WO2022190263A1 - 情報処理装置、分析方法およびプログラム - Google Patents
情報処理装置、分析方法およびプログラム Download PDFInfo
- Publication number
- WO2022190263A1 WO2022190263A1 PCT/JP2021/009556 JP2021009556W WO2022190263A1 WO 2022190263 A1 WO2022190263 A1 WO 2022190263A1 JP 2021009556 W JP2021009556 W JP 2021009556W WO 2022190263 A1 WO2022190263 A1 WO 2022190263A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- value
- quality
- experience
- contribution
- video
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 title claims description 6
- 238000004364 calculation method Methods 0.000 claims abstract description 92
- 238000000034 method Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 description 15
- 239000013598 vector Substances 0.000 description 14
- 238000010586 diagram Methods 0.000 description 5
- 101100072620 Streptomyces griseus ind2 gene Proteins 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25808—Management of client data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2407—Monitoring of transmitted content, e.g. distribution time, number of downloads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44209—Monitoring of downstream path of the transmission network originating from a server, e.g. bandwidth variations of a wireless network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
- H04N21/44224—Monitoring of user activity on external systems, e.g. Internet browsing
Definitions
- the present invention relates to an information processing device, an analysis method, and a program.
- Non-Patent Document 1 a quality-of-experience estimation model for estimating the quality of experience from information of distributed video has been proposed.
- ABR Adaptive Bitrate
- ABR is composed of a distribution server and a terminal.
- An image consists of audio and video (image without audio).
- the video is pre-divided into data called chunks every few seconds, each chunk is encoded at multiple bitrates considering the resolution and frame rate of the video, and stored on the distribution server.
- Audio is similarly split into chunks similar to video, encoded at multiple bitrates, and stored on distribution servers.
- a video encoded under each condition is hereinafter referred to as a representation.
- the terminal repeats the operation of selecting an appropriate representation for each chunk and requesting the selected video from the distribution server based on the network communication status, playback buffer length, and other conditions.
- the quality of experience estimation model estimates the value of the quality of experience in the range of 1 to 5 based on information such as the bit rate of the representation and the status of playback stop due to exhaustion of the playback buffer length. Based on this estimated quality of experience value, the video distributor monitors the distributed video and designs or redesigns the distribution system according to the situation. For example, if the user's QoE value is declining, the user's QoE value can be improved by changing the encoding bit rate value or candidate, or by changing the buffer length of the terminal. It can be designed or redesigned to go up.
- the disclosed technology aims to output information indicating the degree of contribution to the quality of experience of each bit rate for video encoding.
- a quality of experience estimation unit that estimates a quality of experience value by replacing a plurality of index values included in video viewing history data with an index value for a case where the bit rate is not one of a plurality of predetermined bit rates.
- a contribution calculation unit that calculates a contribution to the QoE value of each bit rate included in the plurality of bit rates based on the estimated QoE value, and a contribution that outputs information indicating the contribution. and a degree output unit.
- FIG. 2 is a functional configuration diagram of an information processing apparatus according to Embodiment 1;
- FIG. 7 is a flowchart showing an example of the flow of contribution degree calculation processing according to Embodiment 1;
- FIG. 11 is a flowchart showing an example of the flow of contribution degree calculation processing according to the second embodiment;
- FIG. 10 is a functional configuration diagram of an information processing device according to Embodiment 3;
- FIG. 13 is a flowchart showing an example of the flow of contribution degree calculation processing according to the third embodiment;
- FIG. It is a figure which shows the hardware structural example of an information processing apparatus.
- Embodiment 1 of the present invention will be described below with reference to the drawings.
- the embodiments described below are merely examples, and embodiments to which the present invention is applied are not limited to the following embodiments.
- the information processing apparatus calculates the contribution of each index value included in the viewing history data to the quality of experience.
- the index value is a value that serves as an index for estimating the perceived quality of the viewed video, and a combination of a plurality of values may be used as one index value.
- FIG. 1 is a functional configuration diagram of an information processing apparatus according to Embodiment 1.
- FIG. Information processing apparatus 10 includes storage unit 11 , contribution calculation unit 12 , quality of experience estimation unit 13 , and contribution output unit 14 .
- the storage unit 11 stores various data, specifically, viewing history data.
- Viewing history data is data indicating a history of viewing videos by the user.
