drawings. Fig. 10 is a flowchart showing the flow of the information processing method S2.

As shown in the figure, information processing method S2 includes the following steps. In step S21, at least one processor (e.g., personal identification information acquisition unit 11) acquires personal identification information input from the terminal. In addition, in step S22, at least one processor (e.g., biometric information acquisition unit 12) acquires biometric information of the operator of the terminal. In addition, in step S23, at least one processor (e.g., model construction unit 14) constructs a biometric information model of the operator under normal circumstances from the operator's biometric information under normal circumstances.

(Effects of information processing method S2)
As described above, in the information processing method S2 according to this exemplary embodiment, a configuration is adopted in which at least one processor acquires identity verification information input from a terminal, acquires biometric information of an operator of the terminal, and constructs a biometric information model of the operator under normal circumstances from the operator's biometric information under normal circumstances.

Therefore, according to the information processing method S2 of this exemplary embodiment, it is possible to obtain the effect of constructing a biometric information model that can identify whether or not an operation using a terminal was performed willingly by the person in question.

Exemplary embodiment 4
A fourth exemplary embodiment of the present invention will be described in detail with reference to the drawings. Note that components having the same functions as those described in the first to third exemplary embodiments are given the same reference numerals, and the description thereof will be omitted as appropriate.

(Configuration and Functions of Information Processing Device 1C)
Fig. 11 is a block diagram showing the configuration of an information processing device 1C according to this exemplary embodiment. As shown in the figure, the information processing device 1C includes a control unit 10C, a communication unit 15, a memory 16, and a display unit 19. The configurations of the communication unit 15 and the memory 16 are as described in the exemplary embodiment 1. The display unit 19 may be, for example, a display. Also, instead of or in addition to the display, an alarm lamp or an alarm sound generating device may be provided. Note that, in the example shown in Fig. 11, the display unit 19 is included in the information processing device 1C, but the display unit 19 may be disposed outside the information processing device 1C.

The information processing device 1C identifies whether or not a certain operation is being performed voluntarily by the person in question, and sequentially updates the biometric information identification model each time new biometric information under normal circumstances is acquired. The information processing device 1C is communicatively connected to the terminal 30 via an information communication network N such as the Internet by the communication unit 15. The information processing device 1C is also communicatively connected to the biometric information model 20 via the communication unit 15.

The control unit 10C includes a personal identification information acquisition unit 11, a biometric information acquisition unit 12, an identification unit 13, a model update unit 17, and an output unit 18. The configurations of the personal identification information acquisition unit 11, the biometric information acquisition unit 12, and the identification unit 13 are as described in the above-mentioned exemplary embodiments. The model update unit 17 updates the biometric information model 20. The model update unit 17 may have the same function as the model construction unit 14. The output unit 18 outputs information to be displayed on the display unit 19.

The information processing device 1C identifies whether or not a certain operation is being performed of the operator's will. The information processing device 1C also updates the biometric information model 20 of the operator 40 using newly acquired biometric information of the operator 40 under normal circumstances. In addition, in the information processing device 1C, when the identification unit 13 identifies that a certain operation is not being performed of the operator's will, the output unit 18 outputs warning information. The output warning information is transmitted to the display unit 19 and displayed.

Figure 12 is an example of warning information displayed on the display unit 19. As shown in the figure, the warning information may include information that an abnormal operation may have occurred, the date and time of the operation, information about the terminal on which the operation was performed, the operator, etc.

For example, if a remittance operation at a bank ATM is identified as an abnormal operation, such content may be displayed on a display unit 19 located in the security department of the bank. This allows a bank employee to ask the operator about the situation and check if there is anything suspicious. Also, if a camera or other device detects a clearly suspicious situation, measures can be taken to suspend processing at the ATM.

(Effects of information processing device 1C)
As described above, the information processing device 1C according to this exemplary embodiment is configured to include an output unit 18 that outputs warning information when the identification unit 13 identifies that a certain operation has not been performed of the user's will. Therefore, according to the information processing device 1C according to this exemplary embodiment, in addition to the effects of the information processing device 1 according to the exemplary embodiment 1, the information processing device 1C according to this exemplary embodiment can obtain an effect that a person in charge of security or the like can take some kind of action against an operation identified as abnormal by outputting warning information when an operation that may not have been performed of the user's will is found.

