JP6509137B2 - Authentication device, authentication method and authentication program - Google Patents

Description

  The present invention relates to an authentication device, an authentication method, and an authentication program.

  In recent years, techniques for authenticating a user are known. As a technique related to such user authentication, there is known a technique for authenticating a user using a plurality of pieces of information. For example, in such a technology, authentication information generated by combining various action history information such as purchase history, entering and leaving a building, merging with acquaintances, photographing of an image, etc. is compared with the input from the user. Authentication of the user.

JP, 2011-59837, A JP 2009-230653 A

  However, in the above-mentioned prior art, it has not always been possible to authenticate the user with high accuracy. For example, in the above-mentioned prior art, it is difficult to dynamically reflect the change of the user's behavior in the authentication, since the authentication of the user is performed by comparing the authentication information generated in advance and the input from the user. . From such a thing, in said prior art, it was not necessarily able to authenticate a user with high precision.

  This application is made in view of the above, and it aims at providing an authentication device, an authentication method, and an authentication program which can authenticate a user with high accuracy.

  The authentication device according to the present application includes: an acquisition unit that acquires a user's action history; a learning unit that learns a feature of the user based on the user's action history acquired by the acquisition unit; and the learning unit The information processing apparatus may further include an authentication unit that authenticates the user based on the learning result and the input information on the user's behavior.

  According to one aspect of the embodiment, the effect of being able to authenticate the user with high accuracy is achieved.

FIG. 1 is an explanatory view showing an example of an authentication process by the authentication system according to the embodiment. FIG. 2 is a diagram showing an example of the configuration of the authentication device according to the embodiment. FIG. 3 is a diagram illustrating an example of the action information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of the feature information storage unit according to the embodiment. FIG. 5 is a flowchart showing an authentication processing procedure by the authentication device according to the embodiment. FIG. 6 is a diagram showing an example of the feature of the user. FIG. 7 is a hardware configuration diagram showing an example of a computer for realizing the function of the authentication device.

  Hereinafter, an authentication apparatus, an authentication method, and a mode for carrying out an authentication program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the authentication device, the authentication method, and the authentication program according to the present application are not limited by the embodiment. Further, in the following embodiments, the same parts will be denoted by the same reference numerals, and overlapping descriptions will be omitted.

[1. Embodiment]
[1-1. Authentication process according to the embodiment]
First, an example of the authentication process according to the embodiment will be described with reference to FIG. FIG. 1 is an explanatory view showing an example of an authentication process by the authentication system 1 according to the embodiment. In the example of FIG. 1, an authentication process for authenticating the user U1 having the terminal device 10 is performed.

  As shown in FIG. 1, the authentication system 1 includes a terminal device 10 and an authentication device 100. The terminal device 10 and the authentication device 100 are communicably connected to a network by wire or wirelessly.

  The terminal device 10 is an information processing device such as a smartphone, a PC (Personal Computer), a tablet terminal, a mobile phone, or a PDA (Personal Digital Assistant). The authentication device 100 is a server device that authenticates a user.

  Specifically, the authentication device 100 first acquires the action history of the user U1 (step S1). For example, the authentication device 100 acquires, as the action history of the user U1, information regarding the content of the action performed by the user U1 and the date and time when the action is performed. As an example, the authentication device 100 acquires information indicating that the user U1 has “stayed in Shibuya” at the date and time “2015/12/10 11:00”. In another example, the authentication device 100 acquires information indicating that the user U1 has accessed “A site” at the date and time “2015/12/10 11:04”. In another example, the authentication device 100 acquires information indicating that the user U1 has used the “X application” at the date and time “2015/12/10 11:10”. Then, the authentication apparatus 100 associates the acquired content of the action performed by the user U1 and the information regarding the date and time of the action with the user ID assigned to the user U1 in the action information storage unit 121 illustrated in FIG. Store.

