Method, apparatus, device and storage medium for template creation

Abstract

Embodiments of the present disclosure provide a template creation method, apparatus, device and storage medium to create a target template for document generation. In the method, a template creation instruction for a target template is received. Structure information of the target template is presented, the structure information indicating a document structure generated based on the template creation instruction. The target template is created based on at least corresponding configuration information of one or more document parts included in the target template. According to the scheme of the present disclosure, the structure of the template is first generated according to the creation requirement. The creator of the template is allowed to configure each part to be included in the document, i.e. the creator is allowed to finely adjust the template. In this way, it can be ensured that the generated template is consistent with the expectation of the creator, thereby improving the efficiency of the document generation by the user of the template.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and more particularly to methods, apparatus, devices, and computer-readable storage media for template creation. Background Technology

[0002] Currently, machine learning models can be used to generate text content. By training on large amounts of text data, machine learning models learn language rules and patterns, thus automatically generating new text content. Such machine learning models have been widely applied in content creation, data analysis, and other fields, providing users with convenient and efficient text generation services. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for creating a template is provided. The method includes: receiving a template creation instruction for a target template, the target template being used for document generation; presenting structural information of the target template, the structural information indicating a document structure generated based on the template creation instruction; and creating the target template based at least on corresponding configuration information of one or more document portions included in the target template.

[0004] In a second aspect of this disclosure, an apparatus for template creation is provided. The apparatus includes: a receiving module configured to receive a template creation instruction for a target template, the target template being used for document generation; a rendering module configured to render structural information of the target template, the structural information indicating a document structure generated based on the template creation instruction; and a creation module configured to create the target template based at least on corresponding configuration information of one or more document portions included in the target template.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0008] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0010] Figure 2 A schematic diagram of an example interface for initiating template creation according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic diagram of an example interface for presenting structural information according to some embodiments of the present disclosure is shown;

[0012] Figure 4A A schematic diagram is shown for presenting an example interface for a selected data source according to some embodiments of the present disclosure;

[0013] Figure 4B A schematic diagram of an example interface for updating content description information according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A schematic diagram of an example interface for selecting a knowledge base according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic diagram of an entry interface for a user to specify a data object is shown according to some embodiments of the present disclosure;

[0016] Figure 7 A schematic diagram of an example interface for skill selection according to some embodiments of the present disclosure is shown;

[0017] Figure 8 A schematic diagram of an example interface for configuring dependencies according to some embodiments of the present disclosure is shown;

[0018] Figure 9A A schematic diagram illustrating an example of an entry interface for receiving document preview information according to some embodiments of the present disclosure is shown;

[0019] Figure 9B A schematic diagram of another example of an entry interface for receiving document preview information according to some embodiments of the present disclosure is shown;

[0020] Figure 9C A schematic diagram illustrating an example of an interface for presenting a preview document according to some embodiments of the present disclosure is shown;

[0021] Figure 9DA schematic diagram of another example of an interface for presenting a preview document according to some embodiments of the present disclosure is shown;

[0022] Figure 10 A flowchart illustrating an example process for creating a template according to some embodiments of this disclosure is shown;

[0023] Figure 11 A schematic structural block diagram of an example apparatus for template creation according to some embodiments of the present disclosure is shown; and

[0024] Figure 12 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0025] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0026] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0027] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0028] 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.

[0029] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0030] 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 the technical solution disclosed herein based on the prompt message.

[0031] 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.

[0032] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure. The activation of digital assistant-related functions, the acquisition of data, the processing and storage of data, etc., in the embodiments of this disclosure shall all require prior authorization from the user and other rights holders associated with the user, and shall comply with the agreements and rules between relevant laws and regulations and rights holders.

[0033] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0034] As used in this text, the term "document" refers to material used to record information. In some embodiments, a document can be an electronic document in any suitable format, such as a document on a web page, a Word document, a Portable Document Format (PDF) document, etc. In embodiments of this disclosure, a document can have any suitable type of content, including but not limited to text, tables, images, formulas, etc.

[0035] As used herein, the term "document section" can refer to a portion of a document used to organize its content. Depending on the specific implementation, document sections can have different granularities. For example, a document section can be a chapter. Or, a document section can be a paragraph. Furthermore, although all are called document sections, multiple document sections within the same document can have a hierarchy. For example, one document section can be a level below another document section. A document section can have headings, body text, and optional supplementary text (e.g., comments, footnotes, etc.). In particular, if document section A is a level below document section B, then document section A can be considered at least a portion of the body text of document section B.

[0036] As used in this article, "document template" or "template" can refer to an electronic, computer-processable file that describes how to generate the document.

[0037] As briefly described above, machine learning models can be applied to content creation, data analysis, and other fields. In one approach, service providers can leverage machine learning models to offer services such as document generation to users (e.g., enterprise users). In this approach, the machine learning model freely generates documents based on its learned knowledge. However, in some scenarios (e.g., in enterprise-facing scenarios), users may have similar or uniform requirements for a certain type of document. In such scenarios, if the machine learning model generates documents freely, users may need to spend considerable time and effort modifying the generated documents. This undoubtedly reduces the efficiency of document generation.

[0038] In view of this, embodiments of the present disclosure provide a template creation scheme for creating a target template for document generation. In this scheme, a template creation instruction for the target template is received. Structural information of the target template is presented, indicating the document structure generated based on the template creation instruction. The target template is created based at least on corresponding configuration information of one or more document portions included in the target template.

[0039] The following description will make it clearer that, according to the scheme disclosed herein, the template structure is first generated based on the creation requirements. The template creator can use the configuration generated according to the creation requirements, and can also configure the various parts that the document will include, thus allowing the creator to fine-tune the template. In this way, it can be ensured that the generated template matches the creator's expectations, thereby improving the efficiency of document generation for template users.

[0040] Example Environment

[0041] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 relates to an application management platform 110, which can support the creation and / or execution of applications. In some embodiments, the portion of the application management platform 110 used to support application creation may also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 used to support application execution may also be referred to as an application execution portion.

[0042] As shown in the figure, the application creation section provides an environment for user 105 to create and publish applications. User 105 can be referred to as the application creation user or creator. In some embodiments, the application creation section can be a low-code platform that provides a collection of tools for application creation. The application creation section can support visual development of various types of applications, allowing developers to skip the manual coding process and accelerate the application development cycle and reduce costs. The application creation section can support any suitable platform for users to develop one or more types of applications, such as an application platform as a service (aPaaS) based platform. Such a platform enables users to efficiently develop applications, enabling operations such as application creation and application function adjustment.

