Document generation method and apparatus, device, storage medium, and program product

Abstract

The embodiments of the present disclosure provide a document generation method and apparatus, a device, a storage medium, and a program product. In the present solution, a document generation request for a target document is received, the document generation request at least indicating a generation requirement for the target document and a target template for generating the target document. Structure information of the target document is presented, the structure information indicating a document structure generated on the basis of the document generation request. On the basis of interaction for the structure information, corresponding configuration information of one or more document portions included in the target document is determined. On the basis of the corresponding configuration information of the one or more document portions, the target document is generated.

Description

Methods, apparatus, devices, storage media, and program products for document generation

[0001] This application claims priority to Chinese Patent Application No. 202411537993.6, filed on October 30, 2024, entitled "A method, apparatus, device and storage medium for document generation", the entire contents of which are incorporated herein by reference. Technical Field

[0002] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to a method, apparatus, device, computer-readable storage medium, and computer program product for document generation. Background Technology

[0003] 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

[0004] In a first aspect of this disclosure, a method for document generation is provided. The method includes: receiving a document generation request for a target document, the document generation request indicating at least generation requirements for the target document and a target template for generating the target document; presenting structural information of the target document, the structural information indicating a document structure generated based on the document generation request; determining corresponding configuration information for one or more document portions included in the target document based on interaction with the structural information; and generating the target document based on the corresponding configuration information for the one or more document portions.

[0005] In a second aspect of this disclosure, an apparatus for document generation is provided. The apparatus includes: receiving a template, configured to receive a document generation request for a target document, the document generation request indicating at least generation requirements for the target document and a target template for generating the target document; presenting a template, configured to present structural information of the target document, the structural information indicating a document structure generated based on the document generation request; determining a template, configured to determine corresponding configuration information for one or more document portions included in the target document based on interaction with the structural information; and generating a template, configured to generate the target document based on the corresponding configuration information of the one or more document portions.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0007] 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.

[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0009] 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

[0010] 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:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;

[0012] Figure 2 shows a schematic diagram of an example interface for initiating document generation according to some embodiments of the present disclosure;

[0013] Figure 3 shows a schematic diagram of an example interface for presenting a document structure generation process according to some embodiments of the present disclosure;

[0014] Figure 4 shows a schematic diagram of an example interface for presenting a document structure according to some embodiments of the present disclosure;

[0015] Figure 5 shows a schematic diagram of an example interface for updating content description information according to some embodiments of the present disclosure;

[0016] Figure 6 shows a schematic diagram of an entry interface for receiving document generation information according to some embodiments of the present disclosure;

[0017] Figure 7 shows a schematic diagram of an example interface for presenting a target document according to some embodiments of the present disclosure;

[0018] Figure 8 shows a schematic diagram of an example interface for presenting preview content according to some embodiments of the present disclosure;

[0019] Figure 9 illustrates a flowchart of an example process for document generation according to some embodiments of this disclosure;

[0020] Figure 10 shows a schematic structural block diagram of an example apparatus for document generation according to some embodiments of the present disclosure; and

[0021] Figure 11 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] As used in this article, "document template" or "template" can refer to an electronic, computer-processable file that describes how to generate the document.

[0034] 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.

[0035] In view of this, embodiments of the present disclosure provide a document generation scheme for generating documents based on a target template provided by a platform. In this scheme, a document generation request for a target document is received, the document generation request indicating at least the generation requirements for the target document and a target template for generating the target document. Structural information of the target document is presented, indicating the document structure generated based on the document generation request. Based on interaction with the structural information, corresponding configuration information for one or more document portions included in the target document is determined. Based on the corresponding configuration information of the one or more document portions, the target document is generated.

[0036] As will be more clearly understood from the following description, the scheme disclosed herein allows users to select the target template they wish to use. This allows the document structure to be generated first, based on the document generation requirements and the target template. Furthermore, it allows users to configure the various document sections that will be included, enabling template users to fine-tune the document structure. In this way, it ensures that the generated document matches the template user's expectations, thereby improving the efficiency of document generation for the template user.

