Word processing method, device and equipment and readable storage medium
Through deep learning algorithms, the text content is split and refined, and combined with user editing, the problem that the generation results of existing models in large paragraph text generation are not consistent with user intentions, and more accurate picture or video generation is achieved.
Patent Information
- Application Number
- CN202411196674.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-24
AI Technical Summary
There is a deviation between the generated results and the user's desired results when an existing model generates pictures or videos based on large paragraph text.
The original text content is split and processed through deep learning algorithms, words and sentences are obtained, and refine them according to the part of speech and description scenes. Combined with the user's editing operations, the target text content is generated to reduce the deviation of the generated results.
Effectively reduce the deviation between the generated pictures or videos and the pictures or videos that the user wants to generate, improve the accuracy of the generated results and the degree to which the user intends.
Smart Images
Figure CN119180284A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to a word processing method, apparatus, device and readable storage medium. Background Art
[0002] The existing process of generating text-generated images or text-generated videos is as follows: the user inputs a text description of the content to be generated, and the model generates the corresponding image or video based on the content input by the user. In some scenarios, it is necessary to generate images or videos based on an entire book, an entire article, or a large paragraph of text. However, when the existing model generates images or videos based on a large paragraph of text, there is a certain deviation between the generated images or videos and the images or videos that the user wants to generate. Summary of the invention
[0003] The embodiments of the present application provide a text processing method, device and readable storage medium to solve the problem of how to reduce the deviation between the generated pictures or videos and the pictures or videos that the user wants to generate when the existing model generates pictures or videos based on large paragraphs of text.
[0004] In a first aspect, an embodiment of the present application provides a text processing method, comprising:
[0005] Using a deep learning algorithm to split the original text content to obtain at least two split objects, wherein the split objects include words and / or phrases;
[0006] According to the part of speech and / or description scene of the split object, extracting content of the original text content is obtained and the extracting content is displayed, wherein the extracting content includes at least one pre-selected split object, and the pre-selected split object includes words corresponding to preset parts of speech and / or words and sentences corresponding to preset description scenes in the at least two split objects;
[0007] According to the user's first operation on the pre-selected split object in the refined content, the target text content is obtained, the target text content is the text content used to generate a picture or a video, and the first operation is an operation of editing the pre-selected split object.
[0008] Optionally, displaying the refined content includes:
[0009] Determining the positional relationship between each pre-selected split object in the refined content according to the position information of the split object in the original text content;
[0010] According to the positional relationship, the pre-selected split objects in the refined content are displayed.
[0011] Optionally, the method of the embodiment of the present application further includes:
[0012] In a target interface displaying the refined content, displaying at least one candidate split object, wherein the candidate split object is a split object other than the pre-selected split object among the at least two split objects;
[0013] The first operation includes: an operation of adding a target candidate split object selected from the candidate split objects to the refined content.
[0014] Optionally, the method of the embodiment of the present application further includes:
[0015] Determine the target position of the target candidate split object in the refined content according to the position information of the target candidate split object in the original text content or according to the second operation of the user on the target candidate split object, wherein the second operation is an operation of moving the target candidate split object to the target position in the refined content;
[0016] Arrange the target candidate split objects at target positions in the refined content.
[0017] Optionally, obtaining target text content according to a first operation of the user on the displayed pre-selected split object includes:
[0018] Obtaining updated refined content according to a first operation of the user on at least one displayed pre-selected split object;
[0019] receiving a first input from a user regarding a target pre-selected split object in the updated refined content;
[0020] In response to the first input, at least two preset association description information corresponding to the target pre-selected split object are displayed, where the preset association description information is used to describe the preset attributes of the target pre-selected split object, and different preset association description information corresponds to different preset attributes;
[0021] The target text content is obtained according to the preset associated description information selected by the user and the updated refined content.
[0022] In a second aspect, a word processing device is provided, comprising:
[0023] A first acquisition module is used to split the original text content using a deep learning algorithm to obtain at least two split objects, wherein the split objects include words and / or phrases;
[0024] A processing module, configured to obtain and display refined content of the original text content according to the part of speech and / or description scene of the split object, wherein the refined content includes at least one pre-selected split object, and the pre-selected split object includes words corresponding to preset parts of speech and / or words and sentences corresponding to preset description scenes in the at least two split objects;
[0025] The second acquisition module is used to obtain target text content according to the user's first operation on the pre-selected split object in the refined content, wherein the target text content is the text content used to generate a picture or video, and the first operation is the operation of editing the pre-selected split object.
