Server, method and program

Abstract

To provide a server for acquiring a promotional message that can be used to promote products or services.SOLUTION: A server 12 generates a candidate for a promotional message for a product or a service on the basis of information on the product or the service. The server 12 acquires a plurality of modified promotional messages which are the results of modification to the candidate promotional message and have been modified by each of a plurality of modifiers. The server 12 acquires a voting result for each of the plurality of modified promotional messages by each of a plurality of voters.SELECTED DRAWING: Figure 1

Description

Technical Field

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

Background Art

[0002] Conventionally, a management device for generating information used for advertising or sales promotion of products has been known (for example, Patent Document 1). Patent Document 1 discloses that an evaluation item of a product is input to a learned estimation model, and at least one piece of text output by the estimation model is used as a candidate for a persuasive message of the product.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although Patent Document 1 discloses that the text output from a learned estimation model is used as a candidate for a persuasive message of a product, it is difficult to directly use the persuasive message for promoting the sales of the product or service. Therefore, even if the technology disclosed in Patent Document 1 is used, there is a problem that it is difficult to obtain an advertising message that can be used for promoting the sales of a product or service.

[0005] The present disclosure has been made in view of the above circumstances, and an object thereof is to obtain an advertising message that can be used for promoting the sales of a product or service.

Means for Solving the Problems

[0006] A first aspect of the present disclosure includes a candidate generation unit that generates candidates for an advertising message for a product or service based on information about the product or service, a correction result acquisition unit that acquires correction results for the candidates for the advertising message, which are a plurality of corrected advertising messages corrected by each of a plurality of correctors, and a vote result acquisition unit that acquires vote results for each of the plurality of corrected advertising messages, which are vote results by each of a plurality of voters, and is a server.

Advantages of the Invention

[0007] According to the present disclosure, an effect is obtained that an advertising message that can be used to promote the sale of a product or service can be acquired.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0009] Hereinafter, 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 generation system 10 according to the present embodiment. As shown in FIG. 1, the advertising message generation system 10 according to the present embodiment includes an ordering terminal 11, a server 12, a plurality of correction terminals 14A, 14B, 14C,... a plurality of voting terminals 16A, 16B, 16C,... and a plurality of blockchain nodes 18A, 18B, 18C,.... Each device is communicably connected by a network N such as the Internet. Hereinafter, the plurality of correction terminals 14A, 14B, 14C,... are simply referred to as correction 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, an advertising message for a product or service is created. FIG. 2 is a diagram for explaining the outline of the present embodiment. As shown in FIG. 2, in the present embodiment, when creating an advertising message for a product or service, a learned model which is a generative artificial intelligence (AI), a plurality of corrector U1, and a plurality of voters U2 create and select an advertising message.

[0012] Specifically, first, as shown in FIG. 2, for a pre-trained model generated by a machine learning algorithm, by inputting information about a product or service, candidates for advertising messages are generated. The pre-trained model of this embodiment is a so-called generative AI, which has learned past excellent Japanese advertising messages (catchphrases) and is adjusted for the purpose of developing Japanese creative writing. There may be one or more candidates for advertising messages. The information about the product or service includes at least one of, for example, information representing the category of the product or service and information regarding 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. Also, the information regarding the consumer is, for example, information such as men and women in their 20s, and may be more detailed classification information.

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

[0014] (1) In this embodiment, information regarding the usual psychological attributes and behavioral attributes of the target consumers is input into the pre-trained model. For example, information regarding psychological attributes and behavioral attributes such as what kind of personality traits the consumers who purchase the target product or service have and what values they cherish (cherish family or cherish friends, etc.) is input into the pre-trained model. For example, information such as "the target consumers are housewives who cherish their families and prioritize their children" and "are concerned about rough skin" is input into the pre-trained model. This makes it possible to generate candidates for advertising messages for consumers with the corresponding psychological attributes and behavioral attributes.

[0015] (2) In this embodiment, information on what attitude or behavior changes occur when the target consumer uses the target product or service (or brand), and the consumer tendencies that serve as the basis for such changes being possible are input into the learned model. For example, information such as "the skin becomes smooth" and "the waking-up feeling improves" is input into the learned model. This enables the generation of candidates for advertising messages that resonate with consumers who desire their own attitude or behavior changes.

