Intent sales support device

Abstract

To provide an intent sales support device for supporting intent sales to journalists by automating a process of transmitting documents such as article proposals to the journalists.SOLUTION: An intent sales support device 1 includes an article collection unit 111 for collecting articles containing information for identifying a journalist from the Internet, an intent analysis unit 112 for analyzing an intent, the tendency of articles posted by each journalist, by processing using a large-scale language model including the collected articles in input, and a document generation unit 117 for generating a document containing information contributing to creation of an article by the journalist by processing using the large-scale language model including an analysis result of the intent by the intent analysis unit 112 in input.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus for supporting intent sales. [Background technology]

[0002] Using external newspapers, magazines, etc. for public relations can provide a reliable and objective source of information, which strengthens the company's credibility and expertise. In addition, incorporating a third-party perspective can increase the diversity and persuasiveness of public relations content. However, it is not easy to get public relations topics featured in external newspapers, magazines, etc.

[0003] Due to the above circumstances, there is a need for a method to support intent sales to journalists, which involves analyzing journalists' interests and selling them article topics based on the results of that analysis. The "intent" of journalists here includes the fields and topics that the journalist tends to report on, their reporting style, target readership, the content of their past articles, the reactions and engagement to articles written by the journalist, and the frequency of article postings.

[0004] Regarding technology for providing information according to the interests of a target, Patent Document 1 discloses technology for personalized delivery of content items to users of a social networking system, which uses attributes of content posted on a brand page in combination with characteristics of the user profile of the social networking system user to select content to be presented to the user when the brand page is accessed.

[0005] The technology described in Patent Document 1 is a technology that allows various contents posted on a brand page to be shared with users. This may increase the likelihood of interest. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2018-129052 Summary of the Invention [Problem to be solved by the invention]

[0007] Incidentally, in intent-driven sales to journalists, it is important to provide the journalist with a proposal. If the proposal contains information necessary for the journalist to write an article, the likelihood that the journalist will write the desired article can be increased. The technology in Patent Document 1 is limited to selecting content based on a user profile, but does not disclose how a journalist who does not necessarily disclose a user profile indicating intent can compile information necessary for writing an article in a proposal. Therefore, the technology described in Patent Document 1 has room for further improvement in terms of supporting intent-driven sales to journalists.

[0008] The present invention has been made in consideration of the above circumstances, and an object of the present invention is to support intent-based sales to journalists by, for example, automating the process of sending documents such as article proposals to journalists. [Means for solving the problem]

[0009] As a result of intensive research into solving the above-mentioned problems, the inventors have found that the above-mentioned object can be achieved by collecting so-called bylined articles from the Internet, analyzing the intent of journalists through processing using a large-scale language model based on the bylined articles, and generating article proposals through processing using a large-scale language model based on the analysis results. The inventors have then completed the present invention. Specifically, the present invention provides the following:

[0010] The present invention provides an intent sales support device that includes an article collection unit that collects articles from the Internet that are accompanied by information that identifies the reporter, an intent analysis unit that analyzes the intent, which is a tendency of articles posted by the reporter, by processing using a large-scale language model that includes the articles as input, and a document generation unit that generates a document that includes information that contributes to the creation of the article by the reporter by processing using a large-scale language model that includes as input the results of the intent analysis by the intent analysis unit.

[0011] The present invention analyzes intent, which is the tendency of articles submitted by journalists, by processing signed articles and the like collected from the Internet by an article collection unit using a large-scale language model. Then, the document generation unit of the present invention generates a document containing information that contributes to the creation of articles by the journalists by processing using a large-scale language model that includes the analysis results as input. This automates the intent analysis, which is the tendency of articles submitted by journalists, and the generation of proposals and the like based on this analysis, in the process of sending article proposals to journalists. Therefore, the present invention can support intent sales to journalists by automating the process of sending documents such as article proposals to journalists. [Effects of the Invention]

[0012] The present invention can support intent sales to journalists by automating the process of sending documents such as article proposals to journalists. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing an example of the hardware and software configuration of a system S according to this embodiment. [Figure 2] FIG. 2 is an example of the intent analysis database 121. [Figure 3] FIG. 3 is an example of the company database 122. [Figure 4] FIG. 4 is a main flowchart showing an example of a preferable flow of the assistance process executed by the assistance device 1 of this embodiment. [Figure 5] FIG. 5 is a continuation of FIG. [Figure 6] FIG. 6 is a continuation of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of the present invention will be described in detail below with reference to the drawings.

