Work introduction information generation support device and program

Abstract

To provide a work introduction information generation support device and a program that can obtain work introduction information which reflects a taste or interest for each customer.SOLUTION: A work introduction information generation support device comprises: reception means that receives browsing request information which includes customer identification information identifying a customer and work identification information identifying a browsing work; customer information acquisition means that acquires customer information associated with the customer identification information on the basis of the received customer identification information; customization means that customizes prompt information requesting generation of work introduction information associated with the work to prompt information which is appropriate to the customer on the basis of the received browsing request information and the acquired customer information; and provision means that provides the customized prompt information to a large-scale language model.SELECTED DRAWING: Figure 14

Description

Technical Field

[0001] Embodiments of the present invention relate to a work introduction information generation support device and a program.

Background Art

[0002] Conventionally, in stores that sell music CDs, movie DVDs, etc., rental shops for music CDs, movie DVDs, etc., movie theaters, bookstores and art galleries that sell books and paintings, libraries, art museums and museums, or online shops that provide works such as music, videos, books, paintings, illustrations, etc. via the Internet (hereinafter collectively referred to as "stores, etc."), there are terminals that display information related to the works to be purchased, rented, or viewed and introduce the works. This terminal may be a dedicated terminal installed in a store, etc., a mobile terminal carried by a customer, or a television owned by a customer (collectively referred to as an "interface" for dedicated terminals, mobile terminals, televisions, etc.). Customers can operate the interface to view the work introduction information of the desired work.

[0003] However, the conventional technology provides predetermined work introduction information that shows the content and features of the work, and it has been difficult to provide work introduction information that reflects the preferences and interests of each customer. Therefore, there are limitations in attracting customers' interests and differentiating from other work introduction information.

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present invention is to provide a work introduction information generation support device and a program capable of obtaining work introduction information that reflects the preferences and interests of each customer.

Means for Solving the Problems

[0005] The work introduction information generation support device according to the embodiment includes a reception unit that receives browsing request information including customer identification information for identifying a customer and work identification information for identifying a work to be browsed, a customer information acquisition unit that acquires customer information related to the customer identification information based on the received customer identification information, a customization unit that customizes prompt information for requesting work introduction information into prompt information suitable for the customer based on the received browsing request information and the acquired customer information, and a provision unit that provides the customized prompt information to a large language model.

Brief Description of Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0007] Hereinafter, with reference to the drawings, an embodiment of the invention will be described in detail. In the embodiment, the prompt generation device will be described as an example of a work introduction information generation support device. Also, in the embodiment, a mobile terminal carried by a customer will be described as an example of an interface. Further, in the embodiment, a rental shop that rents CDs (Compact Disks), video cassettes, DVDs (digital versatile discs), Blu-ray discs, etc. (hereinafter collectively referred to as "media") will be described as an example of a store. A CD is, for example, a disk on which music is recorded. A DVD is a disk on which movies and music are recorded. Hereinafter, the information (for example, movies, music, etc.) recorded on CDs, video cassettes, DVDs, and Blu-ray discs will be referred to as works. Note that in the following description, the term "work" may be used in a broader sense including movies and music (including paintings, books, art, etc.). The present invention is not limited by the embodiments described below.

[0008] The rental shop has a large number of media items displayed in the store. The rental shop lends media related to works that the customer wants to watch or listen to to the customer. When the customer becomes a member of the rental shop, the customer can use an online platform from a mobile terminal (such as a smartphone, PDA (Personal Digital Assistant), tablet terminal, etc.) that the customer carries, and by specifying the work that the customer wants to watch, the customer can display work introduction information of the work scheduled to be rented or the work that the customer is interested in on the mobile terminal, and can confirm in advance whether the customer really wants to rent the work. Since the displayed work introduction information is information that adds the customer's hobbies and preferences in addition to the work information that introduces the content of the work, the customer can be more attracted to the interest in renting the work by browsing the work introduction information, and can also have the desire to purchase aroused.

[0009] FIG. 1 is a system configuration diagram including a system 10 according to an embodiment. The system 10 is composed of at least a mobile terminal 1 and a prompt generation device 5. In the embodiment, the system 10 is composed of a mobile terminal 1, a customer server 3, and a prompt generation device 5. The mobile terminal 1, the customer server 3, and the prompt generation device 5 are connected to each other and can communicate via a network N such as an Internet line, and can transmit and receive information to and from each other. Further, a processing server 7 equipped with a large language model 742 is connected to the network N.

[0010] The mobile terminal 1 is an example of an interface and is a terminal that a customer can carry, such as a smartphone, PDA, or tablet terminal. The mobile terminal 1 has application software installed. Using the application software, the mobile terminal 1 inputs attribute information (age, gender, work viewing history, etc.) of the customer who has become a member, information about the customer's hobbies, and information about the customer's favorite works to the customer server 3. The mobile terminal 1 also connects to the prompt generation device 5 using the application software, specifies the work that the customer wishes to view, and creates browsing request information including work identification information for identifying the work. The mobile terminal 1 transmits the created browsing request information to the prompt generation device 5.

[0011] Also, the mobile terminal 1 receives work introduction information for introducing a designated work from the prompt generation device 5. The mobile terminal 1 displays the received work introduction information on the display unit 18 (see FIG. 3). By browsing the displayed work introduction information, the customer recognizes the relationship between the content of the work and the customer's hobbies and preferences.

[0012] The customer server 3 is an example of a customer database installed, for example, in the backyard of a rental shop. The customer server 3 stores various customer information related to customers (customer attribute information, customer's past work viewing history information, customer's hobby and preference information, etc.) separately for each customer. The customer server 3 will be described later with reference to FIGS. 4 to 7. Note that the customer server 3 may be installed at the headquarters that operates the rental shop, or the customer server 3 may be a cloud server installed on the cloud.

[0013] When the prompt generation device 5 receives viewing request information related to a work designated by the customer from the mobile terminal 1, the prompt generation device 5 acquires the customer information of the customer from the customer server 3.

