Server, method, and program

Abstract

To obtain a promotional message that can be used to promote a product or service. [Solution] A server 12 generates candidates for promotional messages for a product or service based on information about the product or service. The server 12 obtains a plurality of modified promotional messages, which are results of modifications to the candidate promotional messages and which are modified by each of a plurality of modifiers. The server 12 obtains a voting result for each of the plurality of modified promotional messages, which is a voting result by each of a plurality of voters.

Description

[Technical field]

[0001] The present disclosure relates to a server, a method, and a program. [Background technology]

[0002] Conventionally, a management device that generates information used for advertising or sales promotion of a product is known (for example, Patent Document 1). Patent Document 1 discloses that evaluation items of a product are input to a trained estimation model, and at least one statement output by the estimation model is set as a candidate for a promotional statement for the product. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-149229 A Summary of the Invention [Problem to be solved by the invention]

[0004] Although Patent Document 1 discloses that the words output from a trained estimation model are used as candidates for product appeal words, it is difficult to directly use the appeal words for promoting products or services. Therefore, even if the technology disclosed in Patent Document 1 is used, there is a problem in that it is difficult to obtain an advertising message that can be used for promoting products or services.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to obtain an advertising message that can be used to promote the sale of a product or service. [Means for solving the problem]

[0006] A first aspect of the present disclosure is a server comprising: a candidate generation unit that generates candidates for advertising messages for a product or service based on information about the product or service; a correction result acquisition unit that acquires correction results for the candidate advertising messages, where the corrected candidates are multiple revised advertising messages corrected by each of multiple modifiers; and a voting result acquisition unit that acquires voting results for each of the multiple revised advertising messages, where the voting results are obtained by each of multiple voters. Effect of the Invention

[0007] According to the present disclosure, an advantage is obtained in that an advertising message that can be used to promote a product or service can be obtained. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of a schematic configuration of an advertising message generating system according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a diagram for explaining an overview of the present embodiment. [Diagram 3] FIG. 2 is a schematic block diagram of a computer functioning as each device in the system. [Figure 4] FIG. 2 is an explanatory diagram for explaining the process executed by the advertising message generating system of the present embodiment. [Diagram 5] FIG. 1 is a diagram showing an example of information recorded in a blockchain. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the embodiments will be described in detail with reference to the drawings.

[0010] <Configuration of advertising message generation system> FIG. 1 is a block diagram showing an advertising message generating system 10 according to the present embodiment. As shown in FIG. 1, the advertising message generating system 10 according to the present embodiment includes an order terminal 11, a server 12, a plurality of modification terminals 14A, 14B, 14C,..., a plurality of voting terminals 16A, 16B, 16C,..., and a plurality of blockchain nodes 18A, 18B, 18C,.... Each device is connected to be able to communicate with each other via a network N such as the Internet. In the following, the plurality of modification terminals 14A, 14B, 14C,... are simply referred to as modification terminals 14, the plurality of voting terminals 16A, 16B, 16C,... are simply referred to as voting terminals 16, and the plurality of blockchain nodes 18A, 18B, 18C,... are simply referred to as blockchain nodes 18.

[0011] In the advertising message generation system 10, advertising messages for products or services are generated. Fig. 2 is a diagram for explaining an outline of this embodiment. As shown in Fig. 2, in this embodiment, when generating advertising messages for products or services, advertising messages are generated and selected by a trained model, which is a generative artificial intelligence (AI), a plurality of modifiers U1, and a plurality of voters U2.

[0012] Specifically, as shown in FIG. 2, first, information about a product or service is input to a trained model generated in advance by a machine learning algorithm to generate candidates for advertising messages. The trained model of this embodiment is a so-called generative AI, which has learned excellent Japanese advertising messages (catchphrases) from the past and has been adjusted for the purpose of developing Japanese creative writing. There are one or more candidates for advertising messages. The information about the product or service includes, for example, at least one of information representing the category of the product or service and information about the consumer attributes of the product or service. The information representing the category is, for example, information such as food, clothing, and cosmetics, and may be more detailed classification information. The information about the consumer is, for example, information such as men in their twenties and women in their twenties, and may be more detailed classification information.

