JP2011216031A - Content retrieval control device, content reproducing device, integrated circuit, content retrieval control method, content retrieval control program and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To normally retrieve content related to an object, even when a recognition state of the object is unstable.SOLUTION: A determination part 308 determines that the object exists in the vicinity of the content retrieval control device 304, there is the possibility that the object exists in the vicinity thereof, or the object does not exist in the vicinity thereof each time estimation information is acquired. When it is determined that the object exists in the vicinity of the content retrieval control unit 304, an object identifier for specifying the object determined as to exist is stored in a memory 310 by the determination part 308. When it is determined that the object specified by the stored object identifier does not exist after the object identifier is stored, the determination part 308 deletes the stored object identifier. A retrieval instruction part 309 transmits the object identifier to a content retrieving part 305 in a period in which the object identifier is stored.

Description

  The present invention relates to a content search control device, a content playback device, an integrated circuit, a content search control method, a content search control program, and a recording medium for realizing a search for content related to a recognition target.

  As a conventional content reproduction device, there is a device that captures and recognizes a user's face in front of the content reproduction device with a camera and automatically reproduces content related to the recognized user (for example, Patent Documents). 1). Here, the contents are video, audio and the like.

  FIG. 20 is a block diagram showing a characteristic functional configuration of a conventional content reproduction apparatus described in Patent Document 1. In FIG.

  In the content reproduction apparatus 400, the photographing unit 401 acquires an image by photographing a subject at a predetermined cycle, and transmits the image to the face detecting unit 402. The face detection unit 402 performs face presence / absence detection processing from the received image. When a face is detected, the face detection unit 402 calculates a facial feature value and transmits the facial feature value to the matching unit 403.

  The collation unit 403 collates the received face feature quantity with a pre-registered face feature quantity database. When the collation unit 403 determines that the face is the face of a specific user as a result of the collation, the collation unit 403 transmits a user identifier for identifying the user to the content search unit 405. That is, recognition processing for recognizing the user is performed by the face detection unit 402 and the collation unit 403.

  The content search unit 405 searches the content storage unit 406 for content registered in association with the user based on the received user identifier, sets the search result as a playback file list, and transmits the search result list to the playback unit 407. The playback unit 407 reads the content from the content storage unit 406 based on the received playback file list and plays it back. As a result, content related to the user can be reproduced without a troublesome search operation.

JP 2009-171176 A

  However, the recognition state of the object as a user may become unstable due to, for example, a change in the surrounding environment of the object. The change in the surrounding environment is, for example, a change in lighting conditions. When the recognition state of the object becomes unstable, it is recognized as an object different from the intended object. In this case, the conventional content reproduction apparatus has a problem that content not related to the object as the user is searched.

  The present invention has been made to solve the above-mentioned problems, and its purpose is to realize that content related to an object can be normally searched even when the recognition state of the object is unstable. It is to provide a content search control device and the like that can be enabled.

  In order to solve the above-described problem, a content search control device according to an aspect of the present invention provides feature data indicating features of an object obtained in recognition processing for recognizing the object and registered objects registered in advance. Evaluation information indicating an evaluation value that is a degree of similarity with feature data indicating a feature and an object identifier that identifies the object is sequentially acquired. The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier, and the content search control device receives the evaluation information every time the evaluation information is acquired. A determination unit that determines whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, and may or may not exist; a storage unit; The determination unit further specifies an object determined to exist when it is determined that the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device Store the object identifier in the storage unit The determination unit further determines the stored object identifier when it is determined that there is no object specified by the stored object identifier after the object identifier is stored in the storage unit. If it is determined that the object specified by the stored object identifier exists or may exist, the stored object identifier is continuously stored in the storage unit, The content search control device further transmits the stored object identifier to the content search device during a period in which the object identifier is stored in the storage unit, and an object identifier other than the stored object identifier. Is not transmitted to the content search device Provided with an indicator.

  That is, each time the evaluation information is acquired, the determination unit determines whether the object exists in the vicinity of the content search control device, may exist, or does not exist. When it is determined that an object exists in the vicinity of the content search control device, the determination unit stores an object identifier that identifies the object determined to exist in the storage unit. When it is determined that the object specified by the stored object identifier does not exist after the object identifier is stored, the determination unit deletes the stored object identifier. The search instruction unit transmits the object identifier to the content search device during a period in which the object identifier is stored.

  Thereby, when there is a possibility that the object exists in the vicinity of the content search control device, the object identifier is continuously stored in the storage unit. Therefore, for example, even when the recognition state of the object is unstable due to a change in the surrounding environment of the object, the object identifier for the search instruction unit to transmit to the content search device continues to be stored in the storage unit. Note that the content search control device searches for content related to the object specified by the object identifier by receiving the object identifier.

  As a result, even when the recognition state of the object is unstable, the content related to the object can be normally searched.

  Preferably, when the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is The determination unit determines that the content search control device exists in the vicinity, and the determination unit indicates, when the object identifier is stored in the storage unit, newly acquired evaluation information indicating the stored object identifier If the evaluation value is less than the first threshold value and greater than the second threshold value less than the first threshold value, the object specified by the stored object identifier exists in the vicinity of the content search control device. When the object identifier is stored in the storage unit, the determination unit newly determines that there is a possibility. When the obtained evaluation value indicated by the evaluation information indicating the stored object identifier is equal to or less than the second threshold, the object specified by the stored object identifier is in the vicinity of the content search control device It is determined that it does not exist.

  Preferably, when the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is It is determined that it exists in the vicinity of the content search control device.

  Preferably, in the case where an object identifier is stored in the storage unit, the determination unit further sets a weighting coefficient associated with the stored object identifier to a first coefficient value, and the weighting coefficient Is a coefficient for determining whether or not to delete the object identifier stored in the storage unit, and the determination unit further stores the object identifier during a period in which the object identifier is stored in the storage unit. Each time evaluation information indicating an object identifier other than the object identifier being acquired is acquired, the weighting factor is decreased by a predetermined value, and the determination unit further includes a first coefficient value less than the first coefficient value. When the value is equal to or less than 2 coefficient value, the object specified by the stored object identifier is in the vicinity of the content search control device. It determines not to standing.

  Preferably, when the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is When it is determined that the content search control apparatus exists in the vicinity of the content search control apparatus, and the determination unit acquires k pieces of evaluation information respectively corresponding to different k (an integer greater than or equal to 2) objects determined to exist, the k pieces K object identifiers indicated by each of the evaluation information are stored in the storage unit, and the determination unit further stores the k object identifiers when the k object identifiers are stored in the storage unit. The weighting coefficient associated with each is set to the first coefficient value, and the weighting coefficient erases the object identifier stored in the storage unit. The determination unit further determines m (1 ≦ m <k) of the k object identifiers in a period in which the k object identifiers are stored in the storage unit. ) Each time evaluation information indicating each of the object identifiers is acquired, a weighting factor corresponding to an object identifier other than the m object identifiers among the k object identifiers is decreased by a predetermined value, and the determination is performed. When the object identifier corresponding to the weight coefficient that is equal to or less than the second coefficient value less than the first coefficient value is stored in the storage unit, the object specified by the stored object identifier is It is determined that it does not exist in the vicinity of the content search control device, and the stored object identifier is deleted.

  Preferably, the search instruction unit further includes a maximum weight indicating a maximum value among a plurality of weighting factors respectively corresponding to the plurality of object identifiers when a plurality of object identifiers are stored in the storage unit. A random number is generated using a coefficient, and the search instruction unit, when a weight coefficient other than the maximum weight coefficient among the plurality of weight coefficients is larger than the random number, an object identifier corresponding to a weight coefficient larger than the random number; The object identifier corresponding to the maximum weight coefficient is transmitted to the content search device.

  Preferably, the determination unit stores the object identifier corresponding to a weighting factor that is less than the first coefficient value and greater than the second coefficient value in the storage unit. It is determined that there is a possibility that the object specified by the existing object identifier exists in the vicinity of the content search control device.

  Preferably, the object is a user indicated by a picture obtained by photographing, and the determination unit indicates the user specified by the object identifier indicated by the acquired evaluation information on the picture obtained by photographing. If not, it is determined that the user does not exist in the vicinity of the content search control device, and the recognition processing includes facial feature data indicating the facial features of the user indicated by the picture and a plurality of facial features registered in advance. This is a process of obtaining the evaluation value by comparing with data.

  Preferably, the object is a user, and the recognition process is a process of obtaining the evaluation value by comparing audio data uttered by the user with a plurality of pre-registered audio data. is there.

  A content reproduction device according to another aspect of the present invention includes the content search control device. The content playback device further includes the content search device, a content storage unit that stores a plurality of contents respectively associated with the plurality of registered objects, and a playback unit for playing back the content. At least one of these is associated with a non-public attribute value indicating non-public, and the determination unit of the content search control device has different k (two or more) determined to be present in the vicinity of the content search control device. When k pieces of evaluation information respectively corresponding to (integer) objects are acquired, k object identifiers respectively indicated by the k pieces of evaluation information are stored in the storage unit of the content search control device, and the search is performed. The instruction unit, when the determination unit stores the k object identifiers, the k object identifiers. A child is transmitted to the content search device, and the content search device is associated with a private attribute value among a plurality of contents stored in the content storage unit related to the received k object identifiers. Content specifying information for specifying non-existing content is transmitted to the playback unit, and the playback unit plays back the content stored in the content storage unit specified by the content specifying information.

  An integrated circuit according to still another aspect of the present invention provides a degree of similarity between feature data indicating features of an object and feature data indicating features of a registered object registered in advance in a recognition process for recognizing the object. Evaluation information indicating the evaluation value and the object identifier for specifying the object are sequentially acquired. The integrated circuit communicates with a content retrieval device that retrieves content related to the object specified by the object identifier by receiving the object identifier, and the integrated circuit acquires the evaluation information every time evaluation information is acquired. A determination unit that determines whether the object specified by the object identifier indicated by the evaluation information that is present exists in the vicinity of the integrated circuit, may or may not exist, and a storage unit, and the determination unit Further, when it is determined that the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the integrated circuit, an object identifier for specifying the object determined to exist is stored in the storage unit. And the determination unit further stores an object identifier in the storage unit. If it is determined that the object specified by the stored object identifier does not exist after being stored, the stored object identifier is deleted, and the stored object identifier is stored in the stored object identifier. When it is determined that the object specified by the object identifier exists or is likely to exist, the storage unit continues to store the object identifier, and the integrated circuit further stores the object identifier in the storage unit. And a search instructing unit that transmits the stored object identifier to the content search device and does not transmit an object identifier other than the stored object identifier to the content search device.

  According to still another aspect of the present invention, a content search control method includes: feature data indicating characteristics of an object and feature data indicating characteristics of a registered object registered in advance, obtained in a recognition process for recognizing the object. The content search control apparatus sequentially acquires evaluation information indicating an evaluation value that is a similarity and an object identifier that identifies the object. The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier, and the content search control device receives the evaluation information every time the evaluation information is acquired. A determination unit that determines whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, and may or may not exist; a storage unit; The content search control method specifies an object determined to exist when it is determined that the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device The object identifier is stored in the storage unit. And storing the object identifier when it is determined that there is no object specified by the stored object identifier after the object identifier is stored in the storage unit, The stored object identifier is stored in the storage unit when it is determined that the object specified by the stored object identifier exists or is likely to exist, The content search control method further transmits the stored object identifier to the content search device during a period in which the object identifier is stored in the storage unit, and an object identifier other than the stored object identifier. To the content search device Comprising the step of not trust.

  According to still another aspect of the present invention, a content search control program includes feature data indicating characteristics of an object and feature data indicating characteristics of a registered object registered in advance, which are obtained in a recognition process for recognizing the object. The content search control apparatus sequentially acquires evaluation information indicating an evaluation value that is a similarity and an object identifier that identifies the object. The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier, and the content search control device receives the evaluation information every time the evaluation information is acquired. A determination unit that determines whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, and may or may not exist; a storage unit; And the content search control program specifies an object determined to exist when it is determined that the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device The object identifier Storing in the storage unit; and after storing the object identifier in the storage unit, if it is determined that there is no object specified by the stored object identifier, the stored object identifier is deleted. The stored object identifier is stored in the storage unit when it is determined that the object specified by the stored object identifier exists or may exist. Subsequently, the content search control program further transmits the stored object identifier to the content search device during a period in which the object identifier is stored in the storage unit, and other than the stored object identifier. The object identifier of the content Comprising the step of not transmitting to the search apparatus.

