Content processing methods, apparatus, electronic devices, media, programs and program products

Abstract

This disclosure relates to a content processing method, apparatus, electronic device, medium, program, and program product, and pertains to the field of computer technology. The content processing method of this disclosure includes: extracting the main idea and keywords of a story fragment from a first story; generating a topic based on the content, main idea, and keywords of the story fragment, wherein the topic is used to guide users to create a second story related to the topic; and displaying the topic.

Description

Content processing methods, apparatus, electronic devices, media, programs and program products Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a content processing method, apparatus, electronic device, medium, program, and program product. Background Technology

[0002] With the development of internet technology, e-reading materials are becoming increasingly accepted. A vast number of e-books exist on internet reading platforms and applications, allowing users to comment on, discuss, and share their own stories after reading. For example, users can create topics related to the content of an e-book that interest them, and other users can participate in discussions and share their own stories related to that topic.

[0003] Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] According to some embodiments of this disclosure, a content processing method is provided, including: extracting the main idea and keywords of a story fragment from a first story; generating a topic based on the content, main idea, and keywords of the story fragment, wherein the topic is used to guide users to create a second story related to the topic; and displaying the topic.

[0006] According to some other embodiments of this disclosure, a content processing apparatus is provided, including: an extraction module configured to extract the theme and keywords of a story fragment based on the content of a story fragment in a first story; a generation module configured to generate a topic based on the content, theme, and keywords of the story fragment, wherein the topic is used to guide users to create a second story related to the topic; and a display module configured to display the topic.

[0007] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions, which, when executed by the processor, cause the processor to perform a content processing method according to any embodiment of the present disclosure.

[0008] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the content processing method of any embodiment of the present disclosure.

[0009] According to some further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the content processing method of any embodiment of the present disclosure.

[0010] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the content processing method of any embodiment of the present disclosure.

[0011] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0012] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0013] Figure 1 shows a schematic flowchart of a content processing method according to some embodiments of this disclosure;

[0014] Figure 2 shows a schematic flowchart of a content processing method according to some other embodiments of this disclosure;

[0015] Figures 3 to 5 show schematic diagrams of the display interfaces of some embodiments of this disclosure;

[0016] Figure 6 shows a schematic diagram of the structure of a content processing apparatus according to some embodiments of the present disclosure;

[0017] Figure 7 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure;

[0018] Figure 8 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.

[0019] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0021] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0022] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0023] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0024] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0028] For e-books, such as novels, relevant topics can guide users to share their stories and experiences. The more users participate in topic discussions and related creations, the richer the content on the reading platform becomes, thus providing users with a more interactive reading environment with a better atmosphere for creation and reading. This also benefits the promotion of e-books and attracts more users to participate in discussions and creations.

[0029] Currently, topics are generally initiated by users, resulting in a limited number of topics and low generation efficiency, making it difficult to effectively guide more users to participate in topic discussions and publish topic-related stories. In view of this, this disclosure proposes a content processing method that can automatically generate topics based on the content of story fragments, improving topic generation efficiency and attracting more users to create topic-related stories. Some embodiments of the content processing method of this disclosure are described below with reference to Figures 1-5.

[0030] Figure 1 is a flowchart of some embodiments of the content processing method of this disclosure. As shown in Figure 1, the content processing method of this embodiment includes steps S102 to S106. The method of this embodiment can be implemented by a client. The client can be implemented in the form of software, hardware, or a combination of software and hardware. For example, the client is a reading platform or application, or the client is a terminal, not limited to the examples given.

[0031] In step S102, the main idea and keywords of the story fragments are extracted based on the content of the story fragments in the first story.

[0032] The first story can be a long story, such as a novel. A story segment can be a chapter, a section, or other ways of dividing story segments, not limited to the examples given. The main idea of ​​a story segment can be used to describe its core thought, theme, etc. Natural language processing algorithms can be used to extract the main idea and keywords of a story segment.

[0033] In step S104, a topic is generated based on the content, theme, and keywords of the story fragment.

[0034] The topic is used to guide users to create a second story related to the topic. The topic is associated with the content, theme, and keywords of the story fragment. Users who read the first story, especially the story fragment, are more likely to be inspired to create and share a second story related to the topic and the story fragment under the guidance of the topic. The second story can be a short story.

[0035] For example, machine learning models can be used to generate topics based on the content, theme, and keywords of story fragments. For instance, the machine learning model could be an LLM (Large Language Model), but is not limited to the examples given.

[0036] In step S106, the topic is displayed.

[0037] For example, topics can be displayed at the end of a story segment or in the discussion area of ​​the first story. Topics can be displayed in different distribution scenarios (or interfaces), and are not limited to the examples given. After the topic is displayed, users can create and input a second story based on the topic's guidance.

[0038] In the method described above, the main idea and keywords of a story fragment are extracted from the content of the first story. Then, topics are generated and displayed based on the content, main idea, and keywords of the story fragment. This achieves automatic topic generation based on the content of the first story, improving topic generation efficiency. Furthermore, since the topics are associated with specific story content, main idea, and keywords of the first story, it is easier to stimulate the creative enthusiasm of users who read the first story, thereby more effectively guiding users to create second stories related to the topics, improving the accuracy and effectiveness of the topics.

[0039] The following describes, with some examples, how to extract the main idea and keywords of a story fragment from the content of the first story.

