Search support system, search support method, and program

Abstract

The system presents the user with appropriate search criteria in a searchable system that uses parameters. [Solution] The search support system comprises a parameter storage unit that stores parameters that can be set as search conditions in the object search system, a related information database that stores related information related to the object, a reception unit that receives search conditions input from the user in natural language, an extraction unit that extracts related information corresponding to the input search conditions by referring to the related information database, a generation unit that generates parameter-based search conditions corresponding to the input search conditions based on the extracted related information, and an output processing unit that outputs the generated search conditions.

Description

Technical Field

[0001] The present invention relates to a search support system, a search support method, and a program.

Background Art

[0002] There is a document search device that presents recommended words useful for narrowing down search results to a user in response to an inquiry from the user (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] On the other hand, there is a search system having a detailed search function for narrowing down search targets such as products by specifying search conditions with parameters. For example, on a manufacturer's website or the like, there is a search system for searching for products by specifying product specifications and specifications. However, in such a search system, it is difficult to narrow down the search for products unless the user knows what search conditions (parameter settings) should be used to narrow down the products. For example, when a user wants to search for a product that can be used for a certain purpose, it is difficult to set appropriate search conditions (parameters) in the narrowing-down search unless the user knows what specifications of products can be used for that purpose.

[0005] The present invention has been made in view of such circumstances, and an object thereof is to provide a search support system, a search support method, and a program that can present appropriate search conditions to a user in a search system that can be searched using parameters.

Means for Solving the Problems

[0006] To solve the above-mentioned problems, one aspect of the present invention comprises: a parameter storage unit that stores parameters that can be set as search conditions in an object search system; a related information database that stores related information related to the object; a reception unit that receives search conditions input from a user in natural language; an extraction unit that extracts related information corresponding to the input search conditions by referring to the related information database; a generation unit that generates search conditions using the parameters corresponding to the input search conditions based on the extracted related information; and an output processing unit that outputs the generated search conditions. The related information includes at least one of the following: laws and regulations related to the object or questions and answers regarding the object, and parameters of the object. The receiving unit receives input of search conditions including the use of the object from the user. The generating unit, referring to the parameter storage unit, generates a prompt that includes parameters that can be set as search conditions in the object search system, and provides instructions to present search conditions using the parameters that would match the input search conditions, along with reasons. The generating unit also generates a prompt including the input search conditions and the extracted related information. By inputting the generated prompt into the generating AI, the AI ​​generates search conditions using the parameters and reasons for those search conditions. The output processing unit outputs the generated search conditions and reasons for those search conditions. It is a search assistance system.

[0007] Furthermore, one embodiment of the present invention is: The system includes a parameter storage unit that stores parameters that can be set as search conditions in the object search system. A search support method executed by a computer used in a search support system, comprising: receiving search conditions input in natural language from a user; referring to a related information database that stores related information related to the target object to extract related information corresponding to the input search conditions; generating search conditions with parameters corresponding to the input search conditions based on the extracted related information; and outputting the generated search conditions. A search support method that includes the following: the related information includes at least one of the laws and regulations related to the object or a question and answer regarding the object, and the parameters of the object; accepting the input of the search conditions includes accepting the input of search conditions including the use of the object from the user; generating search conditions by parameters includes referencing the parameter storage unit to generate a prompt that includes parameters that can be set as search conditions in the object search system, an instruction that presents search conditions by parameters that would match the input search conditions with reasons, the input search conditions and the extracted related information, and inputting the generated prompt to the generation AI to generate the search conditions by parameters and the reasons for those search conditions; and outputting the search conditions includes outputting the generated search conditions and the reasons for those search conditions. This is a search assistance method.

