JP2018082314A - Total quality estimation device, total quality estimation method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a total quality estimation device capable of estimating total quality perceived by a user while considering the interaction between psychological factors.SOLUTION: The total quality estimation device includes: input means that receives an input of psychological factor score; storage means that holds coefficients of a mathematical formula for calculating a total quality estimation value which includes a term for reducing influences on the total quality estimation value due to interaction between psychological factors; calculation means that calculates the total quality estimation value by reading the coefficient from the storage means and inputting the psychological factor score input by the input means to the mathematical formula to which the coefficient is applied; and output means that outputs the total quality estimation value calculated by the calculation means.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technique for estimating total quality in a video communication service such as a video distribution service and a TV phone service.

  In order to provide a video service with good quality to the user, it is important to design the system so that the video quality experienced by the user is good before providing the service. In order to implement these, a video quality quantification method capable of appropriately evaluating the quality of the video experienced by the user is necessary.

  Methods for quantifying video quality include a subjective quality evaluation method (for example, see Non-Patent Document 1) and a quality estimation technique (for example, see Non-Patent Documents 2 and 3). The subjective quality evaluation method requires a large number of users to evaluate video images in a facility where the evaluation environment (room illuminance, room noise, etc.) can be reproduced. Therefore, evaluation takes time. Therefore, the development of quality estimation technology that outputs video quality values from physical features related to media signals and services and communications is being developed, and services are designed using quality estimation technology (for example, non-patented). References 2, 3, and 4). Conventional quality estimation techniques for full HD video services are built for image quality such as good or bad video, and full HD video services have been designed based on image quality.

  On the other hand, ultra high-definition video services such as 4K / 8K video have attracted attention in recent years. In the 4K / 8K video service, the resolution, the frame rate, and the bit depth are improved compared to the conventional full HD video service (Non-Patent Document 5). Therefore, it is expected that natural video display becomes possible, and not only high video quality but also a richer sense (psychological factor) can be experienced.

  In order to provide a richer ultra-high-definition video service, the video service should be designed in consideration of not only video quality but also psychological factors (eg, aesthetic feeling, dynamic feeling, etc.) unique to ultra-high-definition video. is necessary. For example, if a travel program with more beautiful images can be provided, the user can clearly have an image of the presented video space, such as the scenery and meals of the travel destination, and the user's satisfaction with the video service (total quality) ) Will improve. In addition, if a sports program that can feel the power of the game and the heat can be provided, the user can feel a sense of dynamism as if he / she was watching at the spectator seat, and the overall quality is improved. In this way, psychological factors that affect the overall quality vary from program to program. Therefore, in order to achieve the same overall quality for travel programs and sports programs, video parameters can be designed for each program so as to improve psychological factors that affect the overall quality. For example, in a travel program with little movement, even if the frame rate is increased to smooth the movement, the user cannot perceive the difference clearly. Therefore, in order to achieve the target total quality, the resolution is improved and the aesthetic feeling is improved. On the other hand, in sports programs, even if the resolution is improved and the video is refined, a user who pays attention to movement cannot perceive the difference clearly. Therefore, in order to achieve the target total quality, the frame rate is improved to improve the dynamic feeling. In this way, it is necessary to change the video parameters so as to improve psychological factors that become appealing points for each program and to achieve the target overall quality.

ITU-T recommendation P.910 "Subjective video quality assessment methods for multimedia applications" ITU-T recommendation J.247 "Objective perceptual multimedia video quality measurement in the presence of a full reference" ITU-T Recommendation J.341 "Objective perceptual multimedia video quality measurement of HDTV for digital cable television in the presence of a full reference" Quality design technology for video communication services (http://www.ntt.co.jp/journal/0901/files/jn200901016.pdf) Upcoming 8K broadcast (https://www.nhk.or.jp/digital/b_tech/pdf2015/nhk2015_02_07.pdf)

  To understand whether the service designer is achieving the overall quality of the service being designed, the technology that estimates the overall quality from the psychological factors (psychological factor scores) felt by the user is required. It is. However, when estimating the total quality from the psychological factor score, there is a problem that the interaction between psychological factors cannot be considered.

