Generating program, information processing device, and generating method

Abstract

To provide a technology for providing new value using a large-scale language model to generate business ideas.SOLUTION: A generating program makes a computer execute: a step to acquire references; a step to specify a sentence included in the reference for a prescribed instruction sentence defined to generate business ideas from specified information; and a step to output a business idea based on a result obtained from a large-scale language model by inputting the instruction sentence, in which the sentence is specified, into the large-scale language model.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a generation program, an information processing device, and a generation method. [Background technology]

[0002] Technologies have been developed to support users in creating ideas. In this regard, Japanese Patent Laid-Open Publication No. 2005-284548 (Patent Document 1) discloses a "creative idea support device that uses a combination of a problem analysis method, an idea creation method, and a scenario creation method to support the creation of proposals for a problem" (paragraph

[0001] ). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2005-284548 A Summary of the Invention [Problem to be solved by the invention]

[0004] Recently, large-scale language models have been developed. The large-scale language models are language models trained with a huge amount of text data and are trained to be able to process various natural languages. When a sentence is input, the large-scale language model outputs an answer to the sentence.

[0005] Large-scale language models can be applied to various services, but there are still few examples of them being realized as concrete services. In this regard, it is desirable to use large-scale language models to generate business ideas and provide new value. [Means for solving the problem]

[0006] In one example of the present disclosure, a business idea generation program is provided, which causes a computer to execute the steps of acquiring literature, specifying a sentence contained in the literature for a predetermined instruction defined to generate a business idea from specified information, and inputting the instruction with the specified sentence into a large-scale language model to output a business idea based on a result obtained from the large-scale language model.

[0007] In one example of the present disclosure, the text is an abstract of the above-mentioned publication.

[0008] In one example of the present disclosure, the document is an article.

[0009] In one example of the present disclosure, the step of specifying further includes specifying a topic related to the article for the predetermined instruction.

[0010] In one example of the present disclosure, in the step of specifying, for each of the plurality of topics, a combination of the topic and an abstract of a paper related to the topic is specified in order.

[0011] In one example of the present disclosure, the output step includes a step of accepting a selection of one of the multiple topics and a step of outputting a business idea corresponding to a combination of the topic selected in the accepting step and an abstract of a paper related to the topic.

[0012] In one example of the present disclosure, the step of specifying further includes specifying customer company information for the predetermined instruction text.

[0013] In another example of the present disclosure, an information processing device capable of generating a business idea is provided. The information processing device includes a control unit for operating the information processing device. The control unit executes a process of acquiring a document, a process of specifying a sentence included in the document for a predetermined instruction defined to generate a business idea from specified information, and a process of inputting the instruction with the specified sentence into a large-scale language model to output the business idea based on a result obtained from the large-scale language model.

[0014] In another example of the present disclosure, a computer-implemented method for generating a business idea is provided, the method comprising the steps of acquiring a document, specifying a sentence contained in the document for a predetermined instruction defined to generate a business idea from specified information, and inputting the instruction with the specified sentence into a large-scale language model to output a business idea based on a result obtained from the large-scale language model.

[0015] The above and other objects, features, aspects and advantages of the present invention will become apparent from the following detailed description of the invention taken in conjunction with the accompanying drawings. [Brief description of the drawings]

[0016] [Figure 1] FIG. 1 illustrates an example of a device configuration of an information processing system. [Diagram 2] FIG. 1 is a diagram showing an outline of a process for generating a business idea. [Diagram 3] FIG. 2 is a schematic diagram illustrating an example of a hardware configuration of an information processing device. [Figure 4] FIG. 11 is a diagram showing an example of paper category information. [Diagram 5] FIG. 1 is a diagram illustrating an example of a paper database. [Figure 6] 1 is a flowchart illustrating a process for generating business ideas from paper abstracts. [Figure 7]It is a flowchart showing a process of generating business ideas from a paper abstract. [Figure 8] It is a diagram showing an example of an instruction statement. [Figure 9] It is a diagram showing an example of output data. [Figure 10] It is a diagram showing an example of a selection screen. [Figure 11] It is a diagram showing an example of an output screen.