[0008] Furthermore, one embodiment of the present invention is: The system includes a parameter storage unit that stores parameters that can be set as search conditions in the object search system. The computer used in the search support system accepts natural language search criteria input from the user. hair, Referencing a related information database that stores related information concerning the aforementioned object, extract related information corresponding to the entered search conditions. death, Based on the extracted related information, generate search conditions using the parameters corresponding to the entered search conditions. death, Output the generated search conditions. The program is configured to perform the following actions, wherein the related information includes at least one of the laws and regulations related to the object or a question and answer regarding the object, and the parameters of the object; accepting the input of the search conditions includes accepting the input of search conditions from the user, including the use of the object; generating the search conditions by the parameters includes referencing the parameter storage unit to generate a prompt that includes parameters that can be set as search conditions in the object search system, an instruction that presents search conditions by the parameters that would match the input search conditions, along with the reasons; generating a prompt that includes the input search conditions and the extracted related information; and inputting the generated prompt to the generating AI to generate the search conditions by the parameters and the reasons for those search conditions; and outputting the search conditions includes outputting the generated search conditions and the reasons for those search conditions. It is a program. [Effects of the Invention]

[0009] As described above, according to this invention, it is possible to present appropriate search conditions to a user in a search system that can be searched using parameters.

Brief Description of the Drawings

[0010] [Figure 1] It is a schematic block diagram showing the system configuration of a search support system according to an embodiment. [Figure 2] It is a schematic block diagram showing a specific example of the functional configuration of a terminal device according to an embodiment. [Figure 3] It is a schematic block diagram showing a specific example of the functional configuration of a search support device according to an embodiment. [Figure 4] It is a diagram showing a specific example of related information stored in a related information database according to an embodiment. [Figure 5] It is a diagram showing a specific example of parameter information stored in a parameter storage unit according to an embodiment. [Figure 6] It is a flowchart showing a specific example of a search support process executed by a search support device according to an embodiment. [Figure 7] It is a diagram showing an example of a prompt according to an embodiment. [Figure 8] It is a diagram showing an example of a dialogue screen according to an embodiment. [Figure 9] It is a diagram showing an example of a dialogue screen according to an embodiment. [Figure 10] It is a diagram showing an example of a dialogue screen according to an embodiment. [Figure 11] It is a diagram showing an example of a dialogue screen according to an embodiment. [Figure 12] It is a diagram showing an example of a dialogue screen according to an embodiment. [Figure 13] It is a diagram showing a modified example of a search support device.

Modes for Carrying Out the Invention

[0011] Hereinafter, a search support system, a search support method, and a program according to an embodiment of the present invention will be described with reference to the drawings.

[0012] <Configuration of Search Support System 100> FIG. 1 is a schematic block diagram showing the system configuration of the search support system 100 according to the present embodiment. The search support system 100 is an information processing system that provides a search support function for assisting a user's search in an existing search system (e.g., a search site, a search API (Application Programming Interface), a search database, etc.) for searching for an object (e.g., a product, a job offer, a residence, etc.). Hereinafter, a case where the search of a user is assisted in a search site for searching for a product will be described as an example.

[0013] The search support system 100 includes a terminal device 10, a search support device 20, and a generation AI device 30. The search support device 20 is communicably connected to the terminal device 10 and the generation AI device 30 via a network N. The network N may be a network using wireless communication or a network using wired communication. The network N may be any one of the Internet, a public land mobile network (PLMN), a local area network (LAN), a virtual private network (VPN), etc., or any combination thereof.

[0014] The terminal device 10 is an information terminal operated by a user. The terminal device 10 is configured using an information device such as a smartphone, a tablet, a personal computer, a dedicated device, etc.

[0015] The search support device 20 is a device that assists a user's search in a search site. The search support device 20 is configured using an information processing device such as one or more personal computers or server devices. The search support device 20 may be a cloud server arranged on so-called cloud.

[0016] The generation AI device 30 is a device that provides the function of generation AI (Artificial Intelligence) by outputting data in response to prompts. The generation AI device 30 is composed of one or more information processing devices such as personal computers or server devices. The generation AI device 30 may also be a cloud server located on a so-called cloud. The generating AI provided by the generating AI device 30 may, for example, use an LLM (Large Language Model). For example, Claude, GPT-4 (registered trademark), Llama2, PaLM2, etc., can be used as generating AIs. The generating AI may have been pre-trained on related information described later (for example, FAQs (Frequently Asked Questions) of the target search site, laws and regulations related to the product, product information including product specifications and specs, etc.).

[0017] <Configuration of terminal device 10> Figure 2 is a schematic block diagram showing a specific example of the functional configuration of the terminal device 10 according to this embodiment. The terminal device 10 comprises a communication unit 11, an input unit 12, a display unit 13, a storage unit 14, and a control unit 15.

