Information processing device, information processing method, and program

By evaluating multi-modal authentication technology for multiple viewpoints and indicators, combined with multiple input data, the problem of insufficient audio signal authentication strength in the existing technology is solved, and multi-modal authentication with high intensity and flexibility is achieved, which enhances security Sex and user experience.

CN119013667AInactive Publication Date: 2024-11-22SONY GROUP CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380029105.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-30
Filing Date
2023-03-13
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing multimodal authentication technology has insufficient authentication strength on audio signals and has failed to effectively evaluate other authentication elements, resulting in the inability to improve the authentication strength.

Method used

Evaluate multiple authentication information of users by evaluating metrics based on multiple viewpoints and each viewpoint, and present the evaluation results to users, including evaluation viewpoints such as security, privacy and availability, combining multiple input data such as location, action, Verification is carried out in modes such as face, fingerprint, voice and other modes.

Benefits of technology

Multimodal authentication with high authentication strength is realized, which improves user accessibility and authentication strength, enhances resistance to attacks by others, and allows users to customize authentication modalities to improve authentication flexibility and security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119013667A_ABST
    Figure CN119013667A_ABST
Patent Text Reader

Abstract

The information processing apparatus includes: an evaluation unit that evaluates a plurality of pieces of authentication information on a user based on a plurality of evaluation viewpoints and an index of each evaluation viewpoint; and a presentation processing unit that performs a process for presenting the evaluation result of the evaluation unit to a user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present technology relates to an information processing device, an information processing method, and a program. Background Art

[0002] In recent years, with the spread of various information devices and Internet services, the importance of information system security has increased. User authentication is performed to perform access control by confirming whether a user who intends to use an information system actually has the authority to use the system.

[0003] As one of means for user authentication, there is multimodal authentication for combining a plurality of data presenting individual differences of users to prove identity.

[0004] Therefore, a technology has been proposed in which registration information of an audio signal is input, and authentication strength is evaluated by appropriately combining knowledge elements of a password and biometric elements of voiceprint authentication, and the result thereof is notified to the user (Patent Document 1).

[0005] Reference List

[0006] Patent Literature

[0007] Patent Document 1: Japanese Translation of PCT International Application Publication No. 2017-511915 Summary of the invention

[0008] Problems to be solved by the present invention

[0009] However, the technology of Patent Document 1 is basically only for audio signals and has a problem of weak authentication strength. In addition, although it is mentioned to add other authentication elements, there is a problem that the authentication strength cannot be increased because the authentication strength including other authentication elements is not evaluated.

[0010] The present technology has been proposed in view of such problems, and an object thereof is to provide an information processing apparatus, an information processing method, and a program capable of realizing multimodal authentication with high authentication strength by evaluating authentication information and presenting the evaluation result to a user.

[0011] Solution to the problem

[0012] In order to solve the above problems, the first technology is an information processing device, which includes: an evaluation unit, which evaluates multiple authentication information about a user based on multiple viewpoints and indicators of each viewpoint; and a presentation processing unit, which performs processing for presenting the evaluation results of the evaluation unit to the user.

[0013] Furthermore, a second technique is an information processing method that performs processing of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint and presenting the evaluation result to the user.

[0014] Furthermore, a third technique is a program for causing a computer to execute an information processing method that performs processing of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint and presenting the evaluation result to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a block diagram showing the configuration of the electronic device 100 .

[0016] Figure 2 2 is a block diagram showing the configuration of the information processing apparatus 200 .

[0017] Figure 3 2 is a flowchart showing the processing of the information processing apparatus 200 .

[0018] Figure 4 is a diagram showing a method of presenting evaluation results of the indicator "certification level".

[0019] Figure 5 2 is a diagram showing a method of presenting evaluation results of the index “resistance to attacks by others”.

[0020] Figure 6 : is a diagram showing a method of presenting the evaluation result of the index "necessity of modality".

[0021] Figure 7 : is a diagram showing a method of presenting the evaluation result of the index "description of used data".

[0022] Figure 8 : is a diagram showing a method of presenting the evaluation result of the index "error rate".

[0023] Fig. 9 is a diagram showing a method of presenting evaluation results of the index “stability”.

[0024] Fig.10 is a diagram showing a method of presenting the evaluation results of the index “cost”.

[0025] Fig.11 is a diagram showing a method of collectively presenting representative numerical values ​​of three evaluation viewpoints.

[0026] Fig.12 This is a flowchart showing processing when authentication information is used for authentication in various services.

[0027] Fig.13is a flowchart illustrating processing in the first modification in which a user selects a modality to be used for authentication.

[0028] Fig.14 is a flowchart illustrating processing in the second modification in which the user selects a modality to be used for authentication.

[0029] Fig.15 is a diagram showing a UI for a user to select a modality.

[0030] Fig.16 is a block diagram showing a modification in which the electronic device 100 is connected to an external server device or another device. DETAILED DESCRIPTION

[0031] Hereinafter, embodiments of the present technology will be described with reference to the drawings. Note that the description will be given in the following order.

[0032] <1. Implementation Method>

[0033] [1-1. Configuration of electronic device 100]

[0034] [1-2. Configuration of Information Processing Device 200]

[0035] [1-3. Processing in Information Processing Device 200]

[0036] [1-3-1. Overall processing]

[0037] [1-3-2. Learning of authentication model]

[0038] [1-3-3. Evaluation of authentication information]

[0039] [1-3-4. Presentation of evaluation results]

[0040] [1-4. When the registered authentication information is used for authentication in the service]

[0041] <2. Modification>

[0042] [2-1. Modification of user selection mode]

[0043] [2-2. Other changes]

[0044] <1. Implementation Method>

[0045] [1-1. Configuration of electronic device 100]

[0046] Will refer to Figure 1The configuration of the electronic device 100 on which the information processing apparatus 200 according to the present technology runs is described. The electronic device 100 includes a data input unit 101 , a control unit 102 , a storage unit 103 , a communication unit 104 , an input unit 105 , and an output unit 106 .

[0047] The electronic device 100 and the information processing device 200 are configured to register multiple authentication information to be used for multimodal authentication by combining multiple input data (authentication information) showing individual differences of users to authenticate authenticity. Authentication includes one-to-one authentication for determining whether the user to be authenticated is a specific person and one-to-N authentication for determining which person the user to be authenticated is.

[0048] The data input unit 101 is configured to input a plurality of input data used as authentication information to the electronic device 100. Specifically, the data input unit 101 is a camera, a microphone, a sensor, an antenna, etc. However, the data input unit 101 is not limited thereto, and any device may be used as long as input data that can be used for authentication can be input to the electronic device 100.

[0049] The authentication information is information used for authentication of a user, and includes input data input from the data input unit 101 , feature data obtained by applying predetermined processing to the input data to extract features, etc. The input data is regarded as authentication information after being input to the information processing device 200 .

[0050] Examples of the sensor include an inertial sensor, a distance sensor, a fingerprint sensor, a position sensor, a heart rate sensor, an electromyographic sensor, a body temperature sensor, a sweat sensor, a brain wave sensor, a pressure sensor, an atmospheric pressure sensor, a geomagnetic sensor, a touch sensor, etc. However, the sensor is not limited thereto, and any sensor may be used as long as input data that can be used for user authentication can be input to the electronic device 100.

