Information processing device, information processing method, and program

Abstract

To appropriately make a response to user-generated content.SOLUTION: An information processing device includes: an acquisition unit that acquires, from a specific service, user-generated content expressing a user's opinion about a specific store posted to the specific service by the user; a generation unit that generates at least a portion of response content using generative artificial intelligence based on the user-generated content; and a control unit that posts the response content to the specific service as a response to the user-generated content if the response content is approved by an administrator of the specific store.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Conventionally, there is known a service that provides word-of-mouth (user-generated content), which is the opinion of consumers (users), and replies to the word-of-mouth from businesses, etc., via the Internet, etc. Word-of-mouth is, for example, an opinion about services at stores such as restaurants and accommodation facilities, or about various goods (products) sold on EC (Electronic Commerce) sites, etc. The service is also called, for example, consumer-generated media, etc. Consumer-generated media includes, for example, so-called word-of-mouth sites, etc.

[0003] Regarding this technology, Patent Document 1 discloses a technology that enables efficient replying to customer reviews written in a foreign language with appropriate content. The technology described in Patent Document 1 determines the written language of the review based on words contained in a specific portion of the review information, and outputs a reply template in another language depending on whether the review has a negative or positive attribute. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2017-174372 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the conventional technology has room for improvement, for example, in terms of replying to word-of-mouth reviews.

[0006] An object of the present disclosure is to provide a technology that can appropriately execute a reply to user-generated content. [Means for solving the problem]

[0007] In a first aspect of the present disclosure, an information processing device is provided that has: an acquisition unit that acquires user-generated content from a specific service, the user-generated content expressing the user's opinion about a specific store, the user-generated content being posted to the specific service; a generation unit that generates at least a portion of reply content using generative artificial intelligence based on the user-generated content; and a control unit that posts the reply content to the specific service as a reply to the user-generated content if the reply content is approved by an administrator of the specific store.

[0008] In addition, in a second aspect of the present disclosure, an information processing method is provided in which an information processing device executes a process of obtaining user-generated content from a specific service, the user-generated content expressing the user's opinion about a specific store, and generating at least a portion of reply content based on the user-generated content using generative artificial intelligence, and if the reply content is approved by an administrator of the specific store, posting the reply content to the specific service as a reply to the user-generated content.

[0009] In addition, in a third aspect of the present disclosure, a program is provided that causes a computer to execute a process of obtaining user-generated content from a specific service, the user-generated content expressing the user's opinion about a specific store, using generative artificial intelligence to generate at least a portion of reply content based on the user-generated content, and if the reply content is approved by an administrator of the specific store, posting the reply content to the specific service as a reply to the user-generated content. Effect of the Invention

[0010] According to one aspect, replies to user generated content can be appropriately performed. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment. [Diagram 3] FIG. 1 is a diagram illustrating an example of a configuration of an information processing device according to an embodiment. [Figure 4] FIG. 4 is a sequence diagram illustrating an example of processing of an information processing system according to an embodiment. [Diagram 5] FIG. 13 is a diagram illustrating an example of a display screen of an administrator terminal according to the embodiment. [Figure 6] FIG. 13 is a diagram illustrating an example of a display screen of an administrator terminal according to the embodiment. [Figure 7] FIG. 2 is a diagram showing an example of a display screen of consumer-generated media according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The principles of the present disclosure are described with reference to some exemplary embodiments. It should be understood that these embodiments are set forth for illustrative purposes only, to aid those skilled in the art in understanding and practicing the present disclosure, without implying any limitation on the scope of the present disclosure. The disclosure described herein may be implemented in various ways other than those described below.

[0013] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. <System configuration> A configuration of an information processing system 1 according to an embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing a configuration example of the information processing system 1 according to an embodiment. In the example of FIG. 1, the information processing system 1 has an information processing device 10, a consumer-generated media server 40, and a generative artificial intelligence (generative AI, generative AI, generative type AI, Generative Artificial Intelligence) server 50. The information processing system 1 also has a user terminal 20A, a user terminal 20B, and a user terminal 20C (hereinafter, when there is no need to distinguish between them, they will also be simply referred to as "user terminal 20"). The information processing system 1 also has an administrator terminal 30A, an administrator terminal 30B, and an administrator terminal 30C (hereinafter, when there is no need to distinguish between them, they will also be simply referred to as "administrator terminal 30"). In the example of FIG. 1, the information processing device 10, the user terminal 20, the administrator terminal 30, the consumer-generated media server 40, and the generative artificial intelligence server 50 are connected to each other so as to be able to communicate with each other via a network N. It should be noted that the numbers of information processing devices 10, user terminals 20, administrator terminals 30, consumer-generated media servers 40, and generative artificial intelligence servers 50 are not limited to those in the example of FIG.

