Information processing device and information processing program

Abstract

To provide an information processing device and an information processing program which can provide information in which readability is improved for a user.SOLUTION: An information processing device comprises: a reception unit which receives a question sentence inputted by a user using a store; an answer sentence acquisition unit which, by inputting the question sentence received by the reception unit to a large-scale language model functionalized so as to output an answer sentence with respect to the question sentence, acquires an answer sentence outputted by the large-scale language model; a related information acquisition unit which acquires related information related to a commodity indicated in the answer sentence; an address information generation unit which generates address information referable to the related information; an answer information generation unit which generates answer information including the answer sentence and the address information; and a provision unit which provides the user with the answer information.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] An embodiment of the present invention relates to an information processing device and an information processing program. [Background technology]

[0002] In recent years, technologies have been proposed for automatically creating sentences using AI models (also called generative AI) such as large-scale language models (LLMs). Large-scale language models are AI models in the field of natural language processing that have been pre-trained with large-scale corpora, and are designed to generate and output answer sentences related to the question in the specified format when, for example, text describing a question is input along with instruction information (also called a prompt) that specifies the output format.

[0003] Incidentally, one possible service using the above AI model is to add information (hereinafter also referred to as related information) related to the matters included in the answer text output by the AI ​​model and provide it to the user. For example, when an answer text about a product is output, related information such as the price and image of the product can be added to the answer text and provided.

[0004] However, if related information is added carelessly, the answer that the user actually wants to see may not stand out. Therefore, when adding related information, it is necessary to consider the readability of the user. Summary of the Invention [Problem to be solved by the invention]

[0005] An object of the present invention is to provide an information processing device and an information processing program that can provide a user with information that is easier to read. [Means for solving the problem]

[0006] The information processing device of the embodiment includes a receiving unit that receives a question text input by a user using a store, an answer text acquisition unit that inputs the question text received by the receiving unit into a large-scale language model that is functionally configured to output an answer text to the question text and acquires the answer text output by the large-scale language model, a related information acquisition unit that acquires related information about a product indicated in the answer text, an address information generation unit that generates address information that can reference the related information, an answer information generation unit that generates answer information that includes the answer text and the address information, and a providing unit that provides the answer information to a user. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a schematic diagram showing a schematic configuration of an information processing system according to this embodiment. [Figure 2] FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device according to this embodiment. [Figure 3] FIG. 3 is a block diagram showing an example of the functional configuration of the information processing device according to this embodiment. [Figure 4] FIG. 4 is a schematic diagram showing an example of reference information according to this embodiment. [Figure 5] FIG. 5 is a schematic diagram showing an example of the first response information according to the present embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of control processing of the information processing device according to this embodiment. [Figure 7] FIG. 7 is a block diagram showing an example of a functional configuration of an information processing device according to the first modification. [Figure 8] FIG. 8 is a schematic diagram showing an example of second response information according to the first modified example. [Figure 9] FIG. 9 is a flowchart showing an example of a control process of the information processing device according to the first modification. [Figure 10] FIG. 10 is a schematic diagram showing an example of reference information according to the second modified example. [Figure 11] FIG. 11 is a schematic diagram showing an example of first response information according to the second modified example. [Figure 12] FIG. 12 is a block diagram showing an example of a functional configuration of an information processing device according to the third modified example. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of an information processing system will be described with reference to the drawings. Furthermore, the present invention is not limited to the following embodiments, and the components in the following embodiments include those that would be easily conceived by a person skilled in the art, those that are substantially the same, and those that are within the scope of what is called equivalents. Furthermore, various omissions, substitutions, modifications, and combinations of the components can be made without departing from the spirit of the following embodiments.

[0009] 1 is a schematic diagram showing a general configuration of an information processing system 10 according to an embodiment. The information processing system 10 is a system including an input / output device 1 and an information processing device 2.

[0010] The input / output device 1 is, for example, a portable terminal device (hereinafter also referred to as a mobile terminal) such as a smartphone. The input / output device 1 is, for example, a mobile terminal owned by a user. The input / output device 1 may be a tablet-type terminal device. Furthermore, the input / output device 1 may be a mobile terminal rented to a user by a store.

[0011] The input / output device 1, for example, acquires text data of a question sentence input by a user, and outputs the acquired text data to the information processing device 2. The input / output device 1 also acquires, for example, answer information corresponding to the question sentence output from the information processing device 2, and provides the acquired answer information to the user. Details of the answer information will be described later.