[0051] Note that the camera, microphone, sensor, and antenna may be replaced with dedicated devices having their functions as well as electronic devices having their functions such as smartphones, tablet terminals, wearable devices, and the like.

[0052] In the present technology, input data as authentication information is classified into multiple types. The types are defined as modalities. Examples of modalities include location, action, motion, face, fingerprint / palmprint, voice, social, belongings, character strings, etc. Therefore, it can be said that any input data as authentication information belongs to any modality.

[0053] Examples of input data about location include latitude-longitude data of the location where the user exists, location data indicating whether the user is outdoors or indoors, etc. These may be acquired by a location sensor or a distance sensor.

[0054] The input data about the action includes the user's walking style, the type of the user's mobility method (walking, car, train, etc.), the user's actions when using various services, etc. These can be obtained from inertial sensors, service usage history information, application usage time, website browsing history, etc.

[0055] Examples of input data about motion include data about the speed and direction of the motion of the user's hand when lifting or operating the device. These can be acquired through inertial sensors.

[0056] Examples of input data about the face include an image of the entire face of the user, an image of a part of the face of the user, etc. These can be acquired by a camera.

[0057] Examples of input data about fingerprints and palm prints include a full or partial image of the user's palm and a full or partial image of the user's fingers. These can be acquired through a camera device or a fingerprint sensor.

[0058] Examples of input data about voice include voice prints, voice data of voice when saying a specific word, voice data of voice when performing daily conversations, environmental sounds, etc. These can be obtained through a microphone.

[0059] Examples of input data of a social nature (real world and Internet) include signals emitted by devices owned by others nearby, personal relationships in various services on the Internet, and the history of users who have communicated on social networking services (SNS). These can be obtained from the usage history of the antenna and various services on the Internet.

[0060] Examples of input data about belongings include wireless signals of various devices owned by the user, images of objects owned by the user, etc. These can be acquired through an antenna or a camera device.

[0061] Examples of input data about character strings include passwords, answers to secret questions, etc. These can be obtained through input from the user.

[0062] Note that data other than the above data may be used as input data. The input data may be raw data that has not been subjected to processing, data processed by a predetermined process, data from which a feature quantity is extracted, or data including a learning model, statistical information indicating an overall trend, etc. as feature data. In addition, in consideration of privacy, the input data may be data subjected to encryption or anonymization processing.

[0063] It is assumed that a tag is provided as metadata to the input data. In the case of one-to-one authentication, the tag represents the user himself / herself as the authentication target as "1", and represents other people as "-1". In the case of one-to-N authentication, the tag represents user A as "0", user B as "1", user C as "2", and user D as "3", etc. The tag may be provided by the electronic device 100, or may be provided by each device as the input unit 105.

[0064] The target period of the data as the input data may be arbitrary. In addition, the input data may include data about a plurality of persons. The input data may be authentication information registered in the electronic device 100 in the past, or various types of data for password authentication, fingerprint authentication, facial authentication, etc. that are usually included in a personal computer or the like as the electronic device 100 and have been registered.

[0065] In addition, data acquired by another device can be received through the communication unit 104 and used as input data. For example, image data captured by a camera installed in a store is received by a smartphone at hand as the electronic device 100 and used as input data or the like.

[0066] The control unit 102 includes a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), etc. The CPU performs various types of processing according to a program stored in the ROM and issues commands, thereby controlling the entire electronic device 100 and each unit thereof.

[0067] The storage unit 103 is configured to store input data input from the input unit 105, registered authentication information, etc. The storage unit 103 is, for example, a large-capacity storage medium such as a hard disk or a flash memory.

[0068] The communication unit 104 is a communication interface between the electronic device 100 and an external device, the Internet, etc. The communication unit 104 may include a wired or wireless communication interface. In addition, more specifically, the wired or wireless communication interface may include cellular communication, Wi-Fi, Bluetooth (registered trademark), near field communication (NFC), Ethernet (registered trademark), High Definition Multimedia Interface (HDMI (registered trademark)), Universal Serial Bus (USB), etc.

[0069] The input unit 105 is used by the user to input instructions and the like to the electronic device 100. When the user performs input on the input unit 105, a control signal corresponding to the input is created and provided to the control unit 102. Then, the control unit 102 performs various types of processing corresponding to the control signal. In addition to physical buttons, the input unit 105 also includes a touch panel, a touch screen, etc. integrally constructed with a monitor.

[0070] The information processing device 200 performs evaluation of authentication information according to the present technology, processing for presenting the evaluation result to the user, etc. The detailed configuration of the information processing device 200 will be described later.

[0071] The output unit 106 is configured to output the evaluation result obtained by the information processing device 200. Examples of the output unit 106 include a display that outputs the evaluation result by display, a speaker that outputs the evaluation result by voice, an actuator that outputs the evaluation result by vibration, and a light emitting diode (LED) that outputs the evaluation result by light. Note that the output unit 106 may be included in a device other than the electronic device 100. For example, the authentication result processed by a smartphone as the electronic device 100 is displayed on a display installed in a store.

[0072] The electronic device 100 is configured as described above. Examples of the electronic device 100 include a personal computer, a smartphone, a tablet terminal, a wearable device, glasses, a television, a car, a drone, a robot, and the like.

[0073] In the case where there is a program necessary for the processing according to the present technology, the program may be pre-installed in the electronic device 100 , or may be distributed through downloading, a storage medium, or the like and installed by the user himself / herself.

[0074] [1-2. Configuration of Information Processing Device 200]

[0075] Will refer to Figure 2 The configuration of the information processing apparatus 200 is described. The information processing apparatus 200 includes an evaluation unit 201 , a registration unit 202 , and a presentation processing unit 203 .

[0076] The evaluation unit 201 evaluates the authentication information based on one or more of the three evaluation viewpoints of security, usability, and privacy. In addition, the evaluation unit 201 evaluates the authentication information based on one or more indicators in the evaluation viewpoints.

[0077] The registration unit 202 performs a process of registering the authentication information based on the consent regarding the registration of the user. In addition, the registration unit 202 learns an authentication model for authenticating the user by multimodal authentication based on the authentication information, and supplies the authentication model to the evaluation unit 201.

[0078] The presentation processing unit 203 performs processing to convert the evaluation result of the authentication information into information for a predetermined presentation method to present the evaluation result to the user. The evaluation result is presented to the user so that the user can determine to register the authentication information or input another input data after understanding and agreeing.

[0079] The information processing device 200 is configured as described above. In the present embodiment, the information processing device 200 is operated in the electronic device 100, but the electronic device 100 may have a function as the information processing device 200 in advance, or the information processing device 200 and the information processing method may be implemented by executing a program in the electronic device 100 having a function as a computer. The program may be pre-installed in the electronic device 100, or may be distributed by downloading, storage media, etc. and installed by a user, etc. In addition, the information processing device 200 may be configured as a single device.

[0080] [1-3. Processing by Information Processing Device 200]

[0081] [1-3-1. Overall processing]

[0082] Next, we will refer to Figure 3 1 and 2 to describe the processing performed by the information processing apparatus 200. Note that the details of each step will be described later.