  A computer-readable recording medium according to still another aspect of the present invention records the content search control program.

  According to the present invention, even when the recognition state of an object is unstable, it is possible to realize that content related to the object is normally searched.

It is a block diagram which shows the structure of the content reproduction apparatus in 1st Embodiment. It is an external view of a content reproduction apparatus. It is a block diagram which shows the characteristic function structure of a content reproduction apparatus. It is a figure for demonstrating a picked-up picture. It is a figure which shows the evaluation information table as an example. It is a figure which shows an example of a management table. It is a flowchart of a search control process. It is a flowchart of a determination process. It is a flowchart of a search instruction process. It is a figure which shows an example of the file list for reproduction | regeneration. It is a figure which shows an example of the change of the evaluation value corresponding to one user identifier. It is a figure which shows an example of a management table. It is a figure which shows the evaluation information table as an example. It is a flowchart of search control processing A. It is a flowchart of the determination process A. It is a figure which shows the determination table as an example. 10 is a flowchart of search instruction processing A. It is a figure which shows the determination table as an example. It is a figure for demonstrating the change of the weighting coefficient with progress of time. It is a block diagram which shows the characteristic function structure of the conventional content reproduction apparatus described in patent document 1. FIG.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.

<First Embodiment>
FIG. 1 is a block diagram illustrating a configuration of a content reproduction apparatus 100 according to the first embodiment. The content playback device 100 is a device for playing back content. In this specification, the contents are contents such as moving images, still images, sounds, and texts.

  The content playback apparatus 100 includes a camera 101, a camera controller 102, a liquid crystal display 103, a liquid crystal display controller 104, a touch panel 105, a touch panel controller 106, a speaker 107, a speaker controller 108, a memory card slot 109, A memory card controller 110, a CPU (Central Processing Unit) 111, a ROM (Read Only Memory) 112, a RAM (Random Access Memory) 113, an internal memory 114, and a power button 115 are provided.

  The camera 101 acquires an image by photographing a subject. The camera 101 is an apparatus using an image sensor. The image sensor is, for example, a complementary metal oxide semiconductor (CMOS) image sensor or a charge coupled device (CCD) image sensor.

The camera controller 102 controls the camera 101.
The liquid crystal display 103 has a screen for displaying an image. The image is a content such as a moving image, a still image, text, or an operation image. The operation image is a user interface image for operating the content reproduction apparatus 100. The liquid crystal display controller 104 controls the liquid crystal display 103.

  When the operation screen is displayed on the screen of the liquid crystal display 103, the touch panel 105 detects that the user has touched the screen in order to operate the content reproduction apparatus 100. The touch panel controller 106 controls the touch panel 105.

  The speaker 107 outputs sound. The speaker controller 108 controls the speaker 107.

  A memory card is inserted into the memory card slot 109. The memory card slot 109 reads content stored in the memory card. The memory card slot 109 stores content in the memory card. The memory card controller 110 controls the memory card slot 109 to perform processing for reading content from the memory card, processing for storing content in the memory card, and the like.

  The CPU 111 controls each unit in the content reproduction apparatus 100. The ROM 112 stores various processing programs and data. The RAM 113 temporarily stores data. The internal memory 114 stores content and a facial feature amount database.

  The face feature amount database is a database indicating a plurality of determination face feature data. The determination face feature data is data indicating the features of the user's face. The determination face feature data is, for example, data indicating the relative position of the face feature portion on the face. The facial features are eyes, nose, mouth and the like. The plurality of determination face feature data indicated by the face feature amount database is data registered in advance. Each of the plurality of determination face feature data is associated with a user identifier that identifies a user corresponding to the determination face feature data.

  The power button 115 is a button for turning on / off the power of the content reproduction apparatus 100.

FIG. 2 is an external view of the content reproduction apparatus 100.
Here, it is assumed that the image content indicating the user's face is stored in the memory card.

  When the user inserts the memory card into the memory card slot 109, the content reproduction apparatus 100 reads the image content stored in the memory card and detects the user's face indicated by the image content.

  Next, when the content reproducing apparatus 100 specifies the user indicated by the image content by collating the detected face feature quantity with the face feature quantity database, the content playback apparatus 100 sets the image content to content related to the specified user. A management table for managing the relationship between the user and the content is updated.

  If the user cannot be identified by the image content, the content reproduction apparatus 100 displays a registration confirmation image on the liquid crystal display 103. When the user cannot be specified by the image content, for example, when the image content does not indicate the user, when the feature amount of the user indicated by the image content is low in similarity with the feature amounts of a plurality of users registered in advance, etc. It is.

  The registration confirmation image is, for example, an image for inquiring whether or not to register user information related to content.

  Note that, for example, even when no music content is stored in the memory card and music content is stored, the content reproduction apparatus 100 may display the registration confirmation image on the liquid crystal display 103.

  The user performs a registration operation using the touch panel 105. When the registration operation is performed, the content reproduction apparatus 100 displays an image for inputting information about the user on the liquid crystal display 103. A user selects a user name to be associated from registered user names or inputs information on an unregistered user by an operation using the touch panel 105.

  FIG. 3 is a block diagram showing a characteristic functional configuration of the content reproduction apparatus 100. That is, FIG. 3 is a block diagram showing the main functions related to the present invention among the functions of the content reproduction apparatus 100 shown in FIG.

  The content reproduction apparatus 100 includes a photographing unit 301, a face detection unit 302, a collation unit 303, and a content search control device 304.

  The photographing unit 301 obtains a picture by photographing a subject every elapse of a predetermined time. The predetermined time is, for example, 1/10 second, 1/30 second, or the like. The subject is an arbitrary object as an example. In the following, information specifying an object is referred to as an object identifier.

  In the present embodiment, it is assumed that the object is a user (human). When the object is a user, hereinafter, an object identifier that identifies the object is referred to as a user identifier.

  The object is not limited to the user, and may be a general object (for example, an animal or a tool).

  The imaging unit 301 transmits the picture to the face detection unit 302 every time a picture is acquired. The imaging unit 301 corresponds to the camera 101 and the camera controller 102. Hereinafter, a picture obtained by photographing by the photographing unit 301 is referred to as a photographed picture. A user indicated by a picture obtained by photographing by the photographing unit 301 is an object.

  The face detection unit 302 performs face detection processing for detecting a face each time a captured picture is received. In the face detection process, the face detection unit 302 detects a face image (hereinafter referred to as a face image) depending on whether or not the photographed picture indicates a face feature. The facial features are eyes, nose, mouth and the like. The process for detecting the face is a well-known technique and will not be described in detail.

  Here, the photographed picture acquired by the photographing unit 301 is, for example, the following photographed picture P100.

FIG. 4 is a diagram for explaining a captured picture.
FIG. 4A shows a photographed picture P100 as an example.

  The photographed picture P100 shows two users showing the face images P110 and P120, respectively. Here, it is assumed that the face images P110 and P120 are detected by the face detection process.

  Referring to FIG. 3 again, the face detection unit 302 associates the detected face identifier with the detected face image. The detected face identifier is an identifier that identifies a face image. In addition, the face detection unit 302 identifies the relative position of the face feature in the detected face image. The face detection unit 302 generates face feature data indicating the relative position of the identified face feature as a face feature. The face detection unit 302 transmits the generated face feature data to the matching unit 303 together with the detected face identifier.

  In addition, since the technique for specifying the relative position of the face characteristic part in a face image is a known technique, detailed description is not given.

  When a plurality of face images are detected by the face detection process, the face detection unit 302 generates face feature data corresponding to each of the detected plurality of face images. In this case, the face detection unit 302 associates a different detected face identifier with each of the generated plurality of face feature data. In this case, the face detection unit 302 transmits each face feature data and a detected face identifier corresponding to the face feature data to the matching unit 303.

  Here, it is assumed that the face images P110 and P120 in FIG. 4A are detected by the face detection process. In this case, as shown in FIG. 4B, the face detection unit 302 associates the detected face identifiers F01 and F02 with the face images P110 and P120, for example.

  When the captured picture does not indicate a face feature, the face detection unit 302 transmits face feature data that does not indicate information to the matching unit 303.

  That is, the face detection unit 302 transmits the face feature data to the matching unit 303 every time a captured picture is received, that is, every time a predetermined time has elapsed.

  Note that when the photographed picture does not indicate a face feature, the face detection unit 302 may not transmit the face feature data.

  The face detection unit 302 corresponds to a program module executed by the CPU 111. Note that the face detection unit 302 may be configured by hardware such as an LSI (Large Scale Integration).

  The collation unit 303 performs collation processing. In the matching process, each time the matching unit 303 receives face feature data, the similarity (hereinafter referred to as evaluation) between the received face feature data and each of the plurality of determination face feature data indicated by the face feature amount database described above. (Also referred to as value).

  The face feature data is feature data indicating the features of the user as an object. The determination face feature data is feature data indicating features of a registered user as a registered object registered in advance.

  That is, recognition processing for recognizing a user as an object is performed by the face detection unit 302 and the collation unit 303. The recognition process is a process including a face detection process and a collation process.

  That is, the recognition process is a process for obtaining an evaluation value by comparing face feature data indicating a user's face feature indicated by a picture with a plurality of pre-registered face feature data.

  Assume that the evaluation value is indicated by a numerical value in the range of 0 to 1 as an example. The closer the evaluation value is to 1, the higher the similarity. On the other hand, the closer the evaluation value is to 0, the lower the similarity.

  Then, each time the evaluation unit calculates the evaluation value, the collation unit 303 detects the detected face identifier associated with the face feature data used to calculate the evaluation value, and the determination face used to calculate the evaluation value. Evaluation information indicating a user identifier associated with the feature data and the calculated evaluation value is generated. The collation unit 303 generates an evaluation information table indicating all the generated evaluation information, and transmits the evaluation information table to the content search control device 304.

  The collating unit 303 corresponds to a module of a program executed by the CPU 111 and an area in the internal memory 114 in which the face feature amount database is stored. Note that dedicated hardware may correspond to a part of the verification unit 303 instead of the program module.

  As described above, the face detection unit 302 transmits the face feature data to the matching unit 303 every predetermined time. That is, the collation unit 303 transmits an evaluation information table to the content search control device 304 every elapse of a predetermined time.

  Here, it is assumed that the face feature quantity database shows three determination face feature data as an example. Assume that user identifiers U01, U02, and U03 are associated with the three determination face feature data, respectively. The photographed picture is the photographed picture P100 in FIG. 4B, and the detected face identifiers F01 and F02 are associated with the face images P110 and P120, respectively.

In this case, it is assumed that the following evaluation information table T100 is generated by the matching process.
FIG. 5 is a diagram illustrating an evaluation information table T100 as an example. The evaluation information table T100 includes a plurality of evaluation information.

  In FIG. 5, “number” is a number for specifying evaluation information. Since the detected face identifier, user identifier, and evaluation value have been described above, detailed description will not be repeated.

  For example, the evaluation information of the number “1” has an evaluation value “0.0” that is a similarity between the face feature data corresponding to the detected face identifier “F01” and the determination face feature data corresponding to the user identifier “U01”. 9 ″. In this case, the similarity between the face feature data and the determination face feature data is 90%.

  Further, for example, the evaluation information of the number “6” has an evaluation value that is a similarity between the face feature data corresponding to the detected face identifier “F02” and the determination face feature data corresponding to the user identifier “U03”. 0.2 ". In this case, the similarity between the face feature data and the determination face feature data is 20%.

  Referring to FIG. 3 again, content reproduction apparatus 100 further includes a content search unit 305, a content storage unit 306, and a reproduction unit 307. In addition, the content search control device 304 includes a determination unit 308, a search instruction unit 309, and a storage unit 310.

  Although the details will be described later, the determination unit 308 determines whether the user exists in the vicinity of the content reproduction apparatus 100, may exist, or does not exist, using the received evaluation information table.

  The content reproduction device 100 includes a content search control device 304. Therefore, the vicinity of the content reproduction apparatus 100 is the vicinity of the content search control apparatus 304. That is, the vicinity of the content search control device 304 is the vicinity of the content reproduction device 100.

  The content storage unit 306 stores content related to the user specified by the user identifier corresponding to each of the plurality of determination face feature data indicated by the face feature amount database, in association with the user identifier. That is, the content storage unit 306 stores a management table described later. The management table is used to search for content.

