JP2010191802A - Information processing system, image display, program, and information storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information processing system, or the like for presenting content reflecting a user's selection history in each user situation. <P>SOLUTION: The information processing system includes: a user recognition section for recognizing a user; a selection history information storage section for storing selection history information of the genre of content selected by the user in association with a user situation, namely at least one of time, a location where the user stays, and the user's state; and a content selection section for reading the selection history information associated with each user situation of a recognized user, based on the user's recognition result and user situation from the selection history information storage section when the user recognition section recognizes the user, and selecting presentation content to the user from among a plurality of pieces of content, based on the read selection history information. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an information processing system, an image display device, a program, an information storage medium, and the like.

  2. Description of the Related Art Conventionally, an information processing system that acquires user action schedule information and location information, selects content based on the acquired information, and presents the content to the user is known (for example, Patent Document 1).

  However, in this information processing system, the system does not store what selection operation the user has performed on the content in each situation. For this reason, there existed a subject that an appropriate content according to a user's selection history cannot be shown to a user.

JP 2003-308407 A

  According to some aspects of the present invention, it is possible to provide an information processing system, an image display device, a program, and an information storage medium that enable presentation of content reflecting a user's selection history in each user situation.

  According to one embodiment of the present invention, a user recognition unit that recognizes a user and selection history information on a genre of content selected by the user are associated with a user situation that is at least one of time, a place where the user stays, and a user's state. And when the user is recognized by the user recognition unit, the selection history information associated with each user status of the recognized user based on the user recognition result and the user status. Is related to an information processing system including a content selection unit that selects content to be presented to the user from a plurality of contents based on the read selection history information. The present invention also relates to a program that causes a computer to function as each of the above-described units, or a computer-readable information storage medium that stores the program.

  In one aspect of the present invention, the selection history information of the genre of the content selected by the user is stored in association with the user situation at that time. When the user is recognized by the user recognition unit, the selection history information associated with each user status of the recognized user is read, and the content to be presented to the user is selected based on the read selection history information. The In this way, in each user situation of the recognized user, the content is selected based on the selection history information associated with the user situation and presented to the user. Accordingly, it is possible to present content reflecting the user's selection history in each user situation.

  Moreover, in one aspect of the present invention, the selection history information storage unit has each probability distribution of the first to Nth probability distribution information for selecting a genre for each user situation of the first to Nth user situations. When the user status of the recognized user is the Kth user status among the first to Nth user statuses (1 ≦ K ≦ N), the information is stored in association with each other. Reads out the Kth probability distribution information associated with the Kth user situation from the selection history information storage unit, selects a genre with the probability according to the read out Kth probability distribution information, and selects Content corresponding to the selected genre may be selected as the presented content.

  In this way, when the user situation is the Kth user situation, the genre is selected with the probability according to the Kth probability distribution information associated with the Kth user situation, and the corresponding content is presented. Will come to be.

  In one aspect of the present invention, the selection history information storage unit stores the first to Nth probability distribution information for each of a plurality of users, and the content selection unit corresponds to a recognized user. The first to Nth probability distribution information to be read may be read from the selection history information storage unit to select the presented content.

  In this way, the presented content is selected according to the probability distribution information that is different for each user, and the optimum content according to each user can be presented.

  In the aspect of the invention, each probability distribution information of the first to Nth probability distribution information may be a probability distribution table in which selection frequencies of each genre are associated with each genre of a plurality of genres. Good.

  By using such a probability distribution table, the genre selection process based on the probability distribution information and the update process of the probability distribution information can be simplified.

  According to another aspect of the present invention, the content selection unit includes a correction unit that corrects the Kth probability distribution information based on at least one of the K−1th probability distribution information and the K + 1th probability distribution information. The presentation content may be selected by selecting a genre with a probability according to the corrected Kth probability distribution information.

  In this way, in the Kth user situation, the (K-1) th probability distribution information associated with the (K-1) th user situation and the (K + 1) th probability distribution information associated with the (K + 1) th user situation are obtained. The reflected presentation content can be selected.

  In the aspect of the invention, the correction unit may weight the K-th probability distribution information before correction based on at least one of the K-1th probability distribution information and the K + 1-th probability distribution information. Correction may be performed.

  By performing such weighting correction, it is possible to seamlessly switch the presented content.

  In one aspect of the present invention, first to Nth time slots are set corresponding to the first to Nth user situations, and the selection history information storage unit includes the first to Nth time slots. Each of the first to N-th probability distribution information is stored in association with each of the time slots, and the content selection unit is configured to store the time corresponding to the user status as the first to N-th times. If the slot belongs to the Kth time slot, the Kth probability distribution information associated with the Kth time slot may be read from the selection history information storage unit to select the presented content. .

  In this way, in each time slot, the presentation content can be selected and presented according to the probability distribution information associated with each time slot.

  In one aspect of the present invention, the correction unit includes a correction unit that corrects the Kth probability distribution information based on at least one of the K−1th probability distribution information and the K + 1th probability distribution information, and the correction unit includes: In the first half period of the Kth time slot, the Kth probability distribution information before correction is subjected to weighting correction based on the K-1th probability distribution information of the K-1 time slot, and In the second half period of the Kth time slot, weight correction may be performed on the Kth probability distribution information before correction based on the K + 1th probability distribution information of the (K + 1) th time slot.

  In this way, it is possible to present content reflecting the (K−1) th probability distribution information in the first half period of the Kth time slot, and the (K + 1) th probability in the second half period of the Kth time slot. The content reflecting the distribution information can be presented.

  According to another aspect of the present invention, the information update unit includes an information update unit that performs an update process of the selection history information stored in the selection history information storage unit, and the information update unit presents a plurality of contents having different genres to the user. When it is determined that the user has performed a selection operation on the presented content, the selection history information update process may be performed.

  In this way, it is possible to update the selection history information reflecting the selection operation of each user.

  In one aspect of the present invention, the selection history information storage unit stores, as the selection history information, information in which a selection frequency of each genre is associated with each genre of a plurality of genres, and the information update unit includes When it is determined that the user has performed a selection operation on the presented content, the selection frequency of the genre corresponding to the content on which the selection operation has been performed may be updated.

  In this way, the update process of the selection history information can be realized by updating the genre selection frequency by the user's selection operation.

  In the aspect of the present invention, the content selection unit may select the presentation content at random from a plurality of contents when the user is not recognized by the user recognition unit.

  In this way, even when the user is not recognized, the randomly selected content can be selected and presented.

  In the aspect of the present invention, the content selection unit may recognize the user when the user recognized by the user recognition unit determines that the selection operation is not performed on the presented content. The presented content may be selected based on the user situation and the selection history information.

  In this way, when the recognized user is not performing the selection operation, it becomes possible to select and present the content according to the user situation and the selection history information. For example, the user is prompted to select the content. It becomes possible.

  In the aspect of the present invention, the content selection unit may perform the selection operation when the user recognized by the user recognition unit performs a selection operation on the presented content. Content belonging to the genre of the presented content may be selected as the presented content.

  In this way, content belonging to the genre of content selected with interest by the user can be presented.

  In the aspect of the invention, the content selection unit may determine that the user is performing a content selection operation when it is determined that the user is watching the display unit on which the content image is displayed. May be.

  In this way, it is possible to determine whether or not the user is selecting the content depending on whether or not the user is gazing.

  According to another aspect of the present invention, the information update unit includes an information update unit that performs an update process on the selection history information stored in the selection history information storage unit, and the information update unit is selected by the user for the presented content. When it is determined that an operation has been performed, the selection history information may be updated.

  In this way, it is possible to update the selection history information reflecting the selection operation of each user.

  Moreover, in one aspect of the present invention, based on information including sensor information from at least one of a behavior sensor that measures a user's behavior, a state sensor that measures a user's state, and an environment sensor that measures a user's environment, A user situation estimation unit for estimating the user situation may be included.

  In this way, it is possible to estimate a user's situation based on information including sensor information from a behavior sensor, a state sensor, or an environment sensor, and to select selection history information corresponding to the estimated user situation and select content. become.

