A text content processing method, device, equipment and storage medium

Abstract

The present application discloses a text content processing method, apparatus, device and storage medium, which relates to the field of artificial intelligence technology, specifically the field of natural language processing and computer vision technology, and further to the fields of content recognition and semantic analysis. The specific implementation scheme is: in response to the user's text processing request, the original text content in the content to be processed is matched with the pictures in the preset picture library; based on the matching result, the target picture and / or universal symbol is filled into the original text content to obtain the target text content; and the content to be processed including the target text content is displayed to the user. It solves the problem that the current input tool cannot automatically optimize the structure of the text content input by the user, and provides a solution for structural processing of text content, which can make the content input by the user more beautiful without manual editing by the user, thereby improving the information reach rate.

Description

Technical Field

[0001] The present application relates to the field of computer technology, in particular to artificial intelligence, natural language processing and computer vision technology, and specifically to a text content processing method, device, equipment and storage medium. Background Art

[0002] With the rise of content sharing products (such as Moments, Xiaoshu, etc.), the development of input tools (such as input methods, text editors, etc.) is being promoted. However, the current input tools only display the text content entered by the user, and do not automatically optimize the structure of the text content, thus failing to meet the user's needs for sharing beautiful content. Summary of the invention

[0003] The present disclosure provides a text content processing method, apparatus, device and storage medium to achieve structured processing of text content.

[0004] According to one aspect of the present disclosure, a text content processing method is provided, the method comprising:

[0005] In response to a user's text processing request, matching the original text content in the content to be processed with the pictures in the preset picture library;

[0006] Filling the target image and / or universal symbol into the original text content according to the matching result to obtain the target text content;

[0007] The content to be processed including the target text content is displayed to the user.

[0008] According to another aspect of the present disclosure, a text content processing device is provided, the device comprising:

[0009] A matching module, for matching the original text content in the content to be processed with the pictures in the preset picture library in response to the text processing request of the user;

[0010] A filling module, used to fill the target image and / or universal symbol into the original text content according to the matching result to obtain the target text content;

[0011] The display module is used to display the to-be-processed content including the target text content to the user.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the text content method described in any embodiment of the present application.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the text content processing method described in any embodiment of the present application.

[0017] The technology according to the present application solves the problem that current input tools cannot automatically optimize the structure of text content input by users, and provides a solution for structural processing of text content, which can make the content input by users more beautiful without the need for manual editing by users, thereby improving the information reach.

[0018] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0020] Figure 1 is a flowchart of a text content processing method provided according to an embodiment of the present application;

[0021] Figure 2A is a flowchart of a text content processing method provided according to an embodiment of the present application;

[0022] Figure 2B-2E is a schematic diagram of content to be processed provided according to an embodiment of the present application;

[0023] Figure 3 is a flowchart of a text content processing method provided according to an embodiment of the present application;

[0024] Figure 4 is a structural schematic diagram of a text content processing device provided according to an embodiment of the present application;

[0025] Figure 5 It is a block diagram of an electronic device used to implement the text content processing method of an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill 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 present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0027] Figure 1 It is a flowchart of a text content processing method provided according to an embodiment of the present application. The embodiment of the present application is applicable to the situation of how to perform structured processing on text content to make the content input by the user more beautiful. This embodiment can be executed by a text content processing device, which can be implemented by software and / or hardware, and can be integrated into an electronic device that carries the text content processing function. Optionally, the electronic device can be a client device such as an application or input method configured with a text editing function, or a server; further, the application with a text editing function can be a separate text editing application, or it can be an application embedded with a text editing function (such as Xiaohongshu, WeChat or Weibo, etc.). Figure 1 As shown, the method includes:

[0028] S101, in response to a text processing request from a user, matching original text content in the content to be processed with pictures in a preset picture library.