[0083] First, in step S101, the information processing device 200 obtains a plurality of input data from the input unit 105. As described above, the input unit 105 includes devices such as a camera, a microphone, a sensor, and an antenna. Here, it is assumed that a plurality of input data belonging to one or more modalities predetermined by an authentication service provider, a system designer, etc. are obtained from a specific device. Therefore, the plurality of input data belonging to the predetermined one or more modalities can be indicated to the user to prompt the user to input the input data.

[0084] Note that the information processing apparatus 200 may directly acquire input data from the input unit 105 , or may temporarily acquire input data stored in the storage unit 103 .

[0085] The input data may be acquired by a general method including instructions to the user by a graphical user interface (GUI). Examples of input data that may be acquired on the spot by instructions to the user by the GUI include passwords, fingerprint images, facial images, movements of the user's hand when lifting the electronic device 100, movements of shaking or operating the electronic device 100, and wireless signals that may be acquired by bringing a device owned by another person close to the user's electronic device 100.

[0086] The input data is processed into authentication information after being acquired by the information processing device 200 .

[0087] Next, in step S102, the registration unit 202 learns the authentication model. The registration unit 202 can use a general machine learning method to classify users according to authentication information. In the case of a one-to-one authentication to determine whether the user to be authenticated is a specific user, a two-class classification problem occurs. In addition, in the case of a one-to-N authentication to determine which user to authenticate, a multi-class classification problem occurs. The authentication model generated by learning can be registered and stored in the storage unit 103. The details of the learning of the authentication model will be described later.

[0088] Note that, in the case where the input data is data registered as authentication information in the past or data registered in a personal computer or the like as the electronic device 100 (authentication information in a common password, fingerprint authentication, face authentication, etc.), the registered authentication information and the newly input input data may be integrated at the time of learning by the registration unit 202. For example, in the case where the electronic device 100 takes a week to completely collect necessary input data, the authentication function is used with the registered authentication information (e.g., a conventional password and fingerprint) until the collection is completed, and after a week, the authentication information is taken over and the main registration is performed, so that the authentication function that extends the conventional authentication function can be used.

[0089] Next, in step S103, the evaluation unit 201 evaluates the authentication information. The evaluation unit 201 evaluates the authentication information from three evaluation viewpoints of security, privacy, and usability. The details of the evaluation of the authentication information will be described later.

[0090] Next, in step S104, the presentation processing unit 203 performs processing for presenting the evaluation result of the authentication information to the user by outputting the evaluation result in the output unit 106. There are a variety of presentation methods, and the presentation processing unit 203 converts the evaluation result into a form for each presentation method and provides the converted result to the output unit 106. Then, the output unit 106 outputs the evaluation result converted for presentation, thereby presenting the evaluation result to the user. Note that, in the case where there is an instruction from the user after the registration of the authentication information, only step S104 may be performed so that the user can reconfirm the authentication information.

[0091] Next, in step S105, the user's consent as to whether to register the authentication information is confirmed, and if the user agrees, the process proceeds to step S106 (Yes in step S105). For example, it is possible to determine whether the user agrees by displaying an option of whether the user agrees on the display used as the output unit 106 and confirming the selection result input by the user through the input unit 105.

[0092] Then, in step S106, the registration unit 202 registers the authentication information based on the consent of the user who has confirmed the presented evaluation result. For example, the authentication information can be registered by storing it in the storage unit 103 associated with the user. Note that the registered authentication information can be stored in the storage unit 103, or the information processing device 200 can include a memory or the like for storing the registered authentication information.

[0093] On the other hand, if the user does not agree to register the authentication information in step S105, the process ends (No in step S105). Since the registration of authentication information is performed based on the user's consent, the authentication information is not registered if the user is dissatisfied with the evaluation result and does not agree to register.

[0094] Note that in order to reduce computation time, the learning of the authentication model in step S102 and the evaluation of the authentication information in step S103 may be done in advance for some variations of the input data. In addition, all or each of the steps may be reset.

[0095] [1-3-2. Learning of authentication model]

[0096] Next, the learning of the authentication model in step S102 will be described. The learning of the authentication model can be performed by a general machine learning method such as a k-nearest neighbor algorithm, a decision tree, a logistic regression, a support vector machine, or a neural network.

[0097] Here, as an example, learning of an authentication model using linear regression in one-to-one authentication will be described. It is assumed that position and action are used as modalities.

[0098] First, the following three feature quantities are calculated.

[0099] The feature quantity x1 related to time = [seconds elapsed from 00:00, Monday to Friday corresponds to integer values ​​0 to 6]

[0100] Feature quantity x2 at the location = [latitude and longitude normalized by discretization in units of 50 km (the surface of the earth is divided into multiple grids in units of 50 km, and latitude and longitude normalized in each discretized 50 km area]

[0101] Motion feature x3 = [10-second average and dispersion of acceleration xyz and 10-second average and dispersion of angular velocity xyz]

[0102] Then, a feature amount obtained by combining x1, x2, and x3 is defined as x.

[0103] Furthermore, as shown in the following Expression 1, by combining the user's own feature amount x g0 , xg1 , ... and the characteristic quantity x of others i0 , x i1 , ...The obtained feature matrix is ​​set as X.

[0104] [Expression 1]

[0105]

[0106] In addition, as shown in the following expression 2, the label column corresponding to the order in which the user himself / herself and others are combined in the feature amount matrix is ​​set to y. In expression 2, the label corresponding to the feature amount of the user himself / herself is 1, and the label corresponding to the feature amount of others is -1.

[0107] [Expression 2]

[0108] y=[1,1,…,-1,-1,…]

[0109] As shown in Expression 3 below, the weight w is learned by minimizing the correct expression to approach y = w T X. In the present technology, the authentication model corresponds to the weight w in Expression 3.

[0110] [Expression 3]

[0111] *d(a, b): distance function between a and b

[0112] Note that when authentication is actually performed, the feature quantity x' is first calculated by using the weight w, and when w T When x'≥0, the feature x' can be determined as the user himself / herself, and when w T When x'<0, the feature amount x' can be determined to be another person. In addition, a general method can be applied to the distance function d and minimized.

[0113] Note that in the learning of the authentication model, in order to improve recognition performance and robustness, the input data can be processed by, for example, data enhancement to increase the data. In addition, a unified rule can be applied regardless of the user, rather than personalizing the user through machine learning. In addition, in the case of using a specific hyperparameter method, the hyperparameter can be adjusted according to the input data. In addition, instead of the late fusion of combining and learning after feature extraction as described above, early fusion of combining and learning the input data as is can be used. In addition, multiple different authentication models can be learned, and the authentication model can be switched according to the situation when the user uses the authentication service. In addition, re-learning of the pre-learned authentication model such as transfer learning can be performed. In addition, in the case of a method that outputs a score or probability, a determination threshold can be set to adjust the false rejection rate (FRR) or the false acceptance rate (FAR).

[0114] [1-3-3. Evaluation of authentication information]

[0115] Next, the evaluation of the authentication information performed by the evaluation unit 201 in step S103 will be described. The evaluation unit 201 evaluates the authentication information from three evaluation viewpoints of security, privacy, and usability. In addition, the evaluation unit 201 evaluates the authentication information with multiple indicators for each evaluation viewpoint.

[0116] First, regarding security, authentication information is evaluated using the indicators of “authentication level” and “resistance to attacks by others”.

