JP5775837B2 - Interest degree estimation apparatus, method and program - Google Patents

Description

  The present invention relates to an interest level estimation apparatus, method, and program for estimating a user's level of interest in viewing content.

  In recent years, television program recorders and the like equipped with a function of recommending a television program suitable for a user using a viewing history and a recording history have been commercialized. However, with existing devices, it is not possible to distinguish whether the user was watching the program with interest or simply watching it while watching it. For this reason, there is a problem that a program that the user has watched with interest and a program that is “watched while watching” are determined to have the same degree of interest, and the recommendation accuracy for the program is reduced.

  Therefore, by monitoring the selection operation of the program by the user, collecting the operation log, analyzing this operation log, setting the search parameter for searching the video that the user is interested in, this search There has been proposed a technique for acquiring a video that is estimated to be of interest to a user by searching for a video using parameters (see, for example, Patent Document 1).

JP 2009-302985 A

  However, in the technique described in Patent Document 1, when the user continues to watch the next program that automatically starts after the end of viewing one program, the user can select the program even if the user is interested in the program. No operations are performed. For this reason, it is difficult to accurately estimate the degree of interest of the user with only the operation log of the user.

  The present invention has been made paying attention to the above circumstances, and an object of the present invention is to provide an interest level estimation device, method, and program capable of more accurately estimating the degree of interest of a user with respect to viewing content. It is in.

  In order to achieve the above object, one aspect of the present invention provides the following means. That is, when watching a content such as a television program, if there is a scary scene, an interesting scene, or the like, a change in biological information such as an increase in pulse or an increase in sweating appears to the user. On the other hand, as one of the Web services, a blog service that provides live commentary on television programs is being provided, but if there are scary scenes or interesting scenes in a television program, the viewing user will receive the timing at that time. There is a tendency for the number of posts to increase instantaneously. Therefore, when a user is watching a television program, there is a high possibility that the change timing of the user's biometric information and the change timing of the number of posts on the blog are synchronized.

Therefore, to calculate the change characteristics by receiving a number of time-of-day post information the user has been paired actually post viewed content from a server apparatus that provides the blog service, the user from the biological information detection apparatus The biometric information is received and its change characteristic is calculated. Then, a change characteristic whose change timing is synchronized with each other is extracted from the calculated number of posts and each change characteristic of biological information, and the degree of interest of the user with respect to the content is calculated from the appearance degree of the change characteristic to be synchronized. It is a thing.

  By doing so, it becomes possible to estimate the user's interest in the content without depending on the user's operation log for the content, for example. For this reason, even when the user is interested in the program, even if the user is interested in the program, such as when the user continues to watch the next program that starts automatically after the end of viewing one program, It becomes possible to estimate the degree of interest of the user more accurately.

One aspect of the present invention is characterized by comprising the following aspects.
In the first aspect, a period in which the user does not exist in the viewable range of the content display device is obtained from the reception quality of the signal transmitted from the biological information detection device, and the biological information detected in the non-existing period is changed. Are excluded from the calculation target.
In this way, in the content display operation period, for example, when the user has temporarily moved to another room or the like and cannot substantially view the content, the biological information detected during this period Is excluded from the interest level calculation target, so that the interest level can be estimated more accurately.

In the second aspect, when calculating the change characteristics of the posted information and the biological information, the change direction of each information value obtained at two adjacent timings is represented by a cosine value, thereby calculating the cosine of each information value. The similarity is calculated, and the calculated cosine similarity is used as the change amount of the posted information and the biological information between the two adjacent timings.
If it does in this way, the change of the biometric information between each timing can be expressed using the parameter | index called cosine similarity. By using the cosine similarity, it is possible to detect a fine change as a smaller value and a large change as a larger value. Therefore, it is possible to reduce the influence of noise caused by the detection accuracy of the biological information detection device and the surrounding environment.

  That is, according to one aspect of the present invention, it is possible to provide an interest level estimation device, method, and program capable of more accurately estimating the degree of interest of a user with respect to viewing content.

The figure which shows the example in case the change timing of biometric information used for description of the principle of this invention and the change timing of the number of contribution to a microblog correspond. The figure which shows the example of calculation of the biometric information variation | change_quantity using cosine similarity used for principle explanation of this invention. The figure which shows an example of the synchronization determination result based on the change timing of the biometric information used based on the principle of this invention, and the change timing of the number of contributions to a microblog. The block diagram which shows the function structure of the biometric information acquisition apparatus used with the interest degree estimation apparatus concerning this Embodiment and this interest degree estimation apparatus. The block diagram which shows the more specific structure of the biometric information acquisition apparatus used with the interest degree estimation apparatus concerning this Embodiment and this interest degree estimation apparatus. The figure which shows an example of the viewing-and-listening program information acquired from TV function part in the interest degree estimation apparatus shown in FIG.4 and FIG.5. The figure which shows an example of the information showing the reception intensity | strength of the electromagnetic wave transmitted from a biometric information acquisition apparatus. The figure which shows an example of the biometric information detected by the biometric information acquisition apparatus. The figure which shows an example of the posting information acquired from the microblog service server. The figure which shows an example of the interest degree calculated for every viewing-and-listening program about each user. The flowchart which shows the whole process sequence and process content of the interest degree estimation apparatus shown in FIG.4 and FIG.5. The flowchart which shows the process sequence and process content of an interest degree calculation process among the whole flowcharts shown in FIG.