[0014] With reference to the acquired customer information, the prompt generation device 5 customizes the prompt information of the designated work related to the customer for the customer to generate prompt information suitable for the customer (including the customer information of the customer). The prompt information is information for requesting the processing device 7 to generate work introduction information related to the work. The customized prompt information includes the customer information of the customer. Then, the prompt generation device 5 provides (transmits) the customized prompt information to the processing server 7. That is, based on the customized prompt information, the prompt generation device 5 requests the processing server 7 to generate work introduction information. Also, the prompt generation device 5 receives the work introduction information generated by the processing server 7 and transmits it to the mobile terminal 1 that transmitted the viewing request information.

[0015] The processing server 7 is a server installed outside the system 10 (for example, constructed by an external company). The processing server 7 is equipped with a large language model 742. The large language model 742 is a language model (program) constructed using an extremely large dataset and deep learning technology. The large language model 742 is constructed by significantly increasing the "computational complexity", "data volume", and "parameter volume" compared to conventional natural language models, enabling smooth conversations similar to those of humans, and is a general-purpose model capable of performing various processes using natural language (for example, content recognition, translation, prediction, generation) with high precision, which is a well-known technology. The large language model 742 is described, for example, in "A Survey of Large Language Models - How to Create a Large Language Model (LLM) Megatron-DeepSpeed Edition Part1 (zenn.dev)".

[0016] The work DB (database) 9 is connected to the network N. The work DB 9 stores various work information related to the works rented out at the rental shop (genre of the work, actors, director, content summary, setting of characters, theme of the work, subtitle data, etc.) for each work. The processing server 7 collects the work information stored in the work DB 9 for each work and stores it in the work information section 743.

[0017] Also, the SNS information section Da and the review information section Db are connected to the network N. The SNS information section Da stores information related to works (for example, review information and SNS information posted on SNS (Social Networking Service)). The review information section Db stores work evaluation information (age of the evaluator, gender of the evaluator, evaluation content) posted on the review site. The processing server 7 collects the SNS information stored in the SNS information section Da and the work evaluation information stored in the review information section Db. From the work evaluation information and SNS information, information such as which age group of people are evaluating the work in what way is collected. The SNS information is, for example, information such as "Recommended for families by men in their 30s" and "There were different discoveries from when I was a child by men in their 30s".

[0018] The network N is also connected to a work information collection unit Dc. The work information collection unit Dc collects work information from the work DB 9, SNS information from the SNS information unit Da, and work evaluation information from the review information unit Db. The processing server 7 collects work information, SNS information, and work evaluation information from the work information collection unit Dc. The processing server 7 stores the collected work information in the work information unit 743, the collected SNS information in the SNS storage unit 744, and the collected work evaluation information in the review storage unit 745.

[0019] The processing server 7 causes the large language model 742 to learn based on the collected information. The large language model 742 learns by collecting a large amount of work information, SNS information, and work evaluation information. The processing server 7 enriches the generated work introduction information by causing the large language model 742 to learn based on the collected work information. Also, the processing server 7 enriches the background information for generating work introduction information tailored to customers by causing the large language model 742 to learn based on the collected work evaluation information. Further, the processing server 7 enriches the background information for generating work introduction information, such as words and comments used in the introduction of works, by causing the large language model 742 to learn based on the collected SNS information and review information.

[0020] The processing server 7 generates work introduction information related to a work based on the prompt information received from the prompt generation device 5. The processing server 7 generates work introduction information suitable for the customer (customized for the customer to fully reflect the customer's hobbies and interests) based on the customer information included in the received prompt information. The work processing information suitable for each individual customer can enhance the satisfaction of the customer. Also, for customers considering purchasing or renting a work, it can enhance the willingness to purchase or rent. The processing server 7 transmits the generated work introduction information to the prompt generation device 5.

[0021] From here, the processes and data flows among the mobile terminal 1, the customer server 3, the prompt generation device 5, and the processing server 7 will be described. FIG. 2 is a sequence diagram showing the processes and data flows among the mobile terminal 1, the customer server 3, the prompt generation device 5, and the processing server 7.

[0022] As shown in FIG. 2, the processing server 7 collects work information, SNS information, and work evaluation information from the work information collection unit Dc, and trains the large language model 742 (T1).

[0023] The mobile terminal 1 accesses the homepage of the rental shop and performs an enrollment registration procedure to become a member of the rental shop (T2). The rental shop issues a customer ID (Identification: customer identification information) that identifies the customer to the customer who carries the enrolled mobile terminal 1. The mobile terminal 1 installs application software during the enrollment registration procedure. The mobile terminal 1 with the installed application software can perform operations such as inputting customer information and sending a work viewing request. Also, the mobile terminal 1 with the installed application software can display the work introduction information received from the prompt generation device 5. The mobile terminal 1 inputs customer information when completing the enrollment procedure and transmits the customer information to the customer server 3 together with the issued customer ID (T3). The customer server 3 stores the customer information received from the mobile terminal 1 in association with the simultaneously received customer ID (T4). Note that the customer information and customer ID of the customer may be transmitted from the terminal of the rental shop that has performed the enrollment registration to the customer server 3 (processing of T3).

[0024] When viewing a work, the customer logs in to the mobile terminal 1 (T5). Then, the mobile terminal 1 creates viewing request information including work identification information (work ID or work name) that identifies the work to be viewed and the customer ID according to the customer's operation (T6). Then, the mobile terminal 1 transmits the created viewing request information to the prompt generation device 5 according to the customer's operation (T7).

[0025] The prompt generation device 5 transmits the customer ID included in the received browsing request information to the customer server 3 (T8). That is, the prompt generation device 5 makes an inquiry about the customer information of the customer to the customer server 3 (T8). The customer server 3 extracts the customer information of the customer based on the received customer ID (T9). Then, the customer server 3 transmits the extracted customer information to the prompt generation device 5 (T10). The prompt generation device 5 calls a fixed sentence of prompt information related to the work based on the work identification information received from the mobile terminal 1, and generates prompt information suitable for the customer (that is, customized for the customer) by reflecting the received customer information in the fixed sentence (T11). Then, the prompt generation device 5 transmits (provides) the generated prompt information for the customer to the processing server 7 via the network N (T12).

[0026] Based on the received prompt information for the customer, the processing server 7 uses the large language model 742 to generate work introduction information suitable for the customer (T13). Then, the processing server 7 transmits the generated work introduction information to the prompt generation device 5 (T14).

