Information processing device, information processing method, and information processing program

Abstract

We generate and provide promotional slogans tailored to each store. [Solution] The information processing device according to the present invention is characterized by comprising: an extraction unit that extracts store information relating to stores with available seats based on search conditions specified by the user; a generation unit that generates store advertisements by inputting store information and instruction sentences that instruct a generation model, which has been trained to generate answers to input questions, to output store advertisements based on the store information; a provision unit that provides the user with store information and advertisements as search results for the search conditions; and a call unit that, when it receives reservation information relating to store reservations from the user, uses a call model to make a call to the store regarding the reservation based on the reservation information.

Description

[Technical Field]

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program. [Background Art]

[0002] Conventionally, techniques for allowing a user to reserve a store are known. As an example of such a technique, there is a known technique that enables store reservation by generating a reservable store list including reservable stores included within a predetermined distance range from a mobile terminal, transmitting the list to the mobile terminal, and inputting store reservation information for reserving a store in the reservable store list into the mobile terminal. [Prior Art Literature] [Patent Literature]

[0003] [Patent Literature 1] Japanese Unexamined Patent Publication No. 2011-186574 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, with the above-described conventional technology, it is not always possible to generate and provide advertising phrases corresponding to each store.

[0005] For example, the above-described conventional technology merely provides a reservable store list indicating reservable stores, and cannot necessarily generate and provide advertising phrases corresponding to each store.

[0006] The present application has been made in view of the above circumstances, and an object of the present application is to generate and provide advertising phrases corresponding to each store. [Means for Solving the Problem]

[0007] The information processing device according to the present invention is characterized by comprising: an extraction unit that extracts store information relating to stores with available seats based on search conditions specified by a user; a generation unit that generates advertising copy for a store by inputting the store information and an instruction sentence that instructs the generation model, which has been trained to generate answers to input questions, to output advertising copy for the store based on the store information; a provision unit that provides the store information and the advertising copy to the user as search results for the search conditions; and a call unit that, when it receives reservation information relating to a reservation for the store from the user, uses a call model to make a call to the store regarding the reservation based on the reservation information. [Effects of the Invention]

[0008] According to one embodiment of the system, it has the effect of generating and providing advertising slogans tailored to each store. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the screen of the user terminal 100 according to this embodiment. [Figure 3] Figure 3 shows an example of the screen of the user terminal 100 according to this embodiment. [Figure 4] Figure 4 shows an example of the configuration of the information processing device 10 according to the embodiment. [Figure 5] Figure 5 shows an example of a user information database 31. [Figure 6] Figure 6 shows an example of the store information database 32. [Figure 7] Figure 7 is a flowchart showing an example of the information processing procedure according to the embodiment. [Figure 8] Figure 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10. [Modes for carrying out the invention]

[0010] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0011] [1. Embodiments] The information processing realized by the information processing device of this embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. In Figure 1, the information processing according to the embodiment is realized by the information processing device 10, which is an example of the information processing device according to the present application.

[0012] As shown in Figure 1, the information processing system 1 according to this embodiment includes an information processing device 10, a user terminal 100, and a store terminal 200. The information processing device 10, the user terminal 100, and the store terminal 200 are connected to each other via wired or wireless connections through a network N (see, for example, Figure 4) so ​​that they can communicate with each other. The network N is, for example, a WAN (Wide Area Network) such as the Internet. Note that the information processing system 1 shown in Figure 1 may include multiple information processing devices 10, multiple user terminals 100, and multiple store terminals 200.

[0013] The information processing device 10 shown in Figure 1 is an information processing device that performs information processing according to the embodiment, and can be realized by, for example, a server device or a cloud system. For example, the information processing device 10 provides a reservation service #1 to a user regarding reservations for a restaurant. To give a specific example, the information processing device 10 receives information on the availability of seats in a restaurant from a restaurant terminal 200. Based on the seat availability information, the information processing device 10 provides the user with information on restaurants with available seats via the reservation service #1 and accepts reservations for restaurants with available seats.

[0014] The information processing device 10 may also function as a web server providing a website related to reservation service #1. Furthermore, the information processing device 10 may be a device that distributes information to be displayed in an application related to reservation service #1 installed on the user terminal 100. The information processing device 10 may also be a server that distributes the application data itself. Additionally, the information processing device 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is written in, for example, a scripting language such as JavaScript®, a stylesheet language such as CSS (Cascading Style Sheets), or a programming language such as Java®, Kotlin, Swift, or Objective-C. The application itself distributed from the information processing device 10 may also be considered as control information.

[0015] The user terminal 100 shown in Figure 1 is an information processing device used by a user. For example, the user terminal 100 can be a smartphone, a tablet device, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Figure 1, the user terminal 100 is shown as a smartphone used by the user.

[0016] The store terminal 200 shown in Figure 1 is an information processing device used by the store manager (e.g., an employee). For example, the store terminal 200 can be implemented as a smartphone, tablet, notebook PC, desktop PC, mobile phone, PDA, etc. In the example shown in Figure 1, the store terminal 200 is a smartphone.

[0017] Note that the user terminal 100 and the store terminal 200 display information provided by the information processing device 10 via a web browser or application. When the user terminal 100 and the store terminal 200 receive control information for realizing information display processing from the information processing device 10 or the like, they implement display processing in accordance with the control information.