[0026] Optionally, the processing module includes:
[0027] A determination submodule, used to determine the positional relationship between each pre-selected split object in the refined content according to the position information of the split object in the original text content;
[0028] The display submodule is used to display the pre-selected split objects in the refined content according to the position relationship.
[0029] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the word processing method as described above when executed by the processor.
[0030] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the word processing method as described above are implemented.
[0031] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the text processing method as described above.
[0032] In the embodiment of the present application, the target text content for generating the image or video is obtained according to the user's editing operation on the pre-selected split object in the refined content. It can be seen that in the above scheme, the original text content is refined based on the split object of the original text content, and then the target text content is obtained in combination with the user's editing of the refined content, so that the deviation between the image or video generated based on the target text content and the image or video that the user wants to generate can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0034] Figure 1A schematic diagram showing a flow chart of a text processing method provided in an embodiment of the present application;
[0035] Figure 2 One of the schematic diagrams showing the splitting process of the original text content in the embodiment of the present application;
[0036] Figure 3 The second schematic diagram showing the splitting process of the original text content in the embodiment of the present application;
[0037] Figure 4 One of the display schematic diagrams showing the pre-selected page and the candidate page in the embodiment of the present application;
[0038] Figure 5 A second schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0039] Figure 6 A third schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0040] Figure 7 A fourth schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0041] Figure 8 A fifth schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0042] Fig. 9 A sixth schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0043] Fig.10 A seventh schematic diagram showing the display of a pre-selected page and a candidate page in an embodiment of the present application;
[0044] Fig.11 A schematic diagram showing a module of a word processing device provided in an embodiment of the present application;
[0045] Fig.12 A schematic diagram showing the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to make the technical problems, technical solutions and advantages to be solved by the application clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the application. In addition, for clarity and brevity, the description of known functions and structures has been omitted.
[0047] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0048] In various embodiments of the present application, it should be understood that the order of execution of the following processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, the terms "system" and "network" are often used interchangeably in this article.
[0049] like Figure 1 As shown, an embodiment of the present application provides a text processing method, comprising the following steps:
[0050] Step 101: Use a deep learning algorithm to split the original text content to obtain split objects, which include words and / or phrases.
[0051] Optionally, the phrase includes at least two words.
[0052] The original text content is the text content that needs to be generated into a picture or video and is input by the user. For example, the original text content is the content selected by the user from an e-book.
[0053] As an implementation method, in the embodiment of the present application, the original text content can be split and processed by a Chinese word segmentation tool, for example, the original text content can be split and processed by the jieba word segmentation.
[0054] For example, the original text above is as follows: "Several huge mammoths approached on the snow, their long hair blowing gently in the wind, in the distance were snow-capped trees and striking snow-capped mountains, the afternoon light formed a warm glow with sparse clouds and the sun in the distance, the low camera's field of view was amazing, capturing this huge hairy mammal with beautiful photography and depth of field". After word segmentation processing by the jieba word segmentation tool, the split results shown in Table 1 are obtained:
[0055] Table 1
[0056]
[0057]
[0058] The description of the labels is shown in Table 2:
[0059] Table 2
[0060]
[0061] As a way to achieve this, Figure 2 As shown, the embodiment of the present application can also perform word segmentation through the large model technology, such as asking questions to the large model through prompt words to obtain the word segmentation results.
[0062] In the present application embodiment, Figure 3 As shown, the original text content can be split into words and sentences through NLP or large model technology to obtain description scenes. The words and sentences can also be described as phrases, and the description scenes can also be described as usage scenes. The description scenes can include weather scenes, character scenes, role scenes, environment scenes, atmosphere scenes, action scenes, etc.
[0063] Step 102: According to the part of speech and / or description scene of the split object, the refined content of the original text content is obtained and the refined content is displayed.