  The content storage unit 306 corresponds to an area in the internal memory 114 where content is stored.

  Hereinafter, content related to the user is referred to as related content. When the related content is, for example, a still image, the related content is, for example, a still image that the corresponding user likes. When the related content is, for example, music data, the related content is, for example, music data that the corresponding user likes.

Here, as an example, it is assumed that the management table is the following management table T200.
FIG. 6 is a diagram illustrating an example of the management table T200. The management table T200 includes a plurality of management information.

  In FIG. 6, “number” is a number for specifying management information. The “content file name” is a file name of related content. The “user identifier” is a user identifier associated with the related content of the corresponding “content file name”.

  For example, the management information with the number “3” indicates that the user identifiers “U01” and “U02” are associated with the related content with the content file name “PIC0003.jpg”.

  The management table T200 is read from the internal memory 114 and stored in the RAM 113 when the content reproduction apparatus 100 is powered on.

  For example, when a management table is updated by registering new content after a memory card is inserted into the content reproduction apparatus 100, the management table stored in the RAM 113 and the internal memory 114 are stored. Both management tables are updated.

  Referring to FIG. 3 again, as will be described in detail later, search instruction unit 309 determines the necessity of content search, and transmits a user identifier to content search unit 305 when a search is necessary. .

  The search instruction unit 309 corresponds to a program module executed by the CPU 111. Note that the search instruction unit 309 may be configured by hardware such as an LSI.

The storage unit 310 is a memory for storing information.
The content search unit 305 detects the content by searching the content stored in the content storage unit 306 in association with the received user identifier. Then, the content search unit 305 creates a reproduction file list indicating the file names of the one or more detected contents, and transmits the reproduction file list to the reproduction unit 307.

  In other words, the content search unit 305 receives the user identifier as the object identifier, and searches for content related to the user as the object specified by the user identifier. The content search unit 305 is a content search device that communicates with the content search control device 304.

  The content search unit 305 corresponds to the RAM 113 and a module of a program executed by the CPU 111. Note that dedicated hardware may correspond to a part of the content search unit 305 instead of the module of the program.

  The playback unit 307 reads the content with the file name from the content storage unit 306 using the file name of the content shown in the received playback file list. Then, the playback unit 307 plays back the read content.

  The reproduction unit 307 corresponds to a module of a program executed by the liquid crystal display 103, the liquid crystal display controller 104, the speaker 107, the speaker controller 108, and the CPU 111. Note that dedicated hardware may correspond to part of the playback unit 307 instead of the program module.

  Next, a process (hereinafter referred to as a search control process) performed by the content search control apparatus 304 in the first embodiment will be described. The search control process is performed every time the content search control device 304 receives the evaluation information table.

FIG. 7 is a flowchart of the search control process.
In FIG. 7, in step S100, the determination unit 308 performs determination processing.

FIG. 8 is a flowchart of the determination process.
In step S110, the determination unit 308 sets the value of the search flag to “0”. The search flag is a flag indicating whether or not content related to the user needs to be searched. The search flag is stored in the storage unit 310. When the value of the search flag is “0”, it indicates that content search is unnecessary. On the other hand, when the value of the search flag is “1”, it indicates that content search is necessary.

  Further, the determination unit 308 sets the value of the counter n to 1. The counter n is a counter used for obtaining evaluation information.

  In step S <b> 111, the determination unit 308 obtains the n (an integer greater than or equal to 1) -th evaluation information indicated in the evaluation information table by reading. Here, it is assumed that the evaluation information table is the evaluation information table T100 of FIG. Further, it is assumed that the value of the counter n is 1.

In this case, the evaluation information with the number “1” in the evaluation information table T100 is acquired.
In step S121, the determination unit 308 determines whether or not the evaluation value indicated by the acquired latest evaluation information is greater than or equal to a predetermined first threshold value. The first threshold value is a value that is considered that the user specified by the user identifier indicated by the evaluation information indicating the evaluation value equal to or higher than the first threshold exists in the vicinity of the content search control device 304.

  That is, the first threshold value is a value that is considered that an object specified by evaluation information indicating an evaluation value equal to or higher than the first threshold value is present in the vicinity of the content search control device 304.

  In other words, when the determination unit 308 determines that the evaluation value indicated by the acquired latest evaluation information is greater than or equal to a predetermined first threshold value, the user indicated by the evaluation information indicating the evaluation value equal to or greater than the first threshold value It is determined that the user specified by the identifier exists in the vicinity of the content search control device 304.

  The first threshold is “0.8”, for example. The first threshold value is not limited to “0.8”, and may be “0.7”, for example.

  If YES in step S121, the process proceeds to step S122. On the other hand, if NO at step S121, the process proceeds to step S131 described later. Here, assuming that the evaluation information of the number “1” in the evaluation information table T100 has been acquired, the process proceeds to step S122.

  In step S122, it is determined whether or not evaluation information indicating the latest detected face identifier has already been stored. Specifically, the determination unit 308 determines whether or not the evaluation information indicating the detected face identifier indicated by the acquired latest evaluation information is already stored in the storage unit 310.

  If YES in step S122, the process proceeds to step S125 described later. On the other hand, if NO at step S122, the process proceeds to step S123. When the process of step S122 is performed for the first time, the process proceeds to step S123.

  In step S123, the determination unit 308 causes the storage unit 310 to store the acquired latest evaluation information. That is, the determination unit 308 causes the storage unit 310 to store the user identifier indicated by the acquired latest evaluation information.

  That is, when it is determined that the user specified by the user identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device 304, the determination unit 308 determines a user identifier that specifies the user determined to exist. The data is stored in the storage unit 310.

In step S124, the determination unit 308 sets the value of the search flag to “1”.
In step S125, the determination unit 308 determines whether or not all evaluation information indicated in the evaluation information table has been acquired. For example, it is assumed that the evaluation information table is the evaluation information table T100 in FIG. In this case, all the evaluation information is six pieces of evaluation information.

  If YES in step S125, the determination process ends, the process returns to the search control process in FIG. 7, and the process proceeds to step S200. On the other hand, if NO at step S125, the process proceeds to step S126.

In step S126, the determination unit 308 increments the value of the counter n by 1.
Then, the process of step S111 is performed again.

If NO in step S121, the process proceeds to step S131.
In step S131, the determination unit 308 determines whether or not the evaluation value indicated by the acquired latest evaluation information is equal to or less than the second threshold value.

  The second threshold is a value less than the first threshold. The second threshold value is a value that is assumed that the user specified by the user identifier indicated by the evaluation information indicating the evaluation value equal to or lower than the second threshold value does not exist in the vicinity of the content search control device 304. That is, the second threshold value is a value that is regarded as an object specified by evaluation information indicating an evaluation value equal to or lower than the second threshold value not existing in the vicinity of the content search control device 304.

  The second threshold is “0”, for example. The second threshold value is not limited to “0”, and may be “0.1”, for example.

  If YES in step S131, the process proceeds to step S132. On the other hand, if NO at step S131, the process proceeds to step S125.

  In step S132, it is determined whether evaluation information indicating the latest detected face identifier and user identifier has already been stored. Specifically, the determination unit 308 determines whether or not the detected face identifier indicated by the acquired latest evaluation information and the evaluation information indicating the user identifier are already stored in the storage unit 310.

  If YES in step S132, the process proceeds to step S133. If it is determined as YES in step S132, it is determined that the user specified by the user identifier indicated by the acquired latest evaluation information does not exist in the vicinity of the content search control device. If YES is determined in step S <b> 132, for example, it is a case where the user specified by the user identifier indicated by the acquired latest evaluation information is not photographed by the photographing unit 301.

  Here, it is assumed that the user identifier is stored in the storage unit 310. Further, it is assumed that the acquired latest evaluation information indicates a user identifier stored in the storage unit 310. Further, it is assumed that the evaluation value indicated by the acquired latest evaluation information is less than the first threshold and greater than the second threshold.

  In this case, NO is determined in step S121, and NO is determined in step S131. In this case, the determination unit 308 determines that there is a possibility that the user specified by the user identifier stored in the storage unit 310 exists in the vicinity of the content search control device 304.

  That is, in the case where the user identifier is stored in the storage unit 310, the determination unit 308 indicates that the evaluation value indicated by the newly acquired evaluation information indicating the user identifier stored in the storage unit 310 is the first threshold value. If it is less than and greater than the second threshold value, it is determined that there is a possibility that the user specified by the user identifier stored in the storage unit 310 may exist in the vicinity of the content search control device 304.

  That is, the user identifier stored in the storage unit 310 continues to be stored in the storage unit 310 when it is determined that the object specified by the stored user identifier exists or is likely to exist. .

  Here, it is assumed that the user identifier is stored in the storage unit 310. It is assumed that the acquired latest evaluation information indicates the user identifier stored in the storage unit 310. In addition, it is assumed that the evaluation value indicated by the acquired latest evaluation information is equal to or less than the second threshold value.

  In this case, NO is determined in step S121, YES is determined in step S131, and YES is determined in step S132. In this case, the determination unit 308 determines that the user specified by the user identifier stored in the storage unit 310 does not exist in the vicinity of the content search control device 304.

  That is, in the case where the user identifier is stored in the storage unit 310, the determination unit 308 has a newly acquired evaluation value indicated by the evaluation information indicating the stored user identifier is equal to or less than the second threshold value. In this case, it is determined that the user specified by the stored user identifier does not exist in the vicinity of the content search control device 304.

  That is, when the user specified by the user identifier indicated by the acquired evaluation information is not indicated in the picture obtained by shooting by the shooting unit 301, the determination unit 308 does not exist in the vicinity of the content search control device 304. Is determined.

  In step S133, the determination unit 308 deletes the evaluation information stored in the storage unit 310 indicating the user identifier indicated by the acquired latest evaluation information.

  That is, after the user identifier is stored in the storage unit 310, the determination unit 308 deletes the stored user identifier when it is determined that there is no user specified by the stored user identifier. .

  In step S134, the determination unit 308 transmits the deletion user identifier to the search instruction unit 309. The erased user identifier is a user identifier indicated by the erased evaluation information.

Then, the process proceeds to step S125.
If YES in step S125, the determination process ends, the process returns to the search control process in FIG. 7, and the process proceeds to step S200.

In step S <b> 200, search instruction processing is performed by the search instruction unit 309.
FIG. 9 is a flowchart of the search instruction process.

  In step S210, the search instruction unit 309 determines whether the value of the search flag stored in the storage unit 310 is “1”. If YES in step S210, the process proceeds to step S211. On the other hand, if NO at step S210, the process proceeds to step S220.

  In step S211, user identifier transmission processing is performed. In the user identifier transmission process, the search instruction unit 309 transmits the user identifier indicated by each of all evaluation information stored in the storage unit 310 to the content search unit 305 as a search instruction.

  That is, the search instruction unit 309 transmits the stored user identifier to the content search unit 305 during the period in which the user identifier is stored in the storage unit 310, and a user identifier other than the stored user identifier. Is not transmitted to the content search unit 305.

  In step S <b> 220, the search instruction unit 309 determines whether an erase user identifier has been received from the determination unit 308. If YES in step S220, the process proceeds to step S221 described later. On the other hand, if NO at step S220, the search instruction process ends, the process returns to the search control process of FIG. 7, and the search control process ends.

  When the content search unit 305 receives one or more user identifiers, the content search unit 305 performs related content search processing. In the related content search process, the content search unit 305 searches for related content using the management table described above. Specifically, when the content search unit 305 receives one or more user identifiers, the content search unit 305 generates a reproduction file list indicating the content file names associated with the received user identifiers in the management table.

  Then, the content search unit 305 transmits the generated reproduction file list to the reproduction unit 307.

  The playback unit 307 reads the related content having the content file name indicated in the received playback file list from the content storage unit 306 and plays back the related content.

  Note that the content search unit 305 performs processing for determining whether or not an erased user identifier has been received, independently of other processing.

  Here, as an example, it is assumed that the content search unit 305 receives user identifiers “U01” and “U02” as search instructions. Further, it is assumed that the management table is the management table T200 of FIG.

  In this case, the content search unit 305 selects “PIC0002.jpg”, “PIC0003.jpg”, and “img091201003.jpg” as the content file names associated with both the user identifiers “U01” and “U02”. To do.

  Then, the content search unit 305 generates the following reproduction file list PL300 indicating the selected content file name.