[0117] The authentication level is an indicator that uses the false acceptance rate (FAR) indicating the error rate at which others are identified as the user to be authenticated to indicate that the closer the value of "1-FAR" is to 0, the weaker the authentication strength, and the closer the value is to 1, the stronger the authentication strength.

[0118] Resistance to attacks by others is an indicator indicating resistance to attacks presented by malicious persons. Regarding resistance to attacks by others, a value between 0 and 1 indicating resistance to attacks presented is estimated for each modality, and the value for the modality is summed with the maximum value of 1, and the value closer to 0 indicates that there is a risk of attacks by others, and the value closer to 1 indicates that it is safe. The index can be calculated based on data accepted by others, data accepted by others, data obtained by processing personal data, and the like. "Data accepted by others" is a data set that is determined to be the user's own / her own when the feature quantity assigned to the label of others at the time of learning, and a data set that is determined to be the person's own / her own when the label of others is assigned for the evaluation and feature quantity of the FAR indicator.

[0119] Here, a method of calculating resistance to attacks by others is described as a specific example.

[0120] First, the tolerance of the modal "position" can be calculated as follows. Using x (expressed by Expression 5) i 'To calculate FAR', at this x i ', with the user's own position modal x 2g Replace the feature quantity x of others (expressed by Expression 4) i Position modal x 2i .

[0121] [Expression 4]

[0122]

[0123] [Expression 5]

[0124]

[0125] The x in expression 5 is i ' is a characteristic amount when the location modal mode is imitated by a malicious person like the user himself / herself.

[0126] For example, although in x i Initially, FAR=0.1 is set, but in x i 'Set FAR'=0.6, and the accepted error rate of others increases.

[0127] The tolerance of the action mode can be calculated as follows. Using x (expressed by Expression 6) i "To calculate FAR", at this x i ", using the user's own action mode x 3g Replace the feature quantity x of others (expressed by Expression 5) i The action mode x 3i .

[0128] [Expression 6]

[0129]

[0130] The x in expression 7 is i ” is a characteristic amount when the action modality pattern is imitated by a malicious person like the user himself / herself.

[0131] For example, although in x i Initially, FAR=0.1 is set, but in x i "FAR" = 0.8 is set in ", and the error rate accepted by others increases.

[0132] Then, the resistance to attack by others is calculated by the following expression 8. When the resistance to attack by others is closer to 0, there is a risk of attack by others, and when the resistance to attack by others is closer to 1, it is safe.

[0133] [Expression 8]

[0134] Resistance to attack by others = (1-FAR') + (1-FAR")

[0135] For example, when FAR' of the position modality is 0.6 and FAR" of the action modality is 0.8, the other person attack resistance is 0.6 based on Expression 8. Note that the other person attack resistance may be calculated not by the sum of multiple modalities but by the average.

[0136] In addition, with regard to privacy, authentication information is evaluated by the indicators of “necessity of modality” and “description of input data to be used”.

[0137] The necessity of a modality is an indicator indicating that a general machine learning method capable of describing the importance of a modality is applied, normalization is performed, and the closer to 0, the smaller the necessity of acquisition, and the closer to 1, the greater the necessity of acquisition. For example, there is importance in a decision tree, a sharp line value in a neural network, etc.

[0138] The description of the input data to be used indicates how to use the input data by converting the feature amount obtained by processing the input data into a format that can be easily understood by a user.

[0139] In addition, with regard to availability, authentication information is evaluated using the indicators of “error rate”, “stability”, and “cost”.

[0140] The error rate is an index which indicates that the closer to 0, the smaller the number of errors, and the closer to 1, the larger the number of errors, using the error rate FRR (False Rejection Rate) of identifying the user to be authenticated as someone else.

[0141] Stability is obtained by calculating and normalizing a general index representing stability and complexity of the authentication model, and is an index indicating that the closer to 0, the more difficult it is for the user to understand the authentication result, and the closer to 1, the easier it is for the user to grasp the authentication result. Note that conditions of available time zones and places can be extracted.

[0142] The cost is an index indicating a value representing battery consumption, storage consumption, and communication volume estimated between 0 and 1, and the closer the value itself or its average value is to 0, the smaller the cost burden is, and the closer the value is to 1, the greater the cost burden is.

[0143] For example, in a case where the battery consumption is 0.6, the storage consumption is 0.4, and the communication volume is 0.3, the average value thereof can be calculated as "(0.6+0.4+0.3) / 3=0.43".

[0144] Note that the index and the calculation method thereof are not limited to the above-mentioned index and the calculation method thereof, and other indexes and other calculation methods may be used.

[0145] The evaluation unit 201 may evaluate a plurality of authentication information for multimodal authentication individually, or may evaluate a plurality of authentication information in combination.

[0146] The evaluation unit 201 evaluates the authentication information by all indicators in each of security, privacy, and usability by default, but it is not always necessary to evaluate the authentication information by all evaluation viewpoints and all indicators, but the authentication information can be evaluated by any one or more evaluation viewpoints and any one or more indicators. In addition, which evaluation viewpoint and indicator the evaluation unit 201 evaluates can be predetermined by the authentication service provider, the system designer, etc., and set in the information processing device 200. In addition, the evaluation viewpoint and indicator can be predetermined according to the type of input data. In addition, the user can determine which evaluation viewpoint and indicator are used for the evaluation.

[0147] In addition, which indicator is ultimately evaluated can be automatically selected based on the value of each indicator. For example, priorities and thresholds can be set for the values ​​of indicators, and the value of an indicator can be selected if the value of the indicator exceeds or drops below a certain threshold.

[0148] For example, the threshold corresponding to the priority 1 of the indicator "Authentication Level" is set to 0.8, and the threshold corresponding to the priority 2 is set to 0.5. In addition, the threshold corresponding to the priority 1 of the indicator "Resistance to Attacks by Others" is set to 0.6, and the threshold corresponding to the priority 2 is set to 0.3. Then, in the case where the value of the indicator "Authentication Level" calculated by the evaluation unit 201 is 0.9 and the value of "Resistance to Attacks by Others" is 0.5, the value of "Authentication Level" exceeds the threshold of Priority 1, and the value of "Resistance to Attacks by Others" does not exceed the threshold of Priority 1. Therefore, the "Authentication Level" exceeding the threshold of Priority 1 is selected as the indicator to be evaluated.

[0149] In addition, when the priority and the threshold are set to be the same, and when the value of the indicator "Authentication Level" calculated by the evaluation unit 201 is 0.7 and the value of "Resistance to Attacks by Others" is 0.6, since the value of "Authentication Level" does not exceed the threshold of priority 1 and the value of "Resistance to Attacks by Others" exceeds the threshold of priority 1, the "Resistance to Attacks by Others" that exceeds the threshold of priority 1 is selected as the indicator for evaluation.

[0150] Note that the maximum number of indicators to be selected when the number of indicators whose values ​​exceed the threshold is large may be predetermined by an authentication service provider, a system designer, etc. In addition, the priority and the threshold may be predetermined by an authentication service provider or a system designer.

[0151] [1-3-4. Presentation of evaluation results]

[0152] Next, the processing performed by the presentation processing unit 203 in step S104 and the presentation of the evaluation result to the user will be described. There are a variety of presentation methods, and the presentation processing unit 203 converts the evaluation result into a form of each presentation method and provides the converted result to the output unit 106. Then, the output unit 106 outputs the evaluation result converted for presentation, thereby presenting the evaluation result to the user.

