Information processing methods, information processing systems, and programs

Abstract

To provide an information processing method, information processing system, and program that more efficiently acquire and summarize the latest personal information. [Solution] The information processing method includes the steps of: having a server device search for web pages on the internet using a search engine with target person information indicating the target person as a keyword; obtaining information from the web pages as a search result; and generating a prompt that includes N lines of data before and after the information matching the keyword's name from the web page information. N is a natural number less than or equal to a predetermined value. The prompt further includes instructions to summarize the web page information and generate a business profile.

Description

Technical Field

[0006] , , ,

[0001] The present invention relates to an information processing method, an information processing system, and a program.

Background Art

[0002] Conventionally, web searches have been performed manually to update or acquire personal information.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to more efficiently obtain and summarize the latest personal information.

Means for Solving the Problems

[0005] According to one aspect of the present disclosure, an information processing method executed by an information processing system is provided. The information processing method includes a step of searching for web pages on the Internet using a search engine with target person information indicating a target person as a keyword, a step of obtaining information of the web pages as search results, and a step of generating a prompt including data of N lines before and after information matching the keyword among the information of the web pages. N is a natural number less than or equal to a predetermined value. The prompt further includes an instruction to summarize the information of the web pages and generate a business profile.

Brief Description of the Drawings

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the system configuration of an information processing system. [Figure 2] FIG. 2 is a diagram showing an example of the hardware configuration of a server device. [Figure 3] Figure 3 shows an example of the hardware configuration of a client device. [Figure 4] Figure 4 shows an example of the functional configuration of a server device. [Figure 5] Figure 5 is a sequence diagram (part 1) showing an example of information processing in an information processing system. [Figure 6] Figure 6 is an example of a search screen (part 1). [Figure 7] Figure 7 illustrates the process of interpolating data into streaming data. [Figure 8] Figure 8 shows an example of the screen transitions displayed on the client device when the processing from sequence SQ550 to sequence SQ575 is executed repeatedly. [Figure 9] Figure 9 is a sequence diagram (part 2) showing an example of information processing in an information processing system. [Figure 10] Figure 10 is a diagram (part 2) showing an example of a search screen. [Figure 11] Figure 11 shows an example of a search screen that includes name selection options. [Modes for carrying out the invention]

[0007] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0008] <Embodiment 1> 1. System Configuration Diagram Figure 1 shows an example of the system configuration of the information processing system 1000. As shown in Figure 1, the information processing system 1000 includes, as a system configuration, a server device 100, a client device 110, a search service providing server device 130, and an LLM service providing server device 140.

[0009] The server device 100, the client device 110, the search service providing server device 130, and the LLM service providing server device 140 are connected to each other via a network 150. The network 150 includes a WAN (Wide Area Network), a LAN (Local Area Network), and the Internet, or any combination thereof. The network 150 includes wired networks and wireless networks.

[0010] Information processing system 1000 is a system that collects information from the Web, summarizes the background and job details of business partners and other individuals entered, and provides a service for outputting this information.

[0011] The server device 100 is a server device that provides the main functions of the information processing system 1000. The main processes described below are performed by the server device 100.

[0012] The client device 110 is a client device that displays screens as shown in Figures 6 and 8, which will be described later.

[0013] The search service server device 130 is a server device that provides search services. A search service is a service that provides users with search functionality using a search engine. For simplicity, the search service server device 130 will also be referred to simply as the search engine 130 below.

[0014] The LLM service providing server device 140 is a server device that provides LLM (Large Language Models) services. The LLM service is a general term for services that utilize artificial intelligence technology called large language models (LLMs). A large language model is an advanced artificial intelligence model that can generate natural-like sentences, answer questions, and translate texts by learning a large amount of text data. A large language model can also be said to be a trained model that has learned a large-scale language model. For simplicity, hereinafter, the LLM service providing server device 140 may also be simply referred to as LLM140. Also, for simplicity of explanation in the specification, the description will be given taking LLM140 as an example. However, instead of the LLM, for example, a trained model of a multimodal model may be used. A multimodal model is an artificial intelligence model that can simultaneously process different types of data such as text, images, and voices. A multimodal model can also be said to be a trained model that has learned a large-scale language model, an image model, and a voice model respectively. By using the trained model of the multimodal model, not only text information but also web images included in web pages and the like can be handled.

