Device and method

Abstract

A device according to an exemplary embodiment comprises: a value information acquisition unit that acquires value information indicating a user's values; an object information acquisition unit that acquires object information about an advertisement object to be advertised to the user; and an advertisement content acquisition unit that acquires advertisement content about the advertisement object for the user by inputting, to a generative AI model, generation request information including the object information of the advertisement object and the value information of the user.

Description

Apparatus and method

[0001] The present disclosure relates to an apparatus and method for obtaining advertising content.

[0002] Patent Literature 1 discloses an information processing device that changes information indicating product attributes for each customer. This device includes a first acquisition unit that acquires first attribute information indicating the customer's attributes, a second acquisition unit that acquires third attribute information from second attribute information indicating the attributes of the product the customer is looking at in accordance with the first attribute information, a generation unit that generates image data including the third attribute information to be displayed in association with the product, and an output unit that outputs the image data to a display device looked at by the customer.

[0003] Japanese Patent Application Laid-Open No. 2020-9147

[0004] In the above technology, information to be provided to a user is simply selected from information indicating product attributes according to the user's attributes. Therefore, it is difficult to say that advertisements that are suitable for and appealing to the user are provided.

[0005] The present disclosure aims to provide an apparatus and method capable of outputting advertising content suited to a user.

[0006] An apparatus according to one aspect of the present disclosure includes a value information acquisition unit that acquires value information indicating a user's values, a target information acquisition unit that acquires target information, which is information about a promotion target to be promoted to the user, and an advertising content acquisition unit that acquires advertising content about the promotion target targeted at the user by inputting generation request information including the target information and value information of the promotion target into a generative artificial intelligence (AI) model.

[0007] In the above device, the content of the advertisement is generated by the generation AI model based on the generation request information including the target information of the advertisement target and the value information. Therefore, the content of the advertisement does not simply reflect the content of the target information of the advertisement target, but also reflects the user's value. Therefore, it is possible to provide advertisement content that is highly appealing to the user and suitable for the user.

[0008] According to one aspect of the present disclosure, it is possible to provide an apparatus and method capable of outputting advertising content suitable for a user.

[0009] FIG. 1 is a schematic diagram showing the configuration of an example information processing system. FIG. 2 is a diagram for explaining an example of value information. FIG. 3 is a diagram for explaining an example of advertising information. FIG. 4 is a flow chart showing a method for acquiring advertising information in an example information processing system. FIG. 5 is a schematic diagram showing an example of a prompt generated by an advertising message acquisition unit. FIG. 6 is a schematic diagram showing an example of a prompt generated by a font reflection unit. FIG. 7 is a schematic diagram showing an example of a prompt generated by an advertising image acquisition unit. FIG. 8 is a diagram showing an example of devices constituting the information processing system.

[0010] Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] 1 is a schematic diagram showing the configuration of an example information processing system. The information processing system 1 is a system for presenting advertising information for advertising an advertising target to a user. The advertising target includes tangible or intangible objects that can be provided to consumers, such as products, content, and services. The advertising information is composed of information that can be recognized by a user, and may include information that recommends the advertising target to a user.

[0012] An example information processing system 1 includes a user terminal 3 and an information processing device 10. In this information processing system 1, advertising information generated by an advertisement generation device 30 is output from the information processing device 10 to the user terminal 3 that accesses the information processing device 10. The advertisement generation device 30 may be provided by, for example, a server device. The user terminal 3 is configured to be able to access the information processing device 10 via a network including a wireless communication network and a fixed communication network. For example, the user terminal 3 may be a desktop PC, a laptop PC, a smartphone, a tablet terminal, a wearable terminal (e.g., a head-mounted display, smart glasses, etc.), etc. The user terminal 3 is equipped with a display for displaying information input from the information processing device 10.