Subsequently, the authentication device 100 learns the features of the user U1 (step S2). Specifically, the authentication device 100 learns the feature of the user U1 based on the acquired action history of the user U1. For example, the authentication device 100 generates a model indicating the feature of the user U1 by using the action history of the user U1 and the action history of another user as learning data. As an example, the authentication apparatus 100 calculates a weight _w 1 to w _n elements _x 1 ~x _n indicating characteristics of the user U1 by Equation (1) below as a model showing the characteristics of the user U1.

Here, the elements x _{1 to} x _n indicate various features such as, for example, the place where the user stays, the site of the web page to view, the application to use, the device to use, and the like. Weight _w 1 to w _n denotes a weighting characteristics indicated elements _x 1 ~x _n. For example, the authentication device 100 calculates a value that is higher as the weight of an element that strongly influences the value of “y” of the model indicating the feature of the user U1. As an example, the authentication device 100 uses the user U1 and the other user's action history to use the location where the user U1 stays relatively more than other users, the site of the web page to view, application calculates a weight _w 1 to w _n higher values of the elements _x 1 ~x _n corresponding to the device to be used.

  Thereafter, the authentication device 100 receives the input information (step S3). Specifically, when the user U1 operates the terminal device 10 and transmits a request for user authentication to the authentication device 100, the authentication device 100 receives, from the terminal device 10, input information on the action of the user U1. For example, the authentication apparatus 100 relates, as input information, to a place where the user U1 is currently staying, a site of a web page visited most recently, an application used most recently, a device used when requesting authentication, etc. Information is received from the terminal device 10.

Subsequently, the authentication device 100 authenticates the user U1 based on the learning result learned and the input information on the action of the user U1 (step S4). Specifically, the authentication device 100 performs a weight w ₁ to w _n elements x ₁ ~x _n to form a model showing the characteristics of the user U1 as a learning result, the authentication of the user based on the input information. For example, the authentication device 100 calculates the value of “y” calculated by substituting the input information into the element corresponding to the action indicated by the input information among the elements x ₁ to x _n forming the model indicating the feature of the user U ₁ Is equal to or greater than a predetermined threshold value, the user U1 is authenticated. Thereafter, the authentication device 100 transmits the authentication result to the terminal device 10 (step S5).

  Thus, the authentication device 100 according to the embodiment acquires a user's action history. In addition, the authentication device 100 learns the feature of the user based on the acquired action history of the user. In addition, the authentication device 100 authenticates the user based on the learning result learned and the input information on the user's action.

  Thus, the authentication device 100 can authenticate the user based on the result of learning the feature from the action history of the user, and thus can authenticate the user with high accuracy. For example, since the authentication device 100 can authenticate the user using the feature based on the user's past behavior and the input information indicating the current situation of the user, the authentication accuracy can be enhanced.

  In addition, the authentication device 100 according to the embodiment authenticates the user based on the weight of the element forming the model indicating the feature of the user as the learning result and the input information. As a result, the authentication device 100 can authenticate the user using the element indicating the user's characteristic and the element indicated by the input information, so that the user can be authenticated with high accuracy.

  Although FIG. 1 illustrates an example in which the authentication system 1 includes one terminal device 10 and one authentication device 100, the authentication system 1 includes a plurality of terminal devices 10 and a plurality of terminal devices 10. One authentication device 100 may be included.

  Also, FIG. 1 shows the place where the user visits, the site of the web page to browse, the application to use, and the device to use as an example of the elements of the model for simplifying the explanation, but the elements described above are actually The model is formed by various elements indicating the features of the user.

[1-2. Configuration of Authentication Device According to Embodiment]
Next, the configuration of the authentication device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an exemplary configuration of the authentication device 100 according to the embodiment. As shown in FIG. 2, the authentication device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The authentication apparatus 100 includes an input unit (for example, a keyboard or a mouse) that receives various operations from a manager or the like who uses the authentication apparatus 100, and a display unit (for example, a liquid crystal display or the like) for displaying various information. You may have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). Specifically, the communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from the terminal device 10 via the network. For example, the communication unit 110 transmits and receives a user's action history, input information used to authenticate the user, and an authentication result.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes an action information storage unit 121 and a feature information storage unit 122.

