Information providing system and information providing method

Abstract

An information providing system (1) according to an embodiment of the present invention comprises: a reception unit (21) that receives input data from a user; a determination unit (23) that determines, on the basis of the input data, product-related information pertaining to a product to be proposed to a user and a search site (3) for searching the product; a search query generation unit (12) that uses, as input, information indicating the product-related information and the search site (3) and uses an AI model (12a), which is for query generation and which is trained by machine learning so as to output a search query, to generate a search query corresponding to the search site (3), and that uses the generated search query to search the search site (3) and acquires a search result; and an output unit (24) that outputs output data which includes the search result.

Description

Information provision system and information provision method

[0001] The present disclosure relates to an information providing system and an information providing method.

[0002] Patent Document 1 describes a technique for shaping a query input by a user into a format suitable for searching for a desired product or the like.

[0003] Japanese Patent Application Laid-Open No. 2023-127542

[0004] The device described in Patent Document 1 improves product search accuracy by searching search sites such as online shopping malls using a formatted search query. However, because the search engines of each search site have different query analysis algorithms, different search results may be output depending on the search site, even when the same search query is used. Therefore, when a search query is automatically generated to suggest products to a user, appropriate search results may not be obtained depending on the search site.

[0005] Therefore, an object of the present disclosure is to provide an information providing system and an information providing method that are capable of generating appropriate search queries according to search sites.

[0006] An information provision system according to one embodiment includes a receiving unit that receives input data from a user, a determination unit that determines, based on the input data, product-related information regarding a product to be suggested to the user and a search site to search for the product, a search query generation unit that receives as input the product-related information and information indicating the search site, generates a search query corresponding to the search site using a query generation model that has been machine-learned to output a search query, searches the search site using the generated search query, and obtains search results, and an output unit that outputs output data including the search results.

[0007] According to the present disclosure, it is possible to generate an appropriate search query according to the search site.

[0008] FIG. 1 is a block diagram showing the functional configuration of an information providing system according to one embodiment. FIG. 2 is a diagram showing an example of an interaction with the information providing system displayed on a display screen of a user terminal. FIGS. 3(a) and 3(b) are diagrams showing example outputs of a query generation AI model. FIG. 4 is a diagram showing an example of an interaction with the information providing system displayed on a display screen of a user terminal. FIG. 5 is a sequence diagram showing an information providing method according to one embodiment. FIG. 6 is a block diagram showing the functional configuration of an information providing system according to another embodiment. FIG. 7 is a block diagram showing the functional configuration of an information providing system according to yet another embodiment. FIG. 8 is a block diagram showing an example of the hardware configuration of an information providing system.

[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicated description will be omitted.

[0010] 1 is a block diagram showing the functional configuration of an information provision system 1 according to an embodiment. The information provision system 1 functions as a chatbot, accepts text input from a user, and supports the user in purchasing products by suggesting products in an interactive format.

[0011] As shown in FIG. 1 , the information providing system 1 is communicably connected to a user's terminal (hereinafter referred to as "user terminal 2"). The user terminal 2 can access the information providing system 1 via a network. The user terminal 2 is, for example, a portable terminal such as a laptop computer, a tablet terminal, a smartphone, a game console, or a PDA (Personal Digital Assistant), and is operated by a user. Note that the number of user terminals 2 connected to the information providing system 1 may be two or more.

[0012] The information providing system 1 includes, as functional components, a RAG (Retrieval-Augmented Generation) device 10 and a server device 20 .

[0013] The information providing system 1 generates a search query to search for a desired product and transmits the generated search query to one of the plurality of search sites 3. The information providing system 1 then obtains search results corresponding to the search query and provides information including the search results to the user.

[0014] The multiple search sites 3 are external EC (Electronic Commerce) sites that sell products over the Internet. Each search site 3 has a database that stores products. When each search site 3 receives a search query, it outputs a list of product pages corresponding to the search query as search results. Users can purchase products by accessing the product pages included in the search results. Each search site 3 is operated by a different business operator. Therefore, each search site 3 searches for products using a different search engine.

[0015] 1 shows three search sites 3A, 3B, and 3C. Note that the number of search sites that can communicate with information provision system 1 is not limited to three and is arbitrary. In the following description, search sites 3A, 3B, and 3C will be collectively referred to as search site 3 unless there is a particular need to distinguish between them.

