Determination system, learning system, determination method, learning method, and computer program

Abstract

To enable estimation of advertising effectiveness with less effort for advertising media of a new format.SOLUTION: A determination system comprises: an advertisement composition feature amount acquisition unit for receiving input of advertisement composition information including data of one or more advertisement elements used in an advertisement to be determined, acquiring a feature amount from the data of each advertisement element, and performing a predetermined calculation on the acquired feature amount and information indicating a format of the advertisement corresponding to each advertisement element to acquire advertisement composition feature amount indicating the feature of the advertisement composition information; and a determination unit for determining an effect obtained by delivering the advertisement to be determined using the advertisement composition feature amount related to the advertisement to be determined and a determination model for determining an effect obtained by delivering the advertisement from the advertisement composition feature amount.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a determination system, a learning system, a determination method, a learning method, a computer program, and an advertisement configuration feature determining device. [Background technology]

[0002] The importance of advertising in business, public activities, etc. has long been recognized, and technologies for predicting the effectiveness of advertising have been developed. One example of such technology is a generation device disclosed in Patent Document 1. Patent Document 1 discloses a technology that uses machine learning technology to estimate the effectiveness of an advertisement when the advertisement is distributed based on the advertisement data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-37229 A Summary of the Invention [Problem to be solved by the invention]

[0004] The format used for advertisements varies depending on the advertisement delivery medium. For example, some advertisement media may arrange text and still images, while other advertisement media may arrange text and moving images. Even if text and still images are used in the same way, their size and arrangement may differ depending on the advertisement medium. For this reason, in the past, in order to more accurately estimate the effect obtained when an advertisement is delivered, a new machine learning model was redesigned for each format. Therefore, when a new format of advertisement medium was created, a great deal of effort was required to estimate the advertising effect.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and provides a technique that makes it possible to estimate the effectiveness of advertising for advertising media of a new format with less effort. [Means for solving the problem]

[0006] One aspect of the present invention is a judgment system that includes an advertisement composition feature acquisition unit that receives advertisement composition information including data on one or more advertisement elements used in an advertisement to be judged, acquires features from the data on each advertisement element, and acquires advertisement composition features indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element, and a judgment unit that judges the effectiveness obtained by delivering the advertisement to be judged by using the advertisement composition features related to the advertisement to be judged and a judgment model for determining the effectiveness obtained by delivering the advertisement from the advertisement composition features.

[0007] One aspect of the present invention is the above-mentioned determination system, wherein the information indicating the format of the advertisement includes information indicating a type of the advertisement element.

[0008] One aspect of the present invention is a learning system that includes an advertisement composition feature acquisition unit that receives advertisement composition information including data on one or more advertisement elements used in advertisements that have been previously distributed, acquires features from the data on each advertisement element, and acquires advertisement composition features that indicate characteristics of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element, and a learning control unit that performs a learning process using the advertisement composition features related to the previously distributed advertisements and effects obtained when the advertisements were previously distributed, thereby generating a learned model in which the advertisement composition features are explanatory variables and the effects are objective variables.

[0009] One aspect of the present invention is a determination method having an advertisement composition feature acquisition step of receiving advertisement composition information including data on one or more advertisement elements used in an advertisement to be determined, acquiring features from the data on each advertisement element, and acquiring advertisement composition features indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element, and a determination step of determining an effectiveness obtained by delivering the advertisement to be determined by using the advertisement composition features related to the advertisement to be determined and a determination model for determining an effectiveness obtained by delivering the advertisement from the advertisement composition features.

[0010] One aspect of the present invention is a learning method having an advertisement composition feature acquisition step of receiving advertisement composition information including data of one or more advertisement elements used in advertisements distributed in the past, acquiring features from the data of each advertisement element, and acquiring advertisement composition features indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element; and a learning control step of performing a learning process using the advertisement composition features related to the advertisements distributed in the past and effects obtained when the advertisements were distributed in the past, thereby generating a learned model in which the advertisement composition features are explanatory variables and the effects are objective variables.