[0016] (3) In this embodiment, information regarding the tone aimed for by the product or service (or brand) is input into the learned model. Specifically, information such as whether the target product or service (or brand) is assertive or empathetic, bright or dark, emotional or inorganic is input into the learned model. This generates candidates for advertising messages that align with the intentions of the orderer (specifically, the brand image) described later.

[0017] (4) In this embodiment, information such as in what situation and current position the category to which the product or service belongs is, and what it wants to do in Japan (future prospects) is input into the learned model. This generates candidates for advertising messages according to the current situation of the target product or service and the intentions of the orderer.

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

[0019] Next, as shown in Figure 2, each of the plurality of revisers U1 creates a revised advertising message by revising the candidate for the advertising message.

[0020] Next, as shown in FIG. 2, each of a plurality of voters U2 determines which of the plurality of modified advertising messages is appropriate for the product or service targeted, and votes on the plurality of modified advertising messages.

[0021] Then, based on the voting results for the modified advertising messages, the final advertising message for the targeted product or service is determined.

[0022] For example, consider the case where there is a request (one case) to create an advertising message for one product. In this case, for example, a prompt such as "Please generate 5 catchphrase proposals for Cosmetics A. Cosmetics A is for 〇〇, and the target consumers are women in their 30s to 50s. Also, the target consumers are housewives who value their families and prioritize their children. Also, the target consumers are concerned about rough skin. What kind of smooth skin can be expected when consumers use Cosmetics A. Also, the tone that Cosmetics A aims for is 〇〇. The current position of Cosmetics A in the market is 〇〇, but it aims for a state like 〇〇 as a future prospect." is input to the learned model, and for example, 5 candidate advertising messages are generated.

[0023] Next, for example, each of 3 revisers creates 15 modified advertising messages by revising each of the 5 candidate advertising messages. Then, for example, 100 voters vote on the 15 modified advertising messages. For example, one voter votes for the modified advertising message that they think is the best among the 15 modified advertising messages. And 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 a predetermined number of points are given as rewards to the modifier who creates the modified advertisement message with the most votes. Also, for example, a predetermined amount of cash or a predetermined number of points are given as rewards to the voter who votes for the modified advertisement messages that have obtained the top 1 to 3 votes.

[0025] In addition, various data obtained in the process of creating the final advertisement message are stored in the blockchain held by the blockchain node 18. For example, as described above, the prompt, candidate advertisement messages, modified advertisement messages, final advertisement messages, voting results, information on the cash or points given to the modifier, and information on the cash or points given to the voter are stored in the blockchain. This will be specifically described below.

[0026] As shown in FIG. 1, the server 12 functionally includes a candidate generation unit 120, a modification result acquisition unit 122, a voting result acquisition 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 the 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. Also, the computer 70 includes an input / output interface (I / F) 7 4 to which an input / output device etc. (not shown) is connected, and a read / write (R / W) unit 75 that controls reading and writing of data to and from a recording medium. Also, the computer 70 includes a network I / F 76 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, or the like. A program for operating the computer 70 is stored in the storage unit 73 as a storage medium. The CPU 71 reads the program from the storage unit 73, expands it in the memory 72, and sequentially executes the processes included in the program.

[0029] <Operation of the advertising message generation system 10>

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

[0031] In step S100, the ordering terminal 11 outputs a signal representing a request for creating an advertising message to the server 12. Specifically, an orderer who operates the ordering terminal 11 requests the creation of an advertising message for a product or service that he / she wants to create an advertising message for. For example, the orderer who operates the ordering terminal 11 requests the server 12 to create an advertising message for a product or service by inputting various information into a predetermined input form displayed on a display unit (not shown) of the ordering terminal 11. For example, at least one of the following types of information related to the product or service (e.g., information representing the category of the product or service, information related to the consumers of the product or service, information representing the psychological or behavioral attributes of the target consumers of the product or service, information representing what kind of attitude change or behavior change occurs when the consumers use the product or service, information representing the tone aimed at by the product or service, and information representing the current situation or future prospect of the category to which the product or service belongs) is input into the input form.