[0016] The RAG device 10 accepts input data from the user terminal 2 and transmits output data to the user terminal as a response to the input data. The input data is text data related to the product input by the user. The output data is text data including search results for the product. In the following description, the user and the information providing system 1 communicate by sending and receiving text data, but this is not limited to this and the communication may also be performed using image data or audio data. Details of the functions of the RAG device 10 will be described later.

[0017] The server device 20 has, as its functional configuration, a conversation generation unit 11 and a search query generation unit 12. In the embodiment shown in Fig. 1, the conversation generation unit 11 and the search query generation unit 12 are realized by a single server device 20, but these functional elements may be distributed across multiple devices.

[0018] The conversation generation unit 11 generates output data that is a response to the input data based on the input data transmitted from the user terminal 2. The conversation generation unit 11 includes an interactive AI model 11a for generating output data. The interactive AI model 11a is a generative AI model that inputs a prompt generated by the RAG device 10 and outputs text data corresponding to the prompt. The generative AI model is a model that can generate content in response to a prompt including input data, according to any one or a combination of the instructions, context, question, and output format indicated by the prompt, and output the content as output data. The generative AI model may be, for example, an interactive AI model that includes a large language model (LLM) and a user interface (UI) for dialogue with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. The interactive AI model 11a may be stored in the server device 20, or may be stored in another device connected to the server device 20 via a network, and configured to enable information exchange with the user via the server device 20. Although a large-scale language model is described above as an example, other AI models may also be used.

[0019] The search query generation unit 12 generates a search query for searching for a product. The search query generation unit 12 includes a query generation AI model 12a that has been machine-trained to receive product-related information about a product to be suggested to a user and information indicating a search site 3 for searching the product as input, and output a search query corresponding to the specified search site 3. The query generation AI model 12a is constructed by machine learning training data including the product-related information, information indicating the search site, the search query, and a correct answer label. The query generation AI model 12a may be stored in the server device 20, or may be stored in another device connected to the server device 20 via a network, and configured to be able to exchange information with the user via the server device 20.

[0020] The RAG device 10 is disposed between the user terminal 2 and the server device 20, relays prompts including input data from the user terminal 2 to the server device 20, and transmits output data from the server device 20 in response to the prompt to the user terminal 2. As shown in FIG. 1, the RAG device 10 functionally comprises a reception unit 21, a prompt generation unit 22, a determination unit 23, and an output unit 24. The reception unit 21 receives input data related to a product from the user terminal 2. The input data is, for example, text data including inquiries or questions about the product. FIG. 2 is a display screen showing a dialogue with the information provision system 1 displayed on the display screen of the user terminal 2. For example, as shown in FIG. 2, the reception unit 21 receives input data M101 such as "I want a PC" from a user 5 who is considering purchasing a PC.

[0021] The prompt generation unit 22 generates a prompt based on the input data M101 of the user 5 and inputs it to the interactive AI model 11a. A prompt is information indicating an instruction or question input by a user in an interactive system, such as a dialogue with an AI model or a command line interface (CLI). The prompt input to the interactive AI model 11a is text data including information indicating, for example, an instruction to be executed by the interactive AI model, a task to be executed by the interactive AI model 11a, a background / context (e.g., role, condition) that the interactive AI model 11a should consider, a question to be answered by the interactive AI model 11a, and an output format of response information from the interactive AI model 11a. The prompt may also include input information that is the target of the instruction / task executed by the interactive AI model 11a. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a predetermined application program.

[0022] The prompt generation unit 22 generates text data to be input to the interactive AI model 11 a as a prompt. The prompt generation unit 22 may input the input data M101 directly to the interactive AI model 11 a as a prompt, or may input a prompt obtained by correcting or formatting the input data M101 to the interactive AI model 11 a.

[0023] For example, the prompt generation unit 22 may generate a prompt (second prompt) for generating output data including a question sentence to identify a specific product or product conditions. For example, the prompt generation unit 22 identifies the product category "PC" from input data M101 such as "I want a PC" and generates a prompt for asking about the product's use or product attributes. Product attributes are information that represent the nature or characteristics of a product. Examples of attributes related to the category "PC" include budget, screen size, weight, battery life, etc. Product attributes can also be considered as product search conditions.