  This invention is made in view of said point, Comprising: It considers the interaction of psychological factors and it aims at providing the technique which makes it possible to estimate the total quality which a user feels. .

According to the disclosed technology, an input means for receiving an input of a psychological factor score;
Storage means for holding a coefficient of a mathematical formula for calculating an overall quality estimate, including a term for reducing an influence on an overall quality estimate by an interaction between psychological factors;
Calculating means for calculating an overall quality estimated value by reading the coefficient from the storage means and inputting the psychological factor score input by the input means to the mathematical formula to which the coefficient is applied;
An overall quality estimation device comprising: output means for outputting the overall quality estimated value calculated by the calculating means.

  According to the disclosed technique, it is possible to estimate the total quality felt by the user in consideration of the interaction between psychological factors.

It is a figure which shows the example of the psychological factor score in case the same total quality is achieved with the different video parameter value in embodiment of this invention. It is a figure which shows the relationship between the psychological factors in embodiment of this invention. It is a figure which shows the structural example 1 of the total quality estimation apparatus 1 in embodiment of this invention. It is a hardware block diagram of the comprehensive quality estimation apparatus 1 in embodiment of this invention. It is a figure which shows the example 1 of setting methods of the coefficient bij reflecting the interaction of the psychological factor i and the psychological factor j in embodiment of this invention. It is a figure which shows the structural example 2 of the comprehensive quality estimation apparatus 1 in embodiment of this invention. It is a figure which shows the flow of a process of the interaction determination part 31 in embodiment of this invention. It is a figure which shows the example 2 of a setting method of the coefficient bij reflecting the interaction of the psychological factor i and the psychological factor j in embodiment of this invention.

  Hereinafter, an embodiment (this embodiment) of the present invention will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment. In this embodiment, three types of psychological factors are used, but these are examples. All of these may not be used, or psychological factors other than these may be used.

(Outline of the embodiment)
In the present embodiment, a technique that makes it possible to estimate the overall quality felt by the user in consideration of the interaction between psychological factors will be described. In the following, first, an outline (establishment) of the technique according to the present embodiment will be described by describing the problem in more detail. Here, as an example, three psychological factors such as aesthetic feeling, dynamic feeling, and three-dimensional feeling are shown.

  Even if the same overall quality is achieved, the psychological factors that are strengthened differ depending on the video parameters, so the values of aesthetic feeling, dynamic feeling, and three-dimensional feeling are different. For example, when the video resolution is high, as shown in FIG. 1A, the aesthetic score that is easily affected by the sharpness of the video is high, and when the frame rate is high, as shown in FIG. As shown in FIG. 1C, when the score of dynamism that is easily influenced by the smoothness of movement is high and the bit depth is high, the stereoscopic effect that is easily affected by the standing condition of the edge is obtained. The score is high. Thus, since the values of the psychological factor scores constituting the total quality are different even if the same total quality is achieved, it is important to estimate the total quality from the three psychological factor scores.

  However, psychological factors are not always independent of each other. Here, the example of the relationship between psychological factors is shown in FIG. FIG. 2B shows that the aesthetic feeling and the three-dimensional effect are related to each other in a region where the psychological factor score of the aesthetic feeling or the three-dimensional effect is high. This is because a high aesthetic sense means a high definition, and a high definition means that the edge stands out and the stereoscopic effect is improved. On the other hand, with respect to lively feeling, since the impression of the presented video scene is strongly received, as can be seen from FIGS. 2 (a) and 2 (c), there is no interaction with other psychological factors.

  Here, as a method for estimating the total quality from the psychological factor score, it is conceivable to estimate the total quality by multiplying each psychological factor score by a coefficient. However, in spite of the interaction between aesthetics and three-dimensionality, if you think that the three psychological factor scores are independent and multiply each psychological factor score by a coefficient, the overall quality is estimated. When the aesthetic feeling and the stereoscopic effect are high, the overall quality is estimated to be higher than the actual quality.

