Information processing method, program, and information processing device

Abstract

This provides an information processing method that enables the creation of proposals for selling products to target companies more efficiently and easily. [Solution] The information processing method involves an information processing device acquiring a research theme and target company, outputting research results regarding the theme and target company using a language model, and outputting a draft proposal for the target company by providing the outputted research results and product information to the language model. The research results may also be output based on keywords suitable for finding the theme's content through website searches, obtained from the language model.

Description

Technical Field

[0006] , , ,

[0005] ,

[0007] , , ,

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

Background Art

[0002] Patent Document 1 discloses estimating and presenting problems and needs that a customer has based on a dialogue with the customer.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In companies and the like, various sales activities are carried out to sell their own products and the like. However, it is difficult to find contact points between their own products and potential customers and to find appropriate proposals that can catch the attention of potential customers.

[0005] One aspect of the present disclosure provides an information processing method and the like that can create proposals for more efficiently and easily selling products to target companies.

Means for Solving the Problems

[0006] An information processing method according to one aspect of the present disclosure is an information processing method in which an information processing apparatus acquires a theme to be researched and a target company, outputs a research result regarding the theme and the target company by a language model, and outputs a proposal draft for the target company by providing the output research result and product information to the language model.

Effects of the Invention

[0007] According to one aspect of this disclosure, the information processing method, program, and information processing device can be used to create proposals for selling products to target companies more efficiently and easily. [Brief explanation of the drawing]

[0008] [Figure 1] This is an overview diagram of the system relating to one aspect of this disclosure. [Figure 2] This is a block diagram showing an example of a server device configuration. [Figure 3] This is a block diagram showing an example configuration of a terminal device. [Figure 4] This is a block diagram showing an example configuration of a generation server device. [Figure 5] This is a sequence diagram showing an example of processing in the system shown in Figure 1. [Figure 6] This is a sequence diagram illustrating an example of the research result output process. [Figure 7] This figure shows an example of a keyword acquisition prompt. [Figure 8] This figure shows an example of an article review prompt. [Figure 9] This figure shows an example of article review information. [Figure 10] This figure shows an example of a research result prompt. [Figure 11] This figure shows an example of research results. [Figure 12] This figure shows an example of a screen displaying research results. [Figure 13] This figure shows an example of a proposed draft prompt. [Figure 14] This figure shows an example of a template. [Figure 15] This figure shows an example of product information. [Figure 16] This figure shows an example of a proposed draft. [Figure 17] This is a sequence diagram showing examples of different processes in the system shown in Figure 1. [Modes for carrying out the invention]

[0009] Next, an example of an information processing method, a program, and a system as an information processing apparatus according to one aspect of the present disclosure will be described in detail based on the drawings. In the description, the same reference numerals are assigned to the same elements, and duplicate descriptions will be omitted as appropriate.

[0010] FIG. 1 is a schematic diagram of a system according to one aspect of the present disclosure. The system according to the embodiment of the present disclosure includes an information processing apparatus 1, an information processing terminal 2, and a generation server apparatus 4, and each apparatus transmits and receives information via a network 3 such as the Internet. The generation server apparatus 4 can utilize a language model 45 (FIG. 4) such as a large language model (LLM) stored in a storage inside or outside the generation server apparatus 4.

[0011] The information processing apparatus 1 is an information processing device that performs processing, storage, and transmission / reception of various information. The information processing apparatus 1 may be configured as, for example, a server apparatus, a personal computer, a tablet terminal, a smartphone, or the like. The information processing apparatus 1 may be composed of a plurality of information processing devices, or may be configured as one of a plurality of virtual devices (virtual machines) configured within one information processing device. In the embodiment of the present disclosure, for the sake of avoiding complicated explanations, the information processing apparatus 1 will be described by substituting it with the server apparatus 1. However, the information processing apparatus 1 is not limited to the server apparatus, and may be configured as any form of information processing device as described above.

[0012] The information processing terminal 2 receives the information output from the server apparatus 1 via the network 3, accepts the operation of the user of the information processing terminal 2, and transmits the information related to the operation to the server apparatus 1 via the network 3. The information processing terminal 2 may be an information processing device such as, for example, a personal computer, a smartphone, a mobile phone, a wearable device, and a tablet. In the embodiment of the present disclosure, for the sake of avoiding complicated explanations, the information processing terminal 2 will be described by substituting it with the terminal device 2.

[0013] FIG. 2 is a block diagram showing a configuration example of the server device 1. The server device 1 can be an information processing device mainly composed of an electronic circuit using semiconductor circuit elements. The server device 1 includes a control unit 11, a communication unit 12, a reading unit 13, and a storage unit 14. Each component of the control unit 11, the communication unit 12, the reading unit 13, and the storage unit 14 is communicably connected by a bus 19 or the like. Note that the server device 1 may have other configurations such as not having the reading unit 13.

[0014] The control unit 11 can be configured to include any one or more of processing devices such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), and a quantum processor. The control unit 11 reads and executes the program (or program product) 16 stored in the storage unit 14.