[0015] <System S> Fig. 1 is a block diagram showing an example of the hardware configuration and software configuration of a system S of this embodiment. An example of a preferred embodiment of the system S of this embodiment will be described below with reference to Fig. 1. The system S of this embodiment is configured to include a support device 1. The support device 1 is capable of communicating with a terminal T via a network N.

[0016] [Support device 1] The support device 1 realizes each software component shown in FIG. 1 using hardware components such as a control unit 11, a storage unit 12, and a communication unit 13. The support device 1 then executes support processing to support intent sales to journalists by automating the process of sending article proposals to journalists using each software component. The type of support device 1 is not particularly limited. The type of support device 1 may be, for example, various server devices, cloud servers, etc.

[0017] [Control unit 11] The control unit 11 includes a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), and the like.

[0018] The control unit 11 cooperates with the storage unit 12 and / or the communication unit 13 as necessary. The control unit 11 then realizes software components of the program of this embodiment executed by the support device 1, such as an article collection unit 111, an intent analysis unit 112, an advertising effectiveness measurement unit 113, an analysis result management unit 114, a reporter extraction unit 115, a data acquisition unit 116, a document generation unit 117, a document transmission unit 118, and a machine learning unit 119.

[0019] [Storage unit 12] The memory unit 12 is a device in which data and / or files are stored, and includes a storage unit that stores data non-temporarily using a hard disk, a semiconductor memory, a recording medium, a memory card, or the like.

[0020] The storage unit 12 stores programs executed by the microcomputer, articles collected by the article collection unit 111, etc. The storage unit 12 preferably further stores an intent analysis database 121 for managing intent analysis results. Additionally, the storage unit 12 preferably further stores a company database 122 for managing data on topics desired to be covered in articles exemplified by data on companies, etc.

[0021] Preferably, the memory unit 12 further stores data associating the URL of an article with the name or pen name of the reporter, so as to enable identification of the reporter from the URL of the article. Preferably, the memory unit 12 further stores feedback from recipients of the document generated by the support device 1 of this embodiment, so as to enable collection and utilization of feedback on the generated document. Preferably, the memory unit 12 further stores associations between the reporter and / or the media in which the reporter publishes the article and the format, so as to enable document generation in a format corresponding to the reporter and / or the media in which the reporter publishes the article. Preferably, the memory unit 12 stores, for each reporter, information on a channel, which is a means of contacting the reporter.

[0022] (Intent Analysis Database 121) The storage unit 12 preferably stores an intent analysis database 121, which is a database that stores intent analysis results. The intent analysis database 121 stores data that associates journalists with analysis results of intents, which are trends in articles posted by the journalists. The intent analysis database 121 is managed by the analysis result management unit 114.

[0023] Intent includes topics, keywords, sentiment, subtopics, time series of interests, reporting style, etc. Topics are the main theme, topic, etc. of an article. Keywords are important words, phrases, etc. in an article. Sentiment is the tone, emotional tendency, etc. of an article. Subtopics indicate finer categories within the main topic. Time series of interests is data showing changes in topics, interests, etc. over time. Reporting style is a style related to reporting, such as objective reporting, opinion articles, investigative reporting, etc.

[0024] To facilitate data management, the above data is preferably stored in association with an analysis result ID that identifies the analysis result. The analysis result preferably includes one or more of various information related to the article, exemplified by analysis results of the article's influence, analysis results of reader engagement with the article, identification results of article trend patterns, comparison results with related articles, etc. The article's influence includes the article's influence and so-called reach evaluation, which indicates article views. The engagement analysis results include engagement measurement results and analysis results of reader responses to the article. The article trend pattern identification results include analysis results of current and past trend patterns related to the article. The comparison results with related articles include comparison analysis results with other articles dealing with similar topics, etc.

[0025] 2 is an example of the intent analysis database 121. This example includes data related to the analysis results of intents associated with the analysis result IDs "A0001," "A0002," and "A0003."

[0026] The data related to analysis result ID "A0001" includes the results of an analysis of the reporter "Kagawa reporter"'s intent, such as the topic "lifestyle," keyword "lifestyle, events, cooking," sentiment "calm," subtopic "lifestyle, cooking," time series of interests "...," and reporting style "investigative reporting." The data related to analysis result ID "A0001" also includes various information related to the article, such as the analysis results of the article's influence "Editor-in-Chief of △△△△△ Magazine," the analysis results of reader engagement with the article "△△ million engagements," the identification results of the article's trend patterns "...," and the results of comparison with related articles "...."