[0015] Here, the information processing system described in the claims may be composed of a plurality of devices or may be composed of a single device. When the information processing system described in the claims is composed of a single device, an example of such a device is the server device 100. When the information processing system described in the claims is composed of a plurality of devices, examples of the plurality of devices include a cloud server composed of a plurality of server devices that provide the functions of the server device 100, or the server device 100 and the LLM service providing server device 140, etc.

[0016] 2. Hardware Configuration (1) Hardware Configuration of Server Device 100 Figure 2 is a diagram showing an example of the hardware configuration of the server device 100. As shown in FIG. 2, the server device 100 includes, as a hardware configuration, a control unit 210, a storage unit 220, a communication unit 230, and an internal bus 240. The control unit 210, the storage unit 220, and the communication unit 230 are electrically connected via the internal bus 240.

[0017] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire server device 100.

[0018] The storage unit 220 is any one of an HDD (Hard Disk Drive), a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid Sate Drive), or any combination thereof, and stores programs, data used when the control unit 210 executes processing based on the programs, and the like. The storage unit 220 is an example of a storage medium. Examples of the data used when the control unit 210 executes processing based on the programs include, for example, search results described later, streaming data, data in a generated display format, and the like. In the following, the server device 100 will be described as having a ROM, a RAM, an HDD, and an SSD as storage units.

[0019] In the specification, it is described that the data used when the control unit 210 executes processing based on the programs is stored in the storage unit 220, but it may be stored in the storage unit of another device communicable with the server device 100. The data may be stored in the storage unit of any device as long as the control unit 210 can refer to or acquire it. By the control unit 210 executing processing based on the programs stored in the storage unit 220, the functional configuration of FIG. 4 described later, the processing of the server device 100 in the sequence diagrams shown in FIGS. 5 and 9 described later, and the like are realized.

[0020] The communication unit 230 connects the server device 100 to the network 150 and controls communication with other devices.

[0021] The hardware configuration of the search service server device 130 and the LLM service server device 140 is the same as the hardware configuration of server device 100.

[0022] Note that the hardware configurations of the control unit 210, storage unit 220, and communication unit 230 are not limited to one. For example, multiple control units may be included in the server device 100. The same applies to the search service providing server device 130 and the LLM service providing server device 140. The same also applies to the client device 110, etc., shown below.

[0023] (2) Hardware configuration of client device 110 Figure 3 shows an example of the hardware configuration of the client device 110. As shown in Figure 3, the client device 110 includes, as a hardware configuration, a control unit 310, a storage unit 320, an input unit 330, an output unit 340, a communication unit 350, and an internal bus 360. The control unit 310, the storage unit 320, the input unit 330, the output unit 340, and the communication unit 350 are electrically connected via the internal bus 360.

[0024] The control unit 310 is a CPU or the like, and controls the entire client device 110.

[0025] The storage unit 320 is one of the following: HDD, ROM, RAM, SSD, etc., or any combination thereof, and stores programs, data used by the control unit 310 when executing processing based on the programs, etc. The storage unit 320 is an example of a storage medium.

[0026] In this specification, the data used by the control unit 310 when executing processing based on the program is described as being stored in the storage unit 320, but it may also be stored in the storage unit of another device that can communicate with the client device 110. The data may be stored in the storage unit of any device as long as the control unit 310 can access or retrieve it. The functions of the client device 110 are realized when the control unit 310 executes processing based on the program stored in the storage unit 320.

[0027] The input unit 330 is a device that inputs information to the client device 110 in response to the operator's operation. The input unit 330 receives operation input made by the operator. The operation input is transferred to the control unit 310 via the internal bus 360 as a command signal. The control unit 310 can, if necessary, perform predetermined control and / or calculations based on the transferred command signal. The input unit 330 may be included in the housing of the client device 110 or it may be externally mounted. For example, the input unit 330 may be implemented as a touch panel integrated with the output unit 340. When the input unit 330 is implemented as a touch panel, the operator can input tap operations, swipe operations, etc. to the input unit 330. Instead of a touch panel, the input unit 330 can be a switch button, mouse, trackpad, keyboard, etc.