[0040] In some embodiments, extracting the theme and keywords of a story segment based on the content of the story segment in the first story includes: segmenting the content of the story segment in the first story into words to determine multiple word segments; and determining the theme and keywords of the story segment based on the clustering results of the multiple word segments.

[0041] For example, the story fragment can be segmented into words first, and stop words can be removed from each segment. The processed segments can then be converted into word vectors. Based on the word vectors of each segment, they can be clustered, and the segment corresponding to the word vector of each cluster center can be used as the keyword of the story fragment. For example, the Word2Vec algorithm can be used to convert the segmented words into word vectors, and this example is not limited to the one given.

[0042] After identifying the keywords, you can select theme words based on the frequency of each keyword in the story segment, and then determine the main theme of the story segment based on the theme words.

[0043] Other methods can also be used to extract the main idea and keywords from story fragments. For example, keywords can be extracted using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm, the main idea can be extracted using the LDA (Latent Dirichlet Allocation) algorithm, or an LLM model can be used directly to output the main idea and keywords based on the input story fragment. These methods are not limited to the examples given.

[0044] The following examples illustrate how topics can be generated based on the content, theme, and keywords of story fragments.

[0045] In some embodiments, there are multiple keywords. Generating a topic based on the content, theme, and keywords of a story fragment includes: determining the relevance of each keyword among the multiple keywords to the content of the story fragment, and generating a topic based on the theme, the multiple keywords, and the relevance of each keyword to the content of the story fragment.

[0046] For example, for each keyword, the relevance between the keyword and the story fragment can be determined based on the semantic information of the keyword and the story fragment itself. Alternatively, the relevance between the keyword and the story fragment can be determined based on the semantic information of the keyword and the theme. The theme reflects the central idea of ​​the story fragment; therefore, the relevance between keywords and the theme reflects the relevance between the keywords and the story fragment's content.

[0047] For example, while extracting multiple keywords, the relevance of each keyword to the story segment can be determined based on its importance within the segment; higher importance equates to higher relevance. Algorithms such as TF-IDF can be used to determine the importance of each keyword; existing technologies can be referenced, and will not be elaborated upon here.

[0048] In addition to considering the main theme and keywords when generating topics, the relevance of each keyword to the content of the story segment is also taken into account. This allows for more accurate selection of keywords to generate topics, resulting in a higher relevance between the generated topics and the story segment. This improves the effectiveness and accuracy of the generated topics and can more effectively guide users to create second stories related to the topics.

[0049] Machine learning models can be used to generate topics based on the main theme, multiple keywords, and the relevance of each keyword to the content of the story segment.

[0050] In some embodiments, generating topics based on the theme, multiple keywords, and the relevance of each keyword to the content of the story segment includes: generating prompts based on the theme, multiple keywords, and the relevance of each keyword to the content of the story segment; and generating topics based on the prompts using a machine learning model.

[0051] Machine learning models can understand prompts and use this understanding to guide the model in generating prompts based on the main theme, multiple keywords, and the relevance of each keyword to the story fragment. For example, the prompt might include an input field containing the main theme, multiple keywords, and the relevance of each keyword to the story fragment. The prompt can also include a task description. For instance, the task description might indicate that the machine learning model's task is to generate topics that align with the story fragment's theme and guide the user's creative process. Further prompts might include one or more constraints, representing the conditions that the generated topic must meet.

[0052] In some embodiments, the prompt information includes one or more constraints, which include at least one of the following: constraints on the relevance of the topic to the theme, constraints on the relevance of the topic to the content of the story segment, constraints on the relevance of the topic to the characters in the story segment, constraints on the form of the topic, and constraints on the number of topics.

[0053] Constraints regarding the relevance of a topic to the main theme can be used to ensure that the topic does not deviate from the main theme of the story segment. Constraints regarding the relevance of a topic to the content of the story segment can be used to ensure that the topic is relevant to the content of the story segment. Constraints regarding the relevance of a topic to the characters in the story segment can be used to ensure that the topic captures information about the characters in the story segment. Constraints regarding the form of a topic can be used to constrain the sentence structure of the topic; for example, a constraint regarding the form of a topic can ensure that the topic is in a question format. Constraints regarding the number of topics can be used to constrain the number of topics generated; for example, the number of topics can be 10. Through one or more constraints, the machine learning model can more accurately generate topics that meet the requirements.

[0054] Machine learning models can be used to analyze prompts, extracting the main idea, multiple keywords, and the relevance of each keyword to the story fragment from the input fields. This allows for the understanding of the task description and one or more constraints. Based on the main idea, keywords, and their relevance to the story fragment, topics that meet one or more constraints can be generated. For example, generated topics should satisfy at least one of the following: relevance to the main idea of ​​the story fragment, relevance to the content of the story fragment, relevance to the characters in the story fragment, representation in a preset format, and a certain number of such topics.

[0055] In some embodiments, the prompt information may also include example topics. These example topics can be used by machine learning models to learn the expression, style, and sentence structure of topics, making the generated topics more natural and fluent.

[0056] You can also add story snippets to the input fields of the prompt information and input them into the machine learning model. During the topic generation process, the machine learning model will understand the content of the story snippets, thereby making the generated topics more relevant to the content of the story snippets and improving the accuracy and effectiveness of the topics.