[0012] The information processing device 2 is, for example, a store server or a server device managed by a company that operates a restaurant. In this embodiment, the information processing device 2 is, for example, a computer equipped with a generation AI that automatically generates text such as a large-scale language model (LLM). The large-scale language model generates product promotional text and input text for generating promotional text to be provided to customers who use the store.

[0013] The information processing device 2 is composed of one or more computers. The information processing device 2 supports sales promotion of products sold in stores based on questions acquired via the input / output device 1. The information processing device 2 is connected to the input / output device 1 via a communication line such as a mobile network.

[0014] Next, the hardware configuration of the information processing device 2 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the hardware configuration of the information processing device 2 according to an embodiment. As shown in Fig. 2, the information processing device 2 includes a CPU (Central Processing Unit) 21, a RAM (Random Access Memory) 22, a ROM (Read Only Memory) 23, an auxiliary storage device 24, and a communication I / F (interface) 25.

[0015] The CPU 21 is the main controller. The RAM 22 expands programs and various data. The ROM 23 stores various programs. The auxiliary storage device 24 stores various programs and data. The communication I / F 25 is an interface for data communication with the input / output device 1.

[0016] The CPU 21, RAM 22, ROM 23, auxiliary storage device 24, and communication I / F 25 are connected to one another via a bus 26. The CPU 21, RAM 22, and ROM 23 constitute a control unit. That is, the control unit executes control processing of the information processing device 2, which will be described later, by the CPU 21 operating in accordance with a control program stored in the ROM 23 or auxiliary storage device 24 and loaded in the RAM 22.

[0017] The auxiliary storage device 24 is configured with a non-volatile memory such as an HDD (Hard Disc Drive) or flash memory that retains stored information even when the power is turned off. The auxiliary storage device 24 stores the answer sentences and promotional information acquired by the information processing device 2, as well as the reference information, address information, and answer information generated by the information processing device 2. Details of the answer sentences, promotional information, reference information, address information, and answer information will be described later.

[0018] The information processing device 2 is installed in a secure environment. A secure environment is a configuration in which the information processing device 2 is placed in a local environment for use. With this configuration, since the text information input for processing a large-scale language model provided in the information processing device 2, which will be described later, may include customer information of customers, etc., the information processing device 2 can contribute to the protection of personal information by being placed in a local environment for use.

[0019] Fig. 3 is a block diagram showing an example of a functional configuration of the information processing device 2 according to the embodiment. As shown in Fig. 3, the information processing device 2 includes a receiving unit 211, a response sentence acquiring unit 212, a related information acquiring unit 213, a reference information generating unit 214, an address information generating unit 215, a response information generating unit 216, and a providing unit 217. Note that the functional configuration of the information processing device 2 is not limited to this.

[0020] The receiving unit 211 receives a question. Specifically, the receiving unit 211 receives a question output by the input / output device 1 and input by a user who uses a store that sells products. For example, the question is data including the content of the question. The question may also include personal information such as the name, phone number, and email address of the user who asked the question. The content of the question may be, for example, content related to products sold in the store, such as "What products do you recommend?" Furthermore, the receiving unit 211 stores the received question in the auxiliary storage device 24.

[0021] The answer sentence acquisition unit 212 acquires an answer sentence. Specifically, the answer sentence acquisition unit 212 inputs the question sentence received by the reception unit 211 into a large-scale language model that is functionally configured to output an answer sentence to the question sentence, and acquires the answer sentence output by the large-scale language model.

[0022] For example, the answer sentence acquisition unit 212 inputs a question sentence and instruction information (also called a prompt) that instructs an answer to the question sentence into a large-scale language model using a known method, thereby causing the large-scale language model to generate an answer sentence that answers the question sentence, and acquires the answer sentence output by the large-scale language model. The answer sentence includes at least product information about a product recommended to the user and a sentence about sales promotion of the product. The product information is, for example, the product genre, the product name, etc. The question sentence may be included in the prompt.

[0023] The answer sentence acquisition unit 212 generates a prompt that instructs (describes) the user to add product information about a product recommended to the user, add a promotional statement about the product, etc., in order to answer a question from the user. The prompt may be one prepared in advance in the auxiliary storage device 24, or may be dynamically generated by the answer sentence acquisition unit 212. The prompt may also include a statement indicating an information source that stores information about candidate products. The answer sentence acquisition unit 212 stores the acquired answer sentence in the auxiliary storage device 24.