[0027] The prompt generation device 5 that has received the work introduction information transmits (outputs) the work introduction information to the mobile terminal 1 (T15). The mobile terminal 1 displays the received work introduction information on the display unit 18 (T16). The customer can view the work introduction information suitable for the customer that is displayed.

[0028] Also, the prompt generation device 5 transmits the work identification information included in the received work introduction information to the customer server 3 together with the customer ID (T17). The customer server 3 adds the browsing information of the work specified by the work identification information to the browsing history of the customer based on the received customer ID and work identification information, and stores it by adding it to the already stored browsing information (T18).

[0029] From here, the hardware configuration of the mobile terminal 1 will be described. FIG. 3 is a block diagram showing the hardware configuration of the mobile terminal 1. As shown in FIG. 3, the mobile terminal 1 includes a CPU (Central Processing Unit) 11 which is an example of a processor, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a memory unit 14, etc. The CPU 11 serves as the control main body. The ROM 12 stores various programs. The RAM 13 expands programs and various data. The memory unit 14 stores various programs. The CPU 11, ROM 12, RAM 13, and memory unit 14 are connected to each other via a bus 15. The CPU 11, ROM 12, and RAM 13 constitute a control unit 100. That is, the control unit 100 executes control processing related to the mobile terminal 1 described later by operating according to a control program stored in the ROM 12 and the memory unit 14 and expanded in the RAM 13.

[0030] The RAM 13 has a browsing request information section 131 and a work information section 132. The browsing request information section 131 stores browsing request information for requesting work introduction information of a work created by a customer. The work information section 132 receives and stores work introduction information generated by the processing server 7 based on the transmitted browsing request information from the prompt generation device 5.

[0031] The memory unit 14 is composed of a non-volatile memory such as an HDD (Hard Disc Drive) or a flash memory that retains stored information even when the power is turned off. The memory unit 14 includes a control program section 141. The control program section 141 stores a control program for controlling the mobile terminal 1. Installed application software is stored in the control program section 141.

[0032] Also, the control unit 100 is connected to an operation unit 17 and a display unit 18 via the bus 15 and a controller 16. The operation unit 17 is a keyboard. The display unit 18 displays information to an operator who operates the mobile terminal 1. Note that the operation unit 17 may be a touch panel provided on the display unit 18.

[0033] The control unit 100 is also connected to the communication unit 19 via the bus 15. The communication unit 19 is communicably connected to the prompt generation device 5 via the network N and can transmit and receive information.

[0034] Next, the hardware configuration of the customer server 3 will be described. FIG. 4 is a block diagram showing the hardware configuration of the customer server 3. As shown in FIG. 4, the customer server 3 includes a CPU 31, which is an example of a processor, a ROM 32, a RAM 33, a memory unit 34, and the like. The CPU 31 serves as the control main body. The ROM 32 stores various programs. The RAM 33 expands programs and various data. The memory unit 34 stores various programs. The CPU 31, the ROM 32, the RAM 33, and the memory unit 34 are connected to each other via the bus 35. The CPU 31, the ROM 32, and the RAM 33 constitute the control unit 300. That is, the control unit 300 executes control processing related to the customer server 3 by operating according to the control program stored in the ROM 32 and the memory unit 34 and expanded in the RAM 33 by the CPU 31.

[0035] The memory unit 34 is composed of a non-volatile memory such as an HDD or a flash memory that retains stored information even when the power is turned off. The memory unit 34 includes a control program unit 341, a customer information unit 342, and the like. The control program unit 341 stores a control program for controlling the customer server 3. The customer information unit 342 stores customer information related to customers who are members of the rental shop. The customer information unit 342 will be described later with reference to FIGS. 5 to 7.

[0036] The control unit 300 is also connected to the operation unit 37 and the display unit 38 via the bus 35 and the controller 36. The operation unit 37 is a keyboard. The display unit 38 displays information to the operator who operates the customer server 3.

[0037] Further, the control unit 300 is connected to the communication unit 39 via the bus 35. The communication unit 39 is communicably connected to the mobile terminal 1 via the network N and can transmit and receive information. Also, the communication unit 39 is connected to the prompt generation device 5 via a communication line and can transmit and receive information.

[0038] Next, the customer information unit 342 will be described. FIG. 5 is a memory map showing the memory configuration of the customer information unit 342. As shown in FIG. 5, the customer information unit 342 stores the customer information of each customer according to the customer ID issued to the customer who has become a member. The customer information unit 342 includes a customer ID unit 3421, an attribute information unit 3422, a browsing history unit 3423, and a preference information unit 3424. The customer ID unit 3421 stores the customer ID for identifying the customer who has become a member for each customer. The attribute information unit 3422 stores, in association with the customer ID stored in the customer ID unit 3421, the attribute information (gender, age, age group, address, phone number, address of the mobile terminal 1, etc.) of the customer as customer information.

[0039] The browsing history unit 3423 stores, in association with the customer ID stored in the customer ID unit 3421, the information of the works (work name, work identification information for identifying the work, date of browsing, etc.) that the customer has browsed and viewed (hereinafter collectively referred to as "browsed") in the past as customer information by genre of the work. FIG. 6 shows the browsing history unit 3423 in detail. FIG. 6 is a memory map showing the memory configuration of the browsing history unit 3423. Note that FIG. 6 shows the information of the browsing history unit 3423 related to one customer, and the browsing history unit 3423 actually stores information for the number of customer IDs.

[0040] As shown in FIG. 6, the browsing history section 3423 has a browsing classification section 34231, a browsing genre section 34232, and a browsed work section 34233. The browsing classification section 34231 stores the classification of the works browsed by the customer in the past. In the embodiment, for example, they are classified into movies, music, books, and paintings. The browsing genre section 34232 stores the genre of the works belonging to each classification. In the embodiment, the works of movies browsed by the customer in the past are classified into the genres of SF (science fiction) and fantasy. Similarly, the genres of music appreciated by the customer in the past are classified into classical and pop. Books and paintings are also classified by genre in the same way. The browsed work section 34233 stores information (work name, work identification information for identifying the work, date of browsing, etc.) of the works browsed by the customer belonging to the genre, in association with the genre stored in the browsing genre section 34232. That is, the browsing history section 3423 stores the information of the works browsed by the customer in a classified manner by classification and genre.

