Content publishing methods, devices, electronic equipment, and storage media

Abstract

This disclosure proposes a method, apparatus, electronic device, and storage medium for publishing content. This disclosure relates to the field of computer technology, and particularly to artificial intelligence technologies such as large language models, deep learning, and natural language processing. The specific implementation scheme is as follows: Upon receiving a content publishing request, the target content to be published, the target summary associated with the target content, and the generation method of the target summary are determined; based on the generation method of the target summary, summary tags associated with the target summary are determined; and the target content, target summary, and summary tags are jointly published. Therefore, by jointly publishing the associated target summary and the summary tags determined according to the summary generation method during content publishing, users can not only quickly understand the content through the summary, but also correctly understand and evaluate the reliability of the summary based on its generation method, thus improving the efficiency and accuracy of users obtaining content.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of artificial intelligence technology such as large language models, deep learning, and natural language processing, specifically to a method, apparatus, electronic device, and storage medium for publishing content. Background Technology

[0002] In scenarios with long content, due to the large amount of content... ， This leads to inefficient reading for users. Therefore, it is extremely important to provide a summary of the full text so that readers can quickly make a judgment on the content and improve the efficiency of reading and information acquisition. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] To this end, this disclosure provides a method, apparatus, electronic device, and storage medium for publishing content.

[0005] According to a first aspect of this disclosure, a method for publishing content is provided, comprising:

[0006] Upon receiving a content publishing request, determine the target content to be published, the target summary associated with the target content, and the method for generating the target summary;

[0007] Based on the method of generating the target summary, determine the summary tags associated with the target summary;

[0008] The target content, the target summary, and the summary tags will be jointly published.

[0009] According to a second aspect of this disclosure, a content publishing device is provided, comprising:

[0010] The first determining module is used to determine, upon receiving a content publishing request, the target content to be published, the target summary associated with the target content, and the method for generating the target summary;

[0011] The second determining module is used to determine the summary tags associated with the target summary based on the generation method of the target summary;

[0012] The publishing module is used to jointly publish the target content, the target summary, and the summary tag.

[0013] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the content publishing method as described in the first aspect.

[0017] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing the computer to perform a method for publishing content as described in the first aspect.

[0018] According to a fifth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of a method for publishing content as described in the first aspect.

[0019] The methods, apparatus, electronic devices, and storage media for publishing the content disclosed herein have the following beneficial effects:

[0020] In this disclosure, upon receiving a content publishing request, the target content to be published, the target summary associated with the target content, and the generation method of the target summary are first determined. Then, based on the generation method of the target summary, the summary tags associated with the target summary are determined. Finally, the target content, target summary, and summary tags are jointly published. Thus, by jointly publishing the associated target summary and the summary tags determined according to the summary generation method during content publishing, users can not only quickly understand the content through the summary but also correctly understand and evaluate the reliability of the summary based on its generation method, improving the efficiency and accuracy of users obtaining content.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, which are provided for a better understanding of the present invention and are not intended to limit the scope of this disclosure, wherein:

[0023] Figure 1 This is a flowchart illustrating a method for publishing content according to an embodiment of this disclosure;

[0024] Figure 2 This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure;

[0025] Figure 3This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure;

[0026] Figure 4 This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure;

[0027] Figure 5 This is a schematic diagram of the structure of a content publishing device according to an embodiment of the present disclosure;

[0028] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0029] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0030] This disclosure relates to the fields of artificial intelligence technologies such as large language models, deep learning, and natural language processing.

[0031] Artificial Intelligence (AI) is a new technological science that studies and develops theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence.

[0032] Large Language Models (LLMs) are deep learning models trained on large amounts of text data that can generate natural language text or understand the meaning of language text. LLMs can handle various natural language tasks, such as text classification, question answering, and dialogue, and are an important pathway to artificial intelligence.