(About the action information storage unit 121)
The action information storage unit 121 stores information on the action history of the user. Specifically, the behavior information storage unit 121 stores, for each user, information on the behavior performed by the user. Here, FIG. 3 illustrates an example of the action information storage unit 121 according to the embodiment. As shown in FIG. 3, the action information storage unit 121 has items such as “user ID”, “date and time”, and “action”.

  "User ID" indicates identification information for identifying a user. For example, “user ID” indicates identification information for identifying a user. For example, the “user ID” stores a character string such as a unique alphanumeric character assigned individually for each user. "Date" indicates the time when the user took action. For example, the year, month, day, time, etc. in which the user performed an action are stored in the “date and time”.

  "Action" indicates the content of the action performed by the user. For example, the “action” stores the place where the user has stayed, the site visited, information on the started application, and the like. In addition, the information regarding the action shown in FIG. 3 is only an example, and the action information storage unit 121 actually stores many pieces of information regarding other various actions.

  That is, FIG. 3 shows an example in which the user identified by the user ID “U1” “stays in Shibuya” at the date and time “2015/12/10 11:00”. The user identified by the user ID “U2” is an example in which “access to site B” is performed at the date and time “2015/12/10 11:00”.

(About the feature information storage unit 122)
The feature information storage unit 122 stores information on the features of the user. Specifically, the feature information storage unit 122 stores, for each user, information on an element forming a model indicating the feature of the user. Here, FIG. 4 illustrates an example of the feature information storage unit 122 according to the embodiment. As shown in FIG. 4, the feature information storage unit 122 has items such as “user ID” and “feature”.

  "User ID" indicates identification information for identifying a user. For example, the “user ID” stores a character string such as a unique alphanumeric character assigned individually for each user. "Feature" indicates information indicating the feature of the user. For example, the “feature” has items such as “position information”, “browsing information”, “application information”, and “device information”. As an example, “position information” stores a weight whose element is the place where the user stays. Here, as one aspect of the “weight”, a higher value is stored as the location where the user visits is higher. The “browse information” stores a weight having a site browsed by the user as an element. Here, as one aspect of the “weight”, a higher value is stored as the site at which the user browses more frequently. The “application information” stores a weight having an application used by the user as an element. Here, as one aspect of the “weight”, a higher value is stored as the application used more frequently by the user. The “device information” stores a weight whose element is the device used by the user. Here, as one aspect, the “weight” stores a higher value as the device is used more frequently by the user.

  That is, FIG. 4 shows an example having the feature that the user identified by the user ID “U1” has a higher frequency of staying in “Shibuya” than “Shinagawa”. Also, an example is shown in which the user identified by the user ID "U1" has a feature that the frequency of browsing "A site" is higher than "B site". Also, an example is shown in which the user identified by the user ID “U1” has a feature that the frequency of using “X application” is higher than that of “Y application”. Also, an example is shown in which the user identified by the user ID "U1" has a feature that the frequency of using the "V phone" is higher than that of the "W personal computer".

(About the control unit 130)
In the control unit 130, for example, various programs (corresponding to an example of an authentication program) stored in a storage device in the authentication device 100 by a central processing unit (CPU), a micro processing unit (MPU), etc. It is realized by being executed as Further, the control unit 130 is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 2, the control unit 130 includes an acquisition unit 131, a learning unit 132, and an authentication unit 133, and implements or executes the function or action of the information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and any other configuration may be used as long as an authentication process to be described later is performed. Moreover, the connection relation of each processing unit included in the control unit 130 is not limited to the connection relation illustrated in FIG. 2, and may be another connection relation.

(About acquisition unit 131)
The acquisition unit 131 acquires the action history of the user. Specifically, the acquisition unit 131 acquires information on the user's behavior from the terminal device 10 that the user has. When acquiring information on the user's action from the terminal device 10, the acquiring unit 131 stores the acquired information on the user's action in the action information storage unit 121. For example, the acquisition unit 131 stores the content of the action performed by the user and the information on the date and time of the action in the action information storage unit 121 in association with the user ID assigned to the user.

