JP2007156688A - User authentication device and its method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To achieve user authentication in a short time even under an environment where it is not possible to acquire stable light quality for acquiring the image of a user. <P>SOLUTION: This user authentication device is provided with a camera 51; an authentication part 52 for executing user authentication based on image information from the camera 51; an utterance part 53 for uttering questions relevant to user authentication when the reliability of authentication result by the authentication part 52 is less than a determination reference value for determining that authentication is successful; and a person specifying part 55 for specifying a user based on the authentication result by the authentication part 52 and the reliability and an answer to the question. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to user authentication, and more particularly to a user authentication apparatus and method suitable for use in a self-propelled robot.

Conventionally, various methods have been proposed as a personal authentication technique for identifying individual persons (see, for example, Patent Document 1, Patent Document 2, etc.).
Patent Document 1 discloses a user authentication device that automatically detects the orientation of a target user's face, performs face authentication according to the face orientation, and performs user authentication.
In Patent Document 2, even when the camera cannot be moved quickly following the movement of the user's face, such as a mobile robot (corresponding to the “self-propelled robot” of the present invention), user authentication is performed with high accuracy. Techniques that can be realized are disclosed. Specifically, the front direction of the user's body is detected, image data in the front direction of the user's body is acquired, and a face image is extracted from the image data and used for face authentication.
JP 2002-288670 A JP 2004-46399 A

  By the way, when performing user authentication with a self-propelled robot that moves indoors and realizes a predetermined job or conversation with a user as in Patent Document 2 described above, the place where user authentication is performed is indoors. Any place. When performing user authentication, it is necessary to acquire an image clear enough to extract facial feature points. However, it is very difficult to obtain a stable light amount indoors. Therefore, even if user authentication is performed using the techniques disclosed in Patent Document 1 and Patent Document 2 described above, there is a high probability that user authentication will fail due to insufficient light amount, and user authentication takes time. There was a problem that.

  The present invention has been made to solve the above problem, and a user authentication device capable of realizing user authentication in a short time even in an environment where a stable light quantity cannot be obtained for acquiring a user's image, and An object is to provide such a method.

In order to solve the above problems, the present invention employs the following means.
The present invention is a user authentication device mounted on a self-propelled robot, and includes a photographing unit, an authentication unit that performs user authentication based on image information from the photographing unit, and a reliability of an authentication result by the authentication unit. Is less than the criterion value for determining that the authentication is successful, the utterance means for issuing a question related to user authentication, the authentication result by the authentication means and its reliability, and the answer to the question, There is provided a user authentication device comprising a person specifying means for specifying the user.

According to such a configuration, the situation around the self-propelled robot is acquired as image information by the imaging unit and output to the authentication unit, and user authentication using the image information is performed by the authentication unit. The reliability is output. In this case, when the reliability of the authentication result is equal to or less than the criterion value for determining that authentication is successful, a question related to user authentication is issued from the utterance means, and the person is identified based on the answer to this question. It will be performed by specific means. In this way, when user authentication based on image information is not successful, it is possible to ask the user a question and perform user authentication that also considers the answer to this question. Even in an environment where a stable light quantity cannot be obtained, user authentication can be realized.
The reliability is, for example, a parameter indicating how reliable the authentication result is, and indicates that the higher the parameter, the higher the probability of being the person. In addition, the reliability and the determination reference value are values that are arbitrarily set within an appropriate range depending on what authentication method the authentication unit employs.

  In the user authentication apparatus, the utterance unit may issue a question according to the reliability of the authentication result by the authentication unit.

According to such a configuration, since the question according to the reliability of the authentication result by the authentication means is issued from the utterance means, there is no sense of incongruity for the user, and the time required for user authentication can be further reduced.
For example, when the reliability is high, a relatively definite question such as “Is it Mr. XX?” Reduces the burden on the user's reception, while when the reliability is low, It is possible to shorten the authentication time by asking a question such as “Who is it?” Or the like that pulls out the person's information from the user himself / herself.

  In the user authentication apparatus, when the answer to the question is different from the authentication result by the authentication unit, the person specifying unit may adopt the authentication result by the authentication unit.

  According to such a configuration, when the answer to the question is different from the authentication result by the authentication means, the authentication result by the authentication means is adopted by the person specifying means, thereby preventing misidentification of user authentication due to impersonation or the like. Is possible. In other words, it is easy to impersonate another person by answering “Yes” or “XX” by voice, but impersonation is difficult in image authentication. By adopting, erroneous detection of user authentication can be prevented.