[0011] One aspect of the present invention is a computer program for causing a computer to function as the above-mentioned determination system or the above-mentioned learning system.

[0012] One aspect of the present invention is an advertisement composition feature acquisition device that includes a plurality of first encoders that convert data of a first type of advertisement element into a value indicating a feature, a plurality of second encoders that convert data of a second type of advertisement element into a value indicating a feature, and a calculation unit that calculates data corresponding to the first type on values ​​obtained by the first encoders, calculates data corresponding to the second type on values ​​obtained by the second encoder, and integrates the values ​​obtained by the calculation to generate a value indicating a feature of an advertisement composition including the first type of advertisement element and the second type of advertisement element. Effect of the Invention

[0013] According to the present invention, it becomes possible to estimate the advertising effectiveness of new formats of advertising media with less effort. [Brief description of the drawings]

[0014] [Figure 1] 1 is a schematic block diagram showing a system configuration of a determination system 100 according to the present invention. [Diagram 2] 2 is a schematic block diagram showing a specific example of the functional configuration of a terminal device 10. FIG. [Diagram 3] 2 is a schematic block diagram showing a specific example of the functional configuration of a learning device 20. FIG. [Figure 4] FIG. 2 is a diagram showing an outline of the configuration of an advertisement composition feature amount acquisition unit 232. [Diagram 5] 1 is a diagram showing an outline of a learning model for the learning process performed by a learning control unit 233. FIG. [Figure 6] 4 is a flowchart showing a specific example of processing by the learning device 20. [Figure 7] 2 is a schematic block diagram showing a specific example of the functional configuration of a determination device 30. FIG. [Figure 8] 4 is a flowchart showing a specific example of the process of the determination device 30. [Figure 9] FIG. 2 is a diagram illustrating an outline of a hardware configuration example of an information processing device 90 applied to the present embodiment. [Figure 10]13 is a diagram illustrating a modified example of the process for acquiring advertisement configuration features. [Figure 11] FIG. 13 is a diagram showing a modified example of the determination device 30. [Figure 12] FIG. 13 is a diagram showing a modified example of the determination device 30. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] 1 is a schematic block diagram showing the system configuration of a determination system 100 of the present invention. The determination system 100 is used to determine the advertising effectiveness obtained when an advertisement is distributed, based on information about the advertisement (hereinafter referred to as "advertising information").

[0016] The determination system 100 includes a terminal device 10, a learning device 20, and a determination device 30. The terminal device 10 and the determination device 30 are communicatively connected via a network 70. The learning device 20 and the determination device 30 may be communicatively connected via the network 70. The network 70 may be a network using wireless communication, or may be a network using wired communication. The network 70 may be configured using, for example, the Internet, or may be configured using a local area network (LAN). The network 70 may be configured by combining a plurality of networks.

[0017] 2 is a schematic block diagram showing a specific example of a functional configuration of the terminal device 10. The terminal device 10 is configured using information devices such as a smartphone, a tablet, a personal computer, a dedicated device, etc. The terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0018] The communication unit 11 is a communication device. The communication unit 11 may be configured as, for example, a network interface. The communication unit 11 performs data communication with other devices via the network 70 in response to the control of the control unit 15. The communication unit 11 may be a device that performs wireless communication or a device that performs wired communication.

[0019] The input unit 12 is configured using existing input devices such as a keyboard, a pointing device (mouse, tablet, etc.), a button, a touch panel, etc. The input unit 12 is operated by a user when inputting a user's instruction to the terminal device 10. The input unit 12 may be an interface for connecting the input device to the terminal device 10. In this case, the input unit 12 inputs an input signal generated in the input device in response to a user's input to the terminal device 10. The input unit 12 may be configured using a microphone and a voice recognition device. In this case, the input unit 12 performs voice recognition on a word spoken by the user, and inputs character string information of the recognition result to the terminal device 10. In this case, the voice recognition may be performed by the control unit 15. The input unit 12 may be configured in any manner as long as it is configured to input a user's instruction to the terminal device 10.

