Content generation method and apparatus, device, medium, and product

Abstract

One or more embodiments of this document provide a content generation method, apparatus, device, medium, and product. The content generation method includes: receiving a first operation triggered in a first document, the first operation being associated with a first content block in the first document; in response to the document content of the first document satisfying a first material recommendation condition, the first operation satisfying a second material recommendation condition, and the first content block containing at least a portion of document content that needs improvement, obtaining first recommended material, the first recommended material being associated with at least a portion of the document content; and sending the first recommended material to the operator of the first operation. The method determines whether material recommendation should be performed for the first content block from three dimensions: document content, the first operation, and the first content block associated with the first operation. This ensures the necessity and rationality of material recommendation, allowing for material recommendation at appropriate times. This helps users improve document editing efficiency while reducing the impact of frequent material recommendations on the user's document editing process.

Description

Technical Field

[0001] One or more embodiments herein relate to a content generation method, content generation apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] A document processing system can be understood as a software system used to manage documents. Users can use the document processing system to perform document-related operations, such as creating documents, editing documents, and viewing documents.

[0003] When users are editing documents using a document processing system, it is especially important to help them improve their editing efficiency at the right time. 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] At least one embodiment of this document provides a content generation method, comprising: receiving a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document; in response to the document content of the first document satisfying a first material recommendation condition, the first operation satisfying a second material recommendation condition, and the first content block having at least a portion of document content that needs to be improved, obtaining a first recommended material, wherein the first recommended material is related to the at least a portion of the document content; and sending the first recommended material to the operator of the first operation.

[0006] At least one embodiment of this document provides a content generation apparatus, comprising: a receiving module configured to: receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document; an obtaining module configured to: obtain first recommended material in response to the document content of the first document satisfying a first material recommendation condition, the first operation satisfying a second material recommendation condition, and the first content block containing at least a portion of document content that needs to be improved, wherein the first recommended material is related to the at least a portion of document content; and a sending module configured to: send the first recommended material to the operator of the first operation.

[0007] At least one embodiment of this document provides an electronic device, including: at least one processor; and at least one memory, including one or more computer program instructions; wherein the one or more computer program instructions are executed by the processor to perform the content generation method provided by at least one embodiment of this document.

[0008] At least one embodiment of this document provides a computer-readable storage medium for non-transitory storage of computer-readable instructions, wherein the content generation method provided by at least one embodiment of this document is implemented when the computer-readable instructions are executed by a processor.

[0009] At least one embodiment of this document provides a computer program product, including a computer program that, when executed by a processor, implements the content generation method provided in at least one embodiment of this document.

[0010] In a content generation method provided in at least one embodiment of this paper, in a document editing scenario, a user can trigger a first operation. The method determines whether material recommendations should be made for the first content block based on three dimensions: document content, the first operation, and the first content block associated with the first operation. When it is determined that material recommendations are needed for the first content block, recommended materials are obtained and sent to the user. Since the recommended materials are related to the document content to be improved in the first content block, the user can use the recommended materials to improve the document content of the first content block, such as supplementing incomplete document content or modifying document content that needs updating. Thus, when automatically recommending materials needed for document editing to the user, a multi-dimensional judgment is performed first to ensure the necessity and rationality of the material recommendations. Material recommendations are made at appropriate times, helping users improve document editing efficiency while reducing the impact of frequent material recommendations on the user's document editing process. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0012] Figure 1 This illustration schematically depicts an application scenario of a content generation method provided in at least one embodiment of this paper.

[0013] Figure 2 The illustration shows a flowchart of a content generation method provided in at least one embodiment of this document;

[0014] Figure 3 The illustration shows a schematic diagram of a first document provided in at least one embodiment of this document;

[0015] Figure 4 The schematic diagram illustrates a structural schematic of a content generation apparatus provided in at least one embodiment of this document; and

[0016] Figure 5A schematic diagram of the structure of an electronic device suitable for implementing at least one embodiment of the present invention is shown. Detailed Implementation

[0017] One or more embodiments of this document will now be described in more detail with reference to the accompanying drawings. While some embodiments of this document are shown in the drawings, it should be understood that this document can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided to provide a more thorough and complete understanding of this document. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of this document.

[0018] It should be understood that the steps described in the method embodiments herein may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this document is not limited in this respect.

[0019] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this article are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions performed by these devices, modules or units or their interdependencies.

[0021] It should be noted that the terms "one" and "more" used in this document 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".

[0022] The names of the messages or information exchanged between the various devices in the embodiments herein are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0023] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0024] It is understood that before using the technical solutions disclosed in the embodiments of this article, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this article and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means. Relevant users may include any type of rights holder, such as individuals, enterprises, or groups.

[0025] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of any embodiment of the present document based on the prompt message.

[0026] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0027] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation method described in this article. Other methods that comply with relevant laws and regulations may also be applied to the implementation method described in this article.

[0028] A document processing system can be understood as a software system used to manage documents. It is widely used in various scenarios such as office work, study, and creation. Users can use the document processing system to perform document-related operations, such as creating, editing, and viewing documents.

[0029] When users edit documents using a document processing system, they often need to use some materials to edit the document content. For example, users need to manually collect the necessary materials and then combine the collected materials to edit the document in the document processing system.

[0030] Taking the example of a user editing a technical introduction document for technology A in a document processing system, the user needs to search for materials related to technology A from different channels such as the internal document library and the Internet, organize the materials related to technology A, and then input the document content into the technical introduction document for technology A.

[0031] However, the above methods require users to manually collect and integrate materials, which takes up a lot of time in the material preparation process and reduces the user's document editing efficiency.

[0032] To at least partially solve the above-mentioned technical problem, at least one embodiment of this paper provides a content generation method, the method comprising: receiving a first operation triggered in a first document, the first operation being associated with a first content block in the first document; in response to the document content of the first document satisfying a first material recommendation condition, the first operation satisfying a second material recommendation condition, and the first content block containing at least a portion of document content that needs to be improved, obtaining a first recommended material, the first recommended material being related to at least a portion of the document content, and sending the first recommended material to the operator of the first operation.

[0033] Based on the content generation method provided in at least one embodiment of this document, at least one embodiment of this document also provides a content generation apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0034] In a content generation method provided in at least one embodiment of this paper, in a document editing scenario, a user can trigger a first operation. The method determines whether material recommendations should be made for the first content block based on three dimensions: document content, the first operation, and the first content block associated with the first operation. When it is determined that material recommendations are needed for the first content block, recommended materials are obtained and sent to the user. Since the recommended materials are related to the document content to be improved in the first content block, the user can use the recommended materials to improve the document content of the first content block, such as supplementing incomplete document content or modifying document content that needs updating. Thus, when automatically recommending materials needed for document editing to the user, a multi-dimensional judgment is performed first to ensure the necessity and rationality of the material recommendations. Material recommendations are made at appropriate times, helping users improve document editing efficiency while reducing the impact of frequent material recommendations on the user's document editing process.