[0015] The communication unit 12 is a communication module for performing communication-related processing, and can transmit and receive information to and from the terminal device 2 or the like via the network 3. The reading unit 13 can read a portable storage medium 15 such as a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc)-ROM, or a USB (registered trademark) memory. The control unit 11 may read the program 16 from the portable storage medium 15 via the reading unit 13 and store it in the storage unit 14. Further, the control unit 11 may download the program 16 from another computer via the network 3 or the like and store it in the storage unit 14.

[0016] The storage unit 14 includes a volatile storage unit such as a RAM (Random Access Memory), and non-volatile memories such as a ROM (Read Only Memory), an HDD (Hard disk drive), and a flash memory It includes a memory unit. As shown in Figure 2, the memory unit 14 stores, for example, a program 16. The program 16 is a program executed by the control unit 11. In this embodiment, the program 16 may also be referred to as a program product 16.

[0017] Figure 3 is a block diagram showing an example configuration of terminal device 2. Here, terminal device 2 can be an information processing device composed mainly of electronic circuits using semiconductor circuit elements. Terminal device 2 may have a control unit 21, a communication unit 22, a reading unit 23, a storage unit 24, a display unit 26, and an input unit 27. The components of the control unit 21, communication unit 22, reading unit 23, storage unit 24, display unit 26, and input unit 27 are connected to each other so as to be able to communicate with one another by a bus 29 or the like.

[0018] The control unit 21 can be configured to include one or more processing units such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), and a quantum processor. The control unit 21 reads and executes the program stored in the storage unit 24.

[0019] The communication unit 22 is a communication module for performing communication-related processing and can send and receive information with the server device 1, etc., via the network 3. The reading unit 23 can read portable storage media 25 such as CD (Compact Disc)-ROM, DVD (Digital Versatile Disc)-ROM, and USB (registered trademark) memory. The control unit 21 can read programs and / or data from the portable storage media 25 via the reading unit 23 and save them to the storage unit 24. In addition, the control unit 21 can download programs from other computers via the network 3, etc., and save them to the storage unit 24.

[0020] The storage unit 24 includes volatile storage devices such as RAM (Random Access Memory), and non-volatile storage devices such as ROM (Read Only Memory), HDD (Hard Disk Drive), and flash memory. The display unit 26 can be a liquid crystal display or an organic EL (Electro Luminescence) display, etc. The input unit 27 can be an input device such as a keyboard, mouse, touch panel, and camera.

[0021] Figure 4 is a block diagram showing an example configuration of the generation server device 4. The generation server device 4 can be an information processing device composed mainly of electronic circuits using semiconductor circuit elements. The generation server device 4 has a control unit 41, a communication unit 42, a reading unit 43, and a storage unit 44. The control unit 41, communication unit 42, reading unit 43, and storage unit 44 are connected to each other so as to be able to communicate with one another by a bus 49 or the like. Except for the contents stored in the storage unit 44, each of these components can be configured the same as the information processing device (server device) 1 in Figure 2, so redundant explanations are omitted. Note that the generation server device 4 may have other configurations, such as not having a reading unit 43, as in the case of server device 1.

[0022] The memory unit 44 can store the language model 45. The language model 45 consists of a program and training data, and the control unit 41 executes the program by referring to the input data and training data input from an external source. The language model 45 may be stored in an external storage device or the like, rather than in the memory unit 44.

[0023] The generation server device 4 is an information processing device that handles language models 45, such as large language models (LLMs) like GPT (Generative Pre-trained Transformer, registered trademark), BERT (Bidirectional Encoder Representations from Transformer), and Gemini (registered trademark). The language models 45 may be stored in the memory unit 44 within the generation server device 4, or they may be stored in storage or the like that which is communicated with the generation server device 4.

[0024] The generation server device 4 inputs input data such as images, audio, and text into the language model 45 and generates a response sentence. The language model 45 is a pre-trained machine learning model and can be a large-scale language model such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformer), but other language models may also be used.

[0025] Server device 1 may be connected to generation server device 4 via network 3, or it may be connected to generation server device 4 directly or via a local network without using network 3. Since generation server device 4 is a device that handles language model 45, from the perspective of server device 1, when server device 1 sends prompts etc. to generation server device 4, it is expressed as server device 1 sending (inputting) to language model 45.

[0026] Figure 5 is a sequence diagram showing an example of processing in the system of Figure 1. In this sequence diagram, the processing of server device 1 is executed based on the instructions of program 16 stored in memory unit 14. As shown in this sequence diagram, first terminal device 2 transmits the theme and target company information to server device 1 (step S11). Here, the target company can be a company to be researched or a potential customer from whom a proposal draft for sales activities can be obtained. In this embodiment, the target company will be described as "ABC Company". The theme can be the content to be researched or information to obtain a proposal draft, which will be described later. The theme can be multiple themes, including general information about the target company, in order to gather all information about the target company.

[0027] For example, themes can include a wide range of topics, from basic company information such as "Company Overview / Business Activities," "Goals / Challenges / Initiatives of the Medium-Term Management Plan," "Human Resources / Talent Development Policy," "Human Capital Management," "Trends in Number of Hires and Employees," "Contact Information / Initiatives / Manager / Recruitment Information for the Human Resources Department," "Talent Management," "System Implementation for the Human Resources Department," "DX Promotion / Contact Information / Initiatives / Manager / Recruitment Information for the Systems Department," and "Labor Management," to matters related to the products you want to sell.