[0027] The data related to analysis result ID "A0002" includes the results of an analysis of the reporter "S Mizu reporter's" intent, such as the topic "crime," keywords "criminal case, real culprit, scandal, false accusation," sentiment "objective, righteous indignation," subtopic "...," time series of interest "...," and reporting style "investigative reporting." Additionally, the data related to analysis result ID "A0002" includes various information related to the article, such as the analysis result of the article's influence "Winner of the Galaxy Award, etc.", the analysis result of reader engagement with the article "△△△ million engagements," the identification result of the article's trend pattern "...," and the comparison result with related articles "...."

[0028] The data related to analysis result ID "A0003" includes the results of an analysis of the reporter "Tasaki reporter's" intent, such as the topic "society," keyword "COVID-19, PCR testing," sentiment "subjective, sensational," subtopic "COVID-19," time series of interest "...", and reporting style "announcement reporting." The data related to analysis result ID "A0003" also includes various information related to the article, such as the analysis results of the article's influence "...", the analysis results of reader engagement with the article "△△ million engagements", the identification results of the article's trend patterns "...", and the results of comparison with related articles "...".

[0029] By storing the above data in the intent analysis database 121, the support device 1 can extract, for example, a reporter "Kagawa reporter" as an information provider for an article related to the topic "Japanese cuisine."Then, the support device 1 can generate a document for the reporter who will be conducting investigative reporting, containing various information that will be useful when conducting an investigation related to the topic.

[0030] (Company Database 122) The storage unit 12 preferably stores a company database 122, which is a database that stores data related to topics desired to be covered in articles. The company database 122 stores topics desired to be covered in articles in association with topic data, which is data related to the topics. The data stored in the company database 122 is acquired by the data acquisition unit 116. The topics are, for example, specific companies, specific products, specific services, etc.

[0031] The topic data includes, for example, company information, etc. The company information includes, for example, the characteristics of the company, etc. (corporate characteristics), the company's response to industry trends, stories related to the company, campaigns and events related to the company, features of products and services offered by the company, insights from the company's management, social responsibility initiatives by the company, technological innovations by the company, success stories by the company, and outlook for future plans for the company, etc. To facilitate data management, the above data is preferably stored in association with a topic ID that identifies the topic.

[0032] 3 is an example of the company database 122. This example includes data on topics associated with topic IDs such as "T0001."

[0033] The data for topic ID "T0001" includes topic data for the topic "Japanese restaurant chain △△." This topic data includes company characteristics "mainly operating within Tokyo," response to industry trends "sustainability and local production for local consumption," story "since its founding, preserving the traditions of Japanese cuisine while also challenging itself to create new dishes...," campaigns and events "seasonal special menus...," product and service characteristics "diverse menus and high-quality service," management insights "pursuing a sustainable business model," social responsibility initiatives "contribution to the local community and educational support," technological innovations "digitalization and efficiency," success stories "successfully expanding stores not only in urban areas but also into the suburbs...," and future plan outlook "expansion both domestically and internationally...."

[0034] By storing the above data in the company database 122, the support device 1 can acquire target data, which is data that a reporter can use to write an article about, for example, the topic "Japanese restaurant chain △△." The support device 1 can then provide the reporter with a document generated based on the target data. This can increase the likelihood that the reporter will write an article based on the target data.

[0035] [Communications Section 13] The communication unit 13 is not particularly limited as long as it connects the support device 1 to the network N and enables communication with the terminal T, etc. An example of the communication unit 13 is a network card compatible with the Ethernet standard.

[0036] [Network N] The type of the network N is not particularly limited as long as it allows the support device 1 and the terminal T to communicate with each other. The type of the network N is, for example, the Internet, a mobile phone network, a wireless LAN, or the like.

[0037] [Terminal T] There is no particular limitation on the type of terminal T. The terminal T may be, for example, a personal computer, a laptop computer, a smartphone, a tablet terminal, or the like.

[0038] [Main flowchart of support processing] Fig. 4 is a main flowchart showing an example of a preferable flow of the support processing executed by the support device 1 of this embodiment. Fig. 5 is a diagram continuing from Fig. 4. Fig. 6 is a diagram continuing from Fig. 5. Below, an example of a preferable flow of the support processing executed by the support device 1 of this embodiment will be described with reference to Figs. 4 to 6.

[0039] First, as part of the support process, the support device 1 executes a series of processes to collect articles attached with information identifying the reporter from the Internet. Steps S1 to S2 are an example of this process. Since the target of collection in this process is "articles attached with information identifying the reporter," the support device 1 can analyze the interests and concerns of the reporter, i.e., the reporter's intent, based on the collected articles.