[0035] The following detailed description, with reference to the accompanying drawings, describes one or more embodiments and some examples thereof.

[0036] Figure 1 The illustration shows an application scenario diagram of a content generation method provided in at least one embodiment of this article.

[0037] like Figure 1 As shown, the application scenario provided in this embodiment may include user 101, terminal device 102, and server 103. Terminal device 102 can be various electronic devices capable of providing interactive pages, such as smart wearable devices, smart appliances, smart cars, mobile phones, tablets, laptops, or desktop computers.

[0038] In one or more embodiments of this document, a client may be installed in the terminal device 102. The client may be a client of a document processing system. The server 103 may be a server that provides support for the operation of the client installed in the terminal device 102. That is, the server 103 may be a server of a document processing system. For example, the server 103 may be a server for a local area network or a wide area network, or a cloud server, etc. The one or more embodiments of this document do not limit this.

[0039] User 101 can be a user of a client installed on terminal device 102. For example, user 101 can be an editor who edits documents, a viewer who views documents, or a commenter who makes comments on documents in a document processing system.

[0040] In one or more embodiments described herein, the document processing system can be deployed in different ways. In some embodiments, the document processing system can be deployed locally, for example, it can be a document processing application (APP), document processing tool, document processing plugin, etc., installed on terminal device 102; or, for example, it can be deployed in the cloud, that is, it can provide document management services in the form of cloud services, for example, it can be an online document processing tool. Furthermore, the document processing system can be integrated into other systems, providing document processing functions as a functional module within those systems. For example, it can be integrated into an office collaboration system, providing document processing services (e.g., cloud document processing services) within that system.

[0041] The server 103 can communicate with the terminal device 102, for example, by providing the client installed on the terminal device 102 with relevant data (such as document content) required by the terminal device to run the client; or, for example, the server 103 can also receive relevant data returned by the terminal device 102 during the running of the client (such as operation data on the document triggered by user 101 on the client).

[0042] For example, the content generation methods provided in one or more embodiments of this document can be implemented in software, hardware, firmware, or any combination thereof.

[0043] For example, the content generation method provided in one or more embodiments of this document is applicable to a terminal device, which can load and execute the content generation method. The embodiments of this document do not limit this. For example, the terminal device may include a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), neural network processing unit (NPU), or other forms of processing units with data processing capabilities and / or instruction execution capabilities, storage units, etc. The server or terminal device may also have an operating system and various types of application programming interfaces (APIs) installed, implementing the content generation method provided in the embodiments of this document by running code or instructions.

[0044] The following will combine Figure 2 and Figure 3 A content generation method provided in at least one embodiment of this document will be described in detail.

[0045] Figure 2 The illustration shows a flowchart of a content generation method provided in at least one embodiment of this document.

[0046] like Figure 2 As shown, the content generation method of this embodiment includes steps S201 to S203. In some embodiments, the execution entity for content generation can be an electronic device with a client deployed, an electronic device with a server deployed, or any electronic device that communicates between the client and the server; one or more embodiments herein do not limit this. The steps included in this content generation method are described below:

[0047] Step S201: Receive the first operation triggered in the first document.

[0048] In one or more embodiments herein, the first document may be understood as any document, for example, the first document may be a document that is currently open and being viewed.

[0049] By dividing the first document in terms of structural logic, the first document is divided into at least one content block. That is, the first document may include one or more content blocks. A content block can be understood as a document section. A content block corresponds to at least a continuous portion of the document content in the first document. For example, the first document may include multiple subheadings. The document content under a subheading can form a content block. Or, for example, the first document may include a table. At least one adjacent area in the table can form a content block.

[0050] In one or more embodiments of this document, a user is supported in triggering a first operation within a first document. The first operation is associated with a first content block within the first document, and the first content block can be any content block among one or more content blocks included in the first document. In other words, when a user processes the first document (e.g., edits the document), they can trigger the first operation associated with the first content block.

[0051] Step S202: In response to the fact that the document content of the first document meets the first material recommendation conditions, the first operation meets the second material recommendation conditions, and the first content block contains at least some document content that needs to be improved, obtain the first recommended material.

[0052] In one or more embodiments of this document, the first operation may be related to material recommendation. For example, the first operation may be used to initiate a decision process on whether to perform material recommendation.

[0053] In some embodiments, considering that document type may affect the effectiveness of material recommendation, the process of determining whether to recommend materials can be started only for some documents based on document type.

[0054] For example, obtain the first document type corresponding to the first document, and in response to the first document type matching the set of document types, start the process of determining whether to recommend materials.

[0055] Document type can be used to represent the characteristics of document content. For example, document type can be periodically updated document, technical related document, creative document, etc. The first document type can be understood as the document type of the first document. The set of document types can include multiple document types. The multiple document types in the set of document types can be understood as document types that need to start the judgment process of whether to perform material recommendation.

[0056] By obtaining the first document type corresponding to the first document, it is determined whether the first document type belongs to the set of document types. If the first document type matches the set of document types, the process of determining whether to recommend materials is initiated; if the first document type does not match the set of document types, the process of determining whether to recommend materials is not initiated is not required.

[0057] For example, the document type set can include periodically updated documents and technology-related documents. Periodically updated documents can be understood as documents that are updated and maintained periodically, such as weekly reports and quarterly meeting documents. Since writing periodically updated documents usually requires the use of external materials, the document type set can include periodically updated documents. Technology-related documents can be understood as documents related to technology, such as technical introduction documents and product manuals. Since writing technology-related documents usually requires the use of external materials, the document type set can include technology-related documents.

[0058] In this way, by pre-configuring a set of document types, the system can filter out a subset of documents from which the material recommendation process needs to be enabled, and enable the material recommendation process only in these documents whose document types match the set of document types, rather than enabling it in all documents. This saves computing resources and improves the efficiency of material recommendation.

[0059] In one or more embodiments of this document, the first document type corresponding to the first document can be obtained in different ways. For example, in response to the document type associated with the first document being non-empty, the first document type associated with the first document can be obtained, or in response to the document type associated with the first document being empty, the first document type corresponding to the first document can be obtained based on at least one of the document title of the first document and the content of the first document in the first document.

[0060] The fact that the document type associated with the first document is not empty can be understood as the first document belonging to a document whose document type has been marked. For example, within a historical time period, the first document type corresponding to the first document is obtained, and the obtained first document type is associated with the first document. For a first document that has already been marked with a document type, the first document type corresponding to the first document can be obtained directly based on the document type associated with the first document.

[0061] If the document type associated with the first document is empty, it can be understood that the first document belongs to a category of documents that have not been tagged with a document type. For example, the first document is a newly created document, and its document type has not been retrieved within the historical time period, meaning the first document is not associated with any document type. For a first document that has not been tagged with a document type, the corresponding first document type can be retrieved by combining at least one of the document title and document content. In addition, the first document type can be associated with the first document; that is, the first document can be tagged after its document type is retrieved for the first time.