[0018] Hereinafter, the information processing executed by the information processing apparatus 10 will be described with reference to FIG. 1. In the following description, it is assumed that the user terminal 100 is used by a user (user U1) identified by the user ID "UID#1". Furthermore, in the following description, the user terminal 100 may be equated with the user U1. That is, in the following description, user U1 may also be read as user terminal 100.

[0019] Furthermore, in the following description, according to the manager who uses the store terminal 200, the store terminals 200 will be described as store terminals 200-1 to 200-N (where N is any natural number). For example, the store terminal 200-1 is a store terminal 200 used by a manager (manager M1) identified by the manager ID "M1". Furthermore, in the following description, when the store terminals 200-1 to 200-N are described without particular distinction, they will be referred to as store terminal 200. Additionally, in the following description, the store terminal 200 may be equated with the manager and the store. That is, in the following description, the manager M1 and store #1 may also be read as the store terminal 200-1.

[0020] Furthermore, in the following description, it is assumed that the information processing device 10 collects user information about users on various services provided by itself or other server devices, and manages it in its own storage unit (for example, the storage unit 30 described later). For example, the information processing device 10 manages user information, including user attributes (for example, demographic attributes, psychographic attributes, etc.), content browsing history, product purchase history, search history, hobbies and preferences, and favorited items (for example, stores), in association with user IDs. Note that user attributes and hobbies and preferences may be information inferred from the user's browsing history, purchase history, search history, favorited stores, etc.

[0021] The services provided by the information processing device 10 and other server devices may include, for example, search services, shopping services, SNS (Social Networking Service), route search services, map provision services, travel services, restaurant recommendation services, facility reservation services, weather forecast services, schedule management services, news provision services, auction services, video content distribution services, financial transaction (stock trading, etc.) services, news article distribution services, and the like.

[0022] Furthermore, in the following explanation, it is assumed that the information processing device 10 collects store information regarding stores that can be reserved via reservation service #1 on various services provided by itself or other server devices, and manages it in its own storage unit. For example, the information processing device 10 manages store information, including store location, food and beverages (menu) that the store can offer, attributes of customers who have visited the store, evaluation information showing store ratings (reviews) posted by users on restaurant introduction services, and history of available seat information received from store terminals 200 (i.e., past reservation status), in association with store identification information (store ID).

[0023] First, the information processing device 10 receives seat availability information from the store terminal 200, which indicates the status of available seats in the store (step S1). For example, the information processing device 10 receives information such as how many seats are available (in other words, the number of people who can make a reservation), the type of available seat (for example, table seats, booth seats, counter seats, etc.), and image information showing an image of an available seat (for example, an image of the area around the seat).

[0024] The information processing device 10 may accept vacancy information indicating the current status of vacant seats in the store, or it may accept vacancy information indicating the status of vacant seats in the store at a future point in time.

[0025] Next, the information processing device 10 receives search conditions for searching for stores with available seats from the user terminal 100 via reservation service #1 (step S2). In the example in Figure 1, the information processing device 10 receives search condition #1 from the user terminal 100 for searching for stores located within a predetermined range (for example, within 500m) from the user U1's current location and that currently have available seats.

[0026] Next, the information processing device 10 extracts store information related to the store corresponding to search condition #1 from its own storage unit (step S3). For example, the information processing device 10 identifies the store corresponding to search condition #1 based on the vacancy information and store location received in step S1. Then, the information processing device 10 extracts store information associated with the identified store (store ID).

[0027] In the example shown in Figure 1, the information processing device 10 extracts store information #1, store information #2, etc., which are associated with store #1, store #2, etc.

[0028] Next, the information processing device 10 generates advertising slogans (sales pitches) for stores based on the extracted store information (step S4). For example, the information processing device 10 generates advertising slogans for a store by inputting store information associated with a store and an instruction sentence that instructs the generative model #1, which has been trained to generate answers to input questions, to output advertising slogans for that store based on that store information.

[0029] To give a specific example, the information processing device 10 generates advertising copy for a store by inputting instruction text along with predetermined rules into the generation model #1. For example, if it is rare for the store for which the advertising copy is to be generated to be available for reservation, the information processing device 10 generates advertising copy #1 for store #1 by inputting a rule to incorporate that rarity, along with instruction text that instructs the generation model #1 to output advertising copy based on store information #1 according to that rule. For example, if the degree of congestion at store #1 at the present time and a corresponding past time, estimated based on the history of seat availability information for store #1, is above a predetermined threshold (i.e., it is usually crowded and it is rare for it to be available for reservation), the information processing device 10 generates advertising copy #1 such as, "We are usually full, but we can give you a seat right now. Please make a reservation."

[0030] Furthermore, the information processing device 10 may generate advertising copy for the store by inputting user information #1 relating to user U1 into the generation model #1. For example, the information processing device 10 generates advertising copy #2 for store #2 by inputting user information #1, store information #2, and an instruction sentence that instructs the generation model #1 to output advertising copy for store #2 based on user information #1 and store information #2 into the generation model #1 along with user information #1 and store information #2. To give a specific example, the information processing device 10 generates advertising copy #2 for store #2 by inputting a rule that includes information corresponding to user information from the store information, and an instruction sentence that instructs the generation model #1 to output advertising copy based on user information #1 and store information #2 in accordance with the rule, along with user information #1 and store information #2 into the generation model #1. For example, if user U1's hobby / preference (for instance, their favorite dish) is "Dish #1" and the menu of store #2 includes "Dish #1", the information processing device 10 generates an advertisement #2 such as, "You can enjoy user U1's favorite dish #1. Please give it a try."