[0013] Furthermore, in this embodiment, the following four pieces of information are also input into the trained model as information about the product or service to generate candidates for advertising messages.

[0014] (1) In this embodiment, information on the usual psychological attributes and behavioral attributes of the target consumer are input to the trained model. For example, information on psychological attributes and behavioral attributes, such as what personality traits consumers who purchase the target product or service have and what values ​​they value (such as valuing family or friends), is input to the trained model. For example, information such as "the target consumer is a housewife who values ​​her family and puts her children first" and "she is concerned about rough skin" is input to the trained model. This makes it possible to generate candidates for advertising messages for consumers who have the corresponding psychological attributes and behavioral attributes.

[0015] (2) In this embodiment, the type of attitude or behavior change that will occur when a target consumer uses a target product or service (or brand), and the consumer tendencies that are the basis for the possibility of such change, are input into the trained model. For example, information such as "your skin will become smooth" or "you will wake up refreshed" is input into the trained model. This makes it possible to generate candidates for advertising messages that will resonate with consumers who wish to change their own attitude or behavior.

[0016] (3) In this embodiment, information regarding the tone that the product or service (or brand) is aiming for is input to the trained model. Specifically, information such as whether the target product or service (or brand) is assertive or compassionate, bright or dark, emotional or impersonal, etc. is input to the trained model. This generates candidates for advertising messages that are in line with the intention of the client (specifically, the brand image), which will be described later.

[0017] (4) In this embodiment, information such as the current status of the category to which the product or service belongs, what the customer wants to do in Japan (future outlook), etc. is input to the trained model. This generates candidates for advertising messages according to the current status of the target product or service and the customer's intentions.

[0018] In the above-mentioned Patent Document 1, only the functional value of the product or service is emphasized. For example, only functional information such as the size and taste of the product is input to the trained estimation model as evaluation items of the product. In contrast, in the present embodiment, by inputting the above-mentioned information to the trained model, candidates for advertising messages that emphasize emotional value are generated, and thus candidates for advertising messages that resonate more with consumers are generated.

[0019] Next, as shown in FIG. 2, each of a plurality of modifiers U1 creates a modified promotional message by modifying the candidate promotional message.

[0020] Next, as shown in FIG. 2, each of the multiple voters U2 determines which of the multiple revised advertising / promotional messages is appropriate for the target product or service, and votes for the multiple revised advertising / promotional messages.

[0021] A final promotional message for the target product or service is then determined based on the votes for the revised promotional message.

[0022] For example, consider a case where there is a request to create an advertising message for one product (one case). In this case, for example, by inputting a prompt such as "Please generate five catchphrases for cosmetic A. Cosmetic A is a cosmetic for XX, and the target consumers are women in their 30s to 50s. The target consumers are housewives who care for their families and put their children first. The target consumers are also concerned about rough skin. The consumers can expect to have smooth skin by using cosmetic A. The tone that cosmetic A aims for is XX. Cosmetic A's current market position is XX, but its future outlook is to aim for a state like XX," into the trained model, and five candidate advertising messages are generated.

[0023] Next, for example, three modifiers each modify each of the five candidate advertising messages to create 15 modified advertising messages. Then, for example, 100 voters vote for the 15 modified advertising messages. For example, one voter votes for the modified advertising message that he / she thinks is the best among the 15 modified advertising messages. Then, the modified advertising message with the most votes is adopted as the final advertising message.

[0024] In addition, rewards are given in the above process. For example, a predetermined amount of cash or points is given as a reward to the person who created the revised advertising message that received the most votes. Also, for example, a predetermined amount of cash or points is given as a reward to the voters who voted for the revised advertising message that received the top 1 to 3 votes.

[0025] Various data obtained in the process of creating the final advertising message is stored in the blockchain held by the blockchain node 18. For example, the above-mentioned prompt, candidate advertising message, corrected advertising message, final advertising message, voting results, information on cash or points given to the corrector, and information on cash or points given to the voter are stored in the blockchain. A specific description will be given below.

[0026] As shown in FIG. 1, the server 12 functionally comprises a candidate generating unit 120, a correction result acquiring unit 122, a voting result acquiring unit 124, and an output unit 126.