[0037] Example Environment

[0038] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Environment 100 relates to an application management platform 110, which can support application creation and / or application execution. 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] Digital assistant 122 can be configured to have intelligent conversational capabilities. In the example shown in Figure 1, 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 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.

[0044] 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.

[0045] For each end user 145, the client of the application runtime portion can present various interfaces of the target application 120 in the client interface. In the example of Figure 1, an interaction window 142 between the end user 145 and the digital assistant 122 is shown, such as a conversation window with the digital assistant 122. The end user 145 can enter conversation messages in the conversation window, and the target application 120 can determine the response message of the digital assistant 122 based on the created configuration information and present it to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction messages with the 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.

[0046] 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).

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] The processes described in the embodiments of this disclosure can be implemented on an application management platform, a terminal device on which the application management platform is 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, such as the application management platform 110 shown in FIG1. ​​The user interface presented by the application management platform 110 can be presented 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 terminal user of the target application 120. It should be understood that the user interface presented by the application management platform 110 can also be presented 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.

[0056] Example Interaction

[0057] Figures 2 through 8 illustrate example interfaces 200 through 800 according to some embodiments of the present disclosure. Interfaces 200 through 800 may be provided, for example, by the application management platform 110 shown in Figure 1.

[0058] End user 145 can generate a desired target document through target application 120. In some embodiments, application management platform 110 receives a document generation request sent by end user 145. Subsequently, based on the document generation request, it determines the end user 145's requirements for generating the target document (such as the genre of the target document, the document content corresponding to the target document, the application scenario of the target document, etc.) and the target template for generating the target document. In some embodiments, the document generation request may also indicate a reference data source that can be used in the target document generation process. The reference data source may include one or more of the following: a knowledge base accessible to the user set to which end user 145 belongs (e.g., an internal enterprise knowledge base), public data (e.g., data that can be obtained through Internet search), and data objects specified by end user 145 (e.g., local documents or online documents uploaded by end user 145), etc. In some embodiments, the document generation request may also be in the form of keywords. Application management platform 110 uses a language model to determine the target template and document generation requirements indicated by the keywords.

[0059] The target template indicates the knowledge base, genre, and hierarchy of the target document that the end user 145 expects to generate. The target template can be a template uploaded by the end user 145 or a template provided to the end user 145 by the application management platform 110. If the application management platform 110 does not receive a document template uploaded by the end user 145, it provides the end user with several different types of candidate document templates to facilitate the selection of a target template.

[0060] Candidate document templates can come from a template library or from an internal template library maintained by the organization to which end user 145 belongs. In some embodiments, to ensure the security of internal data, different data access permissions need to be configured for different members within the organization. When end user 145 generates a target document using a template from the internal template library, application management platform 110 can provide the corresponding document template to end user 145 based on end user 145's access permissions to the internal template library. For example, for any member within organization A, if the member does not have access permissions to certain document templates maintained by organization A in application management platform 110, then these document templates cannot be used as candidate document templates. For example, if the member does not have access permissions to template B, then template B cannot be provided as a candidate document template. Therefore, when application management platform 110 receives a document generation request from end user 145, it first determines the permissions of end user 145. Based on the permissions of end user 145, it determines the candidate document templates that can be used by end user 145.