[0024] The related information acquisition unit 213 acquires related information. Specifically, the related information acquisition unit 213 acquires related information based on products sold in the store. For example, the related information acquisition unit 213 acquires promotional information related to the product indicated in the response from the auxiliary storage device 24. The related information is an example of promotional information. The promotional information includes product information related to the product being promoted, such as the genre, product code, product name, and price of the product being promoted. Note that the products being promoted can be products that are subject to discounts, products with high sales figures, products with a large inventory among the products owned by the store, products that are the subject of a campaign, etc. The related information acquisition unit 213 stores the acquired promotional information in the auxiliary storage device 24.

[0025] The reference information generating unit 214 generates reference information that has been formed into related information based on the answer sentence and the related information. Specifically, the reference information generating unit 214 generates reference information that has been formed into related information based on the answer sentence acquired by the answer sentence acquiring unit 212 and the related information acquired by the related information acquiring unit 213.

[0026] For example, the reference information generating unit 214 generates reference information that is associated with a product included in the response text and that includes sales promotion information related to the product. The reference information includes at least information about the product recommended to the user and the price of the product. Here, the reference information will be described with reference to FIG. 4. FIG. 4 is a schematic diagram showing an example of reference information according to the embodiment.

[0027] 4, it is assumed that the answer sentence acquisition unit 212 inputs the question "What product do you recommend?" into the large-scale language model, and the large-scale language model outputs the answer sentence "How about instant curry?" In this case, the related information acquisition unit 213 acquires from the auxiliary storage device 24 sales promotion information for products that are the subject of sales promotion, based on conditions such as products that are eligible for discounts and products with high sales volume, for the instant curry products sold at the store (Store A).

[0028] Then, the reference information generation unit 214 generates the reference information of FIG. 4 based on the response text and the sales promotion information. Specifically, the reference information generation unit 214 generates reference information 41 that describes sales promotion information for the top three "instant curry" products recommended at "Store A." Here, the reference information 41 indicates the ranking and price as information about the instant curry products. Furthermore, the reference information 41 adds information indicating that "Curry B," which is a product eligible for discount, is a special sale item. The reference information generation unit 214 stores the generated reference information 41 in the auxiliary storage device 24.

[0029] The number of items of the promotional products acquired by the related information acquisition unit 213 and the number of items of the products listed in the reference information by the reference information generation unit 214 are not limited to the example in Figure 4, but it is preferable to set them to a few items (for example, within 5 items) from the perspective of readability.

[0030] In the embodiment, forming the related information may be performed using any one of a plurality of template-like patterns. The related information may also be formed using a large-scale language model.

[0031] Returning to Fig. 3, address information generation unit 215 generates address information that can be referenced. Specifically, address information generation unit 215 generates address information that can be referenced from the related information acquired by related information acquisition unit 213. For example, address information generation unit 215 generates address information that indicates a uniform resource locator (URL) of a homepage (web page) that lists the related information acquired by related information acquisition unit 213. Specifically, address information generation unit 215 stores the related information in a predetermined web server and generates address information that serves as an access destination for the related information.

[0032] Furthermore, address information generation unit 215 generates address information that can refer to the reference information generated by reference information generation unit 214. For example, address information generation unit 215 generates address information that indicates the URL of a homepage (web page) that publishes the reference information generated by reference information generation unit 214. Specifically, address information generation unit 215 stores the reference information in a predetermined web server and generates address information that serves as an access destination for the reference information.

[0033] The address information generated by the address information generating unit 215 is the URL of a homepage to which the input / output device 1 can connect. The address information generating unit 215 stores the generated address information in the auxiliary storage device 24.

[0034] The answer information generation unit 216 generates first answer information. Specifically, the answer information generation unit 216 generates first answer information including the answer sentence acquired by the answer sentence acquisition unit 212 and address information generated by the address information generation unit 215. For example, the answer information generation unit 216 generates first answer information including the answer sentence acquired by the answer sentence acquisition unit 212 and address information generated by the address information generation unit 215 that can refer to related information. Furthermore, the answer information generation unit 216 generates first answer information including address information that can refer to reference information generated by the reference information generation unit 214. The answer information generation unit 216 stores the generated answer information in the auxiliary storage device 24. The first answer information is an example of answer information.

[0035] The providing unit 217 provides the answer information. Specifically, the providing unit 217 provides the first answer information generated by the answer information generating unit 216 to the user via the input / output device 1. Here, the first answer information provided by the providing unit 217 will be described with reference to Fig. 5. Fig. 5 is a schematic diagram showing an example of the first answer information according to the embodiment.

