Advertising evaluation system, advertising evaluation method, and advertising evaluation program

The advertisement evaluation system addresses the challenge of varying advertisement recognition by using a control unit to extract and evaluate advertisements based on multiple factors, ensuring precise effectiveness assessment.

JP7595096B2Active Publication Date: 2024-12-05MIZUHO BANK
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
JP2023004199
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-01-22
Publication Date
2024-12-05
Estimated Expiration
2041-04-21

AI Technical Summary

Technical Problem

Existing systems struggle to accurately evaluate the effectiveness of advertisements due to variations in their recognition status, which depends on factors like player movements and shooting locations in video content, making it difficult to grasp user recognition.

Method used

An advertisement evaluation system that uses a control unit to acquire evaluation target information, extract target advertisements using a recognition model, and calculate advertising effectiveness based on output states using evaluation factors such as probability, uniqueness, placement, size, continuity, change situation, and scene situation.

Benefits of technology

Enables accurate evaluation of advertisements by considering various factors, predicting user visibility, and providing comprehensive assessment of their effectiveness in video content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007595096000001
    Figure 0007595096000001
  • Figure 0007595096000002
    Figure 0007595096000002
  • Figure 0007595096000003
    Figure 0007595096000003
Patent Text Reader

Abstract

An advertisement evaluation system, an advertisement evaluation method, and an advertisement evaluation program for evaluating advertisements included in content are provided. [Solution] A support server 20 includes a control unit 21 that evaluates the advertising effectiveness in the evaluation target information. The control unit 21 acquires the evaluation target information and a target advertisement of the evaluation target, extracts the target advertisement included in the evaluation target information using a recognition model of the target advertisement, specifies the output state of the target advertisement, and calculates the advertising effectiveness using the output state.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an advertisement evaluation system, an advertisement evaluation method, and an advertisement evaluation program for evaluating advertisements included in content such as images. [Background technology]

[0002] A variety of advertisements are provided through various media. Technologies for evaluating the advertising effectiveness of such advertisements have been considered (for example, Patent Document 1). The management server described in this patent document acquires imaging data including images captured by a drive recorder via a network. The drive recorder captures images of the scenery outside the vehicle through the vehicle window from inside the vehicle. The management server recognizes, from images included in the acquired imaging data, the installation status of a specific advertisement posted in a location captured in the image of the vehicle. Then, the management server determines an evaluation of the advertising effectiveness of the advertisement based on the recognized installation status of the advertisement. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-4204 A Summary of the Invention [Problem to be solved by the invention]

[0004] Even if an advertisement is displayed, it will not be effective unless it is recognized. For example, when distributing a video of a match in which a player wears a uniform with an advertisement on it, the appearance of the advertisement will differ depending on the player's movements and the shooting position of the video. In other words, the advertising effect on users will differ depending on the output status of the advertisement included in the content. For this reason, it is difficult to grasp the recognition status of the advertisement. [Means for solving the problem]

[0005] The advertising evaluation system for solving the above problem includes a control unit for evaluating advertising effectiveness in evaluation target information. The control unit acquires evaluation target information and a target advertisement to be evaluated, extracts the target advertisement included in the evaluation target information using a recognition model of the target advertisement, identifies an output state of the target advertisement, and calculates advertising effectiveness using the output state. Effect of the Invention

[0006] According to the present invention, advertisements contained in content can be evaluated. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is an explanatory diagram of an advertisement evaluation system according to an embodiment. [Diagram 2] FIG. 2 is an explanatory diagram of a hardware configuration of the embodiment. [Diagram 3] 4A is an explanatory diagram of an information storage unit of the embodiment, where FIG. 4B is an explanatory diagram of an evaluation index storage unit, FIG. 4C is an explanatory diagram of an evaluation target storage unit, and FIG. 4D is an explanatory diagram of an evaluation result storage unit. [Figure 4] FIG. [Diagram 5] FIG. 4 is an explanatory diagram of an advertisement output state according to the embodiment. [Figure 6] FIG. 4 is an explanatory diagram of an advertisement output state according to the embodiment. [Figure 7] FIG. 4 is an explanatory diagram of an advertisement output state according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] An embodiment in which an advertisement evaluation system, an advertisement evaluation method, and an advertisement evaluation program are embodied will be described with reference to Figs. 1 to 7. In this embodiment, a case is assumed in which a target (advertisement) included in content (information to be evaluated) is evaluated. Here, a video is used as the content, and an advertisement that can be visually grasped is evaluated. As shown in FIG. 1, the advertisement evaluation system of this embodiment uses a user terminal 10 and a support server 20.