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

[0033] In step S104, the candidate generation unit 120 of the server 12 presents the candidates for the advertising message generated in step S102 to the correction terminal 14. For example, the candidate generation unit 120 of the server 12 presents the candidates for the advertising message to the correction terminal 14 using a dedicated site (browser). For example, the candidates for the advertising message are presented only to the correction terminal 14 of a corrector who satisfies the conditions regarding the requested case (for example, the attributes of the target consumers) among the pre-registered correctors.

[0034] ​ Note that the candidate generation unit 120 may extract a corrector, a candidate for corrector, a voter, or a candidate for voter from among a plurality of candidates based on information about a product or service. For example, if it appears that a result such as liking a certain product has been obtained in a prior questionnaire, those who like the product may be extracted as correctors, candidates for corrector, voters, or candidates for voter.

[0035] Also, the candidate generation unit 120 may extract a corrector, a candidate for corrector, a voter, or a candidate for voter according to the degree of similarity between the attribute information indicating the attributes of each of the plurality of candidates and the information about the product or service. For example, when the consumers of a product or service are men in their 20s, correctors, candidates for corrector, voters, or candidates for voter who are men in their 20s may be extracted from among the plurality of candidates.

[0036] In step S106, the plurality of correctors operate their correction terminals 14 to correct the advertising message presented in step S104, thereby creating a corrected advertising message.

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

[0038] In step S110, the candidate generation unit 120 of the server 12 presents the corrected advertising message acquired in step S108 to the voting terminal 16.

[0039] In step S112, the plurality of voters operate their voting terminals 16 to vote on the plurality of corrected advertising messages presented in step S110.

[0040] In step S114, the voting result acquisition unit 124 of the server 12 acquires the voting result obtained in step S112. The voting result acquisition unit 124 of the server 12 is based on the voting result Then, determine the modified advertising message with the largest 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 the final advertising message determined in step S114 to the ordering terminal 11.

[0042] Next, the output unit 126 records on the blockchain the information about the product or service, the number of votes of the modifier who created the modified advertising message adopted as the final advertising message, and the 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 on the blockchain held by the blockchain node 18. As shown in FIG. 5, as advertising message information, the information about the product or service, the final advertising message, the information of the modifier who created the modified advertising message adopted as the final advertising message, and the number of votes thereof are stored in a block on the blockchain.

[0044] By using this information stored in the blockchain, it becomes possible to know which modifier should be asked to make corrections when creating an advertising message for another product or service next time. Note that since the category or consumers as information about the product or service are also recorded in the blockchain, it also becomes possible to know which modifier should be asked to make corrections for any product or service. Also, by treating the various data stored in the blockchain as big data, it is possible to select an appropriate modifier or voter for each requested case. For example, for a case where the conditions set for the requested case are met, notifications are sent to, for example, dozens to hundreds of people, and modifiers or voters are selected in the order of arrival of applicants.

[0045] Therefore, for example, when creating an advertising message for a product or service next time, the server 12 may refer to the above information recorded in the blockchain to select a corrector. This realizes the matching between the product or service and the creator of the advertising message.

[0046] Also, as described above, cash or points may be given to the corrector according to the number of votes. In this case, for example, information on cash or points is stored in the blockchain as corrector information. These points can be used within this system or may be made available for use outside this system. This improves the motivation of the corrector, and more appropriate creation of advertising messages is expected. Also, as described above, cash or points may be given to the voter according to the ranking of the corrected advertising message they voted for.

[0047] Further, the output unit 126 may re - train the above - mentioned learned model based on the information regarding the product or service for which the final advertising message has been created and the data recorded in the blockchain. As shown in FIG. 5, information regarding the product or service and the final advertising message are associated and recorded in the blockchain. Therefore, by using this data to re - train the learned model, it becomes possible to generate better candidates for advertising messages.

[0048] As described above, the server of the advertising message generation system according to the present embodiment generates candidates for advertising messages for a product or service based on information regarding the product or service. Next, the server uses the correction results for the candidates of the advertising messages Obtain a plurality of modified advertising messages each modified by a respective one of a plurality of modifiers. Next, the server obtains the voting results for each of the plurality of modified advertising messages, which are the voting results by each of the plurality of voters. Then, based on the voting results for the plurality of modified advertising messages, the server outputs at least one or more of the plurality of modified advertising messages as the final advertising message for the product or service. Thereby, an advertising message that can be used to promote the sale of the product or service can be obtained.