[0028] Server device 1, having received the theme and target companies, executes research result output processing P30. Research result output processing P30 can be a process in which server device 1 receives research results from generating server device 4. Research result output processing P30 will be described in detail using Figure 6.

[0029] In the research result output processing P30, the server device 1, having acquired the research results, transmits the research results to the terminal device 2 (step S12), and the terminal device 2 can display the research results on the display unit 26 (Figure 12) (step S13). Note that the research results do not have to be displayed on the terminal device 2, nor do they have to be transmitted to the terminal device 2. Next, the user of the terminal device 2 transmits their company's product information (Figure 15) to the server device 1 by operating the terminal device 2 (step S14).

[0030] Server device 1, having received the product information, executes a proposal draft prompt creation process based on the research results and product information (step S15). The proposal draft prompt created in the proposal draft prompt creation process (e.g., Figure 13) is sent to generation server device 4 (step S16), where generation server device 4 uses the language model 45 to execute proposal draft prompt processing (step S17) and generates a proposal draft (step S21).

[0031] The generated proposal draft is transmitted from the generation server device 4 to the server device 1 (step S21). Upon receiving the proposal draft, the server device 1 transmits the proposal draft to the terminal device 2 (step S22). The terminal device 2, upon receiving the proposal draft, can then provide it to the user by displaying it on the display unit 26 or by other means.

[0032] Figure 6 is a sequence diagram showing an example of research result output processing P30. Research result output processing P30 can be a process performed by server device 1 together with generation server device 4. The processing of server device 1 in this sequence diagram may be executed based on instructions of program 16 stored in storage unit 14.

[0033] In the research result output processing P30, the server device 1 first executes the keyword acquisition prompt creation process (step S31). Here, the keyword acquisition prompt creation process is the process of creating a keyword acquisition prompt (Figure 7) to be input to the language model 45. The keyword acquisition prompt may request the extraction of keywords suitable for finding the content of a theme through a website search. Here, multiple themes can be combined into a single prompt.

[0034] The generated keyword acquisition prompt is sent to the generation server device 4 (step S32), and the generation server device 4 executes the keyword acquisition prompt processing, which is the processing described in the received keyword processing prompt (step S33). In the keyword acquisition prompt processing, one or more keywords suitable for finding the content of the requested theme (or each theme if there are multiple themes) are extracted for the requested theme.

[0035] The generating server device 4 sends keywords to the server device 1 (step S35), and the server device 1 receives the keywords. Subsequently, the server device 1 scrapes a group of websites 31 on a network 3 such as the Internet to collect articles based on the received keywords (step S36). In other words, it sequentially browses websites on the network 3 and extracts and collects articles related to the keywords from their content (steps S37, S38). If collecting information on multiple themes, the server device 1 can perform scraping to collect articles for each theme.

[0036] As described above, the server device 1 can generate keywords for searching a theme using the language model 45. Furthermore, it can collect articles related to the theme based on the generated keywords. This allows for the acquisition of more necessary information related to the target company.

[0037] Server device 1, which has collected the articles, executes an article review prompt creation process to create an article review prompt (Figure 8), which is a prompt for reviewing the articles (step S41). Once the article review prompt is created, server device 1 sends the article review prompt to generating server device 4 (step S42). Generating server device 4, which has received the article review prompt, executes the article review prompt process, which is the process described in the received article review prompt (step S43).

[0038] The article review prompt processing can be a process that outputs article review information. In the article review prompt processing, the generation server device 4 uses the language model 45 to extract sentences related to the target company and theme as article review information for each collected article. This makes it easier to perform processing such as searching and extraction on the collected articles. Alternatively, based on prompts that extract whether or not each collected article is related to the theme, sentences within the article related to the theme, and the company name that is the subject of the sentence, the article review information may be extracted for each article, including whether or not each article is related to the theme, sentences within the article related to the theme, and the company name that is the subject of the sentence.

[0039] Here, "sentences from articles related to the theme" can be direct quotes from the original articles. By objectively outputting one or more pieces of information corresponding to the theme in this way, it becomes easy to grasp the target company's approach or direction regarding the theme. Furthermore, by checking the "company name that is the subject of the sentence," it is possible to confirm whether the information is about the target company. This allows the proposal draft, which will be discussed later, to be based on more accurate information.

[0040] The extracted article review information is transmitted from the generation server device 4 to the server device 1 (step S44). The server device 1, having acquired the article review information, can then execute the research result prompt creation process (step S46). In the research result prompt creation process, a research result prompt (Figure 10) is created. The research result prompt can include the title and URL of the article that was the source of the article review information, the target company, and the headline theme, in addition to the acquired article review information.

