Control method for information processing apparatus, information processing apparatus, and program

Abstract

To make it possible to adjust text to be displayed in a text region in a more desirable mode even under a situation where the size of the text region can be changed.SOLUTION: A text data processing necessity determination unit 402 calculates the number of characters displayable in a text region based on size attribute of the designated text region. A prompt generation unit 413 generates a prompt including an instruction related to text processing in which a text input to the text region and the calculated number of characters are designated. A language generation unit 415 inputs the generated prompt to a large language model 416 to cause the large language model 416 to generate a processed text by processing the designated text included in the prompt. The text input into the text region is updated with the processed text generated by the large language model 416.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a control method for an information processing apparatus, the information processing apparatus, and a program.

Background Art

[0002] As an example of a method for editing layout data with a layout such as a poster or a leaflet, for example, a method using a template material can be cited. In this case, for example, after selecting a template material closer to the completed image, contents such as text and images are added to or deleted from the template, and the overall layout is adjusted by changing the position and size of each content. Further, when there is text content, one or more text areas for inputting text are prepared in the template, and text is input into the area. In recent years, it has also become possible to use so-called language generation AI technology when inputting text content in the above-described layout data editing. Examples of such language generation AI technologies include ChatGPT (registered trademark) and Bard (registered trademark).

[0003] When editing layout data, after text is input, the size of the text area may be changed to adjust the layout. At this time, design problems may occur, such as extra white space being generated when the size of the text area is enlarged, or the text overflowing the area when the size of the text area is reduced. The same problem can also occur when the number of characters of the text that can be displayed in the text area changes due to a change in the font size, line pitch, or the like. As a countermeasure against such problems, Patent Document 1 discloses a technique for adjusting the font size according to the size of the area. However, in this case, there is a possibility that the consistency with the surrounding design may be lost because the font size becomes too small or, conversely, the font becomes too large. In contrast, Patent Document 2 discloses a technique for adjusting the number of characters in a text by preparing a replacement dictionary for phrases and replacing the phrases in the text with other phrases having different numbers of characters. In this technique, the process related to the replacement of phrases in the above-described text is repeatedly executed until the number of characters becomes suitable for the size of the area after the size change. In this method, since the number of characters in the text is adjusted, there is no need to change the font size, and it is possible to maintain consistency with the surrounding design.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the technique according to Patent Document 2, since replacement is performed at the phrase level, it may be difficult to cope with a significant change in the number of characters. In addition, since replacement of phrases is performed locally, a situation where the content becomes unnatural when viewed as a series of sentences can also be assumed.

[0006] In view of the above problems, an object of the present invention is to enable adjustment of the text to be displayed in the text area in a more suitable manner even in a situation where the size of the text area can be changed.

Means for Solving the Problems

[0007] The control method of the information processing apparatus according to the present invention includes a calculation step of calculating the number of characters that can be displayed in the specified text area based on the size attribute related to the specified text area, a generation step of generating a prompt including at least an instruction related to the processing of the specified text, the text input in the text area, and the number of characters calculated in the calculation step, and an input step of inputting the prompt generated in the generation step to a model that has been learned to perform processing on the text specified by the prompt based on the input prompt, so as to generate a processed text obtained by processing the text specified by the prompt by the model. The text input in the text area is updated with the processed text generated in the processing step.

Effect of the Invention

[0008] According to the present invention, even in a situation where the size of the text area can be changed, it is possible to adjust the text to be displayed in the text area in a more suitable manner.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0010] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0011] <Overview of Language Generation AI Technology> First, in order to make the features of the information processing system according to an embodiment of the present disclosure easier to understand, an overview of language generation AI technologies such as ChatGPT (registered trademark) and Bard (registered trademark) will be described below. For example, FIG. 7 is a diagram showing an overview of a language generation AI technology. In the language generation AI technology, a large language model (LLM) 701 that outputs a text product 702 with a high probability of matching the prompt 700 representing an instruction regarding the text to be generated is used with the prompt 700 representing an instruction regarding the text to be generated as an input. The relationship between the input value and the "context" is acquired when the large language model 701 learns using a large number of sentences. Also, the large language model 701 can change the generated product 702 by mainly changing the initial value generated from random numbers during the generation of the product 702. Further, by giving appropriate instructions to the text in the prompt 700, various processes such as summarizing the text, expanding the content, and translating it can be performed.

[0012] <First Embodiment> An example of an information processing system according to the first embodiment of the present disclosure will be described below. FIG. 1 is a diagram showing an example of the system configuration of the information processing system according to the present embodiment, and shows an example when configured as a printing system involving layout data editing for an image output device. In the printing system shown in FIG. 1, editing of layout data and transmission of a print job to the image output device are executed by an externally connected client (for example, a terminal device such as a PC). The image output device corresponds to a device that generates and outputs a printed matter by forming an image on a recording medium such as paper. Also, when creating a print job, for example, an editing operation of print settings may be performed on the screen of the client. Hereinafter, the system configuration of the printing system illustrated in FIG. 1 will be described in more detail.

[0013] As shown in FIG. 1, the client 102 is connected to each of the server 104, the image output device 100, and the image output device 101 via the network 103. The client 102 is used, for example, for editing layout data such as posters and flyers, and requests the server 104 to perform some editing and data processing and rendering processing on the layout data. The server 104 schematically shows a server that performs various processes such as editing, data processing, and rendering on various data such as layout data. Further, the client 102 generates a print job by adding print settings to the layout data after the editing operation, and transmits the print job to a desired image output device (for example, a specified image output device among the image output devices 100 and 101). In the example shown in FIG. 1, the case where there are two image output devices accessible by the client 102 via the network 103 is shown, but the number of image output devices is not limited, and it may be one or three or more. Similarly, for the client and the server, in the example shown in FIG. 1, each is one, but there may be two or more.

[0014] As an example of the process related to printing, an example in which a print job is transmitted to the image output device 100 from a printing application installed in the client 102 via a printer driver will be described. It is assumed that the printing application and the printer driver have been previously installed in the client 102. The printing application acquires device information of the associated image output device 100 from the printer driver, and printing parameters such as paper type, paper size, and print quality, and edits the print settings within the range of the acquired set of parameters. The printing application generates a print job based on the above print settings and the layout data image on which rendering processing has been performed by the server 104, and transmits the print job to the image output device 100 via the spool of the printer driver. The image output device 100 executes printing based on the print settings of the print job received from the printing application. In addition, the image output device 100 holds configuration information regarding the ink and paper it handles, and status information such as the idle state and print errors as device information. Further, when printing cannot be executed normally due to factors such as an abnormal state such as insufficient paper remaining or out of ink, or an error in the print settings, the image output device 100 may display a warning message on the main body panel to present to the user the reason why printing cannot be executed normally.