[0153] In the case where the evaluation unit 201 evaluates multiple authentication information for multimodal authentication individually, the evaluation result presented is the evaluation result for the specific individual authentication information. In addition, in the case where the evaluation unit 201 evaluates multiple authentication information in combination, the evaluation result to be presented is the evaluation result for the state where the multiple authentication information is combined.

[0154] As a method of presenting the evaluation result of the index "certification level" of the evaluation viewpoint "security", there is a method of presenting a numerical value (%), such as Figure 4 As shown in A. The presentation processing unit 203 can present the evaluation result as a numerical value (%) by calculating the ratio of the evaluation result as a numerical value (a value between 0 and 1) output from the evaluation unit 201 to the maximum value of the numerical value, such as 100%.

[0155] In addition, when presented by ratio (%), the result of comparison with a representative value in another authentication method may be presented simultaneously, such as Figure 4 As shown in B.

[0156] In addition, as a method of presenting the evaluation result of the indicator "certification level", there is a presentation method by level, such as Figure 4 C. The presentation processing unit 203 compares the evaluation result as a numerical value (a value between 0 and 1) output from the evaluation unit 201 with a threshold value corresponding to each of a plurality of levels (e.g., five levels of evaluation A to evaluation E) so that the evaluation result as a numerical value can be converted into a level and presented.

[0157] Furthermore, as a method of presenting the evaluation result of the indicator "certification level", there is a presentation method using sentences such as Figure 4 D. The presentation processing unit 203 compares the evaluation result as a numerical value (a value between 0 and 1) output from the evaluation unit 201 with a threshold value corresponding to each of a plurality of levels (e.g., 5 levels) associated with the sentence so that the evaluation result as a numerical value can be converted into a sentence and presented.

[0158] As a method of presenting the evaluation results of the indicator "resistance to attacks by others" of the evaluation viewpoint "security", there is Figure 4 A and Figure 4 The same as shown in B Figure 4 The indicator "certification level" shown in C is presented by numerical values ​​similar to the presentation by level.

[0159] In addition, as a method of presenting the evaluation result of the indicator "resistance to attack by others", there is presentation by description of a weak pattern of sentences, such as Figure 5 As shown in A. The presentation processing unit 203 compares the evaluation result indicating resistance output as a numerical value (a value between 0 and 1) from the evaluation unit 201 with a threshold value corresponding to each of a plurality of levels (e.g., 5 levels) associated with the sentence so that the evaluation result as a numerical value can be converted into a sentence and presented.

[0160] Furthermore, as a method of presenting the evaluation result of the indicator "resistance to attacks by others", there is presentation by visualizing the weak pattern, such as Figure 5 As shown in B.

[0161] In the description of weak pattern sentences and the visualization of weak patterns, when the evaluation result of the indication tolerance output as a numerical value from the evaluation unit 201 drops below a specific threshold, the evaluation result can be determined by associating the evaluation result with a specific sentence or figure to present the content. In addition, the evaluation result can be calculated by dividing the time axis by several time scale units (for example, in units of one hour, morning, day and night, days in the week, working days and holidays, and when talking, etc.) or under specific time conditions (for example, when commuting, when traveling, etc.) the evaluation result is calculated and when the evaluation result drops below the threshold, the evaluation result is associated with a specific sentence or figure to determine the presentation content. Similarly, like "area", the evaluation result is calculated by dividing the evaluation result as a spatial axis by several spatial scale units (for example, in units of 100m, in units of 50km, etc.), or the evaluation result is calculated under the conditions of a specific space (for example, home, workplace, store, convenience store, etc.). When the evaluation result drops below the threshold, the presentation content can be determined by associating the evaluation result with a specific sentence or figure.

[0162] As a method of presenting the evaluation result of the index "necessity of modality" of the evaluation viewpoint "privacy", there is a presentation method by graph, such as Figure 6 As shown in A. The presentation processing unit 203 may present the evaluation result as a graph by graphing the evaluation result output as a numerical value (a value between 0 and 1) for each modality, with 0 being the minimum value of the graph and 1 being the maximum value of the graph.

[0163] When presenting with graphics, you can add a description with sentences, such as Figure 6 As shown in B. The presentation of the sentence can be achieved by associating the sentence of the template with each modality in advance, and presenting the sentence of the template for the modality with high necessity (for example, equal to or greater than a threshold).

[0164] In addition, in the indicator "Description of input data to be used" of the evaluation viewpoint "Privacy", there is a Figure 7 The method of presenting the sentences shown in A. The evaluation results can be presented as sentences by associating a plurality of sentences with a plurality of values ​​of different feature quantities in advance and specifying which sentence corresponds to the feature quantity obtained by processing the input data. In addition, as Figure 7 As shown in B, how to use the input data related to the location can also be presented in the form of a map. The presentation content can be determined by associating feature quantities with sentences and graphs in each modality from the viewpoint of causing privacy issues.

[0165] As a method of presenting the evaluation results of the indicator "error rate" of the evaluation viewpoint "usability", there is Figure 4 A and Figure 4 The numerical representation shown in B and Figure 4 The presentation by level similar to the indicator "Certification Level" shown in C.

[0166] In addition, as a method of presenting the evaluation results of the indicator "error rate", there is a method of using Figure 8 The association between the evaluation result of the presentation processing unit 203 and the sentence is similar to Figure 4 The association in the description of D, and in Figure 8 , sentences indicating evaluation regarding error rates are presented.

[0167] As a method of presenting the evaluation results of the indicator "stability" of the evaluation viewpoint "usability", there is Figure 4 A and Figure 4 The numerical representation shown in B and Figure 4 The presentation by level similar to the indicator "Certification Level" shown in C.

[0168] In addition, in the indicator "stability", such as Fig. 9 A and Fig. 9 As shown in B, conditions for using the authentication function may also be presented.

[0169] As a method of presenting the evaluation result of the indicator "cost" of the evaluation viewpoint "usability", there is Figure 4 A and Figure 4 The numerical representation shown in B and Figure 4The presentation by level similar to the indicator "Certification Level" shown in C.

[0170] Furthermore, as a method of presenting the evaluation result of the index “cost”, the consumption of the battery (the prediction result of the usable time of the electronic device 100) may be presented, such as Fig.10 As shown in A. In the case where the value representing the battery consumption between 0 and 1 represents the ratio of the battery consumption per unit time, the battery consumption in the case where the authentication function is turned on is calculated based on the value, and the battery remaining amount, that is, the remaining operable time of the electronic device 100, can also be grasped from the battery consumption and can be presented.

[0171] In addition, as a method of presenting the evaluation result of the index "cost", it is also possible to present the storage consumption of the storage unit 103 when the function and the authentication function of the information processing device 200 are turned on, such as Fig.10 As shown in B. In the case where the value representing the storage consumption between 0 and 1 represents the ratio of the storage unit 103 to the entire storage, the storage consumption when the authentication function is turned on can be calculated and presented based on the value.