[0036] Fig. 5 shows an example of first answer information assuming the same question and answer as in Fig. 4. As shown in Fig. 5, first answer information 51 includes an answer to the above-mentioned question, "How about some instant curry?", and address information "https: / / www.xxxxxxxx.jp / ". Note that the "recommended instant curry information" may be information based on promotional information or reference information of a link destination in the address information, or may be a character string automatically generated by answer information generation unit 216 based on the answer, etc.

[0037] Here, the answer text shown in the first answer information 51 is clearly displayed without being buried in the sales promotion information (reference information). This allows the user to easily check the answer text corresponding to the question text. Furthermore, the user can check the content of the sales promotion information provided by the store by referring to the URL shown in the first answer information 51. Therefore, the information processing device 2 can provide the user with information that is easier to read regarding the answer text to the user's question text.

[0038] Next, the control process of the information processing device 2 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the control process of the information processing device 2 according to the embodiment.

[0039] The receiving unit 211 receives a question sentence input by a user who uses a store selling a product, which is output by the input / output device 1 (step S61). Subsequently, the answer sentence acquiring unit 212 inputs the question sentence received by the receiving unit 211 into a large-scale language model that is functionalized to output an answer sentence to the question sentence, and acquires the answer sentence output by the large-scale language model (step S62).

[0040] Next, the related information acquisition unit 213 acquires related information based on products sold in the store (step S63). Next, the reference information generation unit 214 generates reference information that forms related information based on the answer sentence acquired by the answer sentence acquisition unit 212 and the related information acquired by the related information acquisition unit 213 (step S64). Next, the address information generation unit 215 generates address information that can refer to the related information acquired by the related information acquisition unit 213 (step S65). In addition, the address information generation unit 215 generates address information that can refer to the reference information generated by the reference information generation unit 214.

[0041] Next, the answer information generation unit 216 generates first answer information including the answer sentence acquired by the answer sentence acquisition unit 212 and the address information generated by the address information generation unit 215 (step S66). Next, the provision unit 217 provides the first answer information generated by the answer information generation unit 216 to the user via the input / output device 1 (step S67). When this process ends, the process of the information processing device 2 ends.

[0042] This allows the user to check the answer corresponding to the question. Furthermore, the user can check more detailed information about the sales promotion information provided by the store by referring to the URL indicated in the answer information. Therefore, the information processing device 2 can provide the user with information that is easier to read about the answer to the user's question.

[0043] As described above, the information processing device 2 of this embodiment receives a question entered by a user using a store, inputs the received question into a large-scale language model that is functionally configured to output an answer to the question, acquires the answer output by the large-scale language model, acquires related information about the product indicated in the answer, generates address information that can reference the related information, generates answer information that includes the answer and the address information, and provides the answer information to the user.

[0044] As a result, the information processing device 2 can provide the user with answer information that is easier to read for the answer to the user's question.

[0045] The above-described embodiment can be modified as needed by partially changing the configuration or functions of each of the above-described devices. Therefore, several modifications of the above-described embodiment will be described below as other embodiments. The following mainly focuses on differences from the above-described embodiment, and detailed descriptions of commonalities with the content already described will be omitted. The modifications described below may be implemented individually or in appropriate combination.

[0046] (First Modification) For example, the information processing device 2 may generate hyperlink information for setting address information as a hyperlink for a reply message. Fig. 7 is a block diagram showing an example of the functional configuration of the information processing device 2 according to the first modified example. The information processing device 2 according to the first modified example shown in Fig. 7 further includes a hyperlink information generation unit 218 in addition to the functional configuration shown in Fig. 3.

[0047] The hyperlink information generating unit 218 generates hyperlink information for setting address information as a hyperlink for the answer message. Specifically, the hyperlink information generating unit 218 generates hyperlink information for setting the address information generated by the address information generating unit 215 as a hyperlink for the answer message acquired by the answer message acquiring unit 212.

[0048] For example, the hyperlink information generating unit 218 generates hyperlink information for setting the address information generated by the address information generating unit 215 as a hyperlink to the answer sentence acquired by the answer sentence acquiring unit 212 or to a character string representing a product in the answer sentence. The hyperlink information generating unit 218 stores the generated hyperlink information in the auxiliary storage device 24. Note that the hyperlink information generating unit 218 may generate an answer sentence with a hyperlink added by adding hyperlink information to the answer sentence or to a character string representing a product in the answer sentence.