[0041] In addition to the information of the works browsed by the customer in the past, the browsing history section 3423 stores information of the works browsed in the past related to other facilities such as bookstores, libraries, movie theaters, museums, and art galleries. The information of the works related to other facilities can be input by the customer from the mobile terminal 1. Also, by assigning a common customer ID among the facilities or by associating the customer IDs at each facility with each other, the information of the works browsed at each facility can be collected based on the customer ID.

[0042] The hobby information section 3424 stores information related to the hobbies, preferences, and interests of the customer as customer information for each customer ID, in association with the customer ID stored in the customer ID section 3421. FIG. 7 shows the hobby information section 3424 in detail. Note that FIG. 7 shows the information of the hobby information section 3424 related to one customer, and the hobby information section 3424 actually stores information for each customer ID.

[0043] FIG. 7 is a memory map showing the memory configuration of the preference information section 3424. As shown in FIG. 7, the preference information section 3424 includes a preference classification section 34241, a preference genre section 34242, and a preference work section 34243. The preference classification section 34241 stores the classification of the works preferred by the customer. In the embodiment, for example, it is classified into movies, music, books, and paintings. The preference genre section 34242 stores the genre of the works belonging to each classification. In the embodiment, the works of movies preferred by the customer are classified into the genres of science fiction and suspense. Similarly, the genres of music preferred by the customer are classified into classical and jazz. Books and paintings are also classified by genre in the same way. The preference work section 34243 stores information of the works belonging to the genre (work name, work identification information for identifying the work, etc.) in association with the genre stored in the preference genre section 34242. That is, the preference information section 3424 stores the information of the works preferred by the customer by classifying them by classification and genre. The preference genre section 34242 may store information on the genres of other works that appear in the works stored in the browsing work section 34233.

[0044] In addition to the information of the works in the rental shop preferred by the customer, the preference information section 3424 stores information of the works preferred by the customer in other facilities such as bookstores, libraries, movie theaters, museums, and art galleries. The preference information section 3424 may store information on other works that appear in the works stored in the browsing work section 34233. Information on the works viewed in other facilities can be input by the customer from the mobile terminal 1. Also, by assigning a common customer ID among the facilities or by correlating the customer IDs in each facility with each other, information on the works viewed in each facility may be collected based on the customer ID.

[0045] Note that the customer information stored in the attribute information section 3422, the browsing history section 3423, and the preference information section 3424 can be input from the mobile terminal 1 when the customer registers as a member, and can also be added and input in a timely manner after the membership registration. Also, in the browsing history section 3423, the work information of the works viewed by the customer is added and stored each time.

[0046] Next, the hardware configuration of the prompt generation device 5 will be described. FIG. 8 is a block diagram showing the hardware configuration of the prompt generation device 5. As shown in FIG. 8, the prompt generation device 5 includes a CPU 51 which is an example of a processor, a ROM 52, a RAM 53, a memory unit 54, and the like. The CPU 51 serves as the control main body. The ROM 52 stores various programs. The RAM 53 expands programs and various data. The memory unit 54 stores various programs. The CPU 51, ROM 52, RAM 53, and memory unit 54 are connected to each other via a bus 55. The CPU 51, ROM 52, and RAM 53 constitute a control unit 500. That is, the control unit 500 executes control processing related to the prompt generation device 5 described later by operating according to a control program stored in the ROM 52 or the memory unit 54 and expanded in the RAM 53.

[0047] The RAM 53 has a browsing request unit 531, a customer information unit 532, a prompt information unit 533, and a work introduction information unit 534. The browsing request unit 531 stores browsing request information of a work that the customer wishes to browse received from the mobile terminal 1. The browsing request unit 531 stores browsing request information including work identification information for identifying a work such as "Please tell me information about Work XX", information for requesting browsing, and a customer ID for identifying the customer.

[0048] The customer information unit 532 stores customer information of the relevant customer received from the customer server 3 based on the customer ID included in the browsing request information. The customer information unit 532 will be described later with reference to FIG. 9. The prompt information unit 533 stores prompt information customized for the relevant customer by reflecting the customer information stored in the customer information unit 532 on the prompt information related to the work called from the fixed sentence information unit 542 described later based on the received browsing request information. The work introduction information unit 534 receives and stores work introduction information generated by the processing server 7 based on the customized prompt information.

[0049] The memory unit 54 is composed of a non-volatile memory such as an HDD or a flash memory that retains stored information even when the power is turned off. The memory unit 54 includes a control program unit 541 and a fixed-form sentence information unit 542. The control program unit 541 stores a control program for controlling the prompt generation device 5. The fixed-form sentence information unit 542 stores, for each work, the prompt information to be transmitted to the processing server 7. The prompt information stored in the fixed-form sentence information unit 542 is a fixed-form sentence that requests the generation of the work introduction information prepared in common for each work before the customer information is reflected. Note that the prompt information stored in the fixed-form sentence information unit 542 may be the prompt information common to all works, or may be the prompt information prepared for each genre of the works. The fixed-form sentence information unit 542 will be described later with reference to FIG. 10.

[0050] Also, the control unit 500 is connected to the operation unit 57 and the display unit 58 via the bus 55 and the controller 56. The operation unit 57 is a keyboard. The display unit 58 displays information to the operator who operates the prompt generation device 5.

[0051] Also, the control unit 500 is connected to the communication unit 59 and the communication unit 60 via the bus 55. The communication unit 59 is communicably connected to the mobile terminal 1 and the processing server 7 via the network N, and can transmit and receive information. The communication unit 60 is connected to the customer server 3 via a communication line and can transmit and receive information.

[0052] Next, the customer information department 532 will be described. The customer information department 532 receives and stores the customer information of the customer specified by the customer ID queried to the customer server 3 from the customer server 3. FIG. 9 is a memory map showing the memory configuration of the customer information department 532. In the example of FIG. 9, an example is shown in which the customer information of the customer with the customer ID "001" among the customer information of a plurality of customers stored in the customer information department 342 is read out and stored in the customer information department 532. As shown in FIG. 9, the customer information department 532 has a customer ID department 5321, an attribute information department 5322, a browsing history department 5323, and a preference information department 5324. The customer ID department 5321 stores the customer ID included in the browsing request information. The attribute information department 5322 stores, as customer information, the attribute information (gender, age, age group, address, phone number, address of mobile terminal 1, etc.) of the customer read from the attribute information department 3422 corresponding to the customer ID stored in the customer ID department 5321.