  In another aspect of the present invention, a display for displaying an image, a user recognition unit for recognizing a user, and a display for performing control for displaying an image of content selected from a plurality of contents on the display unit. A selection history information of a genre of content selected by the user is associated with a user situation that is at least one of time, a place where the user stays, and a user state, and the display control unit includes: When a user is recognized by the user recognition unit and content is selected based on the selection history information associated with the user status of the recognized user, an image of the selected content is displayed on the display unit. The present invention relates to an image display device that performs control. The present invention also relates to a program that causes a computer to function as each of the above-described units, or a computer-readable information storage medium that stores the program.

  According to another aspect of the present invention, the selection history information of the content genre is associated with the user situation, and when the user is recognized by the user recognition unit, the selection associated with each user situation of the recognized user. A content is selected based on the history information, and a content image is displayed. Therefore, it is possible to display a content image reflecting the user selection history in each user situation.

  In another aspect of the present invention, the display control unit displays an image of content randomly selected from a plurality of contents on the display unit when the user is not recognized by the user recognition unit. Display control may be performed.

  In another aspect of the present invention, the display control unit is recognized when it is determined that the user recognized by the user recognition unit is not performing a selection operation on the presented content. You may perform control which displays the image of the content selected based on the user's user condition and the selection history information on the display part.

  In another aspect of the present invention, the display control unit may perform a user selection operation when it is determined that the user recognized by the user recognition unit has performed a selection operation on the presented content. You may perform control which displays the image of the content which belongs to the genre of the content currently shown on the said display part.

  In another aspect of the present invention, a gaze state determination unit that determines whether or not the user is gazing at the display unit is included, and the display control unit is determined that the user is gazing at the display unit. In such a case, control may be performed to display an image of content belonging to the content genre displayed at the time of user's gaze on the display unit.

  In another aspect of the present invention, the selection history information is information in which a selection frequency of each genre is associated with each genre of a plurality of genres, and for the content image displayed on the display unit. When it is determined that the user has performed the selection operation, the selection frequency of the content genre displayed during the user's selection operation may be updated.

FIG. 1A and FIG. 1B are explanatory diagrams of the method of this embodiment. 1 is a configuration example of an information processing system according to an embodiment. The flowchart for demonstrating the operation | movement of this embodiment. Explanatory drawing of the content selection method using a time slot. 5A and 5B are examples of a probability distribution table and a user content table. Example of probability distribution (histogram) of selection frequency. FIGS. 7A and 7B are explanatory diagrams of a technique for correcting probability distribution information. 8A and 8B are explanatory diagrams of another example of the probability distribution information correction method. 9A and 9B are diagrams illustrating examples of digital photo frames. 2 is a configuration example of a digital photo frame and an information processing system. 11A and 11B show examples of the user upload screen and user information. The state transition diagram for demonstrating operation | movement of this embodiment. The flowchart for demonstrating operation | movement of a digital photo frame. The flowchart for demonstrating operation | movement of a server.

  Hereinafter, this embodiment will be described. In addition, this embodiment demonstrated below does not unduly limit the content of this invention described in the claim. In addition, all the configurations described in the present embodiment are not necessarily essential configuration requirements of the present invention.

1. Content Selection According to User Recognition Result and Selection History In order to present appropriate content to the user, it is desirable to grasp the user's situation and select and present the content according to the user's situation. For example, if it is morning before going to work, it presents content that informs today's news and weather, and if it is going to work, it presents content such as timetables and traffic information. Alternatively, when the user is in a tension state, the content for relaxing the tension is presented, and when the user's physical condition is not excellent, the content for energizing the user is presented.

  However, in the method of presenting content based on the user's situation in this way, the presented content may be uniform and monotonous. In other words, the morning content is always presented in the morning, and the daytime content is always presented in the daytime, so that the presented content is uniform.

  Moreover, the genre of the content desired by the user varies depending on the user. For example, the genre of content preferred by fathers and the genre of content preferred by mothers and children are often different. Therefore, if the uniform content prepared on the system side is presented without specifying any user, the content that each user actually desires cannot be presented, and the user may feel uncomfortable.

  Therefore, in this embodiment, a method of selecting content according to the user recognition result and the selection history is adopted.

  In other words, in this embodiment, the user situation that is the time, the place where the user stays, and the user status is specified (estimated). In FIG. 1A, the user situation of the user UA is represented as a context designated by the coordinate axes of time, place, and state.

  In the present embodiment, the system stores the user's selection history (selection probability distribution) in each such user situation. For example, when the user situation is the first user situation, the selection history of the content (genre) selected by the user is stored in association with the first user situation as the first selection history, and the second user The selection history of the content (genre) selected by the user in the case of the situation is stored in association with the second user situation as the second selection history. Specifically, the selection history of the content selected in the morning (first user situation) is stored in association with “morning”, and the selection history of the content selected in the daytime (second user situation). Are stored in association with “daytime”. Alternatively, the selection history of the content selected in the case of the tension state (first user situation) is stored in association with the “tension state”, and the selection of the content selected in the case of the poor physical condition (second user situation) The history is stored in association with the “physical condition”.

  Next, when selecting content, first, the current user situation of the user is specified. When the user situation is specified, the selection history associated with the specified user situation is read from the selection history stored in the system, and the content is selected based on the read selection history.

  For example, in the user situation “morning”, the user frequently selects content in the genre of current news and weather, and in the user situation “daytime”, the user frequently selects content in the genre of stock price information that is a hobby. Suppose. In such a case, the system stores these selection frequency histories in association with user situations of “morning” and “daytime”.

  Therefore, if the user situation is identified as “morning”, the content is selected so that the genre of current news or weather is selected with a high probability, and the user situation is identified as “daytime”. The content is selected so that the genre of the stock price information is selected with a high probability.

  By doing in this way, the selection of the content reflecting the user's past selection history is performed. Therefore, it is possible to present appropriate content that reflects the user's preferences and the like as compared with the conventional method that can present only uniform content.

  In addition, the present embodiment employs a method of selecting content that reflects not only the user selection history but also the user recognition result.

  For example, as shown in FIGS. 1A and 1B, different selection histories are stored in the system for the users UA and UB even in the same user situation (context). When presenting the content to the user, the user recognizes whether the user is a registered user UA or UB using face image recognition or the like.

  When the user UA is recognized, a selection history corresponding to the current user status of the user UA is selected from the selection history stored in the system in association with each user status (context) of the user UA. read out. Then, the genre is selected with the probability according to the probability distribution of the read selection history, and the content of the selected genre is presented to the user. On the other hand, when the user UB is recognized, the selection history corresponding to the current user status of the user UB is read out from the selection history stored in the system in association with each user status of the user UB. Then, the genre is selected with the probability according to the probability distribution of the read selection history, and the content of the selected genre is presented to the user.

  In this way, even in the same user situation, different contents can be selected if the users are different, and appropriate contents can be presented for each user. Therefore, the content desired by each user can be presented, and the user can be prevented from feeling uncomfortable.

2. Configuration FIG. 2 shows a configuration example of an information processing system capable of realizing the content selection method of the present embodiment as described above. The information processing system is not limited to the configuration shown in FIG. 2, and various modifications such as omitting some of the components or adding other components are possible.

  The processing unit 102 performs various processes based on operation information from an operation unit (not shown), sensor information acquired from the sensor 150, and the like. For example, sensor information acquisition processing, various types of calculation processing, evaluation processing, and information presentation control processing by the information presentation unit 142 such as a display are performed. The function of the processing unit 102 can be realized by hardware such as various processors (CPU, etc.), ASIC (gate array, etc.), a program stored in the information storage medium 130 (optical disc, IC card, HDD, etc.), and the like.

  The storage unit 120 serves as a work area for the processing unit 102, the communication unit 138, and the like, and functions thereof can be realized by a memory such as a RAM or an HDD (hard disk drive). The storage unit 120 includes a content information storage unit 122, a selection history information storage unit 124, and a schedule information storage unit 126.

  The content information storage unit 122 (content database) stores content information such as images, video, music, audio, text (characters, sentences), or various data. This content may be generated in real time, or may be downloaded from the outside via the communication unit 138, for example. The content information storage unit 122 can store meta information (additional information) associated with the content.

  The selection history information storage unit (selection history database, probability distribution database) 124 stores selection history information (selection frequency history information). Specifically, the selection history information of the content genre by the user is stored in association with the user situation. That is, selection history information representing a history of what genre the user has selected in each user situation is stored. The schedule information storage unit 126 stores user schedule information (schedule data, schedule information).