[0020] The output unit 13 outputs information in a form that can be recognized by the user. The output unit 13 may be, for example, an image display device such as a liquid crystal display or an organic EL (Electro Luminescence) display. The output unit 13 may be an interface for connecting the image display device to the terminal device 10. In this case, the output unit 13 generates a video signal for displaying image data and outputs the video signal to the image display device connected to the output unit 13. The output unit 13 may be a device for outputting sound such as a speaker. The output unit 13 may be an interface for connecting an audio output device such as a speaker or a headphone to the terminal device 10. In this case, the output unit 13 generates an audio signal for reproducing audio data and outputs the audio signal to the audio output device connected to the output unit 13. The output unit 13 may be configured as a touch panel integrated with the input unit 12.

[0021] The storage unit 14 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data required when the control unit 15 performs processing.

[0022] The control unit 15 is configured using a processor such as a CPU (Central Processing Unit) and a memory (main storage device). The control unit 15 functions by the processor executing a program. All or part of the functions of the control unit 15 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a semiconductor storage device (e.g., an SSD: Solid State Drive), or a storage device such as a hard disk or a semiconductor storage device built into a computer system. The above program may be transmitted via an electric communication line.

[0023] The control unit 15 may execute, for example, an application installed in its own device (terminal device 10). A specific example of such an application is an application provided to the terminal device 10 as a dedicated application for the determination system 100. Another specific example of such an application is a WEB browser application. Such an application may be installed in the terminal device 10 in advance, or may be downloaded each time a determination process is executed. For example, when implemented as a WEB browser application, the terminal device 10 may download and execute the application from a device (for example, the WEB server itself or another server) designated by the WEB server in response to the terminal device 10 connecting to the specific WEB server. The control unit 15 operates according to the program of the application being executed.

[0024] The control unit 15 controls the terminal device 10 in response to a user's operation or information received from the determination device 30. For example, the control unit 15 transmits information input by a target person or a user operating the input unit 12 to the determination device 30 by using the communication unit 11. A specific example of information input to the terminal device 10 is information on an advertisement, the effectiveness of which is to be determined. The advertisement information includes, for example, information indicating the composition of the advertisement (hereinafter referred to as "advertisement composition information"), information on the delivery of the advertisement (hereinafter referred to as "advertisement delivery information"), and advertisement format information.

[0025] The advertisement configuration information includes, for example, data on one or more advertisement elements used in an advertisement. Specific examples of advertisement element data include, for example, data on character strings (text), still images, and moving images. The advertisement delivery information includes information on the advertisement target, which is an element of the targeting design of the advertisement. The advertisement delivery information includes, for example, the age, gender, and budget of the advertisement target. The advertisement delivery information may include the advertisement delivery period and the area to which the advertisement is delivered. The advertisement format information is information indicating the format of the advertisement. The advertisement format information may include, for example, each value of the type of advertisement element included in the advertisement (e.g., text, still image, moving image, etc.), the attributes of the advertisement element (e.g., image size, length of playback time of the moving image, text length, character size, etc.), and the position of the advertisement element (e.g., top, middle, bottom, left, center, right, etc.).

[0026] For example, when information (e.g., information on the effectiveness of an advertisement) transmitted from the determination device 30 is received by the communication unit 11 via the network 70, the control unit 15 generates screen data based on the received information and causes the output unit 13 to display the screen data. Such screen data includes images and characters indicating the information transmitted from the determination device 30. For example, when information transmitted from the determination device 30 is received by the communication unit 11 via the network 70, the control unit 15 generates voice data based on the received information and causes the output unit 13 to output the voice data.

[0027] 3 is a schematic block diagram showing a specific example of the functional configuration of learning device 20. Learning device 20 is configured using an information processing device such as a personal computer or a server device. Learning device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0028] The communication unit 21 is a communication device. The communication unit 21 may be configured as, for example, a network interface. The communication unit 21 performs data communication with other devices via the network 70 in accordance with the control of the control unit 23. The communication unit 21 may be a device that performs wireless communication or a device that performs wired communication.

