Information processing device, information processing method, and information processing program
The information processing device analyzes advertisements by detecting and categorizing objects within them, enabling a detailed evaluation of their components' impact, thus addressing the limitations of conventional advertising analysis methods.
Patent Information
- Application Number
- JP2023084368
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-12-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Conventional advertising analysis methods, such as AB testing, struggle to effectively identify effective advertising parameters due to the complexity and vast number of variables, making it impractical to test all possible combinations.
An information processing device and method that includes a detection unit to identify objects within advertisements, a classification unit to categorize these objects, and a calculation unit to determine the proportion of these objects in the advertisement, allowing for a detailed analysis of their impact.
Enables effective analysis of advertisements by identifying and quantifying the significance of various elements within them, facilitating a more nuanced understanding of their effectiveness.
Smart Images

Figure 2024167996000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]
[0002] In recent years, online buying and selling, contracts, and payments for goods and services through electronic commerce (e-commerce) have become increasingly common. At the same time, competition between businesses has intensified. For this reason, it has become important to deliver advertisements that are more effective at attracting customers and making sales. Conventional techniques include, for example, conducting AB testing to analyze advertisements that are more effective at attracting customers and making sales. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2020-004050 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, in recent years, advertisements have become richer, and it is becoming more difficult to analyze which parameters of advertisements are effective in attracting customers and making sales with simple AB testing. Also, it is not realistic to perform AB testing for all possible parameters.
[0005] The present invention has been made in consideration of the above-mentioned problems, and has an object to provide an information processing device, an information processing method, and an information processing program capable of effectively analyzing advertisements. [Means for solving the problem]
[0006] In order to solve the above problem, the information processing device of the present invention is an information processing device that analyzes advertisements, and is equipped with a detection unit that detects objects from the advertisement, and a calculation unit that calculates the proportion of the object detected by the detection unit in the advertisement. Effect of the Invention
[0007] According to the present invention, it is possible to provide an information processing device, an information processing method, and an information processing program capable of effectively analyzing advertisements. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a configuration of a server (information processing device) according to the embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to an embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of a configuration of a user terminal (information processing terminal) according to the embodiment. [Diagram 5] FIG. 2 is a diagram illustrating an example of a functional configuration of a user terminal according to an embodiment. [Figure 6] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 7] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 8] FIG. 4 is a diagram showing an example of major classifications and minor classifications according to the embodiment; [Figure 9] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 10] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 11] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 12] FIG. 11 is a diagram for explaining an example of processing in a server according to the embodiment. [Figure 13]FIG. 4 is a flowchart illustrating an example of processing of the information processing system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] [Embodiment] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that in the following description, an embodiment will be described using a video advertisement (video advertisement) as an example of advertisement. First, an information processing system 1 according to an embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of the information processing system according to the embodiment. The information processing system 1 includes a server 2 (information processing device) and one or more user terminals 3 (information processing terminals) connected to the server 2 via a network 4. The server 2 is also connected to an advertisement delivery server S or the like via the network 4. In the example shown in FIG. 1, the information processing system 1 includes one server 2 and one user terminal 3, but the number of servers 2 and user terminals 3 included in the information processing system 1 is arbitrary. The user terminal 3 may be a desktop PC (Personal Computer), a tablet PC, a smartphone, or the like.
[0010] (Server 2) 2 shows the main hardware configuration of the server 2, in which a communication IF 200A, a storage device 200B, and a CPU 200C are connected via a bus. Although not shown in FIG. 2, the server 2 may also include an input device (e.g., a mouse, a keyboard, a touch panel, etc.) and a display device (CRT (Cathode Ray Tube), a liquid crystal display, an organic EL display, etc.).
[0011] The communication IF 200A is an interface for communicating with other devices (eg, the user terminal 3, an advertisement delivery server, etc.).
[0012] The storage device 200B is, for example, a hard disk drive (HDD) or a semiconductor storage device (solid state drive (SSD)). Various data and information processing programs are stored in the storage device 200B. Some or all of the various data and information processing programs stored in the storage device 200B may be stored in an external storage device such as a universal serial bus (USB) memory or an external HDD, or in a storage device of another information processing device (for example, another server or user terminal 3) connected via the network 4. In this case, the server 2 refers to or acquires various data stored in the external storage device or the storage device of the other information processing device.