[0031] Furthermore, the information processing device 10 generates advertising copy for other stores corresponding to search condition #1 using the same method as described above.

[0032] Here, generative model #1 is a model trained to output a response corresponding to an input question, and is a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Furthermore, generative model #1 resides within the information processing device 10 and was independently created by the business operator managing the information processing device 10. It is desirable that the input information be kept confidential by training the model so that it is not used as a new answer, thereby protecting personal information and other sensitive data.

[0033] Next, the information processing device 10 provides the generated advertising copy, along with store information relating to the store corresponding to search condition #1, to the user terminal 100 as a search result corresponding to search condition #1 via reservation service #1 (step S5).

[0034] Here, we will explain the search results provided to the user terminal 100 using Figure 2. Figure 2 is a diagram showing an example of the screen of the user terminal 100 according to this embodiment.

[0035] As shown in Figure 2, the information processing device 10 provides the user terminal 100 with a screen C11 that displays search results corresponding to search condition #1. For example, the information processing device 10 provides a screen C11 that includes an area AR11 that overlays the stores corresponding to search condition #1 and the number of available seats in those stores onto a map corresponding to the location of user U1, and areas AR12 and AR13 that display store information related to the stores corresponding to search condition #1 along with promotional text.

[0036] To give a specific example, the information processing device 10 displays information such as the number of vacant seats at store #1 and text T11 indicating advertising slogan #1 in area AR12. The information processing device 10 also displays information such as the number of vacant seats at store #2 and text T12 indicating advertising slogan #2 in area AR13. The information processing device 10 may also display further information about other stores corresponding to search condition #1 in response to scrolling operations on screen C11.

[0037] Here, let's assume that user U1 performs the operation to select area AR12 (in other words, the operation to select store #1). In this case, the information processing device 10 transitions the screen of the user terminal 100 from screen C11 to screen C12. For example, the information processing device 10 provides screen C12 which includes area AR14 that displays information based on the availability of seats in store #1. To give a specific example, the information processing device 10 displays images of available seats in store #1 and a button to request a reservation for those available seats in a carousel in area AR14. For example, the information processing device 10 displays an image P11 of table seat #1, which is available in store #1, and a button B11 to request a reservation for table seat #1.

[0038] Let's return to Figure 1 and continue the explanation. Here, let's assume that user U1 has requested a reservation for table seat #1 at store #1 (i.e., pressed button B11 shown in Figure 2). In this case, the information processing device 10 receives reservation information #1 regarding the reservation of table seat #1 from the user terminal 100 (step S6). For example, the information processing device 10 receives reservation information #1 which includes information such as information indicating table seat #1, the number of people reserved, the name of user U1, and the phone number of user U1.

[0039] Next, the information processing device 10 uses call model #1 to make a call regarding the reservation based on reservation information #1 to administrator M1 via store terminal 100-1 (step S7). For example, the information processing device 10 uses call model #1, which has been trained to output a voice response corresponding to the input voice (question), to make a call regarding the reservation based on reservation information #1. For example, the information processing device 10 uses store terminal 200-1 to make a call with administrator M1 and conveys the contents of reservation information #1 to administrator M1. If administrator M1 responds during the call to acknowledge the reservation, the information processing device 10 determines that the reservation is complete, generates reservation number #1 and notifies administrator M1, and then terminates the call.

[0040] The call model #1 consists of a language model such as GPT or BERT that is trained to output a response corresponding to an input question and to handle multimodal input (e.g., voice input), a speech conversion model that converts the output of this language model (e.g., text information) into speech, and a program that implements rules for these two models to work together. The call model #1 resides within the information processing device 10 and was created independently by the business operator managing the information processing device 10. It is desirable that the input information, such as personal information, be kept confidential by training the system so that it is not used as a new response.

[0041] Next, the information processing device 10 notifies the user terminal 100 via reservation service #1 that the reservation based on reservation information #1 has been completed, along with the reservation number #1 (step S8). After that, user U1 can use table seat #1 by visiting store #1 and telling administrator M1 the reservation number #1. In other words, user U1 can reserve and use table seat #1 without having to speak with administrator M1 on the phone.

[0042] Here, using Figure 3, we will explain the screen displayed by the user terminal 100 in steps S6 to S8. Figure 3 is a diagram showing an example of the screen of the user terminal 100 according to this embodiment.

[0043] As shown in Figure 3, when user U1 presses button B11 shown in Figure 2, the information processing device 10 provides user terminal 100 with screen C21 for entering the number of reservations. For example, the information processing device 10 provides screen C21 by superimposing content CT21 for entering the number of reservations on screen C12 shown in Figure 2. Here, for example, when user terminal 100 accepts the input of the number of reservations in content CT21 and presses button B21 to instruct the user to request a reservation, it sends the entered number of reservations, the name of user U1 previously registered in reservation service #1, and user U1's telephone number to the information processing device 10 as reservation information #1. The information processing device 10 then accepts reservation information #1 and transitions the screen of user terminal 100 from screen C21 to screen C22.

[0044] In step S7, the information processing device 10 provides screen C22 to the user terminal 100 as a waiting screen while making a call with administrator M1 using call model #1. If administrator M1 responds during the call to acknowledge the reservation, the information processing device 10 transitions the screen on the user terminal 100 from screen C22 to screen C23. For example, on screen C23, the information processing device 10 notifies the user that the reservation based on reservation information #1 has been completed, along with the reservation number #1.