  Therefore, in the present embodiment, a technique for estimating the overall quality in consideration of the interaction between psychological factors is realized. In particular, when a psychological factor score of a specific psychological factor (eg, aesthetic feeling or three-dimensional effect) is equal to or higher than a certain value, it is possible to estimate the total quality in consideration of the interaction between the psychological factors. Hereinafter, the technique according to the present embodiment will be described in detail. Below, 1st Embodiment and 2nd Embodiment are described.

(First embodiment)
Hereinafter, a first embodiment will be described with reference to the drawings.

<Functional configuration of overall quality estimation apparatus 1 in the first embodiment>
In FIG. 3, the structural example of the total quality estimation apparatus 1 in 1st Embodiment is shown. As shown in FIG. 3, the overall quality estimation apparatus 1 in the first embodiment includes an overall quality estimation unit 2 and a coefficient DB (database) 3. The coefficient DB3 may be referred to as a storage unit.

  The total quality estimation unit 2 is a means for inputting psychological factor scores (x1 to x3) and a means for calculating (estimating and deriving) the total quality S using a total quality derivation function based on the input psychological factor scores. And means for outputting the calculated total quality S.

  The coefficient DB3 stores the coefficient of the total quality derivation function. The coefficient is a coefficient reflecting the interaction between psychological factors.

  The psychological factor score (x1 to x3) to be input is, for example, a psychological factor score derived from a subjective evaluation experiment, or values such as video resolution, frame rate, bit depth, and encoding bit rate. It is the psychological factor score derived using the objective quality estimation device. However, it is good also as using the psychological factor score derived | led-out by methods other than these as a psychological factor score.

<Hardware configuration example of total quality estimation apparatus 1>
The overall quality estimation apparatus 1 according to the first embodiment can be realized, for example, by causing one or a plurality of computers to execute a program describing the processing content described in the present embodiment. That is, the function of the overall quality estimation apparatus 1 is to execute a program corresponding to the process executed by the overall quality estimation apparatus 1 using hardware resources such as a CPU, memory, and hard disk built in the computer. Can be realized. Further, the program can be recorded on a computer-readable recording medium (portable memory or the like), stored, or distributed. It is also possible to provide the program through a network such as the Internet or electronic mail. Thus, the point which can be realized by a computer and a program is the same as in the second embodiment. The same applies to the hardware configuration example described below in the second embodiment.

  FIG. 4 is a diagram illustrating a hardware configuration example in the case where the total quality estimation apparatus 1 is realized by a computer. 4 includes a drive device 108, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, a display device 106, an input device 107, and the like that are connected to each other via a bus B. .

  A program that realizes processing in the overall quality estimation apparatus 1 is provided by a recording medium 101 such as a CD-ROM or a memory card, for example. When the recording medium 101 storing the program is set in the drive device 108, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 108. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 realizes functions related to the overall quality estimation device 1 according to a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network. The display device 106 displays a GUI (Graphical User Interface) or the like by a program. The input device 107 includes a keyboard and mouse, buttons, a touch panel, and the like, and is used to input various operation instructions.

<Total Quality Calculation Processing by Total Quality Estimating Apparatus 1 in First Embodiment>
Next, the total quality calculation process by the total quality estimation apparatus 1 in the first embodiment will be described in detail.

  When psychological factor scores x1 to x3 are input to the overall quality estimation unit 2, the overall quality estimation unit 2 reads the coefficients from the coefficient DB3. Then, the total quality estimation unit 2 inputs psychological factor scores x1 to x3 to the total quality derivation function to which the coefficient is applied, calculates the total quality derivation function, calculates the total quality S, and outputs it. .

  As the total quality derivation function in the first embodiment, Formula (1) and Formula (2) formulated based on the relationship between each psychological factor and total quality and the interaction between psychological factors are used.

上記の各式において、nは対象とする心理要因の数であり、xiは心理要因iの心理要因スコアであり、aiは、xiに対応する係数であり、S'は心理要因同士の相互作用により総合品質が過剰や過小に評価されることを防ぐための値である。つまり、S'は、心理要因同士の相互作用による総合品質推定値への影響を低減するための項である。

In the above formulas, n is the number of psychological factors of interest, xi is the psychological factor score of psychological factor i, ai is a coefficient corresponding to xi, and S 'is the interaction between psychological factors This is a value for preventing the overall quality from being overestimated or underestimated. That is, S ′ is a term for reducing the influence on the overall quality estimation value due to the interaction between psychological factors.