[0029] The storage unit 22 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may function as, for example, a known data storage unit 221, an advertisement composition feature storage unit 222, and a trained model storage unit 223.

[0030] The known data storage unit 221 stores known data used in the learning process executed in the learning device 20. The known data stored in the known data storage unit 221 includes advertising information and information indicating the effect obtained when an advertisement was distributed for each piece of advertising information (hereinafter referred to as "effect information"). The known data stored in the known data storage unit 221 may include a combination of advertising information and effect information of an advertisement that was actually distributed in the past, or may include a combination of advertising information of an advertisement that was not actually distributed and effect information estimated for that advertisement.

[0031] The advertisement composition feature storage unit 222 stores advertisement composition feature amounts. The advertisement composition feature amounts are obtained by performing feature acquisition processing on advertisement composition information of known data. For example, the advertisement composition feature amounts are obtained by using advertisement composition information and advertisement format information. The advertisement composition feature amount is a value obtained by performing a predetermined calculation using this information, and is a value indicating the feature of the advertisement composition.

[0032] The trained model storage unit 223 stores a trained model obtained by the control unit 23 performing a learning process using known data and advertisement composition features.

[0033] The control unit 23 is configured using a processor such as a CPU and a memory. The control unit 23 functions as an information control unit 231, an advertisement composition feature amount acquisition unit 232, and a learning control unit 233 by the processor executing a program. All or part of the functions of the control unit 23 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a semiconductor storage device (e.g., SSD), or a storage device such as a hard disk or a semiconductor storage device built into a computer system. The above program may be transmitted via an electric communication line.

[0034] The information control unit 231 controls the input and output of information. For example, the information control unit 231 acquires known data from other devices (information processing devices and storage media) and records the data in the known data storage unit 221. For example, the information control unit 231 transmits the learned model stored in the learned model storage unit 223 to another device (for example, the determination device 30).

[0035] The advertisement composition feature amount acquisition unit 232 acquires advertisement composition feature amounts by executing a predetermined process on the advertisement composition information included in the known data and the format information indicating the format in which the advertisement is used. Fig. 4 is a diagram showing an outline of the configuration of the advertisement composition feature amount acquisition unit 232. The advertisement composition feature amount acquisition unit 232 functions as a plurality of encoders, a plurality of adders, and a multimodal converter according to various types of advertisement elements by executing a program.

[0036] An encoder is provided for each type of advertisement element. For example, a video encoder, a still image encoder, and a text encoder are provided. In this case, multiple encoders are provided for each type. Therefore, for example, multiple video encoders, multiple still image encoders, and multiple text encoders are provided. It is desirable that each encoder is provided in a number greater than the maximum number of each of video, still images, and text used in one advertisement as a general advertisement format. By providing such a number of various encoders, it becomes possible to respond to any format. Each encoder outputs a value indicating its characteristics based on the advertisement element (e.g., video, still image, text) input according to the type. In the example of FIG. 4, each encoder outputs a multidimensional value (e.g., a 128-dimensional vector). However, the number of dimensions of the vector does not need to be limited to 128 in the embodiment.

[0037] Each adder receives a value indicating format information corresponding to each advertisement element and a value indicating a feature obtained by encoding each advertisement element. Each adder adds the input values ​​together and outputs the result. For example, type information indicating that the text is text, attribute information indicating that the text is large characters, and position information indicating that the text is arranged at the top are added to the output of a text encoder to which text arranged at the top and represented by large characters is input. The position information may be obtained by calculating a 128-dimensional vector using a method called "Positional Embedding" and adding the 128-dimensional vector output by each encoder. The type information and attribute information may be calculated using a method called "Embedding Layer" to calculate a 128-dimensional vector. The addition may be performed by adding the 128-dimensional vector output by each encoder.