[0057] In some embodiments, generating topics using a machine learning model based on prompts includes: using a machine learning model to select one or more target keywords from multiple keywords based on prompts, and generating topics based on the content and theme of the story fragment, one or more target keywords, and one or more constraints.

[0058] For example, a machine learning model can be used to parse the prompt information, extract the main idea, multiple keywords, and the relevance of each keyword to the content of the story segment from the input field, select one or more target keywords from the multiple keywords based on the relevance of each keyword to the content of the story segment, and then generate a topic based on the main idea, one or more target keywords, and one or more constraints.

[0059] By configuring and generating prompts and using machine learning models to learn how to generate topics based on these prompts, topics can be generated more accurately, meeting user needs and more effectively guiding users to create second stories.

[0060] In some embodiments, in response to one or more constraints, including constraints on the relevance of the topic to the characters in the story segment, a machine learning model is used to extract character information from the story segment, and a topic is generated based on the theme, one or more target keywords, character information, and one or more constraints.

[0061] For example, character information includes the character's name, personality, identity, relationships between characters, and other character-related information. Topics related to characters are more likely to spark user discussion and creation; therefore, referencing character information when generating topics can improve the effectiveness of guiding users to create second stories.

[0062] Besides referencing the story fragment content itself, user behavior can also be used to generate topics. For example, while reading a story fragment, users can underline, annotate, or mark up content (e.g., sentences, paragraphs). These user-marked content can be used to generate topics that are more relevant to the user. In some embodiments, generating topics based on the content, theme, and keywords of a story fragment includes: generating topics based on the content, theme, keywords, and marked content of the story fragment.

[0063] Personalized topics can be generated for each user based on the content, theme, keywords, and tags of the story fragments. Alternatively, topics can be generated based on the content tagged by multiple users, identifying content tagged more than a threshold, and then using this information as the basis for generating topics.

[0064] Furthermore, using machine learning models, topics are generated based on the main theme, one or more target keywords, user-tagged content, and one or more constraints. This can be combined with the methods described in the foregoing embodiments, and will not be elaborated further here.

[0065] To improve the relevance of the generated topics to the content of the story fragments, in some embodiments, multiple candidate topics are generated based on the content, theme, and keywords of the story fragments; a preset number of candidate topics are selected as topics based on the relevance of the multiple candidate topics to the content of the story fragments.

[0066] A machine learning model can be used to first generate multiple candidate topics. The relevance of these topics to the story fragments can then be verified. Topics with a relevance higher than a relevance threshold can be selected as the final topics, thus improving the accuracy and effectiveness of the generated topics. For example, the relevance between the candidate topics and the story fragments can be determined based on their semantic information. Since the machine learning model needs to understand the story fragments, these fragments can be added to the input field of the prompt information and fed into the machine learning model.

[0067] After a topic is generated, it can be adjusted to make it more accurate and effective. In some embodiments, the relevance of the topic to the content of the story segment is determined; if the relevance of the topic to the content of the story segment is lower than a first threshold, the topic is adjusted.

[0068] When there are multiple topics, determine the relevance of each topic to the story segment's content, and adjust topics whose relevance to the story segment's content is below a first threshold. Machine learning models can be used to determine the relevance between topics and story segment content, and to adjust the topics accordingly.

[0069] The following describes how to adjust the topic using some examples.

[0070] In some embodiments, adjusting the topic includes: reselecting target keywords from a plurality of keywords, and adjusting the topic based on the reselected target keywords. For example, the topic can be regenerated based on the main idea and the reselected target keywords; or, the topic can be regenerated based on the main idea, the previously selected target keywords, and the reselected target keywords. During the process of regenerating the topic, one or more constraints, tagged content, and / or role information can also be considered, as described in the foregoing embodiments, which will not be repeated here.

[0071] In some embodiments, adjusting a topic includes: adjusting one or more constraints, and regenerating the topic based on the adjusted constraints, the theme, and one or more target keywords.

[0072] Adjusting one or more constraints adjusts the prompt message. You can select new constraints from multiple candidate constraints and add them to the prompt message. Newly selected constraints can be used together with existing constraints or can replace existing constraints. Newly selected constraints are used to constrain at least one of the following: the relevance of the topic to the story fragment's content, the relevance of the topic to the theme, the relevance of the topic to the target keywords, the relevance of the topic to the characters in the story fragment, the relevance of the topic to the location in the story fragment, the relevance of the topic to the scene in the story fragment, and the relevance of the topic to the key plot points in the story fragment.

[0073] In response to the reselected constraints used to constrain the relevance of the topic to the locations in the story fragment, a machine learning model is used to extract location information from the story fragment, and the topic is regenerated based on the theme, one or more target keywords, location information, and the adjusted constraints.

[0074] In response to the reselected constraints used to constrain the relevance of the topic to the scene in the story fragment, the machine learning model is used to extract scene information from the story fragment, and the topic is regenerated based on the theme, one or more target keywords, scene information, and the adjusted constraints.

[0075] In response to the reselected constraints used to constrain the relevance of the topic to key plot points in the story fragment, a machine learning model is used to extract summary information of key plot points from the story fragment. Based on the theme, one or more target keywords, summary information of key plot points, and the adjusted constraints, the topic is regenerated.

[0076] In the process of regenerating topics, the content of the tags and / or the information of the roles can also be used as a reference, as described in the aforementioned embodiments, which will not be repeated here.