[0061] For example, the application management platform 110 can present a template selection interface to the user, including multiple candidate document templates. Subsequently, based on the end user 145's selection of a target template, a template suitable for generating the target document is determined. Figure 2 shows a schematic diagram of an example interface 200 for initiating document generation according to some embodiments of this disclosure. As shown in Figure 2, an interface 200 for obtaining a document generation request is presented on the terminal device of the end user 145. The application management platform 110 can obtain the document generation request input by the end user 145 through the presented interface 200. As shown in Figure 2, the interface 200 includes various interface elements to obtain the document generation request. For example, Figure 2 shows an entry point 210 for receiving a text-type document generation request provided by the end user 145 and an entry point 220 for receiving a target template specified by the end user 145. Entry point 220 presents a first candidate document template 230-1, a second candidate document template 230-2, a third candidate document template 230-3, a fourth candidate document template 230-4, and a fifth candidate document template 230-5, which can be individually or collectively referred to as candidate document templates 230. The number of candidate document templates 230 shown in Figure 2 is merely exemplary and is not intended to be a limitation. Entry point 220 may also present partial information about each candidate document template 230 (e.g., template theme, template structure information, etc.) to end user 145 to facilitate end user 145 in selecting a target template. Subsequently, application management platform 110 determines the target template that can be used for generating the target document based on end user 145's selection of the target template (e.g., clicking, etc.).

[0062] In addition, entry point 210 also includes entry point 211 for end user 145 to obtain text, entry point 212 for receiving links (e.g., internet URLs or online documents), entry point 213 for receiving data objects specified by end user 145 (e.g., local documents), and structure generation control 214. End user 145 can receive different types of knowledge uploaded by end user 145 through entry points 211 to 213. The knowledge received by the application management platform will be used to generate the target document. If structure generation control 214 is enabled, application management platform 110 initiates the document structure generation process to create a document structure based on the target template obtained by the instruction acquisition component 210, indicating the structural information for generating the target document.

[0063] In some embodiments, the application management platform 110 generates the document structure of the target document based on a document generation request. The generated document structure is then presented to the end user 145. Figure 3 shows a schematic diagram of an example interface 300 for presenting the document structure generation process according to some embodiments of this disclosure. As shown in Figure 3, the interface 300 includes a navigation area 310 and an editing area 320. Furthermore, the interface 300 includes a stop generation control for terminating the document structure generation process. Navigation information about the document structure is presented in the navigation area 310. The end user 145 can quickly view the document structure through the navigation information presented in the navigation area. The editing area 320 is used to receive interactive operations from the end user 145 regarding the document structure, so as to adjust the document structure of the target document according to the end user 145's expectations.

[0064] Multiple document sections within the document structure of the target document can be generated at least partially in parallel. For example, the application management platform 110 can simultaneously generate multiple document structures at the same level, or simultaneously generate multiple sub-document sections within a single document section.

[0065] Since the presented document structure will be used to generate the content of the target document, if the document structure does not meet the expectations of end user 145, the generated target document will also fail to meet end user 145's expectations. Therefore, after presenting the structural information of the target document to end user 145, the application management platform 110 can receive feedback from end user 145 regarding the currently generated document structure and adjust the document structure based on the feedback. For any document portion in the document structure, the application management platform 110 can respond to the interaction of end user 145 regarding the structural information corresponding to that document portion and determine the corresponding configuration information for that document portion. The final configuration information for the document portion includes information added or modified by end user 145 and information originally present in the target template. The configuration information includes reference data sources considered during the document portion generation process and document portion description information, etc.

[0066] In some embodiments, after the application management platform 110 presents the reference data source information to the end user 145, in order to ensure that the generated target document meets the user's expectations, the end user 145 can adjust the reference data source in the document structure. This can be achieved by adding new data sources or deleting configured data sources. It should be noted that, to ensure data security, the end user 145 cannot configure an internal knowledge base for the document structure. For example, the end user 145 can configure specified data objects for the document structure through a data source configuration entry. These could include data obtained through internet searches, local documents uploaded by the end user 145, or online documents.