[principle]
First, the principle of the present invention will be described.
As described above, if there is a scary scene or an interesting scene while the user is watching a television program, changes in biological information such as an increase in pulse and an increase in sweating amount appear. On the other hand, in microblogging services where users can view their opinions while watching television programs, when there are scary scenes or interesting scenes, the number of posts from viewers tends to increase instantaneously at that timing. is there. Therefore, if the user is viewing such a scene, there is a high possibility that the change timing of the user's biometric information is synchronized with the change timing of the number of posts to the microblog.

Figure 1 is a graph showing the variation of the biological information UserA (e.g. pulse, etc.), an example of the relationship between the posts of the amount of change in the target program in the micro blogs. As shown in the figure, when a user is watching a television program with interest, it is expected that synchronization occurs between the change in biometric information and the change in the number of posts. That is, the information indicating the presence / absence of synchronization is a criterion for determining whether or not the user has watched a certain television program with interest. Therefore, by using the information indicating the presence / absence of synchronization, it is determined whether the user is watching the television program with interest or the so-called “watching” while reading or doing housework. It becomes possible.

  Further, in order to further improve the estimation accuracy of the degree of interest of the user with respect to the television program, the following device can be considered. That is, two factors, whether the power of the television receiver is turned on and whether the user is close to the television receiver, are also added to the criterion. By using information on whether or not the power of the television receiver is turned on, it is possible to determine whether or not the user is watching a television program at that time. In the first place, it is not possible to watch a television program unless the television receiver is turned on, so it is possible to eliminate the tuning detected during the time when the television receiver is not turned on. Become.

  Further, by using information indicating whether or not the user is close to the television receiver, whether or not the user is at a position where the user can view the television receiver, for example, a television receiver is installed. It is possible to determine whether there is a user in the room. Even if the power of the television receiver is turned on, it is synonymous with not viewing unless a user is in a position where the television program can be viewed. Therefore, by further considering the information as to whether or not the user is in a position where the user can view the television receiver, the user can select from the tuning detected during the time period when the television receiver is turned on. It is possible to eliminate the tuning detected during the time period when the television receiver was not viewed.

The embodiment of the present invention focuses on the points described above, and determines that the user is interested in watching a television program when the following three conditions are met, that is, the degree of interest is greater than zero. To do.
(1) The change timing of biometric information is synchronized with the change timing of the number of posts.
(2) The television receiver is turned on.
(3) The user is in a position where a television program can be viewed.

  By the way, in order to detect the synchronization between the change in the biological information and the change in the number of posts, it is necessary to calculate the amount of change in the biological information and the amount of change in the number of posts. For example, a method applying cosine similarity is used to calculate the amount of change. Cosine similarity is a technique for calculating the similarity between two data using a cosine value. Cosine similarity takes a value in the range of −1 to 1, and the closer to 1, the two data are considered to be similar. By using the Cosine similarity, it is possible to make fine changes to smaller values and large changes to larger values. That is, it is possible to reduce the influence of noise caused by the accuracy of a sensor that acquires biological information such as a pulse and the surrounding environment.

For example, it is assumed that the pulse rates at time t-1 and time t are values as shown in FIG. At this time, if the angle formed by the pulse rate at time t-1 and the pulse rate at time t is θt, θt is as shown in FIG. That is, the similarity sim (t) between the pulse rate at time t and the pulse rate at time t−1 can be expressed by the following equation.
sim (t) = cos (θt)

When the angle θ as shown in FIG. 2 is taken, the range of values that θ can take is from −π / 2 to π / 2. Therefore, the range of values that the similarity sim (t) can take is 0 to 1. The value to be calculated is a change amount, and “similar” is equivalent to “no change”. From the above two things, if the change amount is obtained by subtracting 1 from the value of the similarity sim (t), the smaller the change, the closer to 0, and the greater the change, the closer to 1. Therefore, the amount of change var (t) at time t can be expressed by the following equation.
var (t) = 1-sim (t)

  If the amount of change var (t) is 0 for a value less than a certain threshold and 1 for a value greater than the threshold, the graph shown in FIG. 3 is obtained. When the amount of change in biometric information and the amount of change in the number of posts in the microblog are compared in such a graph, the timing at which the change timings coincide is set as the synchronization start time of the change amount. The synchronized time period continues until no change in biological information is detected. In the example of FIG. 3, the three described sections are time zones in which changes in biometric information are synchronized with changes in the number of posts, and the number of tunings is three.