[0015] With reference to FIG. 2, an example of the hardware configuration of the image output device 100 will be described. Note that since the image output device 101 can be realized with a configuration substantially the same as that of the image output device 100, detailed description thereof will be omitted. The operation of the image output device 100 is controlled by a CPU (Central Processing Unit) 200. The CPU 200 operates based on a control program stored in a program area in a ROM (Read Only Memory) 201, a control program stored in a storage area such as an external memory 208, and the like. The CPU 200 outputs an image signal as output information to a printing unit (printer engine) 207 connected to a printing unit I / F 205 via a system bus 203. The CPU 200 may notify the client 102 of information within the image output device 100 via the communication by communicating with the client 102 via an input unit 204. Further, the CPU 200 can also receive output data to be output to the printing unit 207 via the input unit 204. The RAM (Random Access Memory) 202 is a temporary storage area that functions as the main memory of the CPU 200 and as a work area, etc. The RAM 202 may be configured such that its memory capacity can be expanded by an optional RAM connected to an expansion port (not shown). The RAM 202 is used, for example, for an output information expansion area, an environmental data storage area, a non-volatile memory, etc. The external memory 208 is realized by a hard disk drive (HDD) or an IC card, etc., and access thereto is controlled by a memory controller 206. The external memory 208 can be connected as an option, and can store font data, an emulation program, form data, information on used ink, information on paper feed paper type and size, and main body status information, etc. Also, the operation unit 209 includes a panel realized by a display device such as a liquid crystal display, and is configured such that various information can be displayed on the panel.

[0016] Referring to FIG. 3, an example of the hardware configuration of an information processing apparatus applicable as the client 102 shown in FIG. 1 will be described. Note that since the server 104 can be realized with a configuration substantially the same as that of the client 102, a detailed description thereof will be omitted. Inside the main body 307 of the computer, a CPU 300, a ROM 301, a RAM 302, a keyboard controller 304, a display controller 305, and a disk controller 306 are included. The CPU 300 reads various programs such as a control program, a system program, and an application program from the external memory 311 via the disk controller 306 into the RAM 302. By executing the various programs read into the RAM 302, the CPU 300 performs various data processes and display control of the display 310, etc. The CPU 300 may read a control program, etc. from the ROM 301. Also, the CPU 300 may be realized as a dedicated circuit such as an ASIC. The CPU 300 and the dedicated circuit correspond to an example of a hardware circuit or a hardware processor. The disk controller 306 controls access to external memories 311 such as HDDs, CD-ROMs, DVD-ROMs, and USBs. The RAM 302 may be configured such that its capacity can be expanded by an optional RAM (not shown) or the like, and is mainly used as a work area for the CPU 300. The keyboard controller 304 controls key inputs from input devices such as the keyboard 308 and the pointing device 309. The display controller 305 controls the display on the display 310. In each embodiment of the present disclosure, unless otherwise specified, it is assumed that the CPU 300 controls each unit connected to the main bus 303 via the main bus 303. Of course, in the server 104, components that are not necessarily essential, such as the display 310, may not be included in the configuration.

[0017] Referring to FIG. 4, an example of the functional configuration of the information processing system according to the present embodiment will be described, particularly focusing on the configurations of the image output device 100, the client 102, and the server 104 described with reference to FIGS. 1 to 3. Note that since the image output device 101 is substantially the same as the image output device 100, a detailed description thereof will be omitted.

[0018] First, an example of the functional configurations of the client 102 and the server 104 will be described. The layout data editing unit 401 adds and deletes contents such as characters and images to be placed on printed materials such as posters and flyers, and adjusts the layout of each content. When performing processing such as cropping and filling for each content, a request for such processing is made from the layout data editing unit 401 to the data content editing unit 411 of the server 104. The layout data is stored as a cache in the layout data DB 400 of the client 102, or stored in the layout data DB 410 of the server 104 for each client 102 (or for each account if there is a user account).

[0019] The text data processing necessity determination unit 402 determines whether there is a need to process the text within the text area in the layout data. When it is determined that text processing is necessary, the text replacement unit 403 performs processing of the target text and replacement of the processed text for the original text. When text replacement is performed, the text display update unit 404 updates the display of the target text. Details of the processing of each of the text data processing necessity determination unit 402, the text replacement unit 403, and the text display update unit 404 will be described separately later together with the description of a series of processes of the information processing system.

[0020] The print job transmission unit 405 creates a print job and transmits the created print job to the image output device 100. When creating the print job, the preview image generation unit 417 or the print image generation unit 418 of the server 104 is requested to perform a preview of the layout data or a print image generation process from the print job transmission unit 405.

[0021] The text processing unit 412 of the server 104 receives an instruction from the text replacement unit 403 and requests the language generation unit 415 to generate text. At this time, the prompt generation unit 413 generates prompt information used for text generation, and the text processing unit 412 uses the prompt information for the text generation request. The prompt generation unit 413 may use metadata related to the target text obtained by the metadata acquisition unit 414 when generating the prompt information. Based on the prompt generated by the prompt generation unit 413, the language generation unit 415 uses the large language model 416 to generate text. The generated text is transmitted to the client 102 by the text processing unit 412.

[0022] Next, an example of the functional configuration of the image output device 100 will be described. The ROM 201 holds a device information holding unit 421, a print job receiving unit 422, and a print execution unit 423. The print job receiving unit 422 receives a print job transmitted from the client 102. The print execution unit 423 executes a printing process based on the received print job. The device information holding unit 421 holds information such as the type and remaining amount of ink installed in the image output device 100, information such as the type and size of registration paper and paper for paper feeding, the main body status information of the image output device 100, and the status information of print jobs. When the image output device 100 to be used is determined in advance, the information held in the device information holding unit 421 may be used to create layout data suitable for the image output device 100. In this case, the target information is acquired from the device information holding unit 421 and may be held on the client 102 or server 104 side in association with the layout data DB 400 or 410.

[0023] Referring to FIG. 5, an example of the layout data stored in the layout data DBs 400 and 410 will be described. The data table shown in FIG. 5 is held for each layout data, for example. The data table shown in FIG. 5 is provided with areas such as an ID 500, content 501, content type 502, layout coordinates 503, setting information 504, and metadata 505, and information regarding the content can be set in each area for each content.

[0024] In the area of the ID 500, identification information (ID) for uniquely identifying the content on the layout data is set. In the area of the content 501, the value of each content such as characters and images laid out on the layout data is set. In the area of the content type 502, information indicating the type of the content set in the area of the content 501 is set. In the area of the layout coordinates 503, a value indicating the position of the content on the layout data is set. In the area of the setting information 504, attribute values indicating characteristics specific to each content, such as the color and size of the content, are set. In this embodiment, regarding the coordinates and size in the case where the content type is text, they shall represent the coordinates and size of the text area prepared for the text. Also, when the target content is text, as setting information, attribute values specific to text, such as font type, font size, and line pitch, may be retained.