[0015] Examples of the network N include, for example, the Internet, a mobile communication system, a wireless LAN (Local Area Network), a LAN, and a bus, etc. Examples of the mobile communication system include, for example, a fifth generation mobile communication system (5G), a sixth generation mobile communication system (6G, Beyond 5G), a fourth generation mobile communication system (4G), a third generation mobile communication system (3G), etc.

[0016] The information processing device 10 is, for example, a server, a cloud, a personal computer, a smartphone, etc. The information processing device 10 provides a service such as encouraging users who are customers of a store to post content to a consumer-generated media server 40.

[0017] The user terminal 20 is, for example, a terminal such as a smartphone or tablet that is owned by a user. The manager terminal 30 is, for example, a terminal such as a smartphone or tablet that is owned by a manager (owner, manager, person in charge) of a store.

[0018] The consumer-generated media server 40 may be, for example, a device such as a server or a cloud. The consumer-generated media server 40 provides the user terminal 20 with a service of consumer-generated media made by user-generated content (UGC, User Generated Content, for example, word-of-mouth), which is content generated and posted by a user (consumer). The user-generated content may include, for example, an evaluation point, text, and an image. The evaluation point indicates the value of an evaluation by a user. The evaluation point may be, for example, a five-point evaluation value with 1 being the lowest point and 5 being the highest point, and may be displayed as the number of star marks. In addition, the consumer-generated media server 40 may provide, for example, reply content by a store manager in association with the user-generated content. In the following, the user-generated content is also referred to simply as "word-of-mouth" as appropriate.

[0019] Consumer-generated media server 40 may provide user-generated content through, for example, a word-of-mouth site, a map service, a blog, a wiki, a social networking service (SNS), an Internet bulletin board, a video sharing service, a customer review section of an e-commerce site, and the like.

[0020] The generative artificial intelligence server 50 provides generative artificial intelligence services to the information processing device 10. The generative artificial intelligence provided by the generative artificial intelligence server 50 may be, for example, a model (chatbot) that is machine-learned by deep learning using at least one of supervised learning and reinforcement learning, inputs at least one of text and images, and outputs text.

[0021] The generative artificial intelligence may store past input data by a user in a chat format, for example, and perform output according to the user based on the stored past input data. In this case, for example, ChatGPT-4 by OpenAI, Inc. may be used as the generative artificial intelligence.

[0022] The generative artificial intelligence may, for example, store examples of reply content in response to user-generated content for each business and for each store of the business as past input data, and output reply content using the stored past input data. <Hardware configuration>

[0023] Fig. 2 is a diagram showing an example of a hardware configuration of an information processing device 10 according to an embodiment. In the example of Fig. 2, the information processing device 10 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. These units may be connected by a bus or the like. The memory 102 stores at least a part of a program 104. The communication interface 103 includes an interface required for communication with other network elements.

[0024] When the program 104 is executed by the processor 101, the memory 102, etc. in cooperation with each other, the computer 100 performs at least some processing of the embodiment of the present disclosure. The memory 102 may be of any type. The memory 102 may be a non-transitory computer-readable storage medium, as a non-limiting example. The memory 102 may also be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. Although only one memory 102 is shown in the computer 100, several physically different memory modules may be present in the computer 100. The processor 101 may be of any type. The processor 101 may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as a non-limiting example. The computer 100 may have multiple processors, such as application-specific integrated circuit chips that are time-slaved to a clock that synchronizes the main processor.

[0025] The embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor or other computing device.

[0026] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, that execute on a target real or virtual processor device to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. The machine-executable instructions of the program modules may be executed in local or distributed devices. In a distributed device, the program modules may be located in both local and remote storage media.