  Expression (2) is an expression for calculating S ′. In addition, bij in Equation (2) is a coefficient for reflecting the interaction between psychological factors.

  In this embodiment, as an example, n = 3. x1 is an aesthetic feeling, x2 is a dynamic feeling, and x3 is a psychological factor score for a three-dimensional feeling.

  The coefficients ai (i = 1 to 3) and bij (i = 1 to 2, j = i + 1) are derived on the basis of the results of subjective evaluation experiments performed in advance and stored in the coefficient DB3. To do. As a method of deriving the coefficients ai (i = 1 to 3) and bij (i = 1 to 2, j = i + 1), for example, there is a method of deriving by multiple regression analysis based on the subjective evaluation experiment results.

  The coefficient bij may be determined based on the correlation coefficient rij between the score of the psychological factor i and the score of the psychological factor j. Specifically, in order to determine the presence or absence of interaction, it is determined whether or not rij> r−t is satisfied. r−t is a predetermined threshold, and when there is an interaction, the correlation coefficient becomes high. For example, r−t = 0.8 can be considered. Then, the coefficient bij is set as follows according to the value of rij.

bij = cij when rij> rt (3)
Otherwise, bij = 0 (4)
In Expression (3), cij is a value representing an interaction between the psychological factor i and the psychological factor j, and is derived based on, for example, a subjective evaluation experiment result as described above.

  If there is an interaction between psychological factor i and psychological factor j, Equation (3) adds coefficients for xi and xj in order to avoid overestimation or overestimation of the overall quality due to the interaction. Means to subtract. On the other hand, if no interaction is observed, bij = 0 as in equation (4) and the interaction is not considered.

  The determination of the coefficient bij as described above may be performed outside the total quality estimation apparatus 1 or may be performed by the total quality estimation unit 2 of the total quality estimation apparatus 1. In the former case, an externally determined coefficient bij is stored in the coefficient DB3. In the latter case, for example, rij, rt, and cij are stored in advance in the coefficient DB 3, and the overall quality estimation unit 2 determines the coefficient bij according to the flowchart of FIG. That is, the overall quality estimation unit 2 determines whether or not the correlation coefficient rij between the psychological factor i and the psychological factor j is larger than rt (step S101), and in the case of Yes (when large), bij = cij is set. (Step S102) In the case of No (not large), bij = 0 is set (Step S103). The flow in FIG. 5 is executed for each set of i and j.

  In the first embodiment, an example has been described in which n = 3 and total quality is estimated from three psychological factor scores, but n (n is an integer of 2 or 4 or more) other than n = 3 It is good also as estimating total quality from a psychological factor score. Also in this case, as in the case of n = 3, coefficients ai, bij, and the like are derived based on the subjective evaluation experiment results and the like.

  As described above, the derivation of the total quality in consideration of the interaction between psychological factors is realized by the technique according to the first embodiment.

(Second Embodiment)
Hereinafter, a second embodiment will be described with reference to the drawings.

<Functional Configuration of Total Quality Estimating Device 1 in Second Embodiment>
FIG. 6 shows a configuration example of the total quality estimation apparatus 1 in the first embodiment. As shown in FIG. 6, the overall quality estimation apparatus 1 in the second embodiment includes an overall quality estimation unit 2 and a coefficient DB (database) 3. The coefficient DB 3 includes an interaction determination unit 31 along with a storage unit that stores coefficients and the like. The interaction determining unit 31 may be outside the coefficient DB3.

  The total quality estimation unit 2 is a means for inputting psychological factor scores (x1 to x3) and a means for calculating (estimating and deriving) the total quality S using a total quality derivation function based on the input psychological factor scores. And means for outputting the calculated total quality S.

  In the coefficient DB 3, the interaction determination unit 31 determines the presence / absence of interaction between psychological factors according to the value of each psychological factor score, and sets the coefficient according to the determination result.