[0077] In some embodiments, adjusting a topic includes: determining the relevance of the topic to a character in a story segment; and adjusting the topic based on character information in the story segment in response to the relevance of the topic to a character in the story segment being lower than a second threshold.

[0078] If the topic has low relevance to the content of a story fragment, it can be determined whether the topic has low relevance to the characters in the story fragment. If the topic has low relevance to the characters in the story fragment, it's possible that character information wasn't referenced during topic generation. Therefore, machine learning models can be used to extract character information from the story fragment for topic regeneration. Topics can be regenerated based on the main theme, one or more target keywords, character information, and one or more constraints. Alternatively, topics can be regenerated using machine learning models based on character information and existing topics. The topic regeneration process can also be based on tagged content; refer to the aforementioned examples, which will not be repeated here.

[0079] In some embodiments, adjusting a topic includes: determining the relevance of the topic to a location in a story segment; and adjusting the topic based on location information in the story segment in response to the relevance of the topic to a location in the story segment being lower than a third threshold.

[0080] If the topic has low relevance to the content of a story fragment, it can be determined whether the topic also has low relevance to the location within the story fragment. If the topic has low relevance to the location within the story fragment, it's possible that no reference character information was used during the topic generation process. Therefore, machine learning models can be used to extract location information from the story fragment for topic regeneration. Topics can be regenerated based on the main theme, one or more target keywords, location information, and one or more constraints. Alternatively, topics can be regenerated using machine learning models based on location information and existing topics. The topic regeneration process can also be based on tagged content; refer to the aforementioned examples, which will not be repeated here.

[0081] In some embodiments, adjusting a topic includes: determining the relevance of the topic to a scene in a story segment; and adjusting the topic based on scene information in the story segment in response to the relevance of the topic to a scene in a story segment being lower than a fourth threshold.

[0082] In some embodiments, adjusting the topic includes: determining the relevance of the topic to key plot points in a story segment; and adjusting the topic based on scene information in the story segment in response to the relevance of the topic to key plot points in a story segment being lower than a fifth threshold.

[0083] If there are multiple regenerated topics, some or all of the regenerated topics can be selected to replace topics whose relevance to the story fragments is lower than the first threshold, based on the relevance of the regenerated topics to the story fragments.

[0084] In the above embodiments, the relevance of the generated topics and story fragments is examined, and the topics can be readjusted to improve their accuracy and effectiveness, thus more effectively guiding users to create second stories.

[0085] In addition to examining the relevance of the topic to the story fragments, it is also possible to examine the user group attributes, emotional tendencies, and viewpoints of the topic, so that the topic can provide effective and positive guidance to users.

[0086] In some embodiments, the matching degree between the topic and the attribute information of the user group of the first story is determined; in response to the matching degree between the topic and at least one attribute information of the user group of the first story being lower than the matching degree threshold, the topic is adjusted according to the attribute information of the user group of the first story.

[0087] User group attributes include factors such as age, gender, and preferences. Analysis of the user group for the first story can yield this attribute information. If the topic doesn't match the user group's attributes, it's difficult to effectively guide readers to create content. For example, if the user group's attributes include a female tag, indicating a higher proportion of female users who read more ebooks on female-oriented topics, a male-oriented topic would be less likely to inspire creation. Machine learning models can be used to regenerate topics based on the user group's attributes, the main theme, and one or more target keywords. Alternatively, machine learning models can be used to regenerate topics based on the user group's attributes and existing topics. Machine learning models can also generate topics based on one or more constraints, character information, etc., as illustrated in the previous examples, and will not be repeated here.

[0088] In some embodiments, the sentiment tendency of the topic is determined, and the sentiment tendency of the topic is adjusted in response to the topic being negative; and / or, the viewpoint of the topic is determined, and the viewpoint of the topic is adjusted in response to the viewpoint of the topic not conforming to a preset standard.

[0089] Machine learning models can be used to identify the sentiment of topics. Topics with a negative sentiment can negatively influence users, therefore adjustments are necessary. Machine learning models can be used to adjust the sentiment of topics to a positive one. Alternatively, constraints can be added to the prompts to ensure the topic's sentiment remains positive.

[0090] A topic's viewpoints conforming to preset standards means that the viewpoints expressed are considered correct and accepted by the majority, thus avoiding misleading users. Machine learning models can be used to adjust the viewpoints of topics, generating topics that meet these preset standards.

[0091] By examining the emotional tone and viewpoints of topics, we can prevent generated topics from misleading users and improve network security.

[0092] The above-described embodiments for adjusting the topic can be applied individually or in combination, and will not be elaborated further here.

[0093] Figure 2 is a flowchart of some other embodiments of the content processing method of this disclosure. As shown in Figure 2, the content processing method of this embodiment includes steps S202 to S210.

[0094] In step S202, the main idea and keywords of the story fragments are extracted based on the content of the story fragments in the first story.

[0095] In step S204, topics are generated based on the content, theme, and keywords of the story fragments.

[0096] The topic is used to guide users to create a second story that is related to the topic.

[0097] In step S206, based on the relevance of the topic to the story fragment, the matching degree of the topic to the user group's attribute information, the emotional tendency of the topic, and the viewpoint of the topic, it is determined whether to adjust the topic. If so, step S208 is executed; otherwise, step S210 is executed.