[0025] In the area of the metadata 505, the metadata of each content can be retained. In this embodiment, when the content type 502 is text, the type and purpose of the text to be described, etc., may be set as metadata. For example, in the example shown as sample 508, information indicating the purpose of the target text is set in the area of the metadata 505. Also, in the example shown as sample 506, the ID of the image related to the target text is set in the area of the metadata 505. Also, when the content type 502 is an image, an explanation of the image may be set in the area of the metadata 505. For example, in the example shown as sample 507, for the target image, an explanation "Explanation: Image of cherry blossom viewing" is set in the area of the metadata 505. Also, as shown in FIG. 5, depending on the content, there may be cases where no metadata is set.

[0026] Also, settings regarding the entire layout data, such as the manuscript size and data for variable printing, may be retained. In this case, for example, in the area of the content 501, "entire" may be retained as a value, in the area of the content type 502, the setting type may be retained, and in the area of the setting information 504, the set value may be retained. Of course, the above is merely an example. For example, they may be operated in separate files for each type of parameter, or other types of parameters other than those exemplified above may be included in the layout data.

[0027] Referring to FIG. 6, an example of a layout data editing screen 600 for the image output device 100 displayed on the display 310 of the client 102 will be described. The layout data editing screen 600 includes a template list 601 as an area where candidates for layout templates are displayed as a list. The user can browse and select a template that is closest to the completed form of the layout data via the template list 601. The template selected via the template list 601 is displayed in the layout editing area 604. Information on the templates displayed in the template list 601 may be obtained, for example, from the layout data DB 400 or 410 as layout data, or from an external network service such as a cloud service or an SNS service.

[0028] The layout data editing unit 401 or the data content editing unit 411 performs editing such as position adjustment, color tone correction, clipping, filling, etc. on each content displayed on the layout editing area 604. When the target content is text, for example, based on an instruction received via the keyboard 308, input of the target text is received and editing of the specified text is performed. As a specific example, the user can input desired text into the text area 608 by using the keyboard 308. In addition, regarding the addition of content such as images and text to the layout editing area 604, it is performed based on instructions via the image addition button 602 and the text addition button 603. As a specific example, when the image addition button 602 or the text addition button 603 is pressed, a file dialog is displayed, and content may be imported by importing a file corresponding to the path specified via the file dialog. Of course, not only text and images but also other types of content may be selectable, and in that case, a button for receiving an instruction regarding the addition of the content may be displayed. Also, the import source of the content is not particularly limited, and the target content may be acquired from an external network service such as a cloud service or an SNS service. Also, as another example, when a drag & drop operation of content to the layout editing area 604 is received, the content may be imported.

[0029] Instructions regarding the execution of printing are received, for example, via the print execution button 605. When the print execution button 605 is pressed, the print job transmission unit 405 creates a print job for the layout data displayed in the layout editing area 604 and transmits the print job to a specified image output device (for example, the image output device 100 or 101). Also, an instruction regarding the saving of the layout data being edited may be received via the save button 606. When the save button 606 is pressed, the layout data being edited may be saved in a predetermined storage area (for example, the layout data DB 400 or 410).

[0030] As described above, the information processing system according to the present embodiment is configured to be able to adjust the position and size of each content in the layout editing area 604. For example, FIG. 10 is a diagram showing an example of the layout data editing screen 600. In the example shown in FIG. 10, a text area 1001 is displayed, and the size of the text area 1001 can be enlarged or reduced. The enlargement or reduction of the size of the text area 1001 is performed, for example, based on an instruction received via the pointing device 309.

[0031] On the other hand, when the size of the text area is enlarged, the size of the text area becomes larger than the area occupied by the input text, and extra blank spaces may occur as exemplified in FIG. 10. On the other hand, when the size of the text area is reduced, the size of the text area becomes smaller than the area occupied by the input text, and the text may not fit within the text area. In view of such a situation, the information processing system according to the present embodiment is provided with a function of processing the input text so as to match the size of the text area after the change when the size of the text area is changed. Therefore, hereinafter, the function of the information processing system according to the present embodiment will be described in more detail.

[0032] Referring to FIG. 8, an example of the processing of the information processing system according to the present embodiment will be described, particularly focusing on the processing related to the processing of the text input to the text area when the size of the text area is changed on the layout data editing screen 600. The series of processes shown in FIG. 8 is realized, for example, by the CPU 300 reading out the program stored in the ROM 301 and executing it in the RAM 302.

[0033] The series of processes shown in FIG. 8 is started by the text replacement unit 403, for example, at the timing when the print execution button 605 on the layout data editing screen 600 is pressed or the save button 606 is pressed at the client 102. However, the above is merely an example, and the trigger for starting the series of processes shown in FIG. 8 is not limited to the processes related to printing and saving of content. As a specific example, the series of processes shown in FIG. 8 may be started at the timing that serves as a break in the editing work of the target content. Also, as another example, the series of processes shown in FIG. 8 may be started at the timing when a change in the size of the target text area is detected.

[0034] In S2001, the text data processing necessity determination unit 402 calculates the number of characters of the text that can be displayed in the target text area based on information such as the size of the target text area, the type of character font, the font size, and the line pitch. Note that the method for calculating the number of characters of the text that can be displayed in the target text area in this case is not particularly limited, and for example, a method generally used in character typesetting or the like can also be applied.

[0035] In S2002, the text data processing necessity determination unit 402 determines whether it is necessary to process the text displayed in the text area based on the calculation result of the number of characters of the text that can be displayed in the target text area in S2001. If the text data processing necessity determination unit 402 determines in S2002 that the processing of the target text is unnecessary, the series of processes shown in FIG. 8 is terminated. On the other hand, if the text data processing necessity determination unit 402 determines in S2002 that processing of the target text is necessary, the process proceeds to S2003. For example, when the number of characters of the input text is excessively large or excessively small with respect to the number of characters of the text that can be displayed within the text area (for example, when the difference exceeds a threshold), the text data processing necessity determination unit 402 may determine that processing of the text is necessary. In this way, when the difference between the difference between the number of characters of the text that can be displayed within the text area and the number of characters of the input text and a pre-set threshold satisfies a predetermined condition, the text data processing necessity determination unit 402 may determine that processing of the text is necessary.

[0036] For example, the example shown in FIG. 10 shows a state where the size of the text area 608 is enlarged in the layout data editing screen 600 illustrated in FIG. 6. The text area 1001 shown in FIG. 10 corresponds to the result of enlarging the size of the text area 608 shown in FIG. 6. As the size of the text area 1001 is enlarged, the number of characters of the text that can be displayed has become excessively large compared to the number of characters of the actually input text (for example, the difference exceeds a threshold), and there is white space. Therefore, in this case, the text data processing necessity determination unit 402 determines that processing of the text input to the text area 1001 is necessary. In the above description, an example of the case where the size of the text area is changed has been described. However, the situation where the difference between the number of characters of the text that can be displayed in the text area and the number of characters of the input text becomes excessively large (exceeds the threshold) is not limited to only the example described above. For example, when the font type, font size, line pitch, etc. of the text area are changed, a situation where the difference between the number of characters of the text that can be displayed in the text area and the number of characters of the input text becomes excessively large can also be assumed. Also, as another example, when a change is made to increase or decrease the number of characters of the text input to the text area, a situation where the difference between the number of characters of the text that can be displayed in the text area and the number of characters of the input text becomes excessively large can also be assumed. Even in such a case, the text data processing necessity determination unit 402 may determine that processing of the text displayed in the target text area is necessary. In the present embodiment, for convenience, the size, font type, font size, line pitch, and number of characters of the text in the text area may be collectively referred to as the size attribute of the text area. That is, due to a change in the size attribute of the target text area, a state where processing of the text displayed in the text area may be necessary may occur. Note that the size, font type, font size, line pitch, etc. of each text area may be set or changed by the layout data editing unit 401.