[0027] The program codes for carrying out the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing apparatus. When the program codes are executed by the processor or controller, the functions / operations in the flowcharts and / or the block diagrams they implement are performed. The program codes are executed entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0028] The program can be stored and provided to the computer using various types of non-transitory computer-readable media. The non-transitory computer-readable media include various types of tangible recording media. Examples of the non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disk media, semiconductor memories, and the like. The magnetic recording media include, for example, flexible disks, magnetic tapes, hard disk drives, and the like. The magneto-optical recording media include, for example, magneto-optical disks, and the like. The optical disk media include, for example, Blu-ray disks, CD (Compact Disc)-ROM (Read Only Memory), CD-R (Recordable), CD-RW (ReWritable), and the like. The semiconductor memory includes, for example, solid-state drives, mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, RAMs (random access memories), and the like. The program may also be provided to the computer by various types of temporary computer-readable media. Examples of the temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0029] <Configuration> Next, the configuration of the information processing device 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. The information processing device 10 has an acquisition unit 11, a generation unit 12, and a control unit 13. Each of these units may be realized by cooperation between one or more programs installed in the information processing device 10 and hardware such as a processor 101 and a memory 102 of the information processing device 10.

[0030] The acquisition unit 11 acquires from the consumer-generated media server 40 user-generated content that is posted by a user to the consumer-generated media server 40 and that represents the user's opinion regarding a particular store.

[0031] The generation unit 12 causes the generative artificial intelligence server 50 to generate reply content based on the user-generated content acquired by the acquisition unit 11 .

[0032] When the reply content generated by the generation unit 12 using the generative artificial intelligence server 50 is approved by the administrator of a particular store, the control unit 13 posts the reply content to the consumer-generated media server 40 as a reply to the user-generated content.

[0033] <Processing> Next, an example of processing of the information processing system 1 according to the embodiment will be described with reference to Fig. 4 and Fig. 5. Fig. 4 is a sequence diagram showing an example of processing of the information processing system 1 according to the embodiment. Fig. 5 is a diagram showing an example of a display screen of the administrator terminal according to the embodiment. Fig. 6 is a diagram showing an example of a display screen of the administrator terminal according to the embodiment. Fig. 7 is a diagram showing an example of a display screen of consumer-generated media according to the embodiment.

[0034] The following processes may be executed periodically, or when a user posts a word-of-mouth message. The information processing device 10 may omit, combine, or replace the following processes as appropriate, as long as they are not inconsistent.

[0035] The information processing device 10 may log in to the consumer-generated media server 40 using the ID and password of an account that is permitted to reply to reviews about a specific store. In this case, the account of the manager of the specific store may be set in the consumer-generated media server 40 to give the account used by the information processing device 10 the authority to reply, etc. The account of the manager of the specific store may be authenticated (confirmed) in advance by the operator of the consumer-generated media server 40, etc., based on an application from the manager of the specific store.

[0036] In step S101, the acquisition unit 11 of the information processing device 10 acquires, from the consumer-generated media server 40, user-generated content that has been newly posted (transmitted) by a user from the user terminal 20 to the consumer-generated media server 40 and that represents the user's opinion regarding a specific store.

[0037] Next, the generation unit 12 of the information processing device 10 causes the generative artificial intelligence server 50 to generate at least a part of the reply content based on the user-generated content acquired by the acquisition unit 11 (step S102). Here, the generation unit 12 may input a prompt and the user-generated content to the generative artificial intelligence server 50, for example, using an API (Application Programming Interface) provided by the operator of the generative artificial intelligence server 50.

[0038] Next, the control unit 13 of the information processing device 10 transmits an approval request including at least a part of the reply content generated by the generation unit 12 using the generative artificial intelligence server 50 to the manager terminal 30 of the manager of the specific store (step S103). Here, the control unit 13 may transmit the approval request to the address of the manager terminal 30 that is set (registered) in advance. The approval request may include, for example, a message prompting approval, at least a part of the user-generated content, at least a part of the reply content, a user-generated content ID, and information indicating the store ID. In this case, the approval request may include, for example, a uniform resource locator (URL) of a website including these pieces of information. The user-generated content ID may be identification information for each store of the user-generated content acquired by the acquisition unit 11. The store ID is identification information for the store.