[0018] The communication unit 11 is a communication device. The communication unit 11 may be configured, for example, as a network interface. The communication unit 11 communicates data with other devices via the network N in accordance with the control of the control unit 15. The communication unit 11 may be a device that performs wireless communication or a device that performs wired communication.

[0019] The input unit 12 is configured using existing input devices such as a keyboard, pointing device (mouse, tablet, etc.), buttons, or touch panel. The input unit 12 is operated by the user when inputting user instructions to the terminal device 10. The input unit 12 may also be an interface for connecting the input device to the terminal device 10. In this case, the input unit 12 inputs the input signal generated in the input device in response to the user's input to the terminal device 10. The input unit 12 may also be configured using a microphone and a speech recognition device. In this case, the input unit 12 acquires the acoustic signal generated by the user's speech, performs speech recognition on the words spoken by the user, and inputs the recognized string information to the terminal device 10. The speech recognition process may be performed by the control unit 15. The input unit 12 may be configured in any way that allows user instructions to be input to the terminal device 10.

[0020] The display unit 13 displays information in a format that is recognizable to the user. The display unit 13 may be an image display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The display unit 13 may also be an interface for connecting the image display device to the terminal device 10. In this case, the display unit 13 generates a video signal for displaying image data and outputs the video signal to the image display device connected to it. The display unit 13 may also be configured as a touch panel integrated with the input unit 12.

[0021] The storage unit 14 has the function of storing various types of information. The storage unit 14 is composed of storage media provided as hardware by the terminal device 10, such as an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), RAM (Random Access Memory), ROM (Read Only Memory), or any combination of these storage media. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data necessary when the control unit 15 performs processing.

[0022] The control unit 15 is composed of a processor such as a CPU (Central Processing Unit) and memory (main memory). The control unit 15 functions when the processor executes a program. Note that all or part of the functions of the control unit 15 may be implemented using hardware such as an ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), or FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor memory devices (e.g., SSDs: Solid State Drives), as well as storage devices such as hard disks and semiconductor memory devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0023] The control unit 15 may, for example, execute an application installed on its own device (terminal device 10). A specific example of such an application is an application provided to the terminal device 10 as a dedicated application for the search support system 100. Another specific example of such an application is a web browser application. Such an application may be pre-installed on the terminal device 10, or it may be downloaded each time the search support processing described later is executed. For example, if it is implemented as a web browser application, the terminal device 10 may download and execute the application from a device specified by the web server (for example, the web server itself or another server) when the terminal device 10 connects to a specific web server. The control unit 15 operates according to the program of the application being executed.

[0024] The control unit 15 controls the terminal device 10 in response to user operations and information received from the search support device 20. For example, the control unit 15 transmits information entered by the user through the input unit 12 to the search support device 20 using the communication unit 11. For example, when the control unit 15 receives information transmitted from the search support device 20 via the network N to the communication unit 11, it generates screen data based on the received information and displays the screen data on the display unit 13. Such screen data includes images and characters that represent the information transmitted from the search support device 20.

[0025] <Configuration of the search support device 20> Figure 3 is a schematic block diagram showing a specific example of the functional configuration of the search support device 20 according to this embodiment. The search support device 20 comprises a communication unit 21, a storage unit 22, and a control unit 23.

[0026] The communication unit 21 is a communication device. The communication unit 21 may be configured, for example, as a network interface. The communication unit 21 communicates data with other devices via the network N in accordance with the control of the control unit 23. The communication unit 21 may be a wireless communication device or a wired communication device.

[0027] The storage unit 22 has the function of storing various types of information. The storage unit 22 is composed of storage media provided as hardware by the search support device 20, such as an HDD, SSD, flash memory, EEPROM, RAM, ROM, or any combination of these storage media. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may function, for example, as a related information database 221, a vector database 222, a vector generation model storage unit 223, and a parameter storage unit 224.

[0028] The related information database 221 stores related information related to the product being searched. This related information includes laws and regulations related to the product (for example, laws and regulations related to valves if the product is a valve), FAQs on the search site (questions and answers about the product), and product information for each of the multiple products being searched. The product information includes at least the product's specifications or features (i.e., parameters that can be set as search conditions on the search site). Each of the multiple related information entries is assigned a related information ID to identify it.