[0037] Regarding whether or not processing of the text displayed in the target text area is necessary, for example, it is possible to determine according to whether or not the absolute value of the difference between the number of characters of the text that can be displayed in the text area and the number of characters of the text displayed in the text area exceeds the threshold. In this case, the text data processing necessity determination unit 402 may determine that processing of the target text is necessary when the absolute value of the difference in the number of characters exceeds the threshold, and may determine that processing of the target text is unnecessary when the absolute value of the difference in the number of characters is equal to or less than the threshold. Of course, the above is merely an example, and the criteria for determination may be changed as appropriate. As a specific example, thresholds applied to each of the determination as to whether the number of characters in the target text is greater than or less than the number of characters that can be displayed in the text area may be set individually. Also, the ratio of the number of characters in the target text to the number of characters that can be displayed in the text area may be applied as a comparison target with the threshold value. Of course, also in this case, thresholds may be set individually for each of the determination as to whether the ratio exceeds the threshold value and the determination as to whether it is equal to or less than the threshold value. Thus, as long as it is possible to determine whether the number of characters in the text displayed in the text area is excessively large or excessively small with respect to the number of characters that can be displayed in the text area, the method for such determination is not particularly limited.

[0038] In S2003, the text data processing necessity determination unit 402 asks the user whether to perform processing on the text displayed in the target text area. For example, FIG. 11 is a diagram showing an example of the state of the layout data editing screen 600, and shows an example of an input interface for receiving an instruction from the user as to whether to perform processing on the text displayed in the target text area. Specifically, in the example shown in FIG. 11, a pop-up window 1101 is displayed, and an instruction from the user as to whether to perform processing on the target text is received via the pop-up window 1101. For example, when the "No" button displayed in the pop-up window 1101 is pressed, the text data processing necessity determination unit 402 recognizes that an instruction not to perform processing on the text displayed in the target text area has been received from the user. When the text data processing necessity determination unit 402 determines that an instruction not to perform processing on the text displayed in the target text area has been received from the user in S2003, the series of processes shown in FIG. 8 is terminated. On the other hand, when the "Yes" button displayed in the pop-up window 1101 is pressed, the text data processing necessity determination unit 402 recognizes that an instruction to perform processing on the text displayed in the target text area has been received from the user. If the text data processing necessity determination unit 402 determines in S2003 that an instruction to perform processing on the text displayed in the target text area has been received from the user, the process proceeds to S2004. Note that the process related to receiving an instruction from the user in S2003 corresponds to an example of the first reception process.

[0039] In S2004, the text replacement unit 403 requests the text processing unit 412 of the server 104 to perform a processing operation on the text input in the target text area. Here, it is assumed that the text replacement unit 403 requests the text processing unit 412 to perform a processing operation for changing the number of characters without changing the content of the text currently input in the target text. In S2005, the prompt generation unit 413 generates a prompt for causing the language generation AI (language generation unit 415 and large language model 416) to execute the processing operation requested from the client 102 in S2004. For example, if the number of characters of the text that can be displayed in the target text area is 400 and the number of characters of the text displayed in the target text area is less than 400, the prompt generation unit 413 generates a prompt as exemplified below.

[0040] Please expand the following text to 400 characters without changing the content. A spring festival will be held. ································ Please come and join us.

[0041] Note that a specific example of the process related to the generation of the prompt will be described separately later. Also, the prompt generated in S2005 is output to the language generation unit 415.

[0042] In S2006, the language generation unit 415 uses the large language model 416 to process the target text according to the instructions described in the prompt generated in S2005. The processing of the text can be realized, for example, by language generation AI technology using large language models (LLMs) such as ChatGPT (registered trademark) and Bard (registered trademark). In this embodiment, the applicable language generation AI is not particularly limited as long as it uses a large language model. For example, the language generation unit 415 generates a text with an expanded number of characters while maintaining the content of the target text according to the prompt exemplified in the description of the process of S2005, as shown below.

[0043] We will hold a spring festival. It has been getting warmer day by day. ································ How about deepening friendship while enjoying cherry blossoms? Everyone, please come and participate actively.

[0044] Regarding the text generated in S2006, it is sent by the text processing unit 412 to the text replacement unit 403 of the client 102.

[0045] In S2007, the text replacement unit 403 replaces the original text in the layout data DB400 with the processed text received from the server 104. In S2008, the text display update unit 404 updates the display of the target text area according to the update result of the layout data DB400 in S2007, and then ends the series of processes shown in FIG. 8. For example, FIG. 12 is a diagram showing an example of the layout data editing screen 600, and shows an example of the result of updating the display of the target text area by the series of processes shown in FIG. 8. The text area 1201 shown in FIG. 12 corresponds to the text area 1001 in the example shown in FIG. 10, and text with the number of characters adjusted according to the size is displayed by the series of processes described with reference to FIG. 8.

[0046] Next, with reference to FIG. 9, an example of the process related to the generation of the prompt shown as the process of S2005 in FIG. 8 will be described in more detail. In S3001, the prompt generation unit 413 acquires the text within the target text area held in at least one of the layout data DBs 400 and 410. In S3002, the prompt generation unit 413 calculates the number of characters that can be displayed in the current text area.

[0047] In S3003, the metadata acquisition unit 414 acquires the metadata of the text that is being focused on at that time (in other words, the metadata set in the target text area). In S3004, the metadata acquisition unit 414 determines whether the metadata of the text that was being focused on in S3003 has been acquired. If the metadata acquisition unit 414 determines in S3004 that the metadata of the text that was being focused on has been acquired, the process proceeds to S3008. On the other hand, if the metadata acquisition unit 414 determines in S3004 that the metadata of the text that was being focused on could not be acquired, the process proceeds to S3005. For example, if no metadata is set for the text that is being focused on (in other words, the target text area), the metadata cannot be acquired from the text.