[0009] (Hardware configuration example) FIG. 2 shows an example of the hardware configuration of an information processing device H10 that functions as the user terminal 10, the support server 20, and the like.

[0010] The information processing device H10 includes a communication device H11, an input device H12, a display device H13, a storage device H14, and a processor H 15. Note that this hardware configuration is an example, and the information processing device H10 may include other hardware.

[0011] The communication device H11 is an interface that establishes a communication path with another device and transmits and receives data, and is, for example, a network interface or a wireless interface.

[0012] The input device H12 is a device that accepts input from a user, etc., and is, for example, a mouse, a keyboard, etc. The display device H13 is, for example, a display or a touch panel that displays various information.

[0013] The storage device H14 is a storage device that stores data and various programs for executing various functions of the user terminal 10 and the support server 20. Examples of the storage device H14 include a ROM, a RAM, and a hard disk.

[0014] The processor H15 uses programs and data stored in the storage device H14 to control each process (for example, a process in the control unit 21 described later) in the user terminal 10 and the support server 20. Examples of the processor H15 include a CPU and an MPU. The processor H15 loads a program stored in a ROM or the like into a RAM and executes various processes corresponding to the various processes. For example, when an application program in the user terminal 10 or the support server 20 is started, the processor H15 operates a process that executes each process described later.

[0015] The processor H15 is not limited to a processor that performs software processing for all the processes it executes. For example, the processor H15 may be equipped with a dedicated hardware circuit (e.g., an application specific integrated circuit: ASIC) that performs hardware processing for at least a part of the processes it executes. That is, the processor H15 may be configured as a circuit including (1) one or more processors that operate according to a computer program, (2) one or more dedicated hardware circuits that execute at least a part of the various processes, or (3) a combination thereof. The processor includes a CPU and memory such as RAM and ROM, and the memory stores program code or instructions configured to cause the CPU to execute the processes. The memory, i.e., computer-readable medium, includes any available medium that can be accessed by a general-purpose or dedicated computer.

[0016] (Functions of each information processing device) The functions of the user terminal 10 and the support server 20 will be described with reference to FIG. The user terminal 10 is a computer terminal used by a user who uses this system.

[0017] The support server 20 is a computer system for evaluating advertisements included in content. The support server 20 includes a control unit 21, a recognition model storage unit 22, an evaluation index storage unit 23, an evaluation target storage unit 24, and an evaluation result storage unit 25.

[0018] The control unit 21 performs processes (including a management stage, an extraction stage, an evaluation stage, etc.) described below. By executing an advertisement evaluation program for this purpose, the control unit 21 functions as a management unit 211, an extraction unit 212, an evaluation unit 213, etc.

[0019] The management unit 211 executes a process of managing the evaluation of advertisements included in the content to be evaluated. The extraction unit 212 executes a process of extracting advertisements from the content to be evaluated. The evaluation unit 213 executes a process of evaluating the output state of advertisements in the content to be evaluated.

[0020] 3(a), the recognition model storage unit 22 records the recognition model management data 220. The recognition model management data 220 is recorded during machine learning such as deep learning. The recognition model management data 220 includes a recognition target ID and data related to the recognition model.

[0021] The recognition target ID is an identifier for identifying each recognition model. The recognition model data is a model that recognizes objects contained in the content. These objects include targeted advertisements. When images are used as the content, a recognition model is used that extracts advertisement images from the content images. In this case, a recognition model is generated by performing deep learning using a variety of teacher images that include the object to be recognized. The teacher images have designated areas that include the object to be recognized.