[0029] In this embodiment, the text processing request may be triggered by receiving a certain trigger mechanism or monitoring a certain state, etc., and is used to beautify the original text content in the content to be processed input by the user to present structured and beautiful text content. Optionally, the text processing request may be triggered by monitoring that the current time meets the set time threshold. For example, after the user inputs the content to be processed, if no operation is detected within a preset time period (such as within 15 seconds), the text processing request can be automatically triggered. Optionally, a one-key beautification function key can also be configured in this embodiment, and then the text processing request can be triggered by clicking the function key after the user enters the content to be processed or during the user input of the content to be processed.

[0030] The content to be processed may be manually input by the user in real time, or may be copied and pasted by the user from other places, etc. Optionally, the content to be processed includes at least the original text content, and may also include a scene graph and scene music, etc. The further scene graph may be static or dynamic. It should be noted that the original text content may be a description of the scene graph, or may be text content that is completely unrelated to the scene graph, etc., which is not limited in this embodiment.

[0031] For example, if a user wants to share information in a circle of friends, he can enter the content to be processed in the text editing box and click the one-key beautification function to trigger a text processing request. Then, in response to the user's text processing request, this embodiment recognizes the original text content in the content to be processed (which can further be content recognition and semantic analysis), and matches it from the preset picture library according to the recognition result. In this embodiment, the recognition result can be the original text content itself (for example, the original text content is text content edited in English, and the recognition result can be translated from English into semantically fluent Chinese), or it can be a summary of the original text content, or it can be keywords in the original text content. The preset picture library is a comprehensive picture library with rich pictures, such as fighting pictures, emoticon packs (including emoticon packs provided by various applications such as WeChat), video pictures, music pictures, ordinary graphics (such as balloons) and other pictures.

[0032] Optionally, in order to facilitate fast matching, in this embodiment, the images in the preset image library can be classified, and different label categories can be set for different categories, for example, labels such as joy, anger, sadness, happiness, atmosphere, food, environment, and electrical appliances can be set. Furthermore, the original text content in the content to be processed can be identified (which can further be content identification and semantic analysis), and the label category can be determined according to the identification result, and then matching can be performed under the determined label category in the preset image library.

[0033] S102, filling the target image and / or universal symbol into the original text content according to the matching result to obtain the target text content.

[0034] In this embodiment, the target text content is the text content after the target image and the / general symbol are filled in the original text content. The matching result can be any of the following: 1) no relevant image is matched; 2) the image is matched. Optionally, different matching results may result in different ways of filling the original text content.

[0035] Optionally, if the matching result is that no relevant pictures are matched, a universal symbol can be used to fill in the picture. Among them, the universal symbol can actually be a universal fallback strategy, specifically a way of structurally processing the original text content when no relevant pictures are matched. Optionally, universal symbols can include paragraph symbols and universal artistic characters, etc., and paragraph symbols include but are not limited to circles, ticks, diamonds, squares, musical notes, and digital numbers, etc.; further, paragraph symbols can be single-style or multi-level progressive styles, such as paragraph symbols with digital numbers, the first level can be 2, the second level can be 2.1, etc. In this embodiment, paragraph symbols are introduced for structural processing, which provides an optional way for structural processing of text content.

[0036] Specifically, when the matching result is that no relevant image is matched, a universal symbol can be selected, and the size of the universal symbol can be determined according to the font size in the original text content; the color of the universal symbol can be determined according to the font color in the original text content; and the universal symbol is filled into the original text content according to the size and color of the universal symbol to obtain the target text content. Further, in this embodiment, selecting a universal symbol can be: randomly selecting a universal symbol, or selecting one or more universal symbols according to the number of historical universal symbol filling times, etc.

[0037] If the matching result is a matched image, and the number of images is one, the matched image can be used as the target image and filled into the original text content; or the target image and universal symbols can be filled into the original text content. For example, the target image can be filled into the corresponding position in the original text content, and universal symbols can be added before each sentence or paragraph.