[0067] In some embodiments, there may be a mismatch between the internal knowledge base configured in the target template and the end user 145's expectations for generating the target document, affecting the number of target documents generated. Therefore, the end user 145 can delete (or disable) the internal knowledge base to prevent it from being referenced during the target document generation process. For example, the end user 145 can send a knowledge base deselection instruction for any internal knowledge base to the application management platform 110 through the data source configuration entry. The application management platform 110 removes the corresponding knowledge base based on the received knowledge base deselection instruction. Furthermore, the end user 145 can also remove other types of reference data sources by sending a knowledge base deselection instruction to the application management platform 110.

[0068] Figure 4 illustrates a schematic diagram of an example interface 400 for presenting a document structure according to some embodiments of the present disclosure. As shown in Figure 4, each editable item in the interface 400 has a corresponding entry point 421 for modifying configuration information of the target template and a delete control 422. For any editable item, its corresponding entry point 421 and delete control 422 can be hidden. In response to the terminal user 145'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, etc.), the entry point 421 and delete control 422 corresponding to the editable item are presented in the interface 400. The delete control 422 is used to receive the delete instruction from the terminal user 145 and delete the document portion corresponding to the control.

[0069] In some embodiments, the application management platform 110 can present the configured data sources for each document section to the end user 145, enabling the end user 145 to determine the data source configuration status of the document and improve template creation efficiency. In some embodiments, the application management platform 110, in response to the end user 145's data source configuration instruction for a target document section, presents the configured data source for that target document section to the end user 145. 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 configuration instruction is applied can be any document section in the target template or the entire target template.

[0070] As shown in Figure 4, a data source query control 423 is displayed in the corresponding area of ​​the editable item in the editing area 320. The icon of the data source query control 423 may include the identifier of the configured data source. The end user 145 provides a data source query request to the application management platform 110 through interaction with the data source query control 423 (e.g., click operation). In response to the data source query request for the target document section, the application management platform 110 presents the configured data source information to the end user 145. In the interface 400, different types of data sources can be presented in categories. For example, the data source display area is used to present the knowledge base configured in the target template (e.g., pet industry analysis knowledge base, comprehensive market analysis knowledge base), the data object specified by the end user 145 (e.g., the document uploaded by the end user 145), and public data sources (e.g., Internet URL links). For example, the interface 400 may also present a brief description of the data source to facilitate the identification of the content of the configured data source.

[0071] In some embodiments, the application management platform 110 updates the configuration information of the target template based on a received adjustment instruction for the target template. Subsequently, based on the updated configuration information of the target template, a document template usable by the target user is created. For example, the interface 400 also includes a global settings control 430. The global settings control 430 can be used to adjust or reset the target template in use. For example, the application management platform 110 can present a template settings interface to the end user 145 in response to a triggering action by the end user 145 on the global settings control 430. The template settings interface can be used to receive template configuration information input by the user, such as template identifier, template data source, and template description information.

[0072] Subsequently, the application management platform 110 creates a template for generating documents based on the template configuration information input by the user. The created template can be used by the current target user, for example, by being saved in the target user's document library or template library. For example, in response to a user's template saving instruction, the application management platform 110 can save a template that has been modified by the end user 145 as the end user 145's personal template, so that the end user 145 can use the personal template again to generate documents.

[0073] In some embodiments, the content description information can be content generated by a machine learning model based on the document generation information received from the entry point 210. The content description information indicates the topic, genre, etc., of the corresponding document section. In some embodiments, the content description information generated by the machine learning model may not accurately reflect the user's expectations for the document section. Therefore, the end user 145 can adjust the content description information. The application management platform 110 can update the content description information based on received user input regarding the content description information. Figure 5 shows a schematic diagram of an example interface 500 for updating content description information according to some embodiments of this disclosure. As shown in Figure 5, the interface 500 includes a configuration area 510 for the document section and a document generation control 440. The configuration area 510 can further include an entry point 511 for obtaining content description information of the document section, a content generation control 512, and a dynamic generation control 513. The application management platform 110 can receive the content description information provided by the end user 145 through the entry point 511.