[0022] 3(b), the evaluation index storage unit 23 records evaluation index management data 230 for evaluating the state in which an advertisement is included. This evaluation index management data 230 is registered when an evaluation element for evaluating the output state of an advertisement is determined. In this evaluation index management data 230, data related to a score calculation function is recorded for each evaluation element ID.

[0023] The evaluation element ID is an identifier for identifying an evaluation element for evaluating the output state of an advertisement. In this embodiment, the evaluation elements include advertisement probability, uniqueness, salience, placement, size, continuity, change state, scene state, etc.

[0024] The advertisement probability is the likelihood of a target advertisement recognized in the content using a recognition model. As a score calculation function corresponding to the advertisement probability, a function that calculates a higher score is used as the advertisement probability is higher.

[0025] The uniqueness is determined by the presence or absence of other advertisements other than the recognized target advertisement in the content. As a score calculation function corresponding to the mixedness, a function that calculates a lower score is used as the number of other advertisements increases.

[0026] Prominence is determined by the magnitude of difference (comparison result) between the target ad and its surrounding environment in the content. If the difference is large, the target ad stands out (prominent). Here, the feature amount of the target ad is compared with the feature amount of the surroundings. As a score calculation function corresponding to prominence, a function that calculates a higher score is used as the difference between the feature amounts of both is larger.

[0027] The placement is determined by the display position of the target advertisement in the content. As a score calculation function corresponding to the placement, a function that calculates a higher score is used as the target advertisement is closer to the center of the content.

[0028] The size is the output ratio of the target advertisement to the content (area ratio in the case of an image). As a score calculation function corresponding to the size, a function that calculates a higher score is used as the ratio of the area of ​​the target advertisement to the area of ​​the entire content image is higher.

[0029] The continuity is measured by the duration of time that the target advertisement continues to be output in the content. As a score calculation function corresponding to the continuity, a function that calculates a higher score as the duration is longer is used.

[0030] The change status is determined by the change in the output of the target advertisement in the content. The change (movement) of the target advertisement is evaluated in a time that is recognizable by humans relative to the changes in the surroundings of the target advertisement. As a score calculation function corresponding to the change status, a function that calculates a higher score is used as the change in the target advertisement becomes larger within the range recognizable by humans.

[0031] The scene situation uses an automatically generated explanatory text (image caption) for the scene where the advertisement is displayed. Here, the explanatory text is generated using a known image caption model using image features. Then, as a score calculation function corresponding to the scene situation, a function is used that calculates a higher score the stronger the emotion of the user who viewed the content in response to this scene situation. For example, a high score is calculated for a scene situation (e.g., "goal") in which the team of the target advertisement is dominant.

[0032] As shown in Fig. 3(c), the evaluation target storage unit 24 records evaluation target management data 240 for the evaluation target content. This evaluation target management data 240 is recorded when the evaluation target content is registered. This evaluation target management data 240 includes an evaluation target ID and data related to the content.

[0033] The evaluation target ID is an identifier for identifying each piece of content. The content is the content to be evaluated. In this embodiment, a video is used as the content.

[0034] As shown in Fig. 3(d), the evaluation result storage unit 25 records evaluation result data 250. This evaluation result data 250 is recorded during the advertisement effectiveness evaluation process. This evaluation result data 250 includes an evaluation target ID, a recognition target ID, and data related to the advertisement effectiveness.

[0035] The evaluation target ID is an identifier for identifying the content for which the advertising effectiveness has been evaluated. The recognition target ID is an identifier for identifying a target advertisement recognized in the content. The advertising effect is the sum of the scores of each evaluation element of the target advertisement included in the content.

[0036] Scene evaluation data 251 for each scene in which an advertisement is recognized is associated with this evaluation result data 250. The scene evaluation data 251 includes data related to a scene ID, an evaluation element ID, and a score.

[0037] The scene ID is an identifier for identifying the scene in the content where the target advertisement was recognized. For example, the elapsed time from the start of the video (time index) can be used.

[0038] The evaluation element ID is an identifier for identifying the evaluation element of the advertisement recognized in this scene. The score is calculated based on the evaluation elements of this scene.

[0039] (Advertising effectiveness evaluation processing) Next, the advertising effectiveness evaluation process will be described with reference to Fig. 4. In this embodiment, content (video) stored in the user terminal 10 is evaluated. Here, a recording of a sports game is used as the content to be evaluated.

