Data processing system, data processing method, and program

Abstract

Provided is a data processing system comprising: a document data acquisition unit that acquires document data; a slide generation processing unit that, in response to receiving an instruction to convert the document data into slides, generates a prompt including an instruction to divide the document data into a plurality of document blocks and generate slide data including a plurality of slides corresponding to the plurality of document blocks, inputs the prompt into a generative AI model, and acquires the slide data output from the generative AI model; and an association unit that associates each of the plurality of slides with each of the plurality of document blocks of the document data and stores the slide data in a memory unit.

Description

[Technical Field]

[0001] The present invention relates to a data processing system, a data processing method, and a program. [Background technology]

[0002] Patent document 1 describes an information processing device that includes an acquisition unit that acquires user information about a user who is the target of image generation, a first generation unit that generates target character information, which is character information used for image generation, based on the user information, and a second generation unit that generates a display image, which is an image to be displayed on a screen used by the user, from the target character information using an image generation model, which is a learning model that has been trained to generate images from character information. [Prior art document] [Patent documents] [Patent Document 1] JP 2024-074097 A Summary of the Invention [Means for solving the problem]

[0003] According to one embodiment of the present invention, a data processing system is provided. The data processing system may include a document data acquisition unit that acquires document data. In response to receiving an instruction to convert the document data into slides, the data processing system may include a slide generation processing unit that generates a prompt including an instruction to divide the document data into multiple document blocks and generate slide data including multiple slides corresponding to the multiple document blocks, inputs the prompt to a generative AI model, and acquires slide data output from the generative AI model. The data processing system may include an association unit that associates each of the multiple slides with each of the multiple document blocks of the document data and stores the slide data in a storage unit.

[0004] The data processing device may include an instruction receiving unit that receives instructions for the slide data, and a processing execution unit that, when the instruction receiving unit receives an instruction for the slide data, executes processing corresponding to the instruction on the document data corresponding to the slide data instead of the slide data. When the instruction receiving unit receives a search instruction for the slide data, the processing execution unit may execute a search process on the document data in accordance with the search instruction. When the instruction receiving unit receives a correction instruction for the slide data, the processing execution unit may execute a correction process on the document data in accordance with the correction instruction.

[0005] In any of the data processing devices, the slide generation processing unit may include in the prompt an instruction to generate the slide data with priority given to ease of understanding when viewed by humans over suitability for computer processing.

[0006] In any of the data processing devices, the slide generation processing unit may include in the prompt an instruction to divide the document data into a plurality of document blocks so that the contents of each document block fit on one slide.

[0007] In any of the data processing devices, the slide generation processing unit may include in the prompt a plurality of slide formats and an instruction to select, for each of the plurality of document blocks, a format suitable for the content of the document block from the plurality of formats and generate a slide in the selected format. The slide generation processing unit may include in the prompt a plurality of content images that are areas conveying the content of the slide to be placed in the format, and the instruction to select, from the plurality of content images, a content image suitable for placement in the selected format based on the content of the document block, and generate a slide in which the selected content image is placed in the selected format.

[0008] In any of the data processing devices, the slide generation processing unit may include in the prompt more specific instructions for portions of the slide that have a lower degree of freedom in generation by the generative AI model.

[0009] In any of the data processing devices, the slide generation processing unit may generate the prompt including the instruction to generate the plurality of slides in SVG (Scalable Vector Graphics) format.

[0010] In any of the data processing devices, the slide generation processing unit may include in the prompt instructions to review the slide data from a designer's perspective and a business professional's perspective after generating the slide data and to modify the slide data as necessary.

[0011] In any of the data processing devices, the slide generation processing unit may include instructions to output an explanation for each of the plurality of slides in the prompt, input the prompt to the generative AI model, and acquire the slide data and the explanations output from the generative AI model, and the association unit may associate the plurality of explanations for the plurality of slides with the document data.

[0012] According to one embodiment of the present invention, there is provided a data processing method executed by a computer. The data processing method may include a document data acquisition step of acquiring document data. The data processing method may include a slide generation processing step of, in response to receiving an instruction to convert the document data into slides, generating a prompt including an instruction to divide the document data into multiple document blocks and generate slide data including multiple slides corresponding to the multiple document blocks, inputting the prompt to a generative AI model, and acquiring slide data output from the generative AI model. The data processing method may include an association step of associating the multiple slides with the multiple document blocks, respectively, and storing the slide data and the document data in a storage unit.

[0013] According to one embodiment of the present invention, there is provided a program for causing a computer to execute the data processing method.