[0048] In S3005, the metadata acquisition unit 414 acquires the metadata of the related image of the text being focused on (the text in the target text area). Specifically, the metadata acquisition unit 414 acquires the ID set in the related image metadata among the metadata of the target text area, and acquires the metadata of the image to which the ID is assigned. In S3006, the metadata acquisition unit 414 determines whether the metadata of the related image of the text being focused on in S3005 has been acquired. If the metadata acquisition unit 414 determines in S3006 that the metadata of the related image of the text being focused on has been acquired, the process proceeds to S3008. On the other hand, if the metadata acquisition unit 414 determines in S3006 that the metadata of the related image of the text being focused on cannot be acquired, the process proceeds to S3007. For example, if no related image is set for the text being focused on, or even if a related image is set but no metadata is set for the related image, the acquisition of the metadata of the related image of the text will not be performed.

[0049] The process of S3007 is a process executed when no metadata acquisition is performed for either the text being focused on (in other words, the target text area) or the related image of the text. In this case, the prompt generation unit 413 generates a prompt based on the text in the target text area and the information on the number of characters that can be displayed in the text area. In this case, for example, a prompt as shown below is generated.

[0050] Please expand the following text to 400 characters without changing the content. A spring festival will be held. ································ Please come and participate.

[0051] The process of S3008 is a process that is executed when metadata is obtained for at least one of the text being focused on (in other words, the target text area) and the related image of the text. In this case, the prompt generation unit 413 uses the information of the obtained metadata in addition to the text within the target text area and the information on the number of characters that can be displayed in the text area to generate a prompt. As a specific example, when information such as "Purpose: A text for calling for event participation" is set as metadata for the text area, a prompt as shown below is generated.

[0052] The following text is a text for calling for participation in an event. Please expand this text to 400 characters without changing the content. A spring festival will be held. ································ Please come and join us.

[0053] Regardless of whether the process of S3007 or S3008 is executed, after a series of processes shown in FIG. 9 are executed, the process proceeds to the process of S2006 shown in FIG. 8.

[0054] As described above, when the size, font, line spacing, etc. of a text area such as a poster or flyer are changed in the information processing system according to this embodiment, the target text is processed in accordance with the number of characters that can be displayed in the text area while maintaining the content. By applying such control, for example, it is possible to prevent a situation where text protrudes from the text area or extra white space occurs in the text area, and display the text with the original content maintained in the text area. Also, by applying such control, for example, it is possible to prevent a situation where an inconsistency with the overall design occurs, which is different from the case of preventing text protrusion and the occurrence of extra white space by adjusting the font size.

[0055] Note that the configuration of the information processing system according to the above-described embodiment is merely an example, and the configuration of the information processing system is not limited as long as the contents shown as the respective processes of the client 102 and the server 104 are substantially realized. For example, the assignment of the processes executed by the client 102 and the server 104 may be appropriately changed. As a specific example, the assignment of components (in other words, the assignment of processes) to the client 102 and the server 104 described with reference to FIG. 4 may be appropriately changed. Further, the respective components of the client 102 and the server 104 may be provided in one information processing apparatus. Further, at least some of the respective components of the client 102 and the server 104 may be realized by a network service such as a so-called cloud service.

[0056] <Modification Example> Modification examples of the information processing system according to an embodiment of the present disclosure will be described below as Modification Examples 1 to 6.

[0057] (Modification Example 1) In the above-described first embodiment, an example in which a process related to the processing of a target text is executed using an operation such as printing or saving as a trigger for starting the process has been described. On the other hand, a configuration may be adopted in which, by receiving an explicit instruction from the user, a process related to the processing of the target text is started based on the instruction. As a specific example, a button for receiving an instruction related to text processing from the user may be provided in the layout data editing screen 600, and when the button is pressed, a process related to the processing of the text in the text area selected as the target may be executed. In this case, since it is not necessary to determine the necessity of text processing, for example, among the series of processes shown in FIG. 8, the determination processes shown as S2002 and S2003 may be omitted, and control may be applied to directly transition from S2001 to S2004. Of course, not only when there is an explicit instruction from the user, but also as in the first embodiment, operations such as printing and saving may be applied as a trigger for starting the processing related to text processing. As described above, according to this modification example, it is possible to cause the information processing system to execute the processing related to the text processing of the target text at the timing desired by the user.

[0058] (Modification Example 2) In the first embodiment described above, an example was described in which at least one of the metadata of the text being focused on (in other words, the target text area) and the related image of the text is used for generating the prompt in the prompt generation process described with reference to FIG. 9. On the other hand, as the prompt is generated without using metadata in the process of S3007, it is possible to perform processing on the target text without using metadata. As a specific example, when the target text is processed to be shorter in length, it becomes a summarization process, so it is possible to process the target text without using metadata. Also, as another example, even when the target text is processed to be longer in length, it may be possible to process the target text without metadata by using the information of the original text. When it is assumed that metadata is not used in processing the target text in this way, among the series of components shown in FIG. 4, the metadata acquisition unit 414 may not be provided. Also, among the series of processes shown in FIG. 9, the processes of S3003 to S3006 and S3008 may be omitted, and control may be applied to directly transition from S3002 to S3007. As described above, according to this modification example, since it is not necessary to hold metadata, an effect of reducing the capacity of the memory and storage used in executing a series of processes related to text processing can be expected.

[0059] (Modification Example 3) In the first embodiment described above, an example was described in which the original text, the number of characters, and metadata information are used when generating a prompt. In this modification example, an example in which the content indicated by an explicit instruction from the user is reflected when generating a prompt will be described in addition to this information.

[0060] As a specific example, by receiving an instruction from the user not to change a part of the text to be processed, control may be applied to protect the part. In the above-described embodiment, the text displayed in the target text area is passed as part of the prompt, and the text is processed. At this time, although the content of the target text is maintained, the expression of the text is not always maintained as it is. On the other hand, a situation may be assumed in which the user desires to maintain the expression applied to at least a part of the target text.

[0061] For example, FIG. 16 is a flowchart showing an example of a process related to prompt generation, and shows another example of the process of S2004 shown in FIG. 8. In S4001, the prompt generation unit 413 inquires of the user whether there is an additional instruction regarding the processing of the target text. The inquiry about whether there is an additional instruction for the user can be realized, for example, by displaying it in a window as a message and then displaying buttons for selecting yes / no, and receiving an instruction from the user via the buttons. In S4002, the prompt generation unit 413 determines whether an additional instruction from the user in S4001, that is, an instruction regarding the addition of conditions for text processing, has been received. If the prompt generation unit 413 determines in S4002 that an additional instruction from the user has been received, the process proceeds to S4003. On the other hand, if the prompt generation unit 413 determines in S4002 that no additional instruction from the user has been received, the process proceeds to S4006.

[0062] In S4003, the prompt generation unit 413 determines whether the additional instruction received in S4001 is an instruction related to the protection of a character string. If the prompt generation unit 413 determines in S4003 that the target additional instruction is an instruction related to the protection of a character string, the process proceeds to S4004. On the other hand, if the prompt generation unit 413 determines in S4003 that the target additional instruction is not an instruction related to the protection of a character string, the process proceeds to S4005.

[0063] In S4004, the prompt generation unit 413 receives from the user a specification of the range of the character string to be protected among the text to be processed.