  In the above-described user authentication device, when the reliability of the authentication result by the authentication unit is equal to or higher than the determination reference value between when the question is issued and when an answer to the question is received, the person specifying unit However, it is good also as employ | adopting the authentication result by an authentication means.

  According to such a configuration, when the reliability of the authentication result by the authentication unit is equal to or higher than the determination reference value between when the question is issued and when the answer to the question is received, the person specifying unit Since the authentication result by the means is adopted, it is possible to quickly identify the user without waiting for the user's answer. Further, by adopting the user authentication result based on the image information, it is possible to avoid impersonation and prevent erroneous detection of user authentication.

  In the above-described user authentication device, the authentication unit performs user authentication at a constant time interval, and the utterance unit does not obtain an authentication result having a reliability equal to or higher than the determination reference value within a past predetermined period. In addition, the question may be issued.

  According to the above configuration, the user is identified not only at the time of user authentication but also with reference to the authentication result obtained within the past certain period from that time, so the user authentication is successful even once within the past certain period. In such a case, since the user can be specified based on the authentication result, the authentication time can be shortened.

  The present invention is a self-propelled robot equipped with a user authentication device, in which the user authentication device includes an imaging unit, an authentication unit that performs user authentication based on image information from the imaging unit, and the authentication unit. When the reliability of the authentication result is less than a criterion value for determining that the authentication is successful, an utterance unit that issues a question related to user authentication, an authentication result by the authentication unit and its reliability, and an answer to the question A self-propelled robot having a person specifying means for specifying a user is provided.

  According to such a configuration, when the user authentication based on the image information is not successful, it is possible to ask the user a question and perform the user authentication considering the answer to the question. The user authentication can be performed in a short time even in an environment where the obtained light quantity cannot be obtained.

  The present invention is a user authentication device that is connected to a self-propelled robot including an imaging unit via an information transmission medium and performs user authentication based on information received from the robot, and the imaging device mounted on the robot Receiving means for receiving the image information acquired by the means, authenticating means for performing user authentication based on the received image information, and the reliability of the authentication result by the authenticating means is less than a criterion value for determining that the authentication is successful A question creation means for creating a question related to user authentication, a transmission means for sending the question to the robot, an answer corresponding to the question received from the robot, and an authentication result by the authentication means and And a user specifying means for specifying the user based on the reliability, wherein the transmitting means indicates the result of specifying by the user specifying means. It provides a user authentication apparatus which transmits to the robot.

  With such a configuration, the user authentication device can be installed outside the self-propelled robot. Thereby, it becomes possible to reduce the processing load of the self-propelled robot itself. The information transmission medium may be either wired or wireless. The self-propelled robot and the user authentication device may be connected to each other through a dedicated line, or may be connected to each other via the Internet or the like.

  The present invention is a user authentication method used for a self-propelled robot, in which an authentication process for performing user authentication based on image information from a photographing unit and a reliability of an authentication result in the authentication process are determined to be successful. An utterance process for issuing a question related to user authentication when it is less than a criterion value, and a person specifying process for specifying a user based on an authentication result and its reliability in the authentication process and an answer to the question; A user authentication method is provided.

  The present invention is a user authentication device mounted on a self-propelled robot, and issues an authentication means for performing user authentication, a question related to the user authentication, and depending on the reliability of the authentication result of the authentication means. User comprising speech means for switching the content of the question, and person identifying means for identifying the user based on at least one of reliability of the authentication result of the authentication means and a response from the user to the speech content of the speech means An authentication device is provided.

  According to such a configuration, the question related to the user authentication according to the reliability of the authentication result of the user authentication is made by the utterance means, and the answer from the user to the question and the authentication of the authentication means by the person specifying means A user is identified based on at least one of the reliability of the result. In this way, since the person identification is performed in consideration of the answer from the user regarding the question and the reliability of the authentication result of the authentication means, even if the user authentication by the authentication means fails, the user authentication can be performed efficiently in a short time. Can be done.

  In the above-described user authentication device, the utterance unit may perform the utterance when the reliability of the authentication result by the authentication unit is less than a criterion value for determining that the authentication is successful. According to such a configuration, since the speech is not performed when the authentication by the authentication unit is successful, the authentication can be performed efficiently.

  The present invention has been made to solve the above problem, and has an effect that user authentication can be realized in a short time even in an environment where a stable light quantity cannot be obtained for acquiring a user's image. .