[0041] Server device 1 sends a research result prompt to generation server device 4 (step S47), and generation server device 4, upon receiving the research result prompt, executes research result prompt processing (step S48). In the research result prompt processing, sentences from articles that are relevant to the theme and whose subject is the target company are extracted. This makes it possible to obtain only the necessary information related to the target company. Alternatively, the sentences from each article may be given to the language model 45 to be summarized and research results (Figure 12) may be generated. Note that the summary may include links to the original sentences from which the summary was made. Even if the articles contain a lot of text, the research results can be made easier to understand.

[0042] The generation server device 4 transmits the generated research results to the server device 1 (step S49). The server device 1 further transmits the research results to the terminal device 2 (Figure 5, step S12), where they can be displayed (Figure 5, step S13). By also transmitting multiple generated keywords and links to articles related to the target company, the display can include research results containing summaries of multiple texts and links to each text, multiple generated keywords, and information containing links to articles related to the target company (Figure 12). This allows the information to be displayed in a way that is easier for the user to understand. Note that the research results do not necessarily have to be displayed on the terminal device 2, nor do they necessarily have to be transmitted to the terminal device 2.

[0043] Note that the research result output process P30 may be performed for one theme at a time, and the research result output process P30 may be repeated for each theme. Alternatively, the research result output process P30 may be executed only once, and the keyword acquisition prompt process, keyword scraping, article review prompt process, and research result prompt process included in the research result output process P30 may each be repeated for each theme.

[0044] As described above, the server device 1 acquires the research theme and target company, outputs research results regarding the theme and target company using the language model 45, and can output a draft proposal to the target company by providing the outputted research results and product information to the language model 45. This makes it easy to create proposal content for introducing the product to the target company.

[0045] As described above, the server device 1 can generate keywords for searching a theme using the language model 45 and output research results based on those keywords. Alternatively, it may collect articles related to the theme based on the generated keywords and output research results based on those articles. This allows for the acquisition of more necessary information related to the target company.

[0046] In this way, the server device 1 provides the language model 45 with prompts to extract, for each collected article, whether or not it is related to a theme, the sentences within the article that are related to the theme, and the company name that is the subject of the sentences. By doing so, the server device 1 can extract, for each article, whether or not it is related to a theme, the sentences within the article that are related to the theme, and the company name that is the subject of the sentences, and extract articles that are related to a theme and whose subject is the target company.

[0047] This allows for the objective acquisition of one or more pieces of information related to the theme, making it easy to understand the target company's approach to the theme or its direction. Furthermore, by checking the "company name that is the subject of the text," it is possible to confirm whether the information pertains to the target company. This allows for the acquisition of more necessary information related to the target company, resulting in a more accurate draft proposal.

[0048] Figure 7 shows an example of a keyword acquisition prompt. The keyword acquisition prompt is created, for example, in the keyword acquisition prompt creation process in the sequence diagram of Figure 6 by server device 1. The keyword acquisition prompt is also executed, for example, in the keyword acquisition prompt processing in the sequence diagram of Figure 6 by generation server device 4.

[0049] The keyword acquisition prompt in this example is a prompt that requests the language model 45 to output 1 to 4 search keywords for the target company that will match the content of the theme "Goals / Challenges / Initiatives of the Medium-Term Management Plan". Specifically, the keyword acquisition prompt can include the "theme", "commands for generating keywords to search the theme", and "sample queries and answers".

[0050] In Figure 7, the "theme" is listed in theme column 111, and "Goals / Issues / Initiatives of the Medium-Term Management Plan" is listed as the theme ("query") for which search keywords are requested. The "command to generate keywords for searching the theme" is listed in command column 112, and requests that 1 to 4 search keywords be extracted from the website for the content of the theme ("query") and output in JSON (JavaScript® Object Notation) format.

[0051] The "sample query and answer" is described in sample column 113, and as an example of the answer format, if the theme ("query") is set to "Regarding the goals and status of real estate investment trusts" The following example shows how the keywords "real estate investment trust," "real estate investment trust goals," and "real estate investment trust status" are extracted and output in JSON format.

[0052] The keywords obtained by executing the keyword prompt in Figure 7 included, for example, four types of keywords: "medium-term management plan," "medium-term management plan objectives," "medium-term management plan challenges," and "medium-term management plan initiatives."

[0053] In Figure 7, the number of themes is set to one, but it is also possible to process multiple themes at once. When creating a proposal draft, it is also possible to set multiple themes from a wide range of fields so that various proposal possibilities can be sought.

[0054] In this way, the keyword acquisition prompt can generate keywords by providing the language model 45 with a prompt containing a theme, a command to generate keywords for searching the theme, and sample queries and answers. By using the keywords generated in this way, articles related to the theme can be collected more accurately. Furthermore, research results, as described later, can be output based on the generated keywords.

[0055] Figure 8 shows an example of an article review prompt. The article review prompt is created, for example, in the article review prompt creation process in the sequence diagram of Figure 6 by server device 1. The article review prompt is also executed, for example, in the article review prompt processing in the sequence diagram of Figure 6 by generation server device 4.

[0056] As shown in this diagram, the article review prompt allows you to check each article collected through scraping to see if it contains content relevant to the theme and if it is an article that uses the target company as the subject. The results can then be displayed along with the original text of the source.

