Novel Generation Method, Device, Electronic Device and Medium Based on Text Storage Box

Abstract

The present application provides a novel generation method, device, electronic device, and medium based on text storage boxes. The method first displays a first novel generation page, which includes a first text display area and a first text storage area. The user selects N groups of candidate historical texts in the first text display area and drags them to blank text storage boxes in the first text storage area, obtaining N candidate text storage boxes. The second novel generation page is then displayed, which includes a second text display area and a second text storage area. The N candidate text storage boxes are displayed in the second text storage area. The user selects a target text storage box in the second text storage area and drags the target group of historical texts therein to a target position in the second text display area. The target group of historical texts can then be moved to the target position. Finally, the novel generated and displayed in the second text display area will include the target group of historical texts. The present application effectively improves the efficiency of novel generation.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a novel generation method, device, electronic device and medium based on a text storage box. Background Art

[0002] With the continuous development of artificial intelligence technology, novel generation technology based on artificial intelligence has gradually emerged. It can help people improve their writing efficiency, so the importance of this technology is becoming increasingly prominent. In the process of novel generation, among the large amount of content generated by artificial intelligence, there may be some content that is more in line with the user's wishes. The user not only needs to use these contents in the current location, but also wants to use these contents in other locations of the novel. There are mainly two methods used in the existing technology to use these contents in other locations. One is to manually turn to the original location of these contents based on memory, copy the content, and then turn it back to the current location for pasting. The other is to search in the full text or a specified range by setting keywords, and then find the required content one by one from all the found content. Finally, it is also necessary to copy the content and then turn it back to the current location for pasting.

[0003] However, for long novels generated by artificial intelligence, it is very difficult to find the desired content from a large number of paragraphs by manually searching. Although the keyword search method can relatively narrow the scope, each search will still display a large number of paragraphs that appear with the keyword but are actually irrelevant. It is still necessary to manually screen the found paragraphs one by one, making it difficult to achieve accurate search. Moreover, no matter which of the above methods is used, it depends on the user's memory. If the user does not think of which locations may contain the desired content, or does not think of the appropriate keywords, or the memory is wrong and the wrong keywords are thought of, it is difficult to find the desired content quickly and accurately. Finally, even if these contents are found, the traditional copy and paste method is also cumbersome to operate, especially when the length is long. There are often many paragraphs between the original position and the current position of the desired paragraph, and sometimes it is even necessary to turn many pages to copy and paste from the original position to the current position. All of the above factors greatly reduce the efficiency of novel generation.

[0004] Therefore, the current method of generating novels through artificial intelligence has the technical problem of low generation efficiency and needs to be improved. Summary of the Invention

[0005] The embodiments of the present application provide a novel generation method, device, electronic device and medium based on a text storage box, which are used to alleviate the technical problem of low generation efficiency in current novel generation methods.

[0006] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0007] The present application provides a novel generation method based on a text storage box, the method comprising:

[0008] Displaying a first novel generation page, the first novel generation page including a first text display area and a first text storage area, the first text display area displaying multiple historical texts, and the first text storage area displaying at least one blank text storage box;

[0009] In response to N selection operations on N different groups of candidate historical texts in the first text display area, and in response to a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, the N groups of candidate historical texts are respectively stored in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer;

[0010] Displaying a second novel generation page, the second novel generation page including a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes;

[0011] In response to a selection operation on a target text storage box in the second text storage area and a drag operation of dragging a target group of historical texts in the target text storage box to a target position in the second text display area, moving the target group of historical texts to the target position;

[0012] A novel containing the target group of historical texts is generated and displayed in the second text display area.

[0013] At the same time, the embodiment of the present application also provides a novel generation device based on a text storage box, the device comprising:

[0014] A first display module is used to display a first novel generation page, wherein the first novel generation page includes a first text display area and a first text storage area, wherein the first text display area displays multiple historical texts, and the first text storage area displays at least one blank text storage box;

[0015] a first response module, configured to, in response to N selection operations of N different groups of candidate historical texts in the first text display area, and a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, respectively store the N groups of candidate historical texts in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer;

[0016] A second display module is used to display a second novel generation page, the second novel generation page includes a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes;

[0017] a second response module, configured to move the target group historical text to a target position in response to a selection operation on a target text storage box in the second text storage area and a drag operation on the target group historical text in the target text storage box to a target position in the second text display area;

[0018] The third display module is used to generate and display novels containing the target group of historical texts in the second text display area.

[0019] The present application also provides an electronic device comprising a memory and a processor; the memory stores an application, and the processor is used to run the application in the memory to execute the steps in any one of the above-described novel generation methods.

[0020] An embodiment of the present application provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps in the above-mentioned novel generation method.

[0021] Beneficial effects: The present application provides a novel generation method, device, electronic device and medium based on a text storage box. The method first displays a first novel generation page, which includes a first text display area and a first text storage area. The user selects N groups of candidate historical texts in the first text display area and drags them to the blank text storage boxes in the first text storage area respectively to obtain N candidate text storage boxes. Then, the second novel generation page is displayed, which includes a second text display area and a second text storage area. The above-mentioned N candidate text storage boxes are displayed in the second text storage area. The user selects a target text storage box in the second text storage area and drags the target group historical text therein to the target position in the second text display area. The target group historical text can be moved to the target position. Finally, the novel generated and displayed in the second text display area will include the target group historical text. This application sets up a text storage area and a text storage box, so that the historical texts you like can be stored in the text storage box first. If you need to use them later, you only need to search in N text storage boxes. The search range is small, so you can quickly and accurately find the required target group of historical texts. In addition, when storing and applying historical texts, you only need to perform simple selection and drag operations between different areas of the same page. There is no need to switch back and forth between the location of the historical text and the current location. It is simple and easy to operate. The combination of the above factors effectively improves the efficiency of novel generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The following detailed description of the specific embodiments of the present application in conjunction with the accompanying drawings will make the technical solutions and other beneficial effects of the present application apparent.