[0028] The output unit 340 is, for example, a display unit, which outputs (displays) information as a screen of a graphical user interface (GUI) that can be operated by an operator. The output unit 340 may be included in the housing of the client device 110 or it may be externally attached. More specifically, the output unit 340 may be implemented as a display device such as a liquid crystal display, an organic EL (Electron-Luminescence) display, or a plasma display. It is preferable that these display devices be used according to the type of client device 110.

[0029] The communications unit 350 connects the client device 110 to the network 150 and manages communication with other devices.

[0030] For the purposes of this explanation, we will use a notebook PC (Personal Computer) as an example of a client device. However, the client device may also be a smartphone, tablet computer, desktop computer, etc.

[0031] 3. Functional Configuration Figure 4 shows an example of the functional configuration of the server device 100. As shown in Figure 4, the server device 100 includes, as a functional configuration, a display control unit 410, a search control unit 420, an LLM interface unit 430, and a data completion unit 440.

[0032] The display control unit 410 controls the display of the screen on the client device 110. For example, the display control unit 410 asynchronously renders the JSON (JavaScript Object Notation) data, which has been supplemented by the data supplementation unit 440, into HTML (HyperText Markup Language) and controls it to display it sequentially on the client device 110. The search control unit 420 uses the search engine 130 to search for web pages on the internet.

[0033] The LLM interface unit 430 provides an interface for using the LLM140. The LLM interface unit 430 generates prompts, sends them to the LLM140 (or inputs them to the LLM140), and receives data output from the LLM140 (or receives data from the LLM140). The data completion unit 440 completes the streaming data output by the LLM140. For example, the data completion unit 440 parses the JSON format data output by the LLM140 and completes the data so that it is valid as JSON.

[0034] 4. Information Processing The information processing of Embodiment 1 will be described below.

[0035] (1) Overview of the process The search control unit 420 uses the search engine 130 to search for web pages on the internet using the company name and individual name as keywords. The company name and individual name are examples of target person information that indicate the target person. The search control unit 420 obtains web page information as search results. The LLM interface unit 430 generates a prompt that includes N lines of data before and after the information matching the keywords from the obtained web page information. N is a natural number less than or equal to a predetermined value. More specific examples of N include, for example, 2 or 3. N may be set in advance in the program, or it may be written in a predetermined file such as the storage unit 220 in the form of a definition file. The prompt generated by the LLM interface unit 430 further includes an instruction to summarize the web page information and generate a business profile, and information that the generated information will be output via streaming.

[0036] By performing this type of processing, it becomes possible to acquire and summarize the latest personal information more efficiently.

[0037] (2) Details of the process (Part 1) The details of information processing in the information processing system 1000 will be explained using the sequence diagram in Figure 5. First, to simplify the explanation, we will describe the details of information processing in the information processing system 1000 assuming that the company name and individual name to be searched are entered. Figure 5 is a sequence diagram (part 1) showing an example of information processing in the information processing system 1000.

[0038] In sequence SQ510, the display control unit 410 receives a request from the client device 110 to display a search screen. In sequence SQ515, the display control unit 410 generates a search screen in response to a display request, or retrieves a search screen that has been previously generated and stored in the storage unit 220 or the like in response to a display request, and transmits it to the requesting client device 110. In sequence SQ520, the control unit 310 of the client device 110 displays a search screen on the output unit 340.

[0039] Figure 6 is an example (part 1) of the search screen 600. The search screen 600 is a screen for entering keywords. It can also be said that the search screen 600 is a screen for entering search criteria related to the person from whom the business profile described later was generated. The search screen 600 includes an input field 610 for entering the name of the company to which the person belongs, an input field 620 for entering the surname or given name, and a generate button 630. In the example explained using Figures 5 and 6, it is assumed that the given name is entered in input field 620.

[0040] When a company name is entered in the input area 610 and a person's name in the input area 620 of the search screen 600, and the generate button 630 is selected, a search request is sent from the client device 110 to the server device 100. In sequence SQ525, the search control unit 420 receives the search request from the client device 110 and retrieves the company name and person's name included in the search request.