FIG. 10 is a diagram showing an example of the reproduction file list PL300.
In this case, the playback unit 307 reads the related content of the content file names “PIC0002.jpg”, “PIC0003.jpg”, and “img091201003.jpg” shown in the playback file list PL300 from the content storage unit 306.

  Then, the playback unit 307 plays back the related content. Here, when the related content is a still image, the reproduction unit 307 reproduces the related content by displaying the still image as the related content on the liquid crystal display 103.

  When the related content is audio data, the reproduction unit 307 reproduces the related content by outputting audio data as related content from the speaker 107.

  Again referring to FIG. 9, if it is determined as YES in step S220, the process of step S221 is performed.

  In step S221, reproduction stop instruction transmission processing is performed. In the reproduction stop instruction transmission process, the search instruction unit 309 transmits a reproduction stop instruction to the content search unit 305. The reproduction stop instruction is an instruction to stop the reproduction of the related content having the file name associated with the received erase user identifier.

  When the content search unit 305 receives the erased user identifier, the content search unit 305 transmits, to the playback unit 307, a stop instruction for stopping the playback of the related content having the content file name associated with the received erased user identifier. To do.

  In response to receiving the stop instruction, the playback unit 307 stops the playback of the related content specified by the stop instruction.

  The search control process described above is performed every time the content search control device 304 receives the evaluation information table.

Next, the search control process of FIG. 7 will be described with a specific example.
Here, as an example, it is assumed that the collation unit 303 transmits the evaluation information table T <b> 100 of FIG. 5 to the content search control device 304. Further, it is assumed that the first threshold value and the second threshold value are “0.8” and “0”, respectively.

First, the determination process of the search control process of FIG. 7 is performed.
And the process of step S110 of FIG. 8 is performed. Thereafter, the determination unit 308 acquires the evaluation information of the number “1” in FIG. 5 (S111). The evaluation value indicated by the evaluation information with the number “1” is equal to or greater than the first threshold (YES in S121). Therefore, the process of step S122 is performed. At this point, since the evaluation information indicating the detected face identifier “U01” indicated by the evaluation information with the number “1” is not stored in the storage unit 310 (NO in S122), the determination unit 308 displays the evaluation information with the number “1”. Then, it is stored in the storage unit 310 (S123).

  And after the process of step S124, S125, S126 is performed, the determination part 308 acquires the evaluation information of the number "2" of FIG. 5 (S111). In this case, the process proceeds to step S131.

  Since the evaluation value “0.2” indicated by the evaluation information of the number “2” is larger than the second threshold value (NO in S131), the processes in steps S125 and 126 are performed again.

  Then, the determination unit 308 acquires the evaluation information of the number “3” in FIG. 5 (S111). In this case, the processes of steps S121 and S131 are performed.

  Since the evaluation value “0” indicated by the evaluation information with the number “3” is equal to or smaller than the second threshold (YES in S131), the process of step S132 is performed. At this time, the evaluation information indicating the detected face identifier “F01” and the user identifier “U03” indicated by the evaluation information of the number “3” is not stored in the storage unit 310 (NO in S132). The process 126 is performed.

  Then, the determination unit 308 acquires the evaluation information of the number “4” in FIG. 5 (S111). In this case, steps S121, S131, S125, and S126 are performed again.

  Then, the determination unit 308 acquires the evaluation information of the number “5” in FIG. 5 (S111). The evaluation value “0.8” indicated by the evaluation information with the number “5” is equal to or greater than the first threshold (YES in S121). Therefore, the process of step S122 is performed.

  At this time, since the evaluation information indicating the detected face identifier “U02” indicated by the evaluation information of the number “5” is not stored in the storage unit 310 (NO in S122), the determination unit 308 displays the evaluation information of the number “5”. Then, it is stored in the storage unit 310 (S123).

  And after the process of step S124, S125, S126 is performed, the determination part 308 acquires the evaluation information of the number "6" of FIG. 5 (S111). In this case, the process proceeds to step S131.

  Since the evaluation value “0.2” indicated by the evaluation information with the number “6” is larger than the second threshold value (NO in S131), the process of step S125 is performed again. In this case, it is determined as YES in Step S125, and this determination process ends.

  At this time, the storage unit 310 stores evaluation information of numbers “1” and “5” in FIG. The value of the search flag is “1”.

  Then, the search instruction process of FIG. 9 is performed. In this case, YES is determined in the step S210, and the process of the step S211 is performed.

  The search instruction unit 309 transmits the user identifiers “U01” and “U02” indicated by the evaluation information of the numbers “1” and “5” to the content search unit 305 as search instructions (S211). Here, it is assumed that the erasure user identifier has not been received. In this case, NO is determined in step S220, the search instruction process ends, and the search control process ends.

  Here, it is assumed that the management table used by the content search unit 305 is the management table T200 of FIG.

  In this case, the content search unit 305 causes the content file names “PIC0002.jpg”, “PIC0003.jpg”, “img091201003.jpg” associated with both the user identifiers “U01” and “U02” in the management table T200. The reproduction file list PL300 of FIG.

  Then, content search unit 305 transmits reproduction file list PL300 to reproduction unit 307.

  In response to the reception of the reproduction file list PL300, the reproduction unit 307 reproduces the related contents having the content file names “PIC0002.jpg”, “PIC0003.jpg”, and “img091201003.jpg” in the same manner as described above.

The related content is reproduced as described above.
Next, processing when the content search control device 304 sequentially receives evaluation information tables indicating different evaluation values will be described.

FIG. 11 is a diagram illustrating an example of a change in evaluation value corresponding to one user identifier.
In FIG. 11, the vertical axis represents the evaluation value, and the horizontal axis represents time. Here, it is assumed that the content search control device 304 receives the evaluation information table at each of the times t1 to t10 by performing the above-described collation processing, for example, 10 times. In the following description, the user identifier “U01” will be described as an example.

  In the following, the two users identified by the user identifiers “U01” and “U02” are referred to as user U01 and user U02, respectively.

  Assume that the evaluation value associated with the user identifier “U01” is less than the first threshold in each piece of evaluation information indicated by the evaluation information table received by the content search control device 304 at each of times t1 and t2.

  In this case, even when the search control process of FIG. 7 is performed, the evaluation information indicating the user identifier “U01” is not stored in the storage unit 310.

  Here, it is assumed that, for example, the face of the user U01 is photographed by the photographing unit 301 at time t3. In addition, in at least one piece of evaluation information indicated by the evaluation information table received by the content search control device 304 at time t3, the evaluation value associated with the user identifier “U01” is greater than or equal to the first threshold value.

  In this case, when the search control process of FIG. 7 is performed, YES is determined in step S121 of FIG. 8, and the processes of steps S122 and S123 are performed, whereby the user identifier “U01” is stored in the storage unit 310. The evaluation information to be shown is stored.

  Thereafter, in each piece of evaluation information indicated by the evaluation information table received by the content search control device 304 at each of times t4, t5, and t6, the evaluation value associated with the user identifier “U01” is greater than or equal to the first threshold value. To do. The reason why the evaluation value changes is because, for example, the face direction of the user U01 changes.

  Here, it is assumed that the user U01 gradually moves away from the content search control device 304 after time t6. Then, it is assumed that the user U01 is no longer photographed by the photographing unit 301 at time t10.

  In this case, in each piece of evaluation information indicated by the evaluation information table received by the content search control device 304 at each of the times t7, t8, and t9, the evaluation value associated with the user identifier “U01” is less than the first threshold value. Suppose that it is equal to or greater than the second threshold value.

  At each of the times t7, t8, and t9, the search control process of FIG. 7 is performed, so that NO is determined in step S121 of FIG. 8, and NO is determined in step S131.

  In this case, as described above, the determination unit 308 determines that the user U01 specified by the user identifier “U01” stored in the storage unit 310 may exist in the vicinity of the content search control device 304. . That is, it is determined that there is a possibility that the user U01 exists in the vicinity of the content search control device 304 between times t7 and t9.

  Further, in each piece of evaluation information indicated by the evaluation information table received by the content search control device 304 at time t10, the evaluation value associated with the user identifier “U01” is equal to or less than the second threshold value.

  In this case, the search control process of FIG. 7 is performed, so that the processes of steps S121, S131, and S132 of FIG. 8 are sequentially performed. And it determines with YES by step S132 and the process of step S133 is performed.

  In this case, as described above, the determination unit 308 determines that the user U01 specified by the user identifier “U01” stored in the storage unit 310 does not exist in the vicinity of the content search control device 304.

  In this case, the determination unit 308 deletes the evaluation information indicating the user identifier “U01” stored in the storage unit 310 (S133). Then, the determination unit 308 transmits the erased user identifier “U01” to the search instruction unit 309 (S134).

  And the process of step S124, S125, S210, S211 and S220 is performed in order.

  In this case, YES is determined in the step S220, and the process of the step S221 is performed.

  In this case, the search instruction unit 309 transmits a reproduction stop instruction indicating the erasure user identifier “U01” to the content search unit 305.

  In this case, the content search unit 305 transmits to the playback unit 307 a stop instruction for stopping the playback of the related content with the content file name associated with the received erased user identifier “U01” in the management table.

  In response to receiving the stop instruction, the playback unit 307 stops the playback of the related content specified by the stop instruction.

  As described above, according to the present embodiment, the evaluation information once stored in the storage unit 310 is stored in the storage unit 310 until the evaluation value corresponding to the user identifier indicated by the evaluation information becomes equal to or less than the second threshold value. Continue to be remembered.

  That is, after it is determined that the user specified by the user identifier exists in the vicinity of the content search control apparatus, the evaluation information continues to be stored until it is determined that the user does not exist in the vicinity of the content search control apparatus.

  That is, while the user identifier is stored in the storage unit 310 and while it is determined that there is a possibility that a user specified by the stored user identifier exists, the user identifier continues to be stored. There is a possibility that the user exists, for example, when the surrounding environment of the user is changed, when the orientation of the user's face is changed, or when the user moves.

  Thereby, in the reproduction of the related content related to the user specified by the evaluation information stored in the storage unit 310, the evaluation value corresponding to the user is less than the first threshold value, and the determination result of the matching process is not stable. However, the related content is not stopped immediately.

  The case where the determination result of the collation processing is not stable is, for example, when the user's surrounding environment has changed, when the user's face orientation has changed, or when the user has moved.

  That is, even when a user's recognition state as an object is unstable, related content related to the user can be stably reproduced.

  Further, the user identifier stored in the storage unit 310 continues to be stored in the storage unit 310 when it is determined that an object specified by the stored user identifier exists or may exist. .

  The search instruction unit 309 transmits the stored user identifier to the content search unit 305 during the period in which the user identifier is stored in the storage unit 310, and sets the user identifier other than the stored user identifier to the content. Not transmitted to the search unit 305.

  Thereby, even when the recognition state of the user as an object is unstable, the content search unit 305 can search related content related to the user. That is, even when the recognition state of the object is unstable, it is possible to realize that the content related to the object is normally searched.

  In this embodiment, evaluation information (user identifier) whose evaluation value is equal to or less than the second threshold is immediately deleted, but the present invention is not limited to this. For example, the weighting factor and evaluation information are held as a set in the control means, and the evaluation information (user identifier) whose evaluation value is equal to or smaller than the second threshold value is not immediately deleted, and the weight is reduced by a predetermined value. Thus, the user's degree of association may be gradually reduced as time elapses.

  As a result, even when the evaluation value is equal to or lower than the second threshold despite the presence of the user in front of the content reproduction apparatus 100, it is possible to prevent the reproduction of the content related to the user from being suddenly stopped. Become.

<Second Embodiment>
In the present embodiment, the effectiveness of the content search control apparatus when public attributes are associated with content will be described.

  The content reproduction apparatus in the present embodiment is the content reproduction apparatus 100 in FIGS. 1 and 3. Therefore, detailed description of each part in content reproduction apparatus 100 will not be repeated.

  The present embodiment is different from the first embodiment in the processing of the content search unit 305. Since the processing of each other part is the same as that of the first embodiment, detailed description will not be repeated.

  Note that the content search control device 304 of the present embodiment performs the search control process of FIG. 7 as in the first embodiment. That is, the search instruction transmission process of FIG. 9 is performed.

As a result, the user identifier is transmitted to the content search unit 305.
When receiving the user identifier, the content search unit 305 performs related content search processing A. Here, it is assumed that the management table used in the related content search processing A is the following management table T200A.