Next, the degree of interest in the television program that the user was watching is calculated using the calculated number of tunings and the amount of change in the number of posts in the microblog. Count the number of times the change in the number of posts in the microblog exceeds the threshold during the time period when the user was watching the television program, and record the number of times (hereinafter referred to as the number of excitement). The degree of interest is calculated by using the probability of how many times the tuning has occurred among the number of climaxes. For example, the following formula is used.
The degree of interest = number of times of tuning / number of times of climax. It is possible to estimate the user's degree of interest in the viewing program.

  In the above description, the amount of change is calculated using only the data before time t and one sampling timing t−1. However, in order to have stronger noise resistance, data before n sampling timing is used. The amount of change may be calculated. For example, when n = 5, the average value of var (t-4), var (t-3), var (t-2), var (t-1), and var (t) is The amount of change at time t. That is, the amount of change at time t is calculated using the following equation.

ここで、ωk は時刻ｋにおける加重値であり、その取りうる範囲を０≦ωt ≦１とすることで、もともとの変化量が取りうる範囲を変えずに加重をかけることが可能となる。また、上記説明では生体情報（脈拍）を例にして述べたが、マイクロブログの投稿数も同様の式を用いてその変化量を算出する。

Here, ωk is a weighted value at time k, and by setting the range that can be taken as 0 ≦ ωt ≦ 1, it is possible to apply the weight without changing the range that the original change amount can take. In the above description, biometric information (pulse) has been described as an example, but the amount of change in the number of microblog posts is also calculated using the same formula.

[Embodiment]
Embodiments according to the present invention will be described below with reference to the drawings.
(Functional configuration of the device)
FIG. 4 is a block diagram illustrating the functional configuration of the interest level estimation apparatus according to the embodiment of the present invention, together with the functional configuration of the biological information acquisition apparatus used together with the interest level estimation apparatus.
The interest level estimation apparatus according to this embodiment includes a recording unit 102, an interest level calculation unit 103, a proximity wireless module 115, an input / output interface 117, a communication interface 118, and a timer 121. Reference numeral 101 denotes a television function unit (also referred to as a TV function unit or a TV function unit), which displays video content received from a broadcasting station or website or input from an external device such as a video recorder. It has a function for displaying.

  The timer 121 performs a time measuring operation at a plurality of preset periods, and a calculation start trigger given to the interest degree calculation unit 103 and a measurement trigger given to the proximity wireless module 115 at time intervals defined by these periods. And an acquisition start trigger to be given to the communication interface 118, respectively.

  The proximity wireless module 115 has a function of performing a data transmission / reception operation for acquiring the biological information of the user with the biological information acquisition device 200 and a function of detecting the reception intensity of the radio wave transmitted from the biological information acquisition device 200. Have.

  The communication interface 118 has a function of receiving post information on a broadcast program from the microblog service server 300 by accessing the microblog service server 300 via the communication network 400.

  The recording unit 102 records various data necessary for calculating the degree of user interest in the broadcast program. The recorded data includes viewing program information output from the television function unit 101 and television reception. Machine power information, user biometric information acquired by the proximity wireless module 115 or the input / output interface 117, radio wave intensity information detected by the proximity wireless module 115, and post information received by the communication interface 118 There is.

  The degree-of-interest calculation unit 103 is activated when a calculation start trigger is given from the timer 121, reads various data recorded at the broadcast time for each broadcast program viewed by the user from the recording unit 102, and reads the data. In addition, based on the various data, it has a function of calculating a value indicating how much interest the user has viewed each broadcast program.

On the other hand, the biological information acquisition device 200 includes a pulse sensor 201, a recording unit 202, a proximity wireless module 215, an input / output interface 217, and a timer 221.
The timer 221 performs a time measuring operation at a preset period, and gives a biological information acquisition start trigger to the pulse sensor 201. The pulse sensor 201 is activated by a biological information acquisition start trigger given from the timer 221 and detects the user's pulse.

  The recording unit 202 records the count value of the pulse detected by the pulse sensor 201, reads out untransmitted biological information from the recording unit 202 at a preset time interval, and outputs it to the proximity wireless module 215. Then, it has a function of deleting the read biometric information from the storage unit 202 after the output is completed.

  The proximity wireless module 215 has a function of transmitting the biological information read from the recording unit 202 to the interest level estimation device 100. The proximity wireless module 215 also has a function of transmitting radio waves continuously or intermittently while the biological information acquisition apparatus 200 is operating. This transmitted radio wave is used for the interest degree estimating apparatus 100 to measure the reception intensity of the radio wave transmitted from the biological information acquiring apparatus 200.

(Specific configuration of equipment)
FIG. 5 is a block diagram showing a specific configuration for realizing the functions of the interest level estimation device and the biological information acquisition device described above.
Here, the case where the function of the interest degree estimation device 100 is provided in the television receiver and the function of the biological information acquisition device is provided in the remote controller of the television receiver will be described as an example. The interest level estimation device can be provided in a video recorder, a set top box, or a personal computer, and the biometric information acquisition device is for viewing 3D video in addition to the remote controller (remote controller) of the television receiver. It can also be provided on glasses or the like.