[0041] In sequence SQ530, the search control unit 420 uses the search engine 130 to search for web pages on the internet using the acquired company name and personal name as keywords. A web page is a single unit of information on the internet. A web page contains various elements such as text, images, and videos, and is displayed in a browser. Note that a web page can also be called a website. A website refers to a collection of web pages on the internet that are linked to each other and form a single unit. Examples of websites include company homepages, personal blogs, and e-commerce sites.

[0042] In sequence SQ535, the search control unit 420 obtains the URL (Uniform Resource Locator) of the search result web page from the search engine 130. Based on the URL of the web page obtained as a search result, the search control unit 420 obtains the site name of the website containing the relevant web page, the page name of the web page, images contained in the web page, and text information of the main body contained in the web page. More specifically, if automated retrieval is permitted in a predetermined file such as robots.txt, the search control unit 420 obtains the site name of the website containing the relevant web page, the page name of the web page, images contained in the web page, and text information of the main body contained in the web page.

[0043] In sequence SQ540, the LLM interface unit 430 generates a prompt for generating a profile of a person based on the company name and individual name entered on the search screen 600. More specifically, the prompt includes N lines of data from the web page that match the keyword, such as the main text. Limiting the data to N lines is to prevent the inclusion of information about other individuals and to prevent excessive data from slowing down communication speed and / or processing speed. The prompt also includes instructions to summarize the web page information and generate a business profile, and information indicating that the generated information will be output via streaming. Furthermore, the prompt includes information indicating that the output will be in a predetermined format. One example of a predetermined format is JSON format.

[0044] In sequence SQ550, the LLM interface unit 430 sends a prompt to the LLM 140. The processing of sequence SQ550 is an example of the process of sending a prompt to a large-scale language model. LLM140 is an example of a large-scale language model. In sequence SQ560, the LLM interface unit 430 receives streaming data output from LLM140. The processing of sequence SQ560 is an example of the process of receiving streaming data output from a large-scale language model.

[0045] In sequence SQ565, the data completion unit 440 analyzes the received streaming data and completes the data based on the analysis results. Specifically, the data completion unit 440 analyzes the incomplete JSON data received via streaming and completes the data to make it valid as JSON data. The display control unit 410 then asynchronously renders the completed JSON data into the designed HTML format and transmits it to the client device 110. The processing of sequence SQ565 is an example of a process that interpolates data into the received streaming data.

[0046] Figure 7 illustrates the process of interpolating data into streaming data. Data 700 is an example of streaming data output from LLM140. Because Data 700 is streaming data, for example, it is data in which the start tag and end tag pairs are not formed with respect to HTML tags that define the structure and / or content of a web page. The data completion unit 440, for example, parses the HTML code of the received data and, if it detects a missing closing tag, performs completion processing such as completing the corresponding tag pair.

[0047] Furthermore, the data to be supplemented is not limited to tags that have not been closed. For example, the data supplementation unit 440 may analyze the streaming data using natural language processing to understand the context, infer missing parts, and supplement those missing parts. Alternatively, the data supplementation unit 440 may use techniques such as Super Resolution or inpainting to supplement missing parts of images.

[0048] Data 710 is an example of data obtained by supplementing Data 700 with data (data necessary to form pairs of start and end tags).

[0049] In sequence SQ570, the display control unit 410 asynchronously renders the completed JSON data into designed HTML format data and sends it to the client device 110 as display data. The processing of sequence SQ570 can be considered an example of a process that displays a business profile screen based on the generated display format data. In sequence SQ575, the control unit 310 of the client device 110 displays the received data on the output unit 340.

[0050] The processing from sequence SQ550 to sequence SQ575 is repeatedly executed until the streaming data output from LLM140, based on the prompt, is finished.