Hereinafter, an embodiment of a self-propelled robot (hereinafter simply referred to as “robot”) according to the present invention will be described with reference to the drawings.
FIG. 1 is a front view of a robot according to an embodiment of the present invention, and FIG. 2 is a left side view of the robot shown in FIG.
As shown in FIGS. 1 and 2, the robot body 1 includes a head 2, a chest 3 that supports the head 2 from below, a right arm 4 a provided on the right side of the chest 3, and a chest 3. A left arm portion 4b provided on the left side, a waist portion 5 connected below the chest portion 3, a skirt portion 6 connected below the waist portion 5, and a leg portion 7 connected below the skirt portion 6; Is provided.

One omnidirectional camera 11 is provided near the top of the head 2. A plurality of infrared LEDs 12 are arranged on the ring at predetermined intervals along the outer periphery of the omnidirectional camera 11.
In the vicinity of the center of the front surface of the head 2, as shown in FIG. 1, the front camera 13 for imaging the front is one on the right side when viewed from the front, and the microphone 14 is one on the left side when viewed from the front. Is provided.

  One monitor 15 is provided near the center of the front surface of the chest 3. One ultrasonic distance sensor 16 for detecting a person is provided above the monitor 15. One power switch 17 is provided below the monitor 15. Above the ultrasonic distance sensor 16, two speakers 18 are provided one on each side. In addition, as shown in FIG. 2, a backpack 33 that can store luggage is provided on the back of the chest 3. The school bag 33 is provided with an opening / closing door 33a that can be rotated around a hinge provided at the top. As shown in FIG. 1, one shoulder switch 19 that functions as a man-machine interface is provided on each of the left and right shoulders of the chest 3. For the shoulder switch 19, for example, a touch sensor is employed.

  A multi-joint structure is adopted for the right arm portion 4a and the left arm portion 4b. In the right arm portion 4a and the left arm portion 4b, side switches 20 are provided in the vicinity of the connection portion with the chest portion 3 to detect the pinching of a body or an object and stop the movement of the arm. As shown in FIG. 1, a handshake switch 21 that functions as a man-machine interface is built in the palm of the right arm 4a. For the side switch 20 and the handshake switch 21, for example, a pressure sensor is employed.

  In the vicinity of the center of the front surface of the waist 5, one ultrasonic distance sensor 22 for detecting a person is provided on each side. Below these ultrasonic distance sensors 22, a sensor region 24 in which a plurality of infrared sensors 23 are arranged is provided. These infrared sensors 22 are for detecting an obstacle or the like in the lower front of the robot body 1. As shown in FIG. 1 and FIG. 2, a total of four microphones 25 are provided below the waist 5 for detecting the sound source direction, one on the left and one on the front and back. As shown in FIG. 2, one handle portion 26 used for lifting the main body is provided on each of the left and right sides of the waist portion 5. The handle 26 is a recess so that the operator's hand can be inserted.

  Below the front surface of the skirt portion 6, a total of three infrared sensors 27 for detecting a step are provided in the center and on the left and right. As shown in FIG. 2, a charging connector 28 is provided on the back surface of the skirt portion 6.

As shown in FIG. 1, one infrared sensor 29 for detecting a lateral distance is provided on the front surface of the leg portion 7 on the left and right sides. These infrared sensors 29 are mainly used for level difference detection.
As shown in FIG. 2, a hook 30 for fixing the position of the robot body 1 to the charging station is provided on the back surface of the leg portion 7. The leg portion 7 is a carriage provided with traveling wheels 31 and four ball casters 32.

Such a robot has a configuration capable of moving independently in a work space by supplying power from a battery built in the robot body 1, and coexists with a human being as a work space indoors. For example, it is used to provide various services for assisting, supporting, and caring for the lives of users such as robot owners and operators in general households.
Therefore, in addition to a conversation function that realizes a conversation with the user, the robot has a function of watching the user's action, assisting the user's action, and acting with the user. Specifically, the robot has a “voice mail function”, a “message function”, a “calling function”, an “information providing function”, and the like. Further, since user authentication is required as a premise for realizing such a function, the robot according to the present embodiment has a user authentication function.
The various functions as described above are realized by, for example, a control device including a microcomputer built in the robot body 1. Specifically, various cameras and various sensors shown in FIG. 1 and FIG. 2 are connected to the control device, and image information from the cameras and sensor detection information from the sensors are acquired, and these information are stored in the information. Various functions described above are realized by executing various programs based on the above. The shape of the robot body 1 is not limited to the shape shown in FIGS. 1 and 2, and various shapes such as a model imitating an animal for pets can be adopted.

  Next, a user authentication function that is a characteristic part of the present invention will be described. This user authentication function is a function realized by the user authentication device provided in the control device described above. The user authentication result by this user authentication function is used when confirming that the user has returned home in the above-mentioned "answering machine function", and in various functions such as identifying the user who transmits the message in the "message function". It is used appropriately.