Furthermore, the information processing device 1C according to this exemplary embodiment is configured to include a model update unit 17 that updates the biometric information model 20 of the operator 40 using newly acquired biometric information of the operator 40 under normal circumstances. Therefore, according to the information processing device 1C according to this exemplary embodiment, in addition to the effects of the information processing devices 1 and 1A according to exemplary embodiments 1 and 2, the effect of being able to continue to build a more accurate model by updating the biometric information model 20 is obtained.

[Software implementation example]
Some or all of the functions of the information processing devices 1, 1A, 1B, 1C (hereinafter referred to as "information processing devices 1, etc.") may be realized by hardware such as an integrated circuit (IC chip), or by software.

In the latter case, the information processing device 1 etc. is realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 13. Computer C has at least one processor C1 and at least one memory C2. Memory C2 stores program P for operating computer C as information processing device 1 etc. In computer C, processor C1 reads and executes program P from memory C2, thereby realizing each function of information processing device 1 etc.

The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a microcontroller, or a combination of these. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination of these.

The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may further include a communications interface for transmitting and receiving data to and from other devices. The computer C may further include an input/output interface for connecting input/output devices such as a keyboard, mouse, display, and printer.

The program P can also be recorded on a non-transitory, tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communications network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[Additional Note 1]
The present invention is not limited to the above-described embodiment, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiment are also included in the technical scope of the present invention.

[Additional Note 2]
Some or all of the above-described embodiments can be described as follows. However, the present invention is not limited to the following described aspects.
(Appendix 1)
An information processing device comprising: an identity verification information acquisition means for acquiring identity verification information input from a terminal; a biometric information acquisition means for acquiring biometric information of an operator of the terminal; and an identification means for executing an identification process for identifying whether or not the operation is being performed of the individual's will by referring to one or more biometric information models learned using the operator's normal biometric information, the biometric information acquired by the biometric information acquisition means, and the identity verification information acquired by the identity verification information acquisition means.

According to the above configuration, it is possible to identify whether an operation on a terminal is based on the operator's will, based on the personal authentication information input by the operator and the operator's biometric information.

(Appendix 2)
The information processing device described in Appendix 1, characterized in that the identification means acquires information indicating the importance of an operation of the terminal, selects one of a plurality of the biometric information models according to the acquired information indicating the importance, and executes the identification process using the selected biometric information model.

According to the above configuration, it is possible to more accurately identify whether operations on the terminal are based on the user's own will.

(Appendix 3)
The information processing device described in Appendix 1, characterized in that the identification means acquires information indicating a purpose of operation of the terminal, selects one of a plurality of the biometric information models according to the acquired information indicating the purpose of the operation, and executes the identification process using the selected biometric information model.

According to the above configuration, it is possible to more accurately identify whether operations on the terminal are based on the user's own will.

(Appendix 4)
The information processing device described in Appendix 2, characterized in that the importance of the operation includes at least one of the type of financial transaction, the amount of the financial transaction, the type of commercial transaction, the amount of the commercial transaction, the counterparty of the operation, and the frequency of operations performed on the counterparty in the past.

According to the above configuration, it is possible to more accurately identify whether operations on the terminal are based on the user's own will.

(Appendix 5)
The information processing device according to claim 3, wherein the purpose of the operation includes at least one of a financial transaction, a commercial transaction, an administrative procedure, paying a tax, and remote voting.

According to the above configuration, it is possible to more accurately identify whether operations on the terminal are based on the user's own will.

(Appendix 6)
The information processing device described in any one of Appendices 1 to 5, characterized in that the identification means sets a threshold value to be referenced to identify whether the operation is being performed of the person's will, based on the amount of information of the operator's normal biometric information acquired.

According to the above configuration, the frequency of erroneous identification of an abnormality can be reduced by changing the threshold depending on the accuracy of the model.

(Appendix 7)
The information processing device described in any one of Appendices 1 to 6, characterized in that the identification means records the acquired biometric information of the operator as operation information in an abnormal event when the result of the identification process indicates that the operation was not performed of the person's will.