[0040] [Step S1: Determine whether to collect articles] The control unit 11 cooperates with the storage unit 12 and the communication unit 13 to execute the article collection unit 111. Then, the control unit 11 executes a process of determining whether to collect articles with information identifying a reporter from the Internet using the article collection unit 111 (step S1, article collection determination step). If it is determined that the articles should be collected, the control unit 11 shifts the process to step S2. If it is not determined that the articles should be collected, the control unit 11 shifts the process to step S7.

[0041] [Step S2: Collect articles] The control unit 11 executes a process of collecting articles attached with information identifying the reporter from the Internet by the article collection unit 111 (step S2, article collection step). The control unit 11 moves the process to step S3.

[0042] The "information that identifies the reporter" in this step is various information attached to the article that can be used to identify the reporter, such as the reporter's signature included in a signed article, the reporter's name or pen name determined based on the article's URL, or the reporter's name or pen name stored in the Author field included in the article's metadata.

[0043] [Step S3: Analyze intent] The control unit 11 executes a process of analyzing intent, which is a tendency of articles posted by reporters related to the articles, by processing the articles collected in the article collection step as input by the article collection unit 111 (step S3, intent analysis step). The control unit 11 moves the process to step S4.

[0044] The process of analyzing intent in the intent analysis step is not particularly limited. This process may include a procedure for referencing analysis data received from an external source. This process preferably includes a process for analyzing intent, which is a trend in articles posted by journalists related to the articles, by processing using a large-scale language model that includes the articles collected in the article collection step as input. This process is realized by inputting, for example, prompts asking about each element constituting intent, such as topics, keywords, sentiment, subtopics, time series of interests, and reporting style, and the article to be analyzed for intent, into the large-scale language model. In this case, it is preferable that the large-scale language model has undergone preprocessing, such as fine-tuning and pre-training, related to intent analysis. This preprocessing is performed, for example, using training data that associates articles with elements constituting intent and examples of analysis results related to those elements.

[0045] This enables the support device 1 to perform topic identification to identify the main theme or topic of an article, keyword identification to identify important words or phrases, sentiment analysis to analyze the tone or emotional trend of an article, subtopic analysis to identify finer categories within the main topic, time series analysis of interest to track changes in topics or interests over time, and reporting style identification to identify styles such as objective reporting, opinion articles, and investigative reporting.

[0046] In addition, the intent analysis step preferably includes processing for analyzing current and past trends and patterns related to the reporter's intent and for performing a comparative analysis with other articles dealing with similar topics. This processing is realized using time-series data of intent stored in the intent analysis database 121, data of other articles stored in the storage unit 12, etc. In addition, the intent analysis step preferably includes processing for analyzing the language used by the reporter and the wording preferred by the reporter.

[0047] As part of the support process, the support device 1 preferably executes a series of processes for measuring advertising effectiveness. Steps S4 to S5 are an example of such processes. Through such processes, the support device 1 can measure advertising effectiveness, exemplified by evaluations of article influence, reach, and engagement, and extract journalists based on advertising effectiveness such as influence.

[0048] [Step S4: Determine whether to measure advertising effectiveness] The control unit 11 cooperates with the storage unit 12 to execute the advertising effectiveness measurement unit 113. Then, the control unit 11 executes a process of determining whether to measure the advertising effectiveness related to the article written by the reporter related to the intent analysis step, using the advertising effectiveness measurement unit 113 (step S4, advertising effectiveness measurement determination step). If it is determined that the advertising effectiveness should be measured, the control unit 11 shifts the process to step S5. If it is not determined that the advertising effectiveness should be measured, the control unit 11 shifts the process to step S6.

[0049] [Step S5: Measuring advertising effectiveness] The control unit 11 executes a process of measuring the advertising effectiveness related to the article written by the reporter related to the intent analysis step (step S5, advertising effectiveness measurement step) by the advertising effectiveness measurement unit 113. The control unit 11 shifts the process to step S6.

[0050] The measurement related to the advertising effectiveness measurement step is not particularly limited. The measurement includes, for example, a procedure of collecting various information related to the influence of an article from the Internet and measuring the influence based on the collected information. The various information related to the influence of an article includes, for example, the number of views of the article, the number of comments on the article, the award history of the reporter, the reporter's popularity, and the engagement with the article.

[0051] As part of the assistance process, the assistance device 1 preferably executes a process for managing intent analysis results, etc. Step S6 is an example of such a process. This allows the assistance device 1 to assist intent marketing using intent analysis results, etc.