[0057] Specifically, the article review prompt extracts information such as "whether or not each collected article is relevant to the theme," "sentences within the article related to the theme," and "the company name that is the subject of the sentence." The article review prompt may also include a "summary of the content about the theme." The extracted content should be output in the specified "output format."

[0058] In Figure 8, the "Output Format" is set to "return_format" in the format field 126. It is described as follows. In the format field 126, the output format ("return_format") is in JSON format and has three elements: "relevance to the theme for each collected article" ("related"), "summary of the content about the theme" ("summary"), and "text within the article related to the theme" ("extraced_texts"). Furthermore, "text within the article related to the theme" ("extraced_texts") has the elements of the id of the text within the article ("id"), the text of that text ("text"), and "the name of the company that is the subject of the text" ("subject_company"). Here, "id" can be considered to be the subscripts 1 to 6 of symbols A1 to A6 in the diagram showing an example of article analysis information in Figure 9.

[0059] The article review prompt allows for further specification of the requirements for each element. In the example in Figure 8, for "Relevance to the theme of each collected article" ("related"), the prompt requires that "yes" be entered in the relevance field 124 if there is text related to the theme ("query"), and "no" if there is no text related. For "Text within the article related to the theme" ("extraced_texts"), the prompt requires that the text directly related to the theme be entered in its original form in the related text field 122.

[0060] For "the company name that is the subject of the document" ("subject_company"), see Company Name 123. Therefore, we require you to include the company name that is the subject of the sentence directly related to the theme ("query"). It is. For the "summary of the content on the theme," see summary section 121. They are requesting a summary of the answer (result) regarding the theme ("query"). ru.

[0061] Furthermore, in Figure 8, the theme field 125 of the article review prompt is set to "Medium-term economics". The content is presented as "Goals / Challenges / Initiatives of the Business Plan," followed by each article to be extracted ("content"). Here, "query" may be expressed as a question prompting an answer about the theme.

[0062] The article review prompt may request, for each collected article, the extraction of one or more of the following: whether or not it is relevant to the theme, sentences within the article that are related to the theme, and the name of a company that is the subject of the sentence.

[0063] This allows for the objective output of multiple pieces of information related to a theme, making it easy to grasp the target company's direction regarding the theme. Furthermore, by checking the "company name that serves as the subject of the text," it's possible to verify whether the information pertains to the target company. This allows for the creation of proposal drafts based on more accurate information.

[0064] Figure 9 shows an example of article review information. Article review information is generated, for example, by the generation server device 4 during the article review prompt processing in the sequence diagram of Figure 6. This example of article review information is output in JSON format. This article review information indicates, for a given article, whether there are sentences related to the theme ("related"), and the content related to the theme. It has a "summary" field and an "extraced_texts" field containing texts directly related to the theme. Furthermore, the "extraced_texts" field contains the text itself ("text") and a "subject_company" field, which is the subject of the text.

[0065] Here, if an article contains multiple sentences directly related to the theme, multiple lists of the extracted sentences ("extraced_texts") can be created. In Figure 9, six sentences, A1 to A6, are extracted from article A as sentences directly related to the theme. Article A can be multiple articles, and multiple articles collected in step S36 may be targeted. Furthermore, multiple sentences directly related to the theme can be extracted from each of the multiple articles.

[0066] In this example, the "related" field indicates that there are relevant sentences to the theme, and a summary of the content on the theme is provided in the "summary" field. Additionally, six "extracted texts" are listed, and the subject of each of these texts is "ABC Company".

[0067] Figure 10 shows an example of a research result prompt. The research result prompt is created, for example, in the research result prompt creation process in the sequence diagram of Figure 6 by server device 1. The research result prompt is also executed, for example, in the research result prompt processing in the sequence diagram of Figure 6 by generation server device 4.

[0068] Here, the research results prompt can request that the article extract sentences that are "relevant to the theme" and "the subject is the target company." Regarding "relevance to the theme," the relevance column 131 in Figure 10 contains information that is not relevant to the theme ("query"). The report states that it will be excluded. Regarding the requirement that "the subject is the target company," Figure 10, in the target company column 132, etc., requires that the company name ("subject_company") which is the subject is the same company as the target company ("company_name").

[0069] Furthermore, the research results prompt compiles the acquired article review information, along with the titles and URLs of the articles from which the acquired article review information originated, into a document ("doc"), and asks the user to answer the question ("query") based on this document ("doc").

[0070] Also, example answer(" <example>The example answer requires that, in addition to the content of the answer, the "text" of the article that served as the basis be shown in the format of citation ID [item_X_X]. Here, the first "X" in [item_X_X] indicates the number assigned to the article, and the last "X" may indicate which sentence (or extracted sentence) it is. Also, if there is no information related to the theme ("query") The organization requests that irrelevant information not be included, stating, "No relevant information was found."

[0071] Here, the article review information to be entered is not limited to one; multiple entries can be entered. Also, since the system is designed to "exclude information that is not relevant to the theme as much as possible," for example, by referring to the "presence or absence of text related to the theme ("related")" item in the article review information of a document ("doc"), if it is "no", the entire article will not be reviewed, thereby improving processing speed. Note that the articles in the document ("doc") to be included in the prompt may have already been reviewed by the server device 1 before being entered into the language model 45, so that only articles where the "presence or absence of text related to the theme ("related")" item is "yes" are included.