[0023] Figure 1 A schematic diagram of a scenario of a novel generation method based on a text storage box provided in an embodiment of the present application.

[0024] Figure 2 This is a flow chart of the novel generation method based on the text storage box provided in an embodiment of the present application.

[0025] Figure 3 This is a first schematic diagram of generating a page for the first novel in an embodiment of the present application.

[0026] Figure 4 This is a second schematic diagram of generating a page for the first novel in an embodiment of the present application.

[0027] Figure 5 This is a third schematic diagram of generating a page for the first novel in an embodiment of the present application.

[0028] Figure 6 This is a first schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0029] Figure 7 This is a second schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0030] Figure 8 This is a third schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0031] Figure 9 This is a fourth schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0032] Figure 10 This is a fifth schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0033] Figure 11 This is a sixth schematic diagram of generating a page for the second novel in an embodiment of the present application.

[0034] Figure 12 A schematic structural diagram of a novel generation device based on a text storage box provided in an embodiment of the present application.

[0035] Figure 13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0036] Description of reference numerals:

[0037] Generation device 11; large language model 12; first text display area 100; first text storage area 200; blank text storage box 30; blank label 31; candidate text storage box 40; first feature label 41; second text display area 300; second text storage area 400; label display area 500; storage box display area 600; first display module 121; first response module 122; second display module 123; second response module 124; third display module 125; radio frequency circuit 101; memory 102; input unit 103; display unit 104; sensor 105; audio circuit 106; WiFi module 107; processor 108. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0039] See also Figure 1 , Figure 1 A schematic diagram of a scenario for the application of the novel generation method based on the text storage box provided in an embodiment of the present application, wherein the scenario includes a generation device 11 and a large language model 12. A novel generation application / website runs in the generation device 11, and the user issues various instructions for generating a novel in the relevant interface of the novel generation application / website. The generation device 11 responds to the instructions, constructs various prompt words, and calls the large language model 12 to process the prompt words. After processing, the generated content is returned in sequence, and finally the entire novel is obtained and displayed in the generation device 11.

[0040] During the novel generation process, the novel generation application / website first displays the first novel generation page. The first novel generation page includes a first text display area and a first text storage area. The large language model 12 generates a large amount of historical texts, which are displayed to the user through the first text display area. The user can select multiple groups of historical texts of their choice and store them in the blank text storage box in the first text storage area by dragging and dropping. N selection and dragging operations can obtain N candidate text storage baskets, and each candidate text storage box contains a selected group of candidate historical texts. When continuing to generate novels, the novel generation application / website will display a second novel generation page. The second novel generation page includes a second text display area and a second text storage area. The current text generated by the large language model 12 is displayed to the user through the second text display area. At the same time, N candidate text storage boxes are displayed to the user through the second text storage area. The user can select a target text storage box currently required from the second text storage area, and move the target group historical text stored in it to the target position of the second text display area by dragging and dropping. After moving, the target group historical text can be displayed in the second text display area and serve as part of the final generated novel.

[0041] Through the above method, users can quickly and accurately find the target group of historical texts they need, and can generate novels containing the target group of historical texts by simply performing simple selection and drag operations between different areas of the same page. The entire process is simple and easy to operate, which effectively improves the efficiency of novel generation. The following examples will describe the above novel generation process in detail.

[0042] See also Figure 2 , Figure 2 : is a flow chart of a novel generation method based on a text storage box provided in an embodiment of the present application, the method specifically comprising:

[0043] S1: Displaying a first novel generation page, the first novel generation page includes a first text display area and a first text storage area, the first text display area displays multiple historical texts, and the first text storage area displays at least one blank text storage box.

[0044] A large language model is a language model with a large parameter size designed to understand and generate human language. Trained with large amounts of text data, it can perform a wide range of tasks, including text summarization, translation, analysis, and generation. When a novel generation application / website generates novels using a large language model, the novel text is generated incrementally. For generated historical texts, including the main text and outline, the page containing them is the first novel generation page. This first novel generation page includes a first text display area and a first text storage area. The first text display area is used to display multiple historical texts. Initially, the first text storage area contains at least one blank text storage box. A blank text storage box only has a storable shape but is not filled with valid content. The interior of a blank text storage box can be completely blank, or a prompt such as "Drag and drop content" can be set as needed. This prompt disappears automatically after the user performs the drag and drop operation. The number of blank text storage boxes can be customized or created.

[0045] The first text storage area can have two states: folded and expanded. If the user does not currently need to use the text storage function, it can be folded and only the first text display area can be retained on the first novel generation page to facilitate the user to browse or edit historical texts, etc.; if the user currently needs to use the text storage function, the first text display area and the first text storage area can be retained at the same time on the first novel generation page. The two areas can be displayed side by side, for example, the first text display area is on the left and the first text storage area is on the right, to facilitate selection and drag operations.