[0033] Deep learning learns the inherent patterns and hierarchical representations of sample data. The information gained during this learning process greatly aids in interpreting data such as text, images, and sound. The ultimate goal of deep learning is to enable machines to possess analytical and learning capabilities similar to humans, allowing them to recognize data such as text, images, and sound.

[0034] Natural Language Processing (NLP) is an important field within computer science and artificial intelligence. It studies the theories and methods that enable effective communication between humans and computers using natural language. NLP is a science that integrates linguistics, computer science, and mathematics.

[0035] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0036] The following description, with reference to the accompanying drawings, describes methods, apparatus, electronic devices, and storage media for publishing embodiments of this disclosure.

[0037] It should be noted that the content publishing method in this embodiment is executed by a content publishing device, which can be implemented in software and / or hardware. This device can be configured in an electronic device, which may include, but is not limited to, a terminal or a server. This embodiment uses the example of a content publishing device configured in a content publishing platform for illustration.

[0038] Figure 1 This is a flowchart illustrating a method for publishing content according to an embodiment of this disclosure.

[0039] like Figure 1 As shown, the methods for publishing this content include:

[0040] S101: Upon receiving a content publishing request, determine the target content to be published, the target summary associated with the target content, and the method for generating the target summary.

[0041] It should be noted that the target content to be published may contain only text, or it may contain both text and images; this disclosure does not impose any restrictions on this.

[0042] The method of generating the target summary refers to whether the target summary is obtained by the user through self-summarization of the target content, or it may be automatically generated, such as by using a large language model, etc. This disclosure does not limit it.

[0043] In this embodiment of the disclosure, after the user clicks the publish confirmation control in the content editing interface, the content publishing platform can receive the content publishing request sent by the user, and then obtain the main text content written by the user in the content editing interface as the target content to be published, as well as the target summary associated with the target content, the generation method of the target summary, etc.

[0044] Optionally, upon receiving a content publishing request, if the content publishing platform only obtains the main text content written by the user in the content editing interface, it can automatically generate a related target summary based on the main text content. Alternatively, it can return to the summary input interface to prompt the user to input a summary. Alternatively, the content publishing platform can only automatically generate a related target summary, or prompt the user to input a summary, if it determines that the number of characters in the target content to be published exceeds a threshold, etc. This disclosure does not limit this approach.

[0045] Optionally, after entering the target content to be published, the user can choose to click the summary generation control to intelligently generate a summary. Therefore, the content publishing platform can receive the summary automatic generation instruction, then use the large language model to generate the first summary of the target content, and then determine the first summary as the target summary and determine the generation method of the target summary as the first method.

[0046] The first method refers to automatic generation.

[0047] In this embodiment of the disclosure, the content publishing platform can input the target content into a large language model and automatically generate a summary associated with the target content, thereby improving the efficiency of summary generation. Users do not need to spend a lot of time and energy to manually write summaries, thus optimizing the user experience when publishing content.

[0048] S102: Based on the method of generating the target summary, determine the summary tags associated with the target summary.

[0049] The methods for generating abstracts can include automatic generation, manual input, and so on.

[0050] In this embodiment of the disclosure, to facilitate readers' intuitive understanding of the summary generation method, different summary tags can be associated with different summary generation methods. It should be noted that different summary tags can have different images or different displayed text. For example, the tag associated with automatically generated summaries can be "AI Summary," while the tag associated with manually entered summaries can be "Summary." Alternatively, both the image and the displayed text can be different.

[0051] S103: Jointly publish the target content, target summary, and summary tags.

[0052] In this embodiment of the disclosure, after the content publishing platform determines the summary tags associated with the target summary, it can create a content landing page by combining the target content, the target summary, and the summary tags in a certain structural style and publish it to the content display interface.

[0053] Optionally, if the target content is detected to have been modified, the target summary can be updated synchronously based on the modified content.

[0054] In this embodiment of the disclosure, users may modify the target content after it has been published. Therefore, when the content publishing platform detects that the target content has been modified, it can input the modified content into the large language model to generate a new summary and replace the original target summary with the new summary. This enables timely updates of the summary after the content is published, ensuring the timeliness and accuracy of the summary.