[0062] In this way, after obtaining the first document type corresponding to the first document, the document type of the first document is marked by associating the first document with the first document type. When it is necessary to obtain the document type of the first document in the future, if the first document has already been associated with a document type, there is no need to repeat the step of obtaining the document type of the first document, thereby improving the efficiency of obtaining the document type of the first document and thus improving the efficiency of material recommendation.

[0063] Considering that frequently recommending materials to users during the editing of the first document would negatively impact their normal document editing experience and waste computing resources, in one or more embodiments of this paper, it is determined whether to recommend materials to users based on three dimensions: the document content of the first document, the first operation, and the first content block. When the document content of the first document meets the first material recommendation conditions, the first operation meets the second material recommendation conditions, and the first content block contains at least some content that needs to be improved, it is determined that it is necessary to recommend materials for the first content block.

[0064] The first material recommendation criteria can be used to describe the document content of the first document that needs to be recommended. For example, the document content of the first document may include the document title and the document body. The document title can be understood as the name of the first document, and the document body can be understood as the document content that already exists in the first document when the first operation is triggered. In this case, whether the document content of the first document meets the first material recommendation criteria can be obtained in the following way: in response to the document title not being empty, the document body not being empty, and the document body including the set characters, it is determined that the document content of the first document meets the first material recommendation criteria.

[0065] A document title that is not empty can be understood as the first document having a name that is not the default. A document body that is not empty can be understood as the first document having document content and not being a blank document. A document body that includes a set character can be understood as the first document having a set character. The set character can be used to divide content blocks. For example, the set character can be a newline character.

[0066] In other words, the first material recommendation condition can be that the document title is not empty, the document body is not empty, and the document body includes the specified characters. When the document content of the first document meets the first material recommendation condition, it indicates that it is necessary to recommend materials for the first content block in the document content dimension.

[0067] Since the purpose of material recommendation is to recommend materials that can help improve document writing efficiency to users, the recommended materials should match the user's document editing needs. If the first document has an empty title, an empty body, or does not contain the specified characters, it is difficult to extract effective information from the first document, make it difficult to determine the user's document editing needs, and thus it is difficult to recommend materials that can effectively improve document editing efficiency to the user.

[0068] By determining whether the content of the first document meets the first material recommendation criteria, if the content of the first document meets the first material recommendation criteria, that is, if effective information (such as the document title and document body) can be extracted from the first document and the content of the first document can be divided into blocks (such as obtaining the first content block), then material recommendation will be considered to ensure the effectiveness of material recommendation.

[0069] The second material recommendation condition can be used to describe the first operation that requires material recommendation. In some embodiments, the first content block is associated with at least one operator identifier, and the operator of the first operation corresponds to the first operator identifier. In this case, whether the first operation meets the second material recommendation condition can be obtained in the following way: in response to the first content block being associated with at least one operator identifier including the first operator identifier and the first operation being used to perform at least one operation in a set of defined operations, it is determined that the first operation meets the second material recommendation condition.

[0070] In other words, the second material recommendation condition can be at least one operator identifier associated with the first content block, including the first operator identifier, and the first operation is used to perform at least one operation in the set of defined operations.

[0071] The first operator identifier can be the account name of the operator of the first operation. For example, in some document processing systems, it is supported to mention the account name in the document. For example, mentioning the account name can clarify the task owner and the communication object. In this case, the first content block is associated with at least one operator identifier. This can be because the content block body of the first content block includes at least one operator identifier (e.g., the account name of at least one operator), or the document body of the first document indicates that at least one operator identifier is associated with the first content block (e.g., indicating that the account name of at least one operator is the task owner of the first content block).

[0072] When at least one operator identifier associated with the first content block includes the first operator identifier, it indicates that the first content block is related to the operator of the first operation, and the operator of the first operation may need to edit the first content block. When the first operation is used to execute at least one operation in the set of operations, it indicates that the first operation is an operation for recommending materials. By judging whether the first operation meets the second material recommendation conditions, if the first operation meets the second material recommendation conditions, that is, the triggered first operation is used for recommending materials, and the first content block associated with the first operation is related to the operator of the first operation, then material recommendation is considered, to ensure that the timing of triggering the first operation is the appropriate time for recommending materials, and that materials related to the operator of the first operation (i.e., the first content block) can be recommended in a targeted manner.

[0073] For example, the set of operations may include at least one of the following operations: an operation to open a first document, and an operation to move to a first content block.

[0074] In other words, one or more embodiments of this paper can recommend materials at different times in a document editing scenario. When the operator of the first operation opens the first document, since at least one operator identifier associated with the first content block includes the first operator identifier, it can be directly determined that the operator of the first operation needs to edit the first content block and needs to recommend materials for the first content block. When the operator of the first operation moves to the first content block, since at least one operator identifier associated with the first content block includes the first operator identifier, and the first operation indicates that the operator of the first operation has the intention to process the first content block, it can be determined that the operator of the first operation needs to edit the first content block and needs to recommend materials for the first content block.

[0075] For example, content block A in the first document includes a first operator identifier. When the operator of the first operation triggers the first operation by opening the first document, it is determined that the first operation meets the second material recommendation criteria. When the operator of the first operation triggers the first operation by moving to content block A, it is determined that the first operation meets the second material recommendation criteria.

[0076] In this way, by combining the common operations involved in users' actual document editing, a set of operations is pre-configured. By judging whether the first operation is an operation in the set of operations, it is determined whether the current time is appropriate to recommend materials. When the first operation belongs to the set of operations, it indicates that the operator of the first operation has an editing need for the first content block. Materials are recommended to the operator of the first operation in a timely manner to ensure the timeliness of material recommendations.

[0077] In other embodiments, whether the first operation satisfies the second material recommendation criteria can be determined as follows: in response to the first operation being used to edit the first content block, the first operation satisfies the second material recommendation criteria.

[0078] The first operation used to edit the first content block can be understood as an editing operation triggered within the first content block. In other words, when it is determined that the first operation is used to edit the first content block, it indicates that the operator of the first operation has an editing need for the first content block. At this time, if the operator of the first operation can be promptly recommended materials for the first content block, it will help the operator of the first operation to edit the first content block efficiently. Therefore, if the first operation meets the second material recommendation condition, material recommendation can be considered.

[0079] Considering that one or more embodiments of this paper recommend materials, recommending materials when there is no document content to be improved in the first content block would lead to a waste of computing resources. Therefore, it is also possible to determine whether there is at least some document content to be improved in the first content block, that is, to determine whether the document content of the first content block is complete, or to determine whether the document content of the first content block needs to be updated.

[0080] For example, if the first content block has a content block title and includes the content block body, in this case, whether the first content block has at least some document content that needs to be improved can be determined as follows: in response to the content block title being non-empty and the content block body including incomplete content, it is determined that the first content block has at least some document content that needs to be improved.