Modes for Carrying Out the Invention

[0017] Hereinafter, each embodiment according to the present invention will be described with reference to the drawings. In the following description, the same parts and components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated. Note that each embodiment and each modification described below may be selectively combined as appropriate.

[0018] <A. Information Processing System 10> First, with reference to FIG. 1, the device configuration of the information processing system 10 will be described. FIG. 1 is a diagram showing an example of the device configuration of the information processing system 10.

[0019] As shown in FIG. 1, the information processing system 10 includes an information processing device 100, a user terminal 200, and a server 300. The information processing device 100, the user terminal 200, and the server 300 are configured to be communicable with each other through a network NW (for example, the Internet).

[0020] The information processing device 100 is, for example, a notebook or desktop PC (Personal Computer), a tablet terminal, a smartphone, or other computer equipped with a communication function. The number of information processing devices 100 constituting the information processing system 10 may be one or two or more. The information processing device 100 is, for example, owned by a company "A".

[0021] The user terminal 200 is, for example, a notebook or desktop PC, a tablet terminal, a smartphone, or any other computer with a communication function. The number of user terminals 200 constituting the information processing system 10 may be one, or may be two or more. The user terminal 200 is owned, for example, by a company "B". The company "B" may be the same as the company "A" or may be different from the company "A". Alternatively, the user terminal 200 may be owned by an individual.

[0022] The server 300 is, for example, a notebook or desktop PC, a tablet terminal, a smartphone, or any other computer equipped with a communication function. The number of servers 300 constituting the information processing system 10 may be one, or two or more. The server 300 is operated, for example, by a company "C." The company "C" may be the same as the companies "A" and "B," or may be different from the companies "A" and "B."

[0023] The server 300 stores a large-scale language model 324. The large-scale language model 324 is a language model trained on a huge amount of text data of more than several billions, and is trained to be able to process various natural languages. The large-scale language model 324 is also called LLM (Large Language Models). The large-scale language model 324 is trained to generate an output according to an instruction sentence when the instruction sentence is input.

[0024] Examples of large-scale language models 324 include the GPT series, such as GPT-3 (Generative Pretrained Transformer) and GPT-4, PaLM (Scaling Language Modeling with Pathways), LLaMA (Large Language Model Meta AI), and known LLMs.

[0025] Company "C", for example, publishes an API (Application Programming Interface) for utilizing the functions of the large language model 324. As a result, designers and general users of Company "A" can utilize the functions of the large language model 324 through this API.

[0026] In addition, various processes described in this specification may be implemented in the information processing apparatus 100, may be implemented in the user terminal 200, may be implemented in the server 300, or may be implemented in other computers.

[0027] Also, in the above description, an example where the information processing system 10 includes the server 300 has been described, but the information processing system 10 may not include the server 300. In this case, the information processing system 10 is composed of one or more information processing apparatuses 100 and one or more user terminals 200.

[0028] <B. Overview> The information processing apparatus 100 has a function of generating business ideas from the text included in the documents. The generated business ideas are presented to, for example, the above-mentioned Company "B".

[0029] As used in this specification, the "document" means data including text. Examples of the text include, for example, papers, books, newspapers, and patent documents. In the following, the explanation will be given taking a paper as an example, but the "document" is not limited to papers.

[0030] Also, as used in this specification, the "text" means some or all of the text data described in the above-mentioned document. An example of the text is the abstract of the above-mentioned document. In the following, the explanation will be given taking the abstract as an example, but the text is not limited to the abstract.

[0031] In addition, the term "abstract" as used herein means a summary of a document. The abstract may be defined, for example, as a sentence. The abstract may be a summary provided in the document, a summary generated from the document using a large-scale language model, or a summary input by a user.

[0032] In addition, the term "business idea" as used herein means an idea that forms the basis of a new product, a new service, a new business, or a new research topic.

[0033] An overview of the function of generating a business idea 130 from an article abstract 123 will be described below with reference to Fig. 2. Fig. 2 is a diagram showing an outline of the process of generating a business idea 130.

[0034] First, information processing device 100 acquires article abstract 123. The source from which article abstract 123 is acquired is arbitrary. As an example, article abstract 123 is acquired from a second article database 126 (see FIG. 3) stored in a storage device in information processing device 100, which will be described later.