[0172] In addition, as a method of presenting the evaluation result of the index "cost", it is also possible to present the function and communication volume of the information processing device 200 when the authentication function is turned on, such as Fig.10 As shown in C. In the case where the value representing the communication volume between 0 and 1 represents the ratio of the communication volume per unit time, the communication volume per day in the case where the authentication function is turned on can be calculated and presented based on the value.

[0173] Each of the battery consumption, storage consumption, and communication volume when the authentication function is turned on and off is actually measured per unit time, the difference between them is calculated, and normalization is performed with a predetermined upper limit value (for example, a value generally considered to be large in terms of volume and a value calculated according to the specification of the terminal capacity), whereby an evaluation result of a value between 0 and 1 can be obtained. Fig.10 A. Fig.10 B and Fig.10 In the presentation method shown in C, the battery consumption and the increase / decrease in storage consumption per unit time (e.g., one hour, one day, etc.) can be expressed as specific values, or the battery consumption can be expressed by estimating the available time of the battery.

[0174] When presenting the evaluation result, the name of the input data to be evaluated and the name of the modality to which the input data belongs may be presented simultaneously.

[0175] When presenting the evaluation results on the display as the output unit 106 , the evaluation results in all evaluation viewpoints and indices can be presented by switching the evaluation viewpoints and indices with a tab or the like.

[0176] Although it has been described that the presentation processing unit 203 converts the evaluation result of the authentication information into information to be presented, the conversion process may be performed by the evaluation unit 201 .

[0177] In addition, if Fig.11 A and Fig.11 As shown in B, representative values ​​of the three evaluation viewpoints can be presented together. Fig.11 A and Fig.11 In B, “Authentication Level” indicates the evaluation viewpoint “Security”, “Privacy Level” indicates the evaluation viewpoint “Privacy”, and “Availability” indicates the evaluation viewpoint “Availability. Note that any one of the indicators may be selected in each evaluation viewpoint, or an indicator obtained by integrating each of the indicators may be newly calculated. For example, the indicator of “Availability” is set to only “Error Rate”, and the indicator of “Availability” is set to the average of “Error Rate”, “Stability”, and “Cost”.

[0178] Note that the method of presenting the evaluation result is not limited to display on the display, and the evaluation result may be output as speech from a speaker, or presentation of the level of the evaluation result may be performed by the number of lighting times of an LED or the like.

[0179] As described above, the processing by the information processing device 200 is performed. According to the present technology, the authentication information is evaluated and the evaluation result is presented to the user, so that multimodal authentication with high authentication strength and safe and reliable use can be realized. Since the evaluation viewpoints include security, privacy, and usability, and each evaluation viewpoint has an evaluation index, the user can grasp the evaluation of each evaluation viewpoint and its details.

[0180] In addition, since the input data for multimodal authentication can be arbitrarily combined, user accessibility can be improved. For example, even users who cannot use or have difficulty using existing authentication functions using faces, fingerprints, etc. can register authentication information and use the authentication function.

[0181] In addition, since the input data for multimodal authentication can be arbitrarily combined, the authentication strength can be increased and the usability of the user can be improved. For example, the authentication function can be used according to the conditions of the unavailable modalities and the available modalities, such as when the face is out of the field of view of the camera device, or when the face is underground and the location information cannot be obtained.

[0182] In addition, since input data for multimodal authentication can be arbitrarily combined, the number of options for modalities to be used increases, and the user can customize freely.

[0183] [1-4. When the registered authentication information is used for authentication in the service]

[0184] Next, we will refer to Fig.12 The case where the authentication model learned by the information processing device 200 and the authentication information registered by the information processing device 200 are used for authentication required in various services is described. This process is performed when authentication is requested in various services. The authentication performed here is multimodal authentication using multiple authentication information.

[0185] A device that performs authentication using an authentication model learned by the information processing device 200 and authentication information registered by the information processing device 200 is referred to as an authentication device. Examples of authentication devices include personal computers, smart phones, tablet terminals, dedicated authentication devices, and the like. It is assumed that the authentication device pre-saves the authentication model learned by the information processing device 200 and the authentication information registered by the information processing device 200. Note that the electronic device 100 on which the information processing device 200 operates can be used as an authentication device. In addition, a device that performs processing for providing a service is referred to as a service device. Examples of service devices include personal computers, smart phones, tablet terminals, dedicated devices, and the like.

[0186] Examples of various services include various websites that require authentication when logging in, online payment services, security services that provide locking systems, etc.

[0187] First, in step S201, the authentication device acquires a plurality of input data. In acquiring the input data, the original input data input from a camera, microphone, sensor, etc. may be acquired, or feature quantity data obtained by processing the input data may be acquired from a storage medium, etc.

[0188] Note that in the case where the data required for authentication is insufficient, the user may be prompted to enter data on the spot to obtain the data. For example, there is a designated user ID in one-to-one authentication, a touch of a fingerprint sensor, a shake of the device, an NFC touch of a specific item, etc.

[0189] Next, in step S202, the user is authenticated using the input data as authentication information and the learned authentication model. In the case of one-to-one authentication, it is determined whether the user corresponds to a specific person, and in the case of one-to-N authentication, it is determined to which person the user corresponds.

[0190] In the case where the result of the authentication is successful, that is, the user corresponds to a specific person (one-to-one authentication) or the user corresponds to a specific person (1-to-N authentication), the process proceeds to step S203 (yes in step S202). Then, in step S203, the authentication device transmits the authentication result to the service device through the network. For this transmission of the authentication result, for example, a general method of verifying the information of the authentication result by adding a predetermined signature in the service device is used.

[0191] Next, in step S204, the authentication result is presented to the user through a display on a display, etc. In the case where the user corresponds to a specific person through one-to-one authentication, the user is presented that the authentication has been successful. In addition, information related to the person corresponding to the user is presented through one-to-N authentication.

[0192] On the other hand, in the case where the result of the authentication in step S202 is authentication failure (error) (No in step S202), the process proceeds to step S204, and the fact that the authentication has failed is presented to the user. Then, the process ends.

[0193] Note that the authentication state can be continued by frequently or periodically performing a series of processes while using the service.

[0194] Note that, in the case of an unexpected condition such as insufficient input data or the input data obtained is invalid data, authentication can be determined to be an error. In addition, in the case of determining that there are a predetermined number of times or more errors within a specific period, it can be determined that authentication has failed.

[0195] In the case where multiple authentication models are registered, an appropriate authentication model can be selected according to the situation at the time of authentication. For example, instead of an authentication model for which the input data required for authentication of a modality is insufficient, an authentication model that can already obtain the input data required for authentication of the modality can be selected. In addition, for example, in the case where the user's position is a predetermined distance away from the normal range of action based on the position information, an authentication model learned for the fingerprint modality can be selected. In addition, a model that meets the authentication level required for each service can be selected.

[0196] In the event that it is determined in step S202 that "there is applicability", the authentication model may be updated using input data up to that time.

[0197] The device that outputs the authentication result may be another device other than the authentication device. For example, the authentication device is a smartphone, and the result of the authentication performed by the smartphone is displayed on a display of a cash register in a store, etc.

[0198] In addition, how many authentication results are presented to the user can be arbitrary. For example, the authentication result is presented only with an icon indicating that the key is released or not released, or only an icon indicating that the authentication is performed is presented.