  FIG. 12 is a diagram illustrating an example of the management table T200A. The management table T200A includes a plurality of management information.

  Since each item shown in management table T200A has been described with reference to FIG. 6, detailed description will not be repeated. In this case, in the content storage unit 306, as an example, the content of the six content file names shown in the management table T200A is stored as related content related to the corresponding registered user.

  That is, the content storage unit 306 stores a plurality of contents respectively associated with registered users as a plurality of registered objects.

  Each management information in FIG. 12 is different from each management information in FIG. 6 in that a public attribute is associated with a user identifier indicated by some management information. That is, the public attribute is associated with the content file name indicated by some management information.

  In the example of FIG. 12, an attribute value “private” indicating non-disclosure is registered in association with a part of the user identifier as a public attribute for content that the user does not want to disclose. In the following, an attribute value indicating private is referred to as a private attribute value.

  For example, the private attribute value “private” is associated with the content file name indicated by each of the management information of the numbers “1” and “5”. That is, the private attribute value “private” is associated with the content of the content file name indicated by each of the management information of the numbers “1” and “5”.

  In other words, at least one of a plurality of contents respectively associated with a plurality of registered users stored in the content storage unit 306 is associated with a non-public attribute value indicating non-public.

  Next, related content search processing A performed by the content search unit 305 in the present embodiment will be described. Here, as an example, it is assumed that the face of one user U01 is shot by the shooting unit 301.

  In this case, the imaging unit 301, the face detection unit 302, the collation unit 303, and the content search control device 304 perform the same processing as in the first embodiment, so that the content search unit 305 uses the user identifier “U01”. Suppose it is received.

  In the related content search processing A, the content search unit 305 includes content file names “PIC0001.jpg”, “PIC0002.jpg”, “PIC0003.jpg”, which are associated with the user identifier “U01” in the management table T200A. Select “img091201003.jpg”.

  Then, the content search unit 305 generates a reproduction file list indicating each selected file name, and transmits the reproduction file list to the reproduction unit 307.

  That is, when only one user is photographed by the photographing unit 301, a content file name associated with a private attribute value “private” as a public attribute is also a search target. In this case, the related content search process A is the same process as the related content search process of the first embodiment.

  Next, it is assumed that the faces of the user U01 and the user U02 are photographed by the photographing unit 301.

  In this case, the photographing unit 301, the face detection unit 302, the collation unit 303, and the content search control device 304 perform the same processing as in the first embodiment.

  Thereby, the determination unit of the content search control device 304 also acquires two pieces of evaluation information corresponding to two different users from the collation unit 303. In this case, the determination unit of the content search control device 304 determines that the user U01 and the user U02 exist in the vicinity of the content search control device 304 in the determination process of FIG. In this case, the determination unit of the content search control device 304 causes the storage unit 310 of the content search control device 304 to store two user identifiers respectively indicated by the two pieces of evaluation information in the determination process of FIG.

  In this case, the search instruction unit 309 of the content search control device 304 transmits the two user identifiers to the content search unit 305 in the search instruction process of FIG.

  Accordingly, it is assumed that the content search unit 305 receives the user identifiers “U01” and “U02”.

  In this case, since there is not one user, in the related content search processing A, the content search unit 305 includes the private attribute value among the content file names associated with both the user identifiers “U01” and “U02”. A content file name not associated with “private” is selected as a search target.

  That is, the content search unit 305 excludes the content file name associated with the private attribute value “private” from the search target.

  In this case, among the content file names associated with both the content search unit 305 and the user identifiers “U01” and “U02”, the content file name not associated with the private attribute value “private” is “ “PIC0002.jpg”, “PIC0003.jpg”, and “img091201003.jpg” are selected.

  Then, the content search unit 305 generates a reproduction file list indicating each selected file name, and transmits the reproduction file list to the reproduction unit 307.

  That is, the content search unit 305 serving as a content search device identifies content that is not associated with a private attribute value among a plurality of contents stored in the content storage unit 306 related to the received two user identifiers. A file list for reproduction as content specifying information to be transmitted is transmitted to the reproduction unit 307.

  The playback unit 307 plays back the related content having the content file name shown in the playback file list. The related content is content stored in the content storage unit 306. That is, the playback unit 307 plays back the content stored in the content storage unit specified by the playback file list as the content specifying information.

  Here, for comparison with the present embodiment, a comparative example in which the content search unit 405 of the conventional content reproduction apparatus 400 performs processing will be described.

  Next, it is assumed that the user U01 and the user U02 are photographed by the photographing unit 401.

  In this case, it is assumed that the result of the collation of the user U01 becomes unstable due to the movement of the head or face of the user U01, and it is determined that only the user U02 is photographed by the photographing unit 401. In this case, the content playback apparatus 400 searches for content related to the user identifier “U02” and plays back the content.

  In this case, it is assumed that the management table T200A of FIG. 12 is used. In this case, “PIC0002.jpg”, “PIC0003.jpg”, “img091201002.jpg”, and “img091201003.jpg” are searched as content file names. However, the user identifier “U02” associated with the private attribute value “private” is associated with “img091201002.jpg”.

  That is, an undesirable situation may occur in which, although the user U01 and the user U02 exist in the vicinity of the content reproduction device 400, content that the user U02 does not want to be seen by others is reproduced.

  However, according to the content reproduction apparatus 100 of the present embodiment, even if the recognition of a certain user becomes unstable, it is determined that there is a possibility that the user exists as described in the first embodiment. In the meantime, the user identifier continues to be stored in the storage unit 310, and new content search caused by recognition instability is suppressed.

  Therefore, even in the situation of the comparative example, while it is determined that the user U01 may exist in the vicinity of the content reproduction device 100 (while the evaluation value of the user U01 is greater than 0), the user U01 and the user U02 However, it is possible to prevent an undesired situation in which content that the user U02 does not want to be seen by others is played back despite the presence of.

  In the present embodiment, the content to which the private attribute value is associated is not reproduced with respect to the reproduction target content selected based on the recognition result of a plurality of people, and the private attribute value is associated with the reproduction target content. Disclosure of playing content that has not been done.

  However, in the present embodiment, even when one or more people are recognized, and even when the presence of a person that cannot be recognized by the face detection unit 302, the collation unit 303, etc. is confirmed, the reproduction is performed. If a private attribute value is associated with any of the target contents, the content with the private attribute value is excluded, and only the content without the private attribute value is played. The processing may be performed as described above.

  As a result, when the existence of another person is confirmed during the reproduction of private content, the reproduction of the content to which the private attribute value is associated is excluded, and the private attribute value is associated. Since only content that is not present can be played back, it is possible to prevent private content from being disclosed to others.

  Thereby, for example, while it is determined that there is a possibility that the user U01 that cannot be recognized by the face detection unit 302, the collation unit 303, and the like exists in the vicinity of the content reproduction device 100, the user U02 exists, It is possible to prevent an undesirable situation in which content that the user U02 does not want to be seen by others is played.

<Third Embodiment>
In the third embodiment, even if it is determined that there is no user due to a change in the surrounding environment of the user or the movement of the user, the reproduction of the content related to the user is not immediately stopped, A content search control apparatus that realizes step-by-step adjustment of playback of video content will be described.

  The content reproduction apparatus in the present embodiment is the content reproduction apparatus 100 in FIGS. 1 and 3. Therefore, detailed description of each part in content reproduction apparatus 100 will not be repeated.

  Note that this embodiment is different from the first embodiment in the processing of the collation unit 303, the content search control device 304, and the content search unit 305. Since the processing of each other part is the same as that of the first embodiment, detailed description will not be repeated.

  Similar to the first embodiment, the face detection unit 302 transmits the face feature data to the matching unit 303 every time a predetermined time elapses.

Next, the operation of the matching unit 303 will be described.
The matching unit 303 performs a matching process A. In the collation process A, each time the collation unit 303 receives face feature data, as in the first embodiment, the received face feature data and a plurality of determination face feature data indicated by the face feature amount database described above. The degree of similarity (hereinafter also referred to as an evaluation value) is calculated.

  Then, each time a plurality of evaluation values are calculated for one face feature data, the collating unit 303 calculates the evaluation value having the largest value among the plurality of calculated evaluation values corresponding to each user identifier, and the user identifier. Evaluation information indicating that is generated.

  The collation unit 303 generates an evaluation information table indicating all the generated evaluation information, and transmits the evaluation information table to the content search control device 304.

  As in the first embodiment, the collating unit 303 transmits an evaluation information table to the content search control device 304 every elapse of a predetermined time.

  A recognition process for recognizing a user as an object is performed by the face detection unit 302 and the collation unit 303. The recognition processing in the present embodiment is processing including face detection processing and matching processing A performed by the face detection unit 302.

  Here, as in the first embodiment, the photographed picture is assumed to be the photographed picture P100 in FIG. 4B as an example. In this case, the evaluation information table generated in the present embodiment is, for example, the following evaluation information table T300.

  FIG. 13 is a diagram illustrating an evaluation information table T300 as an example. The evaluation information table T300 includes a plurality of evaluation information.

  The evaluation information table T300 differs from the evaluation information table T100 of FIG. 5 in that it does not include the detected face identifier item. Since other items are the same as those in the evaluation information table T100, detailed description will not be repeated.

  Next, processing performed by the content search control device 304 in the third embodiment (hereinafter referred to as search control processing A) will be described. The search control process A is performed every time the content search control device 304 receives the evaluation information table.

FIG. 14 is a flowchart of the search control process A.
In FIG. 14, in step S <b> 100 </ b> A, determination processing A is performed by the determination unit 308.

  FIG. 15 is a flowchart of the determination process A. In FIG. 15, the process with the same step number as the step number of FIG. 8 is the same as the process described in the first embodiment, and therefore detailed description will not be repeated.

  In step S110, processing similar to that in the first embodiment is performed. Thereby, the value of the search flag is set to “0”. Further, the value of the counter n is set to “1”.

  In step S110A, the determination unit 308 generates a determination table that indicates the number of user identifiers indicating determination information that associates each user identifier indicated by the received evaluation information table, a check flag, and a weighting coefficient that will be described later. . Then, the determination unit 308 stores the determination table in the storage unit 310.

  Then, the determination unit 308 sets the value of each check flag to “0”. The check flag is a flag indicating whether it is checked whether or not the corresponding user identifier is stored.

  When the value of the check flag is “0”, it indicates that it is not checked whether or not the corresponding user identifier is stored. When the value of the check flag is “1”, it indicates that it is checked whether or not the corresponding user identifier is stored.

  For example, when the detection of the user's face becomes unstable and the number of faces detected in the current process is smaller than the number of faces detected in the previous process, the user identifier corresponding to the check flag indicating “0” Will remain remembered.

  In step S111, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. Here, it is assumed that the evaluation information table is the evaluation information table T300 of FIG. Further, it is assumed that the value of the counter n is 1.

In this case, the evaluation information with the number “1” in the evaluation information table T300 is acquired.
In step S111A, the determination unit 308 determines whether or not the user identifier indicated by the acquired latest evaluation information is stored in the storage unit 310. If NO in step S111A, the process proceeds to step S121. On the other hand, if YES in step S111A, the process proceeds to step S124A described later.

  In step S121, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. If YES in step S121, the process proceeds to step S123A. On the other hand, if NO at step S121, the process proceeds to step S125 described later.

  As in the first embodiment, when the determination unit 308 determines that the evaluation value indicated by the acquired latest evaluation information is equal to or greater than a predetermined first threshold, the determination value is equal to or greater than the first threshold. It is determined that the user specified by the user identifier indicated by the evaluation information is present in the vicinity of the content search control device 304.

  In step S123A, the determination unit 308 causes the storage unit 310 to store the user identifier indicated by the acquired latest evaluation information.

In step S124, the determination unit 308 sets the value of the search flag to “1”.
In step S124A, the determination unit 308 sets the value of the check flag corresponding to the user identifier indicated by the acquired latest evaluation information to “1”.

  In addition, the determination unit 308 sets the value of the weighting coefficient corresponding to the user identifier indicated by the acquired latest evaluation information to Wmax as the first coefficient value.

  The weighting coefficient is a coefficient for probabilistically representing the presence of the user specified by the corresponding user identifier. The weight coefficient is a coefficient for determining whether or not to delete the user identifier stored in the storage unit 310 corresponding to the weight coefficient.