[0053] The browsing history department 5323 stores, as customer information by genre of the work, the information of the works (work name, work identification information for identifying the work, date of browsing, etc.) browsed by the customer in the past, read from the browsing history department 3423 corresponding to the customer ID stored in the customer ID department 5321. Note that the browsing history department 5323 has the same configuration as the browsing history department 3423 related to one customer, specifically shown in FIG. 6. The browsing history department 5323 shown in FIG. 9 stores the information of the works browsed by the customer with the customer ID "001" in the past.

[0054] The preference information department 5324 stores, as customer information, the information related to the hobbies, preferences, and interests of the customer read from the preference information department 3424 corresponding to the customer ID stored in the customer ID department 5321. The preference information department 5324 has the same configuration as the preference information department 3424 related to one customer, specifically shown in FIG. 7.

[0055] Next, the fixed-form sentence information section 542 will be described. FIG. 10 is a memory map showing the memory configuration of the fixed-form sentence information section 542. The fixed-form sentence information section 542 is a template that stores, for each work, the fixed-form sentences of the prompt information to be transmitted to the processing server 7. As shown in FIG. 10, the fixed-form sentence information section 542 has a work ID section 5421 and a fixed-form sentence section 5422. The work ID section 5421 stores, for each work, the work ID which is work identification information for identifying the work. The fixed-form sentence section 5422 stores the fixed-form sentences of the prompt information related to the work in association with the work ID stored in the work ID section 5421. For example, for work A specified by the work ID "AAA", fixed-form sentences such as "Please recommend work A to those with the following characteristics as much as possible so that relevance can be found. People in their ○○s, who like works such as ○○ and ○○ or works of the ○○ genre. Also like music such as ○○." are stored. By inserting parameters composed of various words and the like extracted from the customer information into ○○, prompt information in which the customer information is reflected in the fixed-form sentence is generated.

[0056] Next, the hardware configuration of the processing server 7 will be described. FIG. 11 is a block diagram showing the hardware configuration of the processing server 7. As shown in FIG. 11, the processing server 7 includes a CPU 71 which is an example of a processor, a ROM 72, a RAM 73, a memory section 74, and the like. The CPU 71 serves as the control entity. The ROM 72 stores various programs. The RAM 73 expands programs and various data. The memory section 74 stores various programs. The CPU 71, the ROM 72, the RAM 73, and the memory section 74 are connected to each other via a bus 75. The CPU 71, the ROM 72, and the RAM 73 constitute a control section 700. That is, the control section 700 executes the control processing related to the processing server 7 described later by operating according to the control program stored in the ROM 72 and the memory section 74 and expanded in the RAM 73 by the CPU 71.

[0057] The RAM 73 has a prompt information section 731 and a work introduction information section 732. The prompt information section 731 stores the prompt information customized for a specific customer received from the prompt generation device 5. The work introduction information section 732 stores the work introduction information suitable for the customer, which is generated based on the received prompt information.

[0058] The memory section 74 is composed of non-volatile memories such as an HDD or a flash memory that retains stored information even when the power is turned off. The memory section 74 has a control program section 741, a large language model 742, a work information section 743, an SNS storage section 744, and a review storage section 745. The control program section 741 stores a control program for controlling the processing server 7. The large language model 742 is a program that generates work introduction information of a work reflecting the customer information included in the prompt information based on the received prompt information. The work information section 743 stores the work information collected from the work DB 9 for each work. The SNS storage section 744 stores the SNS information collected from the SNS information section Da. The review storage section 745 stores the work evaluation information collected from the review information section Db.

[0059] Also, the control unit 700 is connected to the operation unit 77 and the display unit 78 via the bus 75 and the controller 76. The operation unit 77 is a keyboard. The display unit 78 displays information to the operator who operates the processing server 7.

[0060] Also, the control unit 700 is connected to the communication unit 79 via the bus 75. The communication unit 79 is communicably connected to the prompt generation device 5 via the network N and can transmit and receive information.

[0061] From here, the control of the mobile terminal 1 will be described. FIG. 12 is a flowchart showing the flow of the control process of the mobile terminal 1. As shown in FIG. 12, the control unit 100 of the mobile terminal 1 determines whether the mobile terminal 1 has logged in (S11). It waits until it logs in (No in S11), and when it determines that it has logged in (Yes in S11), the control unit 100 performs a login process on the mobile terminal 1 (S12). Next, the control unit 100 determines whether an enrollment registration operation has been performed on the mobile terminal 1 (S13). When it determines that an enrollment registration operation has been performed on the mobile terminal 1 (Yes in S13), a registration process that enables the transmission and reception of information with the prompt generation device 5 is executed by the application software installed on the mobile terminal 1 (S14). Then the control unit 100 returns to S13.

[0062] Also, when it determines that it is not an enrollment registration process (No in S13), the control unit 100 determines whether the customer has instructed a work viewing request by operating the mobile terminal 1 (S15). For example, when the customer inputs work information (such as the name or work ID of the work) and operates a viewing request key (not shown), the control unit 100 determines that a work viewing request has been instructed. When the viewing request key has not been operated, the control unit 100 determines that no work viewing request has been instructed. When it determines that a viewing request has been instructed (Yes in S15), the control unit 100 creates viewing request information for requesting viewing from the prompt generation device 5 (the viewing request information includes the customer ID of the customer requesting viewing and the work identification information for identifying the work (which may be the work ID for identifying the work or the work name)), and stores it in the viewing request information unit 131 (S16). Then the control unit 100 transmits the stored viewing request information to the prompt generation device 5 (S17). Then the control unit 100 returns to S13.

[0063] Also, when it is determined that the instruction is not a viewing request (No in S15), the control unit 100 determines whether it has received work introduction information as a response to the viewing request information transmitted in S17 from the prompt generation device 5 (S18). When it is determined that the work introduction information has been received (Yes in S18), the control unit 100 stores the received work introduction information in the work information unit 132 (S19), and displays the stored work introduction information on the display unit 18 (S19). Then, the control unit 100 returns to S13.