  The television receiver 1 includes a central processing unit (CPU; Control Processing Unit) 111, and a television function unit 101, a program memory 113, a data memory 114, and a proximity wireless communication via a bus 112 to the CPU 111. The module 115, the timer interface 120, the input / output interface 117, and the communication interface 118 are connected.

  The close proximity wireless module 115 includes a wireless interface that adopts a short-range wireless data communication standard such as Bluetooth (registered trademark), for example, and acquires the user's biological information from the biological information acquisition device 200 according to a communication protocol defined by the wireless interface. Data transmission / reception operation is performed. At the same time, whenever a measurement start trigger is given from the timer 121, the reception intensity of the radio wave transmitted from the biological information acquisition apparatus 200 is detected.

  The input / output interface 117 has, for example, a function of receiving an infrared signal transmitted from a remote controller of a television receiver, a connection terminal of a wired signal cable represented by a USB (Universal Serial Bus) cable, or a slot of a memory card. Prepare. The input / output interface 117 can be used as an alternative interface when capturing biological information from the biological information acquisition apparatus 200 without using the proximity wireless module 115.

  The communication interface 118 has a function for accessing a Web site on the Internet such as a Web browser. By accessing the microblog service server 300 on the Web via the communication network 400, the communication interface 118 is provided. Post information on the broadcast program is received from the service server 300.

  The data memory 114 includes a viewing program information recording area 1141, a radio wave intensity information storage area 1142, a biological information storage area 1143, and a posted information recording area 1144 as data storage areas necessary for carrying out the present embodiment. An interest degree information storage area 1145 is provided.

  In the viewing program information recording area 1141, viewing program information representing the viewing history of the broadcasted program displayed on the display in the television function unit 101 is recorded. The viewing program information includes, for example, as shown in FIG. 6, the identification information (program ID) of a broadcasted program that associates the name of the station that broadcasts the program with the broadcast start time and broadcast end time.

  In the radio field intensity information storage area 1142, the radio field intensity information detected by the close proximity wireless module 115 is recorded. For example, as shown in FIG. 7, the radio wave intensity information is obtained by associating identification information (biological information acquisition apparatus ID) of the biological information acquisition apparatus 200 with a value [dB] indicating the detected radio wave intensity with respect to the detection time. Become.

  In the biological information storage area 1143, the biological information received by the proximity wireless module 115 is recorded. For example, as illustrated in FIG. 8, the biometric information includes identification information (biological information acquisition apparatus ID) of the biometric information acquisition apparatus 200, information indicating the type of biometric information (for example, pulse), and a biometric information value ( (Pulse rate).

  Post information acquired from the microblog service server 300 is recorded in the post information recording area 1144. For example, the posted information is formed by associating broadcast program identification information (program ID) with information indicating the number of posts for each time set at a fixed time interval as shown in FIG.

  In the interest degree information storage area 1145, interest degree information calculated by an interest degree calculation program described later is recorded. For example, as shown in FIG. 10, the interest degree information is formed by associating a user ID with the ID of the viewed program and the calculated value of the user interest degree with respect to the program.

  The program memory 113 stores an input / output control program 1131, a change amount tuning calculation program 1132, and an interest degree calculation program 1133 as application programs necessary for carrying out the present embodiment.

The input / output control program 1131 performs the following processing.
(1) Every time a broadcast program is received and displayed on the television function unit 101, processing for generating viewing program information related to the broadcast program and storing it in the viewing program information recording area 1141 of the data memory 114.
(2) Every time a measurement start trigger is generated from the timer 121, the reception intensity of the radio wave transmitted from the biological information acquisition apparatus 200 is detected via the proximity wireless module 115, and a value representing the detected radio wave intensity is included. Processing for generating radio wave intensity information and storing it in the radio wave intensity information recording area 1142 of the data memory 114.
(3) Each time an acquisition start trigger is generated from the timer 121, the communication interface 118 is activated to access the microblog service server 300, and post information posted during the broadcast time of the program viewed by the user is displayed on the microblog. A process of receiving from the service server 300 and storing it in the posted information recording area 1144 of the data memory 114.
(4) A process of storing the received biometric information in the biometric information recording area 1143 of the data memory 114 each time biometric information transmitted from the biometric information acquisition apparatus 200 is received by the proximity wireless module 115.

The change amount tuning calculation program 1132 performs the following processing.
(1) When a calculation start trigger is generated from the timer 121, the biological information and the posted information are read from the biological information recording area 1143 and the posted information recording area 1145 of the data memory 114 for each viewing program, respectively. Processing to calculate the amount of change in post information. For example, a method applying cosine similarity is used to calculate the amount of change.
(2) A process of extracting a change in biometric information and post information in which the calculated change amount exceeds a preset threshold value and the change timing is synchronized with each other among the changes in biometric information and post information.
(3) The radio field intensity information detected at the broadcast time of the viewing program is read from the radio field intensity information recording area 1142 of the data memory 114, and the user can read the radio field intensity information based on the read radio field intensity information. A period that does not exist in the displayable range of the display is obtained. Then, the process of excluding the biological information detected during the non-existing period from the calculation target of the change amount according to (1).