[0052] [Step S6: Store the analysis results] The control unit 11 executes the analysis result management unit 114 in cooperation with the storage unit 12. Then, the control unit 11 executes a process of storing the analysis results related to the intent analysis step in the intent analysis database 121 by the analysis result management unit 114 (step S6, analysis result management step). The control unit 11 moves the process to step S7.

[0053] Furthermore, when the advertising effectiveness measurement step is performed, the analysis result management step executes a process of storing the measurement results related to the advertising effectiveness measurement step in the intent analysis database 121.

[0054] As part of the support process, the support device 1 executes a process of generating a document including information that contributes to the creation of an article by a reporter based on the intent analysis result, etc. Steps S7 to S11 are an example of this process.

[0055] [Step S7: Determine whether a document generation instruction has been issued] The control unit 11, in cooperation with the storage unit 12 and the communication unit 13, executes a process of determining whether an instruction to generate a document has been issued (step S7, document generation determination step). If it is determined that an instruction has been issued, the control unit 11 proceeds to step S8. If it is not determined that an instruction has been issued, the control unit 11 proceeds to step S14. This determination includes, for example, a procedure of determining that an instruction to generate a document has been issued when the instruction has been received from the terminal T.

[0056] [Step S8: Extract reporters] The control unit 11 cooperates with the memory unit 12 and the communication unit 13 to execute the reporter extraction unit 115. Then, the control unit 11 executes a process to extract reporters who will be provided with the document generated in response to the instruction related to the document generation determination step, using the reporter extraction unit 115 (step S8, reporter extraction step). The control unit 11 then moves the process to step S9.

[0057] The reporter extraction step includes a procedure for extracting a reporter specified from instructions related to the document generation determination step, a procedure for extracting a reporter using the intent analysis results, etc. The procedure for extracting a reporter using the intent analysis results includes, for example, a procedure for extracting a reporter related to a topic by comparing a topic desired to be covered in an article with the analysis results related to the intent analysis step. This allows the support device 1 to extract a reporter whose intent is related to the topic and provide the reporter with a document containing information that will contribute to the creation of the article.

[0058] The procedure for extracting reporters based on advertising effectiveness preferably further includes a procedure for extracting reporters based on advertising effectiveness. For example, the procedure for extracting reporters based on advertising effectiveness includes a procedure for extracting, from among multiple reporters, reporters related to a topic desired to be covered in an article, reporters whose advertising effectiveness meets given conditions. This allows the support device 1 to extract reporters who meet desired conditions, such as reporters with high advertising effectiveness (e.g., influence, engagement, etc.), from among reporters whose intent is related to the topic, and provide the reporters with documents containing information that will contribute to the creation of the article.

[0059] As part of the assistance process, the assistance device 1 preferably executes a series of processes for acquiring data related to a topic. Steps S9 to S10 are an example of such processes. Through such processes, the assistance device 1 acquires target data, which is data related to the topic that a reporter will use to write an article, from a database such as the corporate database 122, and generates a document to be provided to the reporter through processing using a large-scale language model that includes the acquired target data as input. Thus, the assistance device 1 can provide the reporter with a document that is richer in information that will contribute to writing an article.

[0060] [Data Preparation Steps] When the above-described series of processes are executed, it is preferable that the support process includes a data preparation step of collecting data related to the topic desired to be covered in the article and storing it in the company database 122 so that data related to the topic is stored in advance in the company database 122.

[0061] [Step S9: Determine whether to acquire data related to the topic] The control unit 11 cooperates with the storage unit 12 to execute the data acquisition unit 116. Then, the control unit 11 executes a process of determining whether to acquire data related to a topic desired to be covered in an article by the data acquisition unit 116 (step S9, data acquisition determination step). If it is determined that data should be acquired, the control unit 11 shifts the process to step S10. If it is not determined that data should be acquired, the control unit 11 shifts the process to step S11.

[0062] The procedure for determining in the data acquisition determination step is not particularly limited. For example, the procedure includes a procedure for determining to acquire data when data related to a topic desired to be covered in an article is stored in advance in a database such as the company database 122.

[0063] [Step S10: Obtain data on the topic] The control unit 11 executes a process of acquiring, by the data acquisition unit 116, target data, which is data related to the topic desired to be covered in the article and which the reporter extracted in the reporter extraction step will use to write the article, from a database such as the company database 122 (step S10, data acquisition step). The control unit 11 then proceeds to step S11.