[0027] The server 12, the modification terminal 14, the voting terminal 16, and the blockchain node 18 can be realized, for example, by a computer 70 shown in FIG. 3. The computer 70 includes a CPU 71, a memory 72 as a temporary storage area, and a non-volatile storage unit 73. The computer 70 also includes an input / output interface (I / F) 74 to which an input / output device or the like (not shown) is connected, and a read / write (R / W) unit 75 that controls reading and writing of data to a recording medium. The computer 70 also includes a network I / F 76 that is connected to a network such as the Internet. The CPU 71, the memory 72, the storage unit 73, the input / output I / F 74, the R / W unit 75, and the network I / F 76 are connected to each other via a bus 77.

[0028] The storage unit 73 can be realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage unit 73 as a storage medium stores a program for operating the computer 70. The CPU 71 reads the program from the storage unit 73, expands it in the memory 72, and sequentially executes the processes contained in the program.

[0029] <Function of advertising message generation system 10>

[0030] Next, the operation of the advertising message generating system 10 of this embodiment will be described. The various operations of the advertising message generating system 10 can be realized, for example, by a program that can be installed in a computer. Specifically, the server 12 can perform various operations related to the creation of advertising messages by installing a program in advance. The advertising message generating system 10 executes the sequence shown in FIG. 4.

[0031] In step S100, the order terminal 11 outputs a signal representing a request to create an advertising message to the server 12. Specifically, the orderer who operates the order terminal 11 requests the creation of an advertising message for a product or service for which he / she wishes to create an advertising message. For example, the orderer who operates the order terminal 11 requests the server 12 to create an advertising message for the product or service by inputting various information into a predetermined input form displayed on the display unit (not shown) of the order terminal 11. For example, the input form is input with information about the product or service (for example, at least one of information representing the product or service category, information about the consumer of the product or service, information representing the psychological or behavioral attributes of the consumer who is the target of the product or service, information representing what kind of attitude or behavioral change will occur by the consumer using the product or service, information representing the tone that the product or service aims for, and information representing the current situation or future prospects of the category to which the product or service belongs).

[0032] In step S102, the candidate generation unit 120 of the server 12 generates candidates for the advertising message of the target product or service based on the creation request output in step S100. Specifically, the candidate generation unit 120 of the server 12 acquires the received request for creating the advertising message. Then, information about the target product or service is input to a trained model that has been generated in advance by machine learning. The trained model outputs candidates for the advertising message of the target product or service. More specifically, the candidate generation unit 120 generates candidates for the advertising message of the product or service by inputting a prompt corresponding to the information about the product or service to a trained model that has been generated in advance for generating the advertising message. For example, the candidate generation unit 120 of the server 12 displays an "advertising message creation button" on the display unit (not shown) of the order terminal 11, and in response to the orderer pressing the "advertising message creation button," inputs a prompt corresponding to the information about the product or service to a trained model that has been generated in advance for generating the advertising message, thereby generating candidates for the advertising message of the product or service. As mentioned above, the pre-created trained model for generating advertising messages is a generative AI such as ChatGPT, which learns from excellent Japanese advertising messages (catchphrases) from the past and is pre-tuned for the purpose of developing Japanese creative writing.

[0033] In step S104, the candidate generating unit 120 of the server 12 presents the candidates for advertising messages generated in step S102 to the editing terminal 14. For example, the candidate generating unit 120 of the server 12 presents the candidates for advertising messages to the editing terminal 14 using a dedicated site (browser). For example, the candidates for advertising messages are presented only to the editing terminals 14 of the pre-registered revisers who satisfy the conditions related to the requested case (for example, the attributes of the target consumer).

[0034] The candidate generating unit 120 may extract a corrector, a candidate for a corrector, a voter or a candidate for a voter from among a plurality of candidates based on information about a product or service. For example, if a result that a certain product is liked is obtained in a preliminary questionnaire, people who like the product may be extracted as a corrector, a candidate for a corrector, a voter or a candidate for a voter.

[0035] The candidate generating unit 120 may extract a reviser, a candidate reviser, a voter, or a candidate voter according to the degree of similarity between attribute information indicating the attributes of each of the multiple candidates and information related to the product or service. For example, if the consumer of the product or service is a man in his twenties, a reviser, a candidate reviser, a voter, or a candidate voter who is a man in his twenties may be extracted from the multiple candidates.