- the contribution calculation unit 12 calculates the contribution of each index value included in the viewing history data. Specifically, the contribution calculation unit 12 treats each index value as a player in cooperative game theory, and acquires the QoE value for each combination of game participation and non-participation of each index value from the QoE estimation unit 13 . Then, the contribution calculation unit 12 calculates the Shapley value of each index value from the acquired QoE values for each combination as the contribution.
- the shapley value is determined according to the importance of each player's work as a whole when players participating in the game cooperate with each other and distribute the rewards they have earned. It is one of the fair reward calculation methods to calculate reasonable rewards [2].
- the quality of experience estimating unit 13 executes a process specified in the quality of experience estimation model to estimate the quality of experience value.
- the quality of experience estimation model is, for example, the model proposed in [1]. Let QoE est denote the estimated quality of experience value. Also, the estimated quality of experience value takes a value from 1 to 5.
- the contribution output unit 14 outputs the Shapley value of each index value calculated by the contribution calculation unit 12 as a contribution.
- FIG. 2 is a flowchart showing an example of the flow of contribution degree calculation processing according to the first embodiment.
- the contribution calculation unit 12 acquires viewing history data (step S101).
- viewing history data and videos to be viewed will be described.
- Video consists of audio and video (video without audio), and the bit rate used for encoding is
- B a and B v are the number of types of audio and video bit rates, respectively, b 1 a and b 1 v are the minimum bit rates,
- T time representing the length of video data.
- num stall is the number of times the playback stop occurred
- the notation is not limited to the above, and any format that can count the number of occurrences may be used.
- the viewing history data acquired in step S101 includes S a , S v , and stalling as index values.
- the contribution calculation unit 12 specifies 3, 2, 1 , 4, 5, . ].
- the contribution calculation unit 12 is all possible patterns (2T+1)! streets, ie ind 1 to ind (2T+1)! generate up to
- the quality of experience estimation unit 13 estimates the quality of experience value by treating the index value corresponding to the element x of ind l as non-participation in game theory (step S103).
- the initial values of both l and x are 1. where the 1st to Tth elements of the vector ind l correspond to the 1st to Tth elements of S a , and the T+1th to 2nd T elements of the vector ind l correspond to the 1st to T elements of S v It corresponds to the Tth element, and the 2T+1th element of the vector ind l corresponds to stalling.
- the QoE estimator 13 estimates in advance the QoE est in the actual viewing history data (S a , S v , stalling). Then, the QoE estimation unit 13 replaces s ta , s t v corresponding to the element i whose element of ind 1 is 1, or a temporary value when stalling does not participate, and estimates QoE. Estimate the quality of experience value QoEl ,1 in the model.
- the contribution calculation unit 12 calculates the Shapley value of each index value based on the difference between the quality of experience estimated this time and the quality of experience estimated last time (step S104). Specifically, the contribution calculation unit 12 calculates the Shapley value by the following equation (1).
- step S105 determines whether or not the Shapley values have been calculated for 2T+1 index values.
- step S105: No the contribution calculation unit 12 determines that the Shapley values have not been calculated for 2T+1 index values.
- step S104 when x is 2 or more, the contribution calculation unit 12 calculates the Shapley value by the following equation (2).
- step S105 determines whether or not the Shapley values of all ind l have been calculated. If the contribution calculation unit 12 determines that there is an ind l for which the Shapley value has not been calculated (step S107: No), it adds 1 to l (step S108), and returns to the process of step S103.
- the contribution calculation unit 12 determines that the Shapley values of all ind l have been calculated (step S107: Yes), it calculates the average value of all the calculated Shapley values for each index value as the contribution (step S109 ). Specifically, the contribution calculation unit 12 calculates the average Shapley value of each index value by dividing the Shapley value of each index value added by Equation (1) or Equation (2) by 2T+1. .
- the contribution output unit 14 outputs information indicating the calculated contribution (step S110).
- the viewing history data is as follows.
- the contribution calculation unit 12 generates the following vectors.
- the contribution calculation unit 12 calculates 11! Generate street ind l .
- ind1 [2, 1 , 3, 4, 5, 6, 7, 8, 9, 10, 11]
- ind2 [3, 2 , 1, 4, 5, 6, 7, 8, 9, 10 , 11], ...
- the contribution calculation unit 12 adds to the second element of shap by calculation according to formula (1).
- the contribution calculation unit 12 adds to the first element of shap by calculation according to formula (1).
- the contribution calculation unit 12 adds to the third element of shap by calculation according to formula (1).
- the contribution calculation unit 12 performs calculation for ind2 .