[0049] The answer information generation unit 216 generates an answer sentence to which hyperlink information is set as answer information. Specifically, the answer information generation unit 216 generates an answer sentence to which hyperlink information generated by the hyperlink information generation unit 218 is set as answer information. This answer information is also referred to as second answer information. The answer information generation unit 216 stores the generated second answer information in the auxiliary storage device 24.

[0050] The providing unit 217 provides the second answer information generated by the answer information generating unit 216 to the user via the input / output device 1. Here, the second answer information provided by the providing unit 217 will be described with reference to FIG.

[0051] Fig. 8 is a schematic diagram showing an example of second answer information according to the first modified example. Fig. 8 shows an example of second answer information assuming the same question and answer as those in Fig. 4. As shown in Fig. 8, in the second answer information 81, a hyperlink is set for the character string "instant curry" representing the product included in the answer.

[0052] This allows the user to check the answer corresponding to the question by looking at the second answer information 81. Furthermore, the user can check the content of the promotional information (reference information) provided by the store by referring to the URL set for "instant curry" in the second answer information.

[0053] Fig. 9 is a flowchart showing an example of the control process of the information processing device 2 according to the first modified example. The process from step S61 to step S65 shown in Fig. 9 is the same as the process from step S61 to step S65 shown in Fig. 6, and therefore a description of the process will be omitted.

[0054] 9, the hyperlink information generating unit 218 generates hyperlink information for setting the address information generated by the address information generating unit 215 as a hyperlink for the answer sentence acquired by the answer sentence acquiring unit 212 (step S68). Subsequently, the answer information generating unit 216 generates second answer information 81 including the answer sentence acquired by the answer sentence acquiring unit 212 and the hyperlink information generated by the hyperlink information generating unit 218 (step S69).

[0055] Next, the providing unit 217 provides the second answer information 81 generated by the hyperlink information generating unit 218 to the user via the input / output device 1 (step S70). When this process ends, the processing of the information processing device 2 ends. This allows the user to check the answer corresponding to the question. Furthermore, the user can check more detailed content of the sales promotion information provided by the store by referring to the hyperlink indicated in the second answer information 81.

[0056] (Second Modification) In the above-described embodiment, the user's question is about the recommended products sold in the store, but is not limited thereto. For example, the user's question may be about a menu for a meal that the user will cook.

[0057] For example, the question content included in the question text received by the receiving unit 211 may be "What should we have for dinner today?".

[0058] For example, in order to answer a question from a user, the answer sentence acquisition unit 212 generates a prompt stating that information about a menu to be recommended to the user should be added, product information about products necessary for the recommended menu should be added, a sentence about sales promotion of the product should be added, etc. Then, the answer sentence acquisition unit 212 inputs the question sentence received by the receiving unit 211 into a large-scale language model that is functionally configured to output an answer sentence to the question sentence, and acquires the answer sentence output by the large-scale language model.

[0059] The related information acquisition unit 213 acquires promotional information about products necessary for the recommended menu, which are indicated in the response text. Then, the reference information generation unit 214 generates reference information that references the promotional information acquired by the related information acquisition unit 213.

[0060] FIG. 10 is a schematic diagram showing an example of reference information according to the second modified example. The reference information 101 shown in FIG. 10 indicates curry ingredients as products necessary for a menu recommended to a user. The reference information 101 also indicates information about the curry ingredients, such as the required quantities and prices of the products. The reference information 101 also indicates the total price when all the products are purchased. Because the price of a product may vary depending on the time of day it is sold in a store, the reference information 101 includes the date and time when the reference information generation unit 214 generated the reference information 101. The reference information generation unit 214 stores the generated reference information 101 in the auxiliary storage device 24.

[0061] FIG. 11 is a schematic diagram showing an example of first answer information according to the second modified example. FIG. 11 shows first answer information 111. The first answer information 11 includes an answer text that answers the question text described above and address information. The answer text shown in the first answer information 111 is "How about some curry?" The address information shown in the first answer information 111 is the URL "https: / / www.zzzzzzzz.jp / ". Note that the "curry recipe reference price" may be information based on reference information for the link destination of the promotional information or the address information, or may be a character string automatically generated by the answer information generation unit 216 based on the answer text, etc.

[0062] The answer text shown in the first answer information 111 is clearly displayed without being buried in the sales promotion information. This allows the user to check the answer text corresponding to the question text. Furthermore, the user can check more detailed content of the sales promotion information provided by the store by referring to the URL shown in the first answer information 111.