  The psychological factor score (x1 to x3) to be input is, for example, a psychological factor score derived from a subjective evaluation experiment, or values such as video resolution, frame rate, bit depth, and encoding bit rate. It is the psychological factor score derived using the objective quality estimation device. However, it is good also as using the psychological factor score derived | led-out by methods other than these as a psychological factor score.

<Total Quality Calculation Processing by Total Quality Estimating Apparatus 1 in Second Embodiment>
Next, the total quality calculation process by the total quality estimation apparatus 1 in the second embodiment will be described in detail.

  When psychological factor scores x1 to x3 are input to the overall quality estimation unit 2, the interaction determination unit 31 sets a coefficient, and the overall quality estimation unit 2 reads the coefficient from the coefficient DB 3 and applies the coefficient. The psychological factor scores x1 to x3 are input to the total quality derivation function, the total quality derivation function is calculated, and the total quality S is calculated and output.

  Formulas (1) and (2) formulated based on the relationship between each psychological factor and the total quality and the interaction between psychological factors are used as the total quality derivation function in the second embodiment. Expressions (1) and (2) are the same as Expressions (1) and (2) in the first embodiment.

上記の各式において、nは対象とする心理要因の数であり、xiは心理要因iの心理要因スコアであり、aiは、xiに対応する係数であり、S'は心理要因同士の相互作用により総合品質が過剰や過小に評価されることを防ぐための値である。つまり、S'は、心理要因同士の相互作用による総合品質推定値への影響を低減するための項である。

In the above formulas, n is the number of psychological factors of interest, xi is the psychological factor score of psychological factor i, ai is a coefficient corresponding to xi, and S 'is the interaction between psychological factors This is a value for preventing the overall quality from being overestimated or underestimated. That is, S ′ is a term for reducing the influence on the overall quality estimation value due to the interaction between psychological factors.

  Expression (2) is an expression for calculating S ′. Also, bij in equation (2) is a coefficient for reflecting the interaction between psychological factors. In the second embodiment, bij varies depending on the value of the input psychological factor score.

  In this embodiment, as in the first embodiment, as an example, n = 3. x1 is an aesthetic feeling, x2 is a dynamic feeling, and x3 is a psychological factor score for a three-dimensional feeling.

<About bij settings>
In the second embodiment, the interaction determining unit 31 determines the value of bij (i = 1 to 2, j = i + 1) as follows according to the input psychological factor scores xi and xj. Set.

When xi> xi-min and xj> xj-min, bij = cij (5)
Otherwise, bij = 0 (6)
In equation (5), xi-min is the threshold of the psychological factor score xi indicating the region where the interaction between psychological factors i and j is seen, and xj-min is the region where the interaction between psychological factors i and j is seen Is a threshold value of the psychological factor score xj. Cij is a value indicating an interaction between psychological factors. xi-min and xj-min may be determined in advance and stored in the coefficient DB 3, or, as will be described later, the interaction determination unit 31 calculates (sets) when determining the overall quality. It is good to do.

  FIG. 7 is a flowchart showing processing for setting the value of bij as in the above formulas (5) and (6). As shown in FIG. 7, the interaction determination unit 31 determines whether xi> xi-min and xj> xj-min are satisfied based on the input psychological factor scores xi and xj (step S201). If the determination result in step S201 is Yes, bij = cij is set (step S202), and if the determination result in step S201 is No, bij = 0 is set (step S203).

  (5) In the region where there is an interaction between psychological factors i and j, add or subtract the coefficients for xi and xj to avoid overestimating or overestimating the overall quality due to the interaction. means. On the other hand, in cases other than “xi> xi-min and xj> xj-min”, no interaction is observed, so bij = 0 as shown in Equation (6) and the interaction is not considered. The flow in FIG. 7 is executed for each set of i and j.

  The coefficients ai (i = 1 to 3) and cij (i = 1 to 2, j = i + 1) are derived on the basis of the results of subjective evaluation experiments performed in advance and stored in the coefficient DB3. To do. As a method of deriving the coefficients ai (i = 1 to 3) and cij (i = 1 to 2, j = i + 1), for example, there is a method of deriving by multiple regression analysis based on the subjective evaluation experiment results.

