JP6730231B2 - User operation behavior estimation device, user operation behavior estimation method and program - Google Patents

Description

The present invention relates to a user operation action estimation device, a user operation action estimation method, and a program.

In order to maintain and improve user retention in video distribution services, it is necessary to quantify the risk of users leaving the service. To do so, user operation behaviors such as pause, seek (fast forward, fast rewind), and resolution change, network factors (throughput, etc.), content factors (content length, popularity, etc.), service factors (bit rate, frame rate, etc.) , Resolution, etc.), terminal factors (buffer size, etc.), and other factors related to user operation behavior must be clarified to estimate the user operation behavior.

Patent Document 1 proposes a model for calculating user satisfaction based on a user's video viewing state and a method for optimizing user satisfaction based on the model.

As a technique for clarifying the relationship between the user behavior and various factors related to the user behavior, the relationship between the initial buffering time, the buffering ratio, the frame rate and the video viewing time is clarified (Non-Patent Document 1). There is a document that clarifies the relationship between the length and popularity of a moving image and the video viewing completion rate (Non-Patent Document 2).

Japanese Patent No. 6085885

F. Dobrian, V. Sekar, A. Awan, I. Stoica, D. Joseph, A. Ganjam, J. Zhan, H. Zhang. Understanding the impact of video quality on user engagement, in Proc. of SIGCOMM'11, 2011. Y. Chen, B. Zhang. Measurement and Modeling of Video Watching Time in a Large-Scale Internet Video-on-Demand System, IEEE, 2013.

However, Patent Document 1 does not estimate a user operation action. In addition, Non-Patent Documents 1 and 2 are studies that clarify the relationship between various factors related to user behavior and user behavior, but focus on video viewing time and video viewing completion rate as user activity indexes, It does not directly estimate user operation behavior such as pause, seek, and resolution change.

The present invention has been made in view of the above points, and an object thereof is to make it possible to estimate a user operation action based on various factors related to the user operation action.

Therefore, in order to solve the above problem, the user operation behavior estimation device includes an input unit that receives an input of a value of any one of one or more indexes that become a factor of the operation behavior when the user of the video distribution service views the video. A calculating unit that calculates a value of a second index that is associated with a first index of which the input unit has received a value input, of the indexes indicating the operation behavior of the user when viewing the video. And an output unit that outputs the value of the second index.

The user operation behavior can be estimated based on various factors related to the user operation behavior.

It is a figure which shows the hardware structural example of the user operation behavior estimation apparatus 10 in 1st Embodiment. It is a figure which shows the function structural example of the user operation behavior estimation apparatus 10 in 1st Embodiment. 9 is a flowchart for explaining an example of a processing procedure executed by the user operation behavior estimation device 10 according to the first embodiment. It is a figure which shows the function structural example of the user operation behavior estimation apparatus 10 in 2nd Embodiment. It is a flow chart for explaining an example of a processing procedure which user operation behavior estimating device 10 in a 2nd embodiment performs.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram illustrating a hardware configuration example of a user operation behavior estimation device 10 according to the first embodiment. The user operation behavior estimation device 10 of FIG. 1 includes a drive device 100, 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, which are mutually connected by a bus B. Have.

A program that implements the processing in the user operation behavior estimation device 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed in the auxiliary storage device 102 from the recording medium 101 via the drive device 100. However, the program does not necessarily have to 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 the program when an instruction to activate the program is given. The CPU 104 realizes the function of the user operation behavior estimation device 10 according to the 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 according to a program. The input device 107 includes a keyboard, a mouse, and the like, and is used to input various operation instructions.

FIG. 2 is a diagram illustrating a functional configuration example of the user operation behavior estimation device 10 according to the first embodiment. In FIG. 2, the user operation behavior estimation device 10 includes an input unit 11, a user operation behavior estimation unit 12, an output unit 13, and the like. The user operation behavior estimation unit 12 is realized by a process that causes the CPU 104 to execute one or more programs installed in the user operation behavior estimation apparatus 10. The user operation behavior estimation device 10 also uses the function storage unit 111. The function storage unit 111 can be realized using, for example, the auxiliary storage device 102 or a storage device that can be connected to the user operation behavior estimation device 10 via a network.