[0064] In S4005, the prompt generation unit 413 receives an additional instruction input from the user. As a specific example, the prompt generation unit 413 may receive an additional instruction input from the user via the keyboard 308.

[0065] In S4006, the text replacement unit 403 transmits a text processing request to the server 104. At this time, if the additional instruction has been received from the user in S4004 or S4005, the text replacement unit 403 may include information indicating the additional instruction in the text processing request. Note that the process related to receiving an additional instruction from the user, shown as the processes of S4001 to S4005, corresponds to an example of the second reception process.

[0066] After the series of processes shown in FIG. 16 are executed, the series of processes shown in FIG. 9 are continuously executed. And if an additional instruction from the user has been received in the series of processes shown in FIG. 16, in S3007 or S3008 shown in FIG. 9, the prompt is generated so that the content indicated by the additional instruction is reflected.

[0067] For example, FIG. 13 is a diagram showing an example of the layout data editing screen 600, and shows an example when receiving an instruction from the user for the range of character string protection. Specifically, in the example shown in FIG. 13, a pop-up window 1301 for receiving an instruction from the user regarding the specification of the range of character string protection is displayed. Moreover, when an instruction from the user is received via the pop-up window 1301, the specification of the range of the character string to be protected in the text displayed in the target text area is received from the user. By designating at least a part of the character strings in the target text as described above, the character string is set as the object to be protected.

[0068] Also, in the series of processes shown in FIG. 9, when a prompt is generated in S3007 or S3008, an instruction "Do not process this part" is added to the prompt for the previously specified character string. In this case, for example, a prompt as shown below is generated.

[0069] The following text is a message calling for participation in an event. Please expand this text to 400 characters without changing the content. However, do not modify the character string between and ***. We will hold a spring festival. *** ································ Please come and join us.

[0070] As described above, according to this modification example, it is possible to reflect the user's request when the text is processed. As a specific example, when processing the text, by giving an instruction from the user to keep at least a part of the character strings without changing them, it is possible to control so that the text to be targeted is processed while maintaining the character strings.

[0071] (Modification Example 4) ​In the first embodiment described above, an example in which the original text is automatically replaced with the processed text in the process of S2007 shown in FIG. 8 was explained. On the other hand, after presenting the processed text to the user before the replacement is performed, and receiving an instruction regarding the replacement of the text from the user, the original text may be replaced with the processed text based on the instruction. Further, in this case, assuming a situation where the processed text is different from what the user intends, the user may be allowed to receive an instruction regarding the re-execution of text processing.

[0072] Generally, even if the same prompt is input, the language generation AI does not always output the same thing. Therefore, when the text processing is re-executed by the language generation unit 415, it can be expected that an output will be obtained in which the target text is processed differently from the previous execution. Also, in view of the above characteristics, by providing a plurality of language generation units 415, when re-executing text processing, text processing may be executed by another language generation unit 415 different from the language generation unit 415 used during the previous processing. In this case, the plurality of language generation units 415 may be provided on the same server, or may be individually provided on different servers.

[0073] Referring to FIG. 17, as an example of the processing of the information processing system according to this modification example, another example of the processing of S2007 in FIG. 8 will be described. The text replacement unit 403 displays the processed text in a predetermined display area in S5001, and inquires of the user whether to approve the replacement of the original text with the processed text in S5002. As a specific example, the text replacement unit 403 may display the processed text in a window and also display buttons for selecting yes / no in the window, and receive an instruction from the user via the window. Then, the text replacement unit 403 determines whether the user's approval of text replacement has been received for the inquiry presented to the user in S5001. If it is determined in S5002 that approval for text replacement has been received from the user, the text replacement unit 403 proceeds with the process to S5005. In S5005, the text replacement unit 403 replaces the original text with the processed text, ends the series of processes shown in FIG. 17, and then transitions the process to S2008 in FIG. 8. On the other hand, if it is determined in S5002 that approval for text replacement has not been received (rejected) from the user, the text replacement unit 403 proceeds with the process to S5003. Note that the process related to receiving an instruction from the user to approve text replacement in S5001 corresponds to an example of a third reception process.

[0074] In S5003, the text replacement unit 403 asks the user whether to re - execute text processing. As a specific example, the text replacement unit 403 may display a message related to confirmation of re - execution in a window and also display buttons for selecting yes / no in the window, and receive an instruction from the user via the window. Then, the text replacement unit 403 determines whether an instruction related to re - execution of text processing has been received from the user. If it is determined in S5003 that an instruction related to re - execution of text processing has been received, the text replacement unit 403 ends the series of processes shown in FIG. 17 and then transitions the process to S2005 in FIG. 8. On the other hand, if it is determined in S5003 that an instruction related to re - execution of text processing has not been received (re - execution has been rejected), the text replacement unit 403 ends the series of processes shown in FIG. 17 and then transitions the process to S2008 in FIG. 8. Note that the process related to receiving an instruction from the user to re - execute text processing in S5003 corresponds to an example of a fourth reception process.

[0075] By applying the control as described above, when processing the target text, a result closer to the user's intention can be obtained.

[0076] (Modification Example 5) In the first embodiment described above, an example of the case where the layout data is finally output to the image output device, that is, an example of the case where the information processing system according to this embodiment is realized as a printing system, was described. On the other hand, the application target of the technology according to this embodiment is not necessarily limited to only the printing system. For example, even when editing layout data assuming content mainly displayed via a display, the technology according to this embodiment can be similarly applied. Specifically, even when content is displayed on a display, a situation can be assumed where the number of characters that can be displayed within the text area and the number of characters that can be input within the text area are restricted according to the display size constraints, system-side constraints, etc. The technology according to the present disclosure may be applied under such circumstances.

[0077] Regarding the system configuration of the information processing system according to this modification example, among the systems and configurations illustrated in FIG. 1, the image output devices 100 and 101 do not necessarily need to be provided. Regarding the hardware configuration of each of the server 104 and the client 102, the configuration shown in FIG. 3 can be applied in the same manner as in the first embodiment. Also, regarding the functional configuration, among the series of components of the server 104 and the client 102 illustrated in FIG. 4, the print job transmission unit 405 and the print image generation unit 418 do not necessarily need to be provided. Also, since the image output device 100 does not necessarily need to be provided as a system configuration as described above with reference to FIG. 1, the components corresponding to the image output device 100 in the example shown in FIG. 4 do not necessarily need to be provided either. Of course, it goes without saying that it is not limited to only displaying the edited layout data on the display, and when printing the layout data is possible, it can be realized by providing components related to printing the layout data in the same manner as in the first embodiment. Regarding the processing of the information processing system according to this modification example, a series of processes shown in FIGS. 8 and 9 can be applied in the same manner as in the first embodiment described above.

[0078] As described above, regarding the information processing system according to an embodiment of the present disclosure, even when the layout data is edited assuming the content mainly displayed via the display, it is possible to display the text in an amount suitable for the text area.