[0081] A non-empty content block title can be understood as the first content block having a content block title. For example, the document content of the first content block contains document content that belongs to the content block title. Incomplete content in the content block body can be understood as the document content of the first content block being empty, incomplete, or needing to be updated.

[0082] Since the title of a content block usually reflects the theme of the content block, by analyzing the title of the first content block, we can determine the content block body that the first content block should include, that is, the complete content that the first content block should include. If the content block title is empty, we cannot obtain the content block body that the first content block should include, and therefore we cannot determine whether the first content block has at least some document content that needs to be improved.

[0083] By analyzing the content block titles and content block text, the complete content corresponding to the first content block is obtained based on the content block titles. Then, the complete content corresponding to the first content block is compared with the content block text to determine whether the content block text includes incomplete content, and thus determine whether the first content block contains at least some document content that needs to be improved.

[0084] Thus, only after determining that at least some document content in the first content block needs improvement should we consider recommending materials, ensuring the necessity of material recommendations and reducing the computational resources consumed by unnecessary material recommendations.

[0085] In some possible implementations, artificial intelligence models are used to automatically determine whether the content block body contains incomplete content. For example, whether the content block body contains incomplete content can be determined as follows: the content block title and content block body are sent to a first model, and the output of the first model is used to determine whether the content block body contains incomplete content.

[0086] The first model can be understood as any artificial intelligence model with the ability to recognize element information. For example, the first model can include any one or a combination of multiple large-scale models such as language models, speech models, vision models, and multimodal models. For example, the first model can be a model built on a transformer architecture, a model built on a recurrent neural network, a model built on an attention mechanism, etc. Alternatively, the first model can also be a model obtained by improving on the transformer architecture, such as a mixture of experts (MoE) model.

[0087] One or more embodiments in this paper do not limit the method of obtaining the first model. For example, the first model can be an existing, open-source artificial intelligence model. Alternatively, the first model can be an artificial intelligence model obtained by fine-tuning the pre-trained artificial intelligence model based on the pre-trained artificial intelligence model and using training data related to the judgment of the content block body (such as the judgment results of other content block titles, other content block body and other content blocks).

[0088] The first model can generate judgment results based on prompt learning. Prompt words can be used to guide the artificial intelligence model to make specific outputs in generative tasks (such as text generation, question answering, and dialogue tasks). By configuring prompt words, the artificial intelligence model can understand the background and requirements of the task. This allows the artificial intelligence model to handle different types of processing tasks without retraining, increasing the scalability and flexibility of the artificial intelligence model.

[0089] For example, a first prompt word is generated, which may include: the content block title, the content block body, and prompt information used to indicate whether the content block body contains incomplete content based on the content block title, so as to generate a judgment result. The first prompt word is sent to the first model, and the output of the first model is received (e.g., the output result includes the judgment result). Based on the output of the first model (e.g., information extraction from the output of the first model), it is determined whether the content block contains incomplete content.

[0090] By sending the first prompt word to the first model, the first model can analyze the complete content that should be included under the title of the content block, and then determine whether the body of the content block includes the complete content, thereby generating a judgment result. This achieves automatic determination of whether the body of the content block is complete, improving the automation and efficiency of the determination of the completeness of the body of the content block.

[0091] As mentioned above, the content block title is particularly important for determining whether there is at least some content in the first content block that needs to be improved. In some embodiments, the content block title can be obtained by identifying multi-level titles related to the first content block, which may include the first title in the first content block and at least one parent title associated with the first title, and concatenating the multi-level titles to obtain the content block title.

[0092] In other words, considering the accuracy of content block titles, in one or more embodiments of this paper, not only is the first title in the first content block identified, but also the higher-level parent titles associated with the first content block are identified. By splicing, the content block titles include multi-level titles from broad to narrow scope, ensuring the semantic coherence and accuracy of the content block titles.

[0093] In this way, by splicing multi-level headings, the accurate content block title of the first content block can be obtained. Based on the accurate content block title of the first content block, the accurate and complete content of the content block body can be obtained, thereby improving the accuracy of the content block body completeness judgment.

[0094] One or more embodiments of this document support different methods for identifying multi-level headings, such as identifying multi-level headings related to a first content block, including: identifying multi-level headings related to a first content block based on the table of contents information of a first document.

[0095] In other words, some first documents may include table of contents information, which can characterize the content structure information of the first document, such as multiple levels of headings. By identifying the table of contents information of the first document, the first heading can be found in the table of contents information of the first document. Then, by combining the structure of the table of contents information of the first document, at least one superior heading associated with the first heading can be determined, and multi-level headings related to the first content block can be obtained.

[0096] For example, the table of contents of the first document includes a first-level heading A1, second-level headings B1 and B2, and third-level headings C1, C2 and C3 under second-level heading B1. The first heading in the first content block is C2. Then, at least one parent heading associated with the first heading can include B1 and A1, and the content block title can be "A1—B1—C2".

[0097] For example, identifying multi-level headings related to the first content block includes: obtaining the first table in the first document that includes the first content block, identifying the first table according to the hierarchical relationship of the first table, and obtaining multi-level headings related to the first content block.

[0098] In other words, some first documents may include tables, and the row and column relationships in the tables can represent the content structure information of the first document, such as the hierarchical relationship between different contents. By identifying the table content in the first table, the first title in the first table can be found, and then, combined with the hierarchical relationship of the first table, at least one superior title associated with the first title can be determined, thus obtaining multi-level titles related to the first content block.

[0099] Figure 3 A schematic diagram of a first document provided in at least one embodiment of this document is shown.

[0100] For example, such as Figure 3 As shown, the first document may include a first table, which may include four columns: the first column represents "Product," the second column represents "Module," the third column represents "Responsible Person," and the fourth column represents "Progress." Figure 3 In the first document shown, when the operator of the first operation is user B, since the third column and third row of the first table includes user B's account name, that is, the identifier of the first operator, the first content block associated with the first operation is the content block corresponding to the fourth column and fourth row of the first table. That is, user B needs to edit the document for the fourth column and fourth row of the first table.

[0101] In this case, the first title is "Evaluation Set Construction" corresponding to the third row of the second column, the parent title associated with the first title is "AI-Generated Weekly Report" corresponding to the third row of the first column, and the content block title can be "AI-Generated Weekly Report - Evaluation Set Construction".

[0102] Thus, based on the actual document content included in the first document, different methods can be flexibly selected to identify multi-level headings related to the first content block. Through the hierarchical relationship of the table or table, the first heading and its associated parent headings can be accurately identified, so that the multi-level headings can accurately describe the complete content that the first content block should include.

[0103] After judging the document content, the first operation, and the first content block, if all three judgments indicate that it is necessary to recommend materials for the first content block, that is, if the timing of triggering the first operation is a suitable time to recommend materials for the first content block, then the first recommended material is obtained.