[0036] In step S106, the multiple modifiers operate their own editing terminals 14 to modify the advertising message presented in step S104, thereby creating a modified advertising message.

[0037] In step S108, the revision result acquisition unit 122 of the server 12 acquires the revised advertising messages created in step S106.

[0038] In step S110, the candidate generator 120 of the server 12 presents to the voting terminal 16 the revised advertising message obtained in step S108.

[0039] In step S112, a plurality of voters operate their voting terminals 16 to vote for the plurality of revised promotional messages presented in step S110.

[0040] In step S114, the voting result acquisition unit 124 of the server 12 acquires the voting results obtained in step S112. Based on the voting results, the voting result acquisition unit 124 of the server 12 determines the revised advertising message with the maximum number of votes as the final advertising message for the product or service.

[0041] In step S114, the output unit 126 of the server 12 outputs to the order terminal 11 the final advertising message determined in step S114.

[0042] Next, the output unit 126 records in the blockchain information about the product or service, the number of votes received by the modifier who created the revised advertising message that was adopted as the final advertising message, and information about the product or service for which the final advertising message was created.

[0043] Fig. 5 is a diagram showing an example of information recorded in the blockchain held by the blockchain node 18. As shown in Fig. 5, as advertising message information, information on the product or service, the final advertising message, information on the modifier who created the amended advertising message adopted as the final advertising message, and the number of votes are stored in a block in the blockchain.

[0044] By using this information stored in the blockchain, it becomes possible to know which modifier to ask to make corrections the next time an advertising message for another product or service is created. In addition, since the blockchain also records categories or consumers as information related to products or services, it becomes possible to know which modifier to ask to make corrections for what kind of product or service it is. In addition, by treating the various data stored in the blockchain as big data, it is also possible to select an appropriate modifier or voter for each requested case. For example, notifications are sent to, for example, tens to hundreds of people who meet the conditions set for the requested case, and modifiers or voters are selected on a first-come, first-served basis.

[0045] Therefore, for example, the next time the server 12 creates a promotional message for a product or service, it may refer to the above information recorded in the blockchain to select a modifier, thereby realizing matching between the product or service and the creator of the promotional message.

[0046] As described above, the corrector may be given cash or points according to the number of votes. In this case, for example, cash or point information is stored in the blockchain as corrector information. The points may be used within the system or may be used outside the system. This is expected to increase the motivation of the corrector and to create more appropriate advertising and promotional messages. As described above, the voter may also be given cash or points according to the ranking of the corrected advertising and promotional message for which he or she voted.

[0047] In addition, the output unit 126 may retrain the trained model based on information about the product or service for which the final advertising message was created and data recorded in the blockchain. As shown in Fig. 5, the blockchain records information about the product or service and the final advertising message in association with each other. Therefore, by using this data to retrain the trained model, it is possible to generate better candidates for advertising messages.

[0048] As described above, the server of the advertising message generating system according to the present embodiment generates candidates for advertising messages for products or services based on information about the products or services. Next, the server acquires a plurality of amended advertising messages, which are the results of amendments to the candidate advertising messages and which have been amended by each of the plurality of modifiers. Next, the server acquires a voting result for each of the plurality of amended advertising messages and which has been voted by each of the plurality of voters. Then, based on the voting results for the plurality of amended advertising messages, the server outputs at least one amended advertising message out of the plurality of amended advertising messages as a final advertising message for the product or service. This makes it possible to acquire an advertising message that can be used for sales promotion of the product or service.

[0049] The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the spirit and scope of the present invention.

[0050] For example, in the present embodiment, the case where candidates for advertising messages are generated using a trained model has been described as an example, but the present invention is not limited to this, and candidates for advertising messages may be generated using other methods. For example, information about a product or service may be linked to candidates for advertising messages and stored in a database in advance, and when information about a target product or service is received, candidates for advertising messages corresponding to the information may be read from the database to generate candidates for advertising messages.

[0051] The effects obtained by this embodiment are as follows.