[0013] The information processing device 10 outputs advertising information generated by the advertisement generation device 30 to a user terminal 3 that has accessed the information processing device 10. The information processing device 10 includes a value information acquisition unit 11, a target information acquisition unit 12, and an advertisement content acquisition unit 13. The value information acquisition unit 11 acquires value information indicating the user's values. In one example, the value information acquisition unit 11 acquires the value information from a value information database 21. The value information database 21 may be connected to the information processing device 10 via a network including a wireless communication network and a fixed communication network. The value information is information corresponding to any one of the user's interests, consciousness, personality, cognitive biases, and behavioral characteristics.

[0014] FIG. 2 is a diagram illustrating an example of value information. As shown in FIG. 2, the example of value information is composed of items indicating values ​​and information indicating the degree of a user's value for each item (hereinafter, "score" is used as an example of the information). For example, the score is set so that it is high when the corresponding value is affirmed and low when the corresponding value is denied. In one example, the value information is generated based on the results of a questionnaire, test, etc. administered to the user in advance and stored in the value information database 21. Alternatively, the value information may be estimated in advance based on user behavior data such as location information, payment information, app startup logs, etc. and stored in the value information database 21. The user's value information is stored in the value information database 21 in association with identification information that identifies the user. The value information acquisition unit 11 acquires value information corresponding to the identification information of a target user from the value information database 21.

[0015] The target information acquisition unit 12 acquires target information, which is information about an advertising target to be advertised to a user. In one example, the target information acquisition unit 12 acquires the target information from a target information database 22. The target information database 22 may be connected to the information processing device 10 via a network including a wireless communication network and a fixed communication network. The target information may include the name and description of the advertising target. For example, if the advertising target is a product, the target information may include the product name and product description. Furthermore, if the advertising target is content such as a video, the target information may include a title corresponding to the name and a synopsis corresponding to the product description. The target information is acquired, for example, from an official website operated by a supplier of the advertising target and stored in the target information database 22.

[0016] The advertisement content acquisition unit 13 acquires advertisement content for the user regarding the advertisement target by inputting generation request information including target information and value information of the advertisement target to the advertisement generation device 30. The advertisement generation device 30 in the illustrated example is composed of a first generation AI model 31, a second generation AI model 32, and a third generation AI model 33. The advertisement content acquisition unit 13 in the example is configured to acquire advertisement content that has high appeal to the user by reflecting the user's values. Note that the advertisement content in the example embodiment may be a point-of-purchase advertisement (POP advertisement) presented to the user in a virtual space.

[0017] FIG. 3 is a schematic diagram illustrating an example of a POP advertisement. As shown in FIG. 3, the example POP advertisement 50 includes a modified promotional statement 51 for promoting the promotional target to users through text information. The modified promotional statement 51 is composed of text information that conveys the content and font information that modifies the text information. The POP advertisement also includes image information 55 for promoting the promotional target.

[0018] The example advertising content acquisition unit 13 includes an advertising statement acquisition unit 13a, a font reflection unit 13b, and an advertising image acquisition unit 13c. The advertising statement acquisition unit 13a inputs first generation request information, including target information and value information of the advertising target, into the first generation AI model 31 to acquire advertising statements for advertising the advertising target to users. The advertising statements are composed of text information. The first generation request information is a so-called prompt.

[0019] The first generative AI model 31 generates output data that is a response to input data based on input data transmitted from the information processing device 10. The first generative AI model 31 is a generative AI model that outputs text data corresponding to a prompt generated by the information processing device 10. The generative AI model is a model that can generate content in response to a prompt including input data, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and output the content as output data. The generative AI model may be, for example, an interactive AI model that includes a large language model (LLM) and a user interface (UI) for interacting with a user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc.