[0029] (Related information) Figure 4 shows a specific example of related information stored in the related information database 221 according to this embodiment. This figure shows an example of related information in which FAQ questions and their answers from a search site are associated and converted into tabular data.

[0030] Returning to Figure 3, the vector database 222 stores the vector information obtained by vectorizing each of the multiple related pieces of information, associating it with the related information ID.

[0031] The vector generation model storage unit 223 stores the vector generation model used by the vector transformation unit 232 (described later) when transforming data into vectors. The vector generation model is an AI model that takes text or image data as input and outputs a vector obtained by transforming the input data into vectors. The vector generation model may be, for example, an embedded model. The vector generation model may be constructed using information from a trained model that has been generated in advance by a training process based on related information stored in the related information database 221. Such a training process may be performed by another device, for example, or by the device itself (search support device 20). For example, the vector generation model may be fine-tuned to perform vector transformations suitable for the categories of related information stored in the related information database 221.

[0032] The parameter storage unit 224 stores parameters that can be set as search conditions on the target search site (parameters provided as filtering conditions).

[0033] (Parameter information) Figure 5 shows a specific example of parameter information stored by the parameter storage unit 224 according to this embodiment. The parameter storage unit 224 has a plurality of parameter information records. Each parameter information record contains parameter information, such as a parameter name and a parameter value. The parameter name is the name of the parameter. The parameter value is a value or range that can be set for the parameter. In the example shown in Figure 5, parameters that can be set when searching for the product "valve" include "valve type," "body material," "nominal pressure," "pipe connection," and "operation."

[0034] Returning to Figure 3, the control unit 23 is configured using a processor such as a CPU and memory. The control unit 23 functions as a receiving unit 231, a vector conversion unit 232, an extraction unit 233, a generation unit 234, an output processing unit 235, a search unit 236, and an update unit 237 when the processor executes a program. Note that all or part of each function of the control unit 23 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0035] The reception unit 231 accepts product search criteria (hereinafter sometimes referred to as "user input criteria") from the user in natural language. For example, the reception unit 231 may display an input screen for entering user input criteria on the display unit 13 of the terminal device 10. The reception unit 231 may also accept user input criteria from the user through a chat UI (User Interface) that interacts with the user.

[0036] The vector transformation unit 232 transforms the input user input conditions into vectors. For example, the vector transformation unit 232 inputs the user input conditions into a vector generation model and obtains the vectorized user input conditions output from the vector generation model.

[0037] The extraction unit 233 extracts relevant information corresponding to the user input conditions. For example, the extraction unit 233 extracts relevant information that can serve as the basis for setting the parameters of the search conditions. Specifically, the extraction unit 233 searches the vector database 222 for relevant information IDs that are similar to the vectorized user input conditions. At this time, the extraction unit 233 obtains the similarity between the user input conditions and the relevant information by calculating the similarity between the vectors. For example, cosine similarity or the Jacquard coefficient method may be used to calculate the similarity between the vectors. Also, if the vectors consist of multiple or high-dimensional quantities, weighting of each vector or element may be considered. The extraction unit 233 reads the relevant information corresponding to the retrieved relevant information ID from the relevant information database 221.

[0038] The generation unit 234 generates one or more parameter-based search conditions and the reasons for those search conditions, which correspond to the user input conditions and can be used for refined searches on the search site, based on the extracted related information. Specifically, the generation unit 234 generates parameter-based search conditions and the reasons for those search conditions by inputting a prompt containing the user input conditions and the extracted related information into the generation AI of the generation AI device 30.

[0039] The output processing unit 235 outputs the generated search conditions and the reasons for using those search conditions. For example, the output processing unit 235 displays the generated search conditions and the reasons for using those search conditions on the display unit 13 of the terminal device 10 (for example, on the chat UI). Alternatively, the output processing unit 235 may transmit data indicating the generated search conditions and the reasons for using those search conditions to the terminal device 10 or other server devices via the communication unit 11.

[0040] When the search unit 236 receives an instruction input from the user to search for products using the outputted search conditions, it searches for products on the search site using the outputted search conditions.