[0055] In this embodiment, upon receiving a content publishing request, the content publishing platform first determines the target content to be published, the target summary associated with the target content, and the generation method of the target summary. Then, based on the generation method of the target summary, it determines the summary tags associated with the target summary. Finally, it jointly publishes the target content, the target summary, and the summary tags. Thus, by jointly publishing the content with its associated target content and the summary tags determined according to the summary generation method, users can not only quickly understand the content through the summary but also correctly understand and evaluate the reliability of the summary based on its generation method, improving the efficiency and accuracy of users obtaining content.

[0056] Figure 2 This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure.

[0057] like Figure 2 As shown, the methods for publishing this content include:

[0058] S201: Upon receiving an instruction to automatically generate a summary, generate a first summary of the target content using a large language model.

[0059] The description of S201 above can be found in the above embodiments, and will not be repeated here.

[0060] S202: Display the first summary.

[0061] In this embodiment of the disclosure, after generating the first summary, the content publishing platform can display the first summary in the content editing interface, so that users can directly read the generation result of the summary, and users can modify the displayed first summary.

[0062] S203: Upon receiving a modification instruction for the first summary, obtain the first similarity between the modified summary and the first summary.

[0063] In this embodiment of the disclosure, the user can perform modification operations such as deleting or adding words and phrases in the first summary. The content publishing platform can then receive the modification instruction for the first summary, obtain the modified summary, and determine the first similarity between the modified summary and the first summary by calculating the distance between the text vectors of the modified summary and the first summary.

[0064] S204: If the first similarity is greater than the first threshold, the modified summary is determined as the target summary, and the generation method of the target summary is determined as the second method.

[0065] The first threshold is a value pre-set in the content publishing platform to determine whether a user-written summary deviates excessively from the target content. It can be fixed or determined based on the objectivity requirements of the summary; that is, a higher first threshold is set when the objectivity requirements of the target summary are higher. This disclosure does not limit this. The second method refers to a target summary generated by manually modifying an automatically generated summary, and the summary tags associated with this method are different from those of the first method.

[0066] In this embodiment of the disclosure, when the first similarity is greater than the first threshold, it indicates that the modified summary meets the objectivity requirements of the content publishing platform for the summary. It can be considered that the user has not excessively modified the summary in order to attract readers. Therefore, the modified summary can be determined as the target summary to be published. The generation method of the target summary is the second method.

[0067] Alternatively, if the first similarity is less than or equal to the first threshold, the modified summary can be associated with the content to be published and stored in a preset database, where the data in the preset database is used to update and train the large language model.

[0068] In this embodiment of the disclosure, when the first similarity is less than or equal to the first threshold, the first summary generated by the large language model may lack important information in the target content or be inaccurate in meaning. Therefore, the content publishing platform can associate the modified summary with the content to be published and store it in a preset database. When the amount of data in the preset database reaches a certain amount, or when it is at regular intervals, the large language model can be updated and trained using the data in the preset database. This provides data support for the update of the large language model and further improves the accuracy and reliability of the automatically generated summary.

[0069] S205: Upon receiving a content publishing request, determine the summary tags associated with the target summary based on the method of generating the target summary.

[0070] S206: Jointly publish the target content, target summary, and summary tags.

[0071] The descriptions of S205 and S206 above can be found in the above embodiments, and will not be repeated here.

[0072] In this embodiment, after receiving an automatic summary generation instruction, the content publishing platform first generates a first summary of the target content using a large language model, and then displays the first summary. Upon receiving a modification instruction for the first summary, it obtains a first similarity score between the modified summary and the first summary. If the first similarity score is greater than a first threshold, the modified summary is identified as the target summary, and the generation method of the target summary is determined to be the second method. Afterwards, upon receiving a content publishing request, the platform determines the summary tags and jointly publishes the target content, the target summary, and the summary tags. This allows users to modify the automatically generated summary, further improving the accuracy of the summary. Furthermore, by calculating the similarity of the summary before and after modification, it avoids excessive modification by users and ensures the objectivity of the target summary content.