[0014] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions. [Brief explanation of the drawings]

[0015] [Figure 1] An example of a data processing system 10 is shown schematically. [Figure 2] FIG. 10 is an explanatory diagram for explaining generation of slide data 500. [Figure 3] 10 is an explanatory diagram for explaining the processing content by data processing system 10 when an instruction for slide data 500 is received. FIG. [Figure 4] 1 shows an example of a functional configuration of a server 100. [Figure 5] 10 shows an example of a processing flow by the server 100. [Figure 6] 10 shows an example of a processing flow by the server 100. [Figure 7]1 shows an example of a functional configuration of a user device 300 when the data processing system 10 is realized by the user device 300. [Figure 8] An example of the hardware configuration of a computer 1200 that functions as the server 100 or the user device 300 is shown in schematic form. DETAILED DESCRIPTION OF THE INVENTION

[0016] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] Creating slides in PowerPoint and other applications traditionally required a lot of time and effort, especially for creating visual elements. Recently, automatic slide generation technology using large-scale language models (LLMs) has emerged. As with traditional slide generation using LLMs, emphasis is placed on creating visual elements, with insufficient consideration given to computer processing such as search on slides or inputting slides into AI for use. In contrast, the data processing system 10 according to this embodiment has the function of generating and managing slide data from document data in a form suitable for subsequent computer processing or AI use, for example.

[0018] 1 schematically illustrates an example of a data processing system 10. The data processing system 10 may be realized by a server 100. The data processing system 10 may also be realized by the server 100 and another device. For example, the data processing system 10 is realized by the server 100 and a user device 300 operated by a user 30. The data processing system 10 may also be realized by the user device 300. The user device 300 may be a PC (Personal Computer), a smartphone, a tablet terminal, or the like.

[0019] The data processing system 10 may include an AI system 200. The AI ​​system 200 includes a generative AI model 210. The generative AI model 210 may be an LLM. Note that the server 100 may also include the generative AI model 210.

[0020] The server 100, the AI ​​system 200, and the user device 300 may communicate via a network 20. The network 20 may include a cloud. The network 20 may include the Internet. The network 20 may include a mobile communication network. The network 20 may include a LAN (Local Area Network).

[0021] The data processing system 10 according to this embodiment generates slide data from document data in accordance with instructions from the user 30. For example, the data processing system 10 generates document data while chatting with the user 30 using the generative AI model 210. Then, in response to receiving an instruction to create slides from the user 30, the data processing system 10 generates a prompt including an instruction to generate slide data from the target document data, inputs the prompt to the generative AI model 210, obtains the slide data output from the generative AI model 210, and provides it to the user 30.

[0022] 2 is an explanatory diagram illustrating the generation of slide data 500. Document data 400 may be data consisting of only text data. Document data 400 may also be data consisting of text data and image data such as figures, tables, and graphs. Document data 400 may also be data in Markdown format.

[0023] The data processing system 10 may generate a prompt including instructions to divide the document data 400 into multiple document blocks 410 and generate slide data 500 including multiple slides 510 corresponding to the multiple document blocks 410, and input the generated prompt to the generative AI model 210.

[0024] By inputting such a prompt into the generative AI model 210, the generative AI model 210 divides the document data 400 into multiple document blocks 410, and for each of the multiple document blocks 410, generates a slide 510 containing the content thereof, thereby generating slide data 500 consisting of multiple slides 510.

[0025] The data processing system 10 may include in the prompt an instruction to generate the slide 510 as an image. For example, the data processing system 10 may include in the prompt an instruction to generate the slide 510 as a vector-format image. Examples of vector-format images include, but are not limited to, Scalable Vector Graphics (SVG), Encapsulated PostScript File (EPS), Adobe Illustrator File (AI), Collaborative Design Activity (COLLADA), PostScript (PS), and Enhanced MetaFile (EMF). As a specific example, the data processing system 10 may include in the prompt an instruction to generate the slide 510 as an SVG-format image. The data processing system 10 may also include in the prompt an instruction to generate the slide 510 as a raster-format image. Examples of raster format images include, but are not limited to, JPEG (Joint Photographic Experts Group), PNG (Portable Network Graphics), GIF (Graphics Interchange Format), BMP (Bitmap Image File), TIFF (Tagged Image File Format), and PSD (Adobe Photoshop File).

[0026] The data processing system 10 may generate a prompt including an instruction to output information capable of identifying each of the plurality of document blocks 410 in the document data 400 and information indicating a correspondence between the plurality of document blocks 410 and the plurality of slides 510. Then, the data processing system 10 may store the slide data 500 by associating each of the plurality of slides 510 with each of the plurality of document blocks 410 in the document data 400.

[0027] The data processing system 10 provides the slide data 500 to the user 30, or, with the permission of the user 30, provides the slide data 500 to another user 30. When the data processing system 10 receives an instruction regarding the slide data 500, it may execute processing corresponding to the instruction on the document data 400 corresponding to the slide data 500 instead of the slide data 500.

[0028] 3 is an explanatory diagram for explaining the processing content by the data processing system 10 when an instruction for searching the slide data 500 is received. In FIG. 3, a case where an instruction for searching the slide data 500 is received is illustrated as an example.