  Wmax is the maximum value that can be set for the weighting factor. Wmax is, for example, “100”. That is, when the user identifier is stored in the storage unit 310, the determination unit sets the weighting coefficient associated with the user identifier stored in the storage unit 310 to the first coefficient value.

  In this case, the determination table stored in the storage unit 310 is, for example, the following determination table T400.

  FIG. 16 is a diagram illustrating a determination table T400 as an example. The determination table T400 shows a plurality of determination information.

  In FIG. 16, “number” is a number for specifying the determination information. Since the check flag and the weighting factor have been described above, detailed description will not be repeated.

  The determination information with the number “1” indicates that the value of the check flag and the weighting factor associated with the user identifier “U01” are “1” and Wmax, respectively. In this case, the determination table T400 indicates that it is checked whether or not the user identifier “U01” is stored.

  The determination information with the number “2” indicates that the value of the check flag associated with the user identifier “U02” is “0”. In this case, the determination table T400 indicates that it is not checked whether or not the user identifier “U02” is stored. The determination information with the number “2” indicates that the value of the weighting coefficient associated with the user identifier “U02” is not set.

  Referring to FIG. 15 again, after the process of step S124A, the process proceeds to step S125.

  In step S125, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. If YES in step S125, the process proceeds to step S130A. On the other hand, if NO at step S125, the process proceeds to step S126.

  In step S126, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. By this process, the value of the counter n is incremented by 1. Thereafter, the process of step S111 is performed again.

  In step S <b> 130 </ b> A, the determination unit 308 determines whether or not the user identifier associated with the check flag indicating “0” is stored in the storage unit 310. Specifically, the determination unit 308 determines whether or not the determination table stored in the storage unit 310 indicates determination information indicating a user identifier associated with a check flag indicating “0”.

  If YES in step S130A, the process proceeds to step S131A. On the other hand, if NO at step S130A, the determination process A ends, the process returns to the search control process A of FIG. 14, and the process proceeds to step S200A.

  The case of NO in step S <b> 130 </ b> A is a case where, for example, the value of the check flag associated with all user identifiers indicated by the determination table stored in the storage unit 310 is “1”. If YES in step S130A, the determination table stored in the storage unit 310 indicates determination information indicating a user identifier associated with a check flag indicating “0”.

  In step S131A, the determination unit 308 decreases the value of the weight coefficient associated with the check flag indicating “0” by a predetermined value dw. Specifically, the determination unit 308 decreases the value of the weighting factor indicated by the determination information indicating the check flag indicating “0” in the determination table by a predetermined value dw.

  In step S132A, it is determined whether a user identifier corresponding to a weighting coefficient equal to or smaller than the second coefficient value is stored. Specifically, the determination unit 308 determines whether or not the determination table stored in the storage unit 310 indicates determination information indicating a user identifier associated with a weighting coefficient equal to or smaller than the second coefficient value.

  The second coefficient value is a value less than the first coefficient value. The second coefficient value is “0”, for example. The second coefficient value is not limited to “0”, and may be “0.1”, for example.

  If YES in step S132A, the process proceeds to step S133A. On the other hand, if NO at step S132A, the process proceeds to step S135A described later.

  Here, it is assumed that the determination table stored in the storage unit 310 indicates determination information indicating a user identifier associated with a weighting coefficient equal to or smaller than the second coefficient value. That is, it is assumed that the user identifier corresponding to the weighting coefficient that is equal to or less than the second coefficient value less than the first coefficient value is stored in the storage unit 310.

  In this case, the determination unit 308 determines that the user specified by the user identifier stored in the storage unit 310 does not exist in the vicinity of the content search control device 304.

  That is, when the user specified by the user identifier indicated by the acquired evaluation information is not indicated in the picture obtained by shooting by the shooting unit 301, the determination unit 308 does not exist in the vicinity of the content search control device 304. Is determined.

  Here, it is assumed that the determination table stored in the storage unit 310 indicates determination information indicating a user identifier associated with a weight coefficient that is less than the first coefficient value and greater than the second coefficient value. That is, it is assumed that a user identifier associated with a weighting coefficient that is less than the first coefficient value and greater than the second coefficient value is stored in the storage unit 310.

  In this case, NO is determined in step S132A. In this case, the determination unit 308 may have a user specified by the user identifier corresponding to the weight coefficient that is less than the first coefficient value and greater than the second coefficient value in the vicinity of the content search control device 304. Judge that there is.

  In other words, the determination unit 308 stores the user identifier corresponding to the weighting coefficient that is less than the first coefficient value and greater than the second coefficient value in the storage unit 310. It is determined that there is a possibility that the user specified by the user identifier exists in the vicinity of the content search control device 304.

  In step S133A, the determination unit 308 deletes the user identifier corresponding to the weight coefficient. Specifically, in the determination table, the determination information indicating the user identifier associated with the weighting coefficient equal to or smaller than the second coefficient value is deleted from the determination table.

  For example, in the determination table T400 of FIG. 16, it is assumed that the value of the weighting factor indicated by the determination information with the number “2” is “0”. In this case, the determination information with the number “2” is deleted. That is, the user identifier indicated by the determination information with the number “2” is deleted.

  In step S134A, the erasure user identifier is transmitted to search instruction unit 309. The erased user identifier is a user identifier indicated by the erased determination information.

Then, the process proceeds to step S135A.
In step S135A, the determination unit 308 sets the value of the search flag to “1”.

  And this determination process A is complete | finished, it returns to the search control process A of FIG. 14, and a process transfers to step S200A.

In step S200A, search instruction processing A is performed by the search instruction unit 309.
FIG. 17 is a flowchart of the search instruction process A. In FIG. 17, the process with the same step number as the step number of FIG. 9 is the same as the process described in the first embodiment, and therefore detailed description will not be repeated.

  In step S210, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. If YES in step S210, the process proceeds to step S220. On the other hand, if NO in step S210, the search instruction process A ends, the process returns to the search control process A of FIG. 14, and the search control process A ends.

  The case of YES in step S210 is, for example, a case where there is a change in the presence / absence or configuration of the user who has been shot by the shooting unit 301 of the content reproduction apparatus 100.

  In step S220, the same processing as in the first embodiment is performed, and thus detailed description will not be repeated. If YES in step S220, the process proceeds to step S221. On the other hand, if NO at step S220, the process proceeds to step S230.

  In step S221, the same processing as that in the first embodiment is performed, and thus detailed description will not be repeated. Through this process, a playback stop instruction is transmitted to the content search unit 305.

  Similar to the first embodiment, the content search unit 305, when receiving the erased user identifier, stops the reproduction of the related content having the content file name associated with the received erased user identifier in the management table. A stop instruction is transmitted to the playback unit 307.

  In response to receiving the stop instruction, the playback unit 307 stops the playback of the related content specified by the stop instruction.

  In step S230, it is determined whether or not a plurality of user identifiers are stored in the storage unit 310. Specifically, the search instruction unit 309 determines whether the determination table stored in the storage unit 310 indicates a plurality of user identifiers respectively corresponding to a plurality of weighting factors.

  If YES in step S230, the process proceeds to step S231. On the other hand, if NO at step S230, the process proceeds to step S240 described later.

  In step S231, it is determined whether or not all weighting factors stored in the storage unit 310 are equal. Specifically, the search instruction unit 309 determines whether all the weighting factors indicated by the determination table stored in the storage unit 310 are equal.

  If YES in step S231, the process proceeds to step S240. On the other hand, if NO at step S231, the process proceeds to step S232.

  In step S232, the maximum weight coefficient is acquired, and the user identifier corresponding to the maximum weight coefficient is set as the user identifier to be transmitted. Here, the maximum weight coefficient is a weight coefficient indicating the maximum value among all weight coefficients respectively corresponding to all object identifiers indicated by the determination table.

  Specifically, the search instruction unit 309 reads out the determination information indicating the maximum weight coefficient among all the weight coefficients indicated by the determination table stored in the storage unit 310, whereby the maximum weight coefficient indicated by the determination information is obtained. To get.

  Also, the search instruction unit 309 sets the user identifier corresponding to the maximum weight coefficient as the user identifier to be transmitted.

  In step S233, a determination weight coefficient and a user identifier corresponding to the determination weight coefficient are acquired. Here, the determination weighting factor is a weighting factor other than the maximum weighting factor among all the weighting factors indicated by the determination table stored in the storage unit 310.

  Specifically, the search instruction unit 309 includes one determination weight coefficient and a user identifier corresponding to the determination weight coefficient among all the weight coefficients indicated by the determination table stored in the storage unit 310. Is obtained by reading When there are a plurality of determination weight coefficients, the acquired determination weight coefficient is, for example, a determination weight coefficient indicating the largest value. The obtained determination weight coefficient is not limited to the determination weight coefficient showing the largest value.

  In step S234, the search instruction unit 309 generates a random number using the acquired latest maximum weight coefficient. For example, when the value of the maximum weight coefficient is 100, the generated random number indicates one of 1 to 100. For example, when the value of the maximum weight coefficient is 30, the generated random number indicates any one of 1 to 30.

  In step S235, the search instruction unit 309 determines whether or not the acquired latest determination weight coefficient is larger than the generated random number. If YES in step S235, the process proceeds to step S236. On the other hand, if NO at step S235, the process proceeds to step S237 described later.

  In step S236, the search instruction unit 309 sets the latest user identifier acquired in step S233 as a transmission target user identifier. In this case, the acquired latest user identifier is a user identifier corresponding to a weighting factor larger than the random number.

  Through the processing in steps S235 and S236, a user identifier that does not correspond to the maximum weighting coefficient is set as a transmission target with a probability calculated by the formula (weighting coefficient for determination / maximum weighting coefficient).

  In step S237, the search instruction unit 309 determines whether all weighting factors indicated by the determination table have been acquired. If YES in step S237, the process proceeds to step S241. On the other hand, if NO at step S237, the process proceeds to step S238.

  In step S238, an unacquired weight coefficient and a user identifier corresponding to the unacquired weight coefficient are acquired from all the weight coefficients indicated by the determination table.

  Specifically, the search instruction unit 309 reads out the determination information indicating the unacquired weighting factor from all the weighting factors indicated by the determination table stored in the storage unit 310, thereby indicating the undetermined information indicated by the determination information. An acquisition weight coefficient and a user identifier corresponding to the unacquired weight coefficient are acquired. The acquired unacquired weighting factor is a determination weighting factor.

Then, the process of step S235 is performed again.
If NO in step S230 or YES in step S231, the process proceeds to step S240.

  In step S240, all user identifiers are set as transmission targets. Specifically, the search instruction unit 309 sets all user identifiers indicated by the determination table stored in the storage unit 310 as user identifiers to be transmitted.

  In step S241, user identifier transmission processing A is performed. In the user identifier transmission process A, the search instruction unit 309 transmits all user identifiers set as transmission targets to the content search unit 305 as search instructions.

  In step S242, the search instruction unit 309 cancels the transmission target setting for all user identifiers set as transmission targets.

  Then, the search instruction process A ends, the process returns to the search control process A of FIG. 14, and the search control process A ends.

  Note that the processing when the content search unit 305 receives the user identifier and the processing of the playback unit 307 are the same as those in the first embodiment, and thus detailed description will not be repeated.

Next, the search control process A in FIG. 14 will be described with a specific example.
Here, as an example, it is assumed that the collation unit 303 transmits the evaluation information table T300 of FIG. 13 to the content search control device 304. Further, it is assumed that the first threshold value and Wmax are “0.8” and “100”, respectively.

First, determination processing A of search control processing A in FIG. 14 is performed.
And the process of step S110 of FIG. 15 is performed. Then, the determination unit 308 sets the value of the check flag corresponding to each of the user identifiers “U01” and “U02” indicated by the received evaluation information table T300 to “0” (S110A).

  Thereafter, the determination unit 308 acquires the evaluation information of the number “1” in FIG. 13 (S111). At this point, since the user identifier “U01” indicated by the evaluation information with the number “1” is not stored in the storage unit 310 (NO in S111A), the process of step S121 is performed.

  The evaluation value indicated by the evaluation information with the number “1” is equal to or greater than the first threshold (YES in S121). Therefore, the process of step S123A is performed. Then, the determination unit 308 stores the user identifier “U01” indicated by the evaluation information with the number “1” in the storage unit 310 (S123A). Then, the determination unit 308 sets the value of the search flag to “1” (S124).