[0098] In step S208, the topic is adjusted.

[0099] For details on whether to adjust the topic and the methods for adjusting the topic, please refer to the aforementioned embodiments, which will not be repeated here.

[0100] In step S210, the topic is displayed.

[0101] The methods described in the above embodiments can improve the accuracy and effectiveness of topics, reduce the probability of topics misleading users, and improve network security.

[0102] The following describes some examples of how topics are displayed, with reference to Figures 3-5.

[0103] Topics can be displayed in various distribution scenarios, as shown in Figure 3. For example, topic 304 can be displayed at the end of a chapter. Figure 3 shows the display interface of an e-book. The display interface can show the chapter's terms 301 and the chapter's ending content 302. It can also display discussion information 303 from users reading the chapter, such as the number of discussions and the avatars of the discussing users. In response to the current user triggering the control corresponding to the discussion information, the discussion information can be displayed using a new interface, window, or overlay, etc. The specific display method is not limited here. Based on the method of the aforementioned embodiment, the chapter's topic 304, "What is the most beautiful love?", can be generated and displayed in the topic display area. In response to the user triggering the topic's input control 305, an input interface can be displayed. The input interface can use a new interface, window, overlay, etc., and is not limited to the examples given. Users can create and input a second story in the input interface. The topic display area can also display trigger controls 306 for other topics. In response to the user triggering other topic trigger controls 306, other topics can be displayed. For example, if multiple topics are generated, only one topic may be displayed on the current screen, while the remaining topics can be displayed in response to the user triggering other topic trigger controls 306. Multiple topics can also be displayed on the current screen, allowing users to create content on any one or more topics. Creation tasks can also be set. In response to the user triggering a creation task control 307, the specific creation task can be displayed; for example, users can receive a reward after completing a creation task.

[0104] As shown in Figure 4, in response to the user triggering the input control 305 "Share Story", an input interface can be displayed. The input interface displays the topic 401 of this chapter, "What is the most beautiful love like?", and also includes an input area 404 and an input display area 402. The input display area 402 can display the content entered by the user. The input interface may also include trigger controls 403 for other topics. In response to the user triggering other topic trigger controls 403, other topics can be displayed. The input display area 402 can also display guidance information, which guides the user to share their real experiences or create stories based on the topic, guides the user to create complete long content, and provides input formatting instructions, etc.

[0105] In some embodiments, guidance information is generated to guide users in creating a second story, based on the topic; the guidance information is then displayed.

[0106] The guidance information can include at least one piece of information related to the topic, such as prompts, story outlines, story structures, and story beginnings, to guide the user's creation. Machine learning models can be used to generate guidance information based on the topic. Users can enrich and refine the content of their second story based on this guidance, making creation easier, providing inspiration, and improving efficiency. For example, the guidance information can also be displayed in input display area 402.

[0107] In some embodiments, in response to user input of content for the second story, the second story is displayed; in response to user sharing of the second story, the second story is shared to one or more distribution scenarios.

[0108] As shown in Figure 4, the user inputs the content of the second story through the input area 404, and the second story is displayed in the input display area 402. In response to the user triggering the sharing control 405, the second story can be shared so that other users can read it. Users can share the second story to their own homepage, the discussion forum of the reading platform, or other scenarios, not limited to the examples given.

[0109] Figure 5 shows the display interface for the second story. After a user shares the second story, they can view it, and other users can also view it. The display interface for the second story can show topic 501 "What is the most beautiful love like?", the second story 503, and information 502 about the user who created the second story, such as the user's name, posting time, and avatar, etc., not limited to the examples given. After reading the second story, other users can comment, like, etc. The display interface for the second story can show access information 504, including the number of comments, the number of likes, etc., not limited to the examples given. 504 can also be a comment / like control, allowing users to directly comment and like. The display interface for the second story can also include an invitation control 505 and a creation control 506. In response to a user triggering the invitation control 505, an invitation channel can be displayed. In response to a user selecting an invitation channel, the invitation information is sent to the corresponding application or user through that channel. In response to the user triggering the creation control 506, one or more topics to be created are displayed. These topics can be the first story or topics related to the current topic, or popular topics with more than a threshold of creations, etc., and are not limited to the examples given.

[0110] For each topic, the interface corresponding to that topic can be displayed. The interface corresponding to that topic can include one or more items, each item corresponding to a story. In response to the user triggering any item, the display interface of the corresponding story is displayed, for example, the interface shown in Figure 5.

[0111] The content processing method in this embodiment can automatically generate topics, improving the efficiency of topic generation and guiding more users to create stories related to the topics, enriching the content in the reading platform and providing users with a more interactive reading environment with a better atmosphere for creation and reading.

[0112] This disclosure also provides a content processing apparatus, which will be described below with reference to FIG6.

[0113] Figure 6 is a structural diagram of some embodiments of the content processing apparatus of this disclosure. As shown in Figure 6, the content processing apparatus 60 of this embodiment includes: an extraction module 610, a generation module 620, and a display module 630.

[0114] The extraction module 610 is configured to extract the main idea and keywords of the story fragments based on the content of the story fragments in the first story.

[0115] The generation module 620 is configured to generate topics based on the content, theme, and keywords of the story fragments, whereby the topics are used to guide users to create a second story related to the topic.

[0116] Display module 630 is configured to display topics.