- cooperative game theory is applied to output information indicating the degree of contribution of each index value included in the viewing history data to the quality of experience.
- non-participation in a cooperative game theory replaces each element of S a and S v with a provisional value when the lowest bit rate is selected.
- the temporary value may be other. For example, it may be replaced with a temporary value when the highest bit rate is selected.
- non-participation in the game means replacing each element of S a and S v with a provisional value when the highest bit rate is selected.
- Embodiment 2 will be described below with reference to the drawings.
- Embodiment 2 differs from Embodiment 1 in that each element of audio bit rate and video bit rate is used as an index value instead of each element of S a or S v as an index value. Therefore, in the following description of the second embodiment, the differences from the first embodiment will be mainly described. The same reference numerals as the reference numerals are given, and the description thereof is omitted.
- Quality of experience estimation unit 13 replaces a plurality of index values included in video viewing history data with an index value in the case where the bit rate is not one of a plurality of predetermined bit rates, and calculates the quality of experience value.
- FIG. 3 is a flowchart showing an example of the flow of contribution degree calculation processing according to the second embodiment.
- the process of step S201 of the contribution calculation process according to the present embodiment is the same as step S101 of the contribution calculation process according to the first embodiment.
- the contribution calculation unit 12 specifies 3, 2, 1 , 4, 5, . . . , B a +B v +1].
- the contribution calculation unit 12 is all possible patterns (B a +B v +1)! streets, ie ind 1 to ind (Ba+Bv+1)! generate up to
- the quality of experience estimation unit 13 estimates the quality of experience value by treating the index value corresponding to the element x of ind l as non-participation in game theory (step S203).
- the initial values of both l and x are 1.
- the first to Bath elements of the vector indl correspond to the first to Bath elements of the audio bit rate
- the Ba + 1th to Ba + Bv elements of the vector indl correspond to
- the B a +B v +1 -th element of the vector ind l corresponds to stalling.
- bit rate of the non-participating element when the bit rate of the non-participating element is not selected, replace the bit rate of the non-participating element with the temporary value when the lowest possible bit rate is selected.
- the QoE estimator 13 estimates in advance the QoE est in the actual viewing history data (S a , S v , stalling). Then, the quality of experience estimating unit 13 replaces b i a , b i v or stalling corresponding to the element i whose ind 1 element is 1 if it does not participate, and replaces the quality of experience value with the quality of experience estimation model. Estimate QoE l,1 .
- the quality of experience estimation unit 13 replaces the extracted S j a and S j v with the case of nonparticipation to calculate the quality of experience value QoE l,1 .
- the contribution calculation unit 12 calculates the Shapley value of each index value based on the difference between the quality of experience estimated this time and the quality of experience estimated last time (step S204). Specifically, the contribution calculation unit 12 calculates the Shapley value by the following equation (1).
- the contribution calculation unit 12 determines whether or not the Shapley values have been calculated for B a +B v +1 index values (step S205). If the contribution calculation unit 12 determines that the Shapley value has not been calculated for B a +B v +1 index values (step S205: No), it adds 1 to x (step S206), and performs the process of step S203. back to
- step S204 when x is 2 or more, the contribution calculation unit 12 calculates the Shapley value by the following equation (2).
- step S205 determines whether or not the Shapley values of all ind l have been calculated. If the contribution calculation unit 12 determines that there is ind l for which the Shapley value has not been calculated (step S207: No), it adds 1 to l (step S208), and returns to the process of step S203.
- the contribution calculation unit 12 determines that the Shapley values of all ind l have been calculated (step S207: Yes), it calculates the average value of all the calculated Shapley values for each index value as the contribution (step S209 ). Specifically, the contribution calculation unit 12 calculates the average Shapley value of each index value by dividing the Shapley value of each index value added by the formula (1) or the formula (2) by B a +B v +1. Calculate the value.
- the contribution output unit 14 outputs information indicating the calculated contribution (step S210).
- the viewing history data is as follows.
- the contribution calculation unit 12 generates the following vectors.
- the contribution calculation unit 12 calculates 9! Generate street ind l .
- ind1 [3, 2, 1 , 4, 5, 6, 7, 8, 9]
- ind2 [ 2 , 3, 4, 5, 6, 1, 7, 8, 9], ...
- the contribution calculation unit 12 adds to the third element of shap by calculation according to formula (1).
- the contribution calculation unit 12 adds to the second element of shap by calculation according to formula (1).
- the contribution calculation unit 12 adds to the sixth element of shap by calculation according to formula (1).