[0029] 3 , the server 100 stores slide data 500 and document data 400 in association with each other. When the server 100 receives a search instruction for the slide data 500 from the user 30 via the user device 300, the server 100 executes a search process on the document data 400 corresponding to the slide data 500 instead of the slide data 500. For example, the server 100 receives a search query from the user device 300 and executes a search process on the slide data 500. The server 100 then provides the search results to the user device 300.

[0030] 4 shows an example of the functional configuration of the server 100. The server 100 includes a storage unit 102, a UI unit 104, a document data acquisition unit 106, a slide generation processing unit 108, an association unit 110, an instruction receiving unit 122, and a processing execution unit 124. Note that it is not essential for the server 100 to include all of these units.

[0031] The UI unit 104 interacts with the user 30. The UI unit 104 acquires data input by the user 30 via input devices such as a mouse, keyboard, microphone, and touch panel of the user device 300, and provides data to the user 30 via output devices such as a display and speaker of the user device 300. The UI unit 104 receives, for example, document data 400 prepared by the user 30 from the user device 300. The UI unit 104 stores the received document data 400 in the storage unit 102.

[0032] The UI unit 104 may execute so-called AI chat with the user 30. For example, the UI unit 104 executes the AI ​​chat by inputting data input by the user 30 into the generative AI model 210 and providing data output from the generative AI model 210 to the user 30. The UI unit 104 may generate document data 400 including the contents of the AI ​​chat. The UI unit 104 stores the generated document data 400 in the storage unit 102.

[0033] The document data acquisition unit 106 acquires document data 400. For example, the document data acquisition unit 106 acquires document data 400 received by the UI unit 104 from the storage unit 102. For example, the document data acquisition unit 106 acquires document data 400 generated by the UI unit 104 from the storage unit 102. The document data acquisition unit 106 may receive document data 400 generated in another device from the other device. The UI unit 104 may provide the document data 400 acquired by the document data acquisition unit 106 to the user device 300. The UI unit 104 may display the document data 400 on a display of the user device 300.

[0034] When document data acquisition unit 106 displays document data 400 on the display of user device 300, document data acquisition unit 106 may display document data 400 in a manner that allows an instruction to slide document data 400 to be accepted. For example, document data acquisition unit 106 may display, together with document data 400, an instruction button for accepting an instruction to slide document data 400, or a menu.

[0035] In response to receiving an instruction to create slides from document data 400, slide generation processing unit 108 generates slide data 500 corresponding to document data 400. Slide generation processing unit 108 may generate slide data 500 using generative AI model 210. Slide generation processing unit 108 may generate a prompt including an instruction to generate slide data 500 corresponding to document data 400, input the generated prompt to generative AI model 210, and acquire slide data 500 output from generative AI model 210.

[0036] The slide generation processing unit 108 may generate a prompt including an instruction to divide the document data 400 into a plurality of document blocks 410 and generate slide data 500 including a plurality of slides 510 corresponding to the plurality of document blocks 410. If a prompt including an instruction to simply generate slide data from document data is given to the generative AI model 210, one slide including all of the content of the document data may be generated, or one slide including only some of the information in the document data may be generated. However, by generating such a prompt and inputting it to the generative AI model 210, even if the document data 400 includes a relatively large amount of information, the slide generation processing unit 108 can divide the document data 400 into a plurality of document blocks 410 and cause the generative AI model 210 to generate a plurality of slides 510 each corresponding to the content of each of the plurality of document blocks 410.

[0037] The slide generation processing unit 108 may include in the prompt an instruction to divide the document data 400 into multiple document blocks 410 so that the contents of each document block 410 fit on one slide 510. In this case, the slide generation processing unit 108 may include in the prompt information indicating the size of the slide 510 (e.g., 16:9). If a prompt including an instruction to simply generate multiple slides 510 from the document data 400 is input to the generative AI model 210, the amount of content included in the slides 510 may vary, or information may be omitted from some slides 510 while unnecessary information may be added to others. However, by generating such a prompt and inputting it to the generative AI model 210, the slide generation processing unit 108 increases the likelihood of generating a number of slides 510 that can appropriately express the contents of the document data 400, and reduces the likelihood of a single slide 510 containing excessive information or having some of the content of a document block 410 omitted, resulting in a slide 510 that is difficult for people to understand.

[0038] The slide generation processing unit 108 may include in the prompt multiple formats of the slide 510 and instructions to select a format suitable for the content of each of the multiple document blocks 410 from the multiple formats and generate the slide 510 in the selected format. The multiple formats may include multiple formats unique to each company that should be fixed regardless of the slide content, such as a slide header, footer, and logo. The multiple formats may include formats for a cover, an inside cover, content, an EOF (End Of File), and the like. By generating such a prompt, the slide generation processing unit 108 can increase the likelihood that the slide 510 will be accurately generated in accordance with the prepared format.