[0038] If the matching result is that a picture is matched, and there are multiple pictures (i.e., two or more), the target picture can be determined from the multiple pictures according to the number of historical picture filling times, and then the target picture can be filled into the original text content. For any picture, the number of historical picture filling times can be the number of times the picture has been filled into the original text content in history.

[0039] Specifically, the matched pictures can be sorted in descending order according to the number of filling times of historical pictures, and the picture ranked first can be used as the target picture, and the target picture can be filled into the original text content to obtain the target text content; or the pictures ranked in the first n (such as 3) can be used as the target pictures, and for each target picture, the original text content is filled once to obtain multiple target text contents. In this embodiment, the number of filling times of historical pictures is introduced to determine the target picture, which increases the flexibility of the solution and makes the input tool more intelligent.

[0040] S103, displaying the content to be processed including the target text content to the user.

[0041] Specifically, after obtaining the target text content, the content to be processed including the target text content can be displayed to the user. Further, in the case of multiple target text contents, each content to be processed including the target text can be displayed to the user in a dynamic playback mode for the user to select.

[0042] Optionally, after displaying the content to be processed including the target text content to the user, it may also include: if an upload instruction is received, the content to be processed including the target text content may be uploaded, such as shared to a circle of friends. It should be noted that by presenting the text content in a structured form, the shared content can be made more attractive, thereby making the information reach a wider range.

[0043] The technical solution of the embodiment of the present application introduces pictures and universal symbols, combines the original text content in the content to be processed with the matching results of the pictures in the preset picture library, and fills the original text content to achieve text content structuring. It solves the problem that the current input tool cannot automatically optimize the structure of the text content entered by the user, and provides a solution for structuring the text content, which can make the content entered by the user more beautiful without manual editing by the user, thereby improving the information reach rate.

[0044] Figure 2A 1 is a flowchart of a text content processing method provided according to an embodiment of the present application. Based on the above embodiment, this embodiment provides an optional method for filling the original text content with a target image and / or a universal symbol. Figure 2A As shown, the method includes:

[0045] S201, in response to a text processing request from a user, matching original text content in the content to be processed with pictures in a preset picture library.

[0046] S202: Fill the original text content with target images and / or universal symbols according to the matching results and the filling positions.

[0047] In this embodiment, the filling position refers to the position of the original text content where the picture or universal symbol is filled. Optionally, the position before a paragraph or before a sentence of the original text content can be used as the filling position of the universal symbol; at least one of the position before a paragraph, in the middle of a paragraph, and at the end of a paragraph of the original text content, or at least one of the position before a sentence, in the middle of a sentence, and at the end of a sentence of the original text content can be used as the filling position of the picture.

[0048] Specifically, if the matching result is that no image is matched, a symbol can be selected from the universal symbols to fill in the beginning of the paragraph or sentence of the original text content. Figure 2B As shown, the original text content in the content to be processed ( Figure 2B In a), the image in the preset image library is matched. If the matching result is that no image is matched, a symbol (such as a circle) can be selected from the common symbols to fill in the beginning of the paragraph of the original text content, such as Figure 2C shown.

[0049] Optionally, if the matching result is that each sentence or paragraph in the original text content matches a relevant image, or more than half of the sentences or paragraphs in the original text content match a relevant image, the matched relevant image can be used as the target image, and the target image is filled into the original text content according to the filling result. For example, the content to be processed entered by the user is Figure 2DAs shown in the figure, by recognizing the original text content in the content to be processed, it can be recognized that "Bakery is bread" and "Vatertag is Father's Day". Combined with the recognition results, matching pictures can be obtained from the preset picture library. For example, the bread graphic can be obtained as the target picture by using the agreed expression; at the same time, the relevant pictures can be obtained from the atmosphere tag of the preset picture library in combination with the atmosphere of Father's Day as the target picture, such as balloons, fireworks, applause or wine glasses as the target pictures. Afterwards, the target picture can be filled into the original text content according to the filling results, such as Figure 2E shown.