  As shown in FIG. 3, the user authentication apparatus according to the present embodiment includes a camera (imaging unit) 51, an authentication unit (authentication unit) 52 that performs user authentication based on image information from the camera 51, and an authentication unit 52. When the reliability of the authentication result by the user is less than the criterion value for determining that the authentication is successful, the speech unit 53 that issues a question related to user authentication, the microphone 14, and the voice input from the microphone 14 are recognized. The voice recognition unit 54 and the authentication result by the authentication unit 52 and the reliability thereof are input, and the voice recognition result is input from the voice recognition unit 54, and the person specifying unit 55 that specifies the user based on the input information. And.

  The camera 51 is, for example, the omnidirectional camera 11 or the front camera 13 shown in FIGS. 1 and 2, and acquires information about 360 ° around the robot body 1 and surrounding information about the front of the head 2 as an image. The image information is output to the authentication unit 52. The authentication unit 52 detects the face of a person in the image information acquired from the camera 51 and extracts feature points of the face. Then, the extracted feature points are collated with the feature points of each user registered in advance, and the user is identified based on the collation result. The face authentication technique is not limited to the above technique, and a known technique can be employed. When authenticating the user in this way, the authenticating unit 52 outputs the authentication result and the reliability of the authentication result to the person specifying unit 55. Here, the reliability is, for example, a parameter indicating how reliable the authentication result is, and indicates that the higher the parameter, the higher the probability of being the person. For example, as described above, when user authentication is performed by comparing user feature points extracted from image information with user feature points registered in advance, the degree of reliability of the feature points is as described above. , Corresponding to the ratio indicating whether or not they match.

The person identification unit 55 compares the reliability of the authentication result received from the authentication unit 52 with a preset determination reference value. If the reliability is equal to or higher than the determination reference value, the person specifying unit 55 displays the authentication result received from the authentication unit 52. Hire and identify people. On the other hand, if the reliability is less than the criterion value, the person identification unit 55 outputs the authentication result acquired from the authentication unit 52 and its reliability to the utterance unit 53 without adopting the authentication result. . Here, the determination reference value is a reference value for determining that the person photographed by the camera 51 is the same person as the user authenticated by the authentication unit 52, and may be set as appropriate according to the accuracy of user authentication. Possible value.
In addition, the person specifying unit 55 receives a user's answer to the content uttered by the utterance unit 53 described later from the voice recognition unit, and specifies the person in consideration of the voice recognition result. Details will be described later.

The utterance unit 53 includes, for example, a voice data storage unit 60, a voice data creation unit 61, a voice synthesis processing unit 62, and a speaker 18.
The voice data storage unit 60 stores voice data of a user name registered in the robot, voice data used when making a question related to user authentication, and the like. The voice data used when making a question related to user authentication is created as a voice data file having a multistage structure. A plurality of audio data files are created according to the reliability of the authentication result, and each audio data file is stored in the audio data storage unit 60 in association with the reliability of the authentication result.

  The voice data creation unit 61 accepts the authentication result and the reliability thereof by the authentication unit 52 from the person identification unit 55, and stores the voice data file corresponding to the received reliability and the voice data of the user name corresponding to the authentication result as voice data. The voice data for utterance is created using the voice data file extracted from the unit 60 and the voice data of the user name, and the voice data for utterance is output to the voice synthesis processing unit 62.

  The voice synthesis processing unit 62 executes voice synthesis processing for generating a voice signal to be emitted from the speaker 18 based on the voice data received from the voice data creation unit 62, and outputs the voice signal to the speaker 18. The speaker 18 outputs the voice signal from the voice synthesis processing unit 63 as voice.

  The microphone 14 captures the user's voice and life noise such as a telephone bell, doorbell, TV / radio, etc., converts these voices into electrical signals, and outputs them to the voice recognition unit 52. The voice recognition unit 52 executes voice recognition processing for recognizing a voice signal input from the microphone 14 and outputs the voice recognition result to the person specifying unit 55.

  Next, the operation of the user authentication apparatus when a request for a “message function”, which is a function based on user authentication, is made to the robot according to the present embodiment by referring to FIGS. 4 to 7. To do. 4 to 7, the horizontal axis is a time axis, the upper part of the horizontal axis shows the contents of processing and speech by the robot, and the lower part shows the contents of voice input by the user.