[0051] Figure 8 shows an example of the screen transitions displayed on the client device 110 when the processing from sequence SQ550 to sequence SQ575 is repeatedly executed. Screen 800 is an example screen showing the result of processing the first sequence SQ575. Screen 810 shows an example of the result of processing the second sequence SQ575. Screen 820 shows an example of the result of processing the third sequence SQ575. As shown in Figure 8, by having the LLM140 output the generated information via streaming, it is possible to quickly display a screen containing the minimum necessary information, and then control the display to show screens with additional information as needed. Furthermore, by performing data interpolation processing on the streaming data, the client device 110 can display a screen including the business profile. Furthermore, as shown in Figure 8, the screen displayed is the business profile screen. A business profile is a concise summary of business-related information, such as career history, job responsibilities, and speaking engagements.

[0052] (2) Details of the process (Part 2) This section explains the details of information processing in the information processing system 1000 using an example where the company name and surname are entered, but the given name is not. Figure 9 is a sequence diagram (part 2) showing an example of information processing in the information processing system 1000. Figure 10 is a diagram (part 2) showing an example of the search screen 600. In the input area 620 of Figure 10, only the surname is entered.

[0053] In Figure 9, the processing of sequences SQ510 to SQ520 is the same as in Figure 5 and is therefore omitted. In sequence SQ525 in Figure 9, the search control unit 420 receives a search request from the client device 110 and retrieves the company name and surname included in the search request.

[0054] In sequence SQ910, the search control unit 420 uses the search engine 130 to search for web pages on the internet using the acquired company name and surname as keywords. The processing of sequence SQ910 is an example of a process that uses a search engine to search for websites on the internet using the company name and surname as keywords.

[0055] In sequence SQ915, the search control unit 420 retrieves search results from the search engine 130. The search results include the title and / or snippet of the search results. The title of the search results is a short sentence that concisely describes the most important part of each website and web page related to the keywords, and is displayed when a search is performed on the search engine 130. The snippet of the search results is a short descriptive text that is displayed below the title of each website when a search is performed on the search engine 130. The title and / or snippet of the search results are examples of summaries of the search results. The processing of sequence SQ915 is an example of a process that obtains a summary of the search results as a search result.

[0056] In sequence SQ920, the LLM interface unit 430 generates a prompt that includes the title and / or snippet of the search results and instructs the system to estimate the name (full name). An example of a prompt to be generated is as follows: " Is the full name of the person entered in input field 620 the person's full name? If it is, please output the full name of the person entered in input field 620 as is. Based on the "Title and / or Snippet" input, estimate the company name entered in input field 610 and the full name of the person entered in input field 620. Please output all candidates separated by commas. Example output: AAAA, BBBB, CCC " The processing of sequence SQ920 is an example of a process that generates a prompt containing a summary. The prompt further includes instructions to output candidate given names (full names) corresponding to the surname from the summary. As another example, the LLM interface unit 430 may further include a prompt instructing the user to estimate the department and / or job title of the person in question within the company.

[0057] In sequence SQ925, the LLM interface unit 430 sends the generated prompt to the LLM 140. Sequence SQ925 is an example of the process of sending a prompt to a large language model. In sequence SQ930, the LLM interface unit 430 receives data output from LLM140 (the name estimated by LLM140).

[0058] In sequence SQ935, the display control unit 410 determines whether the data entered in the input area 620 of the search screen 600 is only a surname or a given name. For example, if the full name of a person entered in the input area 620 is output directly from the LLM140, the display control unit 410 determines that the data entered in the input area 620 of the search screen 600 is a given name. On the other hand, if the full name of a person entered in the input area 620 is not output directly from the LLM140, the display control unit 410 determines that the data entered in the input area 620 of the search screen 600 is only a surname.

[0059] When sequence SQ935 determines that the data entered in the input area 620 of the search screen 600 is a name, the information processing system 1000 executes the processing from sequence SQ530. If sequence SQ935 determines that the data entered in the input area 620 of the search screen 600 is a surname, then in sequence SQ940, the display control unit 410 generates display data (screen) that includes the data output from LLM140 (the surname estimated by LLM140) as a selection candidate.

[0060] In sequence SQ945, the display control unit 410 transmits the generated screen to the client device 110. The processing of sequence SQ945 is an example of a process that outputs a screen containing candidate given names (surnames) corresponding to surnames output from a large-scale language model. In sequence SQ950, the control unit 310 of the client device 110 displays the received data on the output unit 340.