[0045] As described above, the information processing device 10 according to the embodiment generates and provides to the user promotional text for stores corresponding to the search conditions specified by the user, based on the store's past reservation status, information about the user, etc. In other words, the information processing device 10 according to the embodiment can generate and provide promotional text tailored to each store.

[0046] Furthermore, conventionally, for stores that do not support online reservations, users have to make reservations by calling directly. In contrast, according to the information processing device 10 of this embodiment, the call model can make calls to stores regarding reservations on behalf of the user, based on the information input by the user. As a result, the information processing device 10 of this embodiment can enable users to make reservations at stores as if they were making online reservations, thereby improving convenience.

[0047] Furthermore, with the information processing device 10 according to this embodiment, stores can accept reservations without changing their conventional telephone reservation operations, thus improving convenience.

[0048] [2. Other processing examples] The process described above is merely an example, and the information processing device 10 may perform various processes using various types of information. Examples of this are listed below.

[0049] [2-1. Regarding the generation of promotional text using store evaluation information] In the example shown in Figure 1, the information processing device 10 may generate advertising copy for a store based on store information that indicates evaluation information for the store that is the target of the generation of advertising copy (hereinafter sometimes referred to as "target store"), such as store #1 and store #2. For example, the information processing device 10 generates advertising copy by inputting store information (hereinafter sometimes referred to as "target store information") relating to the target store, which includes target store information indicating evaluation information for the target store, and an instruction sentence that instructs the generation model #1 to output advertising copy for the target store based on the target store information. For example, if the evaluation information for the target store includes a comment such as "This store's specialty is dish #2," the information processing device 10 generates advertising copy such as "Please try dish #2, the specialty of this store." If the evaluation information for the target store includes a rating, the information processing device 10 may also generate advertising copy that includes information about the rating (for example, the average rating).

[0050] [2-2. Regarding the generation of promotional slogans based on the number of users in the vicinity of the store] In the example shown in Figure 1, the information processing device 10 may aggregate the number of users located within a predetermined range from the target store (total number of users) based on the location information of each user detected by the terminal device used by each user. The information processing device 10 may then generate advertising copy for the target store based on the number of users located within a predetermined range from the target store. For example, the information processing device 10 generates advertising copy by inputting the number of users located within a predetermined range from the target store, the target store information, and an instruction sentence that instructs the model to output advertising copy for the target store based on the number of users and the target store information into the generation model #1. To give a specific example, the information processing device 10 generates advertising copy for the target store by inputting a rule that includes a message suggesting that reservations will be highly competitive if there are more than a predetermined threshold of users within a predetermined range from the target store, and an instruction sentence that instructs the model to output advertising copy for the target store based on the number of users and the target store information according to that rule, along with the target store information into the generation model #1. For example, the information processing device 10 generates advertising messages such as, "Many customers are considering visiting our store. Please make your reservation as soon as possible."

[0051] [2-3. Regarding the generation of promotional text based on user favorites] In the example shown in Figure 1, the information processing device 10 may generate advertising copy for a target store by inputting user information #1 indicating a store that user U1 has registered as a favorite in a service such as reservation service #1 (hereinafter sometimes referred to as a "favorite store"), target store information, and instruction text that instructs the device to output advertising copy for the target store based on user information #1 and target store information to generation model #1. For example, if user U1 has registered the target store as a favorite store, the information processing device 10 will generate advertising copy such as, "This is a store that user U1 has registered as a favorite."

[0052] Furthermore, the information processing device 10 may generate advertising copy by inputting a rule that includes corresponding information between the target store information and the store information related to the favorite store, and an instruction sentence that instructs the device to output advertising copy for the target store based on the user information #1 and the target store information in accordance with the rule, along with the user information #1, the target store information, and the store information related to the favorite store, into the generation model #1. For example, if the target store is able to serve dish #3 provided by the favorite store, the information processing device 10 will generate advertising copy such as, "You can eat the same dish #3 as at the store that user U1 has registered as a favorite."

[0053] The information processing device 10 may determine the similarity between the target store information and the store information of the favorite store, and if the similarity is above a predetermined threshold, it may generate promotional phrases such as "This store is similar to a store that user U1 has registered as a favorite," or promotional phrases explaining the similarities. Here, similarity may be, for example, the degree of agreement between the store information of both (for example, menus, genres, etc.). Also, similarity may be, for example, the similarity between an image in the target store and an image in the favorite store. The similarity of images may be determined using any image recognition means.

[0054] [2-4. Regarding the generation of promotional text tailored to user attributes] In the example shown in Figure 1, the information processing device 10 may generate advertising copy for a target store by inputting user information #1 indicating the attributes of user U1, target store information, and an instruction sentence instructing the model #1 to output advertising copy for the target store based on user information #1 and the target store information. For example, the information processing device 10 generates advertising copy by inputting a rule that includes information corresponding to the attributes of user U1 from the target store information, and an instruction sentence instructing the model #1 to output advertising copy for the target store based on user information #1 and the target store information, along with user information #1 and the target store information, into the model #1. For example, the information processing device 10 generates advertising copy such as, "Customers of the same age as user U1 are visiting our store."