[0104] In one or more embodiments of this document, recommended materials can be understood as material information used to assist in editing document content. The first recommended material can be related to at least part of the document content to be improved in the first content block. The at least part of the document content to be improved can be understood as lacking at least part of the document content or having at least part of the document content that needs to be updated. That is, the first recommended material can be used to assist the operator of the first operation in editing the at least part of the document content that is missing in the first content block, or the first recommended material can be used to assist the operator of the first operation in editing the at least part of the document content that needs to be updated in the first content block.

[0105] For example, the first content block should include five document contents from (1) to (5). The first content block is missing two document contents from (3) and (4). The document contents from (5) in the first content block need to be updated. The first recommended material is related to the three document contents from (3) to (5) and can be used to assist the operator of the first operation in editing the three document contents from (3) to (5) in the first content block.

[0106] The first recommended material can include material information in different forms, such as text material information, video material information, image material information, audio material information, file material information, etc.

[0107] In some embodiments, considering that the first recommended material is used to assist the operator of the first operation in editing the first content block, the first recommended material provided to the operator of the first operation should all be material information that the operator of the first operation has access to. By combining the access rights of the operator of the first operation to generate the first recommended material, it is ensured that the material information included in the first recommended material is in line with the access rights of the operator of the first operation, thereby reducing the impact of recommending first recommended material that is not within the access rights of the operator of the first operation.

[0108] One or more embodiments of this document do not limit the method of generating the first recommended material. For example, since it is necessary to recommend materials for at least part of the document content that needs to be improved in the first content block, the first recommended material can be generated by searching from at least one data source corresponding to the first document type based on the first content block.

[0109] For example, for the first document, which is a periodically updated document, since periodically updated documents need to be updated and maintained periodically, and the material information for updating and maintaining periodically updated documents is usually scattered in different functional modules of the office collaboration system, at least one data source corresponding to the periodically updated document can include different functional modules of the office collaboration system, such as instant messaging module, meeting module, document module, etc. Based on the information in different functional modules of the office collaboration system, the first recommended material is generated.

[0110] For the first document, which is a technical document, since technical documents are related to technology and the material information for editing technical documents usually exists in Internet resources or other materials, at least one data source corresponding to the technical document can include the Internet and internal knowledge bases, such as online search engines. Based on the information in the Internet and internal knowledge bases, the first recommended material is generated.

[0111] For example, based on the first information associated with the first content block, a search is performed in at least one data source corresponding to the first document type to obtain candidate materials, and the candidate materials are integrated to generate the first recommended material.

[0112] One or more embodiments in this paper do not limit the method of integrating candidate materials. For example, candidate materials are sent to a second model, and the first recommended material is determined based on the output of the second model.

[0113] For example, the first model and the second model can be the same artificial intelligence model. In other embodiments, the first model and the second model can also be different artificial intelligence models. One or more embodiments herein do not limit this.

[0114] One or more embodiments in this paper do not limit the method of obtaining the second model. For example, the second model can be an existing, open-source artificial intelligence model. Alternatively, the second model can be an artificial intelligence model obtained by fine-tuning the pre-trained artificial intelligence model based on the pre-trained artificial intelligence model using training data related to the generation of recommendation materials (such as other candidate materials, recommendation materials corresponding to other candidate material information, etc.).

[0115] The second model can generate the first recommended material based on prompt learning. For example, it can generate a second prompt word and send the second prompt word to the second model. The second prompt word may include candidate materials and prompt information for integrating candidate materials to form recommended materials. The second prompt word is sent to the second model, and the output of the second model is received (e.g., output results that include instructions for recommending materials). Based on the output of the second model (e.g., information extraction from the output of the second model), the first recommended material is determined.

[0116] By sending the second prompt word to the second model, the second model can analyze the content of the candidate materials and organize them into recommended materials, thereby outputting the first recommended material. This achieves automatic generation of the first recommended material without requiring the first operator to manually organize the candidate materials.

[0117] In some embodiments, considering the accuracy and efficiency of generating the first recommended material, candidate materials can be filtered to remove some of them. For example, candidate materials can be filtered based on at least one of their source and update time, retaining at least a portion of them.

[0118] Unreserved candidate materials may include at least one of the following: candidate materials from the first document, candidate materials from multiple historical documents, and candidate materials whose time period does not match that of the first document. Multiple historical documents include documents corresponding to the first document in multiple historical update cycles. The time period corresponding to the first document is obtained through the document title of the first document or the update cycle of the first document.

[0119] Candidate materials from the first document can be understood as document content belonging to the first document. For the first document currently being edited, the document content inside the first document has low reference value for the document editing of the first document. Therefore, candidate materials from the first document are filtered out.

[0120] Candidate materials from multiple historical documents can be understood as the document content of the first document in multiple historical update cycles. Since the document content of historical documents belongs to different update cycles than the first document, the document content of historical documents has low reference value for the editing of the first document. Therefore, candidate materials from multiple historical documents are filtered out.

[0121] The time period corresponding to the first document can be obtained from the document title. For example, if the document title of the first document is "Project Progress Update from January 1st to January 7th", then the time period corresponding to the first document can be from January 1st to January 7th. The time period corresponding to the first document can also be obtained from the update cycle of the first document. For example, if the update cycle of the first document is one week and the end time of the previous update cycle is December 31st, then the time period corresponding to the first document can be from January 1st to January 7th.

[0122] Candidate materials that do not match the time period corresponding to the first document can be understood as candidate materials whose update time is outside the time period corresponding to the first document. Since the update time of the above candidate materials does not match the time period corresponding to the first document, the above candidate materials have low reference value for the editing of the first document. Therefore, candidate materials that do not match the time period corresponding to the first document will be filtered out.

[0123] In this way, by filtering and screening the candidate materials, only those materials that have reference value and learning value for at least part of the document content to be improved in the first content block are retained, thereby reducing the number of candidate materials and improving the generation efficiency of the first recommended material.

[0124] For example, the first recommended material may include one or more of the following: information related to the first document and the first content block, detailed information about the recommended material, and source information about the recommended material. The information related to the first document and the first content block helps the operator of the first operation to quickly understand the document and content block corresponding to the first recommended material. The detailed information about the recommended material helps the operator of the first operation to quickly determine whether the recommended material is available. The source information about the recommended material helps the operator of the first operation to view the original text of the recommended material and verify its authenticity.

[0125] Furthermore, considering that during the editing process of the first content block, the first recommended material may change as the document content input by the operator of the first operation changes, the first recommended material is updated in response to the second operation triggered in the first content block and the second operation meets the material update condition. This second operation can be used to trigger the judgment logic of whether to update the first recommended material.