[0020] A prompt is information indicating an instruction or question to a generating AI model. In one example, a prompt may be text data including information indicating an instruction to be executed by the AI ​​model, a task to be executed by the AI ​​model, a background / context to be considered by the AI ​​model (e.g., a role or condition), a question to be answered by the AI ​​model, and an output format of response information from the AI ​​model. Furthermore, input information to be used as the target of an instruction / task to be executed by the AI ​​model may be added to the prompt. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0021] In one example, the first generative AI model 31 may have already learned what kind of values ​​resonate with existing advertising language. This learning may be reinforcement learning. Reinforcement learning is additional learning that enables the generative AI model to output a desired answer for a specific task. In one example of reinforcement learning, for example, a dataset composed of advertising language collected from existing POP advertisements and value information of people who resonate with each advertising language is used to learn what kind of language resonates with what kind of values.

[0022] The advertising message acquisition unit 13a generates first generation request information, which is a prompt to be input to the first generation AI model 31, based on target information of the advertising target and value information of the user. For example, the advertising message acquisition unit 13a creates the first generation request information by inputting target information of the advertising target and value information into a specified first format for instructing the generation of advertising messages for the user. In one example, the first format is composed of a sentence such as, "Please create a sentence recommending the 'advertising target' to people who have values ​​such as 'value information'." In this sentence, the "value information" and the "advertising target" are defined as variables.

[0023] The advertising message acquisition unit 13a assigns the user's values ​​acquired by the value information acquisition unit 11 to the "value information" of the first format. The assigned user's values ​​may be all of the user's values ​​acquired by the value information acquisition unit 11, and may be, for example, information including items indicating values ​​and scores corresponding to the items. The advertising message acquisition unit 13a assigns the target information acquired by the target information acquisition unit 12 to the "advertising target" of the first format. The assigned target information of the advertising target may be the name and description of the advertising target. For example, only the name of the advertising target may be assigned to the "advertising target," and the description of the advertising target may be inserted into the first format as additional information.

[0024] The advertising statement acquisition unit 13a inputs the created first generation request information to the first generation AI model 31. The first generation AI model 31 outputs a response to the input first generation request information to the advertising statement acquisition unit 13a. That is, the first generation AI model 31 outputs advertising statements about the advertising target that are thought to resonate with users.

[0025] The font reflection unit 13b inputs second generation request information including the promotional text and value information into the second generation AI model 32 to obtain a modified promotional text in which the font is reflected in the promotional text. The second generation AI model 32 may be, for example, a generation AI model, and outputs an answer corresponding to the instruction indicated by the input prompt. In one example, the second generation AI model 32 may have learned what values ​​people associate with existing fonts. This learning may be reinforcement learning. In one example of reinforcement learning, for example, a dataset composed of fonts collected from existing POP advertisements and value information of people who associate with each font is used to learn what fonts associate with what values ​​people.

[0026] The font reflecting unit 13b generates second generation request information, which is a prompt to be input to the second generation AI model 32, based on the user's value information. For example, the font reflecting unit 13b generates the second generation request information by inputting the user's value information into a specified second format for instructing the presentation of a font to be applied to a modified promotional message directed to the user. In one example, the second format is configured with a sentence such as, "Please present a font that will resonate with people who have values ​​such as 'value information.'"

[0027] The font reflection unit 13b substitutes the user's values ​​acquired by the value information acquisition unit 11 into the "value information" of the second format. The user's values ​​to be substituted may be all of the user's values ​​acquired by the value information acquisition unit 11, and may be, for example, information including items indicating values ​​and scores corresponding to the items.

[0028] The font reflection unit 13b inputs the created second generation request information to the second generation AI model 32. The second generation AI model 32 outputs a response to the input second generation request information to the font reflection unit 13b. That is, the second generation AI model 32 outputs a font that is thought to resonate with users. The font reflection unit 13b applies the output font to the promotional text, thereby generating a modified promotional statement in which the font information is reflected in the text data of the promotional text. The modified promotional statement may be output, for example, as image data.

[0029] The promotional image acquisition unit 13c acquires a promotional image including a modified promotional statement by inputting third generation request information, which is a prompt including a modified promotional statement and value information, into the third generation AI model 33. In one example embodiment, the promotional image acquired by the promotional image acquisition unit 13c is a POP advertisement to be output to the user terminal 3.