[0043] The application creation component can be deployed locally on user 105's terminal device and / or supported by a server device. For example, user 105's terminal device can run a client with the application creation component, which can support interaction between the user and the application creation component provided by the server. When the application creation component runs locally on the user's terminal device, user 105 can directly interact with the local application creation component using the terminal device. When the application creation component runs on a server device, the server device can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application creation component can present a corresponding interface 130 to user 105 based on user 105's operations, to output and / or receive application creation-related information from user 105.

[0044] In some embodiments, the application creation section may be associated with a corresponding database, which stores the data or information required for the application creation process supported by the application creation section. For example, the database may store the code and description information corresponding to the various functional modules that make up the application. The application creation section can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database may also store operations that can be performed on different functional blocks. For example, in a scenario where an application needs to be created, the application creation section can call the corresponding functional blocks from the database to build the application.

[0045] In embodiments of this disclosure, user 105 can create and publish target application 120 as needed in the application creation section. Target application 120 can be published to any suitable application runtime section, as long as the application runtime section can support the operation of target application 120. After publication, target application 120 can be operated by one or more end users 145. End user 145 can operate target application 120 through an associated terminal device 146 and thereby interact with application management platform 110. End user 145 can be referred to as the end user of target application 120. In some embodiments, target application 120 may include or be implemented as digital assistant 122.

[0046] Digital Assistant 122 can be configured to have intelligent conversational capabilities. Figure 1 In the example shown, digital assistant 122 can be integrated into target application 120, serving as part of target application 120 to assist in task processing within target application 120. In other examples, digital assistant 122 can be configured to run as a standalone application, such as a web application or other type of application. In such examples, digital assistant 122 and target application 120 can be considered as the same application. Digital assistant 122 is provided to assist users with various task processing needs in different applications and scenarios. During interaction with digital assistant 122, the user inputs interactive messages, and digital assistant 122 responds to the user's input by providing reply messages. Typically, digital assistant 122 can support users inputting questions in natural language and performs tasks and provides replies based on its understanding of natural language input and logical reasoning capabilities.

[0047] In some embodiments, the digital assistant 122 can interact with the end user 145 as a contact. For example, the digital assistant 122 can be implemented in an instant messaging (IM) application. The digital assistant 122 can interact with the end user 145 in a one-on-one chat session. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session that includes multiple users.

[0048] For each end user 145, the client component of the application runtime can display various interfaces of the target application 120 in the client interface. Figure 1The example illustrates an interaction window 142 between end user 145 and digital assistant 122, such as a conversation window with digital assistant 122. End user 145 can enter conversation messages in the conversation window, and target application 120 can determine the response message from digital assistant 122 based on created configuration information and present it to the user in interaction window 142. In some embodiments, depending on the configuration of target application 120, interaction messages with target application 120 may include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and so on.

[0049] Similar to the application creation component, the application runtime component can be deployed locally on each end user's (145's) terminal device and / or supported by a server device. For example, the end user's (145's) terminal device can run a client with the application runtime component, which can support interaction between the user and the application runtime component provided by the server. When the application runtime component runs locally on the user's terminal device, the end user (145) can directly interact with the local application runtime component using the terminal device. When the application runtime component runs on a server device, the server device can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application runtime component can present corresponding application pages to the end user (145) based on the user's (145's) actions, outputting and / or receiving application-related information from the user (145).

[0050] In some embodiments, the implementation of at least some functions of the target application 120, and / or the implementation of at least some functions of the digital assistant 122 within the target application 120, may be based on a machine learning model (hereinafter referred to as a model). During the creation or operation of the target application 120, one or more models 155 may be invoked, such as the capabilities of model 155. In the target application 120, the digital assistant 122 may utilize model 155 to understand user input and respond to user input based on the output of model 155, such as providing a reply to the user input.

[0051] During the creation process, the application management platform 110 needs to use model 155 to test the target application 120 to determine whether the running results of the target application 120 meet expectations. During operation, in response to different operation requests from users of the target application 120, the application operation part may need to use model 155 to determine the response results to users.

[0052] Although shown as independent of the application management platform 110, one or more models 155 may run on the application management platform 110 or other remote servers. In some embodiments, model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). A language model, by learning from a large corpus, is capable of question answering. Model 155 may also be based on other suitable models.

[0053] In some embodiments, the target application 120 may provide writing functionality; for example, the target application 120 may be a writing application or may include a writing component. This writing functionality may be implemented using one or more models 155, and is therefore also referred to as "intelligent writing." In some embodiments, the user 105 may generate or create document templates for writing through the application management platform 110. The created document templates may be distributed to end users 145 of the target application 120. In some embodiments, the application management platform 110 may support a template creation mode from scratch. For example, the user 105 may initiate a template creation process by inputting requirements for the desired template. In some embodiments, the application management platform 110 may support a template creation mode based on existing documents (also known as templates or reference documents). For example, the user 105 may specify an existing document to initiate a template creation process.

[0054] In some embodiments, end user 145 can write, i.e., generate documents, through target application 120. Application management platform 110 can support various suitable document generation modes. In some embodiments, application management platform 110 can support a template-based document generation mode. For example, end user 145 can use a template created and distributed by user 105 to generate a document. In some embodiments, application management platform 110 can support a document generation mode based on an existing document. For example, end user 145 can specify an existing document as a reference to generate a target document. In some embodiments, application management platform 110 can support a document generation mode from scratch. For example, end user 145 can input the requirements of the document to be generated to initiate the document generation process.

[0055] The application management platform 110 can run on suitable electronic devices. These electronic devices can be any type of computing-capable device, including terminal devices or server devices. Terminal devices can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Server devices can include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on. In some embodiments, the application management platform 110 can be implemented based on cloud services.

[0056] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. For example, although a single user interacting with the application creation section and a single user interacting with the application running section are illustrated, in reality multiple users can access application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0057] The following description will detail some exemplary embodiments of this disclosure with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of this disclosure are not limited in this respect.