  The information storage medium 130 (a computer-readable medium) stores programs, data, and the like, and its function can be realized by an optical disk (CD, DVD), a hard disk (HDD), or the like. The processing unit 102 performs various processes of the present embodiment based on a program (data) stored in the information storage medium 130. That is, in the information storage medium 130, a program for causing a computer (an apparatus including an operation unit, a processing unit, a storage unit, and an output unit) to function as each unit of the present embodiment (a program for causing the computer to execute processing of each unit). Is memorized.

  The processing unit 102 includes a sensor information acquisition unit 104, a user recognition unit 106, a situation estimation unit 108, a content selection unit 110, a correction unit 111, a presentation control unit (display control unit) 112, and an information update unit 114. Various modifications such as omitting some of these components (for example, a sensor information acquisition unit, a situation estimation unit, a correction unit, and an information update unit) or adding other components are possible.

  The sensor information acquisition unit 104 acquires sensor information from the sensor 150 (for example, a wearable sensor). Specifically, the sensor 150 is a user detection sensor such as an imaging sensor, a behavior sensor that measures user behavior (walking, conversation, meal, limb movement, emotional expression, sleep, etc.), and user status (fatigue, tension). At least one sensor that measures a user's environment (location, time, brightness, temperature, humidity, etc.) In addition, the sensor information acquisition unit 104 acquires sensor information from these sensors.

  Here, as a user detection sensor provided as the sensor 150, for example, an imaging sensor such as a CCD or a CMOS sensor can be used. An imaging sensor (image sensor) is an optical sensor that converts one-dimensional or two-dimensional optical information into a time-series electrical signal. By face detection (face image recognition) using this image sensor, recognition processing of a user such as a person identification can be realized. Further, it is possible to detect whether or not a user exists in the detection range, a user's movement existing in the detection range, and the like. Further, it is possible to detect a positional relationship such as the angle of the user's line of sight with respect to the information presentation unit 142 (display unit). Alternatively, it is possible to detect the user's visual state such as whether or not the user is gazing at the information presentation unit 142 (display unit). Alternatively, whether or not the user is approaching can also be detected.

  As the user detection sensor, a human sensor such as a pyroelectric sensor may be used. The pyroelectric sensor is a sensor that receives infrared rays generated by a person or the like, converts the infrared rays into heat, and converts the heat into electric charges by the pyroelectric effect of the element. By using this pyroelectric sensor, it is possible to detect whether there is a user (person) in the detection range (detection area), a user's movement in the detection range, and the like. Or as a user detection sensor, you may use distance sensors, such as an ultrasonic sensor, for example.

  The sensor may be the sensor device itself, or may be a sensor device including a control unit, a communication unit, and the like in addition to the sensor device. The sensor information may be sensor primary information obtained directly from the sensor, or sensor secondary information obtained by processing (information processing) the sensor primary information. Moreover, the detection method by a sensor may be an active detection method or a passive detection method. That is, the system side may detect a user by an active method like an imaging sensor such as a CCD, or a passive detection method such as detecting a user by a transmission signal from an RFID provided on the user's mobile phone or the like. The user may be detected.

  Moreover, as a behavior sensor for detecting a user's behavior, a GPS, a pedometer (registered trademark), an acceleration sensor, an altimeter, a microphone, an imaging sensor, or the like can be used. As the state sensor that detects the user's state, various known biological measurement sensors that can measure blood pressure, heart rate, body temperature, eye movement, blood glucose level, and the like can be used. As an environmental sensor for detecting the user's environment, a thermohygrometer, a barometer, a brightness sensor, a microphone, or the like can be used.

  The user recognition unit 106 performs user recognition processing. For example, the user authentication of the user is performed based on the sensor information acquired by the sensor information acquisition unit 104. User authentication of a user can be realized, for example, by face recognition processing using an image sensor. Alternatively, human authentication may be performed using a retina that is a capillary blood vessel pattern in the retina of an eye, or using an iris that is a radial pattern in a black eye.

  The situation estimation unit (situation identification unit) 108 performs processing for estimating (identifying) the situation of the user based on information including the sensor information acquired by the sensor information acquisition unit 104. Specifically, multiplication processing or addition processing of the acquired sensor information is performed to realize various calculation processing for sensor information filtering processing (selection processing) or analysis processing. And the situation identification process which is a process which estimates a user's present condition is performed. Alternatively, a situation prediction process that is a process for estimating the future situation of the user is performed.

  Note that the user situation estimated by the situation estimation unit 108 is at least one of the user's behavior, state, environment, and the like, for example. The estimation of the user's behavior is based on the information of the behavior sensor worn by the user, and the state of the user's stationary / walking / running / sitting / laying down / stepping up / down the stairs is determined, or sensors (external) This can be realized by determining the user's action / posture state using a camera or a home sensor), or determining the user's staying / moving state based on the position locus obtained by the position detection sensor. The user's state is a user's mental state or physical state. The estimation of the user's state can be realized by discriminating stress, excitement, tension, health condition, etc. based on the information of the biosensor worn by the user. The user environment includes user location information, time information, ambient environment information, and the like. The user's environment is estimated by using the position detection sensor to determine where the user is staying (current location), using the clock to obtain the year, month, date, day of the week, and time, and using the ambient environment sensor to determine the temperature, atmospheric pressure, This can be achieved by acquiring noise. In this case, since it is difficult to completely and accurately specify the user situation from the sensor information, the probability of situation estimation by the situation estimation unit 108 has a certain range.

  Information other than sensor information may be used for estimating the user situation. Specifically, the user situation is estimated using the user's schedule information (schedule data, schedule information) stored in the schedule information storage unit 126, or external information acquired through the communication unit 138 or the like. Also good. For example, the user's future schedule is estimated based on the schedule table input by the user, or an incidental schedule is estimated from the input schedule. Alternatively, based on external information such as information acquired from the web information or external database via the Internet (for example, today's weather / traffic information) or information acquired from other users (for example, contact information from other users). To estimate the user situation.

  If such schedule information or external information is used, the accuracy of situation estimation can be improved as compared with the case where the user situation is estimated using only sensor information. For example, by estimating the user's behavior by combining the sensor information and the schedule information, it is possible to estimate the user's behavior more reliably.

  The content selection unit 110 selects content to be presented to the user by the information presentation unit 142. For example, when the user is recognized by the user recognition unit 106, the content selection unit 110 is associated with each user situation of the recognized user based on the user recognition result and the user situation (for example, time, place, and state). The selection history information is read from the selection history information storage unit 124. Then, based on the read selection history information, content to be presented to the user is selected from a plurality of contents.

  Here, more specifically, the selection history information storage unit 124 corresponds to each of the first to Nth (N is an integer of 2 or more) user situations, and the first to first selections of content genres. N probability distribution information is stored in association with each other. That is, the first probability distribution information is stored in association with the first user situation, and the second probability distribution information is stored in association with the second user situation. The genre is a concept including a plurality of contents, but there may be a case where only one content exists or a corresponding content does not exist.

  Therefore, when the recognized user situation of the user is the Kth user situation among the first to Nth user situations (1 ≦ K ≦ N), the content selection unit 110 is the Kth user. The Kth probability distribution information associated with the situation is read from the selection history information storage unit 124. For example, the first probability distribution information is read out in the case of the first user situation, and the second probability distribution information is read out in the case of the second user situation. Then, the genre (category) is selected with the probability according to the read Kth probability distribution information, and the content corresponding to the selected genre is selected as the presented content. For example, in the Kth probability distribution information, the selection probability of the first genre is the probability P1, and the selection probability of the second genre is the probability P2. In this case, the first genre is selected with the probability P1, the content corresponding to the first genre is selected, the second genre is selected with the probability P2, and the content corresponding to the second genre is selected. select.

  The selection history information storage unit 124 stores first to Nth probability distribution information for each of a plurality of users. For example, first to Nth probability distribution information for the first user is stored corresponding to the first user, and the first to Nth probability distributions for the second user are stored corresponding to the second user. Store information. Then, the content selection unit 110 reads the first to Nth probability distribution information corresponding to the recognized user from the selection history information storage unit 124, and selects the presented content. For example, when the first user is recognized and the user situation is the Kth user situation, the Kth probability distribution information for the first user is read. When the second user is recognized and the user situation is the Kth user situation, the Kth probability distribution information for the second user is read out.