[0046] For example, Figure 3 As shown, the first novel generation page includes a first text display area 100 and a first text storage area 200. For ease of representation, the two are separated by a dotted line. The dotted line is only used to divide the area, and does not indicate that the dotted line actually exists in the actual scene. The first text display area 100 displays historical texts, which may specifically include outlines and text contents at all levels. The outlines at all levels may include part outlines, chapter outlines, and paragraph outlines, and the text contents may include the text of each chapter. The first text storage area 200 displays a plurality of blank text storage boxes 30. The blank position in each blank text storage box 30 can display similar prompt information such as "drag and drop content". In addition, each blank text storage box 30 is also provided with a blank label 31. The label part will be further explained in the subsequent embodiments.

[0047] S2: In response to N selection operations on N groups of different candidate historical texts in the first text display area, and the dragging operation of dragging each selected group of candidate historical texts to one of the blank text storage boxes in the first text storage area, the N groups of candidate historical texts are respectively stored in N candidate text storage boxes, each group of candidate historical texts includes at least one section of candidate historical text, and N is a positive integer.

[0048] After the user selects a group of historical texts in the first text display area, the generation device responds to this operation and uses this group of historical texts as a group of candidate historical texts. Candidate means that this group of historical texts is available for the user to select in subsequent steps. Each group of candidate historical texts includes at least one candidate historical text, which means that each time the user selects these contents, they can select only one historical text or two or more historical texts at the same time. If only one historical text is selected, the entire historical text can be selected, or only a part of the text within a historical text can be selected. In other words, when selecting historical texts, users can flexibly select the content of historical texts according to their own needs.

[0049] After selecting, the user drags the set of candidate historical texts to one of the blank text storage boxes in the first text storage area. In response to this operation, the generation device stores the set of candidate historical texts in the corresponding blank text storage box, and the blank text storage box serves as the candidate text storage box. After dragging, the set of candidate historical texts remains displayed in the first text display area, that is, the dragging has no effect on it.

[0050] For example, Figure 4 As shown, the user performs a selection and drag operation on a certain set of historical texts such as "Text Plot 1" displayed in the first text display area 100, and drags it to one of the blank text storage boxes 30. Figure 5 As shown, after the dragging is completed, “Main Text Plot 1” is stored in the blank text storage box 30 , and a candidate text storage box 40 is obtained.

[0051] After performing the above selection and dragging operations, a candidate text storage box is obtained in the first text storage area, which contains a set of candidate historical texts. The user performs the above selection and dragging operations again on another set of historical texts, which results in another candidate text storage box, which contains another set of candidate historical texts. By performing the selection and dragging operations N times, N candidate text storage boxes can be obtained, where N is a positive integer, i.e., there is at least one candidate text storage box.

[0052] In one embodiment, S2 specifically includes:

[0053] S21: Inputting a group of candidate historical texts selected each time into the large language model to obtain at least one first feature label.

[0054] S22: Each group of candidate historical texts and the associated first feature tags are stored together in a corresponding candidate text storage box.

[0055] After selecting a group of candidate historical texts each time, in addition to storing them in a candidate text storage box, you can also perform feature extraction on them to obtain a first feature tag, and store the group of candidate historical texts and the associated first feature tags together and display them in the candidate text storage box. In the subsequent search process, you can first view the first feature tags displayed in each candidate text storage box, select several first feature tags of your choice from all the first feature tags, and then view the specific text content in the candidate text storage boxes corresponding to these tags, and finally determine the desired target text storage box. Compared to the method of directly viewing the text content, the method of viewing the tags first and then viewing the text content can reduce the user's viewing workload, allowing the user to quickly locate the required content, further improving search efficiency.

[0056] Each time a set of candidate historical texts is selected, the backend constructs corresponding prompt words based on the content of the candidate texts and inputs these prompt words into the large language model. The prompt words prompt the large language model to perform feature extraction on the candidate texts, selecting or summarizing the words that best match the characteristics of the texts from all the text content and outputting them. The large language model processes these prompt words and outputs several words as first feature labels. The number of first feature labels can be set as needed, such as two, three, or more.

[0057] Specifically, the prompt words are as follows:

[0058] Please analyze the following novel paragraph, extract key information, annotate it, and output it in JSON format.

[0059] Paragraph content: [User excerpted novel paragraph]

[0060] JSON output format: { "all words": ["word 1", "word 2", "word 3", "..."], "final selection": [ "most characteristic word 1", "most characteristic word 2", "most characteristic word 3"]}

[0061] Notes:

[0062] 1. All words: Extract all nouns, verbs, adjectives, etc. that appear in the paragraph, including characters, places, things, emotions, plot, etc. These words should be able to summarize the content of the paragraph as comprehensively as possible.

[0063] 2. Proper Nouns: "All Words" must include at least one proper noun (e.g., name of a person, place, book, organization, etc.). If there are no obvious proper nouns in the paragraph, try to find implicit proper nouns or proper nouns related to the paragraph's topic.

[0064] 3. Final Selection: From "All Words," select the three words with the highest information content and that best represent the text as the final annotation results. These three words must include at least one proper noun. The most distinctive words are those that best reflect the paragraph's theme, emotion, style, or meaning. The selected words should be representative and general, helping readers quickly grasp the core content of the paragraph.

[0065] 4. JSON format: Please ensure that the output JSON format is correct and avoid syntax errors. "All words" and "Final selection" should be placed in the same array.

[0066] Please be sure to read the above precautions carefully to ensure that the annotation results you provide are accurate and complete.

[0067] Of course, the above is only one example of the prompt word content, and this application is not limited to this. Technical personnel in this field can reasonably set the prompt word content as needed, as long as the large language model can understand and output the corresponding first feature label.