[0013] The storage device 200B stores, for example, a learning model (first learning model) for the detection unit 204 described below to detect an object from an advertisement. Furthermore, the storage device 200B stores, for example, a dictionary for the detection unit 204, which will be described later, to detect objects from the text portion of an advertisement. Furthermore, the storage device 200B stores, for example, a learning model (second learning model) for the classification unit 205, which will be described later, to classify the detected objects.
[0014] The CPU 200C controls the server 2 according to this embodiment, and includes a ROM and a RAM (not shown).
[0015] Fig. 3 is a functional block diagram of the server 2 (information processing device). As shown in Fig. 3, the server 2 includes functions such as a receiving unit 201, a transmitting unit 202 (output unit), a storage device control unit 203, a detecting unit 204, a classifying unit 205, a calculating unit 206, and a comparing unit 207. The functions shown in Fig. 3 are realized by the CPU 200C executing an information processing program stored in the storage device 200B.
[0016] The receiving unit 201 receives, for example, information transmitted from the user terminal 3, advertisement information acquired from the advertisement delivery server S, and the like.
[0017] The transmitting unit 202 (output unit) transmits (outputs) information to the user terminal 3, for example.
[0018] The storage device control unit 203 controls, for example, the storage device 200B, and writes and reads information to and from the storage device 200B.
[0019] The detection unit 204 detects objects from the advertisement. Hereinafter, the detection of objects by the detection unit 204 will be described with reference to FIGS. First, the detection unit 204 detects a point where the advertisement display content changes by a predetermined amount or more, in other words, a point where the advertisement scene changes significantly, and divides the advertisement (divides it into frames). Possible points at which a scene changes significantly are, for example, a change in the background, a change in the person appearing, or a change in image from a person to a product. In this embodiment, the detection unit 204 detects a point where a scene changes significantly in the following manner, but the method is not limited to the example described below and other methods may be used to detect a point where a scene changes significantly. (1) Extract features from the image. (2) Calculate the distance between the extracted features (for example, cosine similarity can be used). (3) If the distance between the features exceeds a predetermined value, it is determined that the scene has changed significantly.
[0020] Fig. 6 is an image diagram of the division of an advertisement by the detection unit 204. In the example shown in Fig. 6, advertisement 3 is divided (frame-divided) into scenes S1 to S6, and for example, the durations of scenes S1, S2, S5, and S6 are 4.0 s (seconds), 2.1 s (seconds), 3.8 s (seconds), and 2.5 s (seconds), respectively. The detection unit 204 detects an object displayed in the first or last video data (frame) of each divided scene. The method of detecting an object by the detection unit 204 will be described below, but the detection method described below is merely an example and is not limited to the example described below. In addition, the detection of an object will be described below by dividing the detection target into text and objects. First, detection of text as an object will be described. The detection unit 204 utilizes known OCR or character transcription techniques to extract text from advertisements, and breaks down the extracted text into words using morphological analysis to detect objects (words). Next, a case where an object is detected will be described. The detection unit 204 detects an object included in an image by using a segmentation learning model. The detection unit 204 may be configured to detect an object included in the first or last video data (frame) of each scene divided by combining a plurality of learning models. FIG. 7 is a diagram showing an example of an object displayed in the first or last video data G (frame) of each divided scene. As shown in FIG. 7, the detection unit 204 detects objects such as images G1 to G3 and texts T1 to T2 from video data G.
[0021] The classification unit 205 classifies the objects detected by the detection unit 204 into corresponding categories. The categories may be divided into a hierarchy of major categories (major categories), minor categories (minor categories), etc. Fig. 8 is a diagram showing an example of major categories and minor categories. In the example shown in Figure 8, The major category "Money / Fees" includes the sub-categories "Free," "Cheap," and "Interest Rate." The major category "Problems / Effects" includes the sub-categories "Problems," "Skin," and "Weight and Body Type." The main category "People / Human Parts" includes the sub-categories "Adult Male," "Adult Female," "Boy," and "Girl." The major category "Goods / non-people" includes the subcategories "Fashion" and "Vehicles." It should be noted that FIG. 8 is merely an example, and how the objects are classified is arbitrary.
[0022] FIG. 9 is a diagram showing an example of a state in which the classification unit 205 has classified the images into corresponding categories. In the example shown in FIG. 9, image G1 is classified as a logo, image G2 as a person (male), image G3 as a product, text T1 as the effects and efficacy of the product, and text T2 as a campaign for the product. Note that the classification unit 205 may refer to a classification dictionary that associates objects with classification destinations (major classifications, minor classifications) of the objects, and classify the objects detected by the detection unit 204 into the corresponding categories. For example, if the detected object is text, the classification unit 205 refers to a classification dictionary that associates text (words) with the classification destination (major classification, minor classification) of the text (word), and classifies the text (word) detected by the detection unit 204 into the corresponding category. In addition, if the detected object is an object, the classification unit 205 may analyze the detected object and refer to a classification dictionary that associates objects with classification destinations (major classifications, minor classifications) to classify the object detected by the detection unit 204 into the corresponding category.