[0050] Furthermore, if the matching result is a matched picture, and the number of pictures is one, and the original text content includes multiple sentences or paragraphs, the matched picture can be used as the target picture, and the target picture and universal symbols can be filled into the original text content at the same time according to the filling position.

[0051] It should be noted that the filling position is introduced in this embodiment to make the text content more structured and more beautiful, while increasing readability; furthermore, different filling methods may have different filling positions, further increasing the flexibility of the solution.

[0052] S203: Displaying the content to be processed including the target text content to the user.

[0053] For example, Figure 2C and 2E The content to be processed is finally displayed to the user.

[0054] The technical solution of the embodiment of the present application introduces pictures and universal symbols, combines the original text content in the content to be processed with the matching results and filling positions of the pictures in the preset picture library, and fills the original text content, so that the text content is more structured and more beautiful, thereby making the information reach wider, while increasing readability, and providing a new idea for realizing the structuring of text content.

[0055] Figure 3 1 is a flowchart of a text content processing method provided according to an embodiment of the present application. This embodiment adds a processing operation for the text content on the basis of the above embodiment. Figure 3 As shown, the method includes:

[0056] S301, in response to a text processing request from a user, determining a content relationship of original text content in content to be processed.

[0057] In this embodiment, the content relationship is used to represent the relationship between paragraphs or sentences in the original text content. For example, the content relationship may be a parallel relationship.

[0058] Optionally, the content relationship of the original text content can be determined by performing content recognition and context semantic analysis on the original text content and combining specific symbols in the original text content. A pre-trained relationship recognition model can also be used to determine the content relationship of the original text content. The specific symbols may include but are not limited to commas, semicolons, and periods.

[0059] S302: segment and / or sentence the original text content according to the content relationship of the original text content.

[0060] Specifically, the original text content may be segmented and / or sentence-wise processed according to the content relationship of the original text content and / or specific symbols in the original text content. Figure 2B Take this as an example. If the original text content entered by the user ( Figure 2B a) In a line, the content relationship of the original text content is determined to be a parallel relationship through context semantic analysis, and the original text content is segmented and processed as follows: Figure 2B Middle a.

[0061] It should be noted that, before the original text content is structured, the present embodiment divides the original text content into segments and / or sentences, thus laying a foundation for the structured presentation of the text content.

[0062] Optionally, while or after the original text content is segmented and / or sentence-processed, the font in the original text content can be adjusted. For example, the content to be processed is copied and pasted by the user from other places, and the fonts and font sizes in the original text content are inconsistent. In order to make the text content more beautiful, the target font and target font size can be determined according to the font proportion in the original text content; according to the target font and target font size, the font in the original text content is adjusted. Among them, for a certain font, the font proportion of the font is the proportion relationship between the number of words using this font in the original text content and the total number of words in the original text content; similarly, for a certain font size, the font proportion of the font size is the proportion relationship between the number of words using this font size in the original text content and the total number of words in the original text content. For example, if the proportion of the font using Songti in the original text is greater than the proportion of the font using Kaiti, Songti can be used as the target font; the proportion of the font using size 4 in the original text is greater than the proportion of the font using size 4, then the target font size is size 4. In this embodiment, the font in the text content is adjusted to make the input tool more intelligent.

[0063] S303, matching the processed original text content with the pictures in the preset picture library.

[0064] S304: Fill the target image and / or universal symbol into the processed original text content according to the matching result to obtain the target text content.

[0065] Optionally, if the matching result is a matched picture, and the number of matched pictures is less than the number of sentences or paragraphs included in the original text content, the matched picture can be used as the target picture and the target picture can be filled into the original text content, or the target picture and universal symbols can be filled into the original text content at the same time.