[0052] As described above, the trained model used in this embodiment is a uniquely tuned trained model. In addition, the trained model has been adjusted for the purpose of developing Japanese creative writing by learning excellent Japanese catchphrases from the past. Therefore, according to this embodiment, it is possible to generate more appropriate candidates for advertising messages.

[0053] In addition, the present embodiment can maintain the transparency of the advertisement message creation process and the voting process, which contributes to preventing tampering. In particular, the voting process is performed before the advertisement message is published, and a more appropriate advertisement message is created through the voting process. This improves the reliability and security of the advertisement message.

[0054] In addition, as in this embodiment, the target demographic of the actual product or service is extracted from within the community and participates as editors for the advertising message generated by the trained model, which is a generative AI, which is an innovative initiative that is unprecedented in the industry. By directly involving the final consumers in the creation process of the advertising message, it is possible to create more effective and relatable marketing content.

[0055] In addition, in this embodiment, the efficiency and speed provided by the trained model and the creative insight that the human community provides that is unique to humans (and unique to the target of the product or service) make it possible to write more efficiently and on a large scale for each target, while also having a self-cleaning effect that catches errors and plagiarism made by the trained model.

[0056] In addition, the use of blockchain in this embodiment can provide a significant differentiation from conventional copywriting solutions in that it increases the transparency and reliability of the promotional message creation and evaluation process.

[0057] In addition, a points system is used to keep modifiers and voters motivated by awarding points that are recorded on the blockchain.

[0058] Furthermore, although the present specification has been described as an embodiment in which the program is pre-installed, the program may also be provided by being stored on a computer-readable recording medium.

[0059] The following supplementary notes are disclosed below. (Appendix 1) a candidate generator for generating candidates for advertising messages for the products or services based on information about the products or services; a correction result acquisition unit that acquires a plurality of corrected advertising messages, which are correction results of the candidates for the advertising message and are corrected by each of a plurality of correctors; a voting result acquisition unit that acquires a voting result for each of the plurality of revised advertising messages by each of the plurality of voters; A server comprising: (Appendix 2) The voting result acquisition unit determines at least one of the plurality of revised advertising messages as a final advertising message for the product or service based on the voting results for the plurality of revised advertising messages; further comprising an output unit for outputting the final advertising message; The server according to claim 1. (Appendix 3) Information about products or services may include: Information that represents the psychological or behavioral attributes of the consumers targeted by the product or service; Information showing what attitude or behavioral change will occur as a result of the consumer's use of the product or service; Information that describes the tone that your product or service aims to achieve; and Contains at least one piece of information that describes the current status or future outlook of the category to which the product or service belongs; 2. A server as described in Appendix 1 or Appendix 2. (Appendix 4) The information about the goods or services includes at least one of information describing a category of goods or services and information about consumers of the goods or services; The server according to any one of claims 1 to 3. (Appendix 5) The candidate generation unit extracts the reviser, the candidate for the reviser, the voter, or the candidate for the voter from a plurality of candidates based on information on a product or service. The server according to any one of claims 1 to 4. (Appendix 6) the candidate generation unit extracts the reviser, the candidate reviser, the voter, or the candidate voter according to a degree of similarity between attribute information indicating attributes of each of the plurality of candidates and information related to the product or service; A server according to any one of claims 1 to 5. (Appendix 7) the voting result acquisition unit determines, based on the voting results, the revised advertising message with the largest number of votes as a final advertising message for the product or service; A server according to any one of claims 1 to 6. (Appendix 8) the candidate generator generates candidate promotional messages for the product or service by inputting the prompts corresponding to the information about the product or service into a pre-created trained model for generating promotional messages; A server according to any one of claims 1 to 7. (Appendix 9) Recording on the blockchain the number of votes of the modifier who created the revised advertising message adopted as the final advertising message and information about the product or service for which the final advertising message was created; A server according to any one of claims 1 to 8. (Appendix 10) retraining a pre-trained model for generating promotional messages based on the information about the product or service for which the final promotional message was generated and the data recorded in the blockchain; A server according to any one of claims 1 to 9. (Appendix 11) generating candidate promotional messages for the product or service based on the information about the product or service; obtaining a plurality of revised advertising / promotion messages, the revised advertising / promotion messages being revision results for the candidate advertising / promotion messages, each revised by a plurality of revisers; obtaining a voting result for each of the plurality of modified promotional messages by each of the plurality of voters; The way a process is carried out by a computer. (Appendix 12) generating candidate promotional messages for the product or service based on the information about the product or service; obtaining a plurality of revised advertising / promotion messages, the revised advertising / promotion messages being revision results for the candidate advertising / promotion messages, each revised by a plurality of revisers; obtaining a voting result for each of the plurality of modified promotional messages by each of the plurality of voters; A program that causes a computer to execute a process. [Explanation of symbols]