The interest degree calculation program 1133 performs the following processing.
(1) For each viewing program, a change in the amount of change calculated by the above-described change amount tuning calculation program 1132 is detected from among changes in the posted information for the program, A process of counting the number of changes in posted information exceeding the threshold value and holding the count value as the number of swells of the viewing program.
(2) The number of changes in the biometric information and the posted information extracted by the processing (2) of the above-described change amount synchronization calculation program 1132, the change amount exceeding the threshold value and the change timings of which are synchronized with each other. Processing to count as the number of synchronization between the message and post information.
(3) A process of calculating, for each viewing program, the ratio of the number of times of tuning obtained by (2) to the number of swells calculated by (1) as information representing the degree of interest of the user with respect to the viewing program.

  On the other hand, the remote controller provided with the function of the biological information acquisition apparatus 200 also includes a central processing unit (CPU; Central Processing Unit) 211, and a pulse sensor 201, a program memory 213, The data memory 214, the proximity wireless module 215, the input / output interface 217, and the timer interface 220 are connected.

  The pulse sensor 201 is activated by a biological information acquisition start trigger given from the timer 221 via the timer interface 220, detects the user's pulse, and outputs the detected value.

  The proximity wireless module 215 includes a wireless interface adopting a short-range wireless data communication standard such as Bluetooth (registered trademark) in the same manner as the proximity wireless module 115 provided in the interest degree estimation apparatus 100 described above, and estimates the degree of interest. Biological information is transmitted to the device 100. The proximity wireless module 215 also has a function of transmitting radio waves continuously or intermittently while the biological information acquisition apparatus 200 is operating.

The program memory 213 uses a non-volatile memory such as ROM or EEPROM, and stores an input / output control program 2131 and a biological information calculation program 2132.
The input / output control program 2131 performs processing for transmitting operation data from the input / output interface 216 using an infrared signal when, for example, a key operation of the remote controller is performed.

  The biological information calculation program 2132 counts the pulse rate per unit time based on the detection output of the pulse sensor 201 every time a biological information acquisition start trigger is generated from the timer 221. Then, the count value of the pulse rate is associated with the measurement time, the user ID, and the biometric information type information as illustrated in FIG. 8 and stored in the biometric information recording area 2141 of the data memory 214 as biometric information. Process.

  The data memory 214 is composed of a storage medium such as a RAM that can be written and read at any time, and has a biological information recording area 2141. The biometric information storage area 2141 is used to store biometric information generated by a biometric information calculation program 2132 described later.

(Operation)
Next, the operation of the degree-of-interest estimation apparatus configured as described above will be described. FIG. 11 is a flowchart showing the entire processing procedure and processing contents.
The timer 121 performs a time measuring operation at a plurality of preset periods, and a calculation start trigger given to the interest degree calculation unit 103 and a measurement trigger given to the proximity wireless module 115 at time intervals defined by these periods. And an acquisition start trigger to be given to the communication interface 118, respectively.

  In the degree-of-interest estimation apparatus 100, the CPU 111 monitors the occurrence of triggers by the timer 121 in steps S1, S3, and S5, and monitors the reception of biological information in step S7. When a trigger is generated from the timer 121 or biometric information is received, each application program stored in the program memory 113 is selectively activated, and the following various processes are executed.

(1) Recording of viewing program information When a broadcast program is received and displayed in the TV function unit 101 and reception and display of the broadcast program is completed, viewing program information relating to the broadcast program is generated under the control of the input / output control program 1131. Then, it is stored in the viewing program information recording area 1141 of the data memory 114. As shown in FIG. 6, this viewing program information is made by associating broadcast program identification information (program ID) with the name of the station that broadcasts the program, the broadcast start time, and the broadcast end time. .

(2) Detection of radio wave intensity information In the biological information acquisition apparatus 200, the proximity wireless module 215 transmits radio waves continuously or intermittently while the power of the apparatus is turned on. On the other hand, when the specific start trigger is generated from the timer 121, the interest level estimation apparatus 100 proceeds from step S3 to step S4 to start the input / output control program 1131 and under the control of the input / output control program 1131. Thus, data representing the reception intensity of the radio wave detected at the present time by the close proximity wireless module 115 is captured. Then, the detection date and time are associated with the identification information (biological information acquisition device ID) of the biometric information acquisition device 200 that is the transmission source, and this is stored in the radio wave intensity information recording area 1142 in the data memory 114 as radio wave intensity information. FIG. 7 shows an example of this, and shows a case where reception intensity information of radio waves transmitted from two biological information acquisition devices is recorded.

(3) Acquisition of biometric information In the biometric information acquisition device 200, every time a biometric information acquisition start trigger is generated from the timer 221, the pulse of the user is detected by the pulse sensor 217 under the control of the biometric information calculation program 2132, The pulse rate per unit time is counted based on the detected data. The count value of the pulse rate is associated with the measurement time, the biometric information acquisition device ID, and the biometric information type information (pulse), and then stored as biometric information in the biometric information recording area 2141 of the data memory 214.