[0066] If the matching result is that multiple pictures are matched, the original text content has only one sentence, and the multiple pictures have the same meaning, the matched pictures can be sorted in descending order according to the number of historical picture fillings, and the picture ranked first can be used as the target picture, and the target picture can be filled into the original text content to obtain the target text content; or the pictures ranked in the first n (such as 3) can be used as target pictures, and for each target picture, the original text content is filled once to obtain multiple target text contents.

[0067] If the matching result is that multiple images are matched, the original text content includes multiple sentences or paragraphs, and each sentence has a matching image, then the matched image can be directly used as the target image and filled into the corresponding position in the original text content.

[0068] If the matching result is that multiple pictures are matched, the original text content includes multiple sentences or paragraphs, and each sentence has multiple matching pictures. At this time, the process of filling pictures into any sentence of the original text content is similar to the above-mentioned case where the original text content has only one sentence and multiple pictures have the same meaning, and will not be repeated here.

[0069] S305: Display the content to be processed including the target text content to the user.

[0070] The technical solution of the embodiment of the present application segments and / or sentences the original text content, laying a foundation for the structured presentation of the text content; then, by introducing pictures and universal symbols, combined with the matching results of the original text content in the content to be processed and the pictures in the preset picture library, the original text content is filled in, making the text content more structured and more beautiful, thereby making the information reach wider, while increasing readability, providing a new idea for realizing the structuring of text content.

[0071] Figure 4400 is a structural diagram of a text content processing device provided according to an embodiment of the present application. The embodiment of the present application is applicable to the situation of how to perform structured processing on text content to make the content input by the user more beautiful. The device can implement the text content processing method described in any embodiment of the present application. The device can be integrated in an electronic device that carries the text content processing function. The text content processing device 400 specifically includes:

[0072] The matching module 401 is used to match the original text content in the content to be processed with the pictures in the preset picture library in response to the text processing request of the user;

[0073] A filling module 402 is used to fill the original text content with the target image and / or universal symbol according to the matching result to obtain the target text content;

[0074] The display module 403 is used to display the to-be-processed content including the target text content to the user.

[0075] The technical solution of the embodiment of the present application introduces pictures and universal symbols, combines the original text content in the content to be processed with the matching results of the pictures in the preset picture library, and fills the original text content to achieve text content structuring. It solves the problem that the current input tool cannot automatically optimize the structure of the text content entered by the user, and provides a solution for structuring the text content, which can make the content entered by the user more beautiful without manual editing by the user, thereby improving the information reach rate.

[0076] Exemplarily, the universal symbol in this embodiment includes a paragraph symbol.

[0077] Exemplarily, the filling module 402 may be specifically used for:

[0078] Fill the original text content with target images and / or universal symbols based on the matching results and the filling positions.

[0079] Exemplarily, the filling module 402 may also be used for:

[0080] Determine the target image based on the matching results and the number of historical image filling times;

[0081] Fill the original text content with the target image.

[0082] Exemplarily, the above device may further include:

[0083] A relationship determination module, used to determine the content relationship of the original text content;

[0084] The content processing module is used to segment and / or sentence the original text content according to the content relationship in the original text content.

[0085] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0086] like Figure 5 , is a block diagram of an electronic device according to a text content processing method according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0087] like Figure 5 As shown, the electronic device includes: one or more processors 501, a memory 502, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 501 is taken as an example.

[0088] The memory 502 is a non-transient computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the text content processing method provided in the present application. The non-transient computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the text content processing method provided in the present application.

[0089] The memory 502 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the text content processing method in the embodiment of the present application (for example, the attached Figure 4The processor 501 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 502, that is, the text content processing method in the above method embodiment is implemented.