[0041] The update unit 237 updates the vector information stored in the vector database 222 based on the updated related information when there is an update to the related information in the related information database 221. In addition, if there is an update in the related information database 221 that exceeds a predetermined amount, the update unit 237 may perform additional training of the vector generation model based on the updated related information (for example, added related information).

[0042] <Processing flow of the search support device 20> Next, with reference to Figures 6 to 12, the processing flow of the search support device 20 according to this embodiment will be described. Figure 6 is a flowchart showing a specific example of the search support processing performed by the search support device 20 according to this embodiment. Below, the case of searching for products will be described using the example of the search target being valves. In this example, the vector generation model is fine-tuned to pre-learn related information for the product category "valves" and output vectors based on the learned related information. In addition, the generation AI of the generation AI device 30 may be fine-tuned to pre-learn related information for the product category "valves" and output based on the learned related information.

[0043] First, the reception unit 231 receives product search criteria (user input criteria) from the user in natural language (step S101). For example, the reception unit 231 may display a dialogue screen providing a chat UI on the display unit 13 of the terminal device 10.

[0044] Next, the vector conversion unit 232 converts the input user input conditions into vectors (step S102).

[0045] Next, the extraction unit 233 refers to the vector database 222 to search for related information IDs of related information similar to the vectorized user input conditions (step S103). Then, the extraction unit 233 reads the related information corresponding to the searched related information ID from the related information database 221.

[0046] Next, the generation unit 234 generates prompts to be input to the generation AI based on the extracted relevant information and user input conditions (step S104).

[0047] (prompt) Figure 7 shows an example of a prompt according to this embodiment. The prompt 700 includes user input conditions, extracted relevant information, the role of the generating AI (e.g., "assist with the search"), specific instructions (e.g., "present search conditions with reasons"), and parameters (parameter names and configurable parameter values) that can be used as filtering conditions on the search site. In the example shown in Figure 7, the prompt 700 includes the role of the generating AI, "You are an AI that assists in searching for valve manufacturers. Specifically, you are a chatbot that will respond to my input with search conditions for https: / / xxxx.yyyy.zzzz / ," and specific instructions, "This search system allows you to specify the following parameters as 'refining conditions' for your search. Interpret the user's input and present search conditions that you believe will match, along with the reasons." The search target "search for bubble manufacturers" 710 and the URL of the search site "https: / / xxxx.yyyy.zzzz / " 720 are set to different values ​​for each target search site. The generation unit 234 also refers to the parameter storage unit 224 and includes parameters (parameter names and configurable parameter values) 730 that can be specified as refinement conditions for the target search site in the prompt 700. By generating such a prompt, the generating AI can be made to generate search conditions that allow for refined searches on the target search site.

[0048] Returning to Figure 6, the generation unit 234 then inputs the generated prompt to the generation AI of the generation AI device 30, thereby generating search conditions based on parameters and the reasons for those search conditions (step S105).

[0049] Next, the output processing unit 235 outputs the generated search conditions and the reasons for using those search conditions (step S106). For example, the output processing unit 235 may display the generated search conditions and the reasons for using those search conditions on the dialogue screen providing the chat UI, which is displayed on the display unit 13 of the terminal device 10.

[0050] (Dialogue screen) Figures 8 to 12 show an example of a dialogue screen 800 according to this embodiment. The dialogue screen 800 provides a chat UI to assist the user in searching. The dialogue screen 800 includes an input area 810 that accepts natural language input from the user, and a display area 820 that displays the dialogue between the user and the assistant chat that assists in searching. The input area 810 may also display a guide that serves as a clue for input (for example, a question or search conditions, etc.) (for example, if you input the intended use, material, question content, etc., the AI ​​will suggest recommended search conditions. Example: "Water purification facility", "Food"). The user inputs the search conditions in natural language into the input area 810 using the guide as a clue. The output processing unit 235 displays the reason section 821 and the refinement condition suggestion section 822 in the display area 820 according to the user input conditions. The output processing unit 235 displays the reason for the generated search conditions in the reason section 821. The output processing unit 235 also displays the generated search conditions in the refinement condition suggestion section 822.