[0064] Also, when it is determined that the work introduction information has not been received (No in S18), the control unit 100 determines whether the mobile terminal 1 has been logged off (S20). When it is determined that the mobile terminal 1 has not been logged off (No in S20), the control unit 100 returns to S13, and when it is determined that the mobile terminal 1 has been logged off (Yes in S20), the control unit 100 ends the process and returns to S11.

[0065] The mobile terminal 1 according to such an embodiment can request viewing of a work, and receives and displays on the display unit 18 the work introduction information customized for the customer, which is generated by reflecting the customer information of the customer who has requested viewing. Therefore, the customer can be more attracted to the work by viewing the work introduction information displayed on the display unit 18.

[0066] Hereinafter, the functional configuration of the prompt generation device 5 will be described. FIG. 13 is a functional block diagram showing the functional configuration of the prompt generation device 5. The control unit 500 of the prompt generation device 5 functions as a reception unit 501, a customer information acquisition unit 502, a customization unit 503, a provision unit 504, a work introduction information acquisition unit 505, and an output unit 506 by following the control program stored in the control program unit 541 of the ROM 52 and the memory unit 54.

[0067] The reception unit 501 receives viewing request information including a customer ID for identifying a customer and work identification information for identifying a work to be viewed.

[0068] The customer information acquisition means 502 acquires customer information related to the received customer ID based on the received customer ID. Specifically, the customer information acquisition means 502 receives, from the customer server 3 based on the customer ID included in the browsing request received from the mobile terminal 1, the customer information stored in the customer information section 342 in association with the customer ID, and stores it in the customer information section 532. The customer information to be acquired is the attribute information of the customer specified by the customer ID (information stored in the attribute information section 3422), the browsing history information (information stored in the browsing history section 3423), and the preference information (information stored in the preference information section 3424). The customer information acquired by the customer information acquisition means 502 includes customer information related to the work the customer wishes to view and information (various information) on works other than the work the customer wishes to view (such as movies, music, paintings, books), that is, works of multiple types. For example, the browsing history information acquired by the customer information acquisition means 502 includes information on the works the customer has viewed in the past and information on works other than the works the customer has viewed in the past (for example, information on other works or works of other genres that appear in the works the customer has viewed in the past (if the work is a movie, different types of works other than movies (music, paintings, books, etc.))). Also, the preference information acquired by the customer information acquisition means 502 includes information on the works the customer likes and information on multiple works other than the work (for example, other works or works of other genres that appear in the work (if the work is a movie, different types of works other than movies (music, paintings, books, etc.))).

[0069] The customization means 503 customizes the prompt information for requesting the generation of work introduction information related to the work into prompt information suitable for the customer based on the received browsing request information and the acquired customer information. Specifically, the customization means 503 inserts, into the blank fields of the prompt information (template text) of the work to be browsed extracted from the template text section 542 based on the received browsing request information, the customer information (the past work browsing history information of the customer, the information on the works the customer likes, and the information on other works related to these works) acquired by the customer information acquisition means 502, thereby customizing it into prompt information suitable for the customer.

[0070] For example, the customization means 503 calls, from the fixed-form sentence information section 542, the prompt information (fixed-form sentence) related to the work A that the user wishes to view, which is "Please recommend the work A to the following characteristics so that as much relevance as possible can be found. Male in his 30s, likes works such as XX and XX and XX genre. Also likes music called XX." Then, the customization means 503 inserts the parameters extracted based on the customer information acquired by the customer information acquisition means 502 into ○○ (the blank part where there is no information).

[0071] For example, as the customer information of the customer with customer ID "001", the information "male in his 30s" is stored in the attribute information section 5322, the information "work B" is stored in the browsing history section 5323, and the information "SF" and "classical" are stored in the preference information section 5324. In this case, the control unit 500 of the prompt generation device 5 extracts "in his 30s", "male", "work B", "SF", "classical", etc. as parameters and inserts them into the ○○ part of the above fixed-form sentence. For example, "Please recommend the work A to the following characteristics so that as much relevance as possible can be found. Male in his 30s, likes works such as work B and SF genre. Also likes classical music." Thus, the prompt information that reflects the customer information in the fixed-form sentence is customized.

[0072] The providing means 504 provides the prompt information customized by the customization means 503 to the large language model 742. Specifically, the providing means 504 transmits the prompt information customized by the customization means 503 to the processing server 7 equipped with the large language model 742.

[0073] The work introduction information acquisition means 505 acquires the work introduction information generated by the large language model 742 based on the prompt information provided to the large language model 742. Specifically, the work introduction information acquisition means 505 receives, from the processing server 7, the work introduction information suitable for the customer, which is generated by the large language model 742 based on the prompt information customized for the customer and transmitted to the processing server 7.

[0074] The output means 506 outputs the acquired work introduction information. Specifically, the output means 506 transmits the work introduction information received from the processing server 7 to the mobile terminal 1.

[0075] Next, the control of the prompt generation device 5 will be described. FIG. 14 is a flowchart showing the flow of the control process of the prompt generation device 5. The control unit 500 of the prompt generation device 5 determines whether it has received browsing request information from the mobile terminal 1 (S31). If it is determined that the browsing request information has been received (Yes in S31), the reception means 501 stores the received browsing request information in the browsing request unit 531 (S32). Then, the control unit 500 makes an inquiry about the customer information of the customer to the customer server 3 based on the customer ID included in the stored browsing request information (S32). Then, the control unit 500 returns to S31.

[0076] If it is determined that the browsing request information has not been received from the mobile terminal 1 (No in S31), the control unit 500 determines whether it has received customer information from the customer server 3 as a response to the inquiry in S32 (S41). If it is determined that the customer information has been received (Yes in S41), the customer information acquisition means 502 stores the received customer information in the customer information unit 532 (S42). Next, the control unit 500 searches the fixed-form text information unit 542 based on the information of the work (work name or work ID for specifying the work) included in the stored browsing request information, and reads out the prompt information (fixed-form text) related to the work (S43).