[0064] Optionally, the split objects in the refined content include words corresponding to preset parts of speech and / or words and sentences corresponding to preset description scenes. The split objects in the above-mentioned refined content can also be described as pre-selected split objects.
[0065] The part of speech here is the above-mentioned label, which is used to indicate the category of the word. The above-mentioned description scenario refers to the usage scenario of the word.
[0066] For example, if the above default part of speech is: noun, then Figure 4 As shown, refined content is displayed in the upper part of the interface, and the refined content may include: mammoth, snow, long hair, trees, and snow-capped mountains.
[0067] For example, the above preset description scenes include role scenes, action scenes and environment scenes. Figure 5 As shown, the upper part of the interface displays refined content, which may include: several huge mammoths, approaching on the snow, blowing gently in the wind, snow-capped trees, and eye-catching snow-capped mountains. Among them, several huge mammoths correspond to the character scene, approaching on the snow and blowing gently in the wind correspond to the action scene, and snow-capped trees and eye-catching snow-capped mountains correspond to the environment scene.
[0068] It should be noted that the above-mentioned preset parts of speech and preset description scenarios can be set according to user needs.
[0069] Step 103: According to the user's first operation on the refined content, target text content is obtained, where the target text content is text content used to generate a picture or video, and the first operation is an operation of editing the refined content.
[0070] Optionally, the first operation is an operation of editing the split object in the refined content, for example, the first operation includes an operation of deleting the split object or an operation of adding the split object.
[0071] In the embodiment of the present application, the original text content is split by using a deep learning algorithm to obtain split objects, wherein the split objects include words and / or phrases; according to the part of speech and / or usage scenario of the split objects, the refined content of the original text content is obtained and displayed;
[0072] According to the user's editing operation on the pre-selected split objects in the refined content, the target text content for generating the image or video is obtained. It can be seen that in the above scheme, the original text content is refined based on the split objects of the original text content, and then the target text content is obtained in combination with the user's editing of the refined content, thereby effectively reducing the deviation between the image or video generated based on the target text content and the user's intention.
[0073] Optionally, displaying the refined content includes:
[0074] Determining the positional relationship between each split object in the refined content according to the position information of the split object in the original text content;
[0075] The split objects in the refined content are displayed according to the positional relationship.
[0076] In the embodiment of the present application, each split object corresponds to a data structure, which includes an identifier of the split object; the part of speech or usage scenario of the split object; and location information of the split object.
[0077] Optionally, the position information includes a starting position and length information in the original text content.
[0078] In an embodiment of the present application, after the original text content is split to obtain split objects, the position information of the split objects in the original text content is determined so as to sort the split objects in the refined content based on the position information.
[0079] Optionally, the method of the embodiment of the present application further includes:
[0080] In a target interface displaying the refined content, displaying at least one candidate split object, wherein the candidate split object is a split object other than the split object in the refined content among the at least two split objects;
[0081] The first operation includes: an operation of adding a target candidate split object selected from the candidate split objects to the refined content.
[0082] In the embodiment of the present application, the above-mentioned first operation also includes a deletion operation on the split objects in the refined content.
[0083] like Figure 4 and Figure 5 As shown, the first display area of the target interface displays the refined content, and the second display area of the target interface displays at least one candidate split object. The first display area can be described as a pre-selected page, and the second display area can also be described as a candidate page. The candidate page is for the user to input the original text content. The user can add, delete, and adjust the order of the refined text in the pre-selected page based on the text in the candidate page to complete the refinement and adjustment of the text content.
[0084] Optionally, the candidate interface may be an e-book reading interface, thereby facilitating the user to add new original text content to the candidate interface.
[0085] Optionally, the target interface also displays the part of speech or description scenario of each split object. Figure 4 As shown in , the parts of speech displayed include names, verbs, adjectives, and quantifiers. Figure 5 As shown, the depicted scene shown includes characters, actions, and environments.
[0086] The candidate split object is used for the user to modify the refined content. Exemplarily, when the user clicks on the split object in the first display area, the first display area is highlighted, and optionally, the second display area is also highlighted. The user can perform editing operations on the split object in the first display area including: deleting the split object in the first display area; or adding the candidate split object in the second display area to the first display area.