[0039] (An example of determining whether or not an administrator needs to approve a review based on the review score) The control unit 13 may determine whether or not the reply content needs to be approved by the administrator, for example, based on the evaluation points included in the user-generated content acquired by the acquisition unit 11. This allows the administrator to add a sentence such as an apology or explanation in a reply to a relatively low-rated review. Also, the administrator can add a sentence such as gratitude in a reply to a relatively high-rated review.

[0040] In this case, the control unit 13 may transmit the reply content to the administrator terminal 30 when the evaluation point included in the user-generated content is a first evaluation point, and may post the reply content to the consumer-generated media server 40 when the response content is approved by the administrator. In addition, the control unit 13 may post the reply content to the consumer-generated media server 40 without obtaining approval from the administrator when the evaluation point included in the user-generated content is a second evaluation point higher than the first evaluation point. This allows the administrator to check the reply content in the case of a reply to a word-of-mouth that is relatively likely to include a complaint or a request for improvement because the evaluation point in the word-of-mouth is relatively low. In this case, the control unit 13 may post the reply content after obtaining approval from the administrator only when the evaluation point is equal to or less than a threshold (for example, 3 points in a 5-point scale where 5 points is the highest point). The threshold value may be set in the information processing device 10 from the administrator terminal 30.

[0041] (An example of determining whether or not a review needs to be approved by the manager based on the review text) Control unit 13 may determine whether or not reply content requires approval by an administrator, based on text included in the user-generated content acquired by acquisition unit 11. This allows the administrator to check the reply content, for example, in the case of a reply to a word-of-mouth that is relatively likely to include text such as a complaint or a request for improvement.

[0042] In this case, the control unit 13 may determine that approval by the administrator is required, for example, when a specific keyword is included in a sentence of the user-generated content. In this case, the control unit 13 may transmit the reply content to the administrator terminal 30, and if the reply content is approved by the administrator, post the reply content to the consumer-generated media server 40.

[0043] In addition, the control unit 13 may, for example, determine (estimate, infer) the negativity of a sentence in user-generated content using AI, and if the determined negativity is equal to or greater than a threshold, determine that approval by an administrator is required.

[0044] (Example of automatic posting after the approval deadline has passed) If the approval deadline corresponding to the evaluation points included in the user-generated content has passed without the reply content being approved by the administrator, control unit 13 may post the reply content to consumer-generated media server 40 without approval from the administrator. This allows, for example, a relatively quick reply to word-of-mouth such as a complaint.

[0045] In this case, the control unit 13 may automatically post the reply content without obtaining approval from the administrator when a first approval deadline (e.g., 24 hours) has elapsed if the evaluation score is equal to or less than a threshold (e.g., 3 points in a 5-point scale where 5 points is the highest). Also, the control unit 13 may automatically post the reply content without obtaining approval from the administrator when a second approval deadline (e.g., 3 days) has elapsed if the evaluation score is not equal to or less than the threshold. Note that the approval deadline according to the evaluation score may be set in the information processing device 10 from the administrator terminal 30.

[0046] (An example of determining whether or not an administrator needs to approve a review based on the review score) The control unit 13 may notify the administrator terminal 30 of the approval request for the reply content by a notification means according to the evaluation points included in the user-generated content acquired by the acquisition unit 11. This allows, for example, an approval request for a reply to a word-of-mouth with a relatively low rating to be notified by a notification means that is relatively quick and easy for the administrator to check.

[0047] In this case, the control unit 13 may, for example, notify the approval request via a specific SNS (Social Networking Service) if the evaluation score is equal to or less than a threshold (for example, 3 points in a 5-point scale where 5 points is the highest). Also, the control unit 13 may, for example, notify the approval request via electronic mail (e-mail) if the evaluation score is not equal to or less than the threshold. In this case, the account information and e-mail address of the administrator in the specific SNS may be set in the information processing device 10 from the administrator terminal 30.

[0048] Next, the administrator terminal 30 displays information based on the received approval request on the display screen (step S104). In the example of Fig. 5, a message 511 prompting approval, a sentence 512 in the user-generated content, a reply content 513, a store name 514, an evaluation score 515 in the user-generated content, a user name 516, a posting date and time 517, a keyword 518 included in the reply content, an "Approve" button 521, a "Do not reply" button 522, and an "Edit reply" button 523 are displayed on a display screen 501 of the administrator terminal 30. The user name 516 may be, for example, a display name of an account of a user who posted a review on the consumer-generated media server 40. The posting date and time 517 may be, for example, a date and time when the user posted the review on the consumer-generated media server 40.