[0074] As shown in Figure 5, the configuration area 510 may further include a preference setting control 514 and a data source configuration control 515. The preference setting control 514 is used to set paragraph length and writing style, etc., in the document section configuration information. The data source configuration control 515 is used to receive configuration instructions from the end user 145 regarding the data source. For example, if the end user 145 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 end user 145 can interact with the data source configuration control 515 (e.g., click the data source configuration control 515) to send a data source configuration request to the application management platform 110 to update the reference data source (data source other than the internal knowledge base) configured for the target document section.

[0075] The updated reference data source will be used in the generation process of the target document portion. In some embodiments, end user 145 and / or user 105 can configure different types of reference data sources. For example, the reference data source can be a text type (e.g., text copied and pasted by the user), a user-specified data object (e.g., a local document or an online document), or a knowledge base. The application management platform 110 can employ different processing methods for different types of reference data sources for model consumption.

[0076] In some embodiments, the reference data source may include a knowledge base, which may include multiple knowledge fragments obtained through vectorization of knowledge. For example, a knowledge fragment may be the vectorized data of a sentence or paragraph in an article. At least one knowledge fragment matching the generation requirements of the document section to be generated can be obtained from the knowledge base as reference data. The vectorized data included in the knowledge fragment can be directly provided to the model as input data as reference data.

[0077] In some embodiments, if the reference data source is a user-specified data object (e.g., an online document or a local document), the application management platform 110 can obtain multiple knowledge fragments for the data object by performing vectorization processing on multiple parts of the data object. For example, an article uploaded or specified by the user can be vectorized into multiple knowledge fragments for model consumption. In some embodiments, the application management platform 110 can retrieve at least one knowledge fragment from the multiple knowledge fragments that matches the generation requirements as reference data. Similar to retrieval in a knowledge base, the application management platform 110 can determine one or more keywords based on the generation requirements, and then retrieve knowledge fragments from the multiple knowledge fragments contained in the user-specified data object whose contextual information or subject information matches at least one of the one or more keywords, and determine the retrieved knowledge fragments as at least one knowledge fragment.

[0078] In some embodiments, if the reference data source includes text entered by the user, the application management platform 110 can identify the text as reference data. That is, the text can be directly consumed by the machine learning model.

[0079] In some embodiments, the application management platform 110 may support dynamic generation (also known as deep generation). Dynamic generation indicates that the titles of document sections are dynamically generated during the document generation process. In the case of dynamic generation, the titles of document sections are generated in real time based on the retrieved information. As shown in Figure 5, for a certain document section, if the dynamic generation control 513 corresponding to that document section in the document template is enabled, 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 the document generation process. In other words, the sub-sections under that document section (e.g., their titles) will not be included in the document structure. For example, which main products under the first-level title "Main Products" are related to the retrieved content during the document generation process, but are not in the template.

[0080] In some embodiments, after determining the configuration information corresponding to each document section, the application management platform 110 generates a target document based on the determined configuration information. The target document includes content corresponding to each document section. For example, in response to the end user 145's selection of the document generation control 440, the application management platform 110 generates the target document based on the determined configuration information and document generation information. The document generation information may include document generation requirements to indicate the user's expectations for the document to be generated. The document generation requirements may be information input by the user or information generated based on a template. In some embodiments, the document generation information may also include supplementary information for generating the target document, such as user-specified data objects, user-input text, publicly available internet data, etc. The application management platform 110 can combine the data source in the target template and the supplementary information indicated by the document generation information to generate the target document, making the target document more in line with user expectations. In some embodiments, to facilitate the end user 145's input of supplementary information, different interfaces can be used to obtain different types of supplementary information.