[0039] The slide generator 108 may include in the prompt instructions to place the common elements of the format on the slide as is, and the prompt may include instructions to leave the position, size, and color of the common elements unchanged.

[0040] The multiple types of formats may include a content image. A content image is an area placed within a format that conveys the content of the slide. A format with a high degree of fixation, such as a cover, may not include a content image. A content image may indicate the type of content. Examples of content types include text, tables, figures, and graphs. A content image may include information on the arrangement of multiple pieces of content. A content image may include information on how the content is presented.

[0041] As a specific example, a content image shows a layout with a large image on the left and a message on the right. The content image may include information on selecting an image appropriate for the content, adding stylish features such as rounded corners to the image, or making the key message stand out.

[0042] Another content image shows a layout with a large graph or illustration on the left and a message on the right. The content image may include information on how to highlight prominent parts of the graph to make it easier to understand what you want to convey, how to display data clearly, and how to highlight parts of the message that should be emphasized or divide them into blocks.

[0043] Another content image shows a layout with a message on the left and a large image on the right. The content image may include information on selecting an image appropriate for the content, highlighting parts of the message that should be emphasized, or dividing them into blocks.

[0044] Another content image shows a layout with four blocks, each with a background image behind it, and each message written on top of the background. The content image may also include information on how to select a background image that matches the content of each block, and how to design the text so that it is clear which parts should stand out and which parts should not.

[0045] Another content image shows a layout with four blocks, each with a message written in it. The content image may include information such as a design that shows which parts of the text should be prominent and which should not, various shapes, and sizes depending on the content to be conveyed.

[0046] Another content image shows a table representation such as an nxn Excel spreadsheet with headers. The content image may include information about the design to help users understand what has a header and what does not, or to indicate that the rows and columns need to be organized in a more organized way.

[0047] The slide generation processing unit 108 may include in the prompt an instruction to select, from the plurality of types of content images, a content image suitable for placement in the selected format based on the contents of the document block 410, and generate a slide 510 in which the selected content image is placed in the selected format. This increases the likelihood that a slide 510 will be generated that conforms to the prepared format and includes a content image suitable for the contents of the document block from the plurality of types of content images prepared.

[0048] The slide generation processing unit 108 may include more specific instructions in the prompt for portions of the slide 510 for which the generative AI model 210 has less freedom to generate. For example, the slide generation processing unit 108 may generate a prompt that includes more specific instructions for portions of the slide 510 corresponding to the format compared to portions corresponding to the content image. Conversely, the slide generation processing unit 108 may generate a prompt that includes more abstract instructions for portions of the slide 510 corresponding to the content image compared to portions corresponding to the format. Giving specific instructions to the generative AI model 210 makes it easier to obtain output as instructed, while giving abstract instructions makes it easier to demonstrate creativity. Therefore, by generating such prompts, the slide generation processing unit 108 can obtain a slide 510 that accurately follows the format and demonstrates the creativity of the generative AI model 210 in terms of the content image.

[0049] The slide generation processing unit 108 may include in the prompt an instruction to generate the slide 510 as an image. For example, the slide generation processing unit 108 may include in the prompt an instruction to generate the slide 510 as a vector format image. As a specific example, the slide generation processing unit 108 may include in the prompt an instruction to generate the slide 510 as an SVG format image. The slide generation processing unit 108 may also include in the prompt an instruction to generate the slide 510 as a raster format image.

[0050] After generating the slide data 500, the slide generation processing unit 108 may include in the prompt an instruction to review the slide data 500 from the perspective of a designer and a business professional and modify the slide data 500 as necessary. The slide generation processing unit 108 may include in the prompt an instruction to check whether elements overlap with each other. The slide generation processing unit 108 may include in the prompt an instruction to check the sophistication of the business presentation. The slide generation processing unit 108 may specify visual hierarchy, consistency, etc. as the sophistication of the business presentation. The slide generation processing unit 108 may include in the prompt an instruction to check whether the alignment of each element is correct on a pixel-by-pixel basis. The slide generation processing unit 108 may include in the prompt an instruction to check the readability of text (font size, line spacing). The slide generation processing unit 108 may include in the prompt an instruction to check the appropriateness of color contrast. The slide generation processing unit 108 may include in the prompt an instruction to generate the slide 510 taking into account behavior when the screen ratio is changed. This makes it possible to adjust the slide data 500 taking into account both the designer's perspective and the business professional's perspective, contributing to the generation of slide data 500 that is optimized from both a design and business perspective.

[0051] The slide generation processor 108 may include in the prompt an instruction to check the generated slide 510 at the specified actual display size and check at least one of readability, spacing, balance, and browser compatibility.