[0049] Next, the manager terminal 30 responds to the operation from the manager of the specific store by transmitting (replying) a response to the information processing device 10 (step S105). Here, for example, when the "Approve" button 521 is pressed on the display screen 501 of Fig. 5, a response indicating approval is transmitted to the information processing device 10. On the other hand, when the "Do not reply" button 522 is pressed, a response indicating that a reply will not be posted this time is transmitted to the information processing device 10.

[0050] When the "Edit reply" button 523 is pressed, for example, a display screen 601 shown in Fig. 6 may be displayed for posting reply content 513 after the administrator has edited it. In the example of Fig. 6, an input field (text box) 611 for editing reply content 513, an "Edit complete" button 612, and an "Auto-generate alternative" button 613 are displayed on the display screen 601 of the administrator terminal 30. When the "Edit complete" button 612 is pressed, a transition may be made to the display screen 501 of Fig. 5 with the reply content 513 replaced with the data input in the input field 611.

[0051] (Example of regenerating reply content) If the first proposal of the reply content generated by the generative artificial intelligence is not approved by the administrator, the generation unit 12 may cause the generative artificial intelligence to generate a second proposal of the reply content. This allows the administrator to create an alternative proposal, for example, if the first proposal is difficult to correct by editing.

[0052] In this case, the generation unit 12 may cause the generative artificial intelligence server 50 to generate at least a part of the first reply content based on the user-generated content. Then, when the generation unit 12 is requested by the administrator to generate content different from the first reply content, the generation unit 12 may cause the generative artificial intelligence server 50 to generate at least a part of the second reply content again based on the user-generated content.

[0053] In this case, the generation unit 12 may determine that the administrator has requested the generation of content different from the first reply content when, for example, the “Auto-generate alternative” button 613 in Fig. 6 is pressed. Then, the generation unit 12 may use, for example, an API provided by the operator of the generative artificial intelligence server 50 to send to the generative artificial intelligence server 50 an instruction (prompt) commanding the re-generation of reply content based on the user-generated content.

[0054] Then, when the second reply content is approved by the administrator, the control unit 13 may post the second reply content as a reply to the user-generated content to the consumer-generated media server 40. In this case, the control unit 13 may display the first reply content and the second reply content on the same display surface, and post one of the first reply content and the second reply content selected by the administrator to the consumer-generated media server 40 as a reply to the user-generated content.

[0055] Next, if the reply content is approved by the manager of the specific store, the control unit 13 of the information processing device 10 posts the reply content as a reply to the user-generated content to the consumer-generated media server 40 (step S106). As a result, the consumer-generated media server 40 associates the reply content with the user-generated content, and the reply content can be viewed from each user terminal 20, etc.

[0056] Here, the control unit 13 may post the reply content generated by the generative artificial intelligence server 50 if the reply content is approved. Also, the control unit 13 may post the revised reply content if the reply content generated by the generative artificial intelligence server 50 is approved after being edited (modified) by an administrator. Note that, if the control unit 13 is instructed by the administrator not to reply (not to approve the reply content), the control unit 13 may discard the reply content without posting it.

[0057] 7, reply content 711 is displayed on display screen 701 of user terminal 20 in association with user-generated content 712. In addition, store name 514, evaluation score 515 in the user-generated content, user name 516, and the like are also displayed in association with user-generated content 712.

[0058] (Example of including a message in the reply content indicating a reward based on the reply content generated by generative artificial intelligence) The generation unit 12 may include in the reply content a message indicating a benefit corresponding to the reply content generated by the generative artificial intelligence server 50. The benefit may include, for example, a notice of a campaign (event, sale, discount service), distribution of a discount coupon, and distribution of a product exchange coupon. This makes it possible to add (add) a message indicating a benefit suitable for the reply content automatically generated by the generative artificial intelligence. This makes it possible to announce, for example, a discount on a drink that is popular in Korea when the reply content to a user's word-of-mouth includes a topic of Korean pop (K-POP).