[0079] (Modification Example 6) In the first embodiment described above, as shown in FIGS. 11 and 13, as an example of the UI (User Interface) that realizes the interaction between the system and the user, an example in the case where message display in a window, menu selection, etc. are applied was described. On the other hand, these UIs are merely examples and do not necessarily limit the UI of the information processing system according to an embodiment of the present disclosure. Therefore, in this modification example, an example in the case where the interaction between the system and the user is realized interactively via a dialogue screen like a chat will be described. The system is assumed to be provided with a dialogue learning model for interactively responding to instructions from the user and making proposals for processing to the user. Note that this dialogue learning model may be realized by the language generation unit 415 and the large language model 416, or another model may be used.

[0080] FIG. 14 is a diagram showing an example of the UI of the information processing system according to this modification example. The window 1400 is a window for realizing the interaction between the system and the user, and the content of the dialogue made between the system and the user is displayed. For example, output information 1401 and 1402 show an example of information indicating the interaction between the system and the user. Output information 1401 shows the content of the user's output information input by the user, and can be input via, for example, the keyboard 308 or the like. In the example shown in FIG. 14, based on the output information 1401, an instruction is given from the user to the system to check the date and time of the SPRING FESTIVAL and input it into the text area. Output information 1402 shows the content of the response from the system. In the example shown in FIG. 14, based on the output information 1402, a response indicating that the date and time have been input is given. Assume that through this interaction, text of the date and time is input into the text area provided near the center of the layout editing area in FIG. 14. Furthermore, assume that text "We will hold the Spring Festival. Please come with enthusiasm." is input into another text area provided at the lower part of the layout editing area in FIG. 14. This text may be text (not shown) generated by interactively performing the user's instruction and the system's response in the window 1400, or may be text directly input by the user. However, at this time, assume that a large margin remains in this text area. An example in which the system detects this situation where a large margin remains and proposes to process the input text from the system side will be described using output information 1403 and 1404. Output information 1403 shows the content of the proposal made from the system to the user. In the example shown in FIG. 14, based on the output information 1403, a proposal is made from the system to the user to consider processing the text because there is a margin in the text area. In response, when the user accepts the proposal from the system, the user will input a confirmation to that effect into the window 1400. Output information 1404 shows the content of the instruction input by the user after receiving the proposal from the system. In the example shown in FIG. 14, based on the output information 1404, an instruction is given to accept the proposal from the system. When the system receives an instruction from the user to accept the proposal, the system executes the same processing as S2005 to S2006 in FIG. 8 described above to perform text processing. Note that the method of receiving input from the user is not limited to using the keyboard 308, and various methods can be applied. As a specific example, input from the user may be received using techniques such as so-called voice input.

[0081] The information processing system according to this modification example can apply the same configuration as that of the first embodiment in terms of system configuration and hardware configuration. The functional configuration of the information processing system according to this modification example will be described below with reference to FIG. 15. In this modification example, the description will mainly focus on the parts different from the first embodiment, and detailed descriptions of the parts substantially the same as those of the first embodiment will be omitted. The client 102 according to this embodiment is different from the example shown in FIG. 4 in that the dialogue input / output unit 1501 is provided. The dialogue input / output unit 1501 is a component on the client 102 side for realizing the dialogue between the system and the user, and receives input from the user and outputs information to be presented to the user from the system. Also, the server 104 according to this embodiment is different from the example shown in FIG. 4 in that the dialogue control unit 1502 is provided. The dialogue control unit 1502 uses the language generation unit 415 based on the large language model 416 to execute various processes for realizing the dialogue between the system and the user. Also, the dialogue control unit 1502 may execute processes for solving problems presented by the user, such as information search. The dialogue between the system and the user can be realized, for example, by using general language generation AI technologies such as ChatGPT and Bard. Also, not limited to language generation AI technologies, other AI technologies may be used. Note that since the processing of the information processing system according to this modification example is substantially the same as that of the information processing system according to the first embodiment described above, detailed description is omitted.

[0082] As described above, regarding the information processing system according to an embodiment of the present disclosure, it is also possible to realize the interaction between the system and the user when processing the text to be displayed in the text area in accordance with the text area in an interactive manner. By applying such a UI, an effect of further improving the usability of the system when editing layout data can be expected.

[0083] <Other Embodiments> The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or device via a network or various storage media, and a computer (or CPU, MPU, etc.) of the system or device reads and executes the program. In the above-described embodiment, a layout data creation application is given as an example of an application. However, it is not limited to this example, and it can be realized and is effective in any application having a similar image layout function. In the above-described embodiment, a personal computer is assumed as the information processing device. However, it is not limited to this example, and it can be realized and is effective for any information processing device (terminal) that can be used in a similar manner. The information processing device (terminal) is, for example, a mobile phone, a personal digital assistant, a digital still camera, a digital video camera, a portable music player, a game, a set-top box, an Internet appliance, etc. In the above-described embodiment, Ethernet is used as an example of the network configuration. However, it is not limited to this example, and other arbitrary network configurations such as wireless LAN, IEEE1394, Bluetooth, etc. may be used. As described above, the preferred embodiments of the present invention have been described in detail. However, the present invention is not limited to the specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0084] The disclosure of the present embodiment also includes the following methods, configurations, and programs. (Method 1) A control method for an information processing apparatus, comprising: a calculation step of calculating the number of characters that can be displayed in a specified text area based on the size attribute related to the specified text area; a generation step of generating a prompt including at least an instruction related to the processing of the specified text, the text input into the text area, and the number of characters calculated in the calculation step; and a processing step of inputting the prompt generated in the generation step to a model that has been learned to perform processing on the text specified by the prompt, thereby causing the model to generate processed text obtained by processing the text specified by the prompt, wherein the text input into the text area is updated with the processed text generated in the processing step. A control method for an information processing apparatus, characterized by this. (Method 2) The processing step inputs the prompt to the model to cause the model to generate the processed text when the difference or ratio between the number of characters of the text input into the text area and the number of characters that can be displayed in the text area calculated in the calculation step satisfies a condition set in advance and a threshold value set in advance. A control method for an information processing apparatus according to Method 1, characterized by this. (Method 3) Including a first reception step of receiving an instruction related to text processing from a user, and the processing step inputs the prompt to the model to cause the model to generate the processed text when the first reception step receives an instruction related to text processing. A control method for an information processing apparatus according to Method 1, characterized by this. (Method 4) The generation step generates the prompt using at least one of the metadata set in the text area and the metadata set in the content associated with the text area. A control method for an information processing apparatus according to any one of Methods 1 to 3, characterized by this. (Method 5) It includes a second reception step of receiving an instruction regarding addition of conditions related to text processing, and in the generation step, when generating the processed text in the processing step, the prompt is generated so that the processed text that satisfies the conditions indicated by the instruction received in the second reception step is generated. The control method of the information processing apparatus according to any one of Methods 1 to 4, characterized in that. (Method 6) The second reception step receives a designation of at least a partial range in the text input to the text area and an instruction regarding restriction of change of the range, and the generation step is based on the instruction received in the second reception step. When generating the processed text in the processing step, the prompt is generated so that the change of the range designated in the second reception step in the text input to the text area is restricted. The control method of the information processing apparatus according to Method 5, characterized in that. (Method 7) A display control step of controlling so that the processed text generated in the processing step is displayed in a predetermined display area, and a third reception step of receiving an instruction regarding update to the processed text for the text input to the text area. When the third reception step receives an instruction regarding update to the processed text, the text input to the text area is updated with the processed text. The control method of the information processing apparatus according to any one of Methods 1 to 6, characterized in that. (Method 8) It includes a fourth reception step of receiving an instruction regarding re-execution of text processing, and in the processing step, when the text previously input to the text area has not been updated with the processed text and the fourth reception step receives an instruction regarding re-execution of text processing, the processed text is generated again. The control method of the information processing apparatus according to Method 7, characterized in that. (Method 9) By inputting an instruction received from a user to a dialogue learning model that has been trained to generate a response to the input instruction, causing the model to generate a response to the instruction, and including an output control step of controlling so that the response is presented interactively to the user. In the output control step, based on a first instruction received from the user, the processed text in the processing step is generated, and the text input to the text area is updated with the processed text. A control method for an information processing apparatus according to any one of Methods 1 to 8, characterized by this. (Method 10) The control method for an information processing apparatus according to Method 9, characterized in that in the output control step, based on a second instruction received from the user, text to be input to the text area is generated. (Configuration 1) Calculation means for calculating the number of characters that can be displayed in a specified text area based on the size attribute related to the specified text area, the text input to the text area, and the number of characters calculated by the calculation means. Generation means for generating a prompt including at least an instruction related to the processing of the specified text, and inputting the prompt generated by the generation means to a model that has been trained to perform processing on the text specified by the prompt, so that the model generates processed text obtained by processing the text specified by the prompt. Processing means, and the text input to the text area is updated with the processed text generated by the processing means. An information processing apparatus characterized by this. (Program 1) A program that causes a computer to function as an information processing apparatus, the program comprising: a calculation means for calculating the number of characters that can be displayed in a specified text area based on size attributes related to the specified text area; a generation means for generating a prompt including at least an instruction related to the processing of the specified text, the text input to the text area, and the number of characters calculated by the calculation means; and a processing means for inputting the prompt generated by the generation means to a model that has been learned to perform processing on the text specified by the prompt, thereby causing the model to generate processed text obtained by processing the text specified by the prompt, wherein the text input to the text area is updated with the processed text generated by the processing means.