[0049] Note that the present invention is not limited to the above-described embodiments, and various modifications and applications are possible without departing from the gist of the present invention.

[0050] For example, in this embodiment, the case of generating candidates for advertising messages using a learned model has been described as an example, but the present invention is not limited thereto, and other methods may be used to generate candidates for advertising messages. For example, information related to a product or service and candidates for advertising messages are associated and stored in a database in advance. When information related to the target product or service is received, candidates for advertising messages corresponding to the information are read from the database to generate candidates for advertising messages.

[0051] Also, the effects obtained by this embodiment are shown below.

[0052] As described above, the learned model used in this embodiment is a learned model that has been independently tuned. Also, the learned model has learned past excellent Japanese catchphrases and has been adjusted for the purpose of developing Japanese creative writing. Therefore, according to this embodiment, more appropriate candidates for advertising messages can be generated.

[0053] In addition, in this embodiment, it is possible to maintain the transparency of the creation process and the voting process of the advertising message and contribute to preventing forgery. In particular, the voting process is executed before the advertisement message is published, and through this voting process, a more appropriate advertisement message is created. As a result, the reliability and safety of the advertisement message are improved.

[0054] Also, as in this embodiment, having the target layer of the actual product or service participate as an extractor / editor from within the community in the advertising message generated by the learned model, which is a generative AI, is an innovative approach unparalleled in the industry. By directly involving the end consumers in the creation process of the advertising message, it becomes possible to produce more effective and empathetic marketing content.

[0055] In addition, in this embodiment, the efficiency and speed provided by the learned model, and the creative insights unique to humans (and even more so unique to the target of the product or service) provided by the human community enable more efficient and mass writing for each target, while also having a self-cleaning effect of detecting errors and plagiarism committed by the learned model.

[0056] In addition, in this embodiment, by using blockchain, it is possible to provide a significant differentiation from conventional copywriting solutions in terms of enhancing the transparency and reliability of the generation and evaluation processes of advertising messages.

[0057] Moreover, by assigning points recorded on the blockchain, it becomes a point system that maintains the motivation of correctors and voters.

[0058] Also, in this specification, although the embodiment in which the program is pre-installed has been described, it is also possible to store the program in a computer-readable recording medium and provide it.

[0059] The following supplementary notes are disclosed. (Supplementary Note 1) 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 candidates for the advertising messages and a plurality of corrected advertising messages corrected by each of a plurality of correctors, A voting result acquisition unit that acquires voting results for each of the plurality of corrected advertising messages and voting results by each of a plurality of voters, A server comprising the above. (Supplementary Note 2) Based on the voting results for the plurality of corrected advertising messages, the voting result acquisition unit determines at least one or more of the plurality of corrected advertising messages as the final advertising message for the product or service, The server further comprising an output unit that outputs the final advertising message, The server according to claim 1. (Supplementary Note 3) The information about the product or service includes information representing the psychological attributes or behavioral attributes of the consumers targeted by the product or service, information indicating what attitude changes or behavioral changes will occur when the consumers use the product or service, information representing the tone aimed at by the product or service, and at least one of information representing the current situation or future prospects of the category to which the product or service belongs, The server according to Supplementary Note 1 or Supplementary Note 2. (Supplementary Note 4) The information about the product or service includes at least one of information representing the category of the product or service and information about the consumers of the product or service, The server according to any one of Supplementary Notes 1 to 3. (Supplementary Note 5) The candidate generation unit extracts the corrector, candidates for the corrector, the voter, or candidates for the voter from among a plurality of candidates based on information related to the product or service. The server according to any one of Appendices 1 to 4. (Appendix 6) The candidate generation unit extracts the corrector, candidates for the corrector, the voter, or candidates for the voter according to the degree of similarity between the attribute information indicating the attributes of each of the plurality of candidates and the information related to the product or service. The server according to any one of Appendices 1 to 5. (Appendix 7) Based on the voting result, the vote result acquisition unit determines the corrected advertisement message with the largest number of votes as the final advertisement message for the product or service. The server according to any one of Appendices 1 to 6. (Appendix 8) The candidate generation unit generates candidates for the advertisement message of the product or service by inputting a prompt corresponding to the information related to the product or service into a pre-trained model for generating advertisement messages. The server according to any one of Appendices 1 to 7. (Appendix 9) Record the number of votes of the corrector who created the corrected advertisement message adopted as the final advertisement message and the information related to the product or service for which the final advertisement message was created on the blockchain. The server according to any one of Appendices 1 to 8. (Appendix 10) Based on the information related to the product or service for which the final advertisement message was created and the data recorded on the blockchain, re-train a pre-trained model for generating advertisement messages. The server according to any one of Appendices 1 to 9. (Appendix 11) Based on the information related to the product or service, generate candidates for the advertisement message of the product or service. Obtain a plurality of modified advertising messages that are the results of modifications to the candidate advertising messages and that have been modified by each of a plurality of modifiers. Obtain the voting results for each of the plurality of modified advertising messages, which are the voting results by each of a plurality of voters. A method for a computer to execute a process. (Appendix 12) Generate candidates for advertising messages for a product or service based on information about the product or service. Obtain a plurality of modified advertising messages that are the results of modifications to the candidate advertising messages and that have been modified by each of a plurality of modifiers. Obtain the voting results for each of the plurality of modified advertising messages, which are the voting results by each of a plurality of voters. A program for causing a computer to execute a process.