[0064] The procedure for acquiring data in the data acquisition step is not particularly limited. For example, the procedure includes generating a query for acquiring target data based on the intent analysis result and acquiring the target data using the query. If a large-scale language model has been subjected to pre-training or the like related to the generation, the query may be generated using such a large-scale language model.

[0065] [Step S11: Generate document] The control unit 11 cooperates with the storage unit 12 to execute the document generation unit 117. Then, the control unit 11 executes a process of generating a document including information that contributes to the creation of an article by the reporter extracted in the reporter extraction step, by processing using a large-scale language model that includes as input at least the intent analysis result by the intent analysis unit 112, using the document generation unit 117 (step S11, document generation step). The control unit 11 then proceeds to step S12.

[0066] By generating documents through processing using a large-scale language model that includes the results of intent analysis as input, the support device 1 can create documents as proposals based on the reporter's intent, i.e., create target-oriented content. This also enables the support device 1 to generate documents that propose innovative and attractive proposals. In other words, the support device 1 can generate documents that include creative proposals.

[0067] The procedure for generating a document in the document generation step is not particularly limited. In order to generate a document that is rich in information that contributes to the creation of an article, the procedure preferably includes a procedure for generating a document by processing using a large-scale language model that includes as input the target data acquired in the data acquisition step.

[0068] The target data includes, for example, information and analytical data such as basic information about the company, its history, major products and services, the current state and trends of the industry to which the company belongs, the competitive situation within the industry, the company's market position and influence, the latest news and events related to the company, profiles of the company's management team, i.e., key executives and leaders, analysis results of financial status, profitability, and growth potential, the company's social responsibility and sustainability, the company's technological innovation and research and development efforts, and the company's reputation and brand image in public. This allows the support device 1 to generate documents that make persuasive proposals, i.e., data-driven proposals, using this various information and analytical data. Furthermore, by including diverse information related to a topic in the target data, the support device 1 can generate documents that explore diverse themes, including proposals from different angles and perspectives.

[0069] If the document generation step includes a procedure for generating a document by processing using a large-scale language model that includes target data as input, the procedure preferably includes a procedure for customizing information about a company or the like. Examples of customization targets include highlighting company characteristics, responding to industry trends, utilizing storytelling, introducing campaigns and events, highlighting product and service features, management insights, social responsibility initiatives, highlighting technological innovations, presenting success stories, and outlooks on future plans. Examples of customization include emphasizing items designated by the user for emphasis and removing items designated by the user for omission. This allows the support device 1 to generate a document customized according to the user's wishes.

[0070] If the analysis of intent includes a language used by a journalist, so as to generate a document in a language tailored to the journalist, the steps preferably include generating the document by processing with a large scale language model, the input of which includes instructions to generate the document in that language. If the analysis of intent includes a language preferred by a journalist, so as to generate a document in a language tailored to the journalist, the steps preferably include generating the document by processing with a large scale language model, the input of which includes instructions to generate the document in that language.

[0071] In order to generate documents that are more attractive as proposals with integrated visual elements, when the large-scale language model is associated with an image database and / or an image generative neural network, the document generation step preferably includes a procedure for generating documents with visual content, which is realized by referencing an image database and / or generating images using an image generative neural network.

[0072] In order to generate a document as a proposal in a format customized to the journalist's preferences and the media format, the document generation step preferably includes a procedure for generating a document in a format associated with the journalist and / or the media in which the journalist will publish an article. This procedure is realized, for example, by referring to the association between the journalist and / or the media in which the journalist will publish an article and the format stored in the storage unit 12.

[0073] As part of the support process, the support device 1 preferably executes a series of processes for sending the document generated in the document generation step to the reporter. Steps S12 to S13 are an example of this process. Through this process, the support device 1 consistently supports everything from intent analysis to the generation and transmission of documents that contribute to intent sales, thereby reducing the user's efforts related to intent sales.

[0074] [Step S12: Determine whether to send the document] The control unit 11 cooperates with the storage unit 12 and the communication unit 13 to execute the document transmission unit 118. Then, the control unit 11 executes a process of determining whether to transmit the document generated in the document generation step by the document transmission unit 118 (step S12, document transmission determination step). If it is determined that the document should be transmitted, the control unit 11 shifts the process to step S13. If it is not determined that the document should be transmitted, the control unit 11 shifts the process to step S14.

[0075] The procedure for determining whether to send a document in the document transmission determination step is not particularly limited. Preferably, the procedure includes a step of determining whether to send a document if the user has set automatic transmission to the reporters extracted in the reporter extraction step, in order to reduce the user's effort in transmitting the document. Furthermore, the procedure preferably includes a step of determining whether to send a document if the user has confirmed the document and authorized its transmission, in order to prevent inappropriate documents from being sent.