  First, in the robot according to the present embodiment, the state around the robot body 1 is always acquired as image information by the camera 51 of the user authentication apparatus shown in FIG. 3 and output to the authentication unit 52. The authentication unit 52 always performs user authentication based on image information provided from the camera, and outputs the authentication result and its reliability to the person specifying unit 55.

  In such a state, when the user inputs a voice of “send” that is a keyword for requesting the “message function”, the voice information “send” is sent to the person via the microphone 14 and the voice recognition unit 54. It is received by the specifying unit 55. When the person identifying unit 55 receives the “recognize” voice recognition result, the reliability Q is set to the determination reference value (in this embodiment, “120” as an example) in the past predetermined period T from this point. It is determined whether the authentication result is received from the authentication unit 52 or not.

As a result, as shown in FIG. 4 (a), an authentication result having a reliability Q equal to or higher than the criterion value was obtained within a predetermined period T in the past from the time when the "recognize" speech recognition result was received. In this case, the person identifying unit 55 adopts “user ID = 4”, which is the authentication result received from the authenticating unit 52, and registers the person who made the request for the “message function” as “user ID = 4”. The user “A child” is identified, and this authentication result is output as a final authentication result.
In FIG. 4A, the upper part shows the speech content and authentication result of the robot, and the lower part shows the voice input from the user (hereinafter, FIGS. 4B to 4D and FIGS. 5 to 7). The same shall apply).

  Next, within the past predetermined period T from the time point when the above-mentioned voice notification result of “tell” is received, the reliability Q is less than a judgment reference value (for example, score 120) and an estimable value (for example, score 100). ) A case where the above recognition result “user ID = 5” is obtained will be described with reference to FIG. Here, the estimable value is a reference value that can be estimated that the person photographed by the camera 51 is the same person as the user authenticated by the authentication unit 52, and is a value that is set lower than the determination reference value. is there.

In this case, the person specifying unit 55 does not adopt “user ID = 4”, which is the authentication result by the authentication unit 52, but uses the authentication result “user ID = 4” and its reliability Q as voice data of the utterance unit 53. The data is output to the creation unit 61.
The voice data creation unit 61 uses the voice data file associated with the certainty factor (120> Q ≧ 100) acquired from the person identification unit 55 and the user name “A child” corresponding to the authentication result “user ID = 4”. Voice data is acquired from the voice data storage unit 60, and voice data for speech is created based on these pieces of information. For example, utterance voice data is created so that the user can answer “Yes” or “No” such as “A child?”. As a result, the utterance voice data is output to the speaker 18 via the voice data creation unit 61, whereby the utterance "A child?"

  In response to this question, when a positive word such as “Yes” is issued by the user, this information is input to the person identification unit 55 via the microphone 14 and the voice recognition unit 54. When the person specifying unit 55 receives the voice information indicating the positive content from the voice recognition unit 54, the person specifying unit 55 determines that the authentication result of the authentication unit 52 is correct, and adopts the authentication result of the authentication unit 52. The person who made the request for “message function” is identified as the user “A child” registered as “user ID = 4”, and this authentication result is output as the final user authentication result.

  On the other hand, as shown in FIG. 4C, when the user inputs a negative content such as “No” to the question uttered by the utterance unit 53, the information is stored in the microphone 14, the voice, The information is input to the person specifying unit 55 via the recognition unit 54. When the person specifying unit 55 receives voice information indicating negative contents from the voice recognition unit 54, the person specifying unit 55 outputs information indicating that the negative answer is received to the uttering unit 53. When the utterance unit 53 obtains information indicating that a negative answer has been received, the utterance unit 53 further utters content that directly asks the name from the user, such as “Who is?”.

  In response to such a question, when information “B child” is input by voice from the user, this information is output to the person specifying unit 55 via the microphone 14 and the voice recognition unit 54. When the person specifying unit 55 receives information about the name, the person specifying unit 55 outputs this information to the uttering unit 53. As a result, the utterance unit 53 utters content that prompts the user to confirm “You are B child”. When the positive information “Yes” is inputted by voice in response to this inquiry, the person identifying unit 55 adopts “B child” input from the user as the user authentication result, and the user authentication result. Is output as the final user authentication result.

  Next, a recognition result “ID = 4” is obtained as a reliability Q that is less than an estimable value (for example, a score of 100) within the past predetermined period T from the time when the above-mentioned speech recognition result “Tell” is received. The case will be described with reference to FIG.