  Here, as the probability distribution information of the first to Nth probability distribution information, a probability distribution table in which the selection frequency (number of selections) of each genre is associated with each genre of a plurality of genres can be used. . For example, in the probability distribution table, when the selection frequency of the first genre by the user is SF1 and the selection frequency of the second genre is SF2, the selection frequency SF1 is associated with the first genre, The selection frequency SF2 is associated with the second genre.

  When the first to Nth time slots are set corresponding to the first to Nth user situations, the selection history information storage unit 124 stores each time slot of the first to Nth time slots. Are stored in association with each probability distribution information of the first to Nth probability distribution information. For example, the first probability distribution information is stored in association with the first time slot, and the second probability distribution information is stored in association with the second time slot.

  When the time corresponding to the user situation belongs to the Kth time slot, the content selection unit 110 reads the Kth probability distribution information associated with the Kth time slot and selects the presented content. become.

  The correcting unit 111 corrects probability distribution information (selection history information). For example, when the correction target is the Kth probability distribution information, the Kth probability distribution information is corrected based on at least one of the (K−1) th probability distribution information and the (K + 1) th probability distribution information. That is, the correction process is performed based on the (K−1) th and (K + 1) th probability distribution information corresponding to the (K−1) th and (K + 1) th user situations before and after the Kth user situation. And the content selection part 110 selects a genre with the probability according to the Kth probability distribution information after correction | amendment, and selects a presentation content.

  More specifically, the correction unit 111 performs weight correction on the Kth probability distribution information before correction based on at least one of the (K−1) th probability distribution information and the (K + 1) th probability distribution information. For example, with respect to the Kth probability distribution information before correction, the genre set by the K-1st probability distribution information and its selection probability information (selection frequency) can be set by a predetermined weighting factor, The genre set by the probability distribution information and the selection probability information (selection frequency) are set by a predetermined weighting coefficient.

  When the first to N-th time slots are set as the first to N-th user situations, the correction unit 111 corrects the first half period (a predetermined period including the start time) of the K-th time slot. Weighting correction is performed on the previous Kth probability distribution information based on the K-1st probability distribution information of the (K-1) th time slot. On the other hand, in the second half period (predetermined period including the end time) of the Kth time slot, the weighting correction based on the K + 1th probability distribution information of the (K + 1) th time slot is applied to the Kth probability distribution information before the correction. Do.

  The presentation control unit 112 performs control for presenting the selected content to the user by the information presentation unit 142. For example, when the information presentation unit 142 is a wearable display or digital photo frame, control is performed to display the selected content (content image) on the wearable display or digital photo frame.

  The information update unit 114 performs selection history information update processing. Specifically, when the information presenting unit 142 presents a plurality of contents with different genres to the user and determines that the user has performed a selection operation on the presented contents, the selection history information is updated. Do. For example, it is assumed that the selection history information storage unit 124 stores information in which the selection frequency of each genre is associated with each genre of a plurality of genres as selection history information (selection probability distribution information). Then, when it is determined that the user has performed a selection operation on the presented content, the information update unit 114 updates the selection frequency (number of selections) of the genre corresponding to the content on which the selection operation has been performed. . For example, the selection frequency of the genre is incremented. The presence or absence of a selection operation can be determined by the presence or absence of a user interface such as a touch panel, or the presence or absence of a selection operation can be determined by eye gaze detection or face orientation detection by an imaging camera or the like. Is possible.

  Next, the operation of this embodiment will be described with reference to the flowchart of FIG.

  First, a user is recognized by a user detection sensor such as an imaging sensor (step S1). For example, the user's face is imaged, collated with a user's face image registered in advance, and the user's personal identification is performed. Also, sensor information, schedule information, and external information from the behavior sensor, state sensor, and environment sensor are acquired (step S2). Based on the acquired information, the user's situation (TPOf) is estimated (step S3).

  Next, the presentation content is selected from a plurality of contents based on the user recognition result in step S1, the user situation estimated in step S3, and the content genre selection history information (step S4). . That is, the selection history information associated with each user situation of the recognized user is read, and the presentation content is selected. Then, the selected content is presented to the user by the information presenting unit (step S5). Further, the selection history information is updated based on the user's content selection operation (step S6). For example, the selection frequency of the genre of the content selected by the user is incremented and updated.

  By doing so, it becomes possible to select and present to the user appropriate content according to the user's recognition result and past selection history.

3. Time Slot Next, a content selection method when setting a plurality of time slots (first to Nth time slots) corresponding to a plurality of user situations (first to Nth user situations) will be described.

  For example, in FIG. 4, one day (24 hours) is divided into a plurality of time slots. For example, when the time slot interval is 1 hour, it is divided into 24 time slots. For each time slot, a selection probability distribution of the content genre (domestic news, politics / economics, overseas news, etc.) is set. Specifically, the selection frequency (number of gazes, number of clicks) of each genre is set as the selection probability distribution.

  For example, in the first time slot (for example, from 0:00 to 1 o'clock), content is presented to the user, and the user selects an operation (for example, a gaze operation or a click operation described later). To do. In this case, the selection frequency (number of selections) of the genre (category) of the selected content is incremented, and the probability distribution of the first time slot is updated. Similarly, when the content is presented to the user in the next second time slot (for example, 1 to 2) and the user performs an operation of selecting the content, the selected content is displayed. The genre selection frequency is incremented, and the probability distribution of the second time slot is updated. In this way, the probability distribution in each time slot is updated each time the user performs a content selection operation.

  If the time corresponding to the user status belongs to the first time slot, the probability distribution associated with the first time slot is read, and the genre is selected with the probability according to the probability distribution. Similarly, when the time corresponding to the user situation belongs to the second time slot, the probability distribution associated with the second time slot is read, and the genre is selected with the probability according to the probability distribution.

  For example, when the probability distribution of the “domestic news” genre is high in the probability distribution of the first time slot, the genre of “domestic news” is selected with high probability, and contents belonging to the selected genre are presented to the user. Will come to be. Similarly, in the probability distribution of the second time slot, when the selection probability of the “political / economic” genre is high, the “political / economic” genre is selected with a high probability, and contents belonging to the selected genre are displayed. It will be presented to the user.

  As described above, in this embodiment, the probability distribution is updated by the user's selection operation in each time slot, and the content presented by the user in each time slot is selected based on the probability distribution updated in this way. The Accordingly, it is possible to present content reflecting the user's selection history, and it is possible to realize an unprecedented type of content presentation.

  FIG. 5A shows an example of the probability distribution table. For example, the probability distribution table UA07 stores the probability distribution information of the time slot from 6:00 to 7:00 of the user UA. Specifically, the selection frequency (number of selections) = 30 is associated with the genre “Today's weather”, and the selection frequency (number of selections) = 35 is associated with the genre “news”. Similarly, the probability distribution table UB20 stores the probability distribution information of the time slot from 19:00 to 20:00 of the user UB. As described above, the probability distribution information of the present embodiment can be realized by a probability distribution table in which selection frequencies of each genre are associated with a plurality of genres.

  FIG. 5B shows an example of a user content table (content information database). For example, the user content table UAC stores content information of the user UA. Specifically, the URL (storage address) of the content is stored, and the genre to which the content belongs is stored in association therewith. For example, when a genre is selected based on the selection history and content belonging to the genre is presented, the URL of the content is acquired using the genre as an argument in the user content table of FIG. 5B, and the URL is accessed. Content.

4). Correction of Probability Distribution Information In this embodiment, the user can set the genre of content to be displayed by a digital photo frame or the like to be described later in each time slot of FIG. The user's content selection operation (gaze etc.) is recorded, and a selection frequency histogram is created for each time slot. The displayed content is determined by the probability of the created histogram.

  For example, FIG. 6 shows an example of a probability distribution which is a histogram created in this way. In this probability distribution, a genre selection frequency (number of selections) is set in association with each time slot.

  As shown in FIG. 6, depending on the genre assignment method set by the user, the content changes greatly at the time slot breaks. For example, the “list of today's attention brands” was displayed until 12:59, but at 13:00, only “recommended spots on the weekend” are suddenly displayed. In addition, although “news” is set to be displayed from 6:00 to 7:00, when the user gets up late and gets up at 7: 5, the “news” to be viewed cannot be viewed.