[0040] First, the control unit 21 of the support server 20 executes a content acquisition process (step S100). Specifically, the management unit 211 of the control unit 21 outputs an evaluation target input screen to the display device H13 of the user terminal 10. This evaluation setting screen includes designation fields for the content to be evaluated and the target advertisement. When the recognition target IDs of the content and advertisement are input in the evaluation setting screen, the management unit 211 acquires the video uploaded from the user terminal 10. In this case, the management unit 211 of the control unit 21 acquires the content and the recognition target ID. Then, the management unit 211 assigns the evaluation target ID to the content and records it in the evaluation target storage unit 24.

[0041] Next, the control unit 21 of the support server 20 executes a process of identifying an evaluation target (step S101). Specifically, the management unit 211 of the control unit 21 extracts an evaluation target (scene image) for checking the presence or absence of an advertisement from the content (video) recorded in the evaluation target storage unit 24. For example, the control unit 211 identifies scene images sequentially at a predetermined time interval from the beginning of the content.

[0042] Next, the control unit 21 of the support server 20 executes an advertisement recognition process (step S102). Specifically, the extraction unit 212 of the control unit 21 recognizes an object included in the evaluation target (scene image) by using the recognition model recorded in the recognition model storage unit 22. The object includes a target advertisement of the recognition target ID.

[0043] Next, the control unit 21 of the support server 20 executes a process of determining whether or not an advertisement is included (step S103). Specifically, the extraction unit 212 of the control unit 21 determines that an advertisement is included in the scene image when the likelihood of the target advertisement is equal to or greater than a reference value.

[0044] When it is determined that an advertisement is included ("YES" in step S103), the control unit 21 of the support server 20 executes a process of identifying the output state of the advertisement (step S104). Specifically, the evaluation unit 213 of the control unit 21 calculates a score according to the output state of the target advertisement included in the scene image by using a score calculation function for each evaluation element ID recorded in the evaluation index storage unit 23.

[0045] 5 to 7, the output state of each scene (510 to 530) of the video of a soccer game will be illustrated. 5, a target advertisement 511 is recognized. This target advertisement 511 is placed large near the center of the first scene 510. Therefore, high scores are calculated for advertisement probability, uniqueness, salience, placement, and size.

[0046] In the second scene 520 shown in Fig. 6, target advertisements 521 and 522 are recognized. When multiple target advertisements are recognized in a scene image, such as in the second scene 520, scores are calculated for each target advertisement and then summed up. The target advertisements 521 and 522 are less visible than the first scene 510, and low scores are calculated for advertisement probability, placement, and size. Since the second scene 520 also includes another advertisement 523, the score for uniqueness is also low.

[0047] 7, a target advertisement 531 is recognized. This target advertisement 531 is less visible than the first scene 510, and a low score is calculated for the advertisement probability. On the other hand, unlike the dribbling scenes of the first scene 510 and the second scene 520, the third scene 530 is a goal scene, and therefore a high score is calculated for the scene situation.

[0048] Next, the control unit 21 of the support server 20 executes a process of recording the evaluation result (step S105). Specifically, the evaluation unit 213 of the control unit 21 generates scene evaluation data 251 in which the scene ID, the evaluation element ID, and the calculated score are recorded, and records the scene evaluation data 251 in the evaluation result storage unit 25.

[0049] On the other hand, if an advertisement cannot be extracted and it is determined that the advertisement is not included ("NO" in step S103), the control unit 21 of the support server 20 skips the process of identifying the advertisement state (step S104) and the process of recording the evaluation result (step S105).

[0050] Next, the control unit 21 of the support server 20 executes a process of determining whether or not the content has ended (step S106). Specifically, the management unit 211 of the control unit 21 determines that the content has ended when all scene images have been evaluated up to the end of the content.

[0051] If it is determined that there are still scene images that have not yet been evaluated and the process is not finished ("NO" in step S106), the control unit 21 of the support server 20 repeats the process of acquiring the evaluation target (step S101) and subsequent processes.