[0068] Specifically, suppose the novel paragraph excerpted by the user (a set of candidate historical texts) contains the following content:

[0069] "The sun sets in the west, and the heartbroken man is far away." He rode a skinny horse, slowly walking along the desolate ancient road. The cold wind blew, stirring up the yellow sand on the ground and blinding his eyes. He felt a surge of loneliness and despair in his heart.

[0070] After processing the content of the prompt words, the large language model obtains "all words" including: "sunset", "heartbroken person", "end of the world", "thin horse", "ancient road", "cold wind", "yellow sand", "loneliness", "despair", "traveler", and "desolation". The "final choice" includes: "sunset", "loneliness", and "heartbroken person". The final first feature tags include: "sunset", "loneliness", and "heartbroken person".

[0071] In existing keyword search schemes, users need to actively think of keywords. If they cannot think of the right keywords at the moment, or if they mistakenly think of the wrong keywords, it is difficult to quickly and accurately find the desired historical text. Therefore, this scheme is difficult to implement and has low search efficiency. In the embodiment of the present application, the first feature tag is the most representative word automatically generated by the large language model after feature recognition of each group of candidate historical texts. Using this as a reference for search can achieve precise positioning, and searching within the range of existing tags will also reduce the difficulty of searching, effectively improving search efficiency.

[0072] In one embodiment, the first feature tag can also be modified or added in a customized manner. By combining customization and model generation, the first feature tag can more accurately reflect the characteristics of each group of historical texts and provide an effective reference for subsequent searches.

[0073] For example, Figure 4 and Figure 5 As shown, "Tag 1" and "Tag 2" are used to represent the specific content of the generated first feature tag 41, and the specific content of these first feature tags 41 will be filled in the blank tag 31. The user can also modify the content filled in the blank tag 31, or add a new blank tag 31 and fill in the content to obtain the final first feature tag 41.

[0074] S3: Display a second novel generation page, which includes a second text display area and a second text storage area. The second text display area displays multiple current texts, and the second text storage area displays N candidate text storage boxes.

[0075] For the currently generated text, including the outline content and the main text content, the page where it is located is the second novel generation page. The second novel generation page includes a second text display area and a second text storage area, wherein the second text display area is used to display multiple paragraphs of current text, and the second text storage area is used to display the N candidate text storage boxes obtained in the above steps.

[0076] Similarly, the second text storage area can have two states: folded and expanded. If the user does not currently need to use the candidate historical text, it can be folded and only the second text display area can be retained on the second novel generation page to facilitate the user to browse or edit the current text; if the user currently needs to use the candidate historical text, the second text display area and the second text storage area can be retained at the same time on the second novel generation page. The two areas can be displayed side by side, for example, the second text display area is on the left and the second text storage area is on the right, to facilitate subsequent selection and drag operations.

[0077] For example, Figure 6As shown, the second novel generation page includes a second text display area 300 and a second text storage area 400. The current text is displayed in the second text display area 300, which may specifically include outlines and main text content at all levels. A plurality of candidate text storage boxes 40 are displayed in the second text storage area 400, and each candidate text storage box 40 contains a group of candidate historical texts selected and dragged in the above steps, such as "Main Text Plot 1", "Main Text Plot 12", "Main Text Plot 15", "Main Text Plot 20", etc. At the same time, each candidate text storage box 40 displays a corresponding first feature tag 41, Figure 6 In the figure, “label 1” to “label 8” are used to represent them respectively.

[0078] S4: In response to the selection operation of the target text storage box in the second text storage area and the dragging operation of dragging the target group history text in the target text storage box to the target position in the second text display area, the target group history text is moved to the target position.

[0079] After the user selects a candidate text storage box in the second text storage area, the generation device responds to the operation and uses the candidate text storage box as the target text storage box, and the group of historical texts stored in the target text storage box as the target group of historical texts. The user drags the target group of historical texts to a target position in the second text display area, and the generation device responds to the operation and moves the target group of historical texts to the target position.

[0080] In one embodiment, S4 specifically includes:

[0081] S41: If generated text exists at the target location, the generated text is replaced with the target group historical text.

[0082] S42: If there is no generated text at the target location, insert the target group history text into the target location.

[0083] The target position can be any position specified by the user. Depending on the specific situation of the target position, the target group historical text can be processed differently. If there is generated text at the target position, that is, the last position of the drag operation is located directly above a certain current text, then the generated text can be replaced with the target group historical text. After the replacement, only the target group historical text is retained at the target position, and the generated text is overwritten. If there is no generated text at the target position, that is, the last position of the drag operation is located in a blank position above or below a certain current text, then the target group historical text can be inserted into the blank position. After the insertion, the target position retains the target group historical text, and the generated text still exists.

[0084] Through the above method, the user can easily complete the insertion or replacement of the historical text of the target group. Of course, the present application is not limited to this. For insertion or replacement, the user can also set it by himself. For example, after the dragging action is completed, a pop-up window can be displayed to the user. The pop-up window includes options for insertion and replacement. When the user selects one of the options, regardless of whether there is generated text at the target location, the result corresponding to the option is generated. Or before dragging, the insertion or replacement is set first. When the user performs the dragging operation, regardless of whether there is generated text at the target location, the result corresponding to the setting is generated. Those skilled in the art can reasonably set the insertion and replacement methods as needed, as long as the corresponding effect can be achieved simply and quickly.

[0085] In one embodiment, after S4, the method further includes:

[0086] S4a: removing the target text storage box from the second text storage area.