[0052] The slide generator 108 may generate a prompt including instructions for grasping the structure, main points, and story type for each of the multiple document blocks 410. The story type may indicate the type of content of the document block 410, such as enumeration, comparison, process, timeline, and cause-and-effect relationship. The slide generator 108 may further generate a prompt including instructions for considering a layout suitable for the identified story type. Examples of the layout may include at least one of a card grid, a two-column comparison, a step flow, a timeline, and a fishbone.

[0053] The association unit 110 associates the slide data 500 generated by the slide generation processing unit 108 based on the document data 400 with the document data 400 and stores the slide data 500 in the storage unit 102. The association unit 110 may associate each of the slides 510 with each of the document blocks 410 of the document data 400 and store the slide data 500 in the storage unit 102.

[0054] The UI unit 104 may provide the slide data 500 stored in the storage unit 102 to the user 30. For example, the UI unit 104 transmits the slide data 500 to the user device 300 to display it.

[0055] The instruction receiving unit 122 receives instructions for the slide data 500. The instruction receiving unit 122 receives instructions for the slide data 500 from the user 30, for example, from the user device 300. The instruction receiving unit 122 receives, for example, a search instruction for the slide data 500. The instruction receiving unit 122 receives, for example, a correction instruction for the slide data 500.

[0056] When the instruction receiving unit 122 receives an instruction for the slide data 500, the processing execution unit 124 executes processing corresponding to the instruction on the document data 400 corresponding to the slide data 500, instead of the slide data 500. When the instruction receiving unit 122 receives an instruction for some of the slides 510 among the plurality of slides 510 included in the slide data 500, the processing execution unit 124 may execute processing corresponding to the instruction on one or more document blocks 410 corresponding to the some of the slides 510, instead of the some of the slides 510. When the instruction receiving unit 122 receives an instruction for one or more of the slides 510 among the plurality of slides 510 included in the slide data 500, the processing execution unit 124 may execute processing corresponding to the instruction on one or more document blocks 410 corresponding to the one or more slides 510, instead of the one or more slides 510. The slide data 500 is basically intended to make the contents of the document data 400 easier for people to understand, and tends to make heavy use of visual representations, etc. While visual representations aid human understanding, they can also hinder a computer's ability to grasp the content. In response to this, the data processing system 10 according to this embodiment provides slide data 500 to humans, but when computer processing is required, the document data 400 that forms the basis of the slide data 500 is used for processing. This configuration improves the accuracy of computer processing and also realizes an environment for generating slide data 500 that is specialized for ease of human understanding.

[0057] For example, when the instruction receiving unit 122 receives a search instruction for the slide data 500, the process executing unit 124 executes a search process on the document data 400 in accordance with the search instruction. For example, the instruction receiving unit 122 receives a search query, and the process executing unit 124 executes a search process on the slide data 500 using the search query. As a specific example, the instruction receiving unit 122 receives a text search query, and the process executing unit 124 searches the slide data 500 for a portion that matches the search query. When the slide data 500 is a raster image, text information is generally not stored, making it difficult to perform an accurate search. When the slide data 500 is a vector image, text information is stored, but various tag information and other information are included in a complex manner, making searchability insufficient. In contrast, the process executing unit 124 executes a search process on the document data 400 instead of the slide data 500, thereby achieving a highly accurate search. When the instruction receiving unit 122 receives a search instruction for one or more slides 510 among the multiple slides 510 included in the slide data 500, the processing execution unit 124 may identify one or more document blocks 410 corresponding to the one or more slides 510 and perform a search process on the identified one or more document blocks 410.

[0058] For example, when the instruction receiving unit 122 receives a correction instruction for the slide data 500, the processing execution unit 124 executes a correction process on the document data 400 in accordance with the correction instruction. When the instruction receiving unit 122 receives a correction instruction for the content of the slide data 500, rather than the appearance of the slide data 500, the processing execution unit 124 may execute a correction process on the document data 400 in accordance with the correction instruction. The slide generation processing unit 108 may regenerate the slide data 500 based on the document data 400 corrected by the processing execution unit 124. To make the slide data 500 easier for people to read, the content of the document data 400 may be modified by adding a frame, color, graphs, etc. Therefore, when a correction instruction for the content of the slide data 500 is received, if the correction is to be directly reflected in the slide data 500, it may be difficult to accurately correct the content itself. In contrast, the processing execution unit 124 executes a correction process on the document data 400 instead of the slide data 500, thereby enabling accurate correction of the content itself. When the instruction receiving unit 122 receives a correction instruction for one or more slides 510 among the multiple slides 510 included in the slide data 500, the processing execution unit 124 may identify one or more document blocks 410 corresponding to the one or more slides 510 and perform a correction process on the identified one or more document blocks 410.