[0038] The value indicating the feature output from each encoder (for example, the above-mentioned 128-dimensional vector) is input to the multimodal converter after each piece of format information is added. By integrating each value converted by the multimodal converter, an advertisement composition feature represented by a single value is generated. The advertisement composition feature acquisition unit 232 acquires the advertisement composition feature by, for example, performing such processing. For example, the Encoder processing of "Transformer" may be applied to the multimodal converter. The multimodal converter outputs values ​​(for example, a 128-dimensional vector) equal to the number of encoders. As a subsequent process, a calculation value (for example, an average value) of the multiple values ​​is calculated, and one value (for example, a 128-dimensional vector) is output. This process is the same in both FIG. 4 and FIG. 10, and may be, for example, a process of calculating an average value.

[0039] The learning control unit 233 executes a learning process using the advertisement information (particularly the advertisement delivery information) stored in the known data storage unit 221, the advertisement composition feature stored in the advertisement composition feature storage unit 222, and the effect information of those advertisements. FIG. 5 is a diagram showing an outline of a learning model of the learning process performed by the learning control unit 233. The advertisement delivery feature and the advertisement composition feature obtained based on the advertisement delivery information are explanatory variables, and the effect information is a target variable. As a specific example of such a learning process, for example, supervised learning for classification or regression such as a neural network may be used. The learning control unit 233 generates a learned model for outputting the effect information based on the input advertisement delivery feature and advertisement composition feature by performing supervised learning, for example. The learning control unit 233 records the generated learned model in the learned model storage unit 223. The learned model obtained by the learning control unit 233 may be transmitted to the determination device 30 and recorded in the determination model storage unit 321 of the determination device 30.

[0040] FIG. 6 is a flowchart showing a specific example of processing of the learning device 20. First, the information control unit 231 acquires known data (step S101). The known data may be input by a user, may be acquired from another information device by communication, or may be acquired from a recording medium connected to the learning device 20. The advertisement composition feature acquisition unit 232 acquires advertisement composition features based on advertisement composition information included in the known data (step S102). The learning control unit 233 acquires advertisement delivery features based on advertisement delivery information included in the known data. The learning control unit 233 acquires a trained model by executing a learning process using the advertisement delivery features and the advertisement composition features, and records the acquired trained model in the trained model storage unit 223 (step S103).

[0041] 7 is a schematic block diagram showing a specific example of a functional configuration of the determination device 30. The determination device 30 is configured using an information processing device such as a personal computer or a server device. The determination device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.

[0042] The communication unit 31 is a communication device. The communication unit 31 may be configured as, for example, a network interface. The communication unit 31 performs data communication with other devices via the network 70 according to the control of the control unit 33. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0043] The storage unit 32 is configured using a storage device such as a magnetic hard disk device, a semiconductor storage device, etc. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may function as a determination model storage unit 321, for example.

[0044] The judgment model storage unit 321 stores a judgment model used by the judgment unit 333 when performing the judgment process. The judgment model may be configured using information of a learned model generated in advance by a learning process, for example. Such a learning process may be executed by another device (for example, the learning device 20) or by the device itself (the judgment device 30). The judgment model does not necessarily have to be generated by a learning process. The judgment model may be configured using, for example, a lookup table that associates advertisement composition features with effect information, or a lookup table that associates advertisement delivery features and advertisement composition features with effect information, or may be configured in another manner.

[0045] The control unit 33 is configured using a processor such as a CPU and a memory. The control unit 33 functions as an information control unit 331, an advertisement composition feature amount acquisition unit 332, and a determination unit 333 by the processor executing a program. All or part of the functions of the control unit 33 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a semiconductor storage device (e.g., SSD), or a storage device such as a hard disk or a semiconductor storage device built into a computer system. The above program may be transmitted via an electric communication line.