[0055] [2-5. Regarding the generation of promotional text based on the number of viewers of store information] In the example in Figure 1, the information processing device 10 may aggregate the current number of viewers of the target store information in the reservation service #1. The information processing device 10 may then generate advertising copy for the target store based on the current number of viewers of the target store information. For example, the information processing device 10 generates advertising copy by inputting the current number of viewers of the target store information, the target store information, and an instruction sentence that instructs the model to output advertising copy for the target store based on the number of viewers and the target store information into the generation model #1. To give a specific example, the information processing device 10 generates advertising copy for the target store by inputting a rule that states that if the current number of viewers of the target store information is above a predetermined threshold, a message suggesting that reservations will be highly competitive should be included, and an instruction sentence that instructs the model to output advertising copy for the target store based on the number of viewers and the target store information according to that rule, along with the number of viewers and the target store information into the generation model #1. For example, the information processing device 10 generates advertising copy such as, "Many customers are considering making a reservation. Please make your reservation quickly."

[0056] [2-6. Training of Generative Model #1 based on conversions] In the example in Figure 1, the information processing device 10 may determine whether user U1 has achieved a conversion with respect to the store corresponding to search condition #1, based on user U1's behavior information after being provided with advertising copy #1, advertising copy #2, etc. The information processing device 10 may then train generative model #1 based on the result of determining whether or not a conversion occurred. For example, based on user U1's reservation request for store #1, the information processing device 10 determines that user U1 has achieved a conversion with respect to store #1 due to advertising copy #1. The information processing device 10 then trains generative model #1 using advertising copy #1 as positive data.

[0057] Furthermore, based on user U1's reservation request for store #1, the information processing device 10 may determine, based on advertising copy #2, that user U1 did not convert to store #2. The information processing device 10 may then use advertising copy #2 as negative data to train the generative model #1.

[0058] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device 10 will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. As shown in Figure 4, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0059] (Regarding Communications Section 20) The communication unit 20 is implemented, for example, by a NIC (Network Interface Card). The communication unit 20 is connected to the network N by wire or wireless connection and transmits and receives information with user terminals 100, store terminals 200, etc.

[0060] (Regarding memory unit 30) The storage unit 30 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. As shown in Figure 4, the storage unit 30 has a user information database 31, a store information database 32, and a model database 33.

[0061] (Regarding User Information Database 31) The user information database 31 stores various types of information about the user. Here, an example of the information stored in the user information database 31 will be explained using Figure 5. Figure 5 is a diagram showing an example of the user information database 31. In the example in Figure 5, the user information database 31 has items such as "User ID," "Attribute Information," "Hobbies and Preferences Information," "Favorites Registration Information," "Browsing History," "Purchase History," and "Search History."

[0062] "User ID" indicates identification information used to identify the user. "Attribute Information" indicates the user's attributes. "Hobbies and Preferences Information" indicates the user's hobbies and preferences, and stores include information such as the food and drinks the user likes, the categories of stores the user likes, the atmosphere of stores the user likes, and the user's hobbies. "Favorite Registration Information" indicates information about stores that the user has registered as favorites, and stores include identification information (store ID) used to identify the store. "Browsing History" indicates the user's content browsing history. "Purchase History" indicates the user's purchase history of products. "Search History" indicates the user's search history across various services.

[0063] In other words, Figure 5 shows an example where the user's attribute information identified by the user ID "UID#1" is "Attribute Information #1", hobby and preference information is "Hobby and Preference Information #1", favorite registration information is "Favorite Registration Information #1", browsing history is "Browsing History #1", purchase history is "Purchase History #1", and search history is "Search History #1".

[0064] (Regarding store information database 32) The store information database 32 stores various types of information about the store. Here, an example of the information stored in the store information database 32 will be explained using Figure 6. Figure 6 is a diagram showing an example of the store information database 32. In the example in Figure 6, the store information database 32 has items such as "Store ID," "Location," "Transaction Target Information," "Vacancy Information History," and "Rating Information."

[0065] "Store ID" indicates identification information used to identify the store. "Location" indicates the store's location. "Transaction Information" indicates information about the transactions offered by the store; for example, if the store is a restaurant, it stores information about the menu. "Vacancy History" shows the history of vacancy information received from the store terminal 200. "Rating Information" shows the ratings of the store posted by users on restaurant referral services, etc.

[0066] In other words, Figure 6 shows an example where the location of a store identified by the store ID "SID#1" is "Location#1", the transaction target information is "Transaction Target Information#1", the vacancy information history is "Vacancy Information History#1", and the evaluation information is "Evaluation Information#1".

[0067] (Regarding Model Database 33) The model database 33 stores models that have undergone a predetermined training process. For example, the model database 33 stores generative model #1 and call model #1.

[0068] (Regarding the control unit 40) The control unit 40 is a controller and is realized, for example, by executing various programs stored in the memory device inside the information processing device 10 using RAM as a working area, using a CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc. Alternatively, the control unit 40 is a controller and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). As shown in Figure 4, the control unit 40 according to this embodiment has an extraction unit 41, a generation unit 42, a provision unit 43, a communication unit 44, a determination unit 45, and a learning unit 46, and realizes or executes the information processing functions and operations described below.

[0069] (Regarding the extraction unit 41) The extraction unit 41 extracts store information for stores with available seats based on the search criteria specified by the user. For example, in the example in Figure 1, the extraction unit 41 extracts store information for stores corresponding to search criteria #1 specified by user U1 in the storage unit 30 (e.g., store information database 32).