[0059] The slide generation processing unit 108 may include in the prompt an instruction to generate slide data 500 that prioritizes ease of understanding when viewed by a human over suitability for computer processing. If a prompt including an instruction to generate slide data 500 is simply input to the generation AI model 210, the decision of what to prioritize when generating the slide data 500 is left to the generation AI model 210. In contrast, by generating such a prompt and inputting it to the generation AI model 210, the slide generation processing unit 108 can generate slide data 500 that prioritizes ease of understanding when viewed by a human over suitability for computer processing. According to the server 100 of this embodiment, when an instruction regarding the slide data 500 is received, the processing execution unit 124 executes processing corresponding to the instruction on the document data 400 instead of the slide data 500. In other words, the slide data 500 itself is not subject to computer processing. This makes it possible to provide slide data 500 that is easier to understand when viewed by a human without degrading computer processing performance.

[0060] The slide generation processing unit 108 may input a prompt to the generative AI model 210, the prompt including an instruction to output a description of each of the slides 510, and acquire the slide data 500 and the descriptions of the slides 510 output from the generative AI model 210. The association unit 110 may associate the descriptions of the slides 510 with the document data 400. When the instruction receiving unit 122 receives an instruction regarding the slide data 500, the processing execution unit 124 may execute processing corresponding to the instruction based on the document data 400 corresponding to the slide data 500 and the descriptions of the slides 510 associated with the document data 400, instead of the slide data 500. A user 30 who previously viewed the slide data 500 may search for the slide data 500 based on their memory of its appearance. For example, the user 30 may want to search for a portion surrounded by a frame or a portion highlighted in bold red. For example, when the instruction receiving unit 122 receives a search query for a framed section, the processing execution unit 124 identifies the framed content of the document data 400 from the multiple descriptions of the multiple slides 510, and provides the search results to the user 30. For example, when the instruction receiving unit 122 receives a search query for a section highlighted in bold red, the processing execution unit 124 identifies the framed content of the document data 400 from the multiple descriptions of the multiple slides 510, and provides the search results to the user 30. This makes it possible to accommodate searches by the user 30 based on their memory of the appearance of the slide data 500.

[0061] 4 illustrates an example in which server 100 includes storage unit 102, UI unit 104, document data acquisition unit 106, slide generation processing unit 108, association unit 110, instruction acceptance unit 122, and process execution unit 124. However, the present invention is not limited to this. For example, server 100 may include storage unit 102, UI unit 104, document data acquisition unit 106, slide generation processing unit 108, and association unit 110, and another device may include instruction acceptance unit 122 and process execution unit 124. In this case, server 100 provides document data 400 and slide data 500 in an associated state to the other device, and the other device stores the received document data 400 and slide data 500 in an associated state.

[0062] 5 shows an example of the processing flow by the server 100. Here, the processing flow will be explained, from when the server 100 generates document data 400 while providing AI chat to the user 30, to when the server 100 generates and stores slide data 500 in accordance with instructions from the user 30.

[0063] In step (sometimes abbreviated as S) 102, the UI unit 104 chats with the user 30. In S104, the UI unit 104 determines whether or not it has received a slide instruction for the document data 400 from the user 30. If it is determined that it has received a slide instruction, the process proceeds to S106.

[0064] In S106, the document data acquisition unit 106 acquires the document data 400 generated by the AI ​​chat. In S108, the slide generation processing unit 108 generates a prompt including an instruction to generate slide data 500 based on the document data 400 acquired by the document data acquisition unit 106 in S106.

[0065] In S110, the slide generation processing unit 108 inputs the prompt generated in S108 to the generative AI model 210 and acquires the slide data 500 output from the generative AI model 210. In S112, the association unit 110 associates the slide data 500 acquired by the slide generation processing unit 108 in S110 with the document data 400 acquired by the document data acquisition unit 106 in S106 and stores them in the storage unit 102. Then, the processing ends.

[0066] 6 shows an example of a processing flow by server 100. Here, the processing flow will be described in which server 100 provides slide data 500 to user 30, receives instructions regarding slide data 500, and executes processing according to the instructions.

[0067] In S202, the UI unit 104 transmits the slide data 500 stored in the storage unit 102 to the user device 300 for display. The user 30 can view the slide data 500 displayed on the user device 300 and issue instructions such as searches and corrections.

[0068] In S204, the instruction receiving unit 122 receives an instruction from the user 30 regarding the slide data 500. The instruction receiving unit 122 receives an instruction from the user device 300.

[0069] In S206, the process execution unit 124 identifies the document data 400 corresponding to the slide data 500 for which the instruction receiving unit 122 received the instruction. In S208, the process execution unit 124 executes the process corresponding to the instruction on the document data 400 identified in S206.

[0070] As described above, the data processing system 10 may be realized by a user device 300. Fig. 7 schematically illustrates an example of the functional configuration of the user device 300 when the data processing system 10 is realized by the user device 300. The user device 300 includes a storage unit 302, a UI unit 304, a document data acquisition unit 306, a slide generation processing unit 308, an association unit 310, an instruction receiving unit 322, and a processing execution unit 324.