[0035] Next, information processing device 100 refers to a predetermined instruction statement 128. Instruction statement 128 is, for example, registered in advance in information processing device 100 as a template. Instruction statement 128 is defined to generate a business idea from specified information. Instruction statement 128 includes argument portion 129A. Information processing device 100 specifies the acquired paper abstract 123 for argument portion 129A.

[0036] The instruction sentence 128 specifying the paper abstract 123 is input to the large-scale language model 324. When the large-scale language model 324 receives the instruction sentence 128, it generates an answer according to the instruction sentence 128.

[0037] The information processing apparatus 100 outputs a business idea 130 based on an answer obtained from the large language model 324. The number of business ideas 130 output may be one or plural. The business idea 130 is represented, for example, by a sentence.

[0038] The output destination of the business idea 130 is arbitrary. As an example, the output destination is the display of the information processing apparatus 100 or the display of the user terminal 200.

[0039] As described above, the information processing apparatus 100 presents the user with the business idea 130 that can be recalled from the paper abstract 123 by using the large language model 324. As a result, the user can get inspiration regarding a new product, a new service, a new business, or a new research theme.

[0040] <C. Hardware Configuration> Next, with reference to FIG. 3, the hardware configuration of the information processing apparatus 100 shown in FIG. 1 described above will be described.

[0041] Note that the hardware configuration of the user terminal 200 shown in FIG. 1 and the hardware configuration of the server 300 shown in FIG. 1 are the same as those of the information processing apparatus 100, and thus will not be described.

[0042] FIG. 3 is a schematic diagram showing an example of the hardware configuration of the information processing apparatus 100. As shown in FIG. 3, the information processing apparatus 100 includes a control device 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a communication interface 104, a display interface 105, an input interface 107, and an auxiliary storage device 120. These components are connected to a bus 110.

[0043] The control device 101 is configured, for example, by at least one integrated circuit. The integrated circuit may be configured, for example, by at least one central processing unit (CPU), at least one graphics processing unit (GPU), at least one application specific integrated circuit (ASIC), at least one field programmable gate array (FPGA), or a combination thereof.

[0044] The control device 101 controls the operation of the information processing device 100 by executing various programs such as a generation program 122 for a business idea 130 and an operating system. Based on receiving an execution command for various programs, the control device 101 reads the programs from the auxiliary storage device 120 or the ROM 102 to the RAM 103. The RAM 103 functions as a working memory and temporarily stores various data required for the execution of the various programs.

[0045] A LAN (Local Area Network), an antenna, and the like are connected to the communication interface 104. The information processing device 100 exchanges data with external devices via the communication interface 104. The external devices include, for example, a user terminal 200, a server 300, and other communication devices.

[0046] A display 106 is connected to the display interface 105. The display interface 105 sends an image signal for displaying an image to the display 106 in accordance with a command from the control device 101 or the like. The display 106 is, for example, a liquid crystal display, an organic EL (Electro Luminescence) display, or other display device. The display 106 may be configured integrally with the information processing device 100, or may be configured separately from the information processing device 100.

[0047] An input device 108 is connected to the input interface 107. The input device 108 is, for example, a mouse, a keyboard, a touch panel, or any other device capable of receiving user operations. Note that the input device 108 may be integrally configured with the information processing apparatus 100 or may be configured separately from the information processing apparatus 100.

[0048] The auxiliary storage device 120 is, for example, a hard disk, a flash memory, an SSD (Solid State Drive), and other storage media. The auxiliary storage device 120 stores a generation program 122, paper category information 124 described later, a first paper database 125 described later, a second paper database 126 described later, and the above-described instruction text 128, etc. These storage locations are not limited to the auxiliary storage device 120 and may be stored in a storage area of the control device 101 (for example, a cache memory, etc.), the ROM 102, the RAM 103, an external device, or the like.

[0049] Note that the generation program 122 may be provided not as a single program but incorporated into a part of an arbitrary program. Even a program that does not include such a part of the module does not deviate from the gist of the generation program 122 according to the present embodiment. Further, part or all of the functions provided by the generation program 122 may be realized by dedicated hardware. Further, the information processing apparatus 100 may be configured in a form such as a so-called cloud service in which at least one server executes a part of the processing of the generation program 122.