[0081] Figure 6 illustrates a schematic diagram of an entry interface 600 for receiving document generation information according to some embodiments of the present disclosure. As shown in Figure 6, the interface 600 includes a document generation control 440 and an entry point 610 for obtaining document generation information. In response to a selection by an end user 145 of the document generation control 440, the application management platform 110 presents the entry point 610 and corresponding navigation information to the user. The end user 145 can provide document generation information to the application management platform 110 through interactive operations with the entry point 610. Furthermore, the entry point 610 also includes an entry point 611 for obtaining text, an entry point 612 for receiving links (e.g., internet URLs), an entry point 613 for receiving user-specified data objects (e.g., local documents or online documents), and a document generation control 614. The user 145 can specify different types of supplementary information through entry points 611 to 613, respectively.

[0082] In some embodiments, the currently configured data sources in the document structure can also be presented to the user to help them understand the currently configured data sources and improve document generation efficiency. As shown in Figure 6, the data source presentation area 620 presents the document structure or the selected document portion of the document structure with the configured data sources to the end user 145. If the user 145 confirms that the required supplementary information is not present in the data source presentation area 620, the supplementary information is provided to the application management platform 110 through the entry point 610. For example, the data source presentation area can present the identifiers of the configured reference data sources to the user 145 in the form of thumbnails.

[0083] Upon receiving document generation information regarding the document structure, the application management platform 110, in response to a triggering action by the end user 145 on the document generation control, initiates the process of generating the content of the target document. Based on the received document generation information and the target template, the application management platform 110 generates the corresponding content of the target document. Subsequently, the generated document is presented to the user. Figure 7 shows a schematic diagram of an example interface 700 for presenting a target document according to some embodiments of this disclosure. As shown in Figure 7, the application management platform 110 generates the target document in response to a triggering action by the end user 145 on the document generation control 614. Subsequently, the target document is presented to the end user 145 in the editing area 320 of the interface 700. The target document includes various document portions of the target template and content corresponding to each document portion.

[0084] In some embodiments, if the generated target document differs significantly from the user's expectations, the end user 145 can update the configuration information corresponding to the target document portion in the document structure. For example, updating the content description information corresponding to the target document portion or the data source referenced by the generated content of the target document portion. Figure 8 shows a schematic diagram of an example interface 800 for presenting preview content according to some embodiments of this disclosure. As shown in Figure 8, the interface 800 presents preview content corresponding to a certain document portion in the editing area 320. The application management platform 110 presents entry points 421, deletion controls 422, and data source query controls 423 corresponding to each document portion in the editing area 320 to obtain the user's update instructions for the target document portion. In some embodiments, the application management platform 110 can present entry points 421 corresponding to each document portion, or it can present entry points 421 corresponding to the selected document portion in response to the end user 145's selection of a document portion. In some embodiments, the application management platform 110 can also present configuration information corresponding to the document portion for the user to view. As shown in Figure 8, in response to the end user 145's selection of a target document section, the configuration information corresponding to the generated document section content is presented in the document section configuration area 510 corresponding to the target document section. The end user 145 can update the configuration information of the target document section through entry points 511 and 515 to ensure the target document meets the user's expectations. Subsequently, the application management platform 110 can regenerate the target document after the end user 145 updates the configuration information.

[0085] In some embodiments, if the end user 145 only performs update operations on the configuration information of certain document sections, or performs multiple update operations on the configuration information corresponding to a certain document section, the application management platform 110 needs to frequently generate the full text of the target document, causing inconvenience to the end user 145. Therefore, in some embodiments, only the document content corresponding to a portion of the document section can be generated. As shown in FIG8, the end user 145 can also control the application management platform 110 to generate the content corresponding to that document section through the content generation control 512. The application management platform 110 responds to the document generation instruction input by the end user 145 and presents the corresponding content. The end user 145 views the presented content and can further modify the configuration information of the document section based on the difference between the expected document and the presented content. Subsequently, the application management platform 110 can regenerate the content corresponding to that document section based on the modified configuration information. In some embodiments, if the created target document can meet the user's expectations, the end user 145 can export the generated target document through the export control 710. Such a target document can be used as a reference document to generate other documents.