[0023] The calculation unit 206 calculates the ratio (display ratio) of the object detected by the detection unit 204 to the advertisement. The calculation unit 206 calculates the ratio of the object detected by the detection unit 204 to the advertisement based on the display area and the display time (playback time). Fig. 10 shows the display area occupied by objects detected by detection unit 204. Calculation unit 206 calculates the area of each object when the sum of the areas of the objects (also called the total area) is set to 100. For example, in the example of Fig. 9, calculation unit 206 calculates the areas of images G1 to G3 and texts T1 and T2 when the sum of the display areas of images G1 to G3 and texts T1 and T2 (also called the total area) is set to 100. The proportion of the display area of each object may be calculated based on, for example, the number of pixels. FIG. 11 visualizes the proportion of each object detected in the first or last video data of each scene S1 to S6 of advertisement 3 described with reference to FIG. 6. The XY axes in FIG. 11 indicate area. Also, the Z axis in FIG. 11 indicates time. In this manner, calculation unit 206 calculates the proportion of each object in the advertisement by area x time. Note that in FIG. 11, the proportion of objects in scenes S2 to S6 is omitted.
[0024] The comparison unit 207 compares the analysis target advertisement with the comparison target advertisement. The comparison unit 207 compares the analysis target advertisement with the comparison target advertisement based on information such as the ratio of the display area of each object calculated by the calculation unit 206, and calculates the values of items A to G described below (see FIG. 12). Item A: Total number of seconds for the ad. Item B: The number of frames into which the detection unit 204 divides the advertisement. Item C: Average length of time per divided scene (frame). Item D: Total number of expressions in the entire advertisement. Item E: Average number of divided scenes (frames). Item F is the unique number. Item G is the unique allocation number of seconds. In addition, Item C is calculated by dividing the value of item A (number of seconds) by the value of item B (number of frames). The expressions in item D are objects contained in the advertisement (detected by the detection unit 204), and the total number of expressions in the entire advertisement is the number of objects detected by the detection unit 204 in the entire advertisement. Item E is calculated by dividing the value of item D (number of expressions (number of objects)) by the value of item B (number of frames). The unique number in item F is the number of unique (unique) objects that do not exist in other (comparison) advertisements. Item G is calculated by dividing the value of item A (number of seconds) by the value of item F (unique number).
[0025] (User terminal 3) The following describes the configuration of the user terminal 3. Figures 4 and 5 are configuration diagrams of the user terminal 3. Note that Figure 4 shows the main hardware configuration of the user terminal 3, and the user terminal 3 has a configuration in which a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, and a CPU 300E are connected via a bus.
[0026] The communication IF 300A is an interface for communicating with another device (the server 2 in this embodiment).
[0027] The storage device 300B is, for example, a hard disk drive (HDD) or a semiconductor storage device (solid state drive (SSD)). The storage device 300B stores a terminal identifier, an information processing program, and the like. The terminal identifier is an identifier for identifying the user terminal 3. By assigning the terminal identifier to information transmitted from the user terminal 3, the server 2 can determine which user terminal 3 transmitted the received information. Note that the terminal identifier may be an Internet Protocol (IP) address, a Media Access Control (MAC) address, or the like, or may be assigned to the user terminal 3 by the server 2.
[0028] The input device 300C is, for example, an input device such as a keyboard, a mouse, or a touch panel, but may be any other device or equipment that allows input. Also, it may be a voice input device.
[0029] The display device 300D is, for example, a liquid crystal display, a plasma display, an organic EL display, or the like, but may be any other device or equipment (for example, a CRT: Cathode Ray Tube) as long as it is capable of displaying.
[0030] The CPU 300E controls the user terminal 3 according to this embodiment, and includes a ROM and a RAM (not shown).
[0031] Fig. 5 is a functional diagram of the user terminal 3. As shown in Fig. 5, the user terminal 3 has functions such as a receiving unit 301, a transmitting unit 302, a storage device control unit 303, an input accepting unit 304, and a display device control unit 305. The functions shown in Fig. 5 are realized by the CPU 300E executing an information processing program stored in the storage device 300B.