  Therefore, in this embodiment, a technique is adopted in which the probability distribution information of each time slot is corrected with the probability distribution information of the time slots before and after the time slot. For example, based on at least one of the (K-1) th probability distribution information of the (K-1) th time slot and the (K + 1) th probability distribution information of the (K + 1) th time slot, the Kth probability distribution information of the Kth time slot is obtained. to correct. Specifically, weighting correction based on at least one of the (K−1) th probability distribution information and the (K + 1) th probability distribution information is performed.

  For example, FIG. 7A shows the probability distribution information before correction, and FIG. 7B shows the probability distribution information after correction. In FIG. 7B, for the probability distribution information of the current time slot (Kth time slot), for example, from the probability distribution information of the preceding and succeeding time slots (K-1th and K + 1th time slots), respectively, Weighting correction for adding selection frequency with 1/2 weighting is performed.

  For example, before the correction shown in FIG. 7A, only the genre selection frequencies of “Today's weather” and “Today's weather information” are set for the current time slot.

  On the other hand, after the correction shown in FIG. 7B, the selection frequency of the “fresh photo” or “news” genre of the previous time slot is weighted to, for example, 1/2 of the current time slot. The weighting correction to be added in is performed. That is, for example, in the first half of the current time slot (Kth time slot), weighting correction for adding the selection frequency of the previous time slot (K-1th time slot) is performed.

  Further, in FIG. 7B, weighting correction is performed in which the frequency of selecting the genre of “regional news” or “today's weather forecast” in the next time slot is added to the current time slot by, for example, 1/2 weighting. Has been done. That is, for example, in the second half of the current time slot (Kth time slot), weighting correction is performed to add the selection frequency of the next time slot (K + 1th time slot).

  If such correction is performed, the contents set in the preceding and succeeding time slots are displayed in the current time slot, so that the displayed contents transition seamlessly at the timing when the time slot changes. . For example, even if the user is set to display “News” at 6:00 to 7:00, but when the user gets up late and gets up at 7: 5, the time slot from 7:00 to 8:00 “News” in the time slot from 6:00 to 7:00 will be displayed with a certain probability. Therefore, it is possible to display content that does not feel uncomfortable for the user.

  FIG. 8A and FIG. 8B show another example of the correction method of the present embodiment. In FIG. 8B, the current time slot is divided into three divided time slots TB1 to TB3. Then, the contribution from the previous time slot (K-1th time slot) is added to the divided time slot TB1 in the first half period, and the contribution from the next time slot (K + 1th time slot) is added to the second half period. To the divided time slot TB3. For the divided time slot TB2 in the middle period, the one before correction is applied as it is.

  Specifically, a weighting correction is performed in which the selection frequency of the “fresh photo” or “news” genre of the previous time slot is added to the divided time slot TB1 of the first half period, for example, with a weight of 1/2. In addition, a weighting correction is performed in which the selection frequency of the genre of “regional news” or “today's weather forecast” in the next time slot is added to the divided time slot TB3 in the second half period by, for example, 1/2 weighting.

  According to this correction method, even if the influence from the preceding and succeeding time slots is large in the divided time slot periods TB1 and TB3 in the first half period and the second half period, the user setting is performed in the divided time slot TB2 in the middle period. It will be possible to ensure that the content is displayed.

  As described above, in FIGS. 7A to 8B, in the first half period of the current time slot (Kth time slot), the previous time slot (first) is compared with the probability distribution information before correction. Weighting correction based on probability distribution information of (K-1 time slots) is performed. On the other hand, in the second half period, weighting correction based on the probability distribution information of the next time slot (K + 1th time slot) is performed on the probability distribution information before correction.

  Although the case where the weighting coefficient is 1/2 has been described in FIGS. 7A to 8B, the weighting coefficient is not limited to 1/2 and can be specified as an arbitrary coefficient. In FIG. 8B, the original time slot is divided into three equal parts. For example, the original time slot “60 minutes” is divided into three parts “5 minutes + 50 minutes + 5 minutes”, etc. It is possible to divide at arbitrary intervals. Further, the correction processing may be realized using, for example, a sigmoid function.

  Further, in FIGS. 7A to 8B, the case where the weighting correction is performed from both of the preceding and succeeding time slots has been described. However, only the weighting correction from the previous time slot is performed, or one time after. Only the weighting correction from the time slot may be performed.

  Further, the corrected probability distribution information may be stored (overwritten) in the selection history information storage unit 124, or may not be stored. For example, when saving, the probability distribution (selection frequency) of the current time slot before correction in FIG. 7A is replaced with the corrected probability distribution as shown in FIG. 7B. On the other hand, if not stored, the corrected result is discarded and always corrected in real time.

  Further, in FIGS. 7A to 8B, the case where the probability distribution information set for each time slot is corrected has been described, but the description has been made with reference to FIGS. 1A and 1B. You may make it correct | amend with respect to the probability distribution information set with respect to each user condition.

  For example, assume that the (K−1) th, Kth, and (K + 1) th probability distribution information is set for the (K−1) th, Kth, and (K + 1) th user situations. In this case, based on at least one of the (K-1) th probability distribution information of the (K-1) th user situation and the (K + 1) th probability distribution information of the (K + 1) th user situation, the Kth probability distribution of the Kth user situation. Correct the information. More specifically, weight correction based on at least one of the (K−1) th probability distribution information and the (K + 1) th probability distribution information is performed on the Kth probability distribution information before correction. Then, the genre is selected with the probability according to the corrected Kth probability distribution information, and the content is displayed.

  For example, it is assumed that the K-1 user situation is “commuting” and the Kth user situation is “working”. In this case, for example, in the first half period immediately after the start of work, the content displayed during commuting is displayed with a certain weight. When the K + 1st user status is “going home”, the content to be displayed while returning home is displayed with a certain weighting probability in the second half period immediately before the end of work. In this way, it is possible to prevent a situation where the displayed content suddenly changes and the user feels uncomfortable. Similarly, when the K-1th user situation is “relaxed” and the Kth user situation is “tensed”, the relaxed state is set in the first half period immediately after it is determined that the user is in a tensioned state. Are displayed with a certain weighting probability. In this way, the displayed content can be naturally switched from the relaxed content to the tensioned content.

  For example, when the user situation is estimated by a sensor, it is difficult to accurately determine the switching of the user situation because the accuracy of the sensor is not perfect. For example, when a user enters the company, it is difficult to accurately determine at which timing the switch is from “commuting” to “working”.

  In this regard, according to the method of the present embodiment, at the time of transition from “commuting” to “working”, the displayed content is seamlessly switched from the content for commuting to the content for work. Therefore, it is possible to cope with the case where the timing for switching from “commuting” to “working” cannot be accurately determined due to the accuracy of the sensor or the like.

5). Digital Photo Frame Next, a case where the method of the present embodiment is applied to a digital photo frame (image display device in a broad sense) will be described. The image display device to which the present embodiment is applied is not limited to a digital photo frame, and can be applied to various image display devices such as a wearable display and a display of a portable information terminal. As a wearable display, for example, a display of a see-through viewer mounted near the user's eyes can be used.

  FIG. 9A shows an example of a digital photo frame 300 (digital photo player, image reproduction apparatus). FIG. 9A illustrates an example of a so-called photo stand type digital photo frame. The digital photo frame 300 is installed by a user in an arbitrary place such as a house. Then, reproduction processing (image reproduction, sound reproduction) of content information such as digital image data and sound data is executed. The digital photo frame 300 can automatically play back content information (media information) such as an image without an explicit playback instruction from the user, for example. For example, a photo slideshow is automatically executed, or an image is automatically reproduced.

  FIG. 9A shows an example of a photo stand type digital photo frame. However, as shown in FIG. As this wall-mounted digital photo frame, for example, electronic paper realized by an electrophoretic display or the like can be used. The digital photo frame 300 may be provided with a content information reproduction instruction button or the like, or a reproduction instruction may be performed using a remote controller.

  The digital photo frame 300 can include a memory card interface such as an SD card, for example. Alternatively, a wireless communication interface such as a wireless LAN or Bluetooth, or a wired communication interface such as USB can be provided. For example, when a user saves content information in a memory card and attaches it to the memory card interface of the digital photo frame 300, the digital photo frame 300 executes automatic reproduction (slideshow or the like) of the content information saved in the memory card. . Alternatively, when the digital photo frame 300 receives content information from the outside through wireless communication or wired communication, the digital photo frame 300 executes a reproduction process (automatic reproduction process) of the content information. For example, when a portable electronic device such as a digital camera or a mobile phone possessed by a user has a wireless function such as Bluetooth, content information is transferred from the portable electronic device to the digital photo frame 300 using this wireless function. Forward. Then, the digital photo frame 300 executes a reproduction process of the transferred content information.