[0073] Figure 3 This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure.

[0074] like Figure 3 As shown, the methods for publishing this content include:

[0075] S301: Upon receiving a second digest input from the user, the second digest is determined as the target digest, and the generation method of the target digest is determined to be user input.

[0076] In this embodiment of the disclosure, after receiving the second summary input by the user, the content publishing platform can compare it with the summary generated by the large language model to determine whether the second summary written by the user is subjective, incorrectly summarizes the target content, or lacks important information.

[0077] Optionally, a first similarity can be determined between the second summary and the first summary generated by the large language model. Then, if the first similarity is less than or equal to a first threshold, a summary modification prompt interface is displayed.

[0078] It should be noted that the display style of the first summary is different from that of the second summary. This difference may be due to at least one of the following: font, color, etc. Different display styles make it easier to intuitively and quickly distinguish between the automatically generated first summary and the user-input second summary, thereby improving the efficiency of subsequent modifications to the second summary.

[0079] In this embodiment, the content publishing platform can calculate a first similarity between the second summary and the first summary generated by the large language model. When the first similarity is less than or equal to a first threshold, the second summary may lack important information or contain grammatical errors, failing to meet the objectivity requirements of the target summary. Therefore, the content publishing platform can display a summary modification prompt interface to prompt the user to modify the second summary. This performs similarity verification on the user-input summary, avoiding misleading readers with subjective or erroneous summaries, and further improving the accuracy and reliability of summaries in published content.

[0080] Optionally, in the summary modification prompt interface, the segments to be modified in the second summary can be determined based on the matching degree between the second summary and the first summary. Then, the second summary and modification prompt characters are displayed in the summary modification prompt interface.

[0081] The display style of the segment to be modified is different from that of other segments. This could be due to different fonts, colors, font sizes, etc. This disclosure does not limit this.

[0082] In this embodiment, the content publishing platform can identify segments that do not match the first summary as segments to be modified within the second summary. These segments are then highlighted in the summary modification prompt interface in a different format than other segments; for example, the text of other segments can be black, while the text of the segment to be modified can be red. The corresponding content of the segment to be modified in the first summary can then be displayed as a modification prompt character in the corresponding position of the second summary within the summary modification prompt interface. This clearly informs the user which segments in the summary need modification and provides modification prompts, reducing the psychological burden on the user when modifying the summary and further improving the efficiency and accuracy of summary writing.

[0083] S302: Upon receiving a content publishing request, determine the summary tags associated with the target summary based on the method of generating the target summary.

[0084] S303: Publish the target content, target summary, and summary tags together.

[0085] The descriptions of S302 and S303 above can be found in the above embodiments, and will not be repeated here.

[0086] In this embodiment, upon receiving a second summary input by the user, the content publishing platform can identify the second summary as the target summary and determine that the target summary is generated by user input. This increases the flexibility of the target summary generation method and ensures the personalization of the summary. Furthermore, the intelligent summary generated based on a large language model can validate the user-input summary, further improving the accuracy and reliability of summaries in published content and enhancing the user experience when publishing content.

[0087] Figure 4 This is a flowchart illustrating a method for publishing content according to another embodiment of this disclosure.

[0088] like Figure 4 As shown, the methods for publishing this content include:

[0089] S401: Upon receiving a content publishing request, determine the target content to be published, the target summary associated with the target content, and the method for generating the target summary.

[0090] S402: Determine the summary tags associated with the target summary based on the generation method of the target summary.

[0091] S403: Publish the target content, target summary, and summary tags together.

[0092] The descriptions of S401-S403 above can be found in the above embodiments, and will not be repeated here.

[0093] S404: If it is detected that some content in the content display interface is selected, determine the size of the selected content.

[0094] The size of the selected content can be determined based on the number of words or lines contained in the content, and this disclosure does not impose any restrictions on this.