[0086] Furthermore, it should be understood that if the target template used by end user 145 is published in target application 120 (e.g., created by the creator), then the configuration modifications made by end user 145 during the use of the target template apply to the generated target document and do not change the configuration information of the target template itself. In other words, templates that other end users of target application 120 can use still have the configuration assigned by the creator.

[0087] In some embodiments, the target template may be configured with dependencies between multiple document parts. During the document generation process based on a template with dependencies, a document part is generated after its dependent document parts are generated, and the content of its dependent document parts is used as reference material. For example, based on the configuration information of the target template, it is determined that a second document part depends on the generation of a first document part. During the document generation process, the content of the first document part is generated before the second document part. The content of the first document part is used as the reference source for the second document part. It is understood that in some embodiments, a document part may only depend on a preceding document part in the document structure. The end user 145 cannot change the dependencies configured in the target template, but can remove dependencies to ensure that the generated document meets the expectations of the end user 145.

[0088] Furthermore, during the document generation process, to ensure that dependent document parts are aware of each other, the generation order of multiple document parts of the target document can be determined based on the dependencies between documents. In some embodiments, the application management platform 110 determines the generation mode of the target document based on the relationship between one or more document parts, whereby the generation mode at least indicates the generation order of one or more document parts. Subsequently, according to the generation mode, the corresponding main content of one or more document parts is generated based on the corresponding configuration information of each document part. In this way, it is ensured that the content of a dependent document part is perceived by other document parts that depend on it, avoiding the generation of duplicate or inconsistent content in the document.

[0089] In some embodiments, the relationship between multiple document sections may include dependencies indicated by the corresponding configuration information of the multiple document sections. Based on the configuration information for a target document section provided by the end user or a template, the application management platform 110 can determine that the generation of a certain document section will depend on the target document section as at least a part of the configuration information of that document section. Thus, the end user can flexibly configure the dependencies between multiple document sections according to specific needs.

[0090] Alternatively or additionally, in some embodiments, the relationship between multiple document sections may include dependencies determined using a machine learning model based on the headings of the multiple document sections. For example, the machine learning model may analyze the associations between the headings of multiple document sections to determine the corresponding dependencies.

[0091] In some embodiments, the relationship between multiple document parts may include a hierarchical relationship indicated by the document structure of the target document. The document structure may also be referred to as an outline. In some embodiments, to determine the generation pattern of the target document, if the hierarchical relationship between multiple document parts indicates that at least one third document part is a sub-part of a fourth document part, the application management platform 110 may determine that the fourth document part is generated after at least one third document part. In such embodiments, the generation pattern of the target document can be determined based on the hierarchical relationship without considering dependencies. However, if dependencies need to be considered, the priority of the hierarchical relationship and dependencies can be preset. That is, if a conflict arises when determining the generation pattern based on the hierarchical relationship and dependencies of some document parts, the priority of the hierarchical relationship and dependencies can be determined based on a preset priority.

[0092] In some embodiments, the application management platform 110 determines the generation order of a group of document parts as a concurrent generation order in response to determining that there is no dependency between them. For example, a group of document parts that need to be generated concurrently can be displayed concurrently on the editing area 320 or the client interface. Exemplarily, in such embodiments, the hierarchical relationship between the multiple document parts can be disregarded, and the corresponding generation mode can be determined based on dependencies. In other words, for a group of document parts belonging to the same level or different levels, if there is no dependency between them, the generation order of the group of document parts can be directly determined as a concurrent generation order. In some embodiments, the application management platform 110 determines that the second document part is generated before the first document part in response to determining that the first document part depends on the second document part. If the application management platform 110 determines that the first document part depends on the second document part, it can determine that the second document part is generated before the first document part. For example, for a second document part and a first document part that need to be generated sequentially, the second document part can be presented before the first document part on the editing area 320 or the client interface. For example, in such an embodiment, the hierarchical relationship between multiple document parts can still be disregarded, and the corresponding generation mode can be determined by the dependency relationship. In other words, regardless of whether the first document part and the second document part belong to the same level or different levels, the second document part is determined to be generated before the first document part because the first document part depends on the second document part.