  FIG. 10 shows a configuration example of a digital photo frame 300 and a server 200 (communication server in a narrow sense, an information processing system in a broad sense) connected to the digital photo frame 300 for communication. The digital photo frame 300 includes a processing unit 302, a storage unit 320, a communication unit 338, a display unit 340, a sensor 350, and an operation unit 360. The server 200 includes a processing unit 202, a storage unit 220, and a communication unit 238. Various modifications may be made such as omitting some of these components or adding other components.

  The processing unit 302 of the digital photo frame 300 performs various control processes and arithmetic processes. For example, each part of the digital photo frame 300 is controlled or overall control is performed. The function of the processing unit 302 can be realized by hardware such as various processors (CPU and the like), ASIC (gate array and the like), a program stored in the information storage medium 330, and the like.

  The storage unit 320 serves as a work area for the processing unit 302, the communication unit 338, and the like, and its functions can be realized by a memory such as a RAM, an HDD (hard disk drive), or the like. The storage unit 320 includes an authentication information storage unit 322 that stores user authentication information.

  The information storage medium 330 (a computer-readable medium) stores programs, data, and the like, and its function can be realized by a memory card, an optical disk, or the like. The processing unit 302 performs various processes of the present embodiment based on a program (data) stored in the information storage medium 330.

  The communication unit 338 exchanges information with an external device (for example, a server or a portable electronic device) by wireless or wired communication, and the function thereof is a hardware such as a communication ASIC or a communication processor. Hardware and communication firmware.

  The display unit 340 is for displaying an image as content information, and can be realized by, for example, a liquid crystal display, a display using a light emitting element such as an organic EL, an electrophoretic display, or the like.

  The sensor 350 (user detection sensor, human body detection sensor) is a sensor for detecting a user (user authentication, user state, etc.) and outputs detection information based on the detection result. In the present embodiment, the sensor 350 is used as a sensor for person authentication. Alternatively, as a sensor for determining the positional relationship between the user and the display unit 340 (display screen, digital photo frame), the user's visual status with respect to the display unit 340, whether the user is within the detection range, or the like. It may be used. As the sensor 350, an image sensor such as a CCD or CMOS sensor, or a human sensor such as a pyroelectric sensor can be used.

  The sensor 350 may be directly attached to the digital photo frame 300, or a home sensor or the like may be used as the sensor 350. When the sensor 350 is attached to the digital photo frame 300, the sensor 350 can be attached to, for example, a frame portion of the digital photo frame 300 as shown in FIG. Alternatively, the sensor 350 and the digital photo frame 300 may be connected using a wired cable or the like.

  The operation unit 360 is used by the user to input various types of information, and can be realized by, for example, an operation button or a remote control device. The user can use this operation unit 360 to perform user registration and registration of playback content (favorite images) desired by the user. For example, the user can input user registration information using the operation unit 360.

  The processing unit 302 includes a sensor information acquisition unit 304, a user recognition unit 306, a user state determination unit 308, and a display control unit 310. Various modifications such as omission of some of these components and addition of other components are possible.

  The sensor information acquisition unit 304 acquires sensor information from the sensor 350. The user recognition unit 306 performs user recognition processing. For example, a user's face image is picked up by the image pickup sensor which is the sensor 350, and image pickup data (feature point data) or the like is stored in the authentication information storage unit 322 as the user's authentication information. At the time of user recognition, person authentication is performed based on the stored user authentication information.

  The user state determination unit 308 determines the user state based on the sensor information acquired by the sensor information acquisition unit 304. For example, based on the acquired sensor information, at least one of the positional relationship between the user (person) and the display unit 340, the user's visual status with respect to the display unit 340, and whether or not the user exists within the detection range. to decide.

  Here, the positional relationship is a distance (distance information, distance parameter) between the user and the display unit 340, a user's line-of-sight direction with respect to the display unit 340, or the like.

  The visual recognition state is a state of the user's visual field range, a gaze state, and the like. Specifically, whether the display unit 340 is in the user's visual field range (view volume) or whether the user is watching the display unit 340. Or not. For example, the gaze state determination unit 309 determines whether or not the user is gazing at the display unit 340.

  For example, it is assumed that an imaging sensor for imaging the user is provided as the sensor 350. In this case, the user state determination unit 308 (positional relationship determination unit) detects the user's face area (rectangular frame area) based on the imaging information from the imaging sensor. Based on the detected size of the face area, the distance between the user and the display unit 340 is determined (estimated). In addition, the user state determination unit 308 sets a measurement area that includes the detected face area and is larger than the face area. That is, a measurement area that overlaps the face area is set. Then, the time during which the face area exists in the measurement area is measured, and based on the measured time, it is determined whether or not the user is gazing at the display unit 340. For example, when the presence time in the measurement area is a predetermined time or more, it is determined that the user is gazing.

  The display control unit 310 performs display control of the display unit 340. Specifically, control is performed to display an image of the presentation content selected from the plurality of contents on the display unit 340. For example, when the presented content is selected by the server 200 and information on the content is received via the communication unit 338, control for displaying a content image on the display unit 340 is performed based on the received content information.

  In this embodiment, as described with reference to FIGS. 1A and 1B, the selection history information of the genre of the content selected by the user includes at least the time, the place where the user stays, and the state of the user. One user status (TPOF) is associated. When the user is recognized by the user recognition unit 306 and the presentation content is selected based on the selection history information associated with the user status of the recognized user, the display control unit 310 displays an image of the selected presentation content. Control to display on the display unit 340 is performed. That is, control is performed to display an image of the content selected based on the user recognition result, the user situation, and the selection history information.

  In addition, when the user is not recognized by the user recognition unit 306, the display control unit 310 performs control to display an image of content randomly selected from a plurality of contents on the display unit 340. For example, slide display or the like of content randomly selected from a plurality of contents is performed.

  Further, the display control unit 310 determines that the user recognized by the user recognition unit 306 has not performed a selection operation (for example, a gaze operation) on the presented content (for example, the user has been recognized). If it is determined that the user is not gazing), control is performed to display an image of the content selected based on the user status of the recognized user and the selection history information. On the other hand, when it is determined that the user recognized by the user recognition unit has performed a selection operation on the presented content (for example, it is determined that the user is recognized and the user is gazing at the display unit 340). In the case of the user), control is performed to display an image of the content belonging to the genre of the content presented at the time of the user's selection operation (for example, during gaze). When it is determined that the user has performed a selection operation on the content image displayed on the display unit, the content genre selection frequency (number of selections) displayed during the user selection operation is updated. (Increment).

  The processing unit 202 of the server 200 performs various processes such as a management process, and can be realized by a processor such as a CPU or an ASIC. The storage unit 220 is a work area for the processing unit 202 and the communication unit 238, and can be realized by, for example, a RAM or an HDD. The communication unit 238 is for performing wired or wireless communication with the digital photo frame 300 or the external server 600, and can be realized by a communication ASIC or a communication processor.

  The processing unit 202 includes a content selection unit 204 and an information update unit 206. The content selection unit 204 reads the selection history information associated with each user situation of the recognized user from the selection history information storage unit 226 based on the user recognition result and the user situation, and reads the read selection history information. The presentation content is selected based on. The information update unit 206 performs an update process of selection history information when it is determined that the user has performed a selection operation on the presented content. The storage unit 220 includes a user information storage unit 222 that stores various information about the user, a content information storage unit 224 that stores content information, and a selection history information storage unit 226 that stores selection history information. FIG. 10 shows an example in which content selection and selection history information are updated on the server side, but these may be performed on the digital photo frame side.

  In FIG. 10, the digital photo frame 300 and the server 200 are communicatively connected via a network such as a wireless LAN. When the digital photo frame 300 recognizes the user, the digital photo frame 300 transmits the user recognition result to the server 200 via the network. Then, the server 200 reads selection history information associated with the user status of the user from the selection history information storage unit 226 based on the received user recognition result. The presentation content is selected based on the read selection history information, and information on the selected presentation content is transmitted to the digital photo frame 300 via the network. Then, the digital photo frame 300 displays an image of the presentation content on the display unit 340 based on the received presentation content information.