[0095] In this embodiment of the disclosure, when a user reads published content in the content display interface, the content publishing platform can monitor the user's selection operation in the display interface to provide a summary generation service for the selected content. Since users can easily obtain information from small amounts of selected content, such as only 20 words or a single line, the content publishing platform does not need to generate a summary for such small amounts of content. Therefore, when partial selection is detected, the size of the selected content can be determined first.

[0096] S405: If the size of the selected content is greater than the size threshold, determine the third summary of the selected content.

[0097] The scale threshold can be a fixed value set in advance on the content publishing platform, or it can be a value determined based on the input data requirements of the large language model for generating summaries.

[0098] In this embodiment of the disclosure, when the size of the selected content is greater than the size threshold, it indicates that the number of words or lines contained in the selected content is large enough. Users need to generate a summary of the selected content to quickly grasp the key information. Therefore, the content publishing platform can input the selected content into the large language model to obtain the third summary associated with the selected content.

[0099] S406: Display the third summary.

[0100] Optionally, a third summary can be displayed at a preset position in the content display interface.

[0101] The preset position may be below the selected content, or it may be the sidebar of the content display interface, etc. This disclosure does not limit it.

[0102] Alternatively, a third summary can be displayed in a preset display window, where the preset display window has a higher display priority than the content display window.

[0103] In other words, a new display window can pop up above the current content display interface to show the third summary associated with the selected content.

[0104] In this embodiment of the disclosure, by displaying the summary of the selected content in different ways, the summary can be presented to the user in a more intuitive and reasonable way, thereby improving the user's reading experience.

[0105] In this embodiment, after the content publishing platform jointly publishes the target content, target summary, and summary tags, it detects that some content is selected in the content display interface. First, it determines the size of the selected content. Then, if the size of the selected content exceeds a size threshold, it determines and displays a third summary of the selected content. Thus, by determining the size of selected content in the published content and generating a summary associated with the selected content, the application scenarios of intelligent summary generation are expanded. This allows users to specify key information of the content according to their needs, improving user reading efficiency and experience.

[0106] Figure 5 This is a schematic diagram of the structure of a content publishing device according to an embodiment of this disclosure.

[0107] like Figure 5 As shown, the content publishing device 500 includes:

[0108] The first determining module 501 is used to determine the target content to be published, the target summary associated with the target content, and the method for generating the target summary when a content publishing request is received.

[0109] The second determining module 502 is used to determine the summary tags associated with the target summary based on the generation method of the target summary;

[0110] The publishing module 503 is used to jointly publish the target content, target summary, and summary tags.

[0111] In some embodiments, the first determining module 501 described above can also be used for:

[0112] Upon receiving an automatic summary generation instruction, a first summary of the target content is generated using a large language model.

[0113] The first abstract is determined as the target abstract, and the method for generating the target abstract is determined as the first method.

[0114] In some embodiments, the first determining module 501 described above can also be used for:

[0115] Display first summary;

[0116] Upon receiving a modification instruction for the first summary, obtain the first similarity between the modified summary and the first summary;

[0117] If the first similarity is greater than the first threshold, the modified summary is determined as the target summary, and the generation method of the target summary is determined as the second method.

[0118] In some embodiments, the first determining module 501 described above can also be used for:

[0119] If the first similarity is less than or equal to the first threshold, the modified summary is associated with the content to be published and stored in a preset database. The data in the preset database is used to update and train the large language model.

[0120] In some embodiments, the first determining module 501 described above can also be used for:

[0121] Determine the first similarity between the second summary and the first summary generated by the large language model;

[0122] If the first similarity is less than or equal to the first threshold, a summary modification prompt interface will be displayed.

[0123] In some embodiments, the first determining module 501 described above can also be used for:

[0124] Based on the matching degree between the second summary and the first summary, the segments to be modified contained in the second summary are determined;

[0125] The summary modification prompt interface displays the second summary and modification prompt characters. The display style of the segment to be modified is different from that of the other segments.