[0058] The processes described in the embodiments of this disclosure can be implemented on an application management platform, a terminal device with the application management platform installed, and / or a server corresponding to the application management platform. In the examples below, for the sake of discussion, the description is from the perspective of the application management platform, for example... Figure 1The application management platform 110 is shown. The user interface presented by the application management platform 110 can be displayed via the terminal device of user 145, and the application management platform 110 can receive user input via the terminal device of user 145. In some embodiments, user 145 is the end user of the target application 120. It should be understood that the user interface presented by the application management platform 110 can also be displayed via the terminal device of user 105, and the application management platform 110 can also receive user input via the terminal device of user 105. In some embodiments, user 105 is the creator, administrator, or maintainer of the target application 120.

[0059] Example Interaction

[0060] Figures 2 to 9D Example interfaces according to some embodiments of this disclosure are shown. Interfaces 200 to 900D may, for example, be provided by... Figure 1 The application management platform 110 shown is provided.

[0061] User 105 creates a document template for document generation through target application 120. A template creation instruction indicates the template the user expects to generate. For example, the template creation instruction may include a template identifier for the target template (e.g., a template name or a number used to distinguish templates). The template creation instruction may include template description information for the target template, indicating the user's requirements for generating the target template (e.g., the genre of the target template, the document content corresponding to the target template, the application scenario of the target template, etc.). The template creation instruction may also include reference data sources that can be used during the target template generation process. Reference data sources include internal data (e.g., the internal knowledge base of the organization where user 105 belongs), public data (e.g., data obtainable through internet searches), and data objects specified by user 105 (e.g., local or online documents uploaded by user 105). In some embodiments, the template creation instruction may also include template hierarchy, such as an outline hierarchy (e.g., 2-level, 3-level).

[0062] Figure 2 A schematic diagram of an example interface 200 for initiating template creation according to some embodiments of the present disclosure is shown. Figure 2 As shown, user 105's terminal device displays an interface 200 for obtaining template creation instructions. The application management platform 110 can obtain the template creation instructions input by user 105 through the displayed interface 200. For example... Figure 2 As shown, interface 200 includes various interface elements to obtain template creation requirements. For example, Figure 2The document illustrates a template generation control 210, an entry point 211 for obtaining template identification information, an entry point 212 for obtaining template description information, an entry point 213 for selecting a knowledge base, and an entry point 214 for setting the template hierarchy. The template identification component 211 receives the template identifier. The template description information component 212 allows the user to provide the generation requirements for the target template. The knowledge base selection entry point 213 allows the user to select the knowledge base to reference for template creation and document generation. The template hierarchy component 214 determines the hierarchy of the generated target template. If the template generation control 210 is enabled, the application management platform 110 initiates the template creation process to generate the target template based on the template creation instructions obtained by the instruction acquisition component 210.

[0063] refer to Figure 2 The description of providing target creation instructions via interface elements is merely exemplary and not intended to be limiting. User 105 can provide template creation instructions in various suitable ways. In some embodiments, user 105 can provide template creation instructions via voice input or text input, and the template creation instructions input by user 105 can be in the form of natural language. In this way, the target creation process can be further simplified, and the efficiency of target creation and the user experience can be improved. However, it should be understood that this is only an exemplary function and is not intended to be limiting.

[0064] In some embodiments, in response to user 105 initiating a template creation process, application management platform 110 generates the document structure (e.g., template outline) of the target template based on the obtained template creation instructions. For example, target application 120 can determine the outline of the target template using a machine learning model (e.g., a general language model or a trained outline generation model) based on the obtained template description information and template hierarchy information. For example, the template description information indicates that the generated target template is for an industry analysis report, and the template creation instructions have two template hierarchy levels. The generated template outline includes at least industry background, industry status analysis, and industry growth trends, and the template outline is divided into two hierarchy levels. The number of hierarchy levels in the template outline generated by target application 120 is determined based on user input. For example, the outline generation model can be a language model. The template creation instructions can be provided to the outline generation model in the form of prompts to generate the corresponding template outline. The outline can include one or more document sections (e.g., paragraphs or chapters of a document).

[0065] After generating the document structure of the target template, the document structure is presented to the user. Figure 3A schematic diagram of an example interface 300 for presenting a selected data source according to some embodiments of the present disclosure is shown. In interface 300, user 105 can view the document structure of a target template to further enhance user participation in the template generation process. Simultaneously, application management platform 110 can also obtain user feedback on the document structure of the template to adjust the document structure according to user expectations. In this way, the generated document structure can better meet user expectations and improve the quality of the target template. For example, application management platform 110 can utilize interface 300 to obtain user feedback information. Figure 3 As shown, interface 300 includes a navigation area 310 and an editing area 320. In addition, interface 300 also includes a "back" control for returning to the previous interface, a "template settings" control 330 for regenerating the target template, and a document preview control 340.

[0066] Navigation area 310 displays navigation information about the document structure. User 105 can quickly view the document structure using the navigation information displayed in the navigation area. For example... Figure 3 As shown, navigation area 310 displays navigation items corresponding to each document section. For example, navigation item 350 corresponds to the document section "Industry Development Overview". User 105 can change the document section displayed in editing area 320 by triggering navigation area 310 (e.g., clicking). For example, in response to a user's trigger on a target navigation item in navigation area, the application management platform displays the document section corresponding to that target navigation item in editing area 320. For example, the document section can be displayed in an editing item within that document section.

[0067] The editing area 320 is used to receive user 105's interactive operations regarding the document structure, so as to adjust the document structure of the template according to the user's expectations. For example... Figure 3 As shown, the editing area 320 displays editable items corresponding to one or more document sections included in the target template. User 105 can configure the corresponding document sections by interacting with the editable items in the editing area 320. If a user selection operation is received for any editable item in the editing area 320 (e.g., clicking the editable item), one or more interface elements corresponding to the document section of that editable item are displayed in the area corresponding to that editable item. For example, in... Figure 2 The document shows a modification configuration entry 321 for editing a section of the document and a delete control 322 for deleting that section of the document.

[0068] exist Figure 3In the example, interface 300 includes interface elements (such as editable items) in an editing area for interaction with user 105, through which the user modifies the structure and configuration of the template. Alternatively or additionally, in some embodiments, the interface may include or be associated with a text or voice input field. The text or voice input field is used to receive text editing instructions or voice editing instructions provided by user 105. The text editing instructions or voice editing instructions may be in the form of natural language. Application management platform 110 responds to the instructions provided by the user in the form of natural language and updates the configuration information of the document section based on its understanding of the natural language instructions.