[0051] In the example shown in Figure 8, in response to the user input condition "I want a valve that can be used in a food production line," the output processing unit 235 displays the reason "Stainless steel is recommended for its corrosion resistance. For reference, the Food Sanitation Law has provisions such as 'prohibition of metals containing lead and antimony, and prohibition of structures that allow copper and lead to be scraped'" in the reason section 821, and displays the generated search condition "'Body material' is 'stainless steel'" in the refinement condition suggestion section 822.

[0052] In the example shown in Figure 9, in response to the user input condition "valves in water treatment facilities," the output processing unit 235 displays the reason "Valves in water treatment facilities must be compliant with water supply facility leaching standards. The following custom orders are available: Stainless steel valves, cast iron valves, stainless steel ball valves, stainless steel butterfly valves" in the reason section 821, and displays the generated search condition "Model number is "A1111"" in the refinement condition suggestion section 822.

[0053] In the example shown in Figure 10, in response to the user input condition "I want a valve that can adjust the gas flow rate," the output processing unit 235 displays the reason "For applications that require fine adjustment of flow rate, 'needle valves' and 'globe valves' with structures suitable for flow rate control are suitable. These allow for easy adjustment of the opening degree and stable control of fluids such as gas. Also, since gas requires airtightness, highly airtight connection methods such as 'threaded type' and 'flange type' are preferred." in the reason section 821, and displays the generated search conditions "'Valve type' as 'needle' or 'globe', 'Pipe connection' as 'threaded type' or 'flange type'" in the refinement condition suggestion section 822.

[0054] In the example shown in Figure 11, in response to the user input condition "I want to create a line for transporting chocolate. Please tell me what valve is appropriate," the output processing unit 235 displays the reason "When handling highly viscous foods like chocolate, which require strict hygiene management, stainless steel valves, which have high sanitary properties (cleanability and washability) and are resistant to corrosion, are suitable. Also, because chocolate solidifies easily, ball valves and butterfly valves, which have smooth flow paths and are less likely to become blocked, are often used. These can secure relatively wide flow paths and are suitable for the passage of highly viscous substances." in the reason unit 821, and displays the generated search conditions "Valve type" as "Ball" or "Butterfly" and "Body material" as "Stainless steel" in the refinement condition suggestion unit 822.

[0055] In the example shown in Figure 12, in response to the user input condition "I want a valve that can be used in a high-temperature steam line," the output processing unit 235 displays the reason "High heat resistance and pressure resistance are required for high-temperature steam, so valves made of 'cast steel' or 'ductile cast iron' are suitable. Furthermore, 'globe valves' are often used for steam control. In addition, the nominal pressure is often JIS '10K' or '20K'." in the reason section 821, and displays the generated search conditions "'Valve type': 'Globe', 'Body material': 'Cast steel' or 'Ductile', 'Nominal pressure': 'JIS 10K' or 'PN 20'" in the refinement condition suggestion section 822.

[0056] Furthermore, the output processing unit 235 displays a search button 823 (user interface) that accepts instruction input from the user to apply the search conditions displayed in the narrowing condition suggestion unit 822 to the search site (alternative input of search conditions for the search site).

[0057] Returning to Figure 6, the search unit 236 determines whether it has received an instruction input from the user to apply the search conditions displayed in the filtering condition suggestion unit 822 to perform a search (for example, by pressing the search button 823) (step S107). If the control unit 23 has not received a search instruction input from the user (step S107: No), it terminates the process.

[0058] On the other hand, when the search unit 236 receives a search instruction input from the user (step S107: Yes), it searches for products by applying the search conditions displayed in the refinement condition suggestion unit 822 to the search site by inputting the search conditions displayed in the refinement condition suggestion unit 822 (step S108).

[0059] The output processing unit 235 outputs the search results from step S108 (step S109). For example, the output processing unit 235 displays the search results on the display unit 13 of the terminal device 10. After that, the process ends.

[0060] As described above, the search support system 100 according to this embodiment includes a parameter storage unit 224 that stores parameters that can be set as search conditions in the object search system, a related information database 221 that stores related information related to the object, a reception unit 231 that receives search conditions input from the user in natural language, an extraction unit 233 that extracts related information corresponding to the input search conditions by referring to the related information database, a generation unit 234 that generates parameter-based search conditions corresponding to the input search conditions based on the extracted related information, and an output processing unit 235 that outputs the generated search conditions.