  Then, the determination unit 308 sets the value of the check flag corresponding to the user identifier “U01” to “1”, and sets the value of the weighting factor corresponding to the user identifier “U01” to 100 as the first coefficient value. Set (S124A).

  And after the process of step S125, S126 is performed, the determination part 308 acquires the evaluation information of the number "2" of FIG. 13 (S111). At this point, since the user identifier “U02” indicated by the evaluation information of the number “2” is not stored in the storage unit 310 (NO in S111A), the process of step S121 is performed.

  The evaluation value indicated by the evaluation information with the number “2” is equal to or greater than the first threshold (YES in S121). Therefore, the process of step S123A is performed. Then, the determination unit 308 stores the user identifier “U02” indicated by the evaluation information with the number “2” in the storage unit 310 (S123A).

  That is, when the determination unit 308 obtains k pieces of evaluation information respectively corresponding to different k (an integer greater than or equal to 2) users determined to exist, k users indicated by the k pieces of evaluation information respectively The identifier is stored in the storage unit 310.

Then, after step S124, step S124A is performed.
Then, the determination unit 308 sets the value of the check flag corresponding to the user identifier “U02” to “1”, and sets the value of the weighting factor corresponding to the user identifier “U02” to 100 as the first coefficient value. Set (S124A).

  That is, by repeatedly performing the process of step S124A, the determination unit 308 associates each of the k user identifiers with k (an integer greater than or equal to 2) user identifiers stored in the storage unit 310. The weighting coefficient to be set is set to the first coefficient value.

  And it determines with YES by step S125, and the process of step S130A is performed.

  At this point, the determination unit 308 determines that the user identifier associated with the check flag indicating “0” is not stored in the storage unit 310 (NO in S130A). Thereby, the determination process A ends.

  At this time, the user identifiers “U01” and “U02” are stored in the storage unit 310. The value of the search flag is “1”. At this time, the determination table stored in the storage unit 310 is the following determination table T400A.

FIG. 18 is a diagram illustrating a determination table T400A as an example.
Then, the search instruction process A in FIG. 17 is performed. In this case, YES is determined in the step S210, and the process of the step S220 is performed. Here, it is assumed that the erasure user identifier has not been received. In this case, NO is determined in step S220, and the process of step S230 is performed.

  And it determines with YES by step S230, determines with YES by step S231, and the process of step S240 is performed.

  Then, the search instruction unit 309 sets the user identifiers “U01” and “U02” as transmission targets (S240).

  The search instruction unit 309 transmits the user identifiers “U01” and “U02” set as transmission targets to the content search unit 305 as search instructions (S241). The search instruction unit 309 cancels the setting of the transmission target for the user identifiers “U01” and “U02” set as the transmission target (S242). Then, the search instruction process A ends, and the search control process A ends.

  Note that the processing when the content search unit 305 receives the user identifier and the processing of the playback unit 307 are the same as those in the first embodiment, and thus detailed description will not be repeated. Thereby, the related content is reproduced.

  Next, processing when the content search control device 304 sequentially receives different evaluation information tables will be described. Here, it is assumed that the first threshold value, Wmax, the second coefficient value, and the predetermined value dw are “0.8”, “100”, “0”, and “20”, respectively.

FIG. 19 is a diagram for explaining the change of the weighting factor with the passage of time.
Hereinafter, the user specified by the user identifier “U03” is referred to as a user U03.

  Here, at least one face of the users U01, U02, and U03 is photographed by the photographing unit 301, and the above-described matching process A is performed eight times, for example, so that content search control is performed at each of the times t1 to t8. Assume that the device 304 receives the evaluation information table. The content search control device 304 performs a search control process A every time it receives an evaluation information table.

  In FIG. 19, (Ux (number), y (integer)) indicates a user identifier Ux and an evaluation value y indicated by the evaluation information table. For example, the content search control device 304 receives an evaluation information table indicating evaluation information indicating the user identifier “U01” and the evaluation value “0.9” at time t1.

  In FIG. 19, for example, “U01 weight coefficient” indicates a weight coefficient corresponding to the user identifier “U01”. The same applies to “U02 weighting factor” and “U03 weighting factor”.

  The content search control device 304 uses the evaluation information shown in the evaluation information table received at time t1, and the search control processing A in FIG. 14 is performed, so that the user identifier “U01” and the weight coefficient “100” are obtained. Is stored in the storage unit 310.

  Then, when the content search unit 305 and the playback unit 307 perform the above-described processing, the content related to the user U01 is searched and the content is played back.

  At time t2, the content search control device 304 receives, for example, the evaluation information table T300 in FIG. In this case, the user identifiers “U01” and “U02” are stored in the storage unit 310 by performing the search control process A. Also, the determination table T400A of FIG.

  Then, when the content search unit 305 and the playback unit 307 perform the above-described processing, the content related to the users U01 and U02 is searched and the content is played back.

  At time t3, the evaluation value of the user U01 falls from “0.9” to “0.6”, but there is a state in which the user identifiers “U01” and “U02” are stored in the storage unit 310 of the content search control device 304. The content is not searched because it does not change.

  Here, it is assumed that the face of the user U01 is no longer photographed by the photographing unit 301 at time t4. Further, it is assumed that the face of the user U03 is photographed by the photographing unit 301 at time t4.

  In this case, the evaluation information table received by the content search control device 304 does not indicate the user identifier “U01” but indicates evaluation information indicating each of the user identifiers “U02” and “U03”.

  In this case, a user identifier “U03” is newly stored in the storage unit 310 by performing the search control process A. Further, the value of the weighting factor corresponding to the user identifier “U03” is set to “100”. Note that the user identifiers “U01” and “U02” are still stored in the storage unit 310.

  Further, in step S131A in FIG. 15, the determination unit 308 decreases the value of the weighting factor corresponding to the user identifier “U01” indicated by the determination table stored in the storage unit 310 by 20.

  That is, the determination unit 308 evaluates one user identifier “U02” among the user identifiers “U01” and “U02” during the period in which the user identifiers “U01” and “U02” are stored in the storage unit 310. Each time information is acquired, the weight coefficient corresponding to the user identifier “U01” other than the user identifier “U02” among the user identifiers “U01” and “U02” is decreased by a predetermined value.

  In other words, the determination unit 308 includes m (1 ≦ m <k) user identifiers among k user identifiers in a period in which k (an integer greater than or equal to 2) user identifiers are stored in the storage unit 310. Each time the evaluation information indicating each of the user IDs is acquired, the weight coefficient corresponding to the user identifiers other than the m user identifiers among the k user identifiers is decreased by a predetermined value.

  That is, the determination unit 308 sets a weighting coefficient every time evaluation information indicating a user identifier other than the user identifier stored in the storage unit 310 is acquired in a period in which the user identifier is stored in the storage unit 310. Decrease by the value of.

  At this time, the user identifier “U01” corresponding to the weight coefficient “80” that is less than the first coefficient value (100) and greater than the second coefficient value (0) is stored in the storage unit 310. .

  In this case, NO is determined in step S132A. In this case, the determination unit 308 has a user U01 specified by the user identifier “U01” corresponding to the weighting coefficient that is less than the first coefficient value and greater than the second coefficient value in the vicinity of the content search control device 304. It is determined that there is a possibility of

  In this case, YES is determined in step S230, NO is determined in step S231, and the process of step S232 is performed.

  Further, the maximum weight coefficient “100” corresponding to each of the user identifiers “U02” and “U03” is acquired by the process of step S232. Also, user identifiers “U02” and “U03” corresponding to the maximum weight coefficient “100” are set as user identifiers to be transmitted.

  Then, the determination weight coefficient “80” and the user identifier “U01” are acquired by the process of step S233. As an example, it is assumed that a random number “50” is generated by the process of step S234.

  In this case, YES is determined in the step S235, and the process of the step S236 is performed. With this process, the user identifier “U01” corresponding to a weighting factor larger than the random number is set as the user identifier to be transmitted. And it determines with YES by step S237, and the process of step S241 is performed.

  In this case, when a weighting factor other than the maximum weighting factor among k weighting factors is larger than a random number, the search instruction unit 309 includes a user identifier corresponding to the weighting factor larger than the random number and a user identifier corresponding to the maximum weighting factor. Are transmitted to the content search unit 305 as a content search device.

  Then, when the content search unit 305 and the playback unit 307 perform the above-described processing, content related to the users U01, U02, and U03 is searched, and the content is played back.

  Then, at each of the times t5, t6, t7, and t8, as in the case of the time t4, the weight coefficient corresponding to the user identifier “U01” is decreased by “20”. Thus, the search control process A using the evaluation information table received at time t8 is performed, so that the weighting coefficient corresponding to the user identifier “U01” becomes “0”.

  In this case, YES is determined in step S132A of FIG. In this case, the determination unit 308 determines that the user U01 specified by the user identifier “U01” stored in the storage unit 310 does not exist in the vicinity of the content search control device 304.

Then, the process of step S133A is performed.
In this case, the determination unit 308 deletes the user identifier “U01” stored in the storage unit 310 (S133A). Then, the determination unit 308 transmits the erased user identifier “U01” to the search instruction unit 309 (S134A).

  In this case, YES is determined in the step S220, and the process of the step S221 is performed.

  In this case, the search instruction unit 309 transmits a reproduction stop instruction indicating the erasure user identifier “U01” to the content search unit 305.

  In this case, the content search unit 305 transmits to the playback unit 307 a stop instruction for stopping the playback of the related content with the content file name associated with the received erased user identifier “U01” in the management table.

  In response to receiving the stop instruction, the playback unit 307 stops the playback of the related content specified by the stop instruction.

  As described above, according to the present embodiment, the content search control device 304 is caused by a change in the surrounding environment of the user or a user's movement. Even if it is determined that the user does not exist in the vicinity of the content search control device 304, the playback unit 307 does not immediately stop the playback of the content related to the user that is determined not to exist.

  Then, the content search control device 304 gradually reduces the weighting factor corresponding to the user identifier, and reproduces the related content according to the weighting factor.

  Therefore, it is possible to prevent a situation in which the reproduction of content related to the user is suddenly stopped and confused even though the user exists in the vicinity of the content reproduction device 100 (content search control device 304). .

  In addition, as a result of the above processing, in the present embodiment, as in the first embodiment, even when the user's recognition state as an object is unstable, the content related to the user is normally displayed. It can be realized to be searched. Therefore, even when the recognition state of a user as an object is unstable, related content related to the user can be stably reproduced.

  Note that the content search unit 305 in the present embodiment may perform the related content search process A described in the second embodiment.

Thereby, also in this embodiment, the same effect as in the second embodiment can be obtained.
In the first to third embodiments, the content search control device 304 and other units are included in one content playback device 100, but the present invention is not limited to this. The content search control device 304 and other units may be mounted on a plurality of devices.

  For example, the content server and the playback device may be connected via a network. The content server includes, for example, an imaging unit corresponding to one or more cameras, a face detection unit, a collation unit, a content search control device, a content search unit, and a storage unit.

The playback device is, for example, a television, a mobile phone, a digital photo frame, or the like.
In this case, the content server acquires facial feature amount information from the imaging unit via the network, performs user verification and search for content related to the user, and transmits the search result to the playback device. In this way, the content may be reproduced.

  In the first to third embodiments, content related to the user is reproduced by detecting and collating a human face, but the present invention is not limited to this. For example, content related to an object or a user may be reproduced by detecting and collating a general object (such as a pet or a tool) instead of the user.

  In the first to third embodiments, the content search unit 305 searches for content corresponding to all received user identifiers, but is not limited thereto. For example, the content search unit 305 may search only content corresponding to a part of all received user identifiers. Moreover, it is good also considering the combination of both of these content search methods as a search result.

  In the first to third embodiments, the presence / absence of the user is determined by performing human detection / collation using an image. However, the present invention is not limited to this. For example, the user may be detected and collated by voice uttered by the user.

  In this case, a voiceprint database is used instead of the face feature database described above. The voiceprint database indicates, for example, voiceprint data indicating each voiceprint of a plurality of users.

  A microphone is connected to the verification unit 303. The microphone transmits voice data uttered by the user to the matching unit 303.

  And the collation part 303 performs the collation process N whenever it receives audio | voice data. That is, the collation process N may be performed instead of the collation process or the collation process A described above.

  In the verification process N, the verification unit 303 generates voiceprint data by performing frequency analysis on the received voice. Then, the collation unit 303 calculates the similarity (evaluation value) between the generated voiceprint data and each of the plurality of voiceprint data indicated by the voiceprint database.