[0076] In order to transmit documents in accordance with a distribution plan determined based on various circumstances, the procedure preferably includes a step of determining whether to transmit the documents when the timing specified in the distribution plan is met, such as a distribution plan that matches the journalist's intent or a distribution plan that matches the optimal time.

[0077] [Step S13: Send document] The control unit 11 executes a process of transmitting the document generated in the document generation step to the reporter involved in the reporter extraction step by the document transmission unit 118 (step S13, document transmission step). The control unit 11 moves the process to step S14.

[0078] The procedure for sending the document is not particularly limited. In order to send the document by a means appropriate for the recipient, the document sending step preferably includes a step of sending the document via a channel associated with the reporter from among multiple channels, such as email, social media, or the web. In order to leave a favorable impression on the document recipient, the document sending step preferably includes a step of sending the document with a message appropriate for the recipient. The message appropriate for the recipient may be a message based on a template stored in the storage unit 12, or may be a message generated by a large-scale language model based on the intent of the recipient (the reporter), etc.

[0079] As part of the support process, the support device 1 preferably executes a series of processes to collect feedback from recipients of the document generated in the document generation step and utilize the feedback for improvements. Steps S14 to S16 are an example of such processes. Through these processes, the support device 1 can consistently support the collection and utilization of feedback from recipients who have received documents that contribute to intent sales.

[0080] [Step S14: Determine whether to collect feedback on the submitted document] The control unit 11, in cooperation with the storage unit 12 and the communication unit 13, executes a process of determining whether to collect feedback on the transmitted document (step S14, feedback collection determination step). If it is determined that feedback should be collected, the control unit 11 moves the process to step S15. If it is not determined that feedback should be collected, the control unit 11 returns the process to step S1 and repeats the processes from step S1 to step S16.

[0081] The procedure for determining whether or not to collect feedback is not particularly limited. For example, the procedure includes a step of determining whether or not to collect feedback when feedback is received, when feedback is stored in the storage unit 12, etc. Furthermore, in order to enable periodic feedback collection after sending a document, the procedure preferably includes a step of determining whether or not to collect feedback when a given time has elapsed since the document sending step or the previous feedback collection.

[0082] [Step S15: Collect feedback] The control unit 11 executes a process of collecting feedback on the transmitted document in cooperation with the storage unit 12 and the communication unit 13 (step S15, feedback collection step), and the control unit 11 moves the process to step S16.

[0083] [Step S16: Run machine learning] The control unit 11 executes the machine learning unit 119 in cooperation with the storage unit 12 and the communication unit 13. Then, the control unit 11 executes a process of executing machine learning using the learning data including the data related to the document generated in the document generation step and the feedback collected in the feedback collection step, by the machine learning unit 119 (step S16, machine learning step). The control unit 11 returns the process to step S1 and repeats the processes from step S1 to step S16.

[0084] In order to improve the generation of documents according to the reporter's intent by the large-scale language model, the machine learning step preferably includes a procedure for fine-tuning the large-scale language model based on training data including the document corrected based on the feedback as a target variable and the topic, the reporter, and the reporter's intent as explanatory variables. The correction of the document based on the feedback may be performed manually, but is preferably performed by the large-scale language model to further reduce labor.

[0085] To further improve the generation of documents according to the intent and the data stored in the database, the machine learning step preferably includes a procedure for fine-tuning a large-scale language model based on training data that includes the documents modified based on the feedback as the target variable and the topic, the reporter, the reporter's intent, and data related to the topic as the explanatory variables.

[0086] [Follow-up steps] In order to measure the effectiveness of intent sales through documents, the support process preferably includes a follow-up step of automatically following up on articles based on the documents sent in the document sending step. This step includes, for example, a procedure in which the control unit 11, in cooperation with the storage unit 12 and the communication unit 13, crawls articles written by journalists who are the destinations of the documents on the Internet, and automatically follows up on the articles when it is determined that the articles are based on the documents sent through processing using a large-scale language model, etc. This allows the support device 1 to automatically follow up on articles after the initial distribution.

[0087] [Engagement Tracking Step] In order to continuously measure the effectiveness of intent sales through documents, the advertising effectiveness measurement step preferably includes an engagement tracking step that tracks engagement and responses after delivery of articles based on the documents sent in the document sending step.