[0052] On the other hand, when all the scene images have been evaluated and it is determined to be finished ("YES" in step S106), the control unit 21 of the support server 20 executes an output process of the advertising effect (step S107). Specifically, the management unit 211 of the control unit 21 calculates the total score of the scene evaluation data 251 recorded in the evaluation result storage unit 25 as the advertising effect, and records it in the evaluation result data 250. Then, the management unit 211 outputs the calculated advertising effect to the display device H13 of the user terminal 10.

[0053] According to this embodiment, the following effects can be obtained. (1) In this embodiment, the control unit 21 of the support server 20 executes an advertisement recognition process (step S102), which makes it possible to extract advertisements from scene images included in a video.

[0054] (2) In this embodiment, if it is determined that an advertisement is included (if "YES" in step S103), the control unit 21 of the support server 20 executes a process of identifying the output state of the advertisement (step S104) and a process of recording the evaluation result (step S105). This allows the advertisement to be evaluated according to the output state of the advertisement.

[0055] (3) In this embodiment, when it is determined that the advertisement is to be ended (YES in step S106), the control unit 21 of the support server 20 executes an output process of the advertisement effect (step S107). This allows the advertisement effect to be accurately evaluated in the content including the time element.

[0056] (4) In this embodiment, the evaluation index storage unit 23 records evaluation index management data 230 for evaluating the state in which an advertisement is included. Here, the evaluation elements used are advertising probability, uniqueness, salience, placement, size, continuity, change state, scene state, etc. This allows advertisements to be comprehensively evaluated using a variety of evaluation elements. In addition, the advertisement probability is used as an evaluation factor. This makes it possible to predict the visibility of the advertisement to the user using the probability calculated by the prediction model. In addition, a high score can be given to a scene image in which the advertisement is easy to read.

[0057] In addition, uniqueness and salience are used as evaluation factors. This allows the effectiveness of advertisements to be evaluated taking into account the surrounding circumstances in which the advertisement is displayed. In addition, a high score can be given to a scene image in which the advertisement stands out.

[0058] In addition, the layout and size are used as evaluation factors. This allows the advertisement effectiveness to be evaluated taking into account the visibility of the advertisement. A high score can be given to a scene image in which the advertisement is easy to read.

[0059] In addition, continuity is used as an evaluation factor. This allows the advertisement effectiveness to be evaluated taking into account the duration of the advertisement. If an advertisement is viewed for a long time, a high score can be given.

[0060] In addition, the change status is used as an evaluation factor. This allows the advertising effectiveness to be evaluated according to the visibility focusing on the movement. And, a high score can be given according to the line of sight focusing on the change.

[0061] In addition, the scene situation is used as an evaluation element. This allows the advertising effectiveness to be evaluated by considering the scene image and the user's emotions. And, a high score can be given to an advertisement output in a scene where the user's emotions are heightened.

[0062] This embodiment can be modified as follows: This embodiment and the following modifications can be combined with each other to the extent that there is no technical contradiction. In the above embodiment, it is assumed that a target (advertisement) included in the content (information to be evaluated) is evaluated. In the present invention, "advertisement" includes not only things actively and widely promoted to the public for commercial purposes, but also company names, product names, etc. (targets) that are widely displayed to the public. For example, it can be used to evaluate the reputation of a company or product. In the above embodiment, a recognition model generated by machine learning such as deep learning is used. However, the recognition means is not limited as long as it can recognize objects in the content.

[0063] In the above embodiment, the control unit 21 of the support server 20 executes a process of identifying an evaluation target (step S101). Specifically, the management unit 211 of the control unit 21 extracts an evaluation target (scene image) for checking the presence or absence of an advertisement from the content (video) recorded in the evaluation target storage unit 24. Alternatively, the advertisement may be evaluated in real time. For example, the advertising effectiveness evaluation process may be executed on a distributed video.

[0064] In the above embodiment, the evaluation factors include advertising probability, uniqueness, salience, placement, size, continuity, change status, scene status, etc. The evaluation factors are not limited to these. Some of these or other factors may be included. In the above embodiment, a recording of a sports game is used as the content to be evaluated. The content to be evaluated is not limited to a recording of a game. It is also possible to use a broadcast of a television program or a recording made by a drive recorder.