  In addition, the interaction determination unit 31 calculates (derived) xi-min and xj-min based on the correlation coefficient rij between the psychological factor i and the psychological factor j in the procedure shown in FIG. It is good also as setting bij using xj-min.

  Specifically, first, a correlation coefficient rij-h between psychological factors in a region where each psychological factor score value is high (xi> x-max and xj> x-max) is obtained. x-max is a threshold value indicating a region having a high psychological factor score. In the calculation of the correlation coefficient rij-h, for example, data of a set of a set of psychological factor i scores and psychological factor j scores obtained through experiments using various images is stored in the coefficient DB 3 in advance. The interaction determination unit 31 calculates the correlation coefficient rij-h in the region of xi> x-max and xj> x-max from the data. The correlation coefficient rij-h is stored in the coefficient DB3. This calculation is performed for each set of i and j.

  Here, when the psychological factor score takes a value of 1 to 5, setting x-max = 4 is considered as an example. This is for deriving a psychological factor pair in which an interaction is seen in a region where each psychological factor score is high.

  The flow in FIG. 8 is performed for each set of i and j. In step S301 of FIG. 8, the interaction determination unit 31 determines whether or not there is an interaction in a region where the psychological factor score is high with respect to the input psychological factor scores x1 to x3, so that xi> x-max and xj> x Determine whether rij-h> rt is satisfied at -max. r-t is a predetermined threshold value. Here, when there is an interaction, the correlation coefficient becomes high, so it is possible to set r−t = 0.8.

  When “xi> x-max and xj> x-max” and rij-h> r-t are not satisfied (No in step S301), bij = 0 is set (step S306). When rij-h> rt is satisfied (Yes in step S301), the process proceeds to step S302, and the interaction determination unit 31 specifies a range in which interaction between psychological factors can be seen, so that psychology satisfying rij-h> rt is satisfied. The minimum value (xi-min, xj-min) of the score of the factor i and the score of the psychological factor j is derived. This corresponds to deriving the maximum range that satisfies rij-h> r-t. For example, in the case where there is the relationship shown in FIG. 2B between the aesthetic score and the three-dimensional score, (xi-min, xj-min) is approximately between the aesthetic score and the three-dimensional score. It is calculated as an aesthetic score and a three-dimensional score at the point where the linear relationship starts. The calculation of (xi-min, xj-min) may be performed in advance for each set of i and j.

  Then, the interaction determination unit 31 sets a coefficient bij indicating the influence of the interaction as follows. The following formulas (5) and (6) are the same as the above-described formulas (5) and (6).

When xi> xi-min and xj> xj-min, bij = cij (5)
Otherwise, bij = 0 (6)
That is, as shown in FIG. 8, the interaction determination unit 31 determines whether xi> xi-min and xj> xj-min are satisfied based on the input psychological factor scores xi and xj (step S303). . If the determination result in step S303 is Yes, bij = cij is set (step S304), and if the determination result in step S303 is No, bij = 0 is set (step S305).

  As mentioned above, when rij-h> rt is not satisfied, it means that there is no interaction in the region (xi> x-max, xj> x-max) where each psychological factor score value is high. bij = 0 is set (step S306).

  In the second embodiment, an example has been described in which n = 3 and total quality is estimated from three psychological factor scores, but n (n is an integer of 2 or 4 or more) other than n = 3. It is good also as estimating total quality from a psychological factor score. Also in this case, as in the case of n = 3, coefficients ai, bij, and the like are derived based on the subjective evaluation experiment results and the like.

  As described above, by using the technology according to the second embodiment, the interaction between psychological factors is determined according to the value of the psychological factor score, and the overall quality derivation function in which the coefficient changes based on the determination result is used. In addition, the overall quality can be derived in consideration of the interaction between psychological factors.