[0069] In some embodiments, user 105 can input an update instruction for a specific document section into target application 120 via editing area 320. Application management platform 110 updates the template's structural information (such as text format, text hierarchy, etc.) according to the update instruction. For example, user 105 inputs an update instruction indicating a change in the position of a target document section; application management platform 110 changes the position of the target document section according to the update instruction, thereby updating the target's structural information.

[0070] For example, users can change the position of parts of a document by dragging editable items. For instance, by dragging... Figure 3 Drag the "Industry Supply Chain Analysis" section below the "Industry Consumer Behavior Analysis" section to change the template's structure. Users can click on the editable "Industry Supply Chain Analysis" item and change the document's hierarchy in the pop-up edit menu.

[0071] In some embodiments, the application management platform 110 determines the corresponding configuration information of the document portions included in the target template based on the interaction between the user 105 and the presented structural information. The user 105's interactive operations may include, for example, selection operations (i.e., selecting any editable item) and input operations (i.e., inputting into the interface 300). For the document information presented by the interface 300, the user 105 provides configuration instructions through the presented editing area 320. Based on the configuration instructions provided by the user, the application management platform 110 determines the configuration information corresponding to each document portion. For example, for the first document portion, the user 105 may provide configuration information to the application management platform 110 through the editable items corresponding to the first document portion. The configuration information may include reference data sources corresponding to each document portion, document description information, and dependencies between multiple document portions, etc.

[0072] Figure 4A A schematic diagram of an example interface 400A for presenting a selected data source, according to some embodiments of this disclosure, is shown. Figure 4AAs shown, each editable item in interface 400A has a corresponding modification configuration entry 321 and a delete control 322. For any editable item, its corresponding modification configuration entry 321 can be hidden. In response to user 105's selection operation on the editable item corresponding to the first document portion in the editing area 320 (e.g., clicking the editable item, or moving the cursor to the editable item), the modification configuration entry 321 corresponding to that editable item is presented in interface 400A.

[0073] The application management platform 110 can present the configured data sources for each document section to the user, enabling the user 105 to determine the data source configuration status of the document and improving template creation efficiency. In some embodiments, in response to a user 105's request to view the data source for a target document section, the application management platform 110 presents the configured data sources for that target document section to the user 105. The data source configured for the target document section will be used to generate the content of that target document section. The target document section for which the data source viewing request is requested can be any document section in the target template or the entire target template.

[0074] like Figure 4A As shown, a data source query control 323 is presented in the corresponding area of ​​the editable item in the editing area 320. The icon of the data source query control 323 may include the identifier of the configured data source. User 105 provides a data source query request to the application management platform 110 through interaction with the data source query control 323 (e.g., click operation, etc.). In response to the data source query request for a portion of the target document, the application management platform 110 presents a data source display area 410 to the user. In the data source display area 410, different types of data sources can be presented in categories. For example, the data source display area 410 includes a first area 411 for presenting knowledge bases (e.g., a pet industry analysis knowledge base, a comprehensive market analysis knowledge base) and data objects specified by user 105 (e.g., documents uploaded by user 105) and a second area 412 for presenting public data sources (e.g., internet URL links). For example, a brief description of the data source may also be presented in the data source display area 410 to facilitate identification of the content of the configured data source.

[0075] In some embodiments, to facilitate user configuration, the application management platform 110 may display information about candidate knowledge bases, including a target template, to user 105. The candidate knowledge bases may include knowledge bases that the user set to which user 105 belongs has access to (e.g., knowledge bases maintained by the organization to which user 105 belongs). Further, based on the template creation requirements, knowledge bases related to the template creation requirements can be selected as candidate knowledge bases from all knowledge bases with access permissions. The information presented for the candidate knowledge bases includes the candidate knowledge base's identifier, a summary description of the knowledge base, etc.

[0076] In some embodiments, the application management platform 110 can provide target creation services to multiple members within an organization. To ensure the security of internal data, different data access permissions need to be provided to different members within the organization. For any member within organization A, the internal knowledge base and internal knowledge of organization A in the application management platform 110 cannot be used as a reference data source for the target template. For example, if the member does not have access to knowledge base B, then knowledge base B cannot be used as a reference data source for the target template created by that member. Therefore, upon receiving a knowledge configuration instruction from user 105, the application management platform 110 first determines the data access permissions of user 105. Based on the data access permissions of user 105, it determines the data and knowledge that can be applied to the template created by user 105. Subsequently, it displays information including candidate knowledge bases that can be used for the target template to user 105 for selection.

[0077] In some embodiments, the content description information generated by the machine learning model may not accurately reflect the user's expectations for a portion of the document. Therefore, user 105 can adjust the content description information. Application management platform 110 can update the content description information based on the received user input regarding the content description information. Figure 4B A schematic diagram of an interface 400B for updating content description information according to some embodiments of the present disclosure is shown. Figure 4B As shown, interface 400B includes a paragraph configuration area 420, a document preview control 340, an entry point 421 for obtaining content description information of document portions, a content generation control 422, and a dynamic generation control 423. Application management platform 110 can receive content description information provided by user 105 through entry point 421. For example... Figure 4B As shown, interface 400B may also include a preference setting control 424 and a data source configuration control 425. The preference setting control 424 is used to set paragraph length and writing style, etc., in the document section configuration information. The data source configuration control 425 is used to receive configuration instructions from user 105 regarding the data source. For example, if user 105 believes that the currently configured data source for the target document section is not comprehensive enough, and the quality of the content generated based on the currently configured data source is poor and does not meet expectations, the user can send a data source configuration request to the application management platform 110 to update the data source configured for the target document section by interacting with the data source configuration control 425 (e.g., clicking the data source configuration control 425).