[0126] On one hand, the second operation can be understood as an operation to trigger a new material recommendation process. For example, the third operation can be an operation to input a set character, which can be a newline character. When the operator of the first operation inputs a newline character in the first content block, a new material recommendation process can be triggered. In this case, since the operator of the first operation has input new document content in the first content block, at least part of the document content to be improved in the first content block has changed. Therefore, the first recommended material will also change. By triggering a new material recommendation process, the first recommended material is updated, and the recommended material is updated to the operator of the first operation in real time, so that the first recommended material is updated in real time with the current document editing content of the operator of the first operation.

[0127] On the other hand, configuring material update conditions involves determining whether the third operation meets the material update conditions. If the conditions are met, the first recommended material is then updated. For example, when the second operation is inputting a set character, the material update condition could be the length of the content between two adjacent set characters in the first content block compared to a set threshold. For instance, the threshold could be 50 characters. This means determining the length of the content input by the operator in the first operation between two material recommendation processes. If the length of the content between two adjacent set characters in the first content block is less than the set threshold, it indicates that the operator in the first operation did not edit much content after the previous material recommendation process. If a new material recommendation process is triggered at this time, the difference between the first recommended materials in the two adjacent material recommendation processes will be small, and the excessively frequent material recommendations will negatively impact the document editing experience of the operator in the first operation.

[0128] In this way, by detecting the second operation triggered in the first content block and determining whether the second operation meets the material update conditions, the first recommended material is provided to the operator of the first operation in real time without affecting the document editing experience, thereby further enhancing the correlation between the first recommended material and the part of the document content that needs to be improved in the first content block.

[0129] Step S203: Send the first recommended material to the operator of the first operation.

[0130] By determining whether to recommend materials and obtaining the first recommended material when it is necessary, the first recommended material is provided as response data for the first operation to the operator of the first operation. For example, the first recommended material is sent to the client installed on the terminal device used by the operator of the first operation so that the first recommended material can be rendered and displayed on the terminal device used by the operator of the first operation.

[0131] In some embodiments, considering that the operator of the first operation may trigger the first operation multiple times, in order to ensure the effectiveness of the material recommendation and reduce the provision of first recommended materials with poor availability to the operator of the first operation, it may also be determined whether the first recommended material needs to be provided to the operator of the first operation. For example, sending the first recommended material to the operator of the first operation includes: in response to the historical recommended material corresponding to the first content block being empty, or in response to the historical recommended material corresponding to the first content block being different from the first recommended material, sending the first recommended material to the operator of the first operation.

[0132] Historical recommended materials can be understood as recommended materials sent to the first operator within a historical time period. In other words, if no recommended materials were sent to the first operator within a historical time period (i.e., no material recommendations were made for the first content block), or if recommended materials were sent to the first operator within a historical time period but were different from the first recommended materials (i.e., the recommended materials for the first content block were updated), it indicates that the first recommended materials have recommendation significance for the first operator, and the first recommended materials are sent to the first operator.

[0133] Thus, by adding a step to determine whether the first recommended material needs to be provided to the first operator before sending the first recommended material to the first operator, the duplicate material recommendations caused by sending the same recommended material to the first operator are reduced, ensuring the real-time nature of material recommendations.

[0134] In one or more embodiments of this document, the first recommended material can provide multifaceted assistance to the operator of the first operation in the document editing scenario of the first content block. For example, sending the first recommended material to the operator of the first operation includes any one of the following: sending the first recommended material to the operator of the first operation so that the first recommended material is presented to the operator of the first operation at a first position associated with the first content block, or sending the first recommended material to the operator of the first operation so that the second document content generated based on the first recommended material is presented to the operator of the first operation in the first content block.

[0135] The first position associated with the first content block can be understood as a position that is related to the location of the first content block. For example, the first position associated with the first content block could be above the first content block.

[0136] On the one hand, the first recommended material can be directly pushed to the operator of the first operation. By presenting the first recommended material to the operator, the operator can view the first recommended material and use it to edit at least some of the document content that needs to be improved in the first content block. For example, the operator can write at least some of the missing document content in the first content block, or modify at least some of the document content that needs to be updated in the first content block. On the other hand, the first recommended material can also be used to generate second document content. The second document content can be at least some of the missing document content in the first content block, or at least some of the updated document content in the first content block. By presenting the second document content to the operator of the first operation, the operator does not need to manually edit the document, thus realizing the automatic continuation or automatic rewriting of the first content block.

[0137] In this way, by judging from three dimensions—document content, the first operation itself, and the content blocks associated with the first operation—before recommending materials, the first recommended material is obtained and sent to the first operation when it is necessary, and materials are recommended to users at the appropriate time, thereby improving document writing efficiency.

[0138] Based on the content generation method provided in at least one embodiment of this document, at least one embodiment of this document also provides a content generation apparatus. The following will be combined with... Figure 4 A detailed description of the content generation device is provided.

[0139] Figure 4 The schematic diagram illustrates a structural schematic of a content generation apparatus provided in at least one embodiment of this document.

[0140] like Figure 4As shown, the content generation apparatus 400 of this embodiment includes a receiving module 401, an acquisition module 402, and a sending module 403. For example, the receiving module 401, the acquisition module 402, and the sending module 403 can be implemented using hardware (e.g., circuit) modules or software modules. The following embodiments are similar and will not be described again. For example, the receiving module 401, the acquisition module 402, and the sending module 403 can be implemented using a central processing unit (CPU), a general-purpose graphics processor (GPGPU), a graphics processing unit (GPU), a tensor processor (TPU), a field-programmable gate array (FPGA), or other processing units with data processing capabilities and / or instruction execution capabilities, along with corresponding computer instructions.

[0141] The receiving module 401 is configured to receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document. For example, the receiving module 401 can be configured to execute step S201 described above; its specific implementation principle can be found in the relevant description of step S201, and will not be repeated here.

[0142] The acquisition module 402 is configured to: in response to the document content of the first document satisfying the first material recommendation condition, the first operation satisfying the second material recommendation condition, and the first content block containing at least a portion of document content that needs improvement, acquire the first recommended material, wherein the first recommended material is related to the at least a portion of the document content. For example, the acquisition module 402 can be configured to execute step S202 described above; its specific implementation principle can be found in the relevant description of step S202, and will not be repeated here.

[0143] The sending module 403 is configured to send the first recommended material to the operator of the first operation. For example, the sending module 403 can be configured to execute step S203 described above. The specific implementation principle can be found in the relevant description of step S203, and will not be repeated here.

[0144] In at least one embodiment of this document, the document content of the first document includes a document title and a document body; the acquisition module 402 is further configured to determine whether the document content of the first document meets the first material recommendation conditions by: in response to the document title being non-empty, the document body being non-empty, and the document body including a set character, determining that the document content of the first document meets the first material recommendation conditions.

[0145] In at least one embodiment of this document, the first content block is associated with at least one operator identifier, and the operator of the first operation corresponds to the first operator identifier; the acquisition module 402 is further configured to determine whether the first operation satisfies the second material recommendation condition by: in response to the fact that the at least one operator identifier associated with the first content block includes the first operator identifier and the first operation is used to perform at least one operation in a set of defined operations, determining that the first operation satisfies the second material recommendation condition.