In this case, the person specifying unit 55 does not adopt “user ID = 4”, which is the authentication result by the authentication unit 52, but uses the authentication result “user ID = 4” and its reliability Q as voice data of the utterance unit 53. The data is output to the creation unit 61.
The voice data creation unit 61 acquires the voice data of the voice data file associated with the certainty factor (100> Q) acquired from the person specifying unit 55 from the voice data storage unit 60, and based on these information, Create speech data for speech. For example, utterance voice data for making a question of directly asking the user a name such as “Who is?” Is created. As a result, the utterance voice data is output to the speaker 18 via the voice synthesis processing unit 62, whereby the utterance “Who is?” Is performed.

  In response to this question, when a content related to a name such as “A child” is input by voice by the user, this information is input to the person specifying unit 55 via the microphone 14 and the voice recognition unit 54. When the person specifying unit 55 receives voice information from the voice recognition unit 54, the person specifying unit 55 outputs this information to the utterance unit 53. As a result, a question that can be answered with “Yes” or “No”, such as “You are A child,” is made from the utterance unit 53, and when the positive information “Yes” is input to this question Based on the voice recognition result, the person specifying unit 55 adopts “A child” input from the user as a user authentication result, and outputs the user authentication result as a final user authentication result.

  Next, as shown in FIGS. 4B and 4C, an authentication result equal to or higher than the criterion value is not obtained by the authenticating unit 52 within a predetermined period T, and the user's interaction with the utterance unit 53 as described above is not obtained. A case where the person specifying unit 55 acquires an authentication result having a reliability Q equal to or higher than the determination reference value from the authentication unit 52 when a dialogue is performed will be described with reference to FIGS. 5 to 7.

As shown in FIGS. 5 (a) and 5 (b), the utterance unit 53 asks "A child?", And "Yes" indicating affirmative or "No" indicating negative. ”Is input from the user by voice before the next utterance corresponding to“ Yes ”or“ No ”, an authentication result having a reliability Q equal to or higher than a criterion value from the authentication unit 52, for example, When “user ID = 5” is received, the person identification unit 55 invalidates the voice input from the user and adopts the authentication result from the authentication unit 52. That is, the person who has requested the “message function” is identified as “B child” registered as “user ID = 5”, and this result is output as the final user authentication result.
In this way, by adopting the authentication result of the authentication unit 52 that performs authentication based on the image information over the voice input from the user in preference, a situation where a third party impersonates the user is prevented. be able to.

  Also, as shown in Fig. 6 (a), when the user inputs a voice indicating that the answer is "No" to the question from the utterance unit 53, "No", Is asked from the utterance unit 53. On the other hand, when a voice input of “B child” is made by the user, an utterance in response to the voice input, for example, “B-san, is it” is performed. In this case, as shown in FIG. 6 (a), before performing the utterance, the authentication unit 52 obtains a recognition result equal to or higher than the criterion value, for example, “user ID = 4”. When input to the unit 55, the person specifying unit 55 invalidates the voice input from the user and adopts the authentication result from the authentication unit 52. That is, the person who has requested the “message function” is identified as “child A” registered as “user ID = 4”, and the result is output as the final user authentication result.

  Also, as shown in FIG. 6 (b), after the utterance unit 53 asks "You are B child?", The period from when the user input is accepted, as shown in FIG. 6 (c). , During the period from when the voice input “Yes” is received in response to the question “Mr. B,” and the utterance is made in response to this voice input, the recognition result of the authentication unit 52 or higher, for example, “User When “ID = 4” is obtained and this result is input to the person specifying unit 55, the person specifying unit 55 invalidates the voice input from the user and adopts the authentication result from the authentication unit 52. That is, the person who has requested the “message function” is identified as “child A” registered as “user ID = 4”, and the result is output as the final user authentication result.

  Similarly, as shown in FIGS. 7A to 7C, when only an authentication result less than an estimable value is obtained within a predetermined period T, the utterance unit 53 asks “Who is it?” The question will be made. When information “B child” is inputted by voice in response to this inquiry, the authentication unit 52 has a reliability Q equal to or higher than a criterion value before performing the next utterance corresponding to this “B child”. For example, when “user ID = 4” is accepted, the person specifying unit 55 invalidates the voice input from the user and adopts the authentication result from the authentication unit 52. That is, the person who has requested the “message function” is identified as “child A” registered as “user ID = 4”, and the result is output as the final user authentication result.

Also, as shown in FIGS. 7B and 7C, the period from the time when the user asks "B-san?" Until the input from the user is accepted, as shown in FIG. 7C. In addition, during the period from when the voice input “Yes” is received in response to the question “B-san”, the authentication unit 52 recognizes a recognition result equal to or higher than the criterion value, for example, “ When “user ID = 4” is received, the person specifying unit 55 invalidates the voice input from the user and adopts the authentication result from the authentication unit 52. That is, the person who has requested the “message function” is identified as “child A” registered as “user ID = 4”, and the result is output as the final user authentication result.
In this way, by adopting the authentication result of the authentication unit 52 that performs authentication based on the image information over the voice input from the user in preference, a situation where a third party impersonates the user is prevented. be able to.