[0078] For example, in response to a data source configuration request sent by user 105, application management platform 110 may present an interface to user 105 for obtaining data and knowledge. This interface includes at least an entry point for receiving data, to obtain user-uploaded data or a specified knowledge base. In some embodiments, application management platform 110 may provide different interfaces for user 105, respectively for receiving different types of data sources uploaded by user 105. Figure 5 A schematic diagram of a knowledge base presentation interface 500 according to some embodiments of the present disclosure is shown. The application management platform 110 can present a knowledge base selection interface to the user in response to an interactive operation by the user 105 regarding the data source configuration control 425. For example... Figure 5 As shown, interface 500 includes an entry point 510 for specifying data objects, an entry point 520 for adding skills from the target application 120, an entry point 530 for configuring dependencies between different document sections, and an entry point 540 for configuring data and knowledge (i.e., determining the target knowledge base for generating document section content). User 105 can configure data sources for document sections through different entry points. For example, in response to the user's selection of entry point 540, application management platform 110 displays multiple candidate knowledge bases available for the target template to user 105 on interface 500 (e.g., a panel). User 105 can select a candidate knowledge base as the target knowledge base through appropriate actions (e.g., checking a checkbox before a candidate knowledge base). Application management platform 110 determines the target knowledge base based on user 105's selection. Accordingly, configuration information for the first document section is determined based on the target knowledge base. That is, it is determined that application management platform 110 will refer to the target knowledge base to generate the content of the first document section. In some embodiments, application management platform 110 can also generate the target template based on other reference data sources.

[0079] Figure 6 A schematic diagram of an entry interface 600 for a user to specify data objects according to some embodiments of the present disclosure is shown. Figure 6 As shown, in response to the user's selection of entry 510, an interface 600 (which may be, for example, a panel) is presented to the user, including entry points for specifying different types of data objects. In this example, interface 600 includes entry point 610 for uploading local files, entry point 620 for adding a Uniform Resource Locator (URL), and entry point 630 for adding text. The user 105 can provide different types of local data to the application management platform 110 by operating different entry points.

[0080] Figure 7 A schematic diagram of an example interface 700 for skill selection according to some embodiments of the present disclosure is shown. Figure 7As shown, in response to the user's selection of entry 520, an interface 700 (which may be, for example, a panel) is presented to the user, including entry points for specifying different skills. The interface 700 presents options 710 to 750 for one or more skills created for the target application 120. The user 105 can select a skill through the interface 700. Thus, after the target template is published, the selected skill can be utilized by the end user 145 during the process of generating a document using the target template. When the target template is created within the target application, the selectable skill can be a skill configured or created within the target application. A skill, also referred to as a function, is configured to perform a predetermined task.

[0081] In some embodiments, to ensure logical coherence among multiple document sections in a template generated by the application management platform 110 and improve document quality, user 105 can configure dependencies between different document sections. Dependencies between different document sections include relationships with one or more logical connections. For example, different document sections can have parallel, causal, or conditional relationships. During the process of generating a document based on a template with dependencies, a document section is generated after its dependent document sections are generated, and the content of its dependent document sections is used as reference material. For example, user 105 can configure a second document section to depend on a first document section. During the process of generating a document using this template, the content of the first document section will be generated before the second document section. The content of the first document section will be used as a reference source for the second document section. It is understood that any document section can only depend on a preceding document section in the document structure.

[0082] In some embodiments, the body content of a document portion that the target document portion depends on (i.e., the dependent body content) is used to generate the body content of the target document portion (i.e., the target body content). The type of dependency relationship between documents will affect how the dependent body content is used in the target body content generation process. For example, if the target document portion and the dependent document portion are parallel, the dependent body content will only be used as a reference and will not appear in the target body content. If the target document portion and the dependent document portion are causally related, the dependent body content will serve as the data source for generating the target body content.

[0083] In some embodiments, a machine learning model can be used to generate target main content. The application management platform 110 provides prompts to the machine learning model based on the main content and dependencies of the target document portion, thereby obtaining the output of the machine learning model. Based on different types of dependencies between document portions, the application management platform can generate different types of prompts to improve the quality of the machine learning model's output. For example, if the target document portion and the dependent document portion have a parallel relationship, the prompt instructs the model to generate target main content with a parallel relationship according to the dependent main content. If the target document portion and the dependent document portion have a causal relationship, the prompt instructs the model to generate target main content with a causal relationship according to the dependent main content. Subsequently, based on the output of the machine learning model, the main content of the second document portion is determined. In this way, it is ensured that the content of the dependent document portion is perceived by the target document portion, avoiding the generation of duplicate or inconsistent content in the document.

[0084] Figure 8 A schematic diagram of an example interface 800 for configuring dependencies according to some embodiments of the present disclosure is shown. Figure 8 As shown, in response to a relationship configuration instruction from user 105 for any document section, application management platform 110 presents options 810 to 840 in interface 800 regarding other document sections in the target template. User 105 can determine the target document section upon which the generation of the current document section will depend by performing an action (e.g., checking a checkbox before the target document section).

[0085] To further ensure that the generated document matches user 105's expectations when the generated template is used, content description information can be configured for each document section. The content description information indicates the generation requirements (i.e., user expectations) for the main content of that document section. In some embodiments, the content description information can be generated based on template creation instructions. For example, the content description information in the template creation instructions is provided to a machine learning model to generate corresponding content description information. The content description information may include information such as the content, genre, and paragraph length for the document section. In some embodiments, the document generated based on the created target template may not meet user 105's expectations. Therefore, to improve the quality of the created target template, the application management platform 110 can support the template creator (e.g., user 105) in debugging the template's configuration information. For example, a preview document can be presented to the user based on the created target template to allow the user to more accurately assess whether the target template meets their expectations. In response to receiving document preview information, the application management platform 110 presents a preview document to user 105. The document preview information may include document generation requirements to indicate the user's expectations for the document to be generated. The document generation requirements can be information entered by the user or information generated based on template creation instructions. In some embodiments, the document preview information may also include supplementary materials for generating the preview document, such as user-specified data objects, user-inputted text, publicly available internet data, etc. The application management platform 110 can combine the data source in the target template and the supplementary materials indicated by the document preview information to generate the preview document, so that the preview document better meets the user's expectations. In some embodiments, to facilitate the user 105 in entering supplementary materials, different interfaces can be used to obtain different types of supplementary materials.

[0086] Figure 9A A schematic diagram of an example of an entry interface 900A for receiving document preview information according to some embodiments of the present disclosure is shown. Figure 9A As shown, interface 900A includes a document preview control 340 and an entry point 910 for obtaining document preview information. In response to user 105's selection of the document preview control, application management platform 110 presents entry point 910 and corresponding navigation information to the user. User 105 can provide document preview information to application management platform 110 through interactive operations with entry point 910. Furthermore, entry point 910 also includes entry point 911 for obtaining text, entry point 912 for receiving links (e.g., internet URLs), entry point 913 for receiving user-specified data objects (e.g., local documents or online documents), and document generation control 914. User 105 can specify different types of supplementary information through entry points 911 to 913.