  The user registers content in the content information storage unit 224 of the server 200 using, for example, an upload screen as shown in FIG. Specifically, the user inputs a user name and a password. Then, using a client program such as a Web browser, the content such as the URL of an image, video, or other homepage that the user has is associated with the user name and password, and the upload screen in FIG. 11A is used. Register in the content information storage unit 224. In this case, for example, on the user registration screen, a user's face image or the like is captured using an imaging sensor or the like, and the user name and password are associated with the captured face image or the like and registered in advance as user registration information. When the user recognizing unit 306 of the digital photo frame 300 (client) recognizes the user based on the face image captured by the image sensor, the server 200 uses the user name and password associated with the face image as arguments. Send a request to. Upon receiving this request, the content selection unit 204 of the server 200 selects the content registered in FIG. 11A as the content to be presented to the user based on the user name and password included in the request. become.

  FIG. 11B shows an example of the data structure of the user information storage unit 222 (user database). The user information storage unit 222 holds a user name (character string), a password (character string), and a genre (character string) transmitted in the state of “seeing” immediately before.

  FIG. 12 shows a state transition diagram for explaining the operation of the system of FIG. As shown in FIG. 12, when it is determined that the user is not recognized and the user is non-existent (none), the content randomly selected from the plurality of contents is displayed (state ST1).

  When the user is recognized, the content selected by the user situation and the selection history information is displayed (state ST2). That is, in the state where the user exists but the display unit 340 is not watched (seeing), the content uploaded by the user in FIG. 11A is displayed in FIG. 1A, FIG. 1B, or FIG. Display using the method described.

  When it is determined that the user is performing the selection operation, specifically, when it is determined that the user is gazing at the display unit 340 (looking), the user is presented during the selection operation (at the time of gazing). The content belonging to the content genre is displayed (state ST3). For example, a slide show of the genre that was watched is created and displayed.

  In FIG. 12, the transition between the states ST1 and ST2, the transition between the states ST2 and ST3, and the transition from the state ST3 to ST1 are possible, but the transition from the state ST1 to ST3 is not possible. ing.

  Next, the operation of the present embodiment will be described with reference to the flowcharts of FIGS. FIG. 13 is a flowchart for explaining the operation of the digital photo frame 300.

  When the digital photo frame 300 is powered on or the like, it is determined whether or not a user is detected by a sensor (step S11). If detected, the user is identified by the authentication information stored in the authentication information storage unit 322. Are collated (step S12). When the detected user is recognized as a registered user (step S13), it is determined whether or not the user is gazing at the display unit 340 (step S16). On the other hand, if the user is not recognized, a request is transmitted to the server 200 in a user non-existence (none) state ST1 in FIG. 12 (step S14). Then, the current user state is held, and the content sent from the server 200 is displayed on the display unit 340 (step S15).

  If it is determined in step S16 that the user is gazing at the display unit 340, the previous user state is determined (step S17). If the previous user state is the user recognition state ST2 (seeing) in FIG. 12, a request is transmitted to the server 200 with the user name, password, and gaze flag = Yes as arguments (step S18). If the immediately preceding state is the user non-existing state ST1 (none) in FIG. 12, a request is transmitted to the server 200 with the user name, password, and gaze flag = No as arguments (step S19). Then, the current state is held, and the content sent from the server 200 is displayed on the display unit 340. On the other hand, if the immediately preceding state is the user attention state ST3 (locating) in FIG. 12, the current state is maintained and the content sent from the server 200 is displayed on the display unit 340.

  FIG. 14 is a flowchart for explaining the operation of the server 200. First, it is determined whether a request has been received from the digital photo frame 300 (step S31). That is, it is determined whether or not the requests in steps S14, S18, and S19 in FIG. 13 have been received. When the request is received, the user name and password that are arguments of the request are confirmed (step S32). When it is recognized that the user is a registered user, it is determined whether or not the user is gazing at the display unit 340 of the digital photo frame 300 based on the argument of the request (steps S33 and S34). For example, if the gaze flag = Yes in step S18 of FIG. 13, it is determined that the user is gazing, and if the gaze flag = No in step S19, it is determined that the user is not gazing. Is done.

  If it is determined that the user is gazing, the selection frequency (number of selections) of the genre of the selected content is incremented by, for example, 1 (step S35). Thereby, the update of the probability distribution information described with reference to FIG. 4 and the like is executed. Next, a slide show of a genre stored in the user information storage unit 222 is created, and contents are transmitted to the digital photo frame 300 (steps S36 and S37).

  On the other hand, if the user is not recognized in step S33, it is considered that the user is absent. Therefore, the content is randomly selected from the content information storage unit 224, and the selected content is transmitted to the digital photo frame 300. (Steps S38 and S37).

  If it is determined in step S34 that the user is not gazing, content is selected based on the user status (time) and selection history information (step S39). Specifically, as described with reference to FIG. 4 and the like, the probability distribution information associated with the time slot to which the time that is the user situation belongs is read, and the genre is selected with the probability according to the read probability distribution information. . Then, the genre of the selected content is stored in the user information storage unit 222, and the content is transmitted to the digital photo frame 300 (steps S40 and S37).

  As described above, according to the present embodiment, as shown in steps S13 and S14 of FIG. 13, when the user is not recognized and the request is transmitted to the server 200 in the absence of the user (none), the step of FIG. As shown in S33 and S38, the content is selected at random. Then, the selected content is transmitted to the digital photo frame 300 and displayed on the display unit 340. Thereby, in the state ST1 of FIG. 12, the randomly selected content is displayed.

  Also, as shown in steps S16 and S19 in FIG. 13, if the user is recognized, but it is determined that the user is not gazing at the display unit 340, and the request is transmitted to the server 200 with the gazing flag = No. As shown in steps S34 and S39 of FIG. 14, content is selected based on the user situation and selection history information. Although the user is watching as shown in steps S16, S17, and S19 in FIG. 13, the same applies to the case where the previous user state is the absence of the user. Then, the selected content is transmitted to the digital photo frame 300 and displayed on the display unit 340. Accordingly, when the user stays in the state ST2 in FIG. 12 or when the state ST1 is shifted to ST2, the content selected based on the user situation and the selection history information is displayed (seeing).

  Further, as shown in steps S16, S17, and S18 of FIG. 13, it is determined that the user is gazing at the display unit 340, and the request is transmitted to the server 200 with the gazing flag = Yes. In this case, as shown in steps S35 and S36 in FIG. 14, the selection frequency of the genre of the selected content is incremented, and a slide show of the genre stored in the user information storage unit 224 is created in step S40. Then, the slide show is displayed on the display unit 340. As a result, when the state is shifted from the state ST2 to ST3 in FIG. 12, the selection frequency is incremented and a slide show of the content genre displayed at the time of gaze is displayed.

  That is, in the present embodiment, as shown in steps S33, S34, and S39 in FIG. 14, when it is determined that the user has been recognized but not watched, the selection history information as described in FIG. 4 is used. Content is selected. Then, as shown in step S40, the genre of the content selected at this time is stored as the genre of the content selected immediately before. Then, when the content is presented and it is determined in step S34 that the user is gazing at the content, the selection frequency of the immediately preceding content genre stored in step S40 is incremented as shown in step S35. Is done. Accordingly, it is possible to appropriately realize the display of the content based on the selection history information and the update of the selection frequency when the content is watched.

  Further, as shown in steps S16, S17, and S20 of FIG. 13, when it is determined that the user is gazing at the display unit 340, and the previous user state is the gazing state, the current user state is retained. The content sent from the server 200 is displayed. Thus, when the state stays in the state ST3 in FIG. 12, the slide show of the content genre displayed at the time of gaze is continuously displayed.

  Although the present embodiment has been described in detail as described above, it will be easily understood by those skilled in the art that many modifications can be made without departing from the novel matters and effects of the present invention. Accordingly, all such modifications are intended to be included in the scope of the present invention. For example, in the specification or drawings, terms (servers, digital photo frames, etc.) described together with different terms (information processing systems, image display devices, etc.) in a broader sense or the same meaning at least once are used anywhere in the specification or drawings. Can also be replaced by the different terms. In addition, the configuration and operation of the information processing system and the image display device, the content selection method, the selection history information storage / update method, and the like are not limited to those described in the present embodiment, and various modifications can be made. is there.