Explanation of Signs

[0085] 102 Client 104 Server 402 Text Data Processing Necessity Judgment Unit 413 Prompt Generation Unit 415 Language Generation Unit 416 Large Language Model

Claims

1. A control method for an information processing apparatus, comprising: a calculation step of calculating the number of characters that can be displayed in the text area based on the size attribute related to the specified text area; a generation step of generating a prompt that includes at least an instruction related to the processing of the specified text, the text input to the text area, and the number of characters calculated in the calculation step; a processing step of inputting the prompt generated in the generation step to a model that has been trained to perform processing on the text specified by the prompt based on the input prompt, thereby causing the model to generate processed text obtained by processing the text specified by the prompt; wherein the text input to the text area is updated with the processed text generated in the processing step A control method for an information processing apparatus, characterized by the above.

2. The processing step is to input the prompt to the model to cause the model to generate the processed text when the difference or ratio between the number of characters of the text input to the text area and the number of characters that can be displayed in the text area calculated in the calculation step satisfies a pre-set condition with a pre-set threshold value. The control method for an information processing apparatus according to Claim 1.

3. including a first reception step of receiving an instruction related to text processing from a user, wherein, when the first reception step receives an instruction related to text processing, the processing step inputs the prompt to the model to cause the model to generate the processed text A control method for an information processing apparatus according to Claim 1, characterized by the above.

4. The generation step is to generate the prompt using at least any one of the metadata set in the text area and the metadata set in the content associated with the text area. The control method for an information processing apparatus according to Claim 1.

5. including a second reception step of receiving an instruction related to adding conditions for text processing In the generation step, when generating the processed text in the processing step, the prompt is generated such that the processed text that satisfies the conditions indicated by the instruction received in the second reception step is generated. The control method for an information processing apparatus according to claim 1, characterized in that.

6. The second reception step receives at least a partial range designation in the text input to the text area and an instruction related to restriction of change of the range. In the generation step, based on the instruction received in the second reception step, when generating the processed text in the processing step, the prompt is generated such that change of the range designated in the second reception step in the text input to the text area is restricted. The control method for an information processing apparatus according to claim 5, characterized in that.

7. A display control step for controlling so that the processed text generated in the processing step is displayed in a predetermined display area; A third reception step for receiving an instruction related to update to the processed text, targeting the text input to the text area; including When the third reception step receives an instruction related to update to the processed text, the text input to the text area is updated by the processed text. The control method for an information processing apparatus according to claim 1, characterized in that.

8. including a fourth reception step for receiving an instruction related to re-execution of text processing; In the processing step, when the text previously input to the text area has not been updated by the processed text and the fourth reception step receives an instruction related to re-execution of the text processing, the processed text is generated again. The control method for an information processing apparatus according to claim 7, characterized in that.

9. Including an output control step of inputting an instruction received from a user to a dialogue learning model that has been learned to generate a response to an input instruction, causing the model to generate a response to the instruction, and controlling so that the response is presented dialogically to the user. In the output control step, based on the first instruction received from the user, the processed text in the processing step is generated, and the text input to the text area is updated with the processed text. A control method for an information processing apparatus according to claim 1, characterized by the above.

10. In the output control step, based on the second instruction received from the user, the text input to the text area is generated. A control method for an information processing apparatus according to claim 9, characterized by the above.

11. Calculation means for calculating the number of characters that can be displayed in the text area based on the size attribute related to the designated text area; Generation means for generating a prompt including at least an instruction related to the processing of the designated text, the text input to the text area, and the number of characters calculated by the calculation means; Processing means for inputting the prompt generated by the generation means to a model that has been learned to perform processing on the text specified by the prompt based on the input prompt, so as to generate processed text obtained by processing the text specified by the prompt by the model; It has: The text input to the text area is updated with the processed text generated by the processing means. An information processing apparatus, characterized by the above.

12. A computer, Calculation means for calculating the number of characters that can be displayed in the text area based on the size attribute related to the designated text area; Generation means for generating a prompt including at least an instruction related to the processing of the designated text, the text input to the text area, and the number of characters calculated by the calculation means; Processing means for inputting the prompt generated by the generation means to a model that has been learned to perform processing on the text specified by the prompt based on the input prompt, so as to generate processed text obtained by processing the text specified by the prompt by the model; It has: The text input to the text area is updated with the processed text generated by the processing means. A program for causing a computer to function as an information processing apparatus characterized by the above.

Images