[0032] The receiving unit 301 receives, for example, information transmitted from the server 2.
[0033] The transmitting unit 302 transmits, for example, information corresponding to the input operation accepted by the input accepting unit 304 to the server 2.
[0034] The storage device control unit 303 controls the storage device 300B. For example, the storage device control unit 303 controls the storage device 300B to write and read information.
[0035] The input receiving unit 304 receives an input operation from the input device 300C.
[0036] Display device control section 305 controls display device 300D to display information received by receiving section 301, such as the comparison results of comparison section 207 shown in FIG. 12, on display device 300D.
[0037] (Information Processing) Fig. 13 is a flowchart showing an example of information processing of the information processing system 1. Hereinafter, the information processing of the information processing system 1 will be described with reference to Fig. 13. Note that the same components as those described with reference to Figs. 1 to 12 are denoted by the same reference numerals, and duplicated descriptions will be omitted.
[0038] (Analysis processing) 13 is a flowchart showing an example of the analysis process of the information processing system 1. Hereinafter, an example of the analysis process of the information processing system 1 will be described with reference to FIG.
[0039] (Step S101) The receiving unit 201 of the server 2 receives the advertisements to be analyzed and compared. The receiving unit 201 receives information such as the URL of a web page on which the advertisement to be analyzed is posted and the URL of a web page on which the advertisement to be compared is posted.
[0040] (Step S102) The detection unit 204 of the server 2 acquires the relevant advertisements based on information such as the URL of the web page on which the advertisement to be analyzed is posted and the URL of the web page on which the advertisement to be compared is posted, and detects points at which the scene changes significantly for each of the advertisements to be analyzed and compared, and divides the advertisements (into frames).
[0041] (Step S103) The detection unit 204 of the server 2 detects objects from the advertisements for each of the advertisements to be analyzed and compared. For example, the detection unit 204 detects objects displayed in the first or last video data (frame) of each divided scene.
[0042] (Step S104) The classification unit 205 of the server 2 classifies the objects detected by the detection unit 204 into the corresponding categories for each of the advertisements to be analyzed and compared.
[0043] (Step S105) The calculation unit 206 of the server 2 calculates the ratio of the object detected by the detection unit 204 to the advertisement for each of the advertisements to be analyzed and compared. For example, the calculation unit 206 calculates the ratio of the object detected by the detection unit 204 to the advertisement for each of the advertisements to be analyzed and compared, based on the display area and the display time.
[0044] (Step S106) The comparison unit 207 of the server 2 compares the analysis target and comparison target advertisements, and calculates the values of items A to G illustrated in FIG. 12 for each of the analysis target and comparison target advertisements.
[0045] (Step S107) The transmitting unit 202 of the server 2 transmits the values (comparison results) of items A to G of the analysis target and comparison target calculated by the comparing unit 207. The comparison results transmitted from the transmitting unit 202 of the server 2 are received by the receiving unit 301 of the user terminal 3 and are displayed on the display device 300D by the display device control unit 305 (see FIG. 12).
[0046] As described above, the server 2 according to the embodiment is an information processing device that analyzes advertisements. The server 2 includes a detection unit 204 that detects an object from the advertisement, and a calculation unit 206 that calculates the ratio of the object detected by the detection unit 204 to the advertisement. In this manner, advertisement objects are detected and the proportion of the detected objects in the advertisement is calculated, so that the proportion of each object in the advertisement can be grasped, and the advertisement can be effectively analyzed.
[0047] Moreover, the server 2 according to the embodiment includes a classification unit 205 that classifies the objects detected by the detection unit 204 into corresponding categories. Then, the calculation unit 206 calculates the ratio of the objects detected by the detection unit 204 to the advertisement for each category. In this way, the advertisement objects are classified and the proportion of the advertisement for each classified category is calculated, so that the proportion of the advertisement that each category accounts for can be grasped, and the advertisement can be effectively analyzed.
[0048] Furthermore, in this embodiment, the advertisement includes a video, and the calculation unit 206 calculates the proportion of the object detected by the detection unit 204 in the advertisement based on the display area and the display time. In this way, the proportion of an object in an advertisement is calculated based on the display area and the display time, so that the proportion of each object in an advertisement can be grasped three-dimensionally, and the advertisement can be effectively analyzed.
[0049] Furthermore, the detection unit 204 of the server 2 according to the embodiment detects an object from an advertisement when the display content of the advertisement changes by a predetermined amount or more. In this way, instead of calculating the proportion of the object in the advertisement for all video data (frames) that make up the advertisement, the object is detected from the advertisement when the advertisement's display content (scene) changes by more than a predetermined amount, so that the proportion of the object in the advertisement can be calculated efficiently.