[0077] Next, the customization means 503 reflects the customer information stored in S42 in the read prompt information (fixed-form text), and customizes it into prompt information suitable for the customer with the received customer ID (S44). Then, the control unit 500 stores the customized prompt information in the prompt information unit 533 (S45). Then, the providing means 504 transmits the prompt information stored in the prompt information unit 533 to the processing server 7 (S46). Then, the control unit 500 returns to S31.

[0078] Also, when it is determined that customer information is not received (No in S41), the control unit 500 determines whether it has received the product introduction information in response to the transmission in S46 from the processing server 7 (S51). When it is determined that the product introduction information has not been received (No in S51), the control unit 500 returns to S31. When it is determined that the product introduction information has been received (Yes in S51), the product introduction information acquisition means 505 stores the received product introduction information in the product introduction information section 534 (S52). Then, the output means 506 transmits the product introduction information stored in the product introduction information section 534 to the mobile terminal 1 that has transmitted the browsing request information (S53). Then, the control unit 500 transmits the information of the product (product name or product ID) included in the product introduction information stored in the product introduction information section 534 to the customer server 3 together with the customer ID included in the browsing request information (S54). The control unit 300 of the customer server 3 additionally stores the received product information in the browsing history section 3423 associated with the customer ID. In this way, the browsing history of the product is accumulated as customer information. Then, the control unit 500 ends the process.

[0079] From here, the control of the processing server 7 will be described. FIG. 15 is a flowchart showing the flow of the control process of the processing server 7. As shown in FIG. 15, the control unit 700 of the processing server 7 determines whether it has received product information from the product DB 9, or SNS information from the SNS information section Da, or product evaluation information from the review information section Db (S61). When it is determined that product information has been received (Yes in S61), the control unit 700 stores the received product information in the product information section 743 (S62). When it is determined that SNS information has been received (Yes in S61), the control unit 700 stores the received SNS information in the SNS storage section 744 (S62). When it is determined that product evaluation information has been received (Yes in S61), the control unit 700 stores the received product evaluation information in the review storage section 745 (S62). Then, the control unit 700 returns to S61.

[0080] Also, when it is determined that the work information, SNS information, and work evaluation information have not been received (No in S61), the control unit 700 determines whether it is a predetermined timing (S63). The predetermined timing is the timing for training the large language model 742. When it is determined that it is the predetermined timing (Yes in S63), the control unit 700 trains the large language model 742 based on the work information stored in the work information unit 743, the SNS information stored in the SNS storage unit 744, and the work evaluation information stored in the review storage unit 745 (S64). Then, the control unit 700 returns to S61.

[0081] Also, when it is determined that it is not the predetermined timing (No in S63), the control unit 700 determines whether it has received prompt information from the prompt generation device 5 (S71). When it is determined that the prompt information has not been received (No in S71), the control unit 700 returns to S61. When it is determined that the prompt information has been received (Yes in S71), the control unit 700 stores the received prompt information in the prompt information unit 731 (S72). Then, the control unit 700 generates work introduction information related to the prompt information stored in the prompt information unit 731 using the large language model 742 (S73).

[0082] Here, an example of the work introduction information generated by the control unit 700 using the large language model 742 will be described. The work introduction information generated using the large language model 742 varies depending on the content of the received prompt information. For example, when the prompt information simply requests an introduction of Work A and no customer information is reflected, the control unit 700 generates work introduction information indicating the content and features of Work A, such as "Work A is a fairy tale novel written by Italian author A in 1883. The story depicts the adventure of a wooden puppet boy to become human. At first, the boy couldn't speak, but he had the characteristic that his nose grew every time he told a lie. The story follows the process of the boy learning the importance of honesty, courage, and friendship while facing various difficulties. This Work A not only conveys the lesson that children must be honest, but also includes elements of adventure and fantasy. This Work A is well-known and loved around the world."

[0083] Also, when the received prompt information reflects customer information (parameters such as "in their 30s", "male", "Work B", "SF", "classical", etc.), the control unit 700 generates attractive work introduction information that can draw the interest of the customer by reflecting the customer information of the customer who views it, in addition to the content and features of Work A, such as "Work A is a special movie among anime movies and can be enjoyed regardless of age or gender. Work A is a wonderful story in which a puppet born from a tree transforms into a real boy by the power of magic. Although this movie is a bit different from SF, since it depicts an adventure in a fantasy world, those who like SF may also enjoy the imaginary world. Also, it includes classical music that enhances the atmosphere of the whole movie. The music that colors the story is part of the charm of the whole movie, and the element of classical music is particularly memorable. Furthermore, in the story, Work A and his friends have adventures, love, and friendship with various animals, and it will surely provide an enjoyable time for those who like animals. This Work A is one of the masterpieces that have been enjoyed by audiences of a wide range of ages, from children to adults. If you are interested in fantasy, adventure, music, and animals, please do watch Work A."

[0084] Also, when the large language model 742 is learning based on the work information stored in the work information unit 743, the SNS information stored in the SNS storage unit 744, or the work evaluation information stored in the review storage unit 745 (for example, when learning information such as "recommended for families with men in their 30s" and "found something different from childhood for men in their 30s" extracted from SNS information based on the parameters of "30s" and "male" included in customer information), the control unit 700 generates attractive work introduction information that reflects the customer information and the learning results of the large language model 742 and is more appealing to the customer, such as "Work A is a special one among anime movies and is recommended for enjoying with family and friends. Work A is a wonderful story where a puppet born from a tree transforms into a real boy with magical powers. Although this movie is slightly different from science fiction, it depicts adventures in a fantasy world, so even fans of science fiction may enjoy the imaginative world. It also includes classic music that enhances the overall atmosphere of the movie. The music that colors the story is part of the charm of the whole movie, and the elements of classic music are particularly memorable. Furthermore, in the story, Pinocchio and his friends have adventures, love, and friendship with various animals, which will surely provide an enjoyable time for those who like animals. Also, although this work is based on a fairy tale, it can be enjoyed from a different perspective than when seen as a child, and there are new discoveries waiting. Please enjoy Work A."

[0085] Next, the control unit 700 stores the generated work introduction information in the work introduction information unit 732 (S74). Then, the control unit 700 transmits the work introduction information stored in the work introduction information unit 732 to the prompt generation device 5 (S75). Then, the control unit 700 returns to S61.