[0030] The third generation AI model 33 may be, for example, an image generation AI that outputs advertising content for a target advertisement for a user as an image. For example, when a prompt including image data and text data is input, the image generation AI outputs an image according to the prompt. An example of the third generation AI model 33 may have learned what kind of values ​​existing POP advertisements resonate with. This learning may be reinforcement learning. In one example of reinforcement learning, for example, a dataset composed of existing POP advertisements and value information of people who resonated with each POP advertisement is used to learn what kind of POP advertisements resonate with what kind of values ​​people.

[0031] The advertising image acquisition unit 13c generates third generation request information based on the modified advertising copy and the user's value information. For example, the advertising image acquisition unit 13c creates the third generation request information by inputting the modified advertising copy and the value information into a specified third format for instructing the generation of a POP advertisement aimed at the user. In one example, the third format is configured with a sentence such as, "Please generate a POP advertisement including a 'modified advertising copy' so that it will resonate with people who have values ​​such as the 'value information'."

[0032] The promotional image acquisition unit 13c assigns the user's values ​​acquired by the value information acquisition unit 11 to the "value information" of the third format. The assigned user's values ​​may be all of the user's values ​​acquired by the value information acquisition unit 11, and may be, for example, information including items indicating values ​​and scores corresponding to the items. The promotional image acquisition unit 13c assigns the modified promotional text acquired by the font reflection unit 13b to the "modified promotional text" of the third format.

[0033] The promotional image acquisition unit 13c inputs the created third generation request information to the third generation AI model 33. The third generation AI model 33 outputs a response to the input third generation request information to the promotional image acquisition unit 13c. In other words, the third generation AI model 33 outputs a POP advertisement that is expected to resonate with users to the promotional image acquisition unit 13c. The promotional image acquisition unit 13c can output the POP advertisement generated by the third generation AI model 33 to the user terminal 3.

[0034] FIG. 4 is a flow chart showing a method for acquiring advertising information in an exemplary information processing system. FIGS. 5 to 7 are schematic diagrams illustrating prompts generated by the information processing device 10. In the processing in the exemplary information processing system 1, first, the value information acquisition unit 11 acquires the user's value information (step S1). For example, if the information processing system 1 provides a virtual space to the user, the user's value information may be acquired in response to the occurrence of an event that executes an advertisement within the virtual space. In this case, the value information acquisition unit 11 acquires the user's value information from the value information database 21 based on the identification information of the user to whom the advertisement is to be provided.

[0035] Next, the target information acquisition unit 12 acquires the content of the advertising target (step S2). That is, the target information acquisition unit 12 acquires the name and description of the advertising target from the target information database 22. Next, the advertising content acquisition unit 13 acquires the POP advertisement, which is the advertising content. Specifically, first, the advertising statement acquisition unit 13a acquires advertising statements (step S3). In step S3, the advertising statement acquisition unit 13a outputs a prompt to the first generation AI model 31 to generate advertising statements for advertising the advertising target acquired in step S2 to people who have the value information acquired in step S1, as shown in FIG. 5. In the example of FIG. 5, the value information and the content of the advertising target are shown together with an instruction statement saying, "Please create statements recommending the advertising target to people who have the following values." As a result, the first generation AI model 31 generates advertising statements.

[0036] Next, a modified advertising statement is obtained by reflecting the font in the advertising statement (step S4). In step S4, the font reflecting unit 13b outputs a prompt to the second generation AI model 32 to obtain a font that will resonate with people who have the value information obtained in step S1, as shown in Figure 6. The font reflecting unit 13b reflects the font output as a response from the second generation AI model 32 in the advertising statement obtained in step S3, thereby generating a modified advertising statement.