[0087] For example, Figure 6 As shown, when the user clicks on a target candidate split object in the second display area, such as "huge", the target candidate split object automatically enters the above-mentioned first display area and is displayed at the corresponding position based on the positional relationship between the target candidate split object and each pre-selected split object in the first display area.
[0088] In addition, if Figure 7 and Figure 8 As shown, the second display area can display the candidate split objects by scrolling or paging.
[0089] By displaying the candidate split objects on the target display interface, it is convenient for users to edit and modify the refined content based on the candidate split objects, so that the pictures or videos generated based on the target text content can meet the needs of users.
[0090] Optionally, the method of the embodiment of the present application further includes:
[0091] Determine the target position of the target candidate split object in the refined content according to the position information of the target candidate split object in the original text content or according to the second operation of the user on the target candidate split object, wherein the second operation is an operation of moving the target candidate split object to the target position in the refined content;
[0092] Arrange the target candidate split objects at target positions in the refined content.
[0093] As an implementation method, after selecting the target candidate split object, the positional relationship between the target candidate split object and each pre-selected split object in the above-mentioned first display area is determined based on the position information in the data structure corresponding to the target candidate split object and the position information in the data structure of each pre-selected split object, and based on the positional relationship, the target position of the target candidate split object in the above-mentioned refined content is determined.
[0094] As another implementation, when the user moves the target candidate split object to the target position in the refined content through the above-mentioned second operation, the target position is directly determined as the position of the target candidate split object in the refined content. That is, the user can drag the target candidate split object into the refined content, and the position when the dragging operation stops is the target position of the target candidate split object in the refined content. Optionally, a dragging operation identifier can be set for the target candidate split object, so that the target candidate split object and other pre-selected split objects are not sorted based on the position information of the target candidate split object, that is, the position of the target candidate split object in the refined content is kept unchanged.
[0095] Through the above implementation method, the user can easily and quickly adjust the position of the split object in the refined content.
[0096] Optionally, obtaining target text content according to a first operation of the user on the refined content includes:
[0097] Obtaining updated refined content according to a first operation of the user on the split object in the refined content;
[0098] receiving a first input from a user regarding a target split object in the updated refined content;
[0099] In response to the first input, at least two preset association description information corresponding to the target split object are displayed, where the preset association description information is used to describe the preset attributes of the target split object, and different preset association description information corresponds to different preset attributes;
[0100] The target text content is obtained according to the preset associated description information selected by the user and the updated refined content.
[0101] Optionally, the first input may be a long press input or a click input to the target split object, or the first input may be an input to a target control of the target split object, such as a click input or a long press input to the target control.
[0102] For example, Fig. 9 As shown, the target split object is "several huge mammoths", the preset attribute is age, and the target split object corresponds to three preset associated description information, namely "young mammoth", "old mammoth" and "middle-aged mammoth". The user selects one preset associated description information from the preset associated description information. Fig.10 As shown, the target text content is obtained based on the preset associated description information selected by the user and the updated refined content.
[0103] The preset associated description information can be used to describe the split object in more detail, so that by combining the preset associated description information and the refined content, the target text content that better fits the user's intention can be obtained.
[0104] It should be noted that the above-mentioned preset associated description information may also be a model, etc., and the embodiments of the present application do not make any specific limitations on this.
[0105] In an embodiment of the present application, the original text content input by the user is split and processed to determine the part of speech or description scene of each split object after the split process, as well as the positional relationship of each split object. Based on the part of speech or description scene of each split object after the split process, a preliminary screening is performed to determine several key split objects as the refined content of the text input by the user. The user further completes the modification and text expansion based on the refined content. In addition, in the first display area, the words and sentences are classified and displayed according to the pre-set description scenes, such as classification from the aspects of role, action, and scene, so that the text display is more organized and convenient for users to view and modify.
[0106] The above scheme of the embodiment of the present application uses a deep learning algorithm to extract the core content in the original text content, obtains refined content, and displays it on a pre-selected page. The user can make a secondary selection of content on the pre-selected page, increase or decrease the content to be selected, and can combine multi-dimensional key information according to the part of speech of the text content or the description scene, such as the environment, characters, weather and other key content. Finally, based on the content after the secondary selection, the corresponding picture or video is generated. In this scheme, the original text content is intelligently refined and the refined content is modified to generate pictures or videos that meet the user's intentions.