- the contribution calculation unit 12 performs calculation for ind2 .
- the information processing apparatus 10 in the contribution calculation method according to the first embodiment, when the viewing time is long, the amount of calculation becomes enormous, and the calculation cannot be completed in a realistic time. There is on the other hand, according to the information processing apparatus 10 according to the present embodiment, by calculating the degree of contribution using a plurality of predetermined bit rates as index values, the amount of calculation is suppressed, and even when the viewing time is long, the degree of contribution is realistic. can be calculated within a certain time.
- the non-participation in the cooperative game theory selects the bit rate of the element for which all representations are non-participation.
- An example of replacing with a temporary value in the case of non-existence is shown.
- the provisional value may be other. For example, if the bitrate of the non-participating element is not selected, replace the bitrate of the non-participating element with a temporary value when the highest possible bitrate is selected. It may also mean that
- Embodiment 3 will be described below with reference to the drawings.
- a short-time quality of experience value at each time calculated based on S a and S v is used as the index value. It differs from form 2. Therefore, in the following description of the third embodiment, the differences from the second embodiment will be mainly described. The same reference numerals as the reference numerals are given, and the description thereof is omitted.
- FIG. 4 is a functional configuration diagram of an information processing device according to the third embodiment.
- Information processing apparatus 10 according to the present embodiment further includes short-time quality of experience estimation unit 15 in addition to information processing apparatus 10 according to the second embodiment.
- the short-term quality of experience estimating unit 15 executes the process specified in the quality of experience estimation model, and calculates the short-term quality of experience value at each time based on the elements s ta and s tv of S a and S v . Estimate q t a , q t v [1].
- FIG. 5 is a flowchart showing an example of the flow of contribution degree calculation processing according to the third embodiment.
- the process of step S301 of the contribution calculation process according to the present embodiment is the same as step S201 of the contribution calculation process according to the second embodiment.
- the short-time quality of experience estimation unit 15 estimates a short-time quality of experience value at each time (step S302).
- the estimation results include q ta , q tv , and stalling as index values.
- q ta and q tv are values obtained by estimating the short-term quality of experience value at each time based on s ta and s tv , respectively.
- the short-term quality of experience estimation unit 15 calculates short-term quality of experience values for representations encoded at certain bit rates b'ia and b'iv .
- the quality of experience estimation unit 13 estimates the quality of experience QoE est based on q ta and q tv in advance [1].
- steps S303 to S311 of the contribution calculation process according to the present embodiment is similar to that of step S202 of the contribution calculation process according to the first embodiment, except that the index values are q t a , q t v , and stalling. - Same as S210.
- the information processing apparatus 10 it is possible to output information indicating the degree of contribution using the estimated value of the QoE for a short time as an index value. As a result, it is possible to understand the influence of short-term quality of experience values on the overall quality of experience values, and use this as a reference for designing or redesigning a video distribution system.
- non-participation in a cooperative game theory game is replaced with a temporary value when q ta and q tv are set to 1, which is the lowest short-term quality of experience value.
- the temporary value may be other.
- they may be replaced with temporary values when q ta and q tv are each set to 5, which is the highest short-term quality of experience value.
- non-participation in the game represents replacement with temporary values when q ta and q tv are set to 5, which is the highest short-time quality of experience value.
- the Shapley values that are output are all 0 or less, and the difference from the highest state (the highest short-term quality of experience value and no playback stop) is calculated. You will be able to see how much each index value is lowering the QoE compared to the best state.
- the information processing apparatus 10 can be realized, for example, by causing a computer to execute a program describing the processing details described in the present embodiment.
- this "computer” may be a physical machine or a virtual machine on the cloud.
- the "hardware” described here is virtual hardware.
- the above program can be recorded on a computer-readable recording medium (portable memory, etc.), saved, or distributed. It is also possible to provide the above program through a network such as the Internet or e-mail.
- FIG. 5 is a diagram showing a hardware configuration example of the computer.
- the computer of FIG. 5 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., which are connected to each other via a bus B, respectively.
- a program that implements the processing in the computer is provided by a recording medium 1001 such as a CD-ROM or memory card, for example.
- a recording medium 1001 such as a CD-ROM or memory card
- the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000 .
- the program does not necessarily need to be installed from the recording medium 1001, and may be downloaded from another computer via the network.
- the auxiliary storage device 1002 stores installed programs, as well as necessary files and data.
- the memory device 1003 reads and stores the program from the auxiliary storage device 1002 when a program activation instruction is received.