  That is, the collation process N is a recognition process for obtaining an evaluation value by comparing voice data uttered by the user with a plurality of voice data registered in advance.

  As described above, the content reproduction apparatus 100 or the content search control apparatus 304 according to the present invention has been described based on the embodiments. However, the present invention is not limited to these embodiments. Unless it deviates from the meaning of this invention, the form which carried out various deformation | transformation which those skilled in the art can think to this embodiment, or the structure constructed | assembled combining the component in different embodiment is also contained in the scope of the present invention. .

  Further, all or some of the plurality of constituent elements constituting the content reproduction apparatus 100 or the content search control apparatus 304 may be configured by hardware. Further, all or some of the components constituting the content reproduction apparatus 100 or the content search control apparatus 304 may be a module of a program executed by a CPU (Central Processing Unit) or the like.

  Further, all or some of the plurality of constituent elements constituting the content reproduction apparatus 100 or the content search control apparatus 304 may be configured by a single LSI (Large Scale Integration). An LSI is a super-functional LSI manufactured by integrating a plurality of components on a single chip. Specifically, a microprocessor, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like are included. Consists of including.

  Here, although expressed as LSI, depending on the difference in circuit integration, it may be referred to as IC (Integrated Circuit), system LSI, super LSI, or ultra LSI.

  Further, the method of circuit integration is not limited to LSI, and circuit integration may be performed with a dedicated circuit or a general-purpose processor. Also, an FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.

  Alternatively, the calculation of these functional blocks can be performed using, for example, a DSP (Digital Signal Processor) or a CPU (Central Processing Unit). Further, these processing steps can be processed by being recorded on a recording medium as a program and executed.

  Further, if integrated circuit technology that replaces LSI appears as a result of the advancement of semiconductor technology or a derivative other technology, it is naturally also possible to integrate function blocks using this technology. Biotechnology can be applied as a possibility.

  For example, in FIG. 3, the determination unit 308, the search instruction unit 309, and the storage unit 310 may be configured from one system LSI. That is, the content search control device 304 may be an integrated circuit.

  In addition, the present invention may be realized as a content search control method in which the operation of characteristic components included in the content reproduction device 100 or the content search control device 304 is a step. The present invention may be realized as a content search control program that causes a computer to execute each step included in such a content search control method. Further, the present invention may be realized as a computer-readable recording medium that stores such a content search control program. The program may be distributed via a transmission medium such as the Internet.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

  INDUSTRIAL APPLICABILITY The present invention can be used as a content search control device that can realize that content related to an object is normally searched even when the recognition state of the object is unstable.

100 Content Playback Device 101 Camera 103 Liquid Crystal Display 105 Touch Panel 107 Speaker 109 Memory Card Slot 111 CPU
112 ROM
113 RAM
114 Internal memory 301 Imaging unit 302 Face detection unit 303 Collation unit 304 Content search control device 305 Content search unit 306 Content storage unit 307 Playback unit

Claims (14)

An evaluation value that is a similarity between the feature data indicating the feature of the object and the feature data indicating the feature of the registered object registered in advance in the recognition process for recognizing the object, and the object that identifies the object A content search control apparatus for sequentially obtaining evaluation information indicating an identifier,
The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier,
The content search control device includes:
Each time evaluation information is acquired, it is determined whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, may exist, or does not exist A determination unit;
A storage unit,
In the case where it is determined that the object specified by the object identifier indicated by the acquired evaluation information is present in the vicinity of the content search control device, the determination unit further includes an object identifier that specifies the object determined to be present Storing in the storage unit,
The determination unit further erases the stored object identifier when it is determined that there is no object specified by the stored object identifier after the object identifier is stored in the storage unit. ,
If it is determined that the object specified by the stored object identifier exists or may exist, the stored object identifier continues to be stored in the storage unit,
The content search control device further includes:
During the period when the object identifier is stored in the storage unit, the stored object identifier is transmitted to the content search device, and no object identifier other than the stored object identifier is transmitted to the content search device. With a search instruction unit,
Content search control device. When the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is the content search control device It is determined that it exists in the vicinity,
In the case where an object identifier is stored in the storage unit, the determination unit has a newly acquired evaluation value indicated by the evaluation information indicating the stored object identifier is less than the first threshold value, And when it is larger than the second threshold value less than the first threshold value, it is determined that there is a possibility that the object specified by the stored object identifier exists in the vicinity of the content search control device,
In the case where an object identifier is stored in the storage unit, the determination unit has a newly acquired evaluation value indicated by the evaluation information indicating the stored object identifier is equal to or less than the second threshold value Determining that the object specified by the stored object identifier does not exist in the vicinity of the content search control device;
The content search control apparatus according to claim 1. When the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is the content search control device Determine that it is in the vicinity,
The content search control apparatus according to claim 1. The determination unit further sets, when an object identifier is stored in the storage unit, a weighting coefficient associated with the stored object identifier as a first coefficient value,
The weight coefficient is a coefficient for determining whether or not to delete the object identifier stored in the storage unit,
The determination unit further sets the weighting coefficient to a predetermined value every time evaluation information indicating an object identifier other than the stored object identifier is acquired in a period in which the object identifier is stored in the storage unit. Only decrease and
The determination unit further includes an object specified by the stored object identifier in the vicinity of the content search control device when the weighting coefficient is less than or equal to a second coefficient value less than the first coefficient value. Decide not to,
The content search control apparatus according to claim 1 or 3. When the evaluation value indicated by the acquired evaluation information is greater than or equal to a predetermined first threshold, the determination unit determines that the object specified by the object identifier indicated by the acquired evaluation information is the content search control device It is determined that it exists in the vicinity,
When the determination unit obtains k pieces of evaluation information respectively corresponding to different k (an integer greater than or equal to 2) objects determined to exist, the k pieces of object identifiers indicated by the k pieces of evaluation information are obtained. Storing in the storage unit,
The determination unit further sets a weighting coefficient associated with each of the k object identifiers to a first coefficient value when the k object identifiers are stored in the storage unit,
The weight coefficient is a coefficient for determining whether or not to delete the object identifier stored in the storage unit,
The determination unit further evaluates each of m (1 ≦ m <k) object identifiers out of the k object identifiers in a period in which the k object identifiers are stored in the storage unit. Each time information is acquired, a weighting factor corresponding to an object identifier other than the m object identifiers among the k object identifiers is decreased by a predetermined value,
In the case where an object identifier corresponding to a weighting coefficient that is less than or equal to a second coefficient value less than the first coefficient value is stored in the storage unit, the determination unit is an object specified by the stored object identifier Is not present in the vicinity of the content search control device, and the stored object identifier is deleted.
The content search control apparatus according to claim 1 or 3. Further, when a plurality of object identifiers are stored in the storage unit, the search instruction unit uses a maximum weight coefficient indicating a maximum value among a plurality of weight coefficients respectively corresponding to the plurality of object identifiers. Generate random numbers,
The search instruction unit, when a weight coefficient other than the maximum weight coefficient among the plurality of weight coefficients is larger than the random number, an object identifier corresponding to the weight coefficient larger than the random number, and an object identifier corresponding to the maximum weight coefficient To the content search device,
The content search control apparatus according to claim 5. The determination unit is specified by the stored object identifier when an object identifier corresponding to a weight coefficient that is less than the first coefficient value and greater than the second coefficient value is stored in the storage unit. It is determined that there is a possibility that the object to be present exists in the vicinity of the content search control device,
The content search control apparatus according to any one of claims 4 to 6. The object is a user indicated by a picture obtained by shooting,
The determination unit determines that the user does not exist in the vicinity of the content search control device when the user specified by the object identifier indicated by the acquired evaluation information is not indicated in the picture obtained by the shooting,
The recognition process is a process of obtaining the evaluation value by comparing face feature data indicating a facial feature of the user indicated by the picture with a plurality of face feature data registered in advance.
The content search control apparatus according to any one of claims 1 to 7. The object is a user;
The recognition process is a process for obtaining the evaluation value by comparing voice data emitted by the user with a plurality of voice data registered in advance.
The content search control apparatus according to any one of claims 1 to 7. A content reproduction device including the content search control device according to any one of claims 1 to 9,
The content playback device further includes:
The content search device;
A content storage unit for storing a plurality of contents respectively associated with the plurality of registered objects;
A playback unit for playing back content,
A private attribute value indicating private is associated with at least one of the plurality of contents,
When the determination unit of the content search control device acquires k pieces of evaluation information respectively corresponding to different k (integer of 2 or more) objects determined to exist in the vicinity of the content search control device, storing k object identifiers respectively indicated by k evaluation information in the storage unit of the content search control device;
The search instruction unit, when the determination unit stores the k object identifiers, transmits the k object identifiers to the content search device;
The content search device includes content specifying information for specifying content not associated with a private attribute value among a plurality of contents stored in the content storage unit related to the received k object identifiers. Send it to the playback unit,
The reproduction unit reproduces content stored in the content storage unit identified by the content identification information;
Content playback device. An evaluation value that is a similarity between the feature data indicating the feature of the object and the feature data indicating the feature of the registered object registered in advance in the recognition process for recognizing the object, and the object that identifies the object An integrated circuit for sequentially obtaining evaluation information indicating an identifier,
The integrated circuit communicates with a content retrieval device that retrieves content related to an object specified by the object identifier by receiving the object identifier;
The integrated circuit comprises:
A determination unit that determines whether the object specified by the object identifier indicated by the acquired evaluation information is present in the vicinity of the integrated circuit, and may or may not exist each time evaluation information is acquired When,
A storage unit,
The determination unit further stores, when it is determined that an object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the integrated circuit, an object identifier that specifies the object determined to exist To remember
The determination unit further erases the stored object identifier when it is determined that there is no object specified by the stored object identifier after the object identifier is stored in the storage unit. ,
If it is determined that the object specified by the stored object identifier exists or may exist, the stored object identifier continues to be stored in the storage unit,
The integrated circuit further includes:
During the period when the object identifier is stored in the storage unit, the stored object identifier is transmitted to the content search device, and no object identifier other than the stored object identifier is transmitted to the content search device. An integrated circuit including a search instruction unit. An evaluation value that is a similarity between the feature data indicating the feature of the object and the feature data indicating the feature of the registered object registered in advance in the recognition process for recognizing the object, and the object that identifies the object A content search control method performed by a content search control device that sequentially obtains evaluation information indicating an identifier,
The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier,
The content search control device includes:
Each time evaluation information is acquired, it is determined whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, may exist, or does not exist A determination unit;
A storage unit,
The content search control method includes:
A step of storing, in the storage unit, an object identifier that identifies an object that is determined to exist when it is determined that an object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device When,
And after the object identifier is stored in the storage unit, if it is determined that there is no object specified by the stored object identifier, the stored object identifier is deleted,
If it is determined that the object specified by the stored object identifier exists or may exist, the stored object identifier continues to be stored in the storage unit,
The content search control method further includes:
During the period when the object identifier is stored in the storage unit, the stored object identifier is transmitted to the content search device, and no object identifier other than the stored object identifier is transmitted to the content search device. A content search control method comprising steps. An evaluation value that is a similarity between the feature data indicating the feature of the object and the feature data indicating the feature of the registered object registered in advance in the recognition process for recognizing the object, and the object that identifies the object A content search control program executed by a content search control device that sequentially obtains evaluation information indicating identifiers,
The content search control device communicates with a content search device that searches for content related to the object specified by the object identifier by receiving the object identifier,
The content search control device includes:
Each time evaluation information is acquired, it is determined whether the object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device, may exist, or does not exist A determination unit;
A storage unit,
The content search control program includes:
A step of storing, in the storage unit, an object identifier that identifies an object that is determined to exist when it is determined that an object specified by the object identifier indicated by the acquired evaluation information exists in the vicinity of the content search control device When,
And after the object identifier is stored in the storage unit, if it is determined that there is no object specified by the stored object identifier, the stored object identifier is deleted,
If it is determined that the object specified by the stored object identifier exists or may exist, the stored object identifier continues to be stored in the storage unit,
The content search control program further includes:
During the period when the object identifier is stored in the storage unit, the stored object identifier is transmitted to the content search device, and no object identifier other than the stored object identifier is transmitted to the content search device. A content search control program comprising steps. A computer-readable recording medium for recording the content search control program according to claim 13.

Images