[0087] In some embodiments, the target template's currently configured data source can also be presented to the user so that the user can understand the currently configured data source and improve document preview efficiency. Figure 9B A schematic diagram of another example of an entry interface 900B for receiving document preview information according to some embodiments of the present disclosure is shown. Figure 9B As shown, the data source presentation area 915 presents the target template or the selected document portion of the target template containing the configured data source to the user 105. If the user 105 confirms that the required supplementary information is not present in the data source presentation area 915, the supplementary information is provided to the application management platform 110 through entry point 910. For example, the data source presentation area can present the configured data source to the user 105 in the form of a thumbnail.

[0088] Upon receiving document preview information for the target template, the application management platform 110, in response to user 105's selection of the document generation control, initiates the process of generating a preview document. Based on the received document preview information and the target template, the application management platform 110 generates the corresponding preview document. Subsequently, the generated preview document is presented to the user so that the user can determine the differences between the target template and their expectations. Figure 9C A schematic diagram of an example of an interface 900C for presenting a preview document according to some embodiments of the present disclosure is shown. Figure 9C As shown, the application management platform 110 generates a preview document in response to user 105's selection of the document generation control. Subsequently, the preview document is presented to user 105 in the editing area 320 of interface 900A. The preview document includes each document section of the target template and the content corresponding to each document section.

[0089] In some embodiments, if the generated preview document differs significantly from the user's expectations, the user 105 can update the configuration information corresponding to the target document portion in the target template. For example, updating the content description information corresponding to the target document portion or the data source on which the generated content of the target document portion depends. Figure 9D A schematic diagram of another example of an interface 900D for presenting a preview document according to some embodiments of the present disclosure is shown. Figure 9DAs shown, the interface 900D displays a preview document in the editing area 320. The application management platform 110 displays entry points 321, deletion controls 322, and data source query controls 323 in the editing area 320, corresponding to each document section, for modifying the configuration of the target document section, to obtain user update instructions for the target document section. In some embodiments, the application management platform 110 may display entry points 321 corresponding to each document section, or it may display entry points 321 corresponding to the selected document section in response to user 105's selection of a document section. In some embodiments, the application management platform 110 may also display configuration information corresponding to the document section for user viewing. Figure 9D As shown, in response to user 105's selection of a target document section, the data source upon which the generated document content depends is displayed in the data source display area 410 corresponding to the target document section. To facilitate user 105's determination of the updated template quality, the application management platform 110 can regenerate the preview document after user 105 updates the configuration information. Thus, the quality of the target template is determined based on the regenerated preview document.

[0090] In some embodiments, if user 105 does not update the configuration information for all parts of a document, or performs multiple update operations on the configuration information corresponding to a certain part of a document, the application management platform 110 needs to frequently generate full-text previews of the document, causing inconvenience to user 105. Therefore, in some embodiments, only preview content corresponding to a portion of the document can be generated. For example... Figure 4B As shown, user 105 can also control application management platform 110 to generate content corresponding to the document section through content generation control 422. Application management platform 110 responds to preview instructions input by user 105 and presents the corresponding content. User 105 views the presented content and, based on the difference between their expectations of the document and the presented content, further modifies the configuration information of the document section. Subsequently, based on the modified configuration information, it regenerates the content corresponding to that document section.

[0091] In some embodiments, if the currently created target template differs significantly from the user 105's expectations, requiring extensive modification of configuration information, it will impact the user's efficiency in creating the target template. Therefore, the user 105 can abandon the current template and create a new target template. For example, the user 105 can select the template settings control 330 to send an instruction to the application management platform 110 to recreate the target template. In response to the user's selection of the template settings control 330, the application management platform 110 presents the interface 200 to the user to re-obtain the template creation instruction used to create the target template.

[0092] In some embodiments, if the created target template meets the user's expectations, the user 105 can export the created target template using an export control. The exported template can be provided to other users within the organization so that users can generate corresponding target documents using the template. For example, the exported template can be published within the target application for end users of the target application to select and use.

[0093] In some embodiments, the application management platform 110 may support dynamic generation (also known as deep generation). Dynamic generation refers to the dynamic generation of document section titles during the document generation process. In the case of dynamic generation, document section titles are generated in real time based on retrieved information. Figure 4B As shown, for a specific document section, the corresponding dynamic generation control 423 is enabled by user 105. Accordingly, the application management platform 110 receives an instruction to enable dynamic generation for that document section and includes this instruction as part of the document section's configuration information. Thus, one or more sub-sections included in that document section will be dynamically determined during document generation. In other words, sub-sections under that document section (e.g., their titles) will not be included in the target template. For example, which main products under the first-level title "Main Products" are relevant to the search content in the document generation process, but are not included in the template.

[0094] Example process

[0095] Figure 10 A flowchart illustrating an example process 1000 of a template creation method according to some embodiments of the present disclosure is shown. Process 1000 can be implemented at an application management platform 110. Reference is made below. Figure 1 To describe process 1000.

[0096] like Figure 10 As shown in box 1010, the application management platform 110 receives a template creation instruction for a target template, which is used for document generation.

[0097] In some embodiments, the template creation instruction includes at least one of the following: a template identifier for the target template, template description information for the target template, the template description information indicating the generation requirements of the target template, one or more candidate knowledge bases for the target template, or the hierarchy of the target template.

[0098] In box 1020, the application management platform 110 presents the structural information of the target template, which indicates the document structure generated based on the template creation instructions.

[0099] In some embodiments, presenting structural information of the target template includes presenting an editing area for the document structure, and wherein the corresponding configuration information of one or more document portions is determined at least in part based on editing instructions associated with the editing area.

[0100] In some embodiments, presenting the structural information of the target template further includes: presenting navigation information about the document structure, the navigation information including one or more navigation items corresponding to one or more document portions respectively; and updating the editing area to present the document portion corresponding to the triggered navigation item in response to triggering one or more navigation items.

[0101] In some embodiments, structural information is determined by: providing a machine learning model with prompts for document structure generation based on template creation instructions to obtain the output of the machine learning model; and determining structural information based on the output of the machine learning model.