- the CPU 1004 implements functions related to the device according to programs stored in the memory device 1003 .
- the interface device 1005 is used as an interface for connecting to the network.
- a display device 1006 displays a GUI (Graphical User Interface) or the like by a program.
- An input device 1007 is composed of a keyboard, a mouse, buttons, a touch panel, or the like, and is used to input various operational instructions.
- the output device 1008 outputs the calculation result.
- Non-Patent Document 1 K. Yamagishi and T. Hayashi, "Parametric Quality-Estimation Model for Adaptive-Bitrate Streaming Services," IEEE Transactions on Multimedia, vol. 19, no. 7, pp. 1545-1557, 2017. DOI: 10.1109/ TMM.2017.2669859.
- Non-Patent Document 1 I. Mann, LS Shapley, Values for large games IV: Evaluating the electoral college by Monte Carlo techniques, Technical report, The RAND Corporation, Santa Monica, 1960.
- This specification describes at least the information processing device, the analysis method, and the program described in each of the following items.
- (Section 1) a quality of experience estimating unit that estimates a quality of experience value by replacing a plurality of index values included in video viewing history data with an index value for a case where the bit rate is not one of a plurality of predetermined bit rates; a contribution calculation unit that calculates the contribution of each bitrate included in the plurality of bitrates to the quality of experience value based on the estimated quality of experience value; A contribution output unit that outputs information indicating the contribution, Information processing equipment.
- the contribution calculation unit calculates, as a contribution, a Shapley value in cooperative game theory when each bit rate is assumed to be a player.
- the information processing device includes: (Section 3)
- the plurality of index values include values obtained by encoding data obtained by dividing the video at one of a plurality of predetermined bit rates,
- the quality of experience estimation unit estimates the quality of experience value by replacing the encoded value with a value in the case where the value is not one of a plurality of predetermined bit rates.
- the information processing device according to item 1 or item 2.
- the plurality of index values include values based on the time at which playback of the video is stopped or the number of times playback is stopped,
- the quality of experience estimating unit replaces the value based on the time when the reproduction of the video is stopped or the number of times the reproduction is stopped with the value when the reproduction of the video is not stopped, and calculates the QoE value.
- the information processing apparatus according to any one of items 1 to 3.
- a short-time quality-of-experience estimation unit that estimates a short-time quality-of-experience value at each time based on data obtained by encoding the data obtained by dividing the video at one of a plurality of predetermined bit rates, wherein the plurality of index values includes the estimated short-term quality of experience value;
- the information processing apparatus according to any one of items 1 to 4.
- the quality of experience estimation unit replaces any of the estimated short-term quality of experience values with the lowest possible value or the highest possible value to estimate the quality of experience value.
- the information processing device according to Item 5.
- (Section 7) A computer implemented method comprising: a step of estimating a quality of experience value by replacing a plurality of index values included in video viewing history data with an index value for a case where the bit rate is not one of a plurality of predetermined bit rates; calculating the degree of contribution of each bitrate included in the plurality of bitrates to the quality of experience value based on the estimated quality of experience value; and outputting information indicating the degree of contribution; Analysis method.
- (Section 8) A program for causing a computer to function as each unit in the information processing apparatus according to any one of items 1 to 6.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Graphics (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
以下、図面を参照して本発明の実施の形態1について説明する。以下で説明する実施の形態は一例に過ぎず、本発明が適用される実施の形態は、以下の実施の形態に限られるわけではない。
上述した各処理における計算の具体例について説明する。音声ビットレートとビデオビットレートとして以下が用意されているものとし、それを用いて符号化された映像があるものとする。
以下に図面を参照して、実施の形態2について説明する。実施の形態2は、指標値としてSaまたはSvの各要素に代えて、音声ビットレートおよびビデオビットレートの各要素を指標値とする点が、実施の形態1と相違する。よって、以下の実施の形態2の説明では、実施の形態1との相違点を中心に説明し、実施の形態1と同様の機能構成を有するものには、実施の形態1の説明で用いた符号と同様の符号を付与し、その説明を省略する。
上述した各処理における計算の具体例について説明する。音声ビットレートとビデオビットレートとして以下が用意されているものとし、それを用いて符号化された映像があるものとする。
以下に図面を参照して、実施の形態3について説明する。実施の形態3は、指標値としてSaまたはSvの各要素に代えて、SaおよびSvを元に計算した各時刻の短時間の体感品質値を指標値とする点が、実施の形態2と相違する。よって、以下の実施の形態3の説明では、実施の形態2との相違点を中心に説明し、実施の形態2と同様の機能構成を有するものには、実施の形態2の説明で用いた符号と同様の符号を付与し、その説明を省略する。
情報処理装置10は、例えば、コンピュータに、本実施の形態で説明する処理内容を記述したプログラムを実行させることにより実現可能である。なお、この「コンピュータ」は、物理マシンであってもよいし、クラウド上の仮想マシンであってもよい。仮想マシンを使用する場合、ここで説明する「ハードウェア」は仮想的なハードウェアである。
[1] K. Yamagishi and T. Hayashi, "Parametric Quality-Estimation Model for Adaptive-Bitrate Streaming Services," IEEE Transactions on Multimedia, vol. 19, no. 7, pp. 1545-1557, 2017. DOI: 10.1109/TMM.2017.2669859.(非特許文献1)
[2] I. Mann, L.S. Shapley, Values for large games IV: Evaluating the electoral college by Monte Carlo techniques, Technical report, The RAND Corporation, Santa Monica, 1960.