[0070] (Regarding the generation unit 42) The generation unit 42 generates store advertisements by inputting store information and instruction sentences that instruct the generative model, which has been trained to generate answers to input questions, to output store advertisements based on the store information. For example, in the example in Figure 1, the generation unit 42 refers to the storage unit 30 (for example, the store information database 32 or the model database 33) and generates store advertisements for the store by inputting store information associated with the store and instruction sentences that instruct the generative model #1, which has been trained to generate answers to input questions, to output store advertisements for the store based on the store information.

[0071] Furthermore, the generation unit 42 may generate advertising copy by inputting store information indicating the store's past reservation status and instruction text into the generation model. For example, in the example in Figure 1, if the store for which the advertising copy is to be generated is rarely available for reservation, the generation unit 42 inputs a rule to incorporate that rarity and an instruction text that instructs the generation model 1 to output advertising copy based on store information #1 according to that rule, along with store information #1, into the generation model 1, thereby generating advertising copy #1 for store #1.

[0072] Furthermore, the generation unit 42 may generate advertising copy by inputting store information indicating an evaluation of the store and instruction text into the generation model. For example, in the example in Figure 1, the generation unit 42 generates advertising copy by inputting target store information indicating an evaluation of the target store and instruction text that instructs the generation model #1 to output advertising copy for the target store based on the target store information.

[0073] Furthermore, the generation unit 42 may generate advertising copy by inputting the number of users located within a predetermined range from the store, store information, and an instruction document that instructs the model to output advertising copy based on the number of users and store information into the generation model. For example, in the example in Figure 1, the generation unit 42 generates advertising copy by inputting the number of users located within a predetermined range from the target store, target store information, and an instruction document that instructs the model to output advertising copy for the target store based on the number of users and target store information into the generation model #1.

[0074] Furthermore, the generation unit 42 may generate advertising copy by inputting the number of viewers of the store information, the store information, and an instruction sentence that instructs the generation model to output advertising copy based on the number of viewers and the store information. For example, in the example in Figure 1, the generation unit 42 generates advertising copy by inputting the current number of viewers of the target store information, the target store information, and an instruction sentence that instructs the generation model #1 to output advertising copy for the target store based on the number of viewers and the target store information.

[0075] Furthermore, the generation unit 42 may generate advertising copy by inputting user information about the user, store information, and an instruction document that instructs the generation model to output advertising copy based on the user information and store information. For example, in the example in Figure 1, the generation unit 42 refers to the storage unit 30 (for example, the user information database 31, the store information database 32, or the model database 33) and inputs user information #1, store information #2, and an instruction document that instructs the generation model #1 to output advertising copy for store #2 based on user information #1 and store information #2, thereby generating advertising copy #2 for store #2.

[0076] Furthermore, the generation unit 42 may generate advertising copy by inputting user information indicating stores that the user has registered as favorites in a predetermined service, store information, and instruction text into the generation model. For example, in the example in Figure 1, the generation unit 42 generates advertising copy for a target store by inputting user information #1 indicating a favorite store, target store information, and instruction text that instructs the system to output advertising copy for the target store based on user information #1 and target store information.

[0077] Furthermore, the generation unit 42 may generate advertising copy by inputting user information, store information, a rule indicating that the store information should include information corresponding to the store that the user has registered as a favorite, and an instruction sentence instructing the generation model to output advertising copy according to the rule. For example, in the example in Figure 1, the generation unit 42 generates advertising copy by inputting a rule indicating that the target store information and the store information related to the favorite store should include corresponding information, and an instruction sentence instructing the generation model #1 to output advertising copy for the target store based on user information #1 and the target store information, along with user information #1 and the target store information.

[0078] Furthermore, the generation unit 42 may generate advertising copy by inputting user information indicating the user's hobbies and preferences, store information, a rule indicating that the store information should include information corresponding to the user's hobbies and preferences, and an instruction sentence instructing the generation model to output advertising copy according to the rule. For example, in the example in Figure 1, the generation unit 42 generates advertising copy #2 for store #2 by inputting a rule indicating that the store information should include information corresponding to the user information, and an instruction sentence instructing the generation model #1 to output advertising copy based on user information #1 and store information #2 according to the rule, along with user information #1 and store information #2, into the generation model #1.

[0079] Alternatively, the generation unit 42 may generate advertising copy by inputting user information indicating the user's attributes, store information, a rule indicating that the store information should include information corresponding to the user's attributes, and an instruction sentence instructing the generation model to output advertising copy according to the rule. For example, in the example in Figure 1, the generation unit 42 generates advertising copy by inputting a rule indicating that the target store information should include information corresponding to the user U1's attributes, and an instruction sentence instructing the generation model #1 to output advertising copy for the target store based on user information #1 and target store information, along with user information #1 and target store information.

[0080] (Regarding Section 43) The provision unit 43 provides the user with store information and advertising copy as search results for the search criteria. For example, in the example in Figure 1, the provision unit 43 provides the user terminal 100 with store information and advertising copy for the store corresponding to search criterion #1, via reservation service #1, as search results for search criterion #1.

[0081] (Regarding the telephone unit 44) When the call unit 44 receives reservation information from a user regarding a store reservation, it uses a call model to make a call to the store regarding the reservation based on that reservation information. For example, in the example in Figure 1, the call unit 44 refers to the storage unit 30 (for example, the model database 33) and uses call model #1 to make a call to administrator M1 regarding the reservation based on reservation information #1 via the store terminal 100-1.