[0024] For example, the prompt generation unit 22 inputs a prompt to the interactive AI model 11a and obtains output data M102 from the interactive AI model 11a, including a question for inquiring about the product's use and attributes, as shown in FIG. 2. In the example shown in FIG. 2, the prompt generation unit 22 obtains output data M102 such as, "You are looking for a PC. What is your main purpose for using it? For example, if you could tell us the scenario in which you will be using it, such as for work, gaming, or learning, we can make the best recommendation for you. Also, please let us know your budget and desired specifications (screen size, weight, battery life, etc.)." The output data M102 is transmitted as output data to the user terminal 2 via the output unit 24, which will be described later.

[0025] As shown in Figure 2, when input data M103 is received from the user terminal 2 as a response to the output data M102, which states, "I would like a laptop that can run the latest games. The resolution should be full HD, and my budget is about 200,000 yen. I'm thinking of a medium screen size. I would like it to weigh no more than 2 kg," the prompt generation unit 22 generates a prompt including the input data M103 and inputs the prompt to the interactive AI model 11a.

[0026] The interactive AI model 11a outputs output data M104 including product attributes that match the user 5's desires as a response to the prompt. In the example shown in FIG. 2, the interactive AI model 11a outputs output data M104 such as, "To summarize your desires, I need to find a PC that meets the following conditions: - For gaming - Screen size: approximately 15 inches to 15.6 inches - Weight: 2 kg or less - Resolution: Full HD (1920 x 1080) - Performance to run the latest games (appropriate CPU and graphics card) - Budget: approximately 200,000 yen. I will search for an appropriate laptop based on these conditions." At this time, depending on the content of the input data M103, output data M104 may be generated that includes information that identifies a specific product (product name or model number) rather than product attributes.

[0027] The prompt generating unit 22 may generate a prompt for generating output data including a question sentence until a specific product or product condition is identified, and may repeatedly send the question sentence to the user terminal 2 .

[0028] The determination unit 23 determines whether a product search is necessary based on the output of the interactive AI model 11a. For example, the determination unit 23 analyzes the output data to determine whether a specific product name, model number, or product attribute has been specified, and if it is determined that a specific product name, model number, or product attribute has been specified, it determines that a product search is necessary. Conversely, if it is determined that a specific product name, model number, or product attribute has not been specified, it determines that a product search is unnecessary. In this case, the information provision system 1 repeatedly sends questions to the user terminal 2 until a specific product name, model number, or product attribute is specified.

[0029] In the example shown in FIG. 2, the output data M104 includes specific product attributes, so the determining unit 23 determines that a product search is necessary.

[0030] When it is determined that a product search is necessary, the determination unit 23 determines a search site 3 for searching for the product. The determination unit 23 can determine the search site 3 for searching for the product by using, for example, statistical data. For example, the determination unit 23 may deterministically select the search site 3 that has been used most frequently based on statistical data of search sites 3 previously used by the user of the user terminal 2. The determination unit 23 may also deterministically select the search site 3 that has been used most frequently to search for a specified product name, model number, or product attribute based on statistical data regarding past search history. Furthermore, the determination unit 23 may select a search site 3 for searching for the product by using a machine learning model that utilizes a conversion rate as an objective function by combining these statistical data.

[0031] Furthermore, if it is determined that a product search is necessary, the determination unit 23 determines product-related information about the product to be recommended to the user based on the input data. The product-related information is information including the product name, model number, or attributes. In the example shown in FIG. 2, the determination unit 23 extracts the product attributes included in the output data M104 and determines the following conditions as the product-related information: Resolution: Full HD Screen size: 14 inches to 15.6 inches Price: 200,000 yen or less Weight: 2 kg or less

[0032] It should be noted that the output data M104 is generated based on the input data M103 of the user 5, and therefore the product-related information can be said to be data generated based on the input data M103.

[0033] The determination unit 23 outputs the determined product-related information and information indicating the search site 3 to the search query generation unit 12. Note that, if the output data M104 includes information for identifying a product, the determination unit 23 may determine the product name or the product model number as the product-related information, instead of the product attributes.

[0034] The decision unit 23 may use a technique called ReAct (Synergizing reasoning and acting in language models), which generates answers by repeating thought, observation, and action, to determine whether a product search is necessary and to determine product-related information and search sites.