[0102] In box 1030, the application management platform 110 creates the target template based on the corresponding configuration information of at least one or more document sections included in the target template.

[0103] In some embodiments, determining the corresponding configuration information for one or more document portions includes: receiving a knowledge configuration instruction for a first document portion among the one or more document portions; in response to the knowledge configuration instruction, presenting information about one or more candidate knowledge bases that can be used for a target template; and in response to the selection of a target knowledge base among the one or more candidate knowledge bases, determining that the generation of the first document portion will reference the target knowledge base as at least a part of the configuration information for the first document portion.

[0104] In some embodiments, determining the corresponding configuration information for one or more document portions includes: receiving a relationship configuration instruction for a second document portion among the one or more document portions; in response to the relationship configuration instruction, presenting information about at least one document portion among the one or more document portions; and in response to the selection of a target document portion among the at least one document portion, determining that the second document portion has a dependency relationship with the target document portion as at least part of the configuration information of the second document portion.

[0105] In some embodiments, the main content of the second document portion is generated by: responding to configuration information in the second document portion indicating a dependency relationship between the second document portion and the target document portion, providing prompt information to the machine learning model based on the main content of the target document portion and the dependency relationship to obtain the output of the machine learning model; and determining the main content of the second document portion based on the output of the machine learning model.

[0106] In some embodiments, dependencies include associations with one or more logical relationships.

[0107] In some embodiments, determining the corresponding configuration information for one or more document portions includes: receiving a configuration editing instruction for a third document portion among the one or more document portions; in response to the configuration editing instruction, presenting content description information for the third document portion, the content description information indicating generation requirements for the main content of the third document portion and being generated using a machine learning model based on a template creation instruction; and updating the content description information as at least a part of the configuration information for the third document portion based on user input for the content description information.

[0108] In some embodiments, determining the corresponding configuration information for one or more document portions includes: receiving an indication to enable dynamic generation for a fifth document portion among the one or more document portions, as part of the configuration information for the fifth document portion, such that one or more sub-parts included in the fifth document portion will be dynamically determined during document generation.

[0109] In some embodiments, process 1000 further includes receiving document preview information for a target template, the document preview information indicating document generation requirements based on the target template; and presenting preview content generated by a machine learning model for one or more document portions based on the document preview information.

[0110] In some embodiments, process 1000 further includes receiving a configuration update instruction for the fourth document portion in response to the presentation of preview content of a fourth document portion in one or more document portions; and updating configuration information for the fourth document portion based on the configuration update instruction.

[0111] In some embodiments, process 1000 further includes receiving an interaction with structural information; and determining, based on the interaction with the structural information, corresponding configuration information for one or more document portions.

[0112] In some embodiments, process 1000 further includes receiving an update instruction for a sixth document portion of one or more document portions, the update instruction indicating at least a change in the sixth document portion in the document structure; and presenting updated structural information based on the update instruction.

[0113] Example devices and equipment

[0114] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 11A schematic structural block diagram of an example apparatus 1100 for template creation according to certain embodiments of the present disclosure is shown. Apparatus 1100 may be implemented as or included in an application management platform 110. Various modules / components in apparatus 1100 may be implemented by hardware, software, firmware, or any combination thereof.

[0115] like Figure 11 As shown, the apparatus 1100 includes: a receiving module 1110 configured to receive a template creation instruction for a target template, the target template being used for document generation; a rendering module 1120 configured to render structural information of the target template, the structural information indicating the document structure generated based on the template creation instruction; and a creation module 1130 configured to create the target template based at least on corresponding configuration information of one or more document portions included in the target template.

[0116] In some embodiments, the presentation module 1120 is further configured to present an editing area for the document structure, and wherein the corresponding configuration information of one or more document portions is determined at least in part based on editing instructions associated with the editing area.

[0117] In some embodiments, the presentation module 1120 is further configured to present navigation information about the document structure, the navigation information including one or more navigation items corresponding to the one or more document portions respectively; and to update the editing area to present the document portion corresponding to the triggered navigation item in response to a triggering of one or more navigation items.

[0118] In some embodiments, the presentation module 1120 is further configured to provide prompts for document structure generation to a machine learning model based on the template creation instruction, so as to obtain the output of the machine learning model; and to determine the structure information based on the output of the machine learning model.

[0119] In some embodiments, the creation module 1130 is further configured to receive a knowledge configuration instruction for a first document portion of the one or more document portions; in response to the knowledge configuration instruction, present information about one or more candidate knowledge bases that can be used for the target template; and in response to the selection of a target knowledge base among the one or more candidate knowledge bases, determine that the generation of the first document portion will refer to the target knowledge base as at least a part of the configuration information of the first document portion.

[0120] In some embodiments, the creation module 1130 is further configured to receive a relationship configuration instruction for a second document portion of the one or more document portions; in response to the relationship configuration instruction, present information about at least one document portion of the one or more document portions; and in response to the selection of a target document portion of the at least one document portion, determine that the second document portion has a dependency relationship with the target document portion as at least a part of the configuration information of the second document portion.

[0121] In some embodiments, the creation module 1130 is further configured to, in response to configuration information of the second document portion indicating that the second document portion has a dependency relationship with the target document portion, provide prompt information to the machine learning model based on the main content of the target document portion and the dependency relationship to obtain the output of the machine learning model; and determine the main content of the second document portion based on the output of the machine learning model.

[0122] In some embodiments, the creation module 1130 is further configured to receive a configuration editing instruction for a third document portion of the one or more document portions; in response to the configuration editing instruction, present content description information for the third document portion, the content description information indicating generation requirements for the main content of the third document portion and being generated using a machine learning model based on the template creation instruction; and update the content description information as at least a part of the configuration information for the third document portion based on user input for the content description information.

[0123] In some embodiments, the creation module 1130 is further configured to receive an instruction to enable dynamic generation for a fifth document portion of the one or more document portions, as part of the configuration information of the fifth document portion, so that one or more sub-parts included in the fifth document portion will be dynamically determined during document generation.

[0124] In some embodiments, the device 1100 further includes a preview content presentation module configured to receive document preview information for the target template, the document preview information indicating document generation requirements based on the target template; and based on the document preview information, to present preview content generated by a machine learning model for each of the one or more document portions.