  As an example, the acquisition unit 131 acquires, as information related to the user's behavior, a stay time, a stay frequency, a stay date and the like of a place where the user has stayed. In another example, the acquisition unit 131 acquires the time when the user accesses the site of the web page, the stay time, the information regarding the device, and the like as the information regarding the user's behavior. In another example, as the information on the user's action, the acquiring unit 131 may calculate the number of responses and the frequency of various sensors (for example, a GPS sensor, a gyro sensor, an acceleration sensor, an illuminance sensor, a proximity sensor, etc.) included in the terminal device 10 , Measurement value, degree of abnormality etc. In another example, the acquisition unit 131 acquires, as the information on the user's behavior, the usage status, frequency, and the like of the service used by the user. In another example, the acquisition unit 131 acquires the usage frequency of the application used by the user, cache information, an operation log in the smartphone, and the like as the information on the user's action. In another example, the acquisition unit 131 acquires information on an action associated with security authentication as information on an action of the user. For example, the acquisition unit 131 acquires success or failure of an ID or a password, biometric information such as a fingerprint or a voiceprint, an inquiry about a user, a user's answer to such a question, and the like as an action accompanying security authentication.

(About the learning unit 132)
The learning unit 132 learns the feature of the user based on the action history of the user acquired by the acquiring unit 131. Specifically, the learning unit 132 generates a model indicating the feature of the user based on the action history of the user. This is because the identity of the user appears in the action history of the user. More specifically, the learning unit 132 uses the action history of the user stored in the action information storage unit 121 as learning data to generate a model indicating the feature of the user for each user. For example, the learning unit 132 refers to the action history of the user stored in the action information storage unit 121, and weights w ₁ of the elements x ₁ to x _n forming a model such as the above (1) indicating the features of the user. to calculate the ~w _n. As an example, the learning unit 132 calculates a value that is higher as the weight of an element that strongly influences the value of “y” of the model indicating the user's feature. In one aspect, the learning unit 132 uses the action history of the user whose model shows a feature and the action history of other users, and places where they stay relatively more compared to other users, and Web browsing page of the site, the application used to calculate the weight _w 1 to w _n higher values of the elements _x 1 ~x _n corresponding to the device to be used. In other words, the learning unit 132 calculates the weights _w 1 to w _n higher value of its own elements _x 1 ~x _n for the user. Then, the learning unit 132 stores the calculated weights w _{1 to} w _n in the feature information storage unit 122 in association with the elements x ₁ to x _n . Thereby, the learning unit 132 generates a model indicating the feature of the user.

(About the authentication unit 133)
The authentication unit 133 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action. Specifically, the authentication unit 133 authenticates the user based on the weight of the element forming the model indicating the feature of the user as the learning result and the input information. For example, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the user's action schedule and the input information. In other words, the authentication device 100 authenticates the user by dynamically changing the weight of the element according to the situation of the user. Here, the weights of the elements do not become the same each time since the action history is sequentially accumulated even for the same user, and there are elements that are easy to change and some elements that are hard to change. Therefore, the authentication unit 133 adjusts the weight for each element according to the reliability of the element. For example, the authentication unit 133 adjusts the weight of the element to be low, assuming that the more the variable element is less reliable. On the other hand, the authentication unit 133 adjusts the weight of the element to be high, assuming that the less variable element is more reliable. As an example, a variable element or a variable element that is easy to change is determined by dividing learning data every several periods and calculating an average or variance for each weight. Note that the action schedule of the user is acquired from, for example, the scheduler of the user, the contents of the mail, and the like.

  As an example, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the predetermined behavior set in advance among the user's behavior schedule and the input information. Here, predetermined types of actions set in advance are those that have short-term effects such as travel, participation in events, events of the anniversary, actions at the time of disasters and changes in the weather, etc. There are long-term effects such as change, birth, job change, job transfer, transfer, hospital admission, etc. In one aspect, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the information input to the user's schedule as the action schedule of the user and the input information. For example, the authentication unit 133 corrects the weight of the element corresponding to the place of stay of the user to “0” when the information on the schedule of the trip or business trip is input in the schedule of the user. In other words, the authentication unit 133 flexibly detaches the element forming the model indicating the feature of the user, reflecting the future schedule of the user. That is, the authentication unit 133 authenticates the user excluding an element which is presumed to be an abnormality in the future. The place of stay, which is very rare for the user to be authenticated, is treated as noise exceptionally to improve authentication accuracy.