(Summary of embodiment)
An expression for calculating an overall quality estimate including an input means for accepting an input of a psychological factor score and a term for reducing the influence on the overall quality estimate due to interaction between psychological factors by the disclosed technology. A storage means for holding a coefficient, and a calculation for reading the coefficient from the storage means and calculating a total quality estimated value by inputting the psychological factor score input by the input means to the mathematical formula to which the coefficient is applied There is provided an overall quality estimation apparatus comprising: means and output means for outputting the overall quality estimated value calculated by the calculating means.

  The overall quality estimation apparatus may further include a coefficient determination unit that determines an interaction between psychological factors and determines a coefficient of the mathematical expression according to a determination result. The interaction determination unit 31 is an example of coefficient determination means.

  The coefficient determination unit may determine an interaction between psychological factors based on a correlation coefficient between psychological factor scores, and may determine a coefficient of the mathematical formula according to a determination result.

  The coefficient determination means may determine the interaction between psychological factors based on the value of the psychological factor score input by the input means, and may determine the coefficient of the mathematical formula according to the determination result. .

(Effect of embodiment)
According to the present embodiment, the video service designer can estimate the total quality felt by the user from the psychological factor score. Therefore, it is possible to grasp whether or not the target total quality can be achieved, and when it is not achieved, it is possible to grasp that improvement of each psychological factor score is necessary. As a result, a video service with higher user satisfaction can be provided.

  Although the present embodiment has been described above, the present invention is not limited to the specific embodiment, and various modifications and changes can be made within the scope of the gist of the present invention described in the claims. Is possible.

1 Comprehensive Quality Estimator 2 Comprehensive Quality Estimator 3 Coefficient DB
31 Interaction determination unit
S Overall quality
S 'Value considering interaction in overall quality estimation
x1 Psychological factor score for aesthetics
x2 Psychological factor score for liveliness
x3 Psychological factor score of 3D effect
n Number of psychological factors
a, b Coefficient of total quality derivation function
c Value indicating interaction between psychological factors
x-max Threshold value indicating a region with a high psychological factor score
xi-min Psychological factor score xi threshold indicating the area where psychological factors i and j interact
xj-min Threshold of psychological factor score xj indicating the area where psychological factors i and j interact
rij Correlation coefficient between psychological factors i and j
rij-h Correlation coefficient between psychological factors i and j in areas with high psychological factor scores

Claims (7)

Input means for receiving input of psychological factor scores;
Storage means for holding a coefficient of a mathematical formula for calculating an overall quality estimate, including a term for reducing an influence on an overall quality estimate by an interaction between psychological factors;
Calculating means for calculating an overall quality estimated value by reading the coefficient from the storage means and inputting the psychological factor score input by the input means to the mathematical formula to which the coefficient is applied;
An overall quality estimation apparatus comprising: output means for outputting the overall quality estimated value calculated by the calculation means. The overall quality estimation apparatus according to claim 1, further comprising coefficient determination means for determining an interaction between psychological factors and determining a coefficient of the mathematical expression according to a determination result. The coefficient determination unit determines an interaction between psychological factors based on a value of a psychological factor score input by the input unit, and determines a coefficient of the mathematical formula according to a determination result. Item 3. The overall quality estimation apparatus according to Item 2. An overall quality estimation apparatus comprising storage means for holding coefficients of mathematical formulas for calculating an overall quality estimate value, including a term for reducing the influence on the overall quality estimate value due to interaction between psychological factors Comprehensive quality estimation method,
An input step for receiving an input of a psychological factor score;
A calculation step of reading out the coefficient from the storage unit, and calculating a total quality estimated value by inputting the psychological factor score input in the input step into the mathematical formula to which the coefficient is applied;
An output step of outputting the total quality estimated value calculated by the calculating step. The overall quality estimation method according to claim 4, further comprising: a coefficient determination step that determines an interaction between psychological factors and determines a coefficient of the mathematical expression according to a determination result. In the coefficient determination step, the overall quality estimation device determines an interaction between psychological factors based on the value of the psychological factor score input in the input step, and determines the coefficient of the mathematical formula according to the determination result. The total quality estimation method according to claim 5, wherein:   The program for functioning a computer as each means in the comprehensive quality estimation apparatus of any one of Claims 1 thru | or 3.

Images