[0126] In some embodiments, the display style of the first summary is different from that of the second summary.

[0127] In some embodiments, the publishing module 503 described above can also be used for:

[0128] If the target content is detected to have been modified, the target summary is updated based on the modified content.

[0129] In some embodiments, the publishing module 503 described above can also be used for:

[0130] If it is detected that some content in the content display interface is selected, determine the size of the selected content;

[0131] If the size of the selected content is greater than the size threshold, determine the third summary of the selected content;

[0132] Display the third summary.

[0133] In some embodiments, the publishing module 503 described above can also be used for:

[0134] Display the third summary in a preset position on the content display interface; or,

[0135] The third summary is displayed in the preset display window, where the preset display...

[0136] The window has a higher display priority than the content display interface.

[0137] It should be noted that the foregoing explanation of the content publishing method also applies to the content publishing device of this embodiment, and will not be repeated here.

[0138] In this embodiment, upon receiving a content publishing request, the content publishing platform first determines the target content to be published, the target summary associated with the target content, and the generation method of the target summary. Then, based on the generation method of the target summary, it determines the summary tags associated with the target summary. Finally, it jointly publishes the target content, the target summary, and the summary tags. Thus, by jointly publishing the associated target summary with the summary tags determined according to the summary generation method during content publishing, users can not only quickly understand the content through the summary but also correctly understand and evaluate the reliability of the summary based on its generation method, improving the efficiency and accuracy of users obtaining content.

[0139] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0140] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0141] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0142] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0143] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as content publishing methods. For example, in some embodiments, the content publishing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the content publishing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform content publishing methods by any other suitable means (e.g., by means of firmware).

[0144] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0146] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0149] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0150] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0151] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of this disclosure, the words "if" and "suppose" as used may be interpreted as "when," "when," "in response to determination," or "in the circumstances."

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. A content publishing method, comprising: in the case of receiving a content publishing request, determining target content to be published, a target abstract associated with the target content, and a generation manner of the target abstract; determining an abstract tag associated with the target abstract based on the generation manner of the target abstract; jointly publishing the target content, the target abstract, and the abstract tag; wherein, before the receiving of the content publishing request, further comprising: in the case of receiving a second abstract input by a user, determining the second abstract as the target abstract, and determining that the generation manner of the target abstract is user input; wherein, after the receiving of the second abstract input by the user, further comprising: determining a first similarity between the second abstract and a first abstract generated by a large language model; in the case that the first similarity is less than or equal to a first threshold, displaying an abstract modification prompt interface; wherein, the displaying of the abstract modification prompt interface comprises: determining a to-be-modified segment contained in the second abstract according to a matching degree between the second abstract and the first abstract, wherein a segment that does not match between the second abstract and the first abstract is determined as the to-be-modified segment contained in the second abstract; displaying the second abstract and a modification prompt character in the abstract modification prompt interface, wherein the display style of the to-be-modified segment is different from that of other segments, and the content corresponding to the to-be-modified segment in the first abstract is displayed as the modification prompt character in the corresponding position of the second abstract in the abstract modification prompt interface.

2. The method of claim 1, wherein, before the receiving of the content publishing request, further comprising: in the case of receiving an abstract automatic generation instruction, generating a first abstract of the target content by using a large language model; determining the first abstract as the target abstract, and determining that the generation manner of the target abstract is a first manner.

3. The method of claim 2, wherein, after the generating of the first abstract of the target content by using the large language model, further comprising: displaying the first abstract; in the case of receiving a modification instruction for the first abstract, obtaining a first similarity between a modified abstract and the first abstract; in the case that the first similarity is greater than a first threshold, determining the modified abstract as the target abstract, and determining that the generation manner of the target abstract is a second manner.

4. The method of claim 3, wherein, after the obtaining of the first similarity between the modified abstract and the first abstract, further comprising: in the case that the first similarity is less than or equal to the first threshold, storing the modified abstract in association with the content to be published in a preset database, wherein the data in the preset database is data for updating and training the large language model.