[0046] The information control unit 331 acquires information (advertising information) corresponding to the explanatory variables of the determination target from another device such as the terminal device 10. The information control unit 331 transmits information indicating the determination result obtained by the determination unit 333 to the other device such as the terminal device 10. Such exchange of information between the information control unit 331 and the other device may be performed by communication using the communication unit 31, for example.

[0047] The advertisement composition feature amount acquisition unit 332 acquires advertisement composition feature amounts by executing a predetermined process on the advertisement composition information acquired by the information control unit 331. The process executed by the advertisement composition feature amount acquisition unit 332 is the same as the process executed in acquiring the advertisement composition feature amount when generating a trained model used by the determination unit 333. That is, the process executed by the advertisement composition feature amount 332 on the advertisement composition information is the same as the process executed by the advertisement composition feature amount acquisition unit 232 on the advertisement composition feature information of known data. In other words, the process executed by the advertisement composition feature amount acquisition unit 332 on the advertisement composition information is the same as the process executed by the configuration shown in FIG. 4. The advertisement composition feature amount acquisition unit 332 acquires advertisement composition feature amounts by executing such a process.

[0048] The determination unit 333 performs a determination process using the determination model stored in the determination model storage unit 321 and the advertisement information of the determination target. The determination process determines effect information regarding the advertisement of the determination target. The determination unit 333 outputs a determination result regarding at least the effect information.

[0049] 8 is a flowchart showing a specific example of the process of the determination device 30. First, the information control unit 331 acquires advertisement information from the terminal device 10 (step S201). The advertisement composition feature acquisition unit 332 acquires advertisement composition feature by performing a predetermined process on the advertisement composition information included in the advertisement information (step S202). The determination unit 333 performs a determination process using at least the advertisement composition feature (step S203). In this embodiment, the effectiveness information is determined by using, as explanatory variables, advertisement delivery feature obtained based on advertisement delivery information in addition to the advertisement composition feature. The determination unit 333 transmits information indicating the determination result to the terminal device 10 (step S204).

[0050] In the determination system 100 configured in this manner, advertisement composition features indicating the composition of an advertisement are acquired by common processing, regardless of the advertisement format. More specifically, by using information indicating the advertisement format (advertising format information) as an input and by providing a plurality of encoders for various types of advertisement elements (e.g., video images, still images, text) in advance, the configuration (processing) for acquiring advertisement composition features is common to a plurality of formats. Then, the advertisement effectiveness information is determined using the advertisement composition features thus acquired. Therefore, when acquiring advertisement composition features, it becomes possible to build a determination model for evaluating a new advertisement format with less effort.

[0051] Furthermore, in the determination system 100, a learning process is performed using a plurality of advertisement composition features generated using a plurality of pieces of advertisement information, and a trained model is obtained. Then, in the determination system 100, advertisement composition features related to a new advertisement to be determined are acquired, and a determination process is performed based on the advertisement composition features to determine effectiveness information of the advertisement. The composition of an advertisement has a strong correlation with the effectiveness of the advertisement. Therefore, the advertisement composition feature, which is a feature indicating the composition of the advertisement, has a correlation with the effectiveness information. Therefore, the determination system 100 configured in this manner can respond to new formats with less effort and estimate the advertising effectiveness with high accuracy.

[0052] FIG. 9 is a diagram showing an outline of a hardware configuration example of an information processing device 90 applied to this embodiment. The information processing device 90 includes a processor 91, a main storage device 92, a communication interface 93, an auxiliary storage device 94, an input / output interface 95, and an internal bus 96. The processor 91, the main storage device 92, the communication interface 93, the auxiliary storage device 94, and the input / output interface 95 are communicably connected to each other via the internal bus 96. The information processing device 90 may be applied to, for example, the learning device 20 and the determination device 30. In this case, for example, the communication unit 21 and the communication unit 31 may be configured using the communication interface 93. For example, the memory unit 22 and the memory unit 32 may be configured using the auxiliary storage device 94. In addition, the control unit 23 and the control unit 33 may be configured using the processor 91 and the main storage device 92.