The input unit 11 receives, for example, a user input of a value of “factor index related to user operation behavior”. “Factor index relating to user operation behavior” is one or more indexes that are factors of operation behavior when a user of the video distribution service views a video. For example, a video viewing application that is affected by factors such as network factors (throughput, etc.), content factors (content length, popularity, etc.), service factors (bit rate, frame rate, resolution, etc.), terminal factors (buffer size, etc.), etc. One or more indexes related to the quality perceivable by the above user correspond to “factor indexes related to user operation behavior”. For example, the number of times playback is stopped, the total playback stop time, and the like are given as examples of the “factor index relating to user operation behavior”. Here, the number of reproduction stops and the total reproduction stop time are not values related to the reproduction stop according to the user's operation, but values related to the reproduction stop that are derived regardless of the user's intention.

The user operation behavior estimation unit 12 estimates (calculates) the “user operation behavior index” based on the “factor index related to the user operation behavior”. The “user operation action index” refers to an index indicating the operation action of the user when viewing a video. For example, the number of pauses by the user, the number of seeks by the user, the number of resolution changes by the user, and the like are examples of the “user operation action index”. The user operation behavior estimation unit 12 is associated with the index of which the input unit 11 has received a value input, out of the “factor index related to the user operation behavior” among the plurality of indexes forming the “user operation behavior index”. Calculate the value of the index. The user operation behavior estimation unit 12 uses one of the one or more functions stored in the function storage unit 111 when calculating the value of the “user operation behavior index”. Each function describes an arbitrary monotonic increase (or decrease) that describes the relationship between any one of the "user operation action index" and any one of the "user operation action index". Is a function. For example, the function storage unit 111 stores a monotonically increasing function that describes the relationship between the number of playback stops and the number of user pauses, a monotonically increasing function that describes the number of playback stops and the number of user resolution changes, and the like. For example, if the number of indexes forming the “factor index related to user operation behavior” is N and the number of indexes forming the “user operation behavior index” is M, then at most N×M functions Can be stored in the function storage unit 111. However, the function corresponding to the combination of indexes for which no correlation is recognized is not stored.

Note that the parameters of each function may be estimated as learning data, for example, an experimentally measured value of “factor operation index relating to user operation behavior” and an experimentally measured value of “user operation behavior index”. Estimated value of "user operation behavior index" obtained by inputting experimentally measured value of "factor index related to user operation behavior" to the function set by the user and temporarily set parameter, and "user operation behavior index" The parameter may be obtained so that the squared error from the actual measurement value of the experiment of “” is minimized.

The output unit 13 outputs the value of the “user operation action index” calculated by the user operation action estimation unit 12.

Hereinafter, the processing procedure of the user operation behavior estimation device 10 of FIG. 1 will be described. FIG. 3 is a flowchart for explaining an example of a processing procedure executed by the user operation behavior estimation device 10 according to the first embodiment.

In step S110, the input unit 11 receives an input of a value of one of the "factor indexes related to user operation behavior". For example, the value of "the number of times playback is stopped" is input.

Then, the user operation behavior estimation unit 12 selects, from the function group stored in the function storage unit 111, a function to which the index of which the input unit 11 has received a value is input (S120). If the index is "reproduction stop count", a function having "reproduction stop count" as an input parameter is selected. For example, a monotonically increasing function (hereinafter referred to as “function A”) that describes the relationship between the number of playback stops and the number of user pauses, and a monotonically increasing function that describes the relationship between the number of playback stops and the number of user resolution changes (hereinafter referred to as “function A”). , "Function B") are selected.

Then, the user operation action estimation unit 12 calculates the value of the “user operation action index” using the selected function (S130). For example, the user operation behavior estimation unit 12 applies (applies) the value of the “playback stop count” input in step S110 to the function A to calculate the value of the “user pause count”. In addition, the user operation behavior estimation unit 12 applies the value of “reproduction stop count” input in step S110 to the function B to calculate the value of “user resolution change count”.

Subsequently, the output unit 13 outputs the value of the “user operation action index” calculated by the user operation action estimation unit 12 (S140). For example, the respective values of “the number of user pauses” and “the number of user resolution changes” are output. That is, when a plurality of functions are selected in step S120, a plurality of "user operation action indexes" are output. The output form is not limited to a predetermined one. It may be displayed on the display device 106, may be stored in the auxiliary storage device 102, or may be transmitted to a printer or another computer via a network.

As described above, according to the first embodiment, the user operation action index can be estimated based on the factor index related to the user operation action. As a result, even a business operator (a network business operator, a service business operator, etc.) that can measure only the factor index of the user operation behavior can estimate the user operation behavior.