[0117] In some embodiments, there are multiple keywords, and the generation module 620 is configured to determine the relevance of each keyword among the multiple keywords to the content of the story segment; and generate a topic based on the theme, the multiple keywords, and the relevance of each keyword to the content of the story segment.

[0118] In some embodiments, the generation module 620 is configured to generate prompts based on the theme, multiple keywords, and the relevance of each keyword to the content of the story segment; and to generate topics based on the prompts using a machine learning model.

[0119] In some embodiments, the prompt information includes one or more constraints, which include at least one of the following: constraints on the relevance of the topic to the theme, constraints on the relevance of the topic to the content of the story segment, constraints on the relevance of the topic to the characters in the story segment, constraints on the form of the topic, and constraints on the number of topics.

[0120] In some embodiments, the generation module 620 is configured to use a machine learning model to select one or more target keywords from a plurality of keywords based on prompts, and to generate a topic based on the content, theme, one or more target keywords, and one or more constraints of the story fragment.

[0121] In some embodiments, the generation module 620 is configured to generate multiple candidate topics based on the content, theme, and keywords of the story fragment; and to select a preset number of candidate topics as topics based on the relevance of the multiple candidate topics to the content of the story fragment.

[0122] In some embodiments, the generation module 620 is further configured to determine the relevance of the topic to the content of the story segment; and to adjust the topic in response to the relevance of the topic to the content of the story segment being lower than a first threshold.

[0123] In some embodiments, the generation module 620 is configured to determine the relevance of a topic to a character in a story segment; and to adjust the topic based on character information in the story segment if the relevance of the topic to a character in the story segment is lower than a second threshold.

[0124] In some embodiments, the generation module 620 is configured to determine the relevance of a topic to a location in a story fragment; and to adjust the topic based on location information in the story fragment if the relevance of the topic to a location in the story fragment is lower than a third threshold.

[0125] In some embodiments, the generation module 620 is further configured to determine the degree of matching between the topic and the attribute information of the user group of the first story; and to adjust the topic according to the attribute information of the user group of the first story in response to the fact that the degree of matching between the topic and at least one attribute information of the user group of the first story is lower than the degree of matching threshold.

[0126] In some embodiments, the generation module 620 is further configured to determine the sentiment tendency of the topic, adjust the sentiment tendency of the topic in response to the negative sentiment tendency of the topic; and / or determine the viewpoint of the topic, adjust the viewpoint of the topic in response to the viewpoint of the topic not conforming to a preset standard.

[0127] In some embodiments, the generation module 620 is further configured to generate guidance information to guide users in creating a second story based on the topic; the display module 630 is further configured to display the guidance information.

[0128] In some embodiments, the display module 630 is further configured to display the second story in response to user input of the content of the second story; and to share the second story to one or more distribution scenarios in response to user sharing operation of the second story.

[0129] In some embodiments, the extraction module 610 is configured to segment the content of a story fragment in the first story to determine multiple segments; and to determine the theme and keywords of the story fragment based on the clustering results of the multiple segments.

[0130] It should be noted that the above-described units (modules) are logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above-described units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the units shown in the accompanying drawings with dashed lines indicate that these units may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0131] In addition, although not shown, the device may also include a memory that can store various information generated by the device and its constituent units during operation, programs and data used for operation, data to be transmitted by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in a manner known in the art, such as including communication components such as antenna arrays and / or radio frequency links, various types of interfaces, communication units, etc. These will not be described in detail here. Furthermore, the device may also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, etc. These will not be described in detail here.

[0132] Some embodiments of this disclosure also provide an electronic device. Figure 7 shows a block diagram of some embodiments of the electronic device of this disclosure. For example, in some embodiments, the electronic device 70 can be various types of devices, such as mobile terminals including, but not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 70 may include a display panel for displaying data and / or execution results utilized in the scheme according to this disclosure. For example, the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a planar panel, but also a curved panel, or even a spherical panel.

[0133] As shown in FIG. 7, the electronic device 70 of this embodiment includes a memory 71 and a processor 72 coupled to the memory 71. It should be noted that the components of the electronic device 70 shown in FIG. 7 are merely exemplary and not limiting; the electronic device 70 may also have other components depending on the actual application requirements. The processor 72 can control other components in the electronic device 70 to perform desired functions.

[0134] In some embodiments, memory 71 is used to store one or more computer-readable instructions. When processor 72 executes the computer-readable instructions, the computer-readable instructions are executed by processor 72 to implement the method according to any of the above embodiments. For specific implementations and related explanations of the various steps of the method, please refer to the above embodiments; repeated details will not be elaborated here.

[0135] For example, processor 72 and memory 71 can communicate with each other directly or indirectly. For example, processor 72 and memory 71 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. Processor 72 and memory 71 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0136] For example, processor 72 can be embodied in various suitable processors, processing devices, such as central processing unit (CPU), graphics processing unit (GPU), network processor (NP), etc.; it can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The central processing unit (CPU) can be an x86 or ARM architecture, etc. For example, memory 71 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Memory 71 can include, for example, system memory, which stores, for example, the operating system, application programs, boot loader, database, and other programs. Various application programs and various data can also be stored in the storage medium.