[0082] (Regarding the determination unit 45) The determination unit 45 determines whether the user has converted to a store based on the user's behavior information after the promotional text has been provided. For example, in the example in Figure 1, the determination unit 45 determines whether user U1 has converted to a store corresponding to search condition #1 based on the user U1's behavior information after the promotional text #1, promotional text #2, etc., have been provided.

[0083] (Regarding Learning Section 46) The learning unit 46 trains the generative model based on the determination result from the determination unit 45. For example, in the example in Figure 1, if the learning unit 46 determines that user U1 has converted to store #1 based on advertising copy #1, it trains the generative model #1 using advertising copy #1 as positive data.

[0084] [4. Information Processing Flow] The information processing procedure of the information processing device 10 according to the embodiment will be explained using Figure 7. Figure 7 is a flowchart of an example of the information processing procedure according to the embodiment.

[0085] As shown in Figure 7, the information processing device 10 extracts store information for stores with available seats based on search conditions specified by the user (step S101). Next, the information processing device 10 generates store advertisements by inputting store information and instruction sentences that instruct the generative model, which has been trained to generate answers to the input questions, to output store advertisements based on the store information (step S102). Subsequently, the information processing device 10 provides the store information and advertisements to the user as search results for the search conditions (step S103).

[0086] Next, the information processing device 10 determines whether or not it has received reservation information from the user regarding the store reservation (step S104). If the reservation information has not been received from the user (step S104; No), the information processing device 10 terminates the process. On the other hand, if the reservation information has been received from the user (step S104; Yes), the information processing device 10 uses a call model to make a call to the store regarding the reservation based on the reservation information (step S105), and then terminates the process.

[0087] [5. Variations] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0088] [5-1. About the store] In the above embodiment, an example was shown where the store is a restaurant, but the store is not limited to such examples. For example, the store may be a beauty salon, a relaxation salon, a hospital, or the like.

[0089] [5-2. Regarding the processing method] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above text and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0090] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0091] Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

[0092] [6. Effects] As described above, the information processing device 10 according to the embodiment includes an extraction unit 41 that extracts store information relating to stores with available seats based on search conditions specified by the user. The generation unit 42 generates store advertisements by inputting store information and instruction text that instructs a generation model, which has been trained to generate answers to input questions, to output store advertisements based on the store information. The provision unit 43 provides the store information and advertisements to the user as search results for the search conditions. When the call unit 44 receives reservation information relating to a store reservation from the user, it uses a call model to make a call to the store regarding the reservation based on that reservation information.

[0093] As a result, the information processing device 10 according to the embodiment can generate and provide to the user advertising copy for stores corresponding to the search conditions specified by the user, based on information about the stores, thus enabling the generation and provision of advertising copy tailored to each store.

[0094] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates advertising copy by inputting store information showing the store's past reservation status and instruction text into the generation model. Also, the generation unit 42 generates advertising copy by inputting store information showing the evaluation of the store and instruction text into the generation model.

[0095] As a result, the information processing device 10 according to the embodiment can generate advertising slogans for stores based on the store's past reservation status, store ratings, etc., and can generate and provide advertising slogans tailored to each store.

[0096] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates advertising copy by inputting the number of users located within a predetermined range from the store, store information, and an instruction sentence that instructs the output of advertising copy based on the number of users and store information into the generation model. In addition, the generation unit 42 generates advertising copy by inputting the number of people viewing the store information, store information, and an instruction sentence that instructs the output of advertising copy based on the number of viewers and store information into the generation model.

[0097] As a result, the information processing device 10 according to the embodiment can generate advertising slogans for stores in accordance with real-time information about the stores, and can therefore generate and provide advertising slogans that are tailored to each store.

[0098] Furthermore, in the information processing device 10 according to the embodiment, for example, the generation unit 42 generates advertising copy by inputting user information relating to a user, store information, and an instruction sentence that instructs the output of advertising copy based on the user information and store information into the generation model. The generation unit 42 also generates advertising copy by inputting user information indicating stores that the user has favorited in a predetermined service, store information, and an instruction sentence into the generation model. The generation unit 42 also generates advertising copy by inputting user information, store information, a rule indicating that the store information should include information corresponding to the store that the user has favorited, and an instruction sentence that instructs the output of advertising copy according to the rule into the generation model. The generation unit 42 also generates advertising copy by inputting user information indicating the user's hobbies and preferences, store information, a rule indicating that the store information should include information corresponding to the user's hobbies and preferences, and an instruction sentence that instructs the output of advertising copy according to the rule into the generation model. Furthermore, the generation unit 42 generates advertising copy by inputting user information indicating the user's attributes, store information, rules indicating that the store information should include information corresponding to the user's attributes, and instruction text instructing the model to output advertising copy according to the said rules.

[0099] As a result, the information processing device 10 according to the embodiment can generate advertising copy for stores in accordance with information about the user, and can generate and provide advertising copy that is appropriate for the user who provides information about the store.

[0100] Furthermore, in the information processing device 10 according to the embodiment, for example, the determination unit 45 determines whether or not the user has made a conversion related to the store based on the user's behavior information after the advertising copy has been provided. Then, the learning unit 46 learns the generative model based on the determination result from the determination unit 45.

[0101] As a result, the information processing device 10 according to the embodiment can learn the generative model depending on whether or not a conversion occurs after the advertising copy is provided, thereby improving the appeal of the advertising copy output by the generative model.