[1-3. Authentication processing procedure according to the embodiment]
Next, the procedure of the authentication process by the authentication device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an authentication processing procedure by the authentication device 100 according to the embodiment.

  As shown in FIG. 5, the authentication device 100 acquires a user's action history (step S101). For example, the authentication device 100 acquires information on the user's behavior from the terminal device 10 that the user has. Here, when the authentication device 100 does not acquire the user's action history (step S101; No), the authentication device 100 stands by until the user's action history is acquired.

  Subsequently, when acquiring the information on the user's action from the terminal device 10 (Step S101; Yes), the authentication device 100 stores the acquired information on the user's action in the action information storage unit 121 (Step S102). For example, the authentication device 100 stores the content of the action performed by the user and the information on the date and time of the action in the action information storage unit 121 in association with the user ID assigned to the user.

  Thereafter, the authentication device 100 learns the feature of the user based on the action history of the user acquired by the acquisition unit 131 (step S103). For example, the authentication device 100 generates a model indicating the feature of the user based on the action history of the user.

  Then, the authentication device 100 stores the learned result of learning in the feature information storage unit 122 (step S104). For example, as a learning result, the authentication device 100 stores, in the feature information storage unit 122, the weight of an element forming a model indicating the feature of the user.

  Subsequently, the authentication device 100 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action (step S105). For example, the authentication device 100 authenticates the user based on the weight of the element forming the model indicating the feature of the user as the learning result and the input information.

[1-4. Effect of Embodiment]
As described above, the authentication device 100 according to the embodiment includes the acquisition unit 131, the learning unit 132, and the authentication unit 133. The acquisition unit 131 acquires the action history of the user. The learning unit 132 learns the feature of the user based on the action history of the user acquired by the acquiring unit 131. The authentication unit 133 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action.

  Thus, the authentication device 100 can authenticate the user based on the result of learning the feature from the action history of the user, and thus can authenticate the user with high accuracy. For example, since the authentication device 100 can authenticate the user using the feature based on the user's past behavior and the input information indicating the current situation of the user, the authentication accuracy can be enhanced.

  Further, in the authentication device 100 according to the embodiment, the authentication unit 133 authenticates the user based on the weight of the element forming the model indicating the feature of the user as the learning result and the input information. As a result, the authentication device 100 can authenticate the user using the element indicating the user's characteristic and the element indicated by the input information, so that the user can be authenticated with high accuracy.

  Further, in the authentication device 100 according to the embodiment, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the action schedule of the user and the input information. As a result, the authentication device 100 can immediately reflect the user's action schedule on the model, and thus can authenticate the user with higher accuracy.

  In addition, in the authentication device 100 according to the embodiment, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the predetermined action set in advance among the action plans of the user and the input information. . Thus, the authentication apparatus 100 can perform authentication in consideration of a future schedule affecting the user, and can authenticate the user with higher accuracy. For example, since the authentication device 100 can perform authentication in consideration of such an action when the user intends to perform an action different from usual, the authentication accuracy can be enhanced.

  In addition, in the authentication device 100 according to the embodiment, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the information input to the user's schedule as the action schedule of the user and the input information. . Thus, the authentication device 100 can perform user authentication in consideration of the user's future schedule, and can therefore authenticate the user with higher accuracy. For example, the authentication device 100 can improve the authentication accuracy by setting the weight of the element related to the place to “0” when the business trip is input in the schedule.

[2. Modified example]
The authentication device 100 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. So, below, other embodiment of said authentication apparatus 100 is described.

[2-1. Correct the weights of the elements that form the model based on the action history]
In the above embodiment, an example in which the authentication device 100 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action has been described. Here, the authentication device 100 may authenticate the user using the weight of the element corrected based on the user's action history.