[0050] <D. Data Structure>

[0051] (D1. Paper Category Information 124) Next, with reference to FIG. 4, the paper category information 124 shown in FIG. 3 will be described. FIG. 4 is a diagram showing an example of the paper category information 124.

[0052] The paper category information 124, for example, associates the number of papers with a topic for each paper category type.

[0053] The paper category defined in the paper category information 124 is classification information indicating the type of paper. The paper category may be defined, for example, by a character string, a numeric string, or a symbol string, or may be defined by at least one combination of letters, numbers, and symbols.

[0054] Each paper category is associated with the total number of papers belonging to that paper category and topics related to that paper category. A topic is a tag that indicates what subject or theme the associated paper category is related to. The number of topics associated with a paper category may be one or more. As an example, the number is 100. Each topic is pre-arranged in order of relevance to the associated paper category.

[0055] The information specified in the paper category information 124 is not limited to the example in Fig. 4, and more information may be specified. As an example, the paper category information 124 may further specify the transition of the number of papers by paper category. The transition is shown, for example, by the number of papers by year.

[0056] (D2. 1st Paper Database 125) Next, the first paper database 125 shown in FIG. 3 will be described.

[0057] The first paper database 125 is, for example, a database that stores paper data from all over the world. The paper data is collected, for example, from the Internet. The number of paper data stored in the first paper database 125 is, for example, about 100 million. Each paper data included in the first paper database 125 is associated with not only the content of the paper, but also various information related to the paper (for example, the paper title, the paper abstract, the author name, and cited paper information).

[0058] (D3. 2nd Paper Database 126) Next, the second paper database 126 shown in Fig. 3 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the second paper database 126.

[0059] The second paper database 126 has a parent-child relationship with the above-mentioned first paper database 125. That is, the second paper database 126 is composed of paper data extracted from the above-mentioned first paper database 125. The second paper database 126 specifies various information related to papers. For example, the second paper database 126 associates a paper category, a paper abstract, a number of citations, and a degree of relevance by paper ID (Identification).

[0060] The paper ID defined in the second paper database 126 is an identifier of the paper. The paper ID may be defined, for example, as a character string, a numeric string, or a symbol string, or may be defined as at least one combination of letters, numbers, and symbols.

[0061] The paper categories defined in the second paper database 126 are information indicating the classification to which each paper belongs. The paper categories correspond to the paper categories defined in the paper category information 124 described above.

[0062] The article abstract defined in the second article database 126 is information indicating a summary of each article. The abstract may be, for example, 100 characters or less, or 1000 characters or less.

[0063] The citation count defined in the second paper database 126 is the number of times each paper is cited by other papers.

[0064] The relevance level defined in the second paper database 126 is a numerical value indicating the degree of relevance between each of a plurality of predefined topics and a paper. As an example, more than 1000 topics are predefined. The topics defined in the second paper database 126 correspond to the topics defined in the paper category information 124 described above.

[0065] The information defined in the second paper database 126 is not limited to the example in Fig. 5, and more information may be defined. As an example, in the second paper database 126, the title and author name of the paper may be further defined for each paper ID.

[0066] <E.フローチャート> Next, a process flow for generating a business idea from an article abstract will be described with reference to FIGS.

[0067] 6 and 7 are flow charts showing a process for generating business ideas from paper abstracts. The process shown in FIG. 7 is carried out subsequent to the process shown in FIG.

[0068] 6 and 7 are realized by the control device 101 of the information processing device 100 executing the above-mentioned generation program 122. In another aspect, a part or all of the processes may be executed by circuit elements or other hardware.

[0069] In step S100, the control device 101 acquires corporate information of the client to whom the business idea is proposed. Examples of the corporate information include the industry classification of the client, the business of the client, and the research theme of the client.

[0070] The method of acquiring the company information is arbitrary. As an example, a person in charge asks a customer about the company information, and the person in charge inputs the company information into the information processing device 100. As another example, the customer inputs his / her own company information into the user terminal 200. In this case, the input company information is transmitted from the user terminal 200 to the information processing device 100.