[0102] [7. Hardware Configuration] Furthermore, the information processing device 10 according to each embodiment described above can be realized by a computer 1000 having a configuration such as that shown in Figure 8. The following explanation will use the information processing device 10 as an example. Figure 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, ROM 1200, RAM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0103] The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400, and controls various parts. The ROM 1200 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0104] The HDD 1400 stores programs executed by the CPU 1100, as well as data used by such programs. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to network N in this embodiment) and sends it to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0105] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the data it generates to output devices via the input / output interface 1600.

[0106] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1300. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1300 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0107] For example, when computer 1000 functions as information processing device 10, the CPU 1100 of computer 1000 realizes the functions of control unit 40 by executing programs loaded on RAM 1300. The HDD 1400 stores the data in the storage device of information processing device 10. The CPU 1100 of computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0108] [8. Other] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0109] Furthermore, the configuration of the aforementioned information processing device 10 can be flexibly changed, for example, by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, depending on the function.

[0110] Furthermore, the term "part" in the claims can be replaced with "means," "circuit," etc. For example, "extraction part" can be replaced with "extraction means" or "extraction circuit." [Explanation of symbols]

[0111] 1. Information Processing System 10 Information Processing Devices 20 Communications Department 30 Storage section 31. User Information Database 32 Store Information Database 33 Model Databases 40 Control Unit 41 Extraction part 42 Generation part 43 Providing Department 44 Telephone section 45 Judgment section 46 Learning Department 100 User Terminals 200 store terminals

Claims

1. An extraction unit that extracts store information for stores with available seats based on search criteria specified by the user, A generation unit generates advertising copy for a store by inputting store information and instruction text that instructs the store to output advertising copy for the store based on the store information to a generative model that has been trained to generate answers to input questions. A provisioning unit that provides the user with the store information and the advertising copy as search results for the aforementioned search conditions, When the aforementioned store receives reservation information from the user, the call unit uses a call model to make a call to the store regarding the reservation based on the reservation information. An information processing device characterized by having the following features.

2. The generating unit is The advertising copy is generated by inputting the store information, which shows the past reservation status of the store, and the instruction text into the generation model. The information processing apparatus according to feature 1.

3. The generating unit is The advertising copy is generated by inputting the store information, which indicates an evaluation of the store, and the instruction text into the generation model. The information processing apparatus according to feature 1.

4. The generating unit is The advertising copy is generated by inputting the number of users located within a predetermined range from the store, the store information, and the instruction text that instructs the model to output the advertising copy based on the number of users and the store information. The information processing apparatus according to feature 1.

5. The generating unit is The advertising copy is generated by inputting the number of viewers of the store information, the store information, and the instruction text that instructs the model to output the advertising copy based on the number of viewers and the store information. The information processing apparatus according to feature 1.

6. The generating unit is The advertising copy is generated by inputting user information relating to the user, store information, and instruction text that instructs the model to output the advertising copy based on the user information and store information into the generation model. The information processing apparatus according to feature 1.

7. The generating unit is The advertising copy is generated by inputting the user information, which indicates the stores that the user has favorited in a predetermined service, the store information, and the instruction text into the generation model. The information processing apparatus according to feature 6.

8. The generating unit is The advertising copy is generated by inputting the user information, the store information, a rule indicating that the store information should include information corresponding to the store that the user has favorited, and an instruction sentence that instructs the model to output the advertising copy in accordance with the rule. The information processing apparatus according to feature 7.

9. The generating unit is The advertising copy is generated by inputting the user information indicating the user's hobbies and preferences, the store information, a rule indicating that the store information should include information corresponding to the user's hobbies and preferences, and an instruction document instructing the model to output the advertising copy according to the rule. The information processing apparatus according to feature 6.

10. The generating unit is The advertising copy is generated by inputting the user information indicating the user's attributes, the store information, a rule indicating that the store information should include information corresponding to the user's attributes, and an instruction document instructing the model to output the advertising copy according to the rule. The information processing apparatus according to feature 6.

11. A determination unit that determines whether or not the user has converted to the store based on the user's behavior information after the aforementioned advertising copy has been provided, A learning unit that learns the generative model based on the determination result by the determination unit. The information processing apparatus according to claim 1, further comprising the features.

12. A method of information processing performed by a computer, An extraction process that extracts store information for stores with available seats based on search criteria specified by the user, A generation process involves inputting store information and instruction text that instructs a generative model, which has been trained to generate answers to input questions, to output advertising text for the store based on the store information, thereby generating advertising text for the store. A provision process that provides the user with the store information and the advertising copy as search results for the aforementioned search conditions, When reservation information regarding the reservation of the store is received from the user, a call process is performed using a call model to make a call to the store regarding the reservation based on the reservation information. An information processing method characterized by including

13. A procedure for extracting store information about stores with available seats based on search criteria specified by the user, A generation procedure for generating advertising copy for a store by inputting store information and instruction text that instructs a generative model, which has been trained to generate answers to input questions, to output advertising copy for the store based on the store information, A procedure for providing the user with the store information and the advertising copy as search results for the aforementioned search conditions, When reservation information regarding the reservation of the aforementioned store is received from the aforementioned user, a call procedure is performed using a call model to make a call to the aforementioned store regarding the reservation based on said reservation information. An information processing program that causes a computer to execute something.

Images