本明細書には、少なくとも下記の各項に記載した情報処理装置、分析方法およびプログラムが記載されている。
(第1項)
映像の視聴履歴データに含まれる複数の指標値を、所定の複数のビットレートのいずれかでなかった場合における指標値に置き換えて、体感品質値を推定する体感品質推定部と、
推定された前記体感品質値に基づいて、前記複数のビットレートに含まれる各ビットレートの体感品質値への貢献度を算出する貢献度算出部と、
前記貢献度を示す情報を出力する貢献度出力部と、を備える、
情報処理装置。
(第2項)
前記貢献度算出部は、各ビットレートをプレイヤーとした場合の協力ゲーム理論におけるshapley値を貢献度として算出する、
第1項に記載の情報処理装置。
(第3項)
前記複数の指標値は、前記映像を分割したデータを、所定の複数のビットレートのいずれかで符号化された値を含み、
前記体感品質推定部は、符号化された前記値を、所定の複数のビットレートのいずれかでなかった場合の値に置き換えて、体感品質値を推定する、
第1項または第2項に記載の情報処理装置。
(第4項)
前記複数の指標値は、前記映像の再生停止が発生した時間または再生停止が発生した回数に基づく値を含み、
前記体感品質推定部は、前記映像の再生停止が発生した時間または再生停止が発生した回数に基づく前記値を、前記映像の再生停止が発生しなかった場合の値に置き換えて、体感品質値を推定する、
第1項から第3項のいずれか1項に記載の情報処理装置。
(第5項)
前記映像を分割したデータを、所定の複数のビットレートのいずれかで符号化されたデータに基づいて、各時刻の短時間の体感品質値を推定する短時間体感品質推定部をさらに備え、
前記複数の指標値は、推定された前記短時間の体感品質値を含む、
第1項から第4項のいずれか1項に記載の情報処理装置。
(第6項)
前記体感品質推定部は、推定された前記短時間の体感品質値のいずれかを、取り得る最も低い値または取り得る最も高い値に置き換えて、体感品質値を推定する、
第5項に記載の情報処理装置。
(第7項)
コンピュータが実行する方法であって、
映像の視聴履歴データに含まれる複数の指標値を、所定の複数のビットレートのいずれかでなかった場合における指標値に置き換えて、体感品質値を推定するステップと、
推定された前記体感品質値に基づいて、前記複数のビットレートに含まれる各ビットレートの体感品質値への貢献度を算出するステップと、
前記貢献度を示す情報を出力するステップと、を備える、
分析方法。
(第8項)
コンピュータを第1項から第6項のいずれか1項に記載の情報処理装置における各部として機能させるためのプログラム。
11 記憶部
12 貢献度算出部
13 体感品質推定部
14 貢献度出力部
15 短時間体感品質推定部
Claims (8)
- 映像の視聴履歴データに含まれる複数の指標値を、所定の複数のビットレートのいずれかでなかった場合における指標値に置き換えて、体感品質値を推定する体感品質推定部と、
推定された前記体感品質値に基づいて、前記複数のビットレートに含まれる各ビットレートの体感品質値への貢献度を算出する貢献度算出部と、
前記貢献度を示す情報を出力する貢献度出力部と、を備える、
情報処理装置。 - 前記貢献度算出部は、各ビットレートをプレイヤーとした場合の協力ゲーム理論におけるshapley値を貢献度として算出する、
請求項1に記載の情報処理装置。 - 前記複数の指標値は、前記映像を分割したデータを、所定の複数のビットレートのいずれかで符号化された値を含み、
前記体感品質推定部は、符号化された前記値を、所定の複数のビットレートのいずれかでなかった場合の値に置き換えて、体感品質値を推定する、
請求項1または2に記載の情報処理装置。 - 前記複数の指標値は、前記映像の再生停止が発生した時間または再生停止が発生した回数に基づく値を含み、
前記体感品質推定部は、前記映像の再生停止が発生した時間または再生停止が発生した回数に基づく前記値を、前記映像の再生停止が発生しなかった場合の値に置き換えて、体感品質値を推定する、
請求項1から3のいずれか1項に記載の情報処理装置。 - 前記映像を分割したデータを、所定の複数のビットレートのいずれかで符号化されたデータに基づいて、各時刻の短時間の体感品質値を推定する短時間体感品質推定部をさらに備え、
前記複数の指標値は、推定された前記短時間の体感品質値を含む、
請求項1から4のいずれか1項に記載の情報処理装置。 - 前記体感品質推定部は、推定された前記短時間の体感品質値のいずれかを、取り得る最も低い値または取り得る最も高い値に置き換えて、体感品質値を推定する、
請求項5に記載の情報処理装置。 - コンピュータが実行する方法であって、
映像の視聴履歴データに含まれる複数の指標値を、所定の複数のビットレートのいずれかでなかった場合における指標値に置き換えて、体感品質値を推定するステップと、
推定された前記体感品質値に基づいて、前記複数のビットレートに含まれる各ビットレートの体感品質値への貢献度を算出するステップと、
前記貢献度を示す情報を出力するステップと、を備える、
分析方法。 - コンピュータを請求項1から6のいずれか1項に記載の情報処理装置における各部として機能させるためのプログラム。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180095166.4A CN116897539A (zh) | 2021-03-10 | 2021-03-10 | 信息处理装置、分析方法和程序 |