102 processing unit, 104 sensor information acquisition unit, 106 user recognition unit,
108 situation estimation unit, 110 content selection unit, 111 correction unit,
112 presentation control unit, 114 information update unit, 120 storage unit,
122 content information storage unit, 124 selection history information storage unit,
126 schedule information storage unit, 130 information storage medium, 138 communication unit,
142 information presentation unit, 150 sensor, 200 server, 202 processing unit,
204 content selection unit, 206 information update unit, 220 storage unit,
222 user information storage unit, 224 content information storage unit,
226 selection history information storage unit, 238 communication unit, 300 digital photo frame,
302 processing unit, 304 sensor information acquisition unit, 306 user recognition unit,
308 user state determination unit, 309 gaze state determination unit, 310 display control unit,
320 storage unit, 322 authentication information storage unit, 330 information storage medium, 338 communication unit,
340 display unit, 350 sensor, 360 operation unit

Claims (25)

A user recognition unit for recognizing a user;
A selection history information storage unit that stores selection history information of a genre of content selected by the user in association with a user situation that is at least one of time, a place where the user stays, and a state of the user;
When the user is recognized by the user recognition unit, the selection history information associated with each user status of the recognized user is read from the selection history information storage unit based on the user recognition result and the user status. A content selection unit that selects content to be presented to the user from a plurality of content based on the read selection history information;
An information processing system comprising: In claim 1,
The selection history information storage unit
For each user situation of the first to Nth user situations, each probability distribution information of the first to Nth probability distribution information for selecting a genre is stored in association with each other.
The content selection unit
If the recognized user situation is the Kth user situation among the first to Nth user situations (1 ≦ K ≦ N), the user situation associated with the Kth user situation K probability distribution information is read from the selection history information storage unit, a genre is selected with a probability according to the read Kth probability distribution information, and content corresponding to the selected genre is used as the presentation content. An information processing system characterized by selecting. In claim 2,
The selection history information storage unit
Storing the first to Nth probability distribution information for each of a plurality of users;
The content selection unit
An information processing system, wherein the first to Nth probability distribution information corresponding to a recognized user is read from the selection history information storage unit and the presented content is selected. In claim 2 or 3,
Each probability distribution information of the first to Nth probability distribution information is a probability distribution table in which a selection frequency of each genre is associated with each genre of a plurality of genres. In any of claims 2 to 4,
A correction unit that corrects the Kth probability distribution information based on at least one of the K-1th probability distribution information and the K + 1th probability distribution information;
The content selection unit
An information processing system, wherein a genre is selected with a probability according to the corrected Kth probability distribution information, and a presentation content is selected. In claim 5,
The correction unit is
An information processing system, wherein weight correction based on at least one of the (K-1) th probability distribution information and the (K + 1) th probability distribution information is performed on the Kth probability distribution information before correction. In any one of Claims 2 thru | or 6.
First to Nth time slots are set corresponding to the first to Nth user situations,
The selection history information storage unit
Storing each probability distribution information of the first to Nth probability distribution information in association with each time slot of the first to Nth time slots;
The content selection unit
If the time corresponding to the user status belongs to the Kth time slot of the first to Nth time slots, the Kth probability distribution information associated with the Kth time slot is used as the selection history information. An information processing system that reads from a storage unit and selects the presented content. In claim 7,
A correction unit that corrects the Kth probability distribution information based on at least one of the K-1th probability distribution information and the K + 1th probability distribution information;
The correction unit is
In the first half period of the Kth time slot, weight correction is performed on the Kth probability distribution information before correction based on the K-1th probability distribution information of the K-1 time slot,
In the second half period of the Kth time slot, weight correction is performed on the Kth probability distribution information before correction based on the K + 1th probability distribution information of the K + 1 time slot. Processing system. In any one of Claims 1 thru | or 8.
An information update unit that performs an update process of the selection history information stored in the selection history information storage unit,
The information update unit
An information processing system, wherein a plurality of contents having different genres are presented to a user, and the selection history information is updated when it is determined that the user has performed a selection operation on the presented contents. . In claim 9,
The selection history information storage unit
Information related to the selection frequency of each genre for each genre of a plurality of genres is stored as the selection history information,
The information update unit
An information processing system that updates the selection frequency of a genre corresponding to a content for which a selection operation has been performed when it is determined that the user has performed a selection operation on the presented content. In any one of Claims 1 thru | or 10.
The content selection unit
An information processing system, wherein when the user is not recognized by the user recognition unit, the presented content is selected at random from a plurality of contents. In any one of Claims 1 thru | or 11,
The content selection unit
When it is determined that the user recognized by the user recognition unit is not performing a selection operation on the presented content, based on the user status of the recognized user and the selection history information, An information processing system that selects presentation content. In claim 12,
The content selection unit
When it is determined that the user recognized by the user recognition unit has performed a selection operation on the presented content, the content belonging to the genre of the content presented at the time of the user selection operation is displayed. An information processing system characterized by being selected as content. In claim 13,
The content selection unit
An image display device characterized in that, when it is determined that a user is gazing at a display unit on which a content image is displayed, the user determines that the content is being selected. In any of claims 12 to 14,
An information update unit that performs an update process of the selection history information stored in the selection history information storage unit,
The information update unit
An information processing system that performs an update process of the selection history information when it is determined that a user has performed a selection operation on the presented content. In any one of Claims 1 thru | or 15,
A user situation in which a user situation is estimated based on information including sensor information from at least one of a behavior sensor that measures a user's action, a state sensor that measures a user's state, and an environment sensor that measures a user's environment An information processing system including an estimation unit. A display for displaying an image;
A user recognition unit for recognizing a user;
A display control unit that performs control to display an image of content selected from a plurality of contents on the display unit,
The selection history information of the genre of the content selected by the user is associated with a user situation that is at least one of time, a place where the user stays, and the user's state,
The display control unit
When a user is recognized by the user recognition unit and content is selected based on the selection history information associated with the user status of the recognized user, an image of the selected content is displayed on the display unit. An image display device characterized by performing control. In claim 17,
The display control unit
When the user is not recognized by the user recognition unit, an image display device is provided that performs control to display an image of content randomly selected from a plurality of contents on the display unit. In claim 17 or 18,
The display control unit
When it is determined that the user recognized by the user recognition unit has not performed a selection operation on the presented content, the user is selected based on the user status of the recognized user and the selection history information. An image display apparatus that controls to display an image of a content on the display unit. In claim 19,
The display control unit
When it is determined that the user recognized by the user recognition unit has performed a selection operation on the presented content, an image of content belonging to the genre of the content presented at the time of the user's selection operation is An image display device that performs control of display on the display unit. In claim 20,
A gaze state determination unit that determines whether the user is gazing at the display unit;
The display control unit
When it is determined that the user is gazing at the display unit, an image of content belonging to the genre of the content displayed when the user is gazing is controlled to be displayed on the display unit Display device. A device according to any one of claims 17 to 21.
The selection history information is information in which the selection frequency of each genre is associated with each genre of a plurality of genres,
When it is determined that the user has performed a selection operation on the image of the content displayed on the display unit, the selection frequency of the content genre displayed at the time of the user's selection operation is updated. An image display device. A user recognition unit for recognizing a user;
A selection history information storage unit that stores selection history information of a genre of content selected by the user in association with a user situation that is at least one of time, a place where the user stays, and a state of the user;
When the user is recognized by the user recognition unit, the selection history information associated with each user status of the recognized user is read from the selection history information storage unit based on the user recognition result and the user status. As a content selection unit that selects content to be presented to the user from among a plurality of content based on the read selection history information,
A program characterized by causing a computer to function. A user recognition unit for recognizing a user;
As a display control unit that performs control to display an image of content selected from a plurality of contents on the display unit,
Make the computer work,
The selection history information of the genre of the content selected by the user is associated with a user situation that is at least one of time, a place where the user stays, and the user's state,
The display control unit
When a user is recognized by the user recognition unit and content is selected based on the selection history information associated with the user status of the recognized user, an image of the selected content is displayed on the display unit. A program characterized by performing control.   A computer-readable information storage medium, wherein the program according to claim 23 or 24 is stored.

Images