[0050] Moreover, the server 2 according to the embodiment includes a comparison unit 207 that compares a plurality of advertisements based on the result calculated by the calculation unit 206. In this way, multiple advertisements can be compared and effectively analyzed.
[0051] (Other embodiments) The present invention can be embodied by appropriately modifying the design without departing from the gist of the invention. For example, the speech of an advertisement may be added to the analysis target. In this case, the server 2 is provided with a speech recognition engine that recognizes the speech of the advertisement and converts it into text, and the classification unit 205 classifies the text converted by the speech recognition engine. Note that the method of classifying the text has been explained in the embodiment, so the explanation is omitted. Also, the calculation unit 206 calculates the proportion of the advertisement based on the playback time. Note that, since speech has no concept of area, the results of analyzing the speech are added as comparison items separately from items A to G in FIG. 12. In this way, since the object includes at least one of an image, a text, and a sound, the advertisement can be effectively analyzed.
[0052] In the above embodiment, the embodiment is described by taking a moving image advertisement (moving image advertisement) as an example of the advertisement, but the present invention is also applicable to non-moving advertisements. In the case of non-moving advertisements, since there is no concept of display time (playback time), for example, the calculation unit 206 calculates the proportion of the advertisement that the object detected by the detection unit 204 occupies based on the display area.
[0053] In addition, in the above embodiment, the advertisement is divided by detecting points where the scene changes significantly, and the object displayed in the first or last video data (frame) of each divided scene is detected, but it is also possible to detect objects in all video data (frames) that make up the advertisement and calculate the proportion of the object in the advertisement.
[0054] Furthermore, in the above embodiment, the comparison unit 207 of the server 2 may be configured to compare the advertisements of the analysis target and the comparison target, and extract unique objects, major categories, and minor categories for each of the advertisements of the analysis target and the comparison target that are not found in other advertisements, and the transmission unit 202 of the server 2 may be configured to transmit the unique objects, major categories, and minor categories extracted by the comparison unit 207 to the user terminal 3 (it may also be configured to display them on a display device of the server 2).
[0055] In addition, some or all of the functions of the server 2 may be provided in the user terminal 3. For example, the user terminal 3 may be provided with functions of the server 2, such as the detection unit 204, the classification unit 205, the calculation unit 206, the comparison unit 207, and a voice recognition engine. [Explanation of symbols]
[0056] 1: Information processing system 2: Server 3: User terminal 4: Network 200A: Communication IF 200B: Storage device 200C: CPU 201: Receiving unit 202: Transmission unit 203: Storage device control unit 204: Detection unit 205: Classification section 206: Calculation section 207: Comparison section 300A: Communication IF 300B: Storage device 300C: Input device 300D:Display device 300E: CPU 301: Receiving unit 302: Transmission department 303: Storage device control unit 304: Input reception section 305: Display device control unit
Claims
1. An information processing device for analyzing advertisements, a detection unit for detecting an object from the advertisement; a calculation unit that calculates a ratio of the object detected by the detection unit to the advertisement; An information processing device comprising:
2. a classification unit that classifies the object detected by the detection unit into a corresponding category, The calculation unit is calculating a ratio of the object detected by the detection unit to the advertisement for each category; 2. The information processing apparatus according to claim 1,
3. the advertisement includes a video; The calculation unit is calculating a ratio of the object detected by the detection unit to the advertisement based on a display area and a display time; 2. The information processing apparatus according to claim 1,
4. The detection unit is detecting an object from the advertisement when the display content of the advertisement changes by a predetermined amount or more; 2. The information processing apparatus according to claim 1,
5. a comparison unit that compares a plurality of advertisements based on the results calculated by the calculation unit; 2. The information processing apparatus according to claim 1,
6. The object may include: At least one of images, text, and audio is included; 2. The information processing apparatus according to claim 1,
7. An information processing method for analyzing advertisements, comprising: A detection unit detects an object from the advertisement; A calculation unit calculates a ratio of the object detected by the detection unit to the advertisement; 13. An information processing method comprising:
8. An information processing program for analyzing advertisements, Computer, a detector for detecting an object from the advertisement; a calculation unit that calculates a ratio of the object detected by the detection unit to the advertisement; An information processing program characterized by causing the program to function as follows.
Citation Information
Patent Citations
Server
JP2020004050A