[0087] For the same group of historical texts, if it has been dragged once, the user will most likely not need to use it again in the new location. If the group of historical texts is still retained in the second text storage area after dragging, it will take up space in the second text storage area, which will increase the workload when searching for the required historical texts later. In addition, if the user forgets that the group of historical texts has been dragged, the group of historical texts may be selected again by the user and appear again in the novel, and too many occurrences of the same content or similar content will affect the quality of the novel. Therefore, after the target group of historical texts is moved to the target position, the target text storage box can be removed from the second text storage area to make room for the second text storage area, and also avoid the decline in novel quality caused by user misselection.

[0088] For example, Figure 7 and Figure 9 As shown, the user performs a selection and drag operation on a group of candidate historical texts such as "Text Plot 12" displayed in the second text storage area 400, and drags it to a target position in the second text display area 300. Figure 8 and Figure 10 As shown, after the dragging is completed, "Main Text Episode 12" is moved to the target position, and the corresponding target text storage box in the second text storage area 400 is removed. Figure 7 If there is a generated text "Main Text Plot Thirty-Two" at the target location, then after moving, "Main Text Plot Twelve" will replace "Main Text Plot Thirty-Two". Figure 9 If there is no generated text at the target location, then after moving, "Main Text Plot 12" will be inserted between "Main Text Plot 31" and "Main Text Plot 32".

[0089] In one embodiment, the second text storage area includes a label display area and a storage box display area, and after S22, further includes:

[0090] S23: Display all candidate text storage boxes in the storage box display area, and display all first feature tags in the tag display area.

[0091] Prior to S4, it also included:

[0092] S4a: In response to a selection operation on the target first characteristic tag in the tag display area, a candidate text storage box associated with the target first characteristic tag is preferentially displayed in the storage box display area.

[0093] Each candidate text storage box is displayed in the second text storage area. In addition to storing a set of candidate historical texts, each candidate text storage box also stores the first feature tag generated in the above steps. If the candidate text storage box is only displayed in the second text storage area, since the candidate text storage box has a certain size and the content displayed on the page of the generating device is limited, when there are many candidate text storage boxes, usually only a part of the candidate text storage boxes will be displayed, and the other part of the candidate text storage boxes will not be displayed first. This part will be displayed when the user performs a page turning operation. In this case, when the user wants to view the first feature tag, he not only needs to view the several candidate text storage boxes displayed on the current page, but also needs to constantly operate to turn out the hidden candidate text storage boxes, which makes the viewing efficiency lower. In addition, the user may sometimes need to view the text content corresponding to several specific tags, and the method of manually selecting tags one by one will also make viewing more difficult.

[0094] Therefore, in this embodiment, the second text storage area is divided into a label display area and a storage box display area. The storage box display area is used to display all candidate text storage boxes, which can be displayed directly or after turning the page. The label display area is used to display all first-character labels without displaying specific text content. Similarly, the first-character label can be displayed directly or after turning the page. The label display area can be expanded or collapsed based on the user's selection. When expanded, the label display area and the storage box display area can be set side by side, for example, the label display area is set above the storage box display area.

[0095] When the user performs a selection operation on one or some first feature tags in the tag display area, the generating device responds to the operation, uses these first feature tags as target first feature tags, and then determines the part of candidate text storage boxes associated with the target first feature tags from all candidate text storage boxes, and preferentially displays these candidate text storage boxes in the storage box display area. There are many ways to prioritize display, such as only displaying this part of the candidate text storage boxes and hiding the others; or displaying this part of the candidate text storage boxes at the top; or distinguishing this part of the candidate text storage boxes from other parts with colors, etc. Those skilled in the art can set the priority display method as needed, so that users can intuitively see this part of the candidate text storage boxes and the specific text content stored therein.

[0096] Since the first feature label has fewer words, through the above method, the user does not need to search through all the candidate text storage boxes to select the desired first feature label. He only needs to select it in the label display area. Later, he only needs to view the candidate text storage boxes that are displayed first, thus reducing the viewing difficulty and improving work efficiency.

[0097] For example, Figure 11 As shown, the second text storage area 400 includes a label display area 500 and a storage box display area 600. The storage box display area 600 is used to display all candidate text storage boxes 40, and the label display area 500 is used to display all first feature labels 41. When there are many display objects, both can display more objects by turning pages. After the user selects one or several first feature labels 41 in the label display area 500, the storage box display area 600 will give priority to displaying the corresponding one or several candidate text storage boxes 40. In addition, a search box can be set in the storage box display area 600. The user can search for the required candidate text storage box 40 by selecting the first feature label 41, or enter relevant information in the search box to search. The combination of the two further improves efficiency.

[0098] In one embodiment, before S4, the method further includes:

[0099] S4b: In response to a selection operation on the target current text in the second text display area, the target current text is input into the large language model to obtain at least one second feature tag.

[0100] S4c: Match the second feature tag with all first feature tags associated with the N candidate text storage boxes.

[0101] S4d: The candidate text storage box associated with the successfully matched first feature tag is preferentially displayed in the second text storage area.

[0102] In the above embodiment, the user first manually selects the target text storage box in the second text storage area, and then drags it into the second text display area. For the manual selection method, the efficiency still needs to be improved. In this embodiment, after the second novel generation page is displayed, the user first selects one or several paragraphs of current text in the second text display area. These current texts are usually texts that need to be replaced later, or these current texts are located near the position that needs to be inserted later. In response to this operation, the generating device uses these current texts as target current texts. The background constructs corresponding prompt words according to the content of the target current text, and inputs the prompt words into the large language model. The prompt words are used to prompt the large language model to extract features of the target current text, and select or extract several words that best match the target current text from all text contents as the second feature label. Different from the above embodiment, the second feature label does not need to be displayed.