[0037] Next, the promotional image acquisition unit 13c acquires a POP advertisement including the modified promotional text (step S5). In step S4, the promotional image acquisition unit 13c outputs a prompt to the third generation AI model 33 to generate a POP advertisement that will resonate with people who have the value information acquired in step S1, as shown in FIG. 7. The prompt in the illustrated example includes an image file of the modified promotional text acquired in step S5 attached. The third generation AI model 33 outputs the POP advertisement in response to the prompt. The information processing device 10 outputs the POP advertisement acquired from the third generation AI model 33 to the user terminal 3. On the user terminal 3, the POP advertisement is displayed, for example, at a predetermined position in a virtual space (step S6).

[0038] As described above, the information processing device 10 includes a value information acquisition unit 11 that acquires value information indicating the user's values, a target information acquisition unit 12 that acquires target information, which is information about the advertising target to be advertised to the user, and an advertising content acquisition unit 13 that acquires the content of the advertising about the advertising target aimed at the user by inputting generation request information including the target information and value information of the advertising target to the advertising generation device 30.

[0039] In the above device, the advertisement content is generated by the advertisement generation device 30 based on generation request information including target information and value information of the advertisement target. Therefore, the advertisement content does not simply reflect the content of the target information of the advertisement target, but also reflects the user's values. Therefore, advertisement content that is highly appealing to the user and suited to the user can be provided. In particular, in the above embodiment, a model that has been trained on the relationship between value information and advertisement content is used. Therefore, even if the user's value information contains content that appears contradictory at first glance, advertisement content that reflects such contradictions, i.e., advertisement content that is optimized for the user, is generated.

[0040] The advertising content acquisition unit 13 may include an advertising statement acquisition unit 13a that acquires advertising statements for advertising the advertising target targeted at the user by inputting first generation request information including target information and value information of the advertising target to the first generation AI model 31. In this configuration, the user's values ​​can be reflected in the advertising statements, which are one of the elements that make up the advertising content.

[0041] The first generation AI model 31 has completed reinforcement learning to determine which values ​​resonate with existing advertising text, and the advertising text acquisition unit 13a may create first generation request information by inputting target information and value information for the advertising target into a specified first format for instructing the generation of advertising text for users. In this configuration, variation in generation instructions to the first generation AI model 31 is unlikely to occur, and advertising text that reflects values ​​is consistently output.

[0042] The advertising content acquisition unit 13 may include a font reflection unit 13b that acquires a modified advertising statement that reflects font in advertising statement by inputting second generation request information including advertising statement and value information into the second generation AI model 32. In this configuration, the user's values ​​can be directly reflected in font, which is one of the elements that make up the advertising content.

[0043] The second generation AI model 32 may have undergone reinforcement learning to determine what values ​​resonate with existing fonts. The font reflection unit 13b may create second generation request information by inputting promotional text and value information into a specified second format for instructing the generation of a modified promotional message for users. In this configuration, variation in generation instructions to the second generation AI model 32 is unlikely to occur, and fonts that reflect values ​​are reliably output.

[0044] The advertising content acquisition unit 13 may include an advertising image acquisition unit 13c that acquires an advertising image including a modified advertising statement by inputting third generation request information including the modified advertising statement and value information into the third generation AI model. In this configuration, the advertising image that constitutes the advertising content can directly reflect the user's values.

[0045] The third generation AI model 33 may have undergone reinforcement learning to determine which values ​​resonate with existing promotional images. The promotional image acquisition unit 13c may create third generation request information by inputting a qualifying promotional statement and value information into a specified third format for instructing the generation of a promotional image for users. In this configuration, variation in generation instructions to the third generation AI model 33 is unlikely to occur, and promotional images that reflect values ​​are reliably output.

[0046] In one exemplary embodiment, an example has been shown in which the information processing device 10 is connected to the value information database 21, the target information database 22, and the advertisement generation device 30 via a network, but the information processing device 10 may be configured to include some or all of the functions of the value information database 21, the target information database 22, and the advertisement generation device 30. Also, for example, the functions of the information processing device 10 and the advertisement generation device 30 may be implemented in the user terminal 3. In this case, the value information database 21 and the target information database 22 may be implemented in the user terminal 3, or may be connected to the user terminal 3 via a network.