[0063] (Third Modification) For example, the information processing device 2 may invalidate the address information and the hyperlink information after a predetermined time has elapsed. Fig. 12 is a block diagram showing an example of the functional configuration of the information processing device 2 according to the third modified example. The information processing device 2 according to the third modified example shown in Fig. 12 further includes a deletion unit 219 in addition to the functional configuration shown in Fig. 7.

[0064] The deletion unit 219 invalidates the address information after a predetermined time has elapsed. For example, the deletion unit 219 invalidates the URL of the address information and the URL of the hyperlink information stored in the auxiliary storage device 24 after a predetermined time has elapsed. The invalidation of the address information may be, for example, but is not limited to, the deletion of the address information.

[0065] The predetermined time is, for example, the time when the price of the product in the promotional information is updated or the time when a predetermined time has elapsed since the response information was provided to the user. However, the predetermined time is not limited to this. This allows the information processing device 2 to provide the user with the latest promotional information. Furthermore, by deleting the URL, the information processing device 2 can prevent unnecessary information from being published on the Internet.

[0066] (Fourth Modification) For example, the address information generating unit 215 of the information processing device 2 may be configured to generate address information for all of the reference information generated by the reference information generating unit 214, or may be configured to generate address information for some of the reference information. For example, when the amount of information (amount of text, data capacity) of the reference information generated by the reference information generating unit 214 exceeds a predetermined threshold, the address information generating unit 215 may generate address information for the reference information.

[0067] (Fifth Modification) In the above-described embodiment, the information processing device 2 equipped with a large-scale language model is configured to be deployed and used in a local environment, but this is not limiting, and the information processing device 2 equipped with a large-scale language model may also be configured to be deployed and used in a highly secure cloud environment. The highly secure cloud environment is not disclosed on the Internet, but is connected to an in-house server environment via a highly confidential communication line.

[0068] The program executed by the information processing device 2 of the embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the program executed by the information processing device 2 of the embodiment and the modified example may be provided or distributed via a network such as the Internet.

[0069] The programs executed by each device in the above-described embodiments are provided in a state where they are pre-installed in a ROM, a storage unit, etc. The programs executed by each device in the above-described embodiments may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a digital versatile disk (DVD).

[0070] Furthermore, the programs executed by each device in the above-described embodiments may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the programs executed by each device in the above-described embodiments may be provided or distributed via a network such as the Internet.

[0071] Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments and their modifications can be embodied in various other forms, and various omissions, substitutions, changes, and combinations can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0072] 1 Input / Output Device 2. Information processing equipment 211 Receiving unit 212 Answer sentence acquisition part 213 Related Information Acquisition Department 214 Reference information generation unit 215 Address information generation unit 216 Answer information generation section 217 Provision Department 218 Hyperlink Information Generation Unit 219 Deleted section [Prior art documents] [Patent documents]

[0073] [Patent Document 1] Japanese Patent Publication No. 2023-120862

Claims

1. a receiving unit that receives a question input by a user who uses the store; an answer sentence acquisition unit that inputs the question sentence received by the receiving unit into a large-scale language model that is configured to output an answer sentence to the question sentence, and acquires the answer sentence output by the large-scale language model; a related information acquisition unit that acquires related information about the product indicated in the reply; an address information generating unit that generates address information that can refer to the related information; a response information generating unit that generates response information including the response sentence and the address information; a providing unit that provides the answer information to the user; An information processing device comprising:

2. a reference information generating unit that generates reference information that is formed from the related information based on the answer sentence and the related information; the address information generating unit generates address information that can refer to the reference information. The information processing device according to claim 1 .

3. the related information acquisition unit acquires the related information based on products sold in the store. The information processing device according to claim 1 .

4. a hyperlink information generating unit that generates hyperlink information for setting the address information as a hyperlink for the reply message; the answer information generation unit generates an answer sentence to which the hyperlink information is set as the answer information; The information processing device according to claim 1 .

5. a deletion unit that invalidates the address information after a predetermined time has elapsed; The information processing device according to claim 2 .

6. The computer of the information processing device, a receiving unit that receives a question input by a user who uses the store; an answer sentence acquisition unit that inputs the question sentence received by the receiving unit into a large-scale language model that is configured to output an answer sentence to the question sentence, and acquires the answer sentence output by the large-scale language model; a related information acquisition unit that acquires related information about the product indicated in the reply; an address information generating unit that generates address information that can refer to the related information; a response information generating unit that generates response information including the response sentence and the address information; a providing unit that provides the answer information to the user; An information processing program that makes it function as such.

Images