[0107] like Fig.11 As shown, the embodiment of the present application also provides a word processing device, including:
[0108] The first acquisition module 1101 is used to split the original text content using a deep learning algorithm to obtain split objects, where the split objects include words and / or phrases;
[0109] Processing module 1102, for obtaining the refined content of the original text content and displaying the refined content according to the part of speech and / or description scene of the split object;
[0110] The second acquisition module 1103 is used to obtain target text content according to the user's first operation on the refined content, where the target text content is text content used to generate a picture or video, and the first operation is an operation of editing the refined content.
[0111] Optionally, the processing module includes:
[0112] A determination submodule, used to determine the positional relationship between each split object in the refined content according to the position information of the split object in the original text content;
[0113] The display submodule is used to display the split objects in the refined content according to the position relationship.
[0114] Optionally, the device of the embodiment of the present application further includes:
[0115] A display module, configured to display at least one candidate split object in a target interface displaying the refined content, wherein the candidate split object is a split object other than the split object in the refined content among the at least two split objects;
[0116] The first operation includes: an operation of adding a target candidate split object selected from the candidate split objects to the refined content.
[0117] Optionally, the device of the embodiment of the present application further includes:
[0118] a determination module, configured to determine a target position of the target candidate split object in the refined content according to position information of the target candidate split object in the original text content or according to a second operation of the user on the target candidate split object, wherein the second operation is an operation of moving the target candidate split object to a target position in the refined content;
[0119] An arrangement module is used to arrange the target candidate split objects at a target position in the refined content.
[0120] Optionally, the second acquisition module includes:
[0121] A first acquisition submodule, configured to obtain updated refined content according to a first operation of a user on a split object in the refined content;
[0122] A receiving submodule, configured to receive a first input from a user regarding a target split object in the updated refined content;
[0123] a response submodule, configured to display, in response to the first input, at least two preset association description information corresponding to the target split object, wherein the preset association description information is used to describe the preset attributes of the target split object, and different preset association description information corresponds to different preset attributes;
[0124] The second acquisition submodule is used to obtain the target text content according to the preset associated description information selected by the user and the updated refined content.
[0125] In the embodiment of the present application, the target text content for generating the image or video is obtained according to the user's editing operation on the pre-selected split object in the refined content. It can be seen that in the above scheme, the original text content is refined based on the split object of the original text content, and then the target text content is obtained in combination with the user's editing of the refined content, so that the deviation between the image or video generated based on the target text content and the image or video that the user wants to generate can be effectively reduced.
[0126] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects.
[0127] like Fig.12 As shown, an embodiment of the present application also provides an electronic device, including: a transceiver 1204, a processor 1201, a memory 1203, and a computer program stored in the memory 1203 and executable on the processor 1201, and the processor 1201 implements the steps of the above-mentioned text processing method when executing the computer program.
[0128] Specifically, the processor 1201 is used to use a deep learning algorithm to split the original text content to obtain split objects, which include words and / or sentences; according to the part of speech and / or description scene of the split object, the refined content of the original text content is obtained and the refined content is displayed; according to the user's first operation on the refined content, the target text content is obtained, and the target text content is text content used to generate a picture or video, and the first operation is an operation to edit the refined content.
[0129] Optionally, the processor 1201 is further configured to:
[0130] Determining the positional relationship between each split object in the refined content according to the position information of the split object in the original text content;
[0131] The split objects in the refined content are displayed according to the positional relationship.
[0132] Optionally, the processor 1201 is further configured to:
[0133] In a target interface displaying the refined content, displaying at least one candidate split object, wherein the candidate split object is a split object other than the split object in the refined content among the at least two split objects;
[0134] The first operation includes: an operation of adding a target candidate split object selected from the candidate split objects to the refined content.
[0135] Optionally, the processor 1201 is further configured to:
[0136] Determine the target position of the target candidate split object in the refined content according to the position information of the target candidate split object in the original text content or according to the second operation of the user on the target candidate split object, wherein the second operation is an operation of moving the target candidate split object to the target position in the refined content;
[0137] Arrange the target candidate split objects at target positions in the refined content.