[0137] Furthermore, according to some embodiments of this disclosure, various operations / processes according to this disclosure, implemented via software and / or firmware, can install programs constituting the software from a storage medium or network onto a computer system with a dedicated hardware architecture, such as the computer system (or electronic device) 80 shown in FIG. 8. When various programs are installed, the computer system is capable of performing various functions, including those described above. FIG. 8 is a block diagram illustrating an example structure of a computer system that may be employed in an embodiment of this disclosure.

[0138] In Figure 8, the Central Processing Unit (CPU) 801 performs various processes based on a program stored in the Read-Only Memory (ROM) 802 or a program loaded from the Storage Section 808 into the Random Access Memory (RAM) 803. The RAM 803 also stores data required as needed when the CPU 801 performs various processes. The CPU is merely exemplary and can be other types of processors, such as the various processors described above. The ROM 802, RAM 803, and Storage Section 808 can be various forms of computer-readable storage media, as described below. It should be noted that although the ROM 802, RAM 803, and Storage Section 808 are shown separately in Figure 8, one or more of them can be combined or located in the same or different memories or storage modules.

[0139] CPU 801, ROM 802 and RAM 803 are interconnected via bus 804. Input / output interface 805 is also connected to bus 804.

[0140] The following components are connected to the input / output interface 805: input section 806, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 807, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 808, including hard disks, magnetic tapes, etc.; and communication section 809, including network interface cards such as LAN cards, modems, etc. The communication section 809 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the computer system 80 shown in Figure 8 communicate via bus 804, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and / or any combination of wireless and wired networks.

[0141] As needed, drive 810 is also connected to input / output interface 805. Removable media 811, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 810 as needed, so that computer programs read from them can be installed into storage section 808 as needed.

[0142] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as removable media 811.

[0143] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the CPU 801, it performs the functions defined in the methods of embodiments of this disclosure.

[0144] It should be noted that, in the context of this disclosure, a computer-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 computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0145] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0146] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the content processing method of any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0147] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0149] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0150] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0151] According to some embodiments of this disclosure, a content processing method is provided, including: extracting the main idea and keywords of a story fragment from a first story; generating a topic based on the content, main idea, and keywords of the story fragment, wherein the topic is used to guide users to create a second story related to the topic; and displaying the topic.

[0152] In some embodiments, there are multiple keywords. Generating topics based on the content, theme, and keywords of a story fragment includes: determining the relevance of each keyword among the multiple keywords to the content of the story fragment; and generating topics based on the theme, the multiple keywords, and the relevance of each keyword to the content of the story fragment.

[0153] In some embodiments, generating topics based on the theme, multiple keywords, and the relevance of each keyword to the content of the story segment includes: generating prompts based on the theme, multiple keywords, and the relevance of each keyword to the content of the story segment; and generating topics based on the prompts using a machine learning model.

[0154] In some embodiments, the prompt information includes one or more constraints, which include at least one of the following: constraints on the relevance of the topic to the theme, constraints on the relevance of the topic to the content of the story segment, constraints on the relevance of the topic to the characters in the story segment, constraints on the form of the topic, and constraints on the number of topics.

[0155] In some embodiments, generating topics using a machine learning model based on prompts includes: using a machine learning model to select one or more target keywords from multiple keywords based on prompts, and generating topics based on the content and theme of the story fragment, one or more target keywords, and one or more constraints.

[0156] In some embodiments, generating topics based on the content, theme, and keywords of a story fragment includes: generating multiple candidate topics based on the content, theme, and keywords of the story fragment; and selecting a preset number of candidate topics as topics based on the relevance of the multiple candidate topics to the content of the story fragment.

[0157] In some embodiments, the content processing method further includes: determining the relevance between the content of the topic and the story segment; and adjusting the topic in response to the relevance between the content of the topic and the story segment being lower than a first threshold.

[0158] In some embodiments, adjusting a topic includes: determining the relevance of the topic to a character in a story segment; and adjusting the topic based on character information in the story segment in response to the relevance of the topic to a character in the story segment being lower than a second threshold.

[0159] In some embodiments, adjusting a topic includes: determining the relevance of the topic to a location in a story segment; and adjusting the topic based on location information in the story segment in response to the relevance of the topic to a location in the story segment being lower than a third threshold.

[0160] In some embodiments, the content processing method further includes: determining the matching degree between the topic and the attribute information of the user group of the first story; and adjusting the topic according to the attribute information of the user group of the first story in response to the matching degree between the topic and at least one attribute information of the user group of the first story being lower than the matching degree threshold.

[0161] In some embodiments, the content processing method further includes: determining the sentiment tendency of a topic, adjusting the sentiment tendency of the topic in response to the topic being negative; and / or determining the viewpoint of a topic, adjusting the viewpoint of the topic in response to the viewpoint of the topic not conforming to a preset standard.

[0162] In some embodiments, the content processing method further includes: generating guidance information based on the topic to guide users in creating a second story; and displaying the guidance information.

[0163] In some embodiments, the content processing method further includes: displaying the second story in response to user input of the content of the second story; and sharing the second story to one or more distribution scenarios in response to user sharing of the second story.

[0164] In some embodiments, extracting the theme and keywords of a story segment based on the content of the story segment in the first story includes: segmenting the content of the story segment in the first story into words to determine multiple word segments; and determining the theme and keywords of the story segment based on the clustering results of the multiple word segments.