  As described above, according to the user authentication device according to the present embodiment, the state around the self-propelled robot is acquired as image information by the camera 51 and output to the authentication unit 52, and this image information is used. User authentication is performed by the authentication unit 52, and the authentication result and its reliability are output. In this case, when the reliability of the authentication result is equal to or less than a criterion value for determining that the authentication is successful, a question related to user authentication is issued from the utterance unit 53, and the person is identified based on the answer to the question. This is performed by the person specifying unit 55. In this way, when user authentication based on image information is not successful, it is possible to ask the user a question and perform user authentication that also considers the answer to this question. Even in an environment where a stable light quantity cannot be obtained, user authentication can be realized.

Furthermore, according to the user authentication apparatus according to the present embodiment, since the question according to the reliability of the authentication result by the authentication unit 52 is issued from the utterance unit 53, there is no sense of incongruity for the user, and further, user authentication is required. Time can be shortened. For example, when the reliability is high, a relatively definite question such as “Is it Mr. XX?” Reduces the burden on the user's reception, while when the reliability is low, It is possible to shorten the authentication time by asking a question such as “Who is it?” Or the like that pulls out the person's information from the user himself / herself.
Furthermore, according to the user authentication device according to the present embodiment, when the answer to the question is different from the authentication result by the authentication unit 52, the authentication result by the authentication unit 52 is adopted by the person specifying unit 55, so It is possible to prevent misidentification of user authentication due to. In other words, it is ready to impersonate another person by answering “Yes” or “XX” by voice, but impersonation is difficult in image authentication. By adopting, erroneous detection of user authentication can be prevented.

  Furthermore, according to the user authentication device according to the present embodiment, when the reliability of the authentication result by the authentication unit 52 is equal to or higher than the determination reference value between when the question is issued and when the answer to the question is received. Since the authentication result by the authentication unit 52 is adopted by the person specifying unit 55, the user can be specified quickly without waiting for the user's reply. Further, by adopting the user authentication result based on the image information, it is possible to avoid impersonation and prevent erroneous detection of user authentication.

Note that the utterance content described above is merely an example, and when user authentication based on image information is difficult, it may be configured such that information for identifying the user is further asked in a guidance format. For example, in FIG. 4B, when the robot asks “Is Mr. A ??”, if the user does not receive an answer for a predetermined period, Please say "Yes". ”Or the like may be issued to explain in more detail how the user should answer.
In FIG. 4D, when the robot asks "Who is?", If the user does not get an answer over a predetermined period, for example, "You are A child Talking about content that induces (guidance) the user's answer, such as “Is it B or Mr. B?” Or “Please answer yes if you are A” Also good.
Thus, by performing the guidance, the user can grasp how he / she should answer, so that convenience can be improved. Moreover, since it becomes possible to narrow down the word of the response from a user on the robot side, the effect that the success rate of speech recognition can be improved is acquired.

  Also, instead of directly listening to the user's name, it is possible to improve the accuracy of user authentication by voice input by registering a password or keyword corresponding to each user in advance and asking the password. Moreover, it is good also as changing the said utterance content according to a user.

  Furthermore, in the above-described embodiment, the case where user authentication is performed in the robot body has been described. However, the present invention is not limited to this example, and a part of the above-described user authentication device is mounted on an external device. Also good. For example, a control device built in the robot body 1 and an external device are connected via an information transmission medium such as the Internet or a LAN to enable bidirectional communication. The robot body 1 is equipped with, for example, the camera 51, the microphone 14, the speech synthesis processing unit 62 of the utterance unit 53, and the speaker 18, and the external device includes the authentication unit 52, the person specifying unit 55, and the utterance unit 53. The voice data creation unit 61 and the voice data storage unit 60 are mounted. Then, by transmitting information from the camera 51 provided in the robot body 1 to the external device from the robot body 1 via the network, the authentication unit 52 provided in the external device performs user authentication, The person specifying unit 55 may specify the user based on this information. If the reliability of the authentication result by the authentication unit 52 is less than the reference determination value, the voice data creation unit (question creation unit) 61 is based on the voice data stored in the voice data storage unit 60. Speech data for speech may be created, and the speech data for speech may be transmitted to the robot body 1 via a communication transmission medium. As a result, the speech data for speech is output as speech via the speech synthesis processing unit 62 and the speaker 18 provided in the robot body 1. In addition, the user's answer to this question is analyzed by the microphone 14 and the voice recognition unit 54, and the analysis result is transmitted from the robot body 1 to the external device via the information transmission medium. It is possible to realize user authentication in consideration of the result. In addition, about each part provided in an external apparatus, it is an example and it is good also as providing each other part in an external apparatus, and good also as providing in a robot main body.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes design changes and the like within a scope not departing from the gist of the present invention.