[0071] In step S102, the control device 101 generates the above-mentioned second paper database 126 from the above-mentioned first paper database 125 based on the company information acquired in step S100. At this time, the control device 101 acquires paper data related to the company information acquired in step S100 from the paper data stored in the first paper database 125, and configures the second paper database 126 with the acquired paper data.

[0072] More specifically, first, a first search query for the first paper database 125 is generated based on company information. The first search query may be generated by a person or may be generated by the control device 101. Typically, the first search query includes company information. Preferably, the company information included in the first search query includes at least one of the company's research theme and business theme. The control device 101 inputs the generated first search query into the first paper database 125 and acquires the paper data obtained as the search result (hereinafter, also referred to as "first paper data group"). The control device 101 configures the second paper database 126 with the first paper data group.

[0073] It should be noted that even more paper data may be stored in the second paper database 126. As an example, the control device 101 generates a second search query for the first paper database 125 from each paper information of the first paper data group (for example, the DOI (Digital Object Identifier) ​​of the cited paper). Next, the control device 101 inputs the generated second search query into the first paper database 125 and acquires the paper data obtained as the search result (hereinafter also referred to as the "second paper data group"). Next, the control device 101 stores the second paper data group in the second paper database 126.

[0074] In step S104, the control device 101 acquires a topic for each paper stored in the second paper database 126, and assigns a topic to each paper.

[0075] Note that the method of acquiring topics is arbitrary. As one example, the control device 101 acquires keywords described in each paper as topics. As another example, the control device 101 acquires topics related to each paper by using an existing topic extraction algorithm. Examples of the topic extraction algorithm include PLSA (Probabilistic Latent Semantic Analysis) and LDA (Latent Dirichlet Allocation).

[0076] In step S112, the control device 101 selects a paper category with reference to the above-mentioned paper category information 124. As an example, the control device 101 selects the paper category with the largest number of papers from among the paper categories defined in the paper category information 124.

[0077] In step S114, the control device 101 selects a topic with reference to the above-mentioned paper category information 124. As an example, the control device 101 selects the topic with the highest relevance among the topics associated with the paper category selected in step S112. As described above, the topics defined in the paper category information 124 are pre-arranged in order of relevance with the associated paper category. Therefore, the control device 101 selects the topic defined at the top among the topics associated with the paper category selected in step S112.

[0078] In step S116, the control device 101 selects an article abstract based on the above-mentioned second article database 126, the article category selected in step S112, and the topic selected in step S114.

[0079] More specifically, first, the control device 101 identifies papers belonging to the paper category selected in step S112 from among the papers defined in the second paper database 126. Next, the control device 101 refers to the second paper database 126 to identify, from among the identified papers, papers that have the topic selected in step S114. Next, the control device 101 refers to the second paper database 126 to identify, from among the identified papers, the paper that has been cited the most, and selects a paper abstract associated with that paper.

[0080] In step S118, the control device 101 generates an instruction statement 128 for generating a business idea. Fig. 8 is a diagram showing an example of the instruction statement 128.

[0081] 8, instruction 128 includes instruction 128A defined to generate a business idea from specified information. Instruction 128A is defined to generate a business idea based on information specified in argument portions 129A to 129C.

[0082] The control device 101 specifies the paper abstract selected in step S116 for argument part 129A. The control device 101 also specifies the topic selected in step S114 for argument part 129B. Furthermore, the control device 101 also specifies the company information acquired in step S100 for argument part 129C.

[0083] In step S120, the control device 101 transmits the generated instruction statement 128 to the server 300. Next, the server 300 inputs the received instruction statement 128 to the large-scale language model 324. As a result, the large-scale language model 324 generates an answer corresponding to the instruction statement 128. The generated answer is transmitted from the server 300 to the information processing device 100. The control device 101 of the information processing device 100 acquires the business idea included in the answer.

[0084] In step S122, the control device 101 acquires all the topics defined in the above-mentioned second paper database 126. Alternatively, the control device 101 may acquire a part of the topics defined in the above-mentioned second paper database 126.

[0085] In step S124, the control device 101 calculates an MMR (Maximal Marginal Relevance) score between each topic acquired in step S122 and the topic selected in step S114. MMR is a method for searching for sentences related to a search key sentence from among multiple sentences to be searched, and ranking search results to ensure versatility of the search results. With this method, topics related to the topic selected in step S114 are ranked higher, while each topic is ranked to eliminate redundancy.