[0146] In at least one embodiment of this document, the set of settings includes at least one of the following operations: an operation for opening the first document, and an operation for moving to the first content block.

[0147] In at least one embodiment of this document, the acquisition module 402 is further configured to determine whether the first operation satisfies the second material recommendation condition by means of the first operation being used to edit the first content block, wherein the first operation satisfies the second material recommendation condition.

[0148] In at least one embodiment of this document, the first content block corresponds to a content block title, and the first content block includes content block body text; the acquisition module 402 is further configured to determine whether the first content block has at least some document content that needs to be improved by: in response to the content block title being not empty and the content block body text including incomplete content, determining that the first content block has the at least some document content that needs to be improved.

[0149] In at least one embodiment of this document, the acquisition module 402 is further configured to determine whether the content block text includes incomplete content by sending the content block title and the content block text to a first model, and determining whether the content block text includes incomplete content based on the output of the first model.

[0150] In at least one embodiment of this document, the acquisition module 402 is further configured to obtain the content block title by: identifying multi-level titles related to the first content block, wherein the multi-level titles include a first title in the first content block and at least one parent title associated with the first title; and concatenating the multi-level titles to obtain the content block title.

[0151] In at least one embodiment of this document, the acquisition module 402 is further configured to: identify multi-level headings related to the first content block based on the directory information of the first document; or acquire a first table in the first document that includes the first content block, and identify the first table based on the hierarchical relationship of the first table to obtain multi-level headings related to the first content block.

[0152] In at least one embodiment of this document, the acquisition module 402 is further configured to: update the first recommended material in response to a second operation triggered in the first content block and the second operation satisfying the material update condition, wherein the second operation is used to trigger the judgment logic of whether to update the first recommended material.

[0153] In at least one embodiment of this document, the sending module 403 is further configured to: send the first recommended material to the operator of the first operation so that the first recommended material is presented to the operator of the first operation at a first position associated with the first content block; or send the first recommended material to the operator of the first operation so that second document content generated based on the first recommended material is presented to the operator of the first operation in the first content block.

[0154] It should be noted that, for clarity and brevity, at least one embodiment herein does not show all the constituent units of the content generation apparatus 400. To achieve the necessary functions of the content generation apparatus 400, those skilled in the art may provide or configure other constituent units (not shown) according to specific needs, and one or more embodiments herein do not impose any limitations on this.

[0155] At least one embodiment of this document also provides an electronic device, including a processing device and a storage device, the storage device including one or more computer program modules; wherein the one or more computer program modules are stored in the storage device and configured to be executed by the processing device, the one or more computer program modules being used to implement the content generation method provided in any embodiment of this document.

[0156] For example, the processing device may be a processor, such as a central processing unit (CPU), digital signal processor (DSP), image processor (GPU), general-purpose graphics processor (GPGPU), or other form of processing unit with data processing capabilities and / or instruction execution capabilities. It may be a general-purpose processor or a dedicated processor and may control other components in the electronic device to perform the desired functions.

[0157] For example, the storage device may be a memory, and may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processing device may execute the program instructions to implement the functions (implemented by the processing device) in at least one embodiment herein and / or other desired functions. Various application programs and various data may also be stored in the computer-readable storage medium, which is not limited by one or more embodiments herein.

[0158] The following is for reference. Figure 5 This document illustrates a structural schematic of an electronic device (e.g., a terminal device or a server) 500 suitable for implementing at least one embodiment of this document. The terminal device in at least one embodiment of this document may include, but is 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 and desktop computers. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of at least one embodiment herein.

[0159] like Figure 5 As shown, electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of electronic device 500. Processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0160] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0161] In particular, according to one or more embodiments herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, one or more embodiments herein include a computer program product comprising a computer program carried on a non-transitory 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 communication device 509, or installed from storage device 508, or installed from ROM 502. When the computer program is executed by processing device 501, it performs the functions defined in the methods of at least one embodiment herein.

[0162] It should be noted that the computer-readable medium described above can be a computer-readable signal medium, 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 document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this document, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit 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 can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0163] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0164] 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.

[0165] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned content generation method.

[0166] Computer program code for performing the operations described herein may be written in one or more programming languages ​​or a combination thereof, including but 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 may execute 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 may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0167] One or more embodiments of this document also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in any embodiment of this document are generated.

[0168] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0169] When the computer program product is executed by a computer, the computer performs any of the aforementioned content generation methods. The computer program product can be a software installation package; when any of the aforementioned content generation methods is required, the computer program product can be downloaded and executed on the computer.

[0170] 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 herein. 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 the 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, may 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.

[0171] The units or modules described in at least one embodiment herein can be implemented in software or hardware. The names of the units or modules do not, in some cases, constitute a limitation on the unit or module itself.

[0172] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, 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.

[0173] In the context of this document, 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.

[0174] According to one or more embodiments of this document, Example 1 provides a content generation method, including:

[0175] Receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document;

[0176] In response to the fact that the document content of the first document meets the first material recommendation criteria, the first operation meets the second material recommendation criteria, and the first content block contains at least some document content that needs to be improved, a first recommended material is obtained, wherein the first recommended material is related to the at least some document content;

[0177] Send the first recommended material to the operator of the first operation.

[0178] According to one or more embodiments of this document, Example 2 provides the document content of the first document in Example 1, including a document title and a document body; whether the document content of the first document meets the first material recommendation criteria is obtained in the following way:

[0179] In response to the document title being non-empty, the document body being non-empty, and the document body including the specified characters, it is determined that the document content of the first document meets the first material recommendation conditions.

[0180] According to one or more embodiments of this document, Example 3 provides that the first content block in Example 1 is associated with at least one operator identifier, and the operator of the first operation corresponds to the first operator identifier; whether the first operation satisfies the second material recommendation condition is obtained in the following way:

[0181] In response to the fact that at least one operator identifier associated with the first content block includes the first operator identifier and the first operation is used to perform at least one operation in a set of defined operations, it is determined that the first operation satisfies the second material recommendation condition.

[0182] According to one or more embodiments of this document, Example 4 provides the set of settings in Example 3 including at least one of the following operations: an operation for opening the first document, and an operation for moving to the first content block.

[0183] According to one or more embodiments of this document, Example 5 provides a method to determine whether the first operation in Example 1 satisfies the second material recommendation condition in the following way:

[0184] In response to the first operation for editing the first content block, the first operation satisfies the second material recommendation criteria.

[0185] According to one or more embodiments of this document, Example Six provides a first content block in Example One that corresponds to a content block title, and the first content block includes the content block body; whether the first content block has at least some document content that needs to be improved is determined in the following way:

[0186] In response to the content block title being non-empty and the content block body containing incomplete content, it is determined that the first content block contains at least a portion of the document content that needs to be improved.