[0053] (Modification) The learning control unit 233 of the learning device 20 may generate a trained model common to a plurality of different advertisement formats, or may generate an individual trained model for each advertisement format. When generating a trained model common to a plurality of different advertisement formats, the learning control unit 233 generates a common trained model by executing a learning process using advertisement composition features obtained based on advertisement information having different advertisement formats. In this case, the determination process in the determination device 30 also uses the common trained model as a determination model regardless of the advertisement format to be determined. This configuration makes it possible to respond to new advertisement formats with less effort.

[0054] When generating an individual trained model for each advertisement format, the learning control unit 233 executes a learning process using only advertisement composition features obtained based on advertisement information having the same advertisement format, thereby generating a different trained model for each advertisement format. In this case, the judgment model storage unit 321 of the determination device 30 stores a judgment model for each advertisement format. In the judgment process in the determination device 30, the judgment process is performed using a judgment model corresponding to the advertisement format to be determined. This configuration makes it possible to more accurately determine effect information.

[0055] In the above-described advertisement composition feature acquisition process, type information, attribute information, and location information are used as the advertisement format information to be used. However, the advertisement format information to be used in the advertisement composition feature acquisition process does not need to be limited to the information including these three pieces of information. FIG. 10 is a diagram showing a modified example of the advertisement composition feature acquisition process. As shown in FIG. 10, in the advertisement composition feature acquisition process, type information and attribute information may be used as the advertisement format information, and location information may not be used. For example, if the advertisement format is a format in which the arrangement of each advertisement element is predetermined or a carousel advertisement format, the location information as described above may be used, but there may be advertisements in which the location information is not necessarily clearly defined in advance. For example, a responsive advertisement format is applicable. In this way, when an advertisement composition feature is acquired for an advertisement format in which the location information is not clearly defined in advance, the advertisement composition feature may be acquired by a process as shown in FIG. 10. Whether the process as shown in FIG. 4 or the process as shown in FIG. 10 is used to acquire the advertisement composition feature may be determined by a person, or may be determined by the advertisement composition feature acquisition unit 232 or the advertisement composition feature acquisition unit 332. When the advertisement composition feature amount acquiring unit 232 or the advertisement composition feature amount acquiring unit 332 makes the determination, the determination may be made based on whether or not the input advertisement format includes location information.

[0056] In this embodiment, the terminal device 10 and the determination device 30 are configured as different devices, but may be configured as an integrated device. FIG. 11 is a diagram showing a modified example of the determination device 30 configured in this manner. The determination device 30 shown in FIG. 11 includes an input unit 34 and an output unit 35. The input unit 34 and the output unit 35 of the determination device 30 shown in FIG. 11 function similarly to the input unit 12 and the output unit 13 of the terminal device 10, respectively. The control unit 33 operates in response to an operation on the input unit 34, performs a determination process using the input advertising information, and outputs effect information using the output unit 35.

[0057] In this embodiment, the learning device 20 and the determination device 30 are configured as different devices, but may be configured as an integrated device. FIG. 12 is a diagram showing a modified example of the determination device 30 configured in this manner. The storage unit 32 of the determination device 30 shown in FIG. 12 also functions as a known data storage unit 322 and an advertisement composition feature amount storage unit 323. The control unit 33 of the determination device 30 shown in FIG. 12 also functions as a learning control unit 334. The known data storage unit 322 and the advertisement composition feature amount storage unit 323 function in the same manner as the known data storage unit 221 and the advertisement composition feature amount storage unit 222 of the learning device 20, respectively. The advertisement composition feature amount acquisition unit 332 acquires not only the advertisement composition feature amount used in the processing of the determination unit 333 of the determination device 30, but also the advertisement composition feature amount used in the processing of the learning control unit 334. The learning control unit 334 functions in the same manner as the learning control unit 233 of the learning device 20.