[0199] In addition, the reason why such an authentication result has been obtained may be presented to the user. For example, it may be presented that the authentication is successful because of what conditions are met, such as "because I am at home", "because I am wearing my_headphone_00", and "because I run daily". In addition, for example, it may also be presented what type of modality is used for authentication, such as "use of facial authentication with a camera", "use of location information", and "use of voice". Note that it is not necessary to present why such an authentication result has been obtained. By not presenting anything, the user can use the service without being aware of the authentication.

[0200] <2. Modification>

[0201] [2-1. Modification of user selection mode]

[0202] Although the embodiments of the present technology have been specifically described above, the present technology is not limited to the above-described embodiments, and various modifications based on the technical concept of the present technology are possible.

[0203] In the embodiment, it has been described that input data belonging to a predetermined modality is input to the information processing device 200, but the present technology is not limited thereto, and the user may select a modality to be used for authentication. Fig.13 A first modification of the information processing apparatus 200 in a case where the user selects a modality is described.

[0204] exist Fig.13 In the flowchart of FIG. 1 , steps S101 to S104 are similar to those in the embodiment.

[0205] In step S301, it is determined whether the user agrees to register the authentication information. In the case where the user does not agree to register the authentication information, the process proceeds to step S302 (No in step S301).

[0206] Next, in step S302, a selection of a modality to be used for authentication is accepted from the user. The user can select a modality after confirming the evaluation result about the presented authentication information. For example, a plurality of modality candidates may be presented on a display as the output unit 106, and the user may select a modality to be used for authentication from the candidates through the input unit 105.

[0207] Next, in step S303, the information processing device 200 obtains a plurality of input data belonging to one or more modalities selected by the user. In order to obtain the input data, the plurality of input data belonging to one or more selected modalities may be presented to the user to prompt the user to input the input data.

[0208] Then, the processing of steps S101 to S104 and steps S301 to S303 is repeated until the authentication information is registered. Then, if the user agrees to register the user's authentication information in step S301, the authentication information is registered in step S106, and the processing ends (Yes in step S301).

[0209] Additionally, the user's selection of a modality can be performed before the input data is obtained. Fig.14 A second modification of the information processing apparatus 200 in which the user selects a modality to be used for authentication is described.

[0210] First, in step S401, a user's selection of input data to be used for authentication is accepted. Here, multiple modality candidates may be presented on a display as output unit 106, and the user may select one or more modalities desired for authentication from the candidates through input unit 105.

[0211] Next, in step S402, the information processing device 200 obtains a plurality of input data belonging to the modality selected by the user. In order to obtain the input data, the plurality of input data belonging to one or more selected modalities may be presented to the user to prompt the user to input the input data.

[0212] Steps S102 to S104 are similar to those in the embodiment.

[0213] Then, in step S403 , in a case where the user does not agree to register the authentication information, the process proceeds to step S401 (NO in step S403 ).

[0214] Then, in step S401 , a selection of a modality is received from the user again.

[0215] Then, the processing of steps S401 to S403 and steps S102 to S104 is repeated until the authentication information is registered. Then, in the case where the user agrees to register the authentication information in step S403, the authentication information is registered in step S106, and the processing ends (Yes in step S403).

[0216] Note that each step can be executed simultaneously on the UI.

[0217] Here, a UI for selecting a mode for a user will be described. As a UI, a user may select a mode such as Fig.15 Generic UI for the items shown in A.

[0218] In addition, if Fig.15 B and Fig.15 As shown in C, a UI that visually represents the modal relationship can be used. Fig.15 B and Fig.15C shows the modality and the sub-modality included in the modality and the sensor that can obtain input data about the modality and the sub-modality. Fig.15 In B, the modality "face" includes sub-modalities "eyes", "nose" and "mouth", and the input data for visually indicating each modality can be obtained through a camera device and a distance sensor. Fig.15 In C, the modality “action” includes “walking style”, “movement style”, and “service usage trend” as sub-modalities, and visually indicates that the input data of each modality can be obtained through inertial sensors and service usage history.

[0219] When the user is caused to select the modality, a plurality of candidates configured for selection of authentication information may be presented to the user so that the user can compare the plurality of candidates.

[0220] The information processing apparatus 200 can automatically select a modality to meet the requirements of the evaluation viewpoints of security, privacy, and usability. For example, the user selects an important evaluation viewpoint from among security, privacy, and usability, and then the information processing apparatus 200 can automatically select a modality.

[0221] In addition, the user may input a degree for which importance is placed on each evaluation viewpoint, and the information processing device 200 may automatically select a modality based on the degree. For example, the degree may be input as a numerical value (e.g., a continuous numerical value from 0 to 100), or may be input in discrete steps (e.g., "strong, medium, and weak"). Note that in the case where there is no modality corresponding to the degree input by the user, an output corresponding to "not applicable" may be performed.

[0222] In the case where the user can select a modality, the information processing device 200 can recommend a modality instead of requiring the user to directly select the modalities one by one. This is because if the degree of freedom of modality selection is too high, it may be a burden for the user.

[0223] In addition, Figure 3 and Fig.13 In step S101 of the flowchart shown in , input data of a modality predetermined by an authentication service provider, a system designer, or the like is acquired, but output data of a modality recommended by the information processing apparatus 200 may be acquired.

[0224] The modality to be recommended may be determined according to the user from three evaluation viewpoints, or may be a generally known combination in each modality.

[0225] A modality emphasizing each of the three evaluation viewpoints may be recommended, such as a recommendation emphasizing security, a recommendation emphasizing privacy, and a recommendation emphasizing usability. In addition, a modality emphasizing a balance of the three evaluation viewpoints may be recommended.

[0226] The user can select which of security, privacy, and usability is prioritized, and the corresponding modality is presented to the user so that the user determines the modality.

[0227] The modality to be recommended can be determined by selecting the modality generally considered to be relevant to each evaluation viewpoint. In addition, it is also possible to prevent a modality generally considered to be irrelevant to each evaluation viewpoint from being included in the modality to be recommended.

[0228] For example, in the case of emphasizing security, face or fingerprint is set as a candidate to be recommended, and motion is excluded from the candidates to be recommended. In addition, in the case of emphasizing privacy, action or motion is set as a candidate to be recommended, and location and face are excluded from the candidates to be recommended. In addition, in the case of emphasizing usability, location and object are set as candidates to be recommended, and action and password are excluded from the candidates to be recommended. Furthermore, in the case of emphasizing balance, face and fingerprint are candidates to be recommended.

[0229] In addition, an index can be determined as an evaluation function according to an important evaluation viewpoint, and the parameter space of the way of combining the modalities can be optimized. For example, in the case of selecting a modality, the parameter space is set to 1, and in the case of not selecting a modality, the parameter space is set to 0. In the case of emphasizing safety, a modality is selected by applying a general optimization method with the index "certification level" as an evaluation function.

[0230] The number of modalities to be recommended is not limited to one, and may be multiple. In addition, the user can confirm the recommendation result and select the modality again. The modality is recommended so that time and effort can be reduced when the user customizes, and the load on the user can be reduced.

[0231] Note that the information processing apparatus 200 may include a recommendation processing unit that performs a process related to recommendation, or the control unit 102 of the electronic device 100 may perform a process related to recommendation.

[0232] [2-2. Other changes]

[0233] Other modifications of the present technology will be described.