JP2023504966A JP7544252B2 (ja) | 2021-03-10 | 2021-03-10 | 情報処理装置、分析方法およびプログラム |
PCT/JP2021/009556 WO2022190263A1 (ja) | 2021-03-10 | 2021-03-10 | 情報処理装置、分析方法およびプログラム |
EP21930119.9A EP4307689A1 (en) | 2021-03-10 | 2021-03-10 | Information processing device, analysis method, and program |
KR1020237033315A KR20230152125A (ko) | 2021-03-10 | 2021-03-10 | 정보 처리 장치, 분석 방법 및 프로그램 |
US18/264,504 US20240114187A1 (en) | 2021-03-10 | 2021-03-10 | Information processing apparatus, analysis method and program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/009556 WO2022190263A1 (ja) | 2021-03-10 | 2021-03-10 | 情報処理装置、分析方法およびプログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022190263A1 true WO2022190263A1 (ja) | 2022-09-15 |
Family
ID=83227581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/009556 WO2022190263A1 (ja) | 2021-03-10 | 2021-03-10 | 情報処理装置、分析方法およびプログラム |
Country Status (6)
Country | Link |
---|---|
US (1) | US20240114187A1 (ja) |
EP (1) | EP4307689A1 (ja) |
JP (1) | JP7544252B2 (ja) |
KR (1) | KR20230152125A (ja) |
CN (1) | CN116897539A (ja) |
WO (1) | WO2022190263A1 (ja) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016125415A1 (ja) * | 2015-02-04 | 2016-08-11 | 日本電信電話株式会社 | 体感品質最適化システム、体感品質最適化装置、レコメンド要求装置、体感品質最適化方法、レコメンド要求方法及びプログラム |
-
2021
- 2021-03-10 EP EP21930119.9A patent/EP4307689A1/en active Pending
- 2021-03-10 JP JP2023504966A patent/JP7544252B2/ja active Active
- 2021-03-10 US US18/264,504 patent/US20240114187A1/en active Pending
- 2021-03-10 WO PCT/JP2021/009556 patent/WO2022190263A1/ja active Application Filing
- 2021-03-10 CN CN202180095166.4A patent/CN116897539A/zh active Pending
- 2021-03-10 KR KR1020237033315A patent/KR20230152125A/ko unknown
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016125415A1 (ja) * | 2015-02-04 | 2016-08-11 | 日本電信電話株式会社 | 体感品質最適化システム、体感品質最適化装置、レコメンド要求装置、体感品質最適化方法、レコメンド要求方法及びプログラム |
Non-Patent Citations (2)
Title |
---|
DAIKI FUKUDOME, HIROYUKI KITADA, MASAAKI KUROZUMI, AYAKA NISHIDE, SATOSHI NISHIMURA, TAKAFUMI OKUYAMA, SHOZOE CHO, AND MASAO YAMAM: "B-8-10 Examination of ABR distribution method by cooperative control based on QoE estimated value", PROCEEDINGS OF THE 2020 SOCIETY CONFERENCE OF IEICE 2; SEPTEMBER 15TH - 18TH, 2020, 1 September 2020 (2020-09-01), JP, pages 57, XP009548318 * |
K. YAMAGISHIT. HAYASHI: "Parametric Quality-Estimation Model for Adaptive-Bitrate Streaming Services", IEEE TRANSACTIONS ON MULTIMEDIA, vol. 19, no. 7, 2017, pages 1545 - 1557, XP011653824, DOI: 10.1109/TMM.2017.2669859 |