[0061] With this configuration, the search support system 100 according to this embodiment can assist the user's search by presenting appropriate search conditions for refined searches in a search system that allows searching using parameters. As a result, users can understand what parameters to set in the search system to perform refined searches. This enables users who were previously unable to use refined searches to do so, and allows them to make more effective use of existing search systems.

[0062] Furthermore, the search support system 100 according to this embodiment further includes a search unit 236 that performs a search using the outputted search conditions when the user gives an instruction to perform a search using the outputted search conditions. With this configuration, the search support system 100 automatically searches for the target object in the search system by inputting the outputted search conditions into the search system in response to the user's instruction input. This eliminates the need for the user to manually input search conditions into the search system when performing a search.

[0063] Furthermore, the search support system 100 according to this embodiment further includes a vector database 222 that stores vector information obtained by vectorizing related information, and searches for related information corresponding to the input search conditions by referring to the vector database 222. This makes it possible to extract related information corresponding to the search conditions entered by the user with greater accuracy.

[0064] Furthermore, the search support system 100 according to this embodiment generates parameterized search conditions by inputting prompts containing the entered search conditions and extracted related information into the generating AI. This makes it possible to present answers that are formatted into more appropriate words in response to the search conditions entered by the user.

[0065] Furthermore, the search support system 100 according to this embodiment accepts input from the user of search conditions including the use or conditions of the target object (e.g., a product), and generates search conditions with parameters set to suit the use or conditions. With this configuration, the search support system 100 according to this embodiment can convert wording indicating the user's intention to find what they want into search conditions with parameter settings to be given to the search system. In this way, it can indirectly support the user's search.

[0066] In the embodiments described above, the example of searching for products on a product search site was used, but the present invention is not limited to this and can also be applied to comparison search sites for job postings (e.g., employment or career change), housing, etc.

[0067] Furthermore, in the embodiments described above, the search support device 20 provides the search support function as a chat UI for a website, but it is not limited to this, and for example, the search support function may be provided as an "API that takes text as an argument and outputs text." Also, the input UI does not necessarily have to be in text chat format; for example, it may be voice input.

[0068] (modified version) In this embodiment, the terminal device 10 and the search support device 20 are configured as separate devices, but they may be configured as a single integrated device. Figure 13 shows a modified example of the search support device 20 configured in this way. The search support device 20 shown in Figure 13 includes an input unit 24 and an output unit 25. The input unit 24 and output unit 25 of the search support device 20 shown in Figure 13 function similarly to the input unit 12 and display unit 13 of the terminal device 10, respectively. The control unit 23 operates in response to operations on the input unit 24, performs search support processing using the input information, and outputs the information using the output unit 25.

[0069] Furthermore, the search support device 20 may be implemented using multiple information processing devices. For example, the search support device 20 may be implemented using a cloud or other similar device. For example, in the search support device 20, the storage unit 22 and the control unit 23 may be implemented on different information processing devices. For example, the related information database 221, vector database 222, vector generation model storage unit 223, and parameter storage unit 224 of the storage unit 22 of the search support device 20 may be distributed and implemented on multiple information processing devices.

[0070] Some or all of the functions of the search support device 20 in the above-described embodiment may be implemented by a computer. In that case, the functions may be implemented by recording a program for implementing these functions on a computer-readable recording medium, loading the program recorded on this recording medium into a computer system, and executing it. Here, "computer system" includes hardware such as an OS and peripheral devices. Furthermore, "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and storage devices such as hard disks built into a computer system. Moreover, "computer-readable recording medium" may also include those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and those that hold programs for a certain period of time, such as volatile memory inside a computer system that acts as a server or client in such a case. Furthermore, the above-mentioned program may be for implementing some of the functions described above, or it may be a program that can implement the above-mentioned functions in combination with a program already recorded in the computer system, or it may be implemented using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0071] Although embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. [Explanation of symbols]