[0072] Figure 11 shows an example of research results. Research results are generated, for example, by the generation server device 4 during the research result prompt processing in the sequence diagram in Figure 6. The research results in this figure show the themes "Basic Policies and Goals," "Management Challenges," "Specific Initiatives," and "Strengthening the Management Foundation" for the target company "ABC Company." The information in Figure 11 is compiled from articles collected by scraping, after which "information unrelated to the theme" is removed during the research result prompt processing, and the articles are refined to include the target company as the subject, etc., and then summarized. This allows users to obtain more accurate information.

[0073] Specifically, in one example of the displayed research results, ABC Company's medium-term management plan is summarized under the headings of "Basic Policy and Goals," "Management Challenges," "Specific Initiatives," and "Strengthening the Management Foundation." Furthermore, the "Specific Initiatives" heading is further divided into sections on "Business Strategy," "Global Expansion," "Investment Plan," and "ESG Management and Sustainability." Each sentence is accompanied by information on a link to the cited article. In the example in Figure 11, in [item_2_1], the first number "2" indicates the article number, and the following "1" may indicate the sentence number (or extracted sentence). Here, the link is not limited to a link to an internet website, but can also be a link to the location where the acquired article is stored.

[0074] Figure 12 shows an example of a screen 100 displaying research results. This screen can be, for example, a screen displayed on the display unit 26 of the terminal device 2 by the server device 1 that acquired the research results (Figure 5, step S12). The screen 100 displaying the research results may output "research results including summaries of multiple texts and links to each text," "multiple generated keywords," and "information including links to articles related to the target company."

[0075] In Figure 12, specifically, the server device 1 can display "research results including summaries of multiple texts and links to each text" in the research results display area 101, "multiple generated keywords" in the search keyword display area 102, and "information including links to articles related to the target company" in the article link area 103.

[0076] The research results display area 101, similar to the research results in Figure 11, displays summarized information and links to each document regarding the themes "Basic Policies and Goals," "Management Challenges," "Specific Initiatives," and "Strengthening the Management Foundation" for the target company "ABC Company."

[0077] In Figure 12, the research results display area 101 has some information omitted due to space limitations in the diagram. The search keyword display area 102 can display keywords extracted by keyword prompt processing. The article link area 103 can display links to articles used in the research results in the research results display area 101. Note that the links are not limited to links to internet websites, but can also be links to the location where the acquired articles are stored, etc.

[0078] Figure 13 shows an example of a proposed draft prompt. The proposed draft prompt is created, for example, in the proposed draft prompt creation process in the sequence diagram of Figure 5 by server device 1. The proposed draft prompt is also executed, for example, in the proposed draft prompt processing in the sequence diagram of Figure 5 by generation server device 4.

[0079] Here, the proposed draft prompt can include "multiple research results," "product information," and "templates." In Figure 13, "multiple research results" are referenced in the research results column 144 by "researched_information." The referenced information can be, for example, research results like those shown in Figure 11. Here, the research results shown in Figure 11 cover a single theme, but the research results used in the proposed draft prompt are not limited to a single theme.

[0080] For example, "Company Overview / Business Overview," "Goals / Challenges / Initiatives of the Medium-Term Management Plan," "Human Resources / Talent Development Policy," "Human Capital Management," "Trends in Number of Hires and Employees," "Contact Information / Initiatives / Responsible Person / Recruitment Information for the Human Resources Department," "About Talent Management," "Systems Related to the Human Resources Department" Research results can be used for all the themes: "About the introduction of the system," "Contact information / initiatives / person in charge / recruitment information for the DX promotion / systems department," and "About labor management." By creating a proposal draft based on such a large amount of research results, server device 1 can create a more persuasive proposal draft.

[0081] Also, in Figure 13, "product information" is in the product information field 143 as "product_information" It is referenced more than once. The specific details of "Product Information" will be explained in detail in Figure 13 and the explanation using Figure 13 described later. "Template" is referenced as "proposal_format" in template column 142. The specific details of "Template" will be explained in detail in Figure 14 and the explanation using Figure 14 described later.

[0082] Furthermore, the proposal draft prompt, in instruction field 141, instructs the language model 45 to respond in the role of an excellent sales assistant and to output a proposal or optimal approach to the customer. It also requests a proposal that is as specific as possible and tailored to the customer's situation.

[0083] Figure 14 shows an example of a template. The template is referenced or substituted, for example, as "proposal_format" in the proposal draft prompt in Figure 13. As shown, the template may include fields for outputting "the target company's challenges," "the supporting documents for the target company's challenges," and "information for accessing the source of the supporting documents for the target company's challenges."

[0084] Specifically, in Figure 14, "Challenges of the target company" are output in the Challenges column 152 as challenges related to the company's products that can be inferred from the referenced texts. "Texts that support the challenges of the target company" are output in the References column 151 as texts that were referenced when listing the challenges. "Information for accessing the source of the texts that support the challenges of the target company" are output in the Links column 153 as the ID of the referenced source. Note that links are not limited to links to internet websites, but can also be links to the location where the acquired articles are stored, etc.