[0125] In some embodiments, the apparatus 1100 further includes a configuration information update module configured to receive a configuration update instruction for the fourth document portion in response to the presentation of preview content of the fourth document portion among the one or more document portions; and to update the configuration information for the fourth document portion based on the configuration update instruction.

[0126] In some embodiments, the apparatus 1100 further includes a configuration information determination module configured to receive interaction with the structure information; and to determine corresponding configuration information for the one or more document portions based on the interaction with the structure information.

[0127] In some embodiments, the apparatus 1100 further includes a structure information determination module configured to receive an update instruction for a sixth document portion of the one or more document portions, the update instruction indicating at least a change in the sixth document portion in the document structure; and to present the updated structure information based on the update instruction.

[0128] Figure 12 Block diagrams of electronic devices capable of implementing various embodiments of the present disclosure are shown. (See diagram for example.) Figure 12 As shown, electronic device 1200 is in the form of a general-purpose electronic device. Components of electronic device 1200 may include, but are not limited to, one or more processors or processing units 1210, memory 1220, storage device 1230, one or more communication units 1240, one or more input devices 1250, and one or more output devices 1260. Processing unit 1210 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1220. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 1200.

[0129] Electronic device 1200 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 1200, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1220 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 1230 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 1200.

[0130] Electronic device 1200 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 12As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 1220 may include computer program product 1225 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0131] The communication unit 1240 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 1200 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 1200 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0132] Input device 1250 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1260 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 1200 can also communicate with one or more external devices (not shown) via communication unit 1240 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 1200, or with any device that enables electronic device 1200 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0133] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0134] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0135] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0136] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0137] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. 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 consecutive 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 action, or using a combination of dedicated hardware and computer instructions.

[0138] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A template creation method, comprising: Receive a template creation instruction for a target template used for document generation, wherein the template creation instruction includes at least one of the following: The template identifier of the target template, The template description information for the target template indicates the generation requirements for the target template. One or more candidate knowledge bases for the target template, or The hierarchy of the target template; Present the structural information of the target template, the structural information indicating the document structure generated based on the template creation instructions; as well as The target template is created based on the corresponding configuration information of at least one or more document portions included in the target template.

2. The method according to claim 1, further comprising: Receive interactions regarding the structural information; as well as Based on the interaction with the structural information, the corresponding configuration information of the one or more document sections is determined.

3. The method according to claim 1, wherein presenting the structural information of the target template includes: An editing area is presented for the document structure, and the corresponding configuration information of the one or more document portions is determined at least in part based on editing instructions associated with the editing area.

4. The method according to claim 3, wherein presenting the structural information of the target template further includes: Present navigation information about the document structure, the navigation information including one or more navigation items corresponding to the one or more document portions respectively; as well as In response to a triggering of one or more navigation items, the editing area is updated to present the document portion corresponding to the triggered navigation item.

5. The method of claim 1, wherein determining the corresponding configuration information for the one or more document portions includes: Receive a knowledge configuration instruction for a first document portion of the one or more document portions; In response to the knowledge configuration instruction, information about one or more candidate knowledge bases that can be used with the target template is presented; as well as In response to the selection of a target knowledge base from the one or more candidate knowledge bases, it is determined that the generation of the first document portion will refer to the target knowledge base as at least a part of the configuration information of the first document portion.

6. The method of claim 1, wherein determining the corresponding configuration information for the one or more document portions includes: Receive a relationship configuration instruction for a second document portion of the one or more document portions; In response to the relationship configuration instruction, information about at least one of the one or more document portions is presented; as well as In response to the selection of a target document portion in the at least one document portion, it is determined that the second document portion has a dependency relationship with the target document portion as at least a part of the configuration information of the second document portion.

7. The method of claim 6, wherein the main content of the second document portion is generated in the following manner: In response to configuration information in the second document portion indicating a dependency between the second document portion and the target document portion, based on the main content of the target document portion and the dependency, prompts are provided to the machine learning model to obtain the output of the machine learning model; and Based on the output of the machine learning model, the main content of the second document portion is determined.

8. The method of claim 6, wherein the dependency relationship includes an association relationship having one or more logical relationships.

9. The method of claim 1, wherein determining the corresponding configuration information for the one or more document portions includes: Receive configuration editing instructions for a third document portion of the one or more document portions; In response to the configuration editing instruction, content description information for the third document portion is presented, the content description information indicating the generation requirements for the main content of the third document portion and being generated using a machine learning model based on the template creation instruction; as well as Based on user input regarding the content description information, the content description information is updated as at least a part of the configuration information of the third document section.

10. The method of claim 1, further comprising: Receive document preview information for the target template, the document preview information indicating document generation requirements based on the target template; as well as Based on the document preview information, preview content generated by a machine learning model for each of the one or more document portions is presented.

11. The method of claim 10, further comprising: In response to the rendering of the preview content of the fourth document portion of the one or more document portions, a configuration update instruction for the fourth document portion is received; as well as Based on the configuration update instruction, update the configuration information for the fourth document section.

12. The method of claim 1, wherein determining the corresponding configuration information for the one or more document portions includes: Receive an instruction to enable dynamic generation for a fifth document portion of the one or more document portions, as part of the configuration information for the fifth document portion, so that one or more sub-parts included in the fifth document portion will be determined based on retrieved information during the document generation process.

13. The method of claim 1, further comprising: Receive an update instruction for a sixth document portion of the one or more document portions, the update instruction indicating at least a change in the sixth document portion within the document structure; as well as Based on the update instruction, the updated structural information is presented.

14. The method of claim 1, wherein the structural information is determined by: Based on the template creation instructions, prompts for document structure generation are provided to the machine learning model to obtain the output of the machine learning model; and The structural information is determined based on the output of the machine learning model.

15. An apparatus for template creation, comprising: A receiving module is configured to receive a template creation instruction for a target template used for document generation, wherein the template creation instruction includes at least one of the following: The template identifier of the target template, The template description information for the target template indicates the generation requirements for the target template. One or more candidate knowledge bases for the target template, or The hierarchy of the target template; A presentation module is configured to present structural information of the target template, the structural information indicating a document structure generated based on the template creation instructions; as well as A module is configured to create the target template based at least on the corresponding configuration information of one or more document portions included in the target template.

16. An electronic device comprising: At least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processing unit.

17. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 14.

Images