According to the above configuration, the operation information that is confirmed to be abnormal can be used, for example, for learning a model. This can further improve the accuracy of the model.

(Appendix 8)
The information processing device according to any one of appendices 1 to 7, characterized in that the biometric information model is learned using combined biometric information that combines a plurality of pieces of biometric information under normal circumstances, and the identification means performs the identification process using the biometric information model to determine whether the operation is being performed of the person's will.

According to the above configuration, it is possible to more accurately identify whether or not a certain operation is being performed willingly by the person in question.

(Appendix 9)
9. The information processing device according to claim 1, wherein the biometric information includes at least one of keystrokes input via a keyboard or touch panel, pulse, body temperature, facial expression, and gaze.

According to the above configuration, since these types of biometric information are easy to obtain, it is possible to obtain the biometric information of a large number of operators and efficiently construct models.

(Appendix 10)
10. The information processing device according to any one of claims 1 to 9, further comprising an output means for outputting warning information when the identification means identifies that the operation has not been performed of the person's will.

According to the above configuration, security personnel can take some kind of action against operations that are identified as abnormal.

(Appendix 11)
An information processing device comprising: a personal identification information acquisition means for acquiring personal identification information input from a terminal; a biometric information acquisition means for acquiring biometric information of an operator of the terminal; and a model construction means for constructing a biometric information model of the operator under normal circumstances from the biometric information of the operator under normal circumstances.

According to the above configuration, when an operation is performed using a terminal, a biometric information model can be constructed that can identify whether or not the operation was performed willingly by the person.

(Appendix 12)
An information processing method including: at least one processor acquiring personal identification information input from a terminal; acquiring biometric information of an operator of the terminal; and identifying whether or not the operation is being performed of the operator's own will by referring to one or more biometric information models trained using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information.

According to the above configuration, the same effect as that of Appendix 1 can be obtained.

(Appendix 13)
An information processing program for causing a computer to execute the following processes: acquiring personal identification information input from a terminal; acquiring biometric information of an operator of the terminal; and identifying whether or not the operation is being performed of the person's own will by referring to one or more biometric information models learned using the operator's normal biometric information, the acquired biometric information, and the acquired personal identification information.

(Appendix 14)
11. The information processing device according to any one of claims 1 to 10, further comprising a model update means for updating the biometric information model.

According to the above configuration, the biometric information model can be updated while performing the classification process, thereby further improving classification accuracy.

[Additional Note 3]
A part or all of the above-described embodiments can be further expressed as follows.
An information processing device comprising at least one processor, the processor executing an identity verification information acquisition process for acquiring identity verification information input from a terminal, a biometric information acquisition process for acquiring biometric information of an operator of the terminal, and an identification process for identifying whether or not the operation is being performed of the operator's own will by referring to one or more biometric information models learned using the operator's normal biometric information, the acquired biometric information, and the acquired identity verification information.

The information processing device may further include a memory, and the memory may store a program for causing the processor to execute the personal identification information acquisition process, the biometric information acquisition process, and the identification process. The program may also be recorded on a computer-readable, non-transitory, tangible recording medium.

Reference Signs List 1, 1A, 1B, 1C... Information processing device 11... Personal identification information acquisition unit 12... Biometric information acquisition unit 13... Identification unit 14... Model construction unit 15... Communication unit 16... Memory 17... Model update unit 18... Output unit 19... Display unit 20... Biometric information model 30... Terminal 40... Operator

Claims (10)