As a result, the business operator can grasp and manage the user operation behavior index of the service being provided for each user. Further, it is possible to grasp and manage the change in the user operation action index when the service level of the service being provided is changed, on a user-by-user basis. As a result, it becomes possible to implement measures for maintaining and improving user retention.

Next, a second embodiment will be described. In the second embodiment, the points different from the first embodiment will be described. The points that are not particularly mentioned in the second embodiment may be the same as in the first embodiment.

FIG. 4 is a diagram illustrating a functional configuration example of the user operation behavior estimation device 10 according to the second embodiment. 4, those parts which are the same as those corresponding parts in FIG. 2 are designated by the same reference numerals, and a description thereof will be omitted. In FIG. 4, the user operation behavior estimation device 10 further includes an output index selection unit 14. The output index selecting unit 14 outputs the “user operation action index” to be output when a plurality of “user operation action index” values can be output for the “factor index related to the user operation action” to which the value is input. Select. Such selection is made based on the designation by the user.

FIG. 5 is a flowchart for explaining an example of a processing procedure executed by the user operation behavior estimation device 10 according to the second embodiment. 5, those steps that are the same as those corresponding steps in FIG. 3 are designated by the same step numbers, and a description thereof will be omitted.

In FIG. 5, step S110 is replaced with S110a, and steps S131 and S132 are added.

In step S110a, the input unit 11 accepts from the user the value of one of the "factor indicators related to user operation behavior" and the designation of the index to be output of the "user operation behavior index".

In step S131, the output index selection unit 14 determines whether or not there are multiple "user operation action index" values calculated in step S130. That is, it is determined in step S131 whether a plurality of functions have been used.

When a plurality of values are calculated in step S131 (Yes in S131), the output index selecting unit 14 selects the value of the “user operation action index” specified as the output target by the user in step S110a from the plurality of values. Is selected (S132). In step S140, the value is output.

It should be noted that at the timing of step S120, one function may be selected that has the index for which the input unit 11 has received a value as an input and outputs the index designated as the output target by the user. In this case, steps S131 and S132 may not be executed.

Note that, in the present embodiment, the user operation behavior estimation unit 12 is an example of a calculation unit.

Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications are possible within the scope of the gist of the present invention described in the claims. It can be modified and changed.

10 user operation behavior estimation device 11 input unit 12 user operation behavior estimation unit 13 output unit 14 output index selection unit 100 drive device 101 recording medium 102 auxiliary storage device 103 memory device 104 CPU
105 interface device 106 display device 107 input device 111 function storage unit B bus

Claims (7)

An input unit that receives an input of a value of any one of one or more indexes that are factors of operation behavior when a user of the video distribution service views a video.
A calculation unit that calculates a value of a second index that is associated with a first index of which the input unit has received a value input, of the indices that indicate the operation behavior when the user views the video. ,
An output unit that outputs the value of the second index,
A user operation behavior estimation device comprising: The calculation unit calculates the first index from among one or more functions that describe a relationship between any one of the one or more indexes that are factors of the operation behavior and any one of the indexes that indicate the operation behavior. A function to be input is selected, and the value of the first index is applied to the selected function to calculate the value of the second index;
The user operation behavior estimation device according to claim 1, wherein The output unit outputs a value calculated by using a function corresponding to an index designated by a user for an index indicating the operation behavior among a plurality of functions having the first index as an input,
The user operation behavior estimation device according to claim 2, wherein An input procedure for receiving an input of a value of any one of one or more indexes that become a factor of operation behavior when a user of the video distribution service views a video;
A calculation procedure for calculating a value of a second index associated with the first index for which the input procedure has received the input of values, among the indexes indicating the operation behavior when the user views the video. ,
An output procedure for outputting the value of the second index,
A computer-executed method for estimating user operation behavior. In the calculation procedure, the first index is selected from among one or more functions that describe the relationship between any of the one or more indexes that are factors of the operation behavior and any of the indexes that indicate the operation behavior. A function to be input is selected, and the value of the first index is applied to the selected function to calculate the value of the second index;
The user operation behavior estimation method according to claim 4, wherein The output procedure outputs a value calculated by using a function corresponding to an index designated by a user for an index indicating the operation behavior among a plurality of functions having the first index as an input,
The method for estimating user operation behavior according to claim 5, wherein A program that causes a computer to function as each unit according to any one of claims 1 to 3.

Images