[0047] Although an example is described in which the first generative AI model 31 and the second generative AI model 32 are configured using a large-scale language model, the first generative AI model 31 and the second generative AI model 32 may also be configured using other AI models.

[0048] As an example of value information, a form showing the degree of a user's values ​​as a score has been given, but the value information may also be information that expresses the degree of a user's values ​​in natural language, such as "high" or "low."

[0049] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0050] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0051] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. Fig. 8 is a diagram illustrating an example of a hardware configuration of the information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0052] In the description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0053] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0054] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, each functional block such as the advertisement content acquisition unit 13 described above may be realized by the processor 1001.

[0055] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the advertisement content acquisition unit 13 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0056] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0057] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0058] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0059] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0060] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0061] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0062] Notification of information is not limited to the aspects / embodiments described in this disclosure, and may be performed using other methods.

[0063] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0064] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0065] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0066] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0067] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0068] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0069] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0070] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0071] In addition, terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0072] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0073] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0074] The names used for the above parameters are not limiting in any way, and furthermore, the mathematical formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure.

[0075] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like, all of which are considered to be "determining." "Determining" and "determining" may also include resolving, selecting, choosing, establishing, comparing, and the like, all of which are considered to be "determining." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Also, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0076] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0077] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0078] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0079] The "unit" in the configuration of each of the above devices may be replaced with "means," "circuit," "device," etc.

[0080] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0081] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0082] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0083] 10...information processing device (device), 11...value information acquisition unit, 12...target information acquisition unit, 13...advertising content acquisition unit, 13a...advertising text acquisition unit, 13b...font reflection unit, 13c...advertising image acquisition unit, 30...advertising generation device, 31...first generation AI model, 32...second generation AI model, 33...third generation AI model.

Claims

1. A device comprising: a value information acquisition unit that acquires value information indicating a user's values; a target information acquisition unit that acquires target information, which is information about an advertising target to be advertised to the user; and an advertising content acquisition unit that acquires advertising content for the advertising target directed to the user by inputting generation request information including the target information of the advertising target and the value information of the user into a generation AI model.

2. The device described in claim 1, wherein the advertising content acquisition unit includes an advertising message acquisition unit that acquires advertising messages for advertising the advertising target to the user by inputting first generation request information including the target information and the value information of the advertising target into a first generation AI model.

3. The device described in claim 2, wherein the first generation AI model has undergone reinforcement learning to determine which people with which values ​​will resonate with existing promotional text, and the promotional text acquisition unit creates the first generation request information by inputting the target information and the value information of the promotional target into a specified first format for instructing the generation of the promotional text aimed at the user.

4. The device described in claim 2, wherein the advertising content acquisition unit includes a font reflection unit that acquires modified advertising text that reflects fonts in the advertising text by inputting second generation request information including the advertising text and the value information into a second generation AI model.

5. The device described in claim 4, wherein the second generation AI model has undergone reinforcement learning to determine what values ​​existing fonts will resonate with, and the font reflection unit creates the second generation request information by inputting the promotional text and the value information into a specified second format for instructing the generation of the modified promotional text aimed at the user.

6. The device described in claim 4, wherein the advertising content acquisition unit includes an advertising image acquisition unit that acquires an advertising image including the modified advertising text by inputting third generation request information including the modified advertising text and the value information into a third generation AI model.

7. The device described in claim 6, wherein the third generation AI model has undergone reinforcement learning to determine what values ​​resonate with existing promotional images, and the promotional image acquisition unit creates the third generation request information by inputting the modified promotional text and the value information into a specified third format for instructing the generation of the promotional image aimed at the user.

8. A method comprising the steps of: acquiring target information, which is information about a promotion target; acquiring value information indicating a user's values; and acquiring advertising content for the promotion target aimed at the user by inputting generation request information including the target information and value information of the promotion target into a generation AI model.

Images