  Specifically, the authentication unit 133 of the authentication device 100 authenticates the user based on the weight of the element corrected based on the action history of the user and the input information. For example, the authentication device 100 authenticates the user based on the weight of the element corrected based on the action history on the service supporting communication with another user as the action history of the user and the input information. In other words, the authentication device 100 authenticates the user based on the weight of the element corrected based on the user's action history on the SNS (Social Networking Service) and the input information. As an example, the authentication device 100 authenticates the user based on the weight of the element corrected based on the posting history in which the user posted the message on the SNS, and the input information. In another example, the authentication device 100 corrects an element weight corrected based on an action related to an interaction with another user who is connected on the SNS who is interested in the field to which the user has not been interested until now, and the input information And authenticate the user based on

  As described above, the authentication device 100 according to the modification authenticates the user based on the weight of the element corrected based on the action history of the user and the input information. As a result, the authentication device 100 can authenticate the user using the weight of the element reflecting the user's action history, so that the authentication accuracy of the user can be further enhanced.

  In addition, the authentication device 100 according to the modification authenticates the user based on the weight of the element corrected based on the action history on the service supporting communication with other users as the action history of the user and the input information. Do. Thus, the authentication device 100 can authenticate the user using the weight of the element reflecting the user's action on the SNS, so that the authentication accuracy of the user can be further enhanced.

[2-2. Correct the weights of the elements that form the model based on the life stage]
In the above embodiment, an example in which the authentication device 100 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action has been described. Here, the authentication device 100 may perform user authentication using the element weight corrected based on the user's life stage.

  Specifically, the authentication unit 133 of the authentication device 100 authenticates the user based on the weight of the element corrected based on the user's action history and the input information. For example, the authentication device 100 first determines the user's situation from various histories such as the user's search history, the Web page browsing history, and the product purchase history. For example, when a user travels, the authentication device 100 belongs to any stage, such as a situation where a user visits a place to travel, a situation when making a reservation for a hotel or airline ticket, and a situation when purchasing belongings necessary for a trip. It is determined from the user's action history whether the situation is Thereafter, the authentication device 100 corrects the weight of the element forming the model based on the determined user's situation. Then, the authentication device 100 authenticates the user based on the corrected element weight and the input information.

  As described above, the authentication device 100 according to the modification authenticates the user based on the weight of the element corrected based on the user's situation based on the user's action history and the input information. Thus, the authentication device 100 can perform user authentication using the weight of the element corrected according to the user's life stage, so that the user authentication accuracy can be further enhanced.

[2-3. Correct input information]
In the above embodiment, an example in which the authentication device 100 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action has been described. Here, the authentication device 100 may correct not only the weights of the elements forming the model but also the input information.

  Specifically, the authentication unit 133 of the authentication device 100 authenticates the user based on the learning result and the input information corrected based on the user's action history. For example, the authentication device 100 corrects the input information based on the place where the user has stayed in the past, the site of the web page browsed, the used application, and the used device as the user's action history. As an example, when the user is staying at a place that is rarely visited, the authentication device 100 corrects the input information by subtracting information corresponding to the place among the input information.

  As described above, the authentication device 100 according to the modification authenticates the user based on the learning result and the input information corrected based on the action history of the user. As a result, the authentication device 100 can authenticate the user using the input information reflecting the user's action history, so that the authentication accuracy of the user can be further enhanced.

[2-4. Visualize user characteristics]
In the above embodiment, an example in which the authentication device 100 authenticates the user based on the learning result learned by the learning unit 132 and the input information on the user's action has been described. Here, the authentication device 100 may use the learning result as information for visualizing the characteristics of the user as well as the authentication of the user. This point will be described with reference to FIG. FIG. 6 is a diagram showing an example of the feature of the user. For example, the authentication device 100 classifies the elements forming the model indicating the feature of the user into categories such as "position information system", "browse information system", "sensor information system", "time system", "smart phone log system", etc. Do. Subsequently, the authentication device 100 adds the weights of the elements forming the model indicating the feature of the user into categories. Then, as shown in FIG. 6, the authentication device 100 displays the sum of the weights of the elements of each category in the form of a graph. The example of FIG. 6 indicates that the user is characterized by the “position information system” and the “time system” from the “viewing information system”, the “sensor information system”, and the “smart phone log system”. As a result, the authentication device 100 can display the features of the user by category, so that it is possible to comprehend relatively easily what category the user has features. Therefore, the authentication device 100 can use, for example, information indicating the characteristics of the user for marketing and advertisement distribution.