[0059] In this case, the generation unit 12 may determine a benefit to be provided to the user at a specific store according to, for example, a reply content generated by the generative artificial intelligence server 50 based on the user-generated content. The generation unit 12 may then generate a reply content including, for example, the reply content and a content indicating the benefit. In this case, when, for example, a specific keyword is included in the generated reply text, the generation unit 12 may add a message indicating a benefit registered in association with the keyword after the reply text. In this case, for example, a combination of a keyword and a message indicating a benefit may be set in the information processing device 10 by the manager of the specific store in association with the specific store.

[0060] (Example of including the translation in the reply content if the translation contains a specific keyword) When a specific keyword is included in the translation of the reply text, the generation unit 12 may include the translation in the reply content. This allows, for example, a specific store that has sent a reply to be displayed higher in the search ranking in a search service provided by the consumer-generated media server 40, which allows users to search for stores. The search ranking may refer to, for example, the display ranking on a display screen displayed in a keyword search. This is because it is considered that the search ranking may be determined in the search service based on the keyword included in the reply content. Also, for example, when it is considered that a reply in a foreign language to a word-of-mouth review by a foreigner in the foreign language is also useful to other users in Japan, a reply in the Japanese language may be displayed to the other users.

[0061] In this case, the generation unit 12 may cause the generative artificial intelligence server 50 to generate a reply text in the first language (e.g., a foreign language) based on the user-generated content in the first language. Then, if a translation of the reply text in a second language (e.g., a national language) contains a specific keyword, the generation unit 12 may include the translation in the reply content. In this case, the generation unit 12 may, for example, add the translation in the second language after the reply text in the first language.

[0062] (Example of learning based on corrections made by the administrator) When the reply content is modified by an administrator and posted to the consumer-generated media server 40, the generation unit 12 may train the generative artificial intelligence of the generative artificial intelligence server 50 based on the user-generated content acquired by the acquisition unit 11 and the reply content modified by the administrator. This allows the generative artificial intelligence to store the reply content as an example of reply content corresponding to the user-generated content for a specific store, and from the next time onwards, the generative artificial intelligence can output reply content using the stored data.

[0063] In this case, the generation unit 12 may, for example, use an API provided by the operator of the generative artificial intelligence server 50 to input the user-generated content and the reply content modified by the administrator along with a specific instruction text to the generative artificial intelligence.

[0064] (Example of learning based on administrator feedback) The generation unit 12 may train the generative artificial intelligence of the generative artificial intelligence server 50 based on the user-generated content, the reply content generated based on the user-generated content, and feedback from the administrator. This allows the generative artificial intelligence to store the user-generated content for a specific store, the reply content, and the feedback thereon, and from the next time onwards, the generative artificial intelligence can output reply content using the stored data.

[0065] In this case, the generation unit 12 may input the user-generated content, the reply content, and the feedback from the administrator together with a specific instruction sentence to the generative artificial intelligence, for example, using an API provided by the operator of the generative artificial intelligence server 50. The feedback from the administrator may be input, for example, by an operation by the administrator on the display screen of the administrator terminal 30 of FIG. 5 or 6. In this case, the feedback from the administrator may be input, for example, by at least one of an operation of pressing a Good button or a BAD button, an operation of inputting a text (sentence) for feedback, and a radio button for specifying one evaluation point from a selection of multiple evaluation points.

[0066] <Other> By replying to a word-of-mouth review about a specific store, it is possible to communicate with users who have visited the specific store. In addition, the reply is also viewed by other users who are looking for a store to visit in the future.

[0067] Responding promptly and courteously to reviews can give a good impression to users. Also, by responding sincerely to the gratitude and criticisms expressed in reviews, it is possible to build a relationship of trust between the user and the business owner of a particular store. In addition, in responding to reviews, it is possible to convey to the user the appeal of a particular store. This can lead to the acquisition of repeat customers and new customers, and an increase in the number of users visiting the particular store. Also, responding to reviews can lead to an increase in the search ranking in search services.

[0068] According to the present disclosure, at least a part of the reply content is generated by a generative artificial intelligence based on user-generated content that is posted by a user to a specific service and expresses the user's opinion about a specific store. Then, if the reply content is approved by an administrator of the specific store, the reply content is posted to the specific service as a reply to the user-generated content. This allows the reply to the user-generated content to be executed appropriately.