An identity verification information acquisition means for acquiring identity verification information input from a terminal;
a biometric information acquiring means for acquiring biometric information of an operator of the terminal;
a plurality of biometric information models learned using biometric information of the operator acquired when the operator performs an operation based on his/her original intention , the plurality of biometric information models for the operator identified by the identity verification information, and an identification means for executing an identification process for identifying whether or not the operation is being performed based on the operator's original intention, using the plurality of biometric information models for the operator identified by the identity verification information and the biometric information acquired by the biometric information acquisition means;
Equipped with
The identification means is
Acquire information indicating the importance of an operation of the terminal;
Selecting one of the plurality of biometric information models according to the acquired information indicating the importance;
The identification process is performed using the selected biometric information model.
Information processing device. An identity verification information acquisition means for acquiring identity verification information input from a terminal;
a biometric information acquiring means for acquiring biometric information of an operator of the terminal;
a plurality of biometric information models learned using biometric information of the operator acquired when the operator performs an operation based on his/her original intention, the plurality of biometric information models for the operator identified by the identity verification information, and an identification means for executing an identification process for identifying whether or not the operation is being performed based on the operator's original intention, using the plurality of biometric information models for the operator identified by the identity verification information and the biometric information acquired by the biometric information acquisition means;
Equipped with
The identification means is
Acquire information indicating the purpose of the operation of the terminal;
selecting one of the plurality of biometric information models according to the acquired information indicating a purpose of the operation;
The identification process is performed using the selected biometric information model.
Information processing device. 2. The information processing device according to claim 1, wherein the importance of the operation includes at least one of the type of financial transaction, the amount of the financial transaction, the type of commercial transaction, the amount of the commercial transaction, the counterparty of the operation, and the frequency of operations performed on the counterparty in the past . The information processing device according to claim 2 , wherein the purpose of the operation includes at least one of a financial transaction, a commercial transaction, an administrative procedure, a tax payment, and a remote voting. The information processing device according to any one of claims 1 to 4, characterized in that the identification means sets a threshold value to be referenced to identify whether the operation is being performed of the operator's own will, based on the amount of biometric information of the operator acquired when the operator performs the operation based on his or her original will . The information processing device according to any one of claims 1 to 5, characterized in that when the result of the identification process indicates that the operation was not performed of the person's will, the identification means records the acquired biometric information of the operator as operation information in an abnormal event. At least one processor
Obtaining identity verification information entered from the terminal;
acquiring biometric information of an operator of the terminal;
A plurality of biometric information models are learned using biometric information of the operator in normal conditions acquired when the operator performs an operation based on his/her original intention , and the plurality of biometric information models for the operator identified by the identity verification information and the acquired biometric information are used to identify whether the operation is being performed based on the operator's original intention;
Including,
In the identifying,
Acquire information indicating the importance of an operation of the terminal;
Selecting one of the plurality of biometric information models according to the acquired information indicating the importance;
Using the selected biometric information model, it is determined whether the operation is performed at the individual's will.
Information processing methods. At least one processor
Obtaining identity verification information entered from the terminal;
acquiring biometric information of an operator of the terminal;
A plurality of biometric information models are learned using biometric information of the operator in normal conditions acquired when the operator performs an operation based on his/her original intention, and the plurality of biometric information models for the operator identified by the identity verification information and the acquired biometric information are used to identify whether the operation is being performed based on the operator's original intention;
Including,
In the identifying,
Acquire information indicating the purpose of the operation of the terminal;
selecting one of the plurality of biometric information models according to the acquired information indicating a purpose of the operation;
Using the selected biometric information model, it is determined whether the operation is performed at the individual's will.
Information processing methods. On the computer,
A process of acquiring identity verification information input from a terminal;
A process of acquiring biometric information of an operator of the terminal;
a process of identifying whether the operation is being performed at the operator's will by referring to a plurality of biometric information models for the operator identified by the identity verification information, the biometric information being learned using the operator's normal biometric information acquired when the operator performs an operation based on the operator's original will , and the acquired biometric information;
Run the command ,
In the identifying process, the computer
acquiring information indicating the importance of an operation of the terminal;
Selecting one of the plurality of biometric information models according to the acquired information indicating the importance;
Using the selected biometric information model, it is determined whether the operation is performed by the person himself/herself.
Information processing program for. On the computer,
A process of acquiring identity verification information input from a terminal;
A process of acquiring biometric information of an operator of the terminal;
a process of identifying whether the operation is being performed at the operator's will by referring to a plurality of biometric information models for the operator identified by the identity verification information, the biometric information being learned using the operator's normal biometric information acquired when the operator performs an operation based on the operator's original will, and the acquired biometric information;
Run the command,
In the identifying process, the computer
Acquire information indicating a purpose of operation of the terminal;
selecting one of the plurality of biometric information models according to the acquired information indicating the purpose of the operation;
Using the selected biometric information model, it is determined whether the operation is performed by the person himself/herself.
Information processing program for.

Images