[0060] 10 Advertising message generation system 11 Ordering terminal 12 Server 14A, 14B, 14C, Correction terminal 16A, 16B, 16C, Voting terminals 18A, 18B, 18C, Blockchain Node 120 Candidate generation section 122 Correction result acquisition part 124 Voting result acquisition unit 126 Output section

Claims

1. a candidate generator for generating candidates for advertising messages for the products or services based on information about the products or services; a correction result acquisition unit that acquires a plurality of corrected advertising messages, which are correction results of the candidates for the advertising message and are corrected by each of a plurality of correctors; a voting result acquiring unit for acquiring a voting result for each of the plurality of revised advertising messages by each of the plurality of voters, and determining a final advertising message for the product or service based on the voting result for the plurality of revised advertising messages; an output unit for outputting the final advertising message; A server comprising:

2. the voting result acquisition unit determines at least one of the plurality of revised advertising messages as a final advertising message for the product or service based on the voting results for the plurality of revised advertising messages; The server of claim 1 .

3. Information about products or services may include: Information that represents the psychological or behavioral attributes of the consumers targeted by the product or service; Information showing what attitude or behavioral change will occur as a result of the consumer's use of the product or service; Information that describes the tone that your product or service aims to achieve; and Contains at least one piece of information that describes the current situation or future outlook for the category to which the product or service belongs; The server according to claim 1 or 2.

4. The information about the goods or services includes at least one of information describing a category of goods or services and information about consumers of the goods or services; The server according to claim 1 or 2.

5. The candidate generation unit extracts the reviser, the candidate for the reviser, the voter, or the candidate for the voter from a plurality of candidates based on information on a product or service. The server according to claim 1 or 2.

6. the candidate generation unit extracts the reviser, the candidate reviser, the voter, or the candidate voter according to a degree of similarity between attribute information indicating attributes of each of the plurality of candidates and information related to the product or service; The server according to claim 5.

7. the voting result acquisition unit determines, based on the voting results, the revised advertising message with the largest number of votes as a final advertising message for the product or service; The server according to claim 1 or 2.

8. the candidate generator generates candidate promotional messages for the product or service by inputting the prompts corresponding to the information about the product or service into a pre-created trained model for generating promotional messages; The server according to claim 1 or 2.

9. Recording on the blockchain the number of votes of the modifier who created the revised advertising message adopted as the final advertising message and information about the product or service for which the final advertising message was created; The server according to claim 2.

10. retraining a pre-trained model for generating promotional messages based on the information about the product or service for which the final promotional message was generated and the data recorded in the blockchain; The server according to claim 8.

11. generating candidate promotional messages for the product or service based on the information about the product or service; obtaining a plurality of revised advertising / promotion messages, the revised advertising / promotion messages being revision results for the candidate advertising / promotion messages, each revised by a plurality of revisers; obtaining a voting result for each of the plurality of revised promotional messages by each of the plurality of voters, and determining a final promotional message for the product or service based on the voting results for the plurality of revised promotional messages; outputting said final promotional message; The way a process is carried out by a computer.

12. generating candidate promotional messages for the product or service based on the information about the product or service; obtaining a plurality of revised advertising / promotion messages, the revised advertising / promotion messages being revision results for the candidate advertising / promotion messages, each revised by a plurality of revisers; obtaining a voting result for each of the plurality of revised promotional messages by each of the plurality of voters, and determining a final promotional message for the product or service based on the voting results for the plurality of revised promotional messages; outputting said final promotional message; A program that causes a computer to execute a process.

Images