[0069] <Modification> The information processing device 10 may be a device contained in one housing, but the information processing device 10 of the present disclosure is not limited thereto. Each unit of the information processing device 10 may be realized by cloud computing configured by one or more computers, for example. In addition, the information processing device 10 and at least one of the user terminal 20, the administrator terminal 30, the consumer-generated media server 40, and the generative artificial intelligence server 50 may be configured as the same information processing device. In addition, at least a part of the processing of each functional unit of the information processing device 10 may be executed by at least one of the user terminal 20, the administrator terminal 30, the consumer-generated media server 40, and the generative artificial intelligence server 50. Such information processing devices 10 are also included in examples of the "information processing device" of the present disclosure.

[0070] The present invention is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0071] 1. Information Processing Systems 10. Information processing device 11 Acquisition Department 12 Generation part 13 Control section 20 User terminal 30 Administrator terminal 40 Consumer Generated Media Servers 50 Generative AI Server

Claims

1. an acquisition unit that acquires user-generated content from a specific service, the user-generated content representing the user's opinion regarding a specific store, the user having posted the content to the specific service; A generator that generates at least a portion of a reply content based on the user-generated content by a generative artificial intelligence; a control unit that, if the reply content is approved by an administrator of the specific store, posts the reply content to the specific service as a reply to the user-generated content; An information processing device having the above configuration.

2. The generation unit is determining a benefit to be provided to the user at the specific store in response to reply content generated by the generative artificial intelligence based on the user-generated content; generating the reply content including the reply content and content indicating the benefit; The information processing device according to claim 1 .

3. the control unit determines whether or not the reply content needs to be approved by the administrator based on an evaluation score included in the user-generated content.

3. The information processing device according to claim 1 or 2.

4. The control unit is If the evaluation point included in the user-generated content is a first evaluation point, sending the reply content to a terminal of the administrator, and if the reply content is approved by the administrator, posting the reply content to the specific service; if the evaluation score included in the user-generated content is a second evaluation score that is higher than the first evaluation score, posting the reply content to the specific service without approval from the administrator; The information processing device according to claim 3 .

5. the control unit determines whether or not the reply content needs to be approved by the administrator based on a sentence included in the user-generated content.

3. The information processing device according to claim 1 or 2.

6. when an approval deadline corresponding to an evaluation point included in the user-generated content has elapsed without the administrator approving the reply content, the control unit posts the reply content to the specific service without obtaining approval from the administrator.

3. The information processing device according to claim 1 or 2.

7. the control unit notifies the manager's terminal of an approval request for the reply content by a notification means corresponding to an evaluation point included in the user-generated content; 3. The information processing device according to claim 1 or 2.

8. The generation unit is generating a reply in the first language using the generative artificial intelligence based on the user-generated content in the first language; If a translation of the reply text in a second language contains a particular keyword, the translation is included in the reply content.

3. The information processing device according to claim 1 or 2.

9. When the reply content is modified by the administrator and posted to the specific service, the generation unit trains the generative artificial intelligence based on the user-generated content and the reply content modified by the administrator.

3. The information processing device according to claim 1 or 2.

10. The generation unit is generating at least a portion of a first reply content by the generative artificial intelligence based on the user-generated content, and when an administrator requests the generation of content different from the first reply content, generating at least a portion of a second reply content by the generative artificial intelligence based on the user-generated content; When the second reply content is approved by the administrator, the control unit posts the second reply content to the specific service as a reply to the user-generated content.

3. The information processing device according to claim 1 or 2.

11. An information processing device, Obtaining user-generated content from a specific service that is posted by a user to the specific service and represents the user's opinion regarding a specific store; generating, by generative artificial intelligence, at least a portion of reply content based on the user-generated content; If the reply content is approved by an administrator of the particular store, posting the reply content to the particular service as a reply to the user-generated content. An information processing method for performing processing.

12. Obtaining user-generated content from a specific service that is posted by a user to the specific service and represents the user's opinion regarding a specific store; generating, by generative artificial intelligence, at least a portion of reply content based on the user-generated content; If the reply content is approved by an administrator of the particular store, posting the reply content to the particular service as a reply to the user-generated content. A program that causes a computer to carry out processing.

Images