Also Published As
Publication number | Publication date |
---|---|
US20240114187A1 (en) | 2024-04-04 |
KR20230152125A (ko) | 2023-11-02 |
EP4307689A1 (en) | 2024-01-17 |
JPWO2022190263A1 (ja) | 2022-09-15 |
JP7544252B2 (ja) | 2024-09-03 |
CN116897539A (zh) | 2023-10-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017053115A1 (en) | Predicting a viewer's quality of experience | |
JP4490374B2 (ja) | 映像品質評価装置および方法 | |
JP6611271B2 (ja) | 動画品質制御装置、ビットレート選択方法、及びプログラム | |
JP2008005108A (ja) | 映像品質推定装置、映像品質管理装置、映像品質推定方法、映像品質管理方法、およびプログラム | |
TWI544786B (zh) | 受到壓縮假象和通道假象所影響的視訊失真之計算方法和裝置,以及在帶寬限制的傳輸系統內對視訊串流和封包損失復原串流指定可用帶寬之方法和裝置 | |
JP7380832B2 (ja) | 数理モデル導出装置、数理モデル導出方法及びプログラム | |
WO2022190263A1 (ja) | 情報処理装置、分析方法およびプログラム | |
Tran et al. | An LSTM-based approach for overall quality prediction in HTTP adaptive streaming | |
WO2022190264A1 (ja) | 情報処理装置、分析方法およびプログラム | |
JP7215229B2 (ja) | 映像品質推定装置、映像品質推定方法及びプログラム | |
JP6907958B2 (ja) | 推定装置、推定方法及びプログラム | |
JP6517342B2 (ja) | 配信レート選択装置、配信レート選択方法、及びプログラム | |
JP7040232B2 (ja) | 視聴行動推定装置、視聴行動推定方法及びプログラム | |
JP2019197996A (ja) | エンゲージメント推定装置、エンゲージメント推定方法及びプログラム | |
JP6533487B2 (ja) | アプリケーション制御装置、ネットワーク品質予測方法、及びプログラム | |
JP7351398B2 (ja) | Vr映像符号化パラメータ算出装置、vr映像符号化パラメータ算出方法、及びプログラム | |
JP2020136922A (ja) | エンゲージメント推定装置、エンゲージメント推定方法及びプログラム | |
JP7400936B2 (ja) | 映像品質推定装置、映像品質推定方法、及びプログラム | |
JP7255704B2 (ja) | エンゲージメント推定装置、エンゲージメント推定方法及びプログラム | |
JP6114702B2 (ja) | ユーザ体感品質推定装置、ユーザ体感品質推定方法及びプログラム | |
JP7351140B2 (ja) | 配信装置、配信システムおよび配信プログラム | |
WO2023021890A1 (ja) | 映像品質推定装置、映像品質推定方法、及びプログラム | |
JP7347527B2 (ja) | 映像品質推定装置、映像品質推定方法、及びプログラム | |
JP6730231B2 (ja) | ユーザ操作行動推定装置、ユーザ操作行動推定方法及びプログラム | |
JP2018082314A (ja) | 総合品質推定装置、総合品質推定方法、及びプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21930119 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18264504 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023504966 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180095166.4 Country of ref document: CN |
|
ENP | Entry into the national phase |
Ref document number: 20237033315 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023125321 Country of ref document: RU Ref document number: 2021930119 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021930119 Country of ref document: EP Effective date: 20231010 |