[0103] After obtaining the second feature tag, the backend will match the second feature tag with all the first feature tags associated with the N candidate text storage boxes. If a first feature tag is the same as any second feature tag, it indicates a successful match; otherwise, it indicates an unsuccessful match. The number of second feature tags can be equal to or different from the number of first feature tags. Those skilled in the art can adjust the number of the two tags appropriately as needed to achieve a better matching effect.

[0104] In the case of a successful match, some candidate text storage boxes associated with the first feature tag are determined from all candidate text storage boxes, and are preferentially displayed in the second text storage area. Similarly, there are many ways to prioritize display, such as only displaying this part of the candidate text storage boxes and hiding the others; or displaying this part of the candidate text storage boxes at the top; or distinguishing this part of the candidate text storage boxes from other parts by color, etc. Those skilled in the art can set the priority display method as needed, so that users can intuitively see this part of the candidate text storage boxes and the specific text content stored therein.

[0105] For example, the second feature label obtained by the target current text selected by the user includes "role a". If the first feature labels of 3 candidate text storage boxes among N candidate text storage boxes all include "role a", then these 3 candidate text storage boxes will be displayed to the user first, and then the user will select the most suitable target text storage box from them.

[0106] This application uses a large language model to generate a first feature tag and a second feature tag respectively. By matching the two types of tags, one or several candidate text storage boxes with the highest content relevance to the target current text can be accurately found from N candidate text storage boxes. This part of the text content is more in line with the creation logic than other content and is more suitable for inserting or replacing the target current text. Since the search range is narrowed from N to one or several, the viewing difficulty is reduced and work efficiency is improved.

[0107] In one embodiment, S2 specifically further includes:

[0108] S24: Obtain the original location information of each group of candidate historical texts.

[0109] S25: Each group of candidate historical texts and the associated original location information are stored together in a corresponding candidate text storage box.

[0110] After S3 also includes:

[0111] S3a: In response to a selection operation on the target original position information associated with the target group historical text, jump to display the target original position where the target group historical text is located in the second text display area.

[0112] The user selects and drags a group of candidate historical texts in order to directly use the group of candidate historical texts. However, in some cases, the user may also need to know where the group of candidate historical texts was excerpted from and what content is written in the context of the excerpt location, so as to select the most appropriate target group of candidate historical texts or better edit the group of candidate historical texts after moving. In this case, when the user selects and drags a group of historical texts, the background can obtain the original location information of the group of candidate historical texts. The original location information is used to record the location of the group of candidate historical texts in the story when they were originally generated, such as Chapter 2, Paragraph 5. After acquisition, each group of candidate historical texts and the associated original location information are stored together in the corresponding candidate text storage box. After the second story generation page is displayed to the user, in addition to performing the selection and dragging operations in S4, the user can also perform a selection operation on the target original position information associated with the target group historical text. In response to this operation, the generation device can jump the second text display area from the current position to the target original position where the target group historical text is located, for example, from the 20th paragraph of Chapter 2 to the 5th paragraph of Chapter 2, so that the user can make a decision after understanding the context information, thereby improving the generation quality of the novel.

[0113] S5: Generate and display a novel containing the target group of historical texts in the second text display area.

[0114] After moving the target group historical text to the target position, multiple segments of current text and target group historical text will be displayed in the second text display area. The user can directly accept or save these contents, or modify them and then accept or save them, so that these contents can be used as the latest generated content of the novel.

[0115] It can be seen from the above embodiments that the novel generation method provided by the present application can first store the favorite historical text into the text storage box by setting the text storage area and the text storage box. If it is needed later, it only needs to be searched in N text storage boxes. The search range is small, so the required target group of historical texts can be found quickly and accurately. In addition, when storing and applying historical texts, it is only necessary to perform simple selection and drag operations between different areas of the same page. There is no need to switch back and forth between the location of the historical text and the current location. It is simple and easy to operate. The combination of the above factors effectively improves the efficiency of novel generation.

[0116] Based on the method described in the above embodiment, this embodiment will further describe the novel generation device based on the text storage box. Figure 12 , the novel generating device may include:

[0117] A first display module 121 is used to display a first novel generation page, wherein the first novel generation page includes a first text display area and a first text storage area, wherein the first text display area displays multiple historical texts, and the first text storage area displays at least one blank text storage box;

[0118] A first response module 122 is configured to, in response to N selection operations of N different groups of candidate historical texts in the first text display area, and a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, store the N groups of candidate historical texts in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer;

[0119] A second display module 123 is used to display a second novel generation page, wherein the second novel generation page includes a second text display area and a second text storage area, wherein the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes;

[0120] A second responding module 124 is configured to move the target group historical text to a target position in response to a selection operation on a target text storage box in the second text storage area and a drag operation on the target group historical text in the target text storage box to a target position in the second text display area;

[0121] The third display module 125 is configured to generate and display a novel containing the target group of historical texts in the second text display area.

[0122] In one embodiment, the first response module 122 includes:

[0123] An input unit, configured to input a group of candidate historical texts selected each time into the large language model to obtain at least one first feature label;

[0124] The first storage unit is used to store each group of candidate historical texts and the associated first feature tags in a corresponding candidate text storage box.