[0085] Furthermore, the "Referenced Texts" section will include a "Reference ID" for each text, which allows for the output of information such as links to the websites or other sources from which the referenced texts were quoted.

[0086] Thus, the template, in the "Direction of the Proposal" section, lists, for example, "Challenges of the Target Company," and in the "References" section, outputs "Documents that support the claims about the challenges of the target company" and "Information to access the sources of those documents." The template is incorporated into the proposal draft prompt creation process, along with prompts that require users to fill in the template's fields.

[0087] The "Information for accessing the source" (referenced ID) can be a link to a website, a link to a saved article, or other links. The template may also include a "Possible Approach" section that describes the optimal way to utilize the product based on challenges related to the company's product that can be identified from the referenced text.

[0088] In this way, the server device 1 inputs a template along with product information and research results into the language model 45, and the template can include fields for outputting the target company's challenges, the text that supports the target company's challenges, and information for accessing the source of the text that supports the target company's challenges.

[0089] Prompts input to the language model 45, including such templates, can request that the model output a proposal draft according to the template. In this way, users can have the language model 45 output the issues of the target company, allowing them to check the supporting documents and sources, and utilize the resulting proposal draft in a more convincing manner. The template may also include general company information such as the company name and number of employees, such as in the "Company Overview" section.

[0090] Figure 15 shows an example of product information. Product information is referenced or substituted, for example, as "product_information" in the proposed draft prompt in Figure 13. The product in question is a talent management system software called "TalentSoft."

[0091] Product information may include any of the following: "Product details," "Past proposals regarding the product," and "Information on company conditions that may be suitable for the product." The example product information in Figure 15 has a "Product Features" item under "Product Details." The "Product Features" item in Figure 15 is a user interface that makes it easier to find the optimal talent even when the number of employees exceeds 10,000. It exhibits characteristics such as being a face.

[0092] Furthermore, the example of product information in Figure 15 includes a "Past Cases" item under "Past Proposals Related to the Product." The "Past Cases" item in Figure 15 shows an example of DEF Company, Inc. successfully developing individualized training plans for digital talent. Additionally, the example of product information in Figure 15 includes a "Company Conditions Suitable for the Product" item under "Company Conditions Potentially Suitable for the Product." The "Company Conditions Suitable for the Product" item in Figure 15 lists companies that have set talent development goals or have implemented systems related to human resources. As a result, server device 1 can efficiently apply the proposal content expected by the user to language model 45, resulting in an easy-to-use proposal draft.

[0093] Figure 16 shows an example of a proposal draft. The proposal draft is generated by the generation server device 4 during the proposal draft prompt processing, for example, as shown in the sequence diagram in Figure 5. As shown in the proposal draft in Figure 16, the proposal draft includes the template items "Company Overview" and "Proposal Direction." The "Proposal Direction" section also includes the items "References," "Issues related to our company's products that can be inferred from the references," and "Expected approach methods," and is output in a format that allows for the completion of each of these items.

[0094] Furthermore, each entry in the "Referenced Texts" section will display a four-digit number as a "Reference ID," and by embedding a link to the cited document, website, or original document indicated by this number, users can access the source of the referenced text. Note that the links are not limited to internet websites; they can also be links to the location where the retrieved articles are stored.

[0095] In this way, server device 1 can output the "Target Company's Challenges" in the proposal draft, as shown in the "Direction of the Proposal" column, and output the "Documents that Support the Target Company's Challenges" and "Information for Accessing the Sources of the Documents that Support the Target Company's Challenges" in the "References" column. Here, "Information for Accessing the Sources" can be links to websites, links to saved articles, or other links. Server device 1 may also output general company information such as the company name and number of employees in the proposal draft, as shown in the "Company Overview" column.

[0096] In this way, the server device 1 outputs multiple research results for each of several different themes using the language model 45, and outputs a proposal draft for the target company by providing the language model 45 with the output research results and product information. This makes it possible to create a proposal draft based on more accurate information.

[0097] Furthermore, the server device 1 may output a proposal draft that includes the target company's challenges, the documents supporting those challenges, and information for accessing the sources of the documents supporting those challenges. This allows users to verify the documents and sources supporting the challenges of the target company output by the language model 45, enabling them to utilize the proposal draft in a more convincing way.

[0098] As shown in the configuration described above, the server device 1 acquires the research theme and target company, outputs research results regarding the theme and target company using the language model 45, and can output a draft proposal to the target company by providing the outputted research results and product information to the language model 45. This makes it easy to create proposal content for introducing the product to the target company. Furthermore, since it can acquire not only information related to the product but also basic information about the target company, it can also explore the problems that the product solves from information unrelated to the product.

[0099] Figure 17 is a sequence diagram showing an example of a different process in the system of Figure 1. The sequence diagram in Figure 17 differs in that it performs the proposal draft prompt creation process without performing the processes in steps S12 and S13 of Figure 5. Here, the transmission of product information (step S14) is performed at the same time as the transmission of the theme and target company (step S11) in the sequence diagram of Figure 17. Even with this processing, the server device 1 can perform the proposal draft prompt creation process using the research results and product information. Therefore, it can output a proposal draft (steps S21 and S22).