[0187] According to one or more embodiments of this document, Example 7 provides a method for determining whether the content block text in Example 6 includes incomplete content in the following way:

[0188] The content block title and the content block body are sent to the first model. Based on the output of the first model, it is determined whether the content block body includes incomplete content.

[0189] According to one or more embodiments of this document, Example 8 provides that the content block title in Example 6 is obtained as follows:

[0190] Identify multi-level headings associated with the first content block, wherein the multi-level headings include a first heading in the first content block and at least one parent heading associated with the first heading;

[0191] By concatenating the multi-level headings, the content block heading is obtained.

[0192] According to one or more embodiments of this document, Example Nine provides the identification of multi-level headings associated with the first content block as in Example Eight, including:

[0193] Based on the table of contents information of the first document, identify the multi-level headings related to the first content block; or

[0194] Obtain the first table in the first document that includes the first content block, and identify the first table according to the hierarchical relationship of the first table to obtain multi-level headings related to the first content block.

[0195] According to one or more embodiments of this document, Example 10 provides a method from any of Examples 1 through 9, and further includes:

[0196] In response to a second operation triggered in the first content block and the second operation satisfying the material update condition, the first recommended material is updated, wherein the second operation is used to trigger the judgment logic for whether to update the first recommended material.

[0197] According to one or more embodiments of this document, Example 11 provides sending the first recommended material to the operator of the first operation in any of Examples 1 to 9, including any one of the following:

[0198] Send the first recommended material to the operator of the first operation, so that the first recommended material is presented to the operator of the first operation at a first position associated with the first content block; or

[0199] The first recommended material is sent to the operator of the first operation so that the second document content generated based on the first recommended material is presented to the operator of the first operation in the first content block.

[0200] According to one or more embodiments herein, Example Twelve provides a content generation apparatus, comprising:

[0201] The receiving module is configured to receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document;

[0202] The acquisition module is configured to: in response to the document content of the first document satisfying the first material recommendation conditions, the first operation satisfying the second material recommendation conditions, and the first content block containing at least some document content that needs to be improved, acquire the first recommended material, wherein the first recommended material is related to the at least some document content;

[0203] The sending module is configured to send the first recommended material to the operator of the first operation.

[0204] According to one or more embodiments herein, Example Thirteen provides an electronic device comprising:

[0205] At least one processor; and

[0206] At least one memory, including one or more computer program instructions;

[0207] The one or more computer program instructions are executed by a processor at runtime using the content generation method provided in at least one embodiment of this document.

[0208] According to one or more embodiments herein, Example Fourteen provides a computer-readable storage medium that non-transitory stores computer-readable instructions, wherein the computer-readable instructions, when executed by a processor, implement the content generation method provided in at least one embodiment herein.

[0209] According to one or more embodiments herein, Example Fifteen provides a computer program product including a computer program that, when executed by a processor, implements the content generation method provided in at least one embodiment of this document.

[0210] The above description is merely a preferred embodiment and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure herein 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-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed herein that have similar functions.

[0211] 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 sequential order. Multitasking and parallel processing may be advantageous in certain environments. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this document. Certain features described in the context of a single embodiment 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.

[0212] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A content generation method, comprising: Receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document; In response to the fact that the document content of the first document meets the first material recommendation criteria, the first operation meets the second material recommendation criteria, and the first content block contains at least some document content that needs to be improved, the first recommended material is obtained, wherein the first recommended material is related to the at least some document content; Send the first recommended material to the operator of the first operation.

2. The method according to claim 1, wherein, The document content of the first document includes a document title and a document body; Whether the content of the first document meets the first material recommendation criteria is determined in the following way: In response to the document title being non-empty, the document body being non-empty, and the document body including the specified characters, it is determined that the document content of the first document meets the first material recommendation conditions.

3. The method according to claim 1, wherein, The first content block is associated with at least one operator identifier, and the operator of the first operation corresponds to the first operator identifier; Whether the first operation satisfies the second material recommendation criteria is determined as follows: In response to the fact that at least one operator identifier associated with the first content block includes the first operator identifier and the first operation is used to perform at least one operation in a set of defined operations, it is determined that the first operation satisfies the second material recommendation condition.

4. The method according to claim 3, wherein, The set of settings includes at least one of the following operations: an operation to open the first document, and an operation to move to the first content block.

5. The method according to claim 1, wherein, Whether the first operation satisfies the second material recommendation criteria is determined as follows: In response to the first operation for editing the first content block, the first operation satisfies the second material recommendation criteria.

6. The method according to claim 1, wherein, The first content block has a corresponding content block title, and the first content block includes the content block body; Whether the first content block contains at least some document content that needs to be improved is determined in the following way: In response to the content block title being non-empty and the content block body containing incomplete content, it is determined that the first content block contains at least a portion of the document content that needs to be improved.

7. The method according to claim 6, wherein, Whether the content block text includes incomplete content is determined in the following way: The content block title and the content block body are sent to the first model. Based on the output of the first model, it is determined whether the content block body includes incomplete content.

8. The method according to claim 6, wherein, The content block title is obtained in the following way: Identify multi-level headings associated with the first content block, wherein the multi-level headings include a first heading in the first content block and at least one parent heading associated with the first heading; By concatenating the multi-level headings, the content block heading is obtained.

9. The method according to claim 8, wherein, The identification of multi-level headings related to the first content block includes: Based on the table of contents information of the first document, identify the multi-level headings related to the first content block; or Obtain the first table in the first document that includes the first content block, and identify the first table according to the hierarchical relationship of the first table to obtain multi-level headings related to the first content block.

10. The method according to any one of claims 1 to 9, further comprising: In response to a second operation triggered in the first content block and the second operation satisfying the material update condition, the first recommended material is updated, wherein the second operation is used to trigger the judgment logic for whether to update the first recommended material.

11. The method according to any one of claims 1 to 9, wherein, Sending the first recommended material to the operator of the first operation includes any one of the following: Send the first recommended material to the operator of the first operation, so that the first recommended material is presented to the operator of the first operation at a first position associated with the first content block; or The first recommended material is sent to the operator of the first operation so that the second document content generated based on the first recommended material is presented to the operator of the first operation in the first content block.

12. A content generation apparatus, comprising: The receiving module is configured to receive a first operation triggered in a first document, wherein the first operation is associated with a first content block in the first document; The acquisition module is configured to: in response to the document content of the first document satisfying the first material recommendation conditions, the first operation satisfying the second material recommendation conditions, and the first content block containing at least some document content that needs to be improved, acquire the first recommended material, wherein the first recommended material is related to the at least some document content; The sending module is configured to send the first recommended material to the operator of the first operation.

13. An electronic device, comprising: At least one processor; as well as At least one memory, including one or more computer program instructions; The one or more computer program instructions are executed by the processor to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium for non-transitory storage of computer-readable instructions, wherein, The method of any one of claims 1 to 11 is implemented when the computer-readable instructions are executed by a processor.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 11.

Images