[0138] Optionally, the processor 1201 is further configured to:
[0139] Obtaining updated refined content according to a first operation of the user on the split object in the refined content;
[0140] receiving a first input from a user regarding a target split object in the updated refined content;
[0141] In response to the first input, at least two preset association description information corresponding to the target split object are displayed, where the preset association description information is used to describe the preset attributes of the target split object, and different preset association description information corresponds to different preset attributes;
[0142] The target text content is obtained according to the preset associated description information selected by the user and the updated refined content.
[0143] It should be noted that in Fig.12In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1201 and various circuits of memory represented by memory 1203 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface 1202 provides an interface. The transceiver 1204 may be a plurality of components, namely, a transmitter and a transceiver, providing a unit for communicating with various other devices on a transmission medium. For different terminals, the user interface 1205 may also be an interface capable of externally connecting or internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc. The processor 1201 is responsible for managing the bus architecture and general processing, and the memory 1203 may store data used by the processor 1201 when performing operations.
[0144] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing relevant hardware through a computer program, wherein the computer program includes instructions for executing part or all of the steps of the above method; and the computer program may be stored in a readable storage medium, and the storage medium may be any form of storage medium.
[0145] In addition, the specific embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above-mentioned text processing method are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0146] The embodiment of the present application also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the various processes of the above-mentioned text processing method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, they are not repeated here.
[0147] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0149] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.
[0150] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications are also within the scope of protection of the present application.
Claims
1. A text processing method, characterized in that: include: Using a deep learning algorithm to split the original text content to obtain split objects, wherein the split objects include words and / or phrases; According to the part of speech and / or description scene of the split object, obtaining the refined content of the original text content and displaying the refined content; According to the user's first operation on the refined content, target text content is obtained, the target text content is text content used to generate a picture or a video, and the first operation is an operation of editing the refined content.
2. The method according to claim 1, characterized in that Display the extracted content, including: Determining the positional relationship between each split object in the refined content according to the position information of the split object in the original text content; The split objects in the refined content are displayed according to the positional relationship.
3. The method according to claim 1, characterized in that Also includes: In a target interface displaying the refined content, displaying at least one candidate split object, wherein the candidate split object is a split object other than the split object in the refined content among the at least two split objects; The first operation includes: an operation of adding a target candidate split object selected from the candidate split objects to the refined content.
4. The method according to claim 3, characterized in that Also includes: Determine the target position of the target candidate split object in the refined content according to the position information of the target candidate split object in the original text content or according to the second operation of the user on the target candidate split object, wherein the second operation is an operation of moving the target candidate split object to the target position in the refined content; Arrange the target candidate split objects at target positions in the refined content.
5. The method according to claim 1, characterized in that The step of obtaining target text content according to the first operation of the user on the refined content includes: Obtaining updated refined content according to a first operation of the user on the split object in the refined content; receiving a first input from a user regarding a target split object in the updated refined content; In response to the first input, at least two preset association description information corresponding to the target split object are displayed, where the preset association description information is used to describe the preset attributes of the target split object, and different preset association description information corresponds to different preset attributes; The target text content is obtained according to the preset associated description information selected by the user and the updated refined content.
6. A word processing device, characterized in that: include: A first acquisition module is used to split the original text content using a deep learning algorithm to obtain split objects, wherein the split objects include words and / or phrases; A processing module, configured to obtain the refined content of the original text content and display the refined content according to the part of speech and / or description scene of the split object; The second acquisition module is used to obtain target text content according to the user's first operation on the refined content, wherein the target text content is text content used to generate a picture or video, and the first operation is an operation of editing the refined content.
7. The device according to claim 6, characterized in that The processing module comprises: A determination submodule, used to determine the positional relationship between each split object in the refined content according to the position information of the split object in the original text content; The display submodule is used to display the split objects in the refined content according to the position relationship.
8. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the text processing method according to any one of claims 1 to 5.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the word processing method according to any one of claims 1 to 5 are implemented.
10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the text processing method according to any one of claims 1 to 5.