Explanation of Signs

[0060] 10 Advertising message generation system 11 Ordering terminal 12 Server 14A, 14B, 14C, Modifying terminal 16A, 16B, 16C, Voting terminal 18A, 18B, 18C, Blockchain node 120 Candidate generation unit 122 Modification result acquisition unit 124 Voting result acquisition unit 126 Output unit

Claims

1. A candidate generation unit that generates candidates for advertising messages for products or services based on information about the products or services; A correction result acquisition unit that acquires correction results for the candidates for the advertising messages, and a plurality of corrected advertising messages corrected by each of a plurality of corrector; A voting result acquisition unit that acquires voting results for each of the plurality of corrected advertising messages, and voting results by each of a plurality of voters; A server comprising the above.

2. Based on the voting results for the plurality of corrected advertising messages, the voting result acquisition unit determines at least one or more of the plurality of corrected advertising messages as the final advertising message for the product or service, The server further comprises an output unit that outputs the final advertising message, The server according to claim 1.

3. The information about the product or service includes Information representing the psychological attributes or behavioral attributes of consumers targeted by the product or service, Information indicating what attitude changes or behavioral changes will occur when the consumer uses the product or service, Information representing the tone aimed at by the product or service, and At least one of information representing the current situation or future prospects of the category to which the product or service belongs, The server according to claim 1 or claim 2.

4. The information about the product or service includes at least one of information representing the category of the product or service and information about the consumers of the product or service, The server according to claim 1 or claim 2.

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

6. Based on the similarity between the attribute information indicating the attributes of each of the plurality of candidates and the information about the product or service, the candidate generation unit extracts the corrector, candidates for the corrector, the voter, or candidates for the voter. The server according to claim 5.

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

8. The candidate generation unit generates candidates for advertising messages for products or services by inputting a prompt corresponding to information about the product or service into a pre-trained model created for generating advertising messages. The server according to claim 1 or claim 2.

9. Record the number of votes received by the reviser 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 on the blockchain. The server according to claim 2.

10. Re-train a pre-trained model created for generating advertising messages based on information about the product or service for which the final advertising message was created and the data recorded on the blockchain. The server according to claim 8.

11. Generate candidates for advertising messages for products or services based on information about the products or services. Obtain the revised advertising messages that are the results of revisions to the candidates for the advertising messages and that have been revised by each of a plurality of revisers. Obtain the voting results for each of the plurality of revised advertising messages, which are the voting results by each of a plurality of voters. A method for a computer to execute the process.

12. Generate candidates for advertising messages for products or services based on information about the products or services. Obtain the revised advertising messages that are the results of revisions to the candidates for the advertising messages and that have been revised by each of a plurality of revisers. Obtain the voting results for each of the plurality of revised advertising messages, which are the voting results by each of a plurality of voters. A program for causing a computer to execute the process.

Images