[0072] 100 Search Support Systems 10 Terminal devices 11 Communications Department 12 Input section 13 Display section 14 Storage section 15 Control Unit 20 Search support device 21 Communications Department 22 Memory section 221 Related Information Database 222 Vector Databases 223 Vector generation model memory 224 Parameter Storage Unit 23 Control Unit 231 Reception Department 232 Vector Transformation Unit 233 Extraction part 234 Generation part 235 Output Processing Unit 236 Search Section 237 Update Department

Claims

1. A parameter storage unit that stores parameters that can be set as search conditions in an object search system, A related information database that stores related information related to the aforementioned object, A reception area that accepts search criteria input from users in natural language, An extraction unit that extracts related information corresponding to the input search conditions by referring to the related information database, A generation unit generates search conditions using the parameters corresponding to the input search conditions based on the extracted related information, An output processing unit that outputs the generated search conditions, Equipped with, The aforementioned related information includes at least one of the following: laws and regulations relating to the subject object or questions and answers regarding the subject object, and parameters of the subject object. The reception unit receives input from the user, including the intended use of the object. The generation unit, by referring to the parameter storage unit, generates a prompt that includes parameters that can be set as search conditions in the object search system, which provides instructions to present search conditions using the parameters that would match the input search conditions, along with reasons; a prompt that includes the input search conditions and the extracted related information; and by inputting the generated prompt to the generation AI, generates search conditions using the parameters and the reasons for choosing those search conditions. The output processing unit outputs the generated search conditions and the reason for using those search conditions. Search assistance system.

2. When the user gives an instruction to perform a search using the outputted search conditions, the search system further includes a search unit that performs a search using the outputted search conditions. The search support system according to claim 1.

3. The system further includes a vector database that stores vector information obtained by vectorizing the aforementioned related information, The extraction unit refers to the vector database to search for relevant information corresponding to the input search conditions. The search support system according to claim 1.

4. A search support method executed by a computer used in a search support system that includes a parameter storage unit for storing parameters that can be set as search conditions in a search system for objects, It accepts search criteria from users in natural language. Referencing a related information database that stores related information related to the aforementioned object, extract related information corresponding to the entered search conditions. Based on the extracted related information, a search condition corresponding to the input search condition is generated using the parameters. Output the search conditions generated above. This is a search support method that includes the following: The aforementioned related information includes at least one of the following: laws and regulations relating to the subject object or questions and answers regarding the subject object, and parameters of the subject object. Accepting the input of the aforementioned search conditions includes accepting from the user the input of search conditions including the use of the aforementioned object, Generating search conditions using the aforementioned parameters includes, by referring to the parameter storage unit, generating a prompt that includes parameters that can be set as search conditions in the object search system, which presents search conditions using the aforementioned parameters that would match the input search conditions, along with the reasons for doing so; generating a prompt that includes the input search conditions and the extracted related information; and by inputting the generated prompt into the generating AI, generating the search conditions using the aforementioned parameters and the reasons for choosing those search conditions. Outputting the aforementioned search conditions includes outputting the generated search conditions and the reasons for using those search conditions. Search support methods.

5. A computer used in a search support system that includes a parameter storage unit for storing parameters that can be set as search conditions in a search system for objects, It accepts search criteria from users in natural language. Referencing a related information database that stores related information related to the aforementioned object, extract related information corresponding to the entered search conditions. Based on the extracted related information, a search condition corresponding to the input search condition is generated using the parameters. Output the search conditions generated above. It is a program that makes something happen. The aforementioned related information includes at least one of the following: laws and regulations relating to the subject object or questions and answers regarding the subject object, and parameters of the subject object. Accepting the input of the aforementioned search conditions includes accepting from the user the input of search conditions including the use of the aforementioned object, Generating search conditions using the aforementioned parameters includes, by referring to the parameter storage unit, generating a prompt that includes parameters that can be set as search conditions in the object search system, which presents search conditions using the aforementioned parameters that would match the input search conditions, along with the reasons for doing so; generating a prompt that includes the input search conditions and the extracted related information; and by inputting the generated prompt into the generating AI, generating the search conditions using the aforementioned parameters and the reasons for choosing those search conditions. Outputting the aforementioned search conditions includes outputting the generated search conditions and the reasons for using those search conditions. program.

Images