5. The method of claim 1, wherein, the display style of the first abstract is different from that of the second abstract.

6. The method of any one of claims 1-5, wherein, after the jointly publishing of the target content, the target abstract, and the abstract tag, further comprising: in the case of monitoring that the target content is modified, updating the target abstract according to the modified content.

7. The method of any one of claims 1-5, wherein, after the jointly publishing of the target content, the target abstract, and the abstract tag, further comprising: In a case where it is monitored that part of the content in the content display interface is selected, a size of the selected content is determined; In a case where the size of the selected content is greater than a size threshold, a third abstract of the selected content is determined; The third abstract is displayed.

8. The method of claim 7, wherein, The displaying of the third abstract comprises: The third abstract is displayed at a preset position in the content display interface; or The third abstract is displayed in a preset display window, wherein a display priority of the preset display window is higher than a display priority of the content display interface.

9. A content publishing apparatus, comprising: A first determination module configured to, in a case where a content publishing request is received, determine target content to be published, a target abstract associated with the target content, and a generation manner of the target abstract; A second determination module configured to determine an abstract tag associated with the target abstract based on the generation manner of the target abstract; A publishing module configured to jointly publish the target content, the target abstract, and the abstract tag; The first determination module is further configured to: In a case where a second abstract input by a user is received, determine the second abstract as the target abstract, and determine that the generation manner of the target abstract is user input; The first determination module is further configured to: Determine a first similarity between the second abstract and a first abstract generated by a large language model; In a case where the first similarity is less than or equal to a first threshold, display an abstract modification prompt interface; The first determination module is further configured to: Determine a to-be-modified segment contained in the second abstract according to a matching degree between the second abstract and the first abstract, wherein a segment that is not matched between the second abstract and the first abstract is determined as the to-be-modified segment contained in the second abstract; Display the second abstract and a modification prompt character in the abstract modification prompt interface, wherein a display style of the to-be-modified segment is different from a display style of other segments, and content corresponding to the to-be-modified segment in the first abstract is displayed as the modification prompt character at a corresponding position of the second abstract in the abstract modification prompt interface.

10. The apparatus of claim 9, wherein, The first determination module is further configured to: In a case where an abstract automatic generation instruction is received, generate a first abstract of the target content by using a large language model; Determine the first abstract as the target abstract, and determine that the generation manner of the target abstract is a first manner.

11. The apparatus of claim 10, wherein, The first determination module is further configured to: Display the first abstract; In a case where a modification instruction for the first abstract is received, determine a first similarity between a modified abstract and the first abstract; In a case where the first similarity is greater than a first threshold, determine the modified abstract as the target abstract, and determine that the generation manner of the target abstract is a second manner.

12. The apparatus of claim 11, wherein, The first determination module is further configured to: In a case where the first similarity is less than or equal to the first threshold, store the modified abstract in association with the content to be published in a preset database, wherein data in the preset database is data for updating and training the large language model.

13. The apparatus of claim 9, wherein, The display style of the first abstract is different from the display style of the second abstract.

14. The apparatus of any one of claims 9-13, wherein, The publishing module is further configured to: update the target abstract according to the modified content when it is monitored that the target content is modified.

15. The apparatus of any of claims 9-13, wherein, The publishing module is further configured to: determine the size of the selected content when it is monitored that part of the content in the content display interface is selected; determine a third abstract of the selected content when the size of the selected content is greater than a size threshold; display the third abstract.

16. The apparatus of claim 15, wherein, The publishing module is further configured to: display the third abstract at a preset position in the content display interface; or display the third abstract in a preset display window, wherein the display priority of the preset display window is higher than the display priority of the content display interface. 17.An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the content publishing method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, wherein the computer instructions are used to enable the computer to perform the content publishing method of any one of claims 1-8.

19. A computer program product, characterised in that, comprising a computer program which, when executed by a processor, implements the steps of the content publishing method according to any one of claims 1-8.

Images