[0088] [Report Generation Step] When an engagement tracking step is performed to visualize the effects of intent sales through documents, it is preferable that the support process includes a report generation step that analyzes the effects of article distribution by processing using a large-scale language model that includes the tracking results as input, and generates a report summarizing the results of the analysis.

[0089] [Content Update Step] To ensure the effectiveness of intent sales through documents is sustainable, the support process preferably includes a content update step of generating documents that contribute to the continuous updating of content (articles) based on various tracking results such as responses tracked in the engagement tracking step, etc., and transmitting the generated documents. This generation is realized in the same way as the document generation step, except that various tracking results are included in the input.

[0090] [Obfuscation Step] In order to comply with privacy protection based on legal regulations, the assistance process preferably includes an obfuscation step of obfuscating data related to privacy protection among the various data stored in the storage unit 12. This reduces the risk of insufficient privacy protection due to data leakage, etc.

[0091] <Usage example> The following is an example of how the support device 1 of this embodiment is used.

[0092] [Data preparation] The user works to store data related to the topic that the user wants to cover in the article in the company database 122. This work is performed by the user directly registering various data, instructing the support device 1 to collect data related to the topic, etc.

[0093] [Intent Analysis] The support device 1 processes signed articles and the like collected from the Internet using a large-scale language model and analyzes the intent, which is the tendency of articles posted by journalists. The support device 1 then stores the analysis results in the intent analysis database 121.

[0094] [Intent Sales Implementation] The user specifies a topic and commands the support device 1 to conduct intent sales for that topic. The support device 1 extracts appropriate reporters based on the topic and the intent of each reporter. Then, the support device 1 generates a document containing information that will contribute to the creation of the article by the extracted reporter through processing using a large-scale language model based on the intent analysis results.

[0095] [Article publication] The support device 1 sends the generated document to a journalist. The journalist creates an article based on the document and publishes it on the Internet. The support device 1 follows up on the article and measures the advertising effectiveness of the article. The support device 1 then performs machine learning related to a large-scale language model based on the article, etc., and feeds back the results for the next intent sales.

[0096] It should be noted that within the scope of the concept of the present invention, those skilled in the art may conceive of various modifications and alterations. Therefore, it is understood that such modifications and alterations fall within the scope of the present invention. For example, even if a person skilled in the art appropriately adds, deletes, or modifies components of the above-described embodiment, or adds, omits, or modifies the conditions of a process, such modifications are also included within the scope of the present invention as long as they maintain the gist of the present invention. [Explanation of symbols]

[0097] S System 1 Support equipment 11 Control section 111 Article Collection Department 112 Intent Analysis Unit 113 Advertising Effectiveness Measurement Department 114 Analysis Results Management Department 115 Reporter Extraction Department 116 Data Acquisition Unit 117 Document Generation Unit 118 Document Transmission Department 119 Machine Learning Department 12 Storage section 121 Intent Analysis Database 122 Corporate Database 13 Communications Department N Network T-Terminal

Claims

1. an article collection unit that collects articles from the Internet that are accompanied by information that identifies the reporter; an intent analysis unit that analyzes intent, which is a tendency of articles posted by the journalist, by processing using a large-scale language model that includes the article as an input; a document generation unit that generates a document containing information that contributes to the creation of an article by the reporter through processing using a large-scale language model that includes as input the intent analysis result by the intent analysis unit; An intent sales support device comprising:

2. an analysis result management unit that manages the intent analysis result; a reporter extraction unit that extracts reporters related to a topic desired to be covered in an article by comparing the analysis result with the topic; Furthermore, The analysis result management unit manages analysis results related to a plurality of reporters, the reporter extraction unit extracts reporters related to the topic from the plurality of reporters; the document generation unit generates a document including information that contributes to the creation of an article by the reporter extracted by the reporter extraction unit; The support device according to claim 1 .

3. An advertising effectiveness measurement unit is further provided to measure advertising effectiveness relating to the article written by the reporter, The reporter extraction unit extracts, from the plurality of reporters, reporters related to the topic whose advertising effect satisfies a given condition. The support device according to claim 2 .

4. a data acquisition unit for acquiring data relating to a topic desired to be covered in the article from a database; the data acquisition unit acquires, from the database, target data that is data that the reporter will use to write an article, among data related to the topic, based on the analysis result of the intent; the document generation unit generates the document by processing using a large-scale language model that includes the target data as input. The support device according to claim 1 .

5. The support device according to claim 1 , further comprising a document sending unit that sends the document generated by the document generating unit to a reporter involved in the generation of the document.

Images