[2-5. Application to terminal device]
In the above embodiment, the authentication device 100 has been described as an example of a server. Here, the authentication device 100 may be applied not only to the server but also to the terminal device 10 owned by the user. In this case, the terminal device 10 includes an acquisition unit that acquires the user's action history, a learning unit that learns the user's features based on the user's action history acquired by the acquisition unit, and a learning result learned by the learning unit And an authentication unit that authenticates the user based on input information regarding the user's behavior. For example, the terminal device 10 acquires a user's operation log or a log detected by a sensor from a storage unit of the terminal device 10 as the user's action history. Subsequently, the terminal device 10 calculates the weight of the element forming the model indicating the feature of the user based on the acquired action history of the user, and stores the calculated weight of the element in the storage unit as a learning result. Then, the terminal device 10 authenticates the user based on the learning result and the input information on the user's action. The terminal device 10 may acquire the action history of the user from the storage unit of another device. In addition, the terminal device 10 may perform user authentication using the weight of an element forming a model indicating the feature of the user calculated by another device and the input information.

[2-6. Detecting Predetermined Behavior with Machine Learning]
In the above embodiment, the authentication device 100 has described the example of performing the user authentication based on the weight of the element corrected based on the predetermined action set in advance among the action plans of the user and the input information. . Here, the authentication device 100 may correct the weight of the element based on a predetermined action detected by machine learning, not limited to the predetermined action artificially set in advance. For example, the authentication device 100 detects an action with a relatively low frequency of occurrence for the user by machine learning, using the action history of the user as learning data. Then, the authentication device 100 corrects the weight of the element by using an action whose occurrence frequency is relatively low as a predetermined action. As a result, since the authentication device 100 can exclude an action unusual for the user as an abnormal action in the authentication of the user, the authentication accuracy of the user can be further enhanced.

[2-7. Effect of modification]
As described above, in the authentication device 100 according to the modification, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the action history of the user and the input information. As a result, the authentication device 100 according to the modification can authenticate the user using the weight of the element reflecting the user's action history, so that the authentication accuracy of the user can be further enhanced.

  In addition, in the authentication device 100 according to the modification, the authentication unit 133 is based on the weight of the element corrected based on the action history on the service that supports communication with another user as the action history of the user, and the input information. Authentication of the user. As a result, the authentication device 100 according to the modification can authenticate the user using the weight of the element reflecting the user's action on the SNS, so that the authentication accuracy of the user can be further enhanced.

  Further, in the authentication device 100 according to the modification, the authentication unit 133 authenticates the user based on the weight of the element corrected based on the user's behavior based on the user's action history and the input information. As a result, the authentication device 100 according to the modification can perform user authentication using the weight of the element corrected according to the user's life stage, so that the user authentication accuracy can be further improved.

  In addition, in the authentication device 100 according to the modification, the authentication unit 133 authenticates the user based on the learning result and the input information corrected based on the user's action history. As a result, the authentication device 100 according to the modification can authenticate the user using the input information reflecting the user's action history, so that the authentication accuracy of the user can be further enhanced.

[3. Other]
Further, among the processes described in the above embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  For example, the behavior information storage unit 121 and the feature information storage unit 122 illustrated in FIG. 2 may be stored in a storage server or the like without being held by the authentication device 100. In this case, the authentication device 100 accesses the storage server to acquire information on the user's action history and the weight of the element forming the model indicating the user's feature.

  In addition, the authentication device 100 may be a learning device that does not perform authentication processing but performs only learning processing. In this case, the learning device does not have the authentication unit 133. Then, the authentication device having the authentication unit 133 authenticates the user based on the learning result and the input information which are learned by the learning device.