[0035] The search query generation unit 12 generates a search query according to the specified search site 3 based on the product-related information and information indicating the search site 3. Because the search engine of the search site 3 employs its own query analysis algorithm, different search results may be output depending on the search site 3 even when the same search query is used for a search. The search query generation unit 12 generates an appropriate search query for searching for a product corresponding to the product-related information according to the specified search site 3.

[0036] The search query generation unit 12 includes a query generation AI model 12a that has been trained by machine learning to input product-related information and information indicating the search site 3 and output a search query corresponding to the input search site 3. The query generation AI model 12a is constructed by machine learning training data including the product-related information, information indicating the search site 3, the search query, and a correct answer label. The correct answer label is set by an administrator based on, for example, the number of products extracted when the specified search site 3 is searched using the search query, the level of relevance, etc.

[0037] For example, as shown in Figure 3(a), when the product name: AAA and search site: 3A are input to the query generation AI model 12a as product-related information, the search query generation unit 12 outputs "'AAA' manufactured by BBB" as the search query. On the other hand, as shown in Figure 3(b), when the product name: AAA and search site: 3B are input to the query generation AI model 12a as product-related information, the search query generation unit 12 outputs "AAA" as the search query. In other words, even when the same product-related information is input, the search query generation unit 12 outputs different search queries depending on the specified search site 3.

[0038] The search query generation unit 12 also searches the specified search site 3 using the generated search query to obtain search results. For example, as shown in FIG. 3( b), when a product name: AAA and a search site: 3B are input as product-related information to the query generation AI model 12a, the search query generation unit 12 transmits the search query "AAA" to the search site 3B and obtains information indicating the search results from the search engine of the search site 3B. For example, the search results are a list of products corresponding to the search query. Typically, the search results include links to product pages of the products corresponding to the search query. The search query generation unit 12 outputs information indicating the obtained search results to the RAG device 10.

[0039] When the information indicating the search results is obtained from the search query generation unit 12, the prompt generation unit 22 of the RAG device 10 outputs a prompt (first prompt) including the information indicating the search results to the conversation generation unit 11. The conversation generation unit 11 inputs the prompt to the interactive AI model 11a to generate output data including the search results.

[0040] The output data M105 shown in FIG. 4 is an example of output data including search results from the search site 3. In the example shown in FIG. 4, the interactive AI model 11a outputs the following output data M105: "We will answer your questions about recommended PCs. Below are some laptops that meet the above conditions: 1. XX BOOK: XX CPU, 8 GB memory, 512 GB SSD, 14-inch display, XX OS 10, price: 200,000 yen 2. XX BOOK: XX CPU, 8 GB memory, 512 GB SSD, 14-inch display, XX OS 10, price: 180,000 yen 3. △△ PAD: △△ CPU, 8 GB memory, 512 GB SSD, 14-inch display, △△ OS 10, price: 180,000 yen Please use the above information to select a PC that suits your preferences." As shown in FIG. 4, the output data M105 includes a list of products that match the product attributes included in the output data M104.

[0041] The output unit 24 outputs output data M105 including information indicating the search results generated by the conversation generation unit 11 to the user terminal 2. As shown in Fig. 4, the output data M105 including the search results is displayed on the display device of the user terminal 2. The user can purchase a desired product by clicking on the link of the product to access the product page.

[0042] Next, an information providing method according to an embodiment will be described. This information providing method is executed by the above-described information providing system 1. Fig. 5 is a sequence diagram showing the information providing method according to an embodiment.

[0043] 5, in this information providing method, the receiving unit 21 of the RAG device 10 receives input data from the user terminal 2 (step ST1). The input data includes a consultation or question about a product.

[0044] Next, the prompt generation unit 22 generates a prompt based on the input data (step ST2). For example, the prompt generation unit 22 may use the input data as the prompt. The prompt generation unit 22 outputs the generated prompt to the conversation generation unit 11 (step ST3).

[0045] The conversation generation unit 11 inputs the prompt to the interactive AI model 11a to generate output data (step ST4). The output data includes a response to the user's inquiry or question about the product. The generated output data is output to the RAG device 10 (step ST5).

[0046] Next, the determination unit 23 of the RAG device 10 analyzes the output data output from the conversation generation unit 11 and determines whether a product search is necessary (step ST6). If it is determined that a product search is necessary, the determination unit 23 determines, based on the output data, product-related information about the product to be proposed to the user of the user terminal 2 and the search site 3 to search for the product (step ST7).