[0100] Therefore, even in a system like the one shown in Figure 17, the server device 1 can acquire the research theme and target company, output research results regarding the theme and target company using the language model 45, and output a draft proposal to the target company by providing the outputted research results and product information to the language model 45. This makes it easy to create proposal content for introducing the product to the target company. Furthermore, since it can acquire not only information related to the product but also basic information about the target company, it can also explore the problems that the product solves from information unrelated to the product.

[0101] In the above configuration, program 16 is stored in the storage unit 14 of server device 1, and the control unit 11 of server device 1 executes the processing of program 16. However, for example, program 16 may be stored in the storage unit 24 of terminal device 2, and the control unit 21 of terminal device 2 may directly access the generation server device 4 to execute the processing of program 16. Alternatively, part of program 16 may be executed in terminal device 2, and the other part of program 16 may be executed in server device 1, allowing terminal device 2 and server device 1 to operate collaboratively. Furthermore, in the above configuration, the language model 45 is stored in the generation server device 4, but the language model 45 may be stored in server device 1 or terminal device 2, and it may operate on either or both terminal device 2 and server device 1 without accessing the generation server device 4.

[0102] The program in program 16 may be referred to as a program product, software, or software product, which may be provided on a recording medium or distributed via a communication network.

[0103] The forms of this disclosure are illustrative in all respects and not restrictive. The scope of the invention is not limited to those shown in the above disclosure but is shown by the claims, and all modifications within the meaning and scope equivalent to the claims are intended.

[0104] Furthermore, the sequences shown in each embodiment described above are not limited, and within a reasonable scope, the order of each processing step may be changed, and multiple processes may be executed in parallel. The processing entity for each process is not limited, and within a reasonable scope, the processing of each device may be executed by other devices.

[0105] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, although the claims do not use the form of a multi-claim that further references a multi-claim (multi-multi-claim), it may be a combination that uses the form of a multi-multi-claim that references all higher-level claims. [Explanation of Symbols]

[0106] 1. Information processing device (server device) 11 Control Unit 12 Communications Department 13 Reading Unit 14 Storage section 15 Portable storage media 16 Programs (Program Products) 19 bus 2. Information processing terminal (terminal device) 21 Control Unit 22 Communications Department 23 Reading section 24 Memory section 25 Portable storage media 26 Display section 27 Input section 29 bus 3 Network 4. Generation Server Device 41 Control Unit 42 Communications Department 43 Reading Unit 44 Storage section 45 Language Models 49 bus< / example>

Claims

1. Information processing device, Obtain the research topic and target companies, The language model outputs research results regarding the aforementioned theme and the aforementioned target company. By providing the outputted research results and product information to the language model, a draft proposal for the target company is generated. Information processing methods.

2. The language model generates keywords for searching the theme, Based on the aforementioned keywords, the research results are output. The information processing method according to claim 1.

3. Based on the generated keywords, collect articles related to the theme. Based on the aforementioned article, output the research results. The information processing method according to claim 2.

4. The language model extracts sentences related to the target company and the theme from each of the collected articles. The information processing method according to claim 3.

5. By providing the language model with prompts to extract, for each collected article, whether or not it is related to the theme, the sentences within the article related to the theme, and the company name that is the subject of the sentences, the language model extracts, for each article, whether or not it is related to the theme, the sentences within the article related to the theme, and the company name that is the subject of the sentences. Extract sentences from the aforementioned article that are related to the aforementioned theme and whose subject is the aforementioned target company. The information processing method according to claim 4.

6. The research results are output by providing the text of each article to the language model and having it summarize it. The information processing method according to claim 4.

7. The system outputs information including the research results, which include summaries of multiple texts and links to each text, the generated keywords, and links to articles related to the target company. The information processing method according to claim 6.

8. The language model outputs multiple research results for each of the different themes. By providing the language model with the multiple research results and product information output, the draft proposal for the target company is generated. The information processing method according to claim 1.

9. The keyword is generated by providing the language model with the theme, a command to generate keywords for searching the theme, and a prompt containing sample queries and answers. Based on the aforementioned keywords, the research results are output. The information processing method according to claim 1.

10. The aforementioned product information includes any of the following: the content of the product, past proposals related to the product, and information on company conditions that may be suitable for the product. The information processing method according to claim 1.

11. The proposed draft is output by providing the language model with prompts including multiple research results, product information, and templates. The template includes fields for outputting the challenges of the target company, the documents supporting the challenges of the target company, and information for accessing the sources of the documents supporting the challenges of the target company. The information processing method according to claim 1.

12. Obtain the research topic and target companies, The language model outputs research results regarding the aforementioned theme and the aforementioned target company. By providing the outputted research results and product information to the language model, a draft proposal for the target company is generated. A program that instructs a computer to perform a process.

13. It includes a control unit, and the control unit is Obtain the research topic and target companies, The language model outputs research results regarding the aforementioned theme and the aforementioned target company. By providing the outputted research results and product information to the language model, a draft proposal for the target company is generated. Information processing device.

Images