  In the biological information acquisition apparatus 200, when the biological information can be transmitted, the biological information is read from the biological information storage area 2141 under the control of the biological information calculation program 2132. The read biometric information is transmitted from the input / output interface unit 217 to the interest level estimation device 100. Note that the transmitted biometric information is deleted from the biometric information storage area 2141 after the transmission is completed.

  On the other hand, in the degree-of-interest estimation apparatus 100, the biometric information transmitted from the biometric information acquisition apparatus 200 is received by the proximity wireless module 115. When the biological information is received, the process proceeds from step S7 to step S8, and the received biological information is stored in the biological information storage area 1143 in the data memory 114 under the control of the input / output control program 1131. The FIG. 8 shows an example.

(4) Acquisition of Posted Information In the degree-of-interest estimation apparatus 100, when an acquisition start trigger is generated from the timer 121, the process proceeds from step S5 to step S6 and the input / output control program 1131 is activated. Then, under the control of the input / output control program 1131, the microblog service server 300 is accessed, and post information posted during the broadcast time of the program viewed by the user is downloaded from the microblog service server 300 and the data memory 114. Is stored in the posted information recording area 1144. FIG. 9 shows an example.

(5) Interest level calculation process In the interest level estimation device 100, when a calculation start trigger is generated from the timer 121, the process proceeds from step S1 to step S2, and the change amount synchronization calculation program 1132 and the interest level calculation program 1133 are activated. . Then, under the control of the change amount synchronization calculation program 1132 and the interest level calculation program 1133, the interest level calculation process is executed as follows. FIG. 12 is a flowchart showing the processing procedure and processing contents.

  That is, first, at step S21, one piece of viewing program information whose interest level has not been calculated is selected and read from the viewing program recording area 1141 of the data memory 114 as the recording unit 102. In step S22, posted information having a broadcast time zone and a broadcast station name defined in the selectively read viewing program information are read from the posted information recording area 1144 of the data memory 114, and The biometric information detected in the broadcast time zone is read from the biometric information recording area 1143 of the data memory 114. Furthermore, the radio wave intensity information detected during the broadcast time period is read from the radio wave intensity information recording area 1142 of the data memory 114.

  Next, in step S23, a period in which the radio wave intensity is less than a preset threshold value is detected based on the read radio wave intensity information. The period in which the radio wave intensity is less than the threshold value corresponds to a period in which the user is away from the television function unit 101 by a predetermined distance or more, that is, a period in which the user is unable to view the display (non-viewing period). . Then, the information included in the calculated non-viewable period is excluded from the biometric information detected in the read broadcast time zone.

  Subsequently, in step S24, the amount of change is calculated for the biometric information from which information included in the unviewable period is excluded (hereinafter referred to as biometric information after exclusion) and the read posted information. . The calculation of the change amount is performed as follows using the change amount calculation method using the cosine similarity described in the explanation of the principle.

That is, the information of the oldest time is selected from the biological information after the exclusion, and the biological information at the time closest to the selected information and the biological information currently selected among all the biological information after the exclusion is selected. The amount of change with information is calculated. Now, assuming that the amount of change at time k is var (k), the following equation (1) is used to calculate the amount of change var (k).
var (k) = 1-cos (θk) (1)
However, θk is an angle formed by the currently selected biological information and the biological information at the latest time closest to the currently selected biological information among all the biological information after exclusion.

  For example, if the biological information after exclusion includes information from time t-4 to t, and the currently selected biological information is information at time t-4, of all the biological information after the exclusion The biometric information that is newer and closest to the currently selected biometric information is time t-3. The angle formed by the two pieces of biological information is θt−3, and the cosine value is the amount of change. When obtaining the angle θ, the horizontal axis is calculated as 1 sampling rate, and the vertical axis is calculated as 1 beat / minute if the pulse is a pulse, and the value is stored in the work memory in the data memory 114.

  Subsequently, of all the biological information after the exclusion, the biological information at the time closest to and newer than the currently selected biological information is set as a new selection destination. For example, if the biometric information at time t-4 is selected, the biometric information at time t-3 becomes a new selection destination. Then, the amount of change is similarly obtained for this new selection destination. Similarly, the time is selected in order and the amount of change is calculated for each piece of biological information. The change amount of the biological information calculated for the biological information at each time is stored in the work memory in the data memory 114.

  As for the read posted information, the amount of change in the number of posts is calculated for each time using the above equation (1) in the same manner as the biological information, and is stored in the work memory in the data memory 114. .

  When the calculation of the change amount of the biometric information after the exclusion and the change amount of the posted information is completed as described above, the oldest time among the calculated change amounts of the biometric information and the posted information is then step S25. Each change amount of the biometric information and the posted information is selected. Then, in step S26, it is determined whether there is information that has not yet been determined for synchronization among the biometric information and the posted information. If undetermined information remains, steps S27 to S29 are described below. It is executed as follows.