[0058] The learning device 20 may be implemented using a plurality of information processing devices. For example, the learning device 20 may be implemented using a device such as a cloud. For example, in the learning device 20, the memory unit 22 and the control unit 23 may be implemented in different information processing devices. For example, the memory unit 22 of the learning device 20 may be distributed and implemented in a plurality of information processing devices. The determination device 30 may be implemented using a plurality of information processing devices. For example, the determination device 30 may be implemented using a device such as a cloud. For example, in the determination device 30, the memory unit 32 and the control unit 33 may be implemented in different information processing devices. For example, the memory unit 32 of the determination device 30 may be distributed and implemented in a plurality of information processing devices.

[0059] Although an embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and designs that do not deviate from the gist of the present invention are also included. [Explanation of symbols]

[0060] 100...determination system, 10...terminal device, 11...communication unit, 12...input unit, 13...output unit, 14...storage unit, 15...control unit, 20...learning device, 21...communication unit, 22...storage unit, 221...known data storage unit, 222...advertising composition feature storage unit, 223...trained model storage unit, 23...control unit, 231...information control unit, 232...advertising composition feature acquisition unit, 233...learning control unit, 30...determination device, 31...communication unit, 32...storage unit, 321...determination model storage unit, 33...control unit, 331...information control unit, 332...advertising composition feature acquisition unit, 333...determination unit

Claims

1. an advertisement composition feature amount acquisition unit that receives advertisement composition information including data of one or more advertisement elements used in an advertisement to be determined, acquires features from the data of each advertisement element, and acquires advertisement composition feature amounts indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element; a determination unit that determines an effect obtained by delivering the advertisement to be determined by using the advertisement composition feature amount related to the advertisement to be determined and a determination model for determining an effect obtained by delivering the advertisement from the advertisement composition feature amount; A determination system comprising:

2. The determination system according to claim 1 , wherein the information indicating the format of the advertisement includes information indicating a type of the advertisement element.

3. an advertisement composition feature acquisition unit that receives advertisement composition information including data of one or more advertisement elements used in advertisements previously distributed, acquires features from the data of each advertisement element, and acquires advertisement composition feature values ​​indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element; a learning control unit that performs a learning process using the advertisement composition feature amounts related to the advertisements distributed in the past and effects obtained when the advertisements were distributed in the past, thereby generating a learned model in which the advertisement composition feature amounts are explanatory variables and the effects are objective variables; A learning system comprising:

4. an advertisement composition feature acquisition step of receiving advertisement composition information including data of one or more advertisement elements used in an advertisement to be determined, acquiring features from the data of each advertisement element, and acquiring advertisement composition feature values ​​indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element; a determination step of determining an effect obtained by delivering the advertisement to be determined by using the advertisement composition feature amount related to the advertisement to be determined and a determination model for determining an effect obtained by delivering the advertisement from the advertisement composition feature amount; The determination method has the following.

5. an advertisement composition feature acquisition step of receiving advertisement composition information including data of one or more advertisement elements used in advertisements previously distributed, acquiring features from the data of each advertisement element, and acquiring advertisement composition feature values ​​indicating features of the advertisement composition information by performing a predetermined calculation on the acquired features and information indicating an advertisement format corresponding to each advertisement element; a learning control step of performing a learning process using the advertisement composition feature amounts related to the advertisements distributed in the past and the effects obtained when the advertisements were distributed in the past to generate a learned model having the advertisement composition feature amounts as explanatory variables and the effects as objective variables; A learning method that has

6. A computer program for causing a computer to function as the determination system according to claim 1 or 2, or the learning system according to claim 3.

7. a plurality of first encoders that convert data of a first type of advertisement element into values ​​indicating feature amounts; a plurality of second encoders that convert data of a second type of advertisement element into values ​​indicating feature amounts; an advertisement composition feature acquisition device comprising: a calculation unit that calculates data corresponding to the first type on the value obtained by the first encoder, calculates data corresponding to the second type on the value obtained by the second encoder, and integrates the values ​​obtained by the calculations to generate a value indicating a feature of an advertisement composition including the first type of advertisement element and the second type of advertisement element.

Images