[0086] In step S126, the control device 101 selects the topic with the Nth largest MMR score. The initial value of “N” is 2.

[0087] In step S128, the control device 101 selects an article abstract based on the second article database 126 described above and the topic selected in step S126.

[0088] More specifically, first, the control device 101 identifies a paper having the topic selected in step S126 from among the papers defined in the second paper database 126. Next, the control device 101 refers to the second paper database 126 to identify the most highly cited paper from among the identified papers, and selects the paper abstract associated with that paper.

[0089] In step S130, the control device 101 specifies various information for the above-mentioned directive 128. More specifically, the control device 101 specifies the paper abstract selected in step S128 for argument section 129A in the directive 128. The control device 101 also specifies the topic selected in step S126 for argument section 129B. Furthermore, the control device 101 also specifies the company information acquired in step S100 for argument section 129C.

[0090] In step S132, the control device 101 transmits the generated instruction statement 128 to the server 300. Next, the server 300 inputs the received instruction statement 128 to the large-scale language model 324. As a result, the large-scale language model 324 generates an answer corresponding to the instruction statement 128. The generated answer is transmitted from the server 300 to the information processing device 100. The control device 101 of the information processing device 100 acquires the business idea included in the answer.

[0091] In step S140, the control device 101 judges whether the value of the variable "N" is smaller than a predetermined value. The predetermined value may be a fixed value (for example, 100) or may be determined according to the number of topics acquired in step S122. If the control device 101 judges that the value of the variable "N" is smaller than the predetermined value (YES in step S140), it switches control to step S142. If not (NO in step S140), the control device 101 switches control to step S150.

[0092] In step S142, the control device 101 increments "N." That is, the control device 101 adds "1" to "N." After that, the control device 101 returns the process to step S126.

[0093] In step S150, the control device 101 generates output data based on the business ideas acquired in steps S120 and S132. Fig. 9 is a diagram showing the output data 132 as an example.

[0094] The output data 132 is used when generating an output screen 400B described later. In the example of Fig. 9, the output data 132 associates an article category, a topic, and one or more business ideas for each article ID.

[0095] The topic shown in the output data 132 corresponds to the topic selected in steps S114 and S126. The business idea shown in the output data 132 corresponds to the business idea obtained in steps S120 and S132.

[0096] In the above, an example has been described in which the abstract of the paper, the topic, and the company information are specified in the instruction statement 128, but it is sufficient that at least the abstract of the paper is specified in the instruction statement 128. Preferably, in addition to the abstract of the paper, at least one of the topic and the company information is specified in the instruction statement 128.

[0097] As described above, for each of the plurality of topics, the control device 101 designates a combination of the topic and the paper abstract related to the topic in the instruction sentence 128. Thereby, a business idea evoked from the combination of the topic and the paper abstract is generated.

[0098] Note that the execution order of the processes is not limited to the examples shown in FIGS. 6 and 7. As an example, the process of step S122 may be executed before the process of step S114.

[0099] Also, in the above description, an example in which topics corresponding to each paper are generated in step S104 has been described, but the topics do not necessarily have to be generated. As an example, the topics may be defined in advance.

[0100] Furthermore, in the above steps S124, S126, S128, S130, S132, and S140, an example in which topics are selected in the order of the MMR scores and instruction sentences corresponding to the selected topics are generated in order has been described, but the method of selecting topics used for generating the instruction sentences is not limited to this example. As an example, the instruction sentences may be generated for all the topics acquired in step S122. <F. Output screen> Next, with reference to FIGS. 10 and 11, an output screen generated based on the output data 132 will be described. FIG. 10 is a diagram showing a selection screen 400A. FIG. 11 is a diagram showing an output screen 400B.

[0101] The output screen 400B shown in FIG. 11 is one of the transition destinations from the selection screen 400A shown in FIG. 10. The selection screen 400A and the output screen 400B are displayed, for example, on the display of the user terminal 200.