[0061] Figure 11 shows an example of a search screen 1100 that includes name selection options. The search screen 1100 displays "Tanaka Kotaro" 1110 and "Tanaka Tokubei" 1120 as name selection options. The operator of the client device 110 can select either "Tanaka Kotaro" 1110 or "Tanaka Tokubei" 1120. In other words, the search screen 1100 in Figure 11 is configured to allow users to select from a list of name candidates.

[0062] For example, if "Tokubei Tanaka" 1120 is selected and the generate button is selected, the information processing system 1000 executes the processing from sequence SQ525 in Figure 5. That is, the search control unit 420 uses the company name and the name selected via the screen as keywords to search for websites on the internet using a search engine.

[0063] According to the processing in Embodiment 1, the latest person information can be acquired and summarized more efficiently. For example, the time required to research the background and / or job description of a business partner can be reduced. In addition, the quality of communication with customers can be improved because the latest person information can be easily acquired. Furthermore, summarization by a large-scale language model allows for the rapid acquisition of only the important information.

[0064] (Variation 1) Modification 1 of Embodiment 1 will now be described. Configurations and processes not described in Modification 1 are the same as those in Embodiment 1. Modification 1 is included in Embodiment 1 and is not different from Embodiment 1.

[0065] In Modification 1, the display control unit 410 may generate a screen displaying the information of a selected person in response to a request from the client device 110 and send it to the client device 110. The person information is information about the selected person generated based on information obtained from the person database. The person database is a database of people constructed based on business card information, etc. The person database includes business card information, information on the person's career, news information about the person, and contact history information about the person. The screen displaying the person information also includes the person's name, and as the latest business card information, the name of the company they belong to, their address, telephone number, email address, etc. The person database is stored in, for example, the storage unit 220. The display control unit 410 may also provide a generate button on such a screen. When the generate button is selected, a search request including the company name and the person's name (name) is sent from the client device 110 to the server device 100. The processing from sequence SQ525 is the same as in Embodiment 1.

[0066] According to the process in Modification 1, the functions of the information processing system 1000 can be called from a screen displaying person information obtained from the person database, allowing for more efficient acquisition and summarization of the latest person information.

[0067] (Modification 2) Modification 2 of Embodiment 1 will now be described. Configurations and processes not described in Modification 2 are the same as those in Embodiment 1 and Modification 1. Modification 2 is included in Embodiment 1 and is not different from Embodiment 1.

[0068] The control unit 210 of Modification 2 registers and / or updates the content such as career history, job description, and speaking engagements included in the business profile screen generated by the processing of Modification 1 as the person information of the corresponding person in the person database.

[0069] According to the process in Modification 2, the latest person information can be obtained, summarized, and registered and / or updated as the person information for the corresponding person in the person database.

[0070] <Note> The product may be provided in any of the following embodiments. (Note 1) An information processing method performed by an information processing system, Using the target person's information as a keyword, a search engine is used to search websites on the internet. The search results retrieve information from web pages. A prompt is generated that includes N lines of data from the information on the aforementioned web page that match the keyword, The aforementioned N is a natural number less than or equal to a predetermined value, The prompt further includes instructions to summarize the information on the web page and generate a business profile. Information processing methods. (Note 2) The information processing method described in Appendix 1, The prompt includes information indicating that the output will be in a predetermined format. Information processing methods. (Note 3) The information processing method described in Appendix 2, The aforementioned specified format is JSON (JavaScript Object Notation) format. Information processing methods. (Note 4) An information processing method described in any one of the appendices 1 to 3, The aforementioned prompt further includes an instruction that the information to be generated should be output via streaming. Information processing methods. (Note 5) An information processing method described in any one of the appendices 1 to 4, The aforementioned prompt is sent to the trained model, The stream data output from the aforementioned trained model is received, The received streaming data is supplemented with data, Generate data in display format. Information processing methods. (Note 6) The information processing method described in Appendix 5, The business profile screen is displayed based on the generated data in the aforementioned display format. Information processing methods. (Note 7) An information processing method described in any one of the appendices 1 to 6, The aforementioned information about the subject person includes the name of the subject person and the name of the company to which the subject person belongs. Information processing methods. (Note 8) An information processing method described in any one of the appendices 1 to 7, Using the company name and the person's name as keywords, a search engine was used to search for websites on the internet. The search results are summarized as follows: A prompt containing the above summary is generated, The prompt further includes an instruction to output candidate names corresponding to the surname from the summary, The aforementioned prompt is sent to the trained model, The system outputs a screen containing name candidates corresponding to the surname output from the aforementioned trained model. The aforementioned screen is configured to allow selection of the candidates. Information processing methods. (Note 9) The information processing method described in Appendix 8, The system uses the company name and the name selected via the aforementioned screen as keywords to search for websites on the internet using a search engine. Information processing methods. (Note 10) The information processing method described in Appendix 5 or Appendix 8, The aforementioned trained model is a large-scale language model or a multimodal model. Information processing methods. (Note 11) An information processing system, It has a search control unit and an interface unit, The search control unit, Using the target person's information as a keyword, a search engine is used to search websites on the internet. The search results retrieve information from web pages. The interface unit is A prompt is generated that includes N lines of data from the information on the aforementioned web page that match the keyword, The aforementioned N is a natural number less than or equal to a predetermined value, The prompt further includes instructions to summarize the information on the web page and generate a business profile. Information processing system. (Note 12) It is a program, On the computer, A program for executing the information processing method described in any one of the items from Appendix 1 to Appendix 10.