[0071] The UI unit 304 interacts with the user 30. The UI unit 304 may accept input from the user 30 via input devices such as a mouse, keyboard, microphone, and touch panel, and provide data to the user 30 via output devices such as a display and speaker. The UI unit 304, for example, acquires document data 400 prepared by the user 30. The UI unit 304 stores the acquired document data 400 in the storage unit 302.

[0072] The UI unit 304 may perform so-called AI chat with the user 30. For example, the UI unit 304 performs AI chat by inputting data input by the user 30 into the generative AI model 210 and providing data output from the generative AI model 210 to the user 30. The UI unit 304 may generate document data 400 including the content of the AI ​​chat. The UI unit 304 stores the generated document data 400 in the storage unit 302.

[0073] The document data acquisition unit 306 acquires document data 400. For example, the document data acquisition unit 306 acquires document data 400 acquired by the UI unit 304 from the storage unit 302. For example, the document data acquisition unit 306 acquires document data 400 generated by the UI unit 304 from the storage unit 302. The document data acquisition unit 306 may receive document data 400 generated in another device from the other device. The UI unit 304 may display the document data 400 acquired by the document data acquisition unit 306 on a display.

[0074] When document data acquisition unit 306 displays document data 400 on a display, it may display document data 400 in a manner that allows an instruction to slide document data 400 to be accepted. For example, document data acquisition unit 306 may display, together with document data 400, an instruction button for accepting an instruction to slide document data 400, or a menu.

[0075] In response to receiving an instruction to create slides from document data 400, slide generation processing unit 308 generates slide data 500 corresponding to document data 400. Slide generation processing unit 308 may generate slide data 500 using generative AI model 210. Slide generation processing unit 308 may generate a prompt including an instruction to generate slide data 500 corresponding to document data 400, input the generated prompt to generative AI model 210, and acquire slide data 500 output from generative AI model 210. Slide generation processing unit 308 may generate the prompt in the same manner as slide generation processing unit 108.

[0076] The association unit 310 associates the slide data 500 generated by the slide generation processing unit 308 based on the document data 400 with the document data 400 and stores the slide data 500 in the storage unit 302. The association unit 310 may associate each of the slides 510 with each of the document blocks 410 of the document data 400 and store the slide data 500 in the storage unit 302.

[0077] The UI unit 304 may provide the slide data 500 stored in the storage unit 302 to the user 30. For example, the UI unit 304 displays the slide data 500 on a display.

[0078] The instruction receiving unit 322 receives instructions for the slide data 500. The instruction receiving unit 322 receives instructions for the slide data 500 from the user 30 via, for example, an input device. The instruction receiving unit 322 receives, for example, a search instruction for the slide data 500. The instruction receiving unit 322 receives, for example, a correction instruction for the slide data 500.

[0079] Similar to the processing execution unit 124, when the instruction receiving unit 322 receives an instruction for the slide data 500, the processing execution unit 324 executes processing corresponding to the instruction on the document data 400 corresponding to the slide data 500 instead of the slide data 500.

[0080] For example, when the instruction receiving unit 322 receives a search instruction for the slide data 500, the processing execution unit 324 executes a search process on the document data 400 in accordance with the search instruction. For example, when the instruction receiving unit 322 receives a correction instruction for the slide data 500, the processing execution unit 324 executes a correction process on the document data 400 in accordance with the correction instruction.

[0081] The slide generation processing unit 308 may generate a prompt including an instruction to output a description of each of the plurality of slides 510, input the prompt to the generative AI model 210, and acquire the slide data 500 and the plurality of descriptions of the plurality of slides 510 output from the generative AI model 210. The association unit 310 may associate the plurality of descriptions of the plurality of slides 510 with the document data 400. When the instruction receiving unit 322 receives an instruction regarding the slide data 500, the processing execution unit 324 may execute processing corresponding to the instruction based on the document data 400 corresponding to the slide data 500 and the plurality of descriptions of the plurality of slides 510 associated with the document data 400, instead of the slide data 500.

[0082] 8 schematically illustrates an example of the hardware configuration of a computer 1200 functioning as the server 100 or the user device 300. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or to perform operations associated with the apparatus or one or more "parts" of the present embodiment, and / or to perform a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0083] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communications interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes a ROM 1230 and legacy input / output units such as a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0084] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller itself, and causes the image data to be displayed on the display device 1218.

[0085] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0086] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0087] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and causes cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

[0088] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0089] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0090] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0091] The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0092] The blocks in the flowcharts and block diagrams in the present embodiments may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, including integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0093] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, etc.

[0094] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0095] Computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or another programmable data processing device, or a programmable circuit, either locally or via a local area network (LAN), a wide area network (WAN) such as the Internet, so that the processor of the programmable data processing device, such as a computer, or the programmable circuit executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Here, the computer may be a personal computer (PC), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, a special-purpose computer, or the like, or may be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system, and is a broad definition of computers. In a distributed computing system, multiple computers collectively execute a program by each executing a portion of the program and passing data between the computers as needed during program execution.