[0102] As shown in FIG. 10, on the selection screen 400A, one or more topics are displayed separately by paper category. The selection screen 400A is generated, for example, by the information processing device 100.

[0103] More specifically, the information processing device 100 refers to the above-mentioned paper category information 124 to acquire each paper category and a topic associated with each paper category. Next, the information processing device 100 arranges the corresponding topics adjacent to each paper category on the selection screen 400A. The generated selection screen 400A is displayed on the user terminal 200. Note that the selection screen 400A may be generated by the user terminal 200 instead of the information processing device 100.

[0104] The selection screen 400A is configured to allow the user to select one of the topics. Based on the user's selection of one of the topics in the selection screen 400A, the information processing device 100 or the user terminal 200 outputs a business idea corresponding to a combination of the selected topic and the abstract of the paper associated with the topic.

[0105] The business idea is output as output screen 400B. Output screen 400B includes paper category 412, topic 414, and business ideas 416A to 416C.

[0106] Topic 414 corresponds to topic 401 selected on selection screen 400A. Article category 412 corresponds to the article category adjacent to topic 401 on selection screen 400A.

[0107] The output screen 400B is generated, for example, by the information processing device 100. More specifically, the information processing device 100 refers to the above-mentioned output data 132 to acquire business ideas 416A to 416C associated with a combination of the paper category 412 and the topic 414. Then, the information processing device 100 generates an output screen 400B including the paper category 412, the topic 414, and the acquired business ideas 416A to 416C. Note that the output screen 400B may be generated by the user terminal 200 instead of the information processing device 100.

[0108] The display format of the business ideas 416A to 416C is arbitrary. As an example, a plurality of sticky note images are displayed on the output screen 400B, and each business idea is displayed within each sticky note image.

[0109] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is defined by the claims, not the above description, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0110] 10 Information processing system, 100 Information processing device, 101 Control device, 102 ROM, 103 RAM, 104 Communication interface, 105 Display interface, 106 Display, 107 Input interface, 108 Input device, 110 Bus, 120 Auxiliary storage device, 122 Generator, 123 Paper abstract, 124 Paper category information, 125 First paper database, 126 Second paper database, 128 Instruction, 128A Instruction, 129A Argument section, 129B Argument section, 129C Argument section, 130 Business idea, 132 Output data, 200 User terminal, 300 Server, 324 Large-scale language model, 400A Selection screen, 400B Output screen, 401 Topic, 412 Paper category, 414 Topic, 416A Business idea, 416B Business idea, 416C Business idea.

Claims

1. A business idea generation program, The generation program is configured to: Obtaining documents; A step of specifying a sentence contained in the document for a predetermined instruction defined to generate a business idea from the specified information; and outputting a business idea based on a result obtained from a large-scale language model by inputting the instruction sentence in which the sentence is specified into the large-scale language model.

2. The generating program of claim 1 , wherein the text is an abstract of the document.

3. The generating program according to claim 2 , wherein the document is a paper.

4. The generating program according to claim 3 , wherein the step of specifying further includes specifying a topic related to the paper for the predetermined instruction sentence.

5. 5. The generating program according to claim 4, wherein in the specifying step, for each of a plurality of the topics, a combination of the topic and an abstract of a paper related to the topic is specified in order.

6. The output step includes: accepting a selection of any of a plurality of said topics; 6. The generating program according to claim 5, further comprising a step of outputting a business idea corresponding to a combination of the topic selected in the receiving step and an abstract of a paper related to the topic.

7. 7. The generating program according to claim 1, wherein in said designating step, customer company information is further designated for said predetermined instruction statement.

8. An information processing device capable of generating business ideas, A control unit for operating the information processing device, The control unit is A process of obtaining documents; A process of specifying a sentence contained in the document in response to a predetermined instruction defined to generate a business idea from the specified information; and outputting a business idea based on a result obtained from a large-scale language model by inputting the instruction sentence in which the sentence is specified into the large-scale language model.

9. 1. A computer implemented method for business idea generation, comprising: Obtaining documents; A step of specifying a sentence contained in the document for a predetermined instruction defined to generate a business idea from the specified information; and outputting a business idea based on a result obtained from a large-scale language model by inputting the instruction sentence in which the sentence is specified into the large-scale language model.

Images