[0234] The authentication information may be updated after registration to improve the performance of the authentication function. The updating of the authentication information may be performed by a process similar to the registration of the authentication information. At this time, any step may be omitted. For example, the step of presenting the authentication information to the user for confirmation is omitted, the step of reselecting the modality is omitted, etc. This is because it is troublesome for the user to be asked for his confirmation every time, and the usability is deteriorated.

[0235] The registered authentication information can be updated by adding new data to the input data used at the time of registration and recalculating. In addition, the registered authentication information can be updated by adding new data to the input data used at the time of registration by a general method of relearning. In the case where the authentication information is updated, the user can be notified of the update by a general notification method such as display on a display or voice output.

[0236] The updating of authentication information may be performed in response to an instruction input from the user, or may be automatically determined by the information processing apparatus 200. In the case where the information processing apparatus 200 automatically performs the updating, the user may be notified of the updating by a common notification method such as display on a display or audio output.

[0237] The authentication information may be updated at any timing. In addition, the number of updates may be predetermined, and updates may be performed at predetermined timings (daily, weekly, monthly, etc.) until the determined number of updates is performed. In addition, updates may be performed periodically, for example, every night, every month, every day within a week after registration, and every month thereafter.

[0238] In addition, the update can be performed under specific conditions. For example, the update can be performed in the case where the authentication level of the determination result is weak (equal to or less than a predetermined threshold). In addition, in the authentication when using various services that request authentication, the update can be performed using the data of the time point at the timing when the person is determined to be the person himself / herself. For example, in the case where the user's position is away from the normal range of action by a predetermined distance based on the position information, the update is performed every hour.

[0239] In addition, in order to switch according to the situation, multiple different authentication models can be learned and registered. In addition, the authentication model can be updated according to the update of authentication information.

[0240] In addition, a step of performing identity confirmation of the user before registering the authentication information may be included. For example, the identity of the user may be confirmed by reading an integrated circuit (IC) chip of a my number card and using a public personal authentication service.

[0241] In addition, the registered authentication information may be transmitted to another device different from the electronic device 100. For example, in the case where the electronic device 100 is a smartphone, the authentication information may be taken over when the model of the smartphone is changed, or the authentication information may be made available in a function in another device.

[0242] like Fig.16 As shown in , the electronic device 100 can be connected to an external server 300, a service server 400 that requests authentication when providing a service, another device 500, and the like.

[0243] The information processing apparatus 200 may acquire input data from the server 300 , the service server 400 , another device 500 , or the like.

[0244] In addition, the server 300 may have a function as the information processing device 200, and the processing according to the present technology may be performed in the server device 300. In this case, the electronic device 100 transmits the input data to the server 300 through the communication unit 104. In addition, the electronic device 100 receives the authentication result output from the server 300 through the communication unit 104, and outputs the authentication result in the output unit 106.

[0245] The present technology may also have the following configurations. (1)

[0247] An information processing device, comprising:

[0248] an evaluation unit that evaluates a plurality of authentication information about a user based on a plurality of evaluation viewpoints and an index for each evaluation viewpoint; and

[0249] A presentation processing unit that performs processing for presenting the evaluation result of the evaluation unit to the user. (2)

[0251] The information processing device according to (1), wherein the evaluation viewpoint is safety. (3)

[0253] The information processing device according to (1) or (2), wherein the evaluation viewpoint is privacy. (4)

[0255] The information processing device according to any one of (1) to (3), wherein the evaluation viewpoint is usability. (5)

[0257] The information processing device according to (2), wherein the index of security includes authentication strength and resistance to attacks by others. (6)

[0259] The information processing device according to (3), wherein the indicator of privacy is necessity of a modality and a description of input data to be used. (7)

[0261] The information processing device according to (4), wherein the indicators of availability include error rate, stability, and cost. (8)

[0263] The information processing device according to any one of (1) to (7), wherein the evaluation unit evaluates the authentication information based on any one or more of the plurality of evaluation viewpoints. (9)

[0265] The information processing device according to any one of (1) to (8), wherein the evaluation unit evaluates the authentication information based on one or more indicators in the evaluation viewpoint. (10)

[0267] The information processing device according to any one of (1) to (9), wherein the presentation processing unit converts the evaluation result into information for a predetermined presentation method. (11)

[0269] The information processing device according to any one of (1) to (10), further including: a registration unit configured to register the authentication information based on the consent of the user who has confirmed the evaluation result processed and presented by the presentation processing unit. (12)

[0271] The information processing device according to any one of (1) to (11), wherein the authentication information is classified into any one of a plurality of information types defined as modalities. (13)

[0273] The information processing device according to (12), wherein the modality is selected by the user. (14)

[0275] The information processing device according to (13), wherein the modality is selected by the user who has confirmed the presented evaluation result regarding predetermined authentication information. (15)

[0277] The information processing device according to (11), wherein the registration unit learns an authentication model based on the authentication information. (16)

[0279] An information processing method,

[0280] A process of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint and presenting the evaluation result to the user is performed. (17)

[0282] A program for causing a computer to execute an information processing method,

[0283] The information processing method performs a process of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint, and presenting the evaluation result to the user.

[0284] Reference numerals list

[0285] 200 Information processing device

[0286] 201 Evaluation Unit

[0287] Registration Unit 202

[0288] 203 Presentation Processing Unit

Claims

1. An information processing device, include: an evaluation unit that evaluates a plurality of authentication information about a user based on a plurality of evaluation viewpoints and an index for each evaluation viewpoint; as well as A presentation processing unit that performs processing for presenting the evaluation result of the evaluation unit to the user.

2. The information processing device according to claim 1, in, The evaluation viewpoint is safety.

3. The information processing device according to claim 1, in, The evaluation viewpoint is privacy.

4. The information processing device according to claim 1, in, The evaluation viewpoint is availability.

5. The information processing device according to claim 2, in, The security indicators include authentication strength and resistance to attacks by others.

6. The information processing device according to claim 3, in, The privacy indicators are the necessity of the modality and the description of the input data to be used.

7. The information processing device according to claim 4, in, The availability indicators include error rate, stability and cost.

8. The information processing device according to claim 1, in, The evaluation unit evaluates the authentication information based on any one or more of the plurality of evaluation viewpoints.

9. The information processing device according to claim 1, in, The evaluation unit evaluates the authentication information based on one or more indicators in the evaluation viewpoint.

10. The information processing device according to claim 1, in, The presentation processing unit converts the evaluation result into information for a predetermined presentation method.

11. The information processing device according to claim 1, further comprising: include: A registration unit that registers the authentication information based on the consent of the user who has confirmed the evaluation result processed and presented by the presentation processing unit.

12. The information processing device according to claim 1, in, The authentication information is classified into any one of a plurality of information types defined as modalities.

13. The information processing device according to claim 12, in, The modality is selected by the user.

14. The information processing device according to claim 13, in, The modality is selected by the user who has confirmed the presented evaluation result regarding predetermined authentication information.

15. The information processing device according to claim 11, in, The registration unit learns an authentication model based on the authentication information.

16. An information processing method, A process of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint and presenting the evaluation result to the user is performed.

17. A program for causing a computer to execute an information processing method, The information processing method performs a process of evaluating a plurality of authentication information on a user based on a plurality of viewpoints and an index for each viewpoint, and presenting the evaluation result to the user.