  That is, first, in step S27, the change amount of the selected posting information is compared with a preset threshold value. If the change amount exceeds the threshold value, the count value of the number of swells is added once. Is done. Next, in step S28, it is determined whether or not each change amount of the selected post information and biometric information exceeds the threshold value. The value is added once. Subsequently, in step S29, the number of swells and the number of tunings after the addition are stored in the work memory in the data memory 114. Then, the biometric information and post information that is newer than the biometric information and post information at the currently selected time and that is closest to the time are selected as the next selection destination. For example, if the biological information and posted information at the current time t are selected, the biological information and posted information at the time t + 1 are selected as the next selection destination.

  When the biometric information and the posted information at the next time are selected, the process returns to step S26 to determine whether or not information that has not been subjected to the synchronization determination remains. If undecided information remains, as described above, in steps S27 to S29, an update process of the number of swells and the number of times of synchronization and a process of selecting biometric information and post information at the next time are performed. . Thereafter, similarly, for all the times in the broadcast time period, the process of counting the number of swells and the number of times of tuning is repeatedly performed based on the amount of change in the biometric information and posted information.

When the process of counting the number of climaxes and the number of tunings is completed for all times in all broadcast hours, the process proceeds from step S26 to step S30. In step S30, the degree of interest is calculated based on the calculated number of swells and the number of tunings. This calculation of interest is
The degree of interest is equal to the number of times of tuning / the number of times of excitement. The value representing the degree of interest obtained by this calculation is stored in the interest degree information recording area 1145 in the data memory 114 in association with the user identification information (identification ID of the biometric information acquisition apparatus 200) and the program ID. .

  Finally, in step S31, it is determined whether or not there is a viewing program whose degree of interest has not yet been calculated in the viewing program information recording area 1141 of the data memory 114. If there is an uncalculated viewing program remaining, the process returns to step S21 to select the next uncalculated viewing program, and processing for calculating the degree of interest in steps S22 to S30 for the selected viewing program. Is done. Then, when there are no uncalculated viewing programs, the process for calculating the degree of interest ends.

(6) Application The interest level information for each user for the broadcast program stored in the interest level information recording area 1145 is sent to, for example, a content distribution service server. Then, the content distribution service server selects a product such as content or goods corresponding to the genre in which the corresponding user is interested based on the interest level information, and the introduction information is transmitted to the television receiver of the user. , Distributed to personal computers or portable terminals.

(Effect of embodiment)
As described in detail above, in this embodiment, the posting information for the broadcast program viewed by the user is received from the microblog service server 300, and the user's biological information is received from the biological information acquisition device 200. The amount of change of information and biological information at each time is calculated. Then, among the changes in the calculated post information at each time, the number of change characteristics whose change amount exceeds a threshold is counted as the number of swells, and the calculated post information and biometric information at each time are changed. The number of changes in which the amount of change exceeds the threshold value and the change timings are synchronized with each other is obtained as the number of tunings, and the ratio of the number of times of tuning to the obtained number of swells is expressed as the degree of interest of the user for the broadcast program. It is calculated as information to be expressed.

  Therefore, for example, the user's interest in the broadcast program can be estimated without relying on the user's operation log for the broadcast program. For this reason, even when the user is interested in the program, even if the user is interested in the program, such as when the user continues to watch the next program that starts automatically after the end of viewing one program, It becomes possible to estimate the degree of interest of the user more accurately.

  Further, in this embodiment, since posted information posted in the broadcast time zone of the viewing program and detected biometric information are acquired based on the viewing program information, the posted posted on the viewed broadcast program The degree of interest of the user for the broadcast program can be calculated based only on the amount of change in the information and the received biometric information, thereby estimating the degree of interest of the user for the broadcast program actually viewed by the user Is possible.

  Furthermore, in this embodiment, a period during which the user cannot view the display of the television function unit is obtained based on the reception intensity of the radio wave transmitted from the biological information acquisition apparatus 200, and is detected during this unviewable period. The biometric information is excluded from the amount of change calculation. For this reason, the user's biometric information detected during the broadcast program reception display period, for example, during which the user has temporarily moved to another room or the like and is not substantially viewing the broadcast program, It is possible to exclude from the calculation target, thereby making it possible to estimate the degree of interest more accurately.

[Other Embodiments]
In the embodiment, based on the viewing program information representing the history of the program viewed by the user, the posted information and the biological information corresponding to the broadcast time zone of the viewing program are acquired. Post information and biometric information may be acquired based on information indicating the power on / off period.

  In the above embodiment, the biological information detected by the biological information acquisition device 200 is transmitted to the interest level estimation device using the short-range wireless modules 215 and 115. However, the input / output interfaces 217 and 117 are used. May be transmitted. Furthermore, whether or not the user is present at a position where the user can view the display of the television function unit is determined by input / output in addition to the reception intensity of the radio wave transmitted from the short-range wireless module 215 to the short-range wireless module 115. You may make it perform based on the reception level of the infrared signal transmitted to the input-output interface 117 from the interface 217.

  Furthermore, in the embodiment, the posting information is acquired from the microblog service server 300 via the wireless network, but the posting information may be acquired via a wired network. The biometric information acquisition apparatus 200 may be provided in glasses or headphones for viewing 3D images, or in a portable terminal that is always held by the user, in addition to being provided in the remote controller of the television receiver.