  Further, the authentication device 100 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in FIG. Hereinafter, the authentication device 100 will be described as an example. FIG. 7 is a hardware configuration diagram showing an example of a computer 1000 for realizing the function of the authentication device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 to control each part. The RAM 1200 temporarily stores various types of information. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the network N.

  The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the CPU 1100 with the program via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a digital versatile disk (DVD) or a phase change rewritable disk (PD), a magneto-optical recording medium such as a magneto optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory It is.

  For example, when the computer 1000 functions as the authentication device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing a program loaded on the RAM 1200. Further, data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

  Although some of the embodiments of the present application have been described above in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the section of the summary of the invention. It is possible to implement the invention in other improved forms.

  In addition, the above-described authentication apparatus 100 may be realized by a plurality of server computers, and depending on the function, an external platform etc. may be called by API (Application Programming Interface) or network computing etc. It can be changed flexibly.

  Further, "section, module, unit" described in the claims can be read as "means", "circuit" or the like. For example, the receiving unit can be read as receiving means or a receiving circuit.

DESCRIPTION OF SYMBOLS 1 authentication system 10 terminal device 100 authentication apparatus 121 behavior information storage part 122 characteristic information storage part 131 acquisition part 132 learning part 133 authentication part

Claims (10)

An acquisition unit that acquires a user's action history;
A learning unit that learns the feature of the user based on the action history of the user acquired by the acquisition unit;
The input information about the user's action and the weight of the element forming the model indicating the feature of the user, which is the learning result learned by the learning unit, of the elements among the weights of the elements corresponding to the input information An authentication apparatus comprising: an authentication unit that authenticates a user based on an integration result of the weight of an element whose reliability of an element showing difficulty in changing the weight is equal to or more than a predetermined threshold value. . The authentication unit
The authentication apparatus according to claim 1, characterized in that performing the weight of the element is corrected based on the activity schedule of the user, the authentication of the user based on said input information. The authentication unit
The weight of the element is corrected on the basis of the preset predetermined action of the action schedule of the user, to claim 1 or claim 2, characterized in that to authenticate the user based on said input information The authentication device described. The authentication unit
Any of claims 1-3, characterized in that to carry out the weight of the element is corrected on the basis of the information entered in the schedule of the user as the action plans of the users, the authentication of the user based on said input information Authentication device described in one. The authentication unit
The authentication apparatus according to any one of claims 1 to 4 , wherein the authentication of the user is performed based on the weight of the element corrected based on the action history of the user and the input information. The authentication unit
The user authentication is performed based on the weight of the element corrected based on an action history on a service supporting communication with another user as the action history of the user and the input information. The authentication device according to any one of 1 to 5 . The authentication unit
The weight of the element is corrected based on the status of the user based on the behavior history of the user, in any one of claims 1-6, characterized in that to authenticate the user based on said input information The authentication device described. The authentication unit
The authentication device according to any one of claims 1 to 7 , wherein the authentication of the user is performed based on the learning result and the input information corrected based on the action history of the user. An authentication method executed by the authentication device,
An acquisition step of acquiring a user's action history;
A learning step of learning features of the user based on the action history of the user obtained by the obtaining step;
The input information about the user's action and the weight of the element forming the model indicating the feature of the user, which is the learning result learned in the learning step, of the elements among the weights of the elements corresponding to the input information An authentication method comprising: an authentication step of authenticating a user based on an integration result of the weight of an element whose reliability of an element showing difficulty in changing the weight is equal to or more than a predetermined threshold value. . Acquisition procedure for acquiring user's action history,
A learning procedure for learning the feature of the user based on the action history of the user obtained by the obtaining procedure;
The input information about the user's action and the weight of the element forming the model indicating the feature of the user, which is the learning result learned by the learning procedure, of the elements among the weights of the elements corresponding to the input information It is characterized in that the computer is caused to execute an authentication procedure for authenticating the user based on the integration result of the weight of the element whose reliability of the element showing the difficulty of changing the weight is equal to or more than a predetermined threshold value. Authentication program.

Images