It is a front view of the robot which concerns on one Embodiment of this invention. It is a left view of the robot shown in FIG. It is a block diagram which shows the example of 1 structure of the user authentication apparatus incorporated in the robot main body shown in FIG. It is a figure for demonstrating an effect | action of the user authentication apparatus which concerns on one Embodiment of this invention. It is a figure for demonstrating an effect | action of the user authentication apparatus which concerns on one Embodiment of this invention. It is a figure for demonstrating an effect | action of the user authentication apparatus which concerns on one Embodiment of this invention. It is a figure for demonstrating an effect | action of the user authentication apparatus which concerns on one Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Robot main body 11 Omnidirectional camera 13 Front camera 14 Microphone 18 Speaker 51 Camera 52 Authentication part 53 Speech part 54 Voice recognition part 55 Person specific part 60 Voice data storage part 61 Voice data creation part 62 Voice synthesis process part

Claims (10)

A user authentication device mounted on a self-propelled robot,
Photographing means;
Authentication means for performing user authentication based on image information from the photographing means;
Utterance means for issuing a question related to user authentication when the reliability of the authentication result by the authentication means is less than a criterion value for determining that authentication is successful;
A user authentication device comprising: a person specifying unit for specifying a user based on an authentication result by the authentication unit, its reliability, and an answer to the question.   The user authentication apparatus according to claim 1, wherein the utterance unit issues a question according to the reliability of the authentication result by the authentication unit.   3. The user authentication device according to claim 1, wherein when the answer to the question is different from the authentication result by the authentication unit, the person specifying unit adopts the authentication result by the authentication unit.   If the reliability of the authentication result by the authentication unit is greater than or equal to the determination reference value between the time when the question is issued and the time when the answer to the question is received, the person specifying unit is the authentication result by the authentication unit. The user authentication device according to claim 1, wherein the user authentication device is employed. The authentication means performs user authentication at regular time intervals,
The user according to any one of claims 1 to 4, wherein the utterance unit issues the question when an authentication result having a reliability equal to or higher than the determination reference value has not been obtained within a certain period in the past. Authentication device. A self-propelled robot equipped with a user authentication device,
The user authentication device is
Photographing means;
Authentication means for performing user authentication based on image information from the photographing means;
Utterance means for issuing a question related to user authentication when the reliability of the authentication result by the authentication means is less than a criterion value for determining that authentication is successful;
A self-propelled robot comprising: a person specifying means for specifying a user based on an authentication result by the authentication means, its reliability, and an answer to the question. A user authentication device that is connected to a self-propelled robot having an imaging unit via an information transmission medium and performs user authentication based on information received from the robot,
Receiving means for receiving image information acquired by the imaging means mounted on the robot;
Authentication means for performing user authentication based on the received image information;
A question creation means for creating a question related to user authentication when the reliability of the authentication result by the authentication means is less than a criterion value for judging that the authentication is successful;
Transmitting means for transmitting the question to the robot;
A user specifying means for specifying the user based on an answer corresponding to the question received from the robot, an authentication result by the authentication means and its reliability, and
A user authentication apparatus in which the transmitting unit transmits a result of identification by the user identifying unit to the robot. A user authentication method used for a self-propelled robot,
An authentication process for performing user authentication based on image information from the imaging means;
An utterance process for issuing a question related to user authentication when the reliability of the authentication result in the authentication process is less than a criterion value for determining that authentication is successful,
A user authentication method comprising: a person specifying step of specifying a user based on an authentication result and its reliability in the authentication step and an answer to the question. A user authentication device mounted on a self-propelled robot,
An authentication means for performing user authentication;
An utterance unit that issues a question related to the user authentication and switches the content of the question according to the reliability of the authentication result of the authentication unit;
A user authentication device comprising: a person specifying unit that specifies a user based on at least one of a reliability of an authentication result of the authentication unit and a response from the user to the utterance content of the utterance unit.   The user authentication device according to claim 9, wherein the utterance unit utters when the reliability of the authentication result by the authentication unit is less than a criterion value for determining that the authentication is successful.

Images