[0165] According to some other embodiments of this disclosure, a content processing apparatus is provided, comprising: an extraction module configured to extract the theme and keywords of a story fragment based on the content of a story fragment in a first story; a generation module configured to generate a topic based on the content, theme, and keywords of the story fragment, wherein the topic is used to guide users to create a second story related to the topic; and a display module configured to display the topic.

[0166] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions, which, when executed by the processor, cause the processor to perform a content processing method according to any embodiment of the present disclosure.

[0167] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the content processing method of any embodiment of the present disclosure.

[0168] According to some further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the content processing method of any embodiment of the present disclosure.

[0169] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the content processing method of any embodiment of the present disclosure.

[0170] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0171] Many specific details are set forth in the description provided herein. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of the description.

[0172] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0173] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A content processing method, comprising: Based on the content of the story fragments in the first story, extract the main theme and keywords of the story fragments; Based on the content of the story fragment, the theme, and the keywords, a topic is generated, wherein the topic is used to guide users to create a second story related to the topic; The topic is displayed.

2. The content processing method according to claim 1, wherein, The keywords are multiple, and the generation of topics based on the content of the story fragment, the main theme, and the keywords includes: Determine the relevance of each keyword among the plurality of keywords to the content of the story segment; The topic is generated based on the theme, the multiple keywords, and the relevance of each keyword to the content of the story segment.

3. The content processing method according to claim 2, wherein, The process of generating the topic based on the theme, the multiple keywords, and the relevance of each keyword to the content of the story segment includes: Based on the main theme, the multiple keywords, and the relevance of each keyword to the content of the story segment, a prompt message is generated; The topic is generated based on the prompt information using a machine learning model.

4. The content processing method according to claim 3, wherein, The prompt information includes one or more constraints, which include at least one of the following: the relevance of the topic to the theme, the relevance of the topic to the content of the story segment, the relevance of the topic to the characters in the story segment, the form of the topic, and the number of topics.

5. The content processing method according to claim 4, wherein, The process of generating the topic based on the prompt information using the machine learning model includes: Using the machine learning model, one or more target keywords are selected from the plurality of keywords based on the prompt information, and the topic is generated based on the content of the story fragment, the theme, the one or more target keywords, and the one or more constraints.

6. The content processing method according to any one of claims 1-5, wherein, The generation of topics based on the content of the story fragment, the main theme, and the keywords includes: Based on the content of the story fragment, the main theme, and the keywords, multiple candidate topics are generated; Based on the relevance of the multiple candidate topics to the content of the story fragment, a preset number of candidate topics are selected as the topics.

7. The content processing method according to any one of claims 1-6, further comprising: Determine the relevance of the topic to the content of the story segment; In response to the topic's relevance to the story segment's content falling below a first threshold, the topic is adjusted.

8. The content processing method according to claim 7, wherein, The adjustment to the topic includes: Determine the relevance of the topic to the characters in the story segment; In response to the topic's relevance to the characters in the story segment being below a second threshold, the topic is adjusted based on the character information in the story segment.

9. The content processing method according to claim 7 or 8, wherein, The adjustment to the topic includes: Determine the relevance of the topic to the locations in the story segment; In response to the fact that the relevance of the topic to the location in the story segment is lower than a third threshold, the topic is adjusted based on the location information in the story segment.

10. The content processing method according to any one of claims 1-9, further comprising: Determine the degree of match between the topic and the attribute information of the user group of the first story; In response to the fact that the matching degree between the topic and at least one attribute of the user group of the first story is lower than the matching degree threshold, the topic is adjusted according to the attribute information of the user group of the first story.

11. The content processing method according to any one of claims 1-10, further comprising: Determine the sentiment tendency of the topic, and adjust the sentiment tendency of the topic in response to the negative sentiment tendency of the topic; and / or If a viewpoint on a given topic is determined, and the viewpoint on that topic does not meet a preset standard, the viewpoint on that topic is adjusted.

12. The content processing method according to any one of claims 1-11, further comprising: Based on the topic, generate guidance information to guide the user in creating the second story; The guidance information is displayed.

13. The content processing method according to any one of claims 1-12, further comprising: In response to the user's input of the content of the second story, the second story is displayed; In response to the user's sharing action on the second story, the second story is shared to one or more... Distribution scenario.

14. The content processing method according to any one of claims 1-13, wherein, The extraction of the main theme and keywords from story fragments in the first story includes: The content of the story fragments in the first story is segmented into words to determine multiple segmentation words; Based on the clustering results of the multiple word segments, the main theme and keywords of the story fragment are determined.

15. A content processing apparatus, comprising: The extraction module is configured to extract the main idea and keywords of the story fragments from the first story; The generation module is configured to generate a topic based on the content of the story fragment, the theme, and the keywords, wherein the topic is used to guide users to create a second story related to the topic; The display module is configured to display the topic.

16. An electronic device comprising: processor; as well as A memory coupled to the processor is used to store instructions that, when executed by the processor, cause the processor to perform the content processing method as described in any one of claims 1-14.

17. A computer-readable storage medium having a computer program stored thereon, wherein, When executed by a processor, the program implements the content processing method according to any one of claims 1-14.

18. A computer program product comprising: Instructions, wherein when executed by a processor, the instructions implement the content processing method according to any one of claims 1-14.

19. A computer program comprising: Instructions, wherein when executed by a processor, the instructions implement the content processing method according to any one of claims 1-14.

Images