[0047] The determination unit 23 outputs the determined product-related information and information indicating the search site 3 to the search query generation unit 12 (step ST8). Next, the search query generation unit 12 inputs the product-related information and information indicating the search site 3 to the query generation AI model 12a, and generates a search query according to the input search site 3 (step ST9).

[0048] Next, the search query generation unit 12 transmits the generated search query to the specified search site 3 (step ST10). The search engine of the search site 3 searches the database using the received search query (step ST11) and transmits the search results to the RAG device 10 (step ST12).

[0049] Next, the prompt generation unit 22 generates a prompt including the search results (step ST13) and outputs the generated prompt to the conversation generation unit 11 (step ST14). The conversation generation unit 11 generates output data including the search results based on the input prompt (step ST15). The conversation generation unit 11 outputs the generated output data to the RAG device 10 (step ST16).

[0050] The output unit 24 of the RAG device 10 transmits the output data to the user terminal 2 (step ST17). The user browses the search results included in the output data, and if there is a product that the user likes, selects the product link and purchases the product.

[0051] As described above, in the information providing system 1, by inputting product-related information and information indicating the search site 3 into the query generation model, it is possible to generate an appropriate search query according to the search site. By searching the search site 3 using the search query generated in this way, it is possible to obtain appropriate search results regardless of the search site 3. Then, by outputting search results including the search results to the user terminal 2, it is possible to suggest products that meet the user's desires.

[0052] Furthermore, the information provision system 1 generates output data by inputting prompts including search results into the interactive AI model 11a, and is therefore able to suggest products to the user in an interactive format, thereby providing the user with a smooth purchasing experience.

[0053] In addition, when a specific product or product conditions are not specified, the information provision system 1 generates output data including a question sentence, so that the product desired by the user can be narrowed down through dialogue with the user.

[0054] The information provision system 1 is not limited to the configuration shown in FIG. 1 . As shown in FIG. 6 , at least one of the interactive AI model 11a and the query generation AI model 12a may be implemented in the RAG device 10. As shown in FIG. 7 , at least some of the functional elements of the information provision system 1 (the conversation generation unit 11, the search query generation unit 12, the reception unit 21, the prompt generation unit 22, the determination unit 23, and the output unit 24) may be implemented in the user terminal 2. As shown in FIG. 7 , if the user terminal 2 includes an output unit 24, the output unit 24 displays output data including search results on the display screen of the user terminal 2 to present the search results to the user. This configuration can be realized by installing an application that executes the functions of each functional element in the user terminal 2.

[0055] The information providing system 1 and the information processing method of the present disclosure may have the following configuration.

[0056] [1] An information provision system comprising: a receiving unit that receives input data from a user; a determination unit that determines, based on the input data, product-related information about a product to be suggested to the user and a search site to search for the product; a search query generation unit that receives as input the product-related information and information indicating the search site, generates the search query corresponding to the search site using an AI model for query generation that has been machine-learned to output a search query, searches the search site using the generated search query, and acquires search results; and an output unit that outputs output data including the search results.

[0057] [2] The information providing system according to [1], wherein the product-related information includes the name, model number, or attributes of the product.

[0058] [3] The information provision system according to [1] or [2], further comprising a prompt generation unit that generates a first prompt based on the search results, inputs the first prompt into an interactive AI model, and acquires output data including the search results.

[0059] [4] The information provision system described in [3], wherein the prompt generation unit generates a second prompt based on the input data, and inputs the second prompt into the interactive AI model to obtain output data including a question sentence for identifying the product.

[0060] [5] The information provision system according to [3] or [4], wherein the determination unit determines whether a product search is necessary based on the output from the interactive AI model, and when it is determined that the product search is necessary, the determination unit outputs the product-related information and information indicating the search site to the search query generation unit in order to generate the search query.

[0061] [6] A method of providing information, comprising: receiving input data from a user; determining, based on the input data, product-related information about a product to be suggested to the user and a search site to search for the product; using the product-related information and information indicating the search site as input, generating a search query corresponding to the search site using an AI model for query generation that has been machine-learned to output a search query; searching the search site using the generated search query to obtain search results; and providing output data including the search results to the user.