[0090] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device of the text content processing method, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 502 may optionally include a memory remotely arranged relative to the processor 501, and these remote memories may be connected to the electronic device of the text content processing method via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0091] The electronic device of the text content processing method may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0092] The input device 503 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device of the text content processing method, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 504 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0093] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0097] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0098] According to the technical solution of the embodiment of the present application, by introducing pictures and universal symbols, and combining the matching results of the original text content in the content to be processed with the pictures in the preset picture library, the original text content is filled in, thereby realizing the structuring of the text content. This solves the problem that the current input tool cannot automatically optimize the structure of the text content entered by the user, and provides a solution for structuring the text content, which can make the content entered by the user more beautiful without manual editing by the user, thereby improving the information reach rate.

[0099] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0100] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A text content processing method, comprising: In response to a user's text processing request, the content relationship of the original text content is determined by performing content recognition and context semantic analysis on the original text content in the content to be processed, combined with specific symbols in the original text content; or a pre-trained relationship recognition model is used to determine the content relationship of the original text content; wherein the specific symbols include a colon, a comma, a semicolon, and a period; and the content relationship is used to characterize the relationship between sentences in the original text content; According to the content relationship of the original text content, the original text content is processed into sentences and segments, and the font in the original text content is adjusted; Matching the original text content in the content to be processed with the pictures in the preset picture library; Filling the target image into the original text content according to the matching result and the filling position to obtain the target text content and realize text content structuring; Displaying the to-be-processed content including the target text content to the user; wherein, in the case where there are multiple target text contents, displaying each to-be-processed content including the target text to the user in a dynamic playback manner for the user to select; Among them, the filling position refers to the position in the original text content where the target image is filled; the front and / or middle of the sentence of the original text content, and the front and middle of the paragraph of the original text content are used as the filling position of the target image.

2. The method according to claim 1, wherein: After matching the original text content in the content to be processed with the pictures in the preset picture library, it also includes: If the matching result is that no relevant image is matched, then fill the original text content with a universal symbol; the filling position also includes the position where the universal symbol is filled in the original text content; the position before the paragraph or before the sentence of the original text content is used as the filling position of the universal symbol; Wherein, the universal symbol includes a paragraph symbol.

3. The method according to claim 1, wherein: Filling the target image into the original text content according to the matching result includes: If the matching result is that at least two images are matched, the target image is determined from the at least two images according to the number of historical image filling times; Fill the original text content with the target image.

4. A text content processing device, comprising: A matching module, for matching the original text content in the content to be processed with the pictures in the preset picture library in response to the text processing request of the user; A filling module is used to fill the target image into the original text content according to the matching result and the filling position to obtain the target text content and realize the structuring of the text content; A display module, used to display the to-be-processed content including the target text content to the user; wherein, when there are multiple target text contents, each to-be-processed content including the target text is displayed to the user in a dynamic playback manner for the user to select; The filling position refers to the position in the original text content where the target image is filled; the front and / or middle of the sentence in the original text content, and the front and middle of the paragraph in the original text content are used as the filling position of the target image; A relationship determination module, used to determine the content relationship of the original text content; A content processing module, used for performing sentence processing and segment processing on the original text content according to the content relationship in the original text content; The content relationship is used to represent the relationship between sentences in the original text content; The relationship determination module is specifically used to: determine the content relationship of the original text content by performing content recognition and context semantic analysis on the original text content, combined with specific symbols in the original text content; or use a pre-trained relationship recognition model to determine the content relationship of the original text content; wherein the specific symbols include commas, semicolons and periods; The font adjustment module is used to adjust the font in the original text content.

5. The device according to claim 4, wherein: After matching the original text content in the content to be processed with the pictures in the preset picture library, if the matching result is that no relevant pictures are matched, the filling module is further used to: Filling the original text content with universal symbols; the filling position also includes the position where the universal symbol is filled in the original text content; the position before the paragraph or before the sentence of the original text content is used as the filling position of the universal symbol; Wherein, the universal symbol includes a paragraph symbol.

6. The device according to claim 4, wherein: The filling module is specifically used for: Determine the target image based on the matching results and the number of historical image filling times; Fill the original text content with the target image.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the text content processing method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the text content processing method according to any one of claims 1 to 3.

Images