  Furthermore, the content whose interest level is to be estimated is not limited to a broadcast program broadcast from a broadcast station, but is a video content downloaded from a website or a video content recorded on a recording medium such as a DVD. Also good. When reproducing and displaying these video contents, the posting information for the video contents is acquired, and the posted information and the user's biometric information detected when the video content is reproduced are synchronized on the time axis. It is sufficient to detect the synchronization of both.

  Note that the present invention is not limited to the above embodiment, and the configuration of the interest level estimation device, the procedure and processing contents of the interest level calculation process, the posted information in the process, the calculation method of the change characteristic of the biological information, and the like However, various modifications can be made without departing from the scope of the present invention.

  In short, the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. Further, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, you may combine suitably the component covering different embodiment.

  DESCRIPTION OF SYMBOLS 100 ... Interest degree estimation apparatus, 200 ... Biometric information acquisition apparatus, 300 ... Microblog service server, 400 ... Communication network, 101 ... TV function part, 102 ... Recording part, 103 ... Interest degree calculation part, 111, 211 ... CPU, 112, 212 ... bus, 113, 213 ... program memory, 114, 214 ... data memory, 115, 215 ... proximity wireless module, 117, 217 ... input / output interface, 118 ... communication interface, 120, 220 ... timer interface, 121, 221 ... Timer, 201 ... Pulse sensor, 1131, 2131 ... Input / output control program, 1132 ... Change amount synchronization calculation program, 1133 ... Interest degree calculation program, 1141 ... Viewing program information recording area, 1142 ... Radio wave intensity information recording area, 1143 Biometric information recording area, 1144 ... posted information recording area, 1145 ... interest degree information recording area, 2132 ... the biological information calculation program, 2141 ... bio-information recording area.

Claims (7)

Content display device that viewable display the content to the user, with respect to the living body information detection apparatus for detecting transmitted biometric information of a user, and a server device that collects and manages information pair was actually posted to the content Each of the connected degree-of-interest estimation devices,
The number of each time zone Post said being paired actually posts the content information received from the server device, a first variation characteristic calculating means for calculating the received number of posts change characteristic,
Second change characteristic calculating means for receiving the biometric information of the user from the biometric information detecting device and calculating the change characteristic of the received biometric information;
A change characteristic whose change timing is synchronized with each other is extracted from the change characteristics of the number of posts and the biometric information calculated by the first and second change characteristic calculation means, respectively, and the user's corresponding to the content is extracted from the frequency of the extraction. An interest level estimation device comprising an interest level calculation means for calculating an interest level. A second determination means for determining whether or not the user is present in the viewable range with respect to the content display device from the reception quality of the signal transmitted from the biological information detection device;
The second change characteristic calculation unit obtains a period during which the user does not exist in the viewable range based on the determination result of the second determination unit, and calculates biometric information detected during the non-existent period as a change characteristic. The interest level estimation apparatus according to claim 1, further comprising a function of excluding the calculation target. The first and second change characteristic calculation means calculates the cosine similarity of each information value by expressing the change direction of each information value obtained at two adjacent timings by a cosine value, and this calculation is performed. 3. The degree of interest estimation device according to claim 1, wherein the cosine similarity is used as the number of posts and the amount of change in biological information between the two adjacent timings. Content display device that viewable display the content to the user, with respect to the living body information detection apparatus for detecting transmitted biometric information of a user, and a server device that collects and manages information pair was actually posted to the content An interest level estimation method executed by each of the connected interest level estimation devices,
A predetermined number of time-of-day post of the against the contents were actually post information received from the server device, a first variation characteristic calculation for calculating the received time zone of posts change characteristics Process,
A second change characteristic calculating step of receiving the user's biological information transmitted from the biological information detecting device and calculating a change characteristic of the received biological information;
A change characteristic whose change timing is synchronized with each other is extracted from the change characteristics of the posted information and the biometric information calculated by the first and second change characteristic calculation processes, respectively, and the user's response to the content is extracted from the frequency of the extraction. An interest degree estimation method comprising: an interest degree calculation process for calculating an interest degree. A second determination step of determining whether or not the user is present in the viewable range with respect to the content display device from the reception quality of the signal transmitted from the biological information detection device;
In the second change characteristic calculation process, a period during which the user does not exist in the viewable range is obtained based on the determination result of the second determination process, and biological information detected during the non-existing period is obtained as a change characteristic. The interest level estimation method according to claim 4, further comprising a function of excluding the calculation target. The first and second change characteristic calculation processes calculate the cosine similarity of each information value by representing the change direction of each information value obtained at two adjacent timings by a cosine value. 6. The interest level estimation method according to claim 4, wherein the cosine similarity is used as the number of posts and the amount of change in biological information between the two adjacent timings.   The program which makes the computer with which an interest degree estimation apparatus performs the process corresponding to each means with which the interest degree estimation apparatus as described in any one of Claims 1 thru | or 3 is provided.

Images