[0125] In one embodiment, the second text storage area includes a label display area and a storage box display area, and the novel generation device further includes a fourth display module operating after the display unit, and a third response module operating before the second response module 124;

[0126] The fourth display module is used to display all candidate text storage boxes in the storage box display area and display all first feature tags in the tag display area;

[0127] The third response module is configured to, in response to a selection operation on a target first feature tag, preferentially display a candidate text storage box associated with the target first feature tag in the second text storage area.

[0128] In one embodiment, the novel generation device further includes an input module, a matching module, and a fifth display module that operate before the second response module 124;

[0129] The input module is configured to, in response to a selection operation on a target current text in the second text display area, input the target current text into the large language model to obtain at least one second feature label;

[0130] The matching module is used to match the second feature tag with all first feature tags associated with the N candidate text storage boxes;

[0131] The fifth display module is used to preferentially display the candidate text storage box associated with the successfully matched first feature tag in the second text storage area.

[0132] In one embodiment, the second response module 124 includes:

[0133] a replacement unit, configured to replace the generated text with the target group historical text if the generated text exists at the target location;

[0134] An inserting unit is configured to insert the target group history text into the target location if no generated text exists at the target location.

[0135] In one embodiment, the novel generation device further includes a removal module operating after the second response module 124, and the removal module is used to remove the target text storage box from the second text storage area.

[0136] In one embodiment, the first response module 122 includes:

[0137] An acquisition unit, used for acquiring original position information of each group of candidate historical texts;

[0138] A second storage unit is used to store each group of candidate historical texts and the associated original location information into a corresponding candidate text storage box;

[0139] The novel generation device also includes a fourth response module that works after the second display module 123. The fourth response module is used to jump to display the target original position of the target group historical text in the second text display area in response to a selection operation of the target original position information associated with the target group historical text.

[0140] Different from the existing technology, the novel generation device based on the text storage box provided by the present application can store the favorite historical text in the text storage box first by setting a text storage area and a text storage box. If it is needed later, it only needs to be searched in N text storage boxes. The search range is small, so the required target group of historical texts can be found quickly and accurately. In addition, when storing and applying historical texts, it is only necessary to perform simple selection and drag operations between different areas of the same page. There is no need to switch back and forth between the location of the historical text and the current location. It is simple and easy to operate. The combination of the above factors effectively improves the efficiency of novel generation.

[0141] Accordingly, the embodiment of the present application further provides an electronic device, such as Figure 13 As shown, the electronic device may include components such as a radio frequency (RF) circuit 101, a memory 102 including one or more computer-readable storage media, an input unit 103, a display unit 104, a sensor 105, an audio circuit 106, a WiFi module 107, a processor 108 including one or more processing cores, and a power supply 109. It will be understood by those skilled in the art that Figure 13 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0142] The radio frequency circuit 101 can be used to receive and transmit signals during information transmission or calls. Specifically, it receives downlink information from the base station and transmits it to one or more processors 108 for processing. It also transmits uplink data to the base station. The memory 102 can be used to store software programs and modules. The processor 108 executes the software programs and modules stored in the memory 102 to perform various functional applications and generate novels. The input unit 103 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0143] The display unit 104 may be used to display information input by a client or information provided to a client, as well as various graphical client interfaces of the server. These graphical client interfaces may be composed of graphics, text, icons, videos, or any combination thereof.

[0144] The electronic device may further include at least one sensor 105, such as a light sensor, a motion sensor, or other sensors. The audio circuit 106 may include a speaker, which may provide an audio interface between the user and the electronic device.

[0145] WiFi is a wireless transmission technology. Electronic devices can help customers send and receive emails, browse web pages and follow up streaming media through WiFi module 107. It provides customers with wireless broadband Internet follow-up. Figure 13 A WiFi module 107 is shown, but it is understandable that it is not an essential component of the electronic device and can be omitted as needed without changing the essence of the application.

[0146] The processor 108 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 102 and calling data stored in the memory 102, it performs various functions of the electronic device and processes data, thereby monitoring the entire mobile phone.

[0147] The electronic device also includes a power supply 109 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 108 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions.

[0148] Although not shown, the electronic device may also include a camera, a Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 108 in the server will load the executable files corresponding to one or more application processes into the memory 102 according to the following instructions, and the processor 108 will run the application stored in the memory 102, thereby achieving the following functions:

[0149] Displaying a first novel generation page, the first novel generation page including a first text display area and a first text storage area, the first text display area displaying multiple historical texts, and the first text storage area displaying at least one blank text storage box;

[0150] In response to N selection operations on N different groups of candidate historical texts in the first text display area, and in response to a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, the N groups of candidate historical texts are respectively stored in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer;

[0151] Displaying a second novel generation page, the second novel generation page including a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes;

[0152] In response to a selection operation on a target text storage box in the second text storage area and a drag operation of dragging a target group of historical texts in the target text storage box to a target position in the second text display area, moving the target group of historical texts to the target position;

[0153] A novel containing the target group of historical texts is generated and displayed in the second text display area.

[0154] The electronic device provided by the present application can store the historical texts you like in the text storage box by setting a text storage area and a text storage box. If you need to use it later, you only need to search among N text storage boxes. The search range is small, so you can quickly and accurately find the required target group of historical texts. In addition, when storing and applying historical texts, you only need to perform simple selection and drag operations between different areas of the same page. There is no need to switch back and forth between the location of the historical text and the current location. It is simple and easy to operate. The combination of the above factors effectively improves the efficiency of novel generation.

[0155] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the detailed description above and will not be repeated here.