[0086] As described above, the prompt generation device 5 of the embodiment includes a reception unit 501 that receives browsing request information including a customer ID for identifying a customer and work identification information for identifying a work to be browsed, a customer information acquisition unit 502 that acquires customer information related to the customer ID based on the received customer ID, a customization unit 503 that customizes prompt information for requesting generation of work introduction information related to the work into prompt information suitable for the customer based on the received browsing request information and the acquired customer information, and a provision unit 504 that provides the customized prompt information to the large language model.

[0087] According to the prompt generation device 5 of such an embodiment, since the customization unit 503 customizes the prompt information based on the browsing request information received by the reception unit 501 and the customer information acquired by the customer information acquisition unit 502, and the provision unit 504 provides the customized prompt information to the processing device 7, it is possible to obtain work introduction information that sufficiently reflects the individual preferences and interests of the customer for the work introduction request.

[0088] The embodiments of the present invention have been described above. However, these embodiments are presented as examples and are not intended to limit the scope of the invention. This novel embodiment can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. This embodiment is included in the scope and gist of the invention, and is also included in the invention described in the claims and its equivalent scope.

[0089] For example, in the embodiment, a rental shop that rents out media is taken as an example, and the prompt generation device 5 installed in the rental shop is described as an example of a work introduction information generation support device. However, it is not limited to this. For example, instead of a rental shop, it may be a media sales store, a bookstore, a painting store, a library, a movie theater, a museum, an art museum, etc., and the work introduction information generation support device may be a device installed in these facilities.

[0090] In the embodiment, the prompt generation device 5 has been described as an example of the work introduction information generation support device. However, the present invention is not limited to this. For example, by installing an application on the mobile terminal 1, the configuration described in claims 1 to 7 may be provided. In this case, the mobile terminal 1 is the work introduction information generation support device. In this case, the output means 506 outputs (displays) the work introduction information received from the processing server 7 to the display unit 18.

[0091] In the embodiment, the mobile terminal 1 has been described as an example of the interface. However, the present invention is not limited to this. The interface may be a dedicated terminal installed inside, for example, a rental bookstore, a media sales store, a bookstore, a library, a movie theater, a museum, an art museum, etc., capable of creating and transmitting browsing request information and browsing work introduction information.

[0092] In the embodiment, three types of information, namely work information, SNS information, and work introduction information, have been collected to train the large language model 742. However, it may be any one or two or more types of information. Alternatively, the large language model 742 may be trained based on other information.

[0093] In the embodiment, the work information collection unit Dc has been described as an external device of the prompt generation device 5. However, the work information collection unit Dc may be a function inside the prompt generation device 5.

[0094] The program executed by the prompt generation device 5 in the embodiment is provided by being recorded on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), etc. in an installable format or an executable format file.

[0095] Alternatively, the program executed by the prompt generation device 5 of the embodiment may be stored on a computer connected to a network such as the Internet and provided by allowing it to be downloaded via the network. Further, the program executed by the prompt generation device 5 of the embodiment may be configured to be provided or distributed via a network such as the Internet.

[0096] Also, the program executed by the prompt generation device 5 of the embodiment may be configured to be provided by being pre - incorporated into a ROM or the like.

Explanation of Reference Numerals

[0097] 1 Mobile terminal 3 Customer server 5 Prompt generation device 7 Processing server 10 System 17 Operation unit 18 Display unit 100 Control unit 131 Browsing request information unit 132 Work information unit 300 Control unit 342 Customer information unit 500 Control unit 501 Reception means 502 Customer information acquisition means 503 Customization means 504 Provision means 505 Work introduction information acquisition means 506 Output means 531 Browsing request section 532 Customer information section 533 Prompt information section 534 Work introduction information section 542 Fixed - phrase information section 700 Control unit 731 Prompt information section 732 Work introduction information section 742 Large - language model 743 Work information section 744 SNS storage section 745 Review Memory Section 3421 Customer ID Section 3422 Attribute Information Section 3423 Browsing History Section 3424 Preference Information Section 5321 Customer ID Section 5322 Attribute Information Section 5323 Browsing History Section 5324 Preference Information Section 5421 Work ID Section 5422 Standard Text Section 34231 Browsing Classification Section 34232 Browsing Genre Section 34233 Browsing Work Section 34241 Preference Classification Section 34242 Preference Genre Section 34243 Preference Work Section Dc Work Information Collection Section

Prior Art Documents

Patent Documents

[0098]

Patent Document 1

Claims

1. Receiving means for receiving browsing request information including customer identification information for identifying a customer and work identification information for identifying a work to be browsed; Customer information acquisition means for acquiring customer information related to the customer identification information based on the received customer identification information; Customization means for customizing prompt information for requesting generation of work introduction information related to the work into prompt information suitable for the customer based on the received browsing request information and the acquired customer information; Providing means for providing the customized prompt information to a large language model; A work introduction information generation support device comprising the above.

2. The customer information includes browsing history information related to a plurality of types of works that the customer has browsed in the past, The customization means customizes the prompt information using the browsing history information, The work introduction information generation support device according to claim 1.

3. The customer information includes information related to a plurality of types of works that the customer prefers, The customization means customizes the prompt information using the plurality of types of works that the customer prefers, The work introduction information generation support device according to claim 2.

4. The customer information includes information on other works that appear in a plurality of types of works that the customer has browsed in the past, The customization means customizes the prompt information using the information on the other works, The work introduction information generation support device according to claim 3.

5. Work introduction information acquisition means for acquiring the work introduction information generated by the large language model based on the prompt information provided to the large language model; Output means for outputting the acquired work introduction information; The work introduction information generation support device according to any one of claims 1 to 4, further comprising the above.

6. The receiving means receives the browsing request information from a mobile terminal carried by the customer, The output means transmits the work introduction information to the mobile terminal, The work introduction information generation support device according to claim 5.

7. A computer as a work introduction information generation support device, Receiving means for receiving browsing request information including customer identification information for identifying a customer and work identification information for identifying a work to be browsed; Customer information acquisition means for acquiring customer information related to the customer identification information based on the received customer identification information; Customizing means for customizing the prompt information for requesting generation of work introduction information related to the work into prompt information suitable for the customer based on the received browsing request information and the obtained customer information; Providing means for providing the customized prompt information to a large language model; A program that can be caused to function.

Images