[0062] The block diagram shown in FIG. 1 shows functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may be realized by combining software with the single device or multiple devices.

[0063] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0064] For example, the information providing system 1 according to an embodiment of the present invention may function as a computer. Fig. 8 is a diagram showing an example of the hardware configuration of the information providing system 1. The information providing system 1 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0065] In the following description, the term "apparatus" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information provision system 1 may be configured to include one or more of the apparatuses shown in FIG. 8, or may be configured to exclude some of the apparatuses.

[0066] Each function in the information provision system 1 is realized by loading specified software (programs) onto hardware such as a processor 1001 and a memory 1002, causing the processor 1001 to perform calculations and control communication via a communication device 1004 and the reading and / or writing of data in the memory 1002 and storage 1003.

[0067] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, each of the functional elements shown in FIG. 1 may be realized by the processor 1001.

[0068] The processor 1001 also reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, each functional element of the information provision system 1 may be implemented by a control program stored in the memory 1002 and running on the processor 1001. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0069] The memory 1002 is a computer-readable recording medium and may be composed of at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be called a register, a cache, a main memory (primary storage device), or the like. The memory 1002 can store executable programs (program codes), software modules, and the like for implementing an information processing method according to one embodiment of the present invention.

[0070] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including memory 1002 and / or storage 1003.

[0071] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0072] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0073] Furthermore, each device such as the processor 1001 and the memory 1002 is connected to a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.

[0074] The information providing system 1 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.

[0075] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0076] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0077] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0078] In the present disclosure, a specific operation described as being performed by a base station may be performed by its upper node in some cases. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal may be performed by at least one of the base station and another network node other than the base station (for example, an MME or an S-GW, etc., but are not limited to these). Although the above example illustrates a case where there is one other network node other than the base station, a combination of multiple other network nodes (for example, an MME and an S-GW) may also be used.

[0079] Information etc. may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer), or may be input / output via multiple network nodes.

[0080] Input and output information may be stored in a specific location (for example, memory) or managed in a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0081] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0082] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0083] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0084] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0085] Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0086] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0087] It should be noted that terms explained in this disclosure and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0088] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0089] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed as absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0090] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0091] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0092] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0093] When designations such as "first," "second," etc. are used in this disclosure, any reference to an element does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0094] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0095] To the extent that the terms "include," "including," and variations thereof are used herein or in the claims, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used herein or in the claims, is not intended to be an exclusive or.

[0096] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0097] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0098] 1...information provision system, 3, 3A, 3B, 3C...search site, 5...user, 11...conversation generation unit, 11a...interactive AI model, 12...search query generation unit, 12a...query generation AI model, 21...reception unit, 22...prompt generation unit, 23...determination unit, 24...output unit, M101, M103...input data, M102, M104, M105...output data.

Claims

1. An information provision system comprising: a reception unit that receives input data from a user; a determination unit that determines, based on the input data, product-related information regarding a product to be suggested to the user and a search site to search for the product; a search query generation unit that receives as input the product-related information and information indicating the search site, generates a search query corresponding to the search site using an AI model for query generation that has been machine-learned to output a search query, searches the search site using the generated search query, and obtains search results; and an output unit that outputs output data including the search results.

2. The information providing system according to claim 1, wherein the product-related information includes the name, model number, or attributes of the product.

3. The information provision system of claim 1, further comprising a prompt generation unit that generates a first prompt based on the search results and inputs the first prompt into an interactive AI model to obtain an answer sentence including the search results.

4. The information provision system of claim 3, wherein the prompt generation unit generates a second prompt based on the input data and inputs the second prompt into the interactive AI model to obtain a question for identifying the product.

5. The information provision system of claim 3, wherein the determination unit determines whether a product search is necessary based on the output from the interactive AI model, and when it determines that the product search is necessary, the determination unit outputs the product-related information and information indicating the search site to the search query generation unit in order to generate the search query.

6. A method of providing information comprising: a step of accepting input data from a user; a step of determining, based on the input data, product-related information regarding a product to be suggested to the user and a search site to search for the product; a step of using the product-related information and information indicating the search site as input and generating a search query corresponding to the search site using an AI model for query generation that has been machine-learned to output a search query; a step of searching the search site using the generated search query to obtain search results; and a step of outputting output data including the search results.

Images