[0156] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0157] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of instructions, which can be loaded by a processor to implement the following functions:

[0158] Displaying a first novel generation page, the first novel generation page including a first text display area and a first text storage area, the first text display area displaying multiple historical texts, and the first text storage area displaying at least one blank text storage box;

[0159] In response to N selection operations on N different groups of candidate historical texts in the first text display area, and in response to a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, the N groups of candidate historical texts are respectively stored in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer;

[0160] Displaying a second novel generation page, the second novel generation page including a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes;

[0161] In response to a selection operation on a target text storage box in the second text storage area and a drag operation of dragging a target group of historical texts in the target text storage box to a target position in the second text display area, moving the target group of historical texts to the target position;

[0162] A novel containing the target group of historical texts is generated and displayed in the second text display area.

[0163] The computer-readable storage medium provided by the present application can store the historical texts you like in the text storage box by setting a text storage area and a text storage box. If you need to use it later, you only need to search in N text storage boxes. The search range is small, so you can quickly and accurately find the required target group of historical texts. In addition, when storing and applying historical texts, you only need to perform simple selection and drag operations between different areas of the same page. There is no need to switch back and forth between the location of the historical text and the current location. It is simple and easy to operate. The combination of the above factors effectively improves the efficiency of novel generation.

[0164] The above is a detailed introduction to the novel generation method, device, electronic device and computer-readable storage medium based on a text storage box provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the technical solutions and core ideas of the present application; ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A novel generation method based on a text storage box, characterized in that: The method comprises: Displaying a first novel generation page, the first novel generation page including a first text display area and a first text storage area, the first text display area displaying multiple historical texts, and the first text storage area displaying at least one blank text storage box; In response to N selection operations on N different groups of candidate historical texts in the first text display area, and in response to a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, the N groups of candidate historical texts are respectively stored in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer; Displaying a second novel generation page, the second novel generation page including a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes; In response to a selection operation on a target text storage box in the second text storage area and a drag operation of dragging a target group of historical texts in the target text storage box to a target position in the second text display area, moving the target group of historical texts to the target position; A novel containing the target group of historical texts is generated and displayed in the second text display area.

2. The novel generation method according to claim 1, characterized in that: The step of storing N groups of candidate historical texts in N candidate text storage boxes respectively includes: Inputting a group of candidate historical texts selected each time into the large language model to obtain at least one first feature label; Each group of candidate historical texts and the associated first feature tags are stored together in a corresponding candidate text storage box.

3. The novel generation method according to claim 2, characterized in that: The second text storage area includes a label display area and a storage box display area. After the step of storing each group of candidate historical texts and the corresponding first feature label in the corresponding candidate text storage box, the method further includes: Displaying all candidate text storage boxes in the storage box display area, and displaying all first feature tags in the tag display area; Before the step of responding to the selection operation of the target text storage box in the second text storage area, the method further includes: In response to a selection operation on a target first characteristic tag in the tag display area, a candidate text storage box associated with the target first characteristic tag is preferentially displayed in the storage box display area.

4. The novel generation method according to claim 2, characterized in that: Before the step of responding to the selection operation of the target text storage box in the second text storage area, the method further includes: In response to a selection operation on a target current text in the second text display area, inputting the target current text into a large language model to obtain at least one second feature label; Matching the second feature tag with all first feature tags associated with the N candidate text storage boxes; The candidate text storage box associated with the successfully matched first feature tag is preferentially displayed in the second text storage area.

5. The novel generation method according to claim 1, characterized in that: The step of moving the target group historical text to the target location includes: If there is generated text at the target location, replace the generated text with the target group historical text; If there is no generated text at the target location, insert the target group history text into the target location.

6. The novel generation method according to claim 1, characterized in that: After the step of moving the target group historical text to the target location, the method further includes: The target text storage box is removed from the second text storage area.

7. The novel generation method according to claim 1, characterized in that: The step of storing N groups of candidate historical texts in N candidate text storage boxes respectively includes: Obtain the original location information of each set of candidate historical texts; Each set of candidate historical texts and the associated original location information are stored together in a corresponding candidate text storage box; After showing the steps for generating the second novel page, it also includes: In response to a selection operation on the target original position information associated with the target group historical text, the target original position where the target group historical text is located is displayed in the second text display area.

8. A novel generating device based on a text storage box, characterized in that: The device comprises: A first display module is used to display a first novel generation page, wherein the first novel generation page includes a first text display area and a first text storage area, wherein the first text display area displays multiple historical texts, and the first text storage area displays at least one blank text storage box; a first response module, configured to, in response to N selection operations of N different groups of candidate historical texts in the first text display area, and a drag operation of dragging each selected group of candidate historical texts into one of the blank text storage boxes in the first text storage area, respectively store the N groups of candidate historical texts in N candidate text storage boxes, each group of candidate historical texts including at least one section of candidate historical text, where N is a positive integer; A second display module is used to display a second novel generation page, the second novel generation page includes a second text display area and a second text storage area, the second text display area displays multiple current texts, and the second text storage area displays the N candidate text storage boxes; a second response module, configured to move the target group historical text to a target position in response to a selection operation on a target text storage box in the second text storage area and a drag operation on the target group historical text in the target text storage box to a target position in the second text display area; The third display module is used to generate and display novels containing the target group of historical texts in the second text display area.

9. An electronic device, characterized in that: It comprises a memory and a processor; the memory stores an application, and the processor is used to run the application in the memory to execute the steps in the novel generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which is executed by a processor to implement the steps in the novel generation method according to any one of claims 1 to 7.

Images