[0071] While various embodiments of the present invention have been described, these are presented as examples only and are not intended to limit the scope of the invention. Novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. Embodiments and variations thereof are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0072] 100: Server device 110: Client device 150: Network 210: Control Unit 220: Storage section 230: Communications Department 1000: Information Processing System

Claims

1. An information processing method performed by an information processing system, Using the target person's information as a keyword, a search engine is used to search for web pages on the internet. The search results retrieve information from web pages. A prompt is generated that includes N lines of data before and after the information on the aforementioned web page that matches the keyword. The aforementioned N is a natural number less than or equal to a predetermined value, The prompt further includes instructions to summarize the information on the web page and generate a business profile. Information processing methods.

2. The information processing method according to claim 1, The prompt includes information indicating that the output will be in a predetermined format. Information processing methods.

3. The information processing method according to claim 2, The aforementioned specified format is the JSON (JavaScript Object Notation) format. Information processing methods.

4. The information processing method according to claim 1, The aforementioned prompt further includes an instruction that the information to be generated should be output via streaming. Information processing methods.

5. The information processing method according to claim 4, The aforementioned prompt is sent to the trained model, The stream data output from the aforementioned trained model is received, The received streaming data is supplemented with data, Generate data in display format. Information processing methods.

6. The information processing method according to claim 5, The business profile screen is displayed based on the generated data in the aforementioned display format. Information processing methods.

7. The information processing method according to claim 1, The aforementioned information about the subject person includes the name of the subject person and the name of the company to which the subject person belongs. Information processing methods.

8. The information processing method according to claim 1, Using the company name and the person's name as keywords, a search engine was used to search for web pages on the internet. The search results are summarized as follows: A prompt containing the above summary is generated, The prompt further includes an instruction to output candidate names corresponding to the surname from the summary, The aforementioned prompt is sent to the trained model, The system outputs a screen containing name candidates corresponding to the surname output from the aforementioned trained model. The aforementioned screen is configured to allow selection of the candidates. Information processing methods.

9. The information processing method according to claim 8, The system uses the company name and the name selected via the aforementioned screen as keywords to search for web pages on the internet using a search engine. Information processing methods.

10. The information processing method according to claim 5, The aforementioned trained model is a large-scale language model or a multimodal model. Information processing methods.

11. An information processing system, It has a search control unit and an interface unit, The search control unit, Using the target person's information as a keyword, a search engine is used to search for web pages on the internet. The search results retrieve information from web pages. The interface unit is A prompt is generated that includes N lines of data before and after the information on the aforementioned web page that matches the keyword. The aforementioned N is a natural number less than or equal to a predetermined value, The prompt further includes instructions to summarize the information on the web page and generate a business profile. Information processing system.

12. It is a program, On the computer, A program for causing the information processing method described in any one of claims 1 to 10.

Images