[0065] Furthermore, multiple images may be applied to the content. In this case, the content does not need to be a single data file, and content that is a compilation of multiple data files may be used. For example, the present invention may be applied to a social networking service (SNS) that uses images. In this case, multiple images included in the SNS are extracted, and the advertising effectiveness is scored based on the evaluation elements. In this case, the scene situation may be identified using a message included in the SNS.

[0066] It may also be applied to web crawling, where a crawler in a search engine crawls through websites and collects website information. In this case, target advertisements included in each website (content) are extracted, and the effectiveness of the advertisements is scored based on the evaluation factors. In this case, a scene situation may be identified using a message included in the website. It may also be applied to clipping news articles.

[0067] In the above embodiment, the advertising effectiveness is evaluated using a video (image) as the content to be evaluated. The evaluation target is not limited to advertisements provided to the senses of sight. The advertising effectiveness may be evaluated using content (e.g., sound) provided to other senses (e.g., hearing). In this case, a recognition model including a time element such as an RNN (Recurrent Neural Network) or an LSTM (Long Short-Term Memory) is used. In this case, the likelihood (advertising probability) output from the recognition model, the difference from environmental sounds, the volume of the advertisement, the scene situation, etc. can be used as evaluation elements. [Explanation of symbols]

[0068] 10...user terminal, 20...support server, 21...control unit, 211...management unit, 212...extraction unit, 213...evaluation unit, 22...recognition model storage unit, 23...evaluation index storage unit, 24...evaluation target storage unit, 25...evaluation result storage unit.

Claims

1. An advertisement evaluation system including a control unit for evaluating an advertisement effect in evaluation target information, The control unit: Obtaining evaluation target information and a target advertisement for the evaluation target; Using a recognition model generated by machine learning of the target advertisement, extracting the target advertisement included in the evaluation target information having a certainty output from the recognition model equal to or greater than a reference value; An advertising evaluation system, characterized in that in a scene in which the target advertisement is output, a score is assigned according to the degree of likelihood to calculate advertising effectiveness.

2. The control unit: If the evaluation target information includes a time element, calculate an output time of the target advertisement; 2. The advertisement evaluation system according to claim 1, wherein the advertisement effect is calculated using the output time.

3. The control unit: Identifying an output ratio of the target advertisement in the evaluation target information; 3. The advertisement evaluation system according to claim 1, wherein the advertisement effectiveness is calculated using the output ratio.

4. The control unit: Identifying a display position of the target advertisement in the image as the evaluation target information; 4. The advertisement evaluation system according to claim 1, wherein the advertisement effectiveness is calculated using the display position.

5. A method for evaluating advertisements using an advertisement evaluation system including a control unit that evaluates advertising effectiveness in evaluation target information, comprising: The control unit: Obtaining evaluation target information and a target advertisement for the evaluation target; Using a recognition model generated by machine learning of the target advertisement, extracting the target advertisement included in the evaluation target information having a certainty output from the recognition model equal to or greater than a reference value; An advertising evaluation method, comprising: calculating advertising effectiveness by assigning a score according to the degree of likelihood in a scene in which the target advertisement is output.

6. An advertisement evaluation program for evaluating advertisements using an advertisement evaluation system including a control unit for evaluating advertising effectiveness in evaluation target information, The control unit, Obtaining evaluation target information and a target advertisement for the evaluation target; Using a recognition model generated by machine learning of the target advertisement, extracting the target advertisement included in the evaluation target information having a certainty output from the recognition model equal to or greater than a reference value; an advertisement evaluation program for functioning as a means for calculating an advertisement effectiveness by assigning a score according to the degree of likelihood in a scene in which the target advertisement is output;

Citation Information

Patent Citations

  • Advertisement video embedding system

    JP2006014200A

  • Advertisement effect evaluation system

    JP2020004204A

  • Information processing device, information processing method, and information processing program

    JP2021047719A

  • Program, game device, control method of game device, and game system

    JP2021078571A

  • Identifying visual objects depicted in video data using video fingerprinting

    US20180082125A1