[0096] Examples of processors include computer processors, central processing units, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of a program and passes data between processors as needed during program execution, allowing the multiple processors to collectively execute the program. For example, in multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at time slice intervals. In this case, which portion of a program each processor executes changes dynamically. Which portion of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0097] By using the invention according to this embodiment, it is possible to support users in creating slides, thereby contributing to the achievement of Goal 9 of the Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization, and build resilient technological infrastructure."

[0098] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0099] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0100] 10 data processing system, 20 network, 30 user, 100 server, 102 memory unit, 104 UI ​​unit, 106 document data acquisition unit, 108 slide generation processing unit, 110 matching unit, 122 instruction reception unit, 124 processing execution unit, 200 AI system, 210 generative AI model, 300 user device, 302 memory unit, 304 UI ​​unit, 306 document data acquisition unit, 308 slide generation processing unit, 310 matching unit, 322 instruction reception unit, 324 processing execution unit, 400 document data, 410 document block, 500 slide data, 510 slide, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphics controller, 1218 display device, 1220 input / output controller, 1222 communication interface, 1224 Storage device, 1230 ROM, 1240 I / O chips

Claims

1. a document data acquisition unit that acquires document data; a slide generation processing unit that, in response to receiving an instruction to convert the document data into slides, generates a prompt including an instruction to divide the document data into a plurality of document blocks and generate slide data including a plurality of slides corresponding to the plurality of document blocks, inputs the prompt into a generative AI model, and acquires the slide data output from the generative AI model; an association unit that associates each of the plurality of slides with each of the plurality of document blocks of the document data and stores the slide data in a storage unit; A data processing system comprising:

2. an instruction receiving unit that receives an instruction regarding the slide data; a processing execution unit that, when the instruction acceptance unit accepts an instruction for the slide data, executes a process corresponding to the instruction on the document data corresponding to the slide data instead of the slide data; 10. The data processing system of claim 1, comprising:

3. The data processing system according to claim 2 , wherein when the instruction receiving unit receives a search instruction for the slide data, the process executing unit executes a search process for the document data in accordance with the search instruction.

4. The data processing system according to claim 2 , wherein when the instruction receiving unit receives an instruction to correct the slide data, the processing execution unit executes a correction process on the document data in accordance with the instruction to correct the slide data.

5. 5. The data processing system of claim 2, wherein the slide generation processing unit includes in the prompt an instruction to generate the slide data with priority given to ease of understanding when viewed by a human over suitability for computer processing.

6. The data processing system according to claim 1 , wherein the slide generation processing unit includes in the prompt an instruction to divide the document data into a plurality of document blocks so that the contents of each document block fit on one slide.

7. 5. The data processing system of claim 1, wherein the slide generation processing unit includes in the prompt instructions for selecting, for each of the plurality of document blocks, a format suitable for the contents of the document block from the plurality of formats, and generating a slide in the selected format.

8. The data processing system of claim 7, wherein the slide generation processing unit includes in the prompt multiple types of content images that are areas that convey the content of the slide to be placed in the format, and instructions to select from the multiple types of content images a content image that is suitable for placement in the selected format based on the content of the document block, and to generate a slide in which the selected content image is placed in the selected format.

9. 5. The data processing system of claim 1, wherein the slide generation processing unit includes in the prompt more specific instructions for portions of the slide that have less freedom of generation by the generative AI model.

10. The data processing system of claim 1 , wherein the slide generation processor generates the prompt including the instructions to generate the plurality of slides in Scalable Vector Graphics (SVG) format.

11. 5. The data processing system of claim 1, wherein the slide generation processing unit includes in the prompt instructions for reviewing the slide data from a designer's perspective and a business professional's perspective after generating the slide data and modifying the slide data as necessary.

12. the slide generation processing unit includes in the prompt an instruction to output an explanation of each of the plurality of slides, inputs the prompt to the generative AI model, and acquires the slide data and the explanation output from the generative AI model; The data processing system according to claim 1 , wherein the associating unit associates the plurality of descriptions of the plurality of slides with the document data.

13. 1. A computer-implemented data processing method comprising: a document data acquisition stage for acquiring document data; a slide generation processing stage in which, in response to receiving an instruction to convert the document data into slides, a prompt including an instruction to divide the document data into a plurality of document blocks and generate slide data including a plurality of slides corresponding to the plurality of document blocks is generated, the prompt is input to a generative AI model, and the slide data output from the generative AI model is obtained; a correspondence step of storing the slide data and the document data in a storage unit by corresponding the plurality of slides and the plurality of document blocks, respectively; A data processing method comprising:

14. A program for causing a computer to execute the data processing method according to claim 13.

Images