[0093] Example process

[0094] Figure 9 shows a flowchart of an example process 900 for document generation according to some embodiments of the present disclosure. Process 900 can be implemented at the application management platform 110. Process 900 will now be described with reference to Figure 1.

[0095] As shown in Figure 9, in box 910, the application management platform 110 receives a document generation request for the target document. The document generation request at least indicates the generation requirements for the target document and the target template used to generate the target document.

[0096] In some embodiments, the target template is determined by presenting a template selection interface that indicates one or more candidate document templates; and in response to the selection of a target template among one or more candidate document templates, a target template that can be used for the generation of the target document is determined.

[0097] In box 920, the application management platform 110 presents the structural information of the target document, which indicates the document structure generated based on the document generation request.

[0098] In box 930, the application management platform 110 determines the corresponding configuration information for one or more document portions included in the target document based on the interaction with the structural information.

[0099] In some embodiments, determining the corresponding configuration information for one or more document portions includes: receiving a configuration editing instruction for a second document portion among the one or more document portions; in response to the configuration editing instruction, presenting content description information for the second document portion, the content description information indicating the generation requirements for the main content of a third document portion and being generated based on a target template; and updating the content description information as at least a part of the configuration information for the second document portion based on user input for the content description information.

[0100] In box 940, the application management platform 110 generates the target document based on the corresponding configuration information of one or more document sections.

[0101] In some embodiments, generating a target document includes: determining a generation mode of the target document based on the relationship between one or more document parts, wherein the generation mode at least indicates the generation order of one or more document parts; and generating corresponding main content of one or more document parts according to the generation mode, based on the corresponding configuration information of one or more document parts respectively.

[0102] In some embodiments, determining the generation mode of the target document includes at least one of the following: in response to determining that there is no dependency between a set of document parts among a plurality of document parts, determining that the generation order of the set of document parts is concurrent generation order, or in response to determining that a first document part among a plurality of document parts depends on a second document part, determining that the second document part was generated before the first document part.

[0103] In some embodiments, the relationship between multiple document sections includes at least one of the following: a dependency relationship indicated by the corresponding configuration information of the multiple document sections, a hierarchical relationship indicated by the document structure of the target document, or a dependency relationship determined by a machine learning model based on the titles of the multiple document sections.

[0104] In some embodiments, the document structure is determined as follows: in response to determining that dynamic generation is not enabled for a first group of document portions indicated by the target template, the title of the first group of document portions is determined based on generation requirements; and in response to determining that dynamic generation is enabled for a second group of document portions indicated by the target template, the title of one or more sub-parts included in the document portion is determined for the document portion in the second group of document portions based on data retrieval results for the document portion.

[0105] In some embodiments, process 900 further includes receiving a data source configuration instruction for a first document portion of one or more document portions; and, in response to the data source configuration instruction, presenting information about one or more reference data sources, which are configured by the target template for the first document portion.

[0106] In some embodiments, determining the corresponding configuration information for one or more document portions included in the target document includes: determining, based on update instructions related to one or more reference data sources, at least one target data source that will be referenced when generating the main content of the first document portion, as at least a part of the configuration information of the first document portion.

[0107] In some embodiments, generating a target document includes: for a target data source in at least one target data source, obtaining reference data for a first document portion from the target data source according to a data query pattern corresponding to the target data source; and generating the main content of the first document portion as part of the target document based on the reference data obtained for each of the at least one target data source.

[0108] In some embodiments, obtaining reference data for the first document portion from the target data source includes one of the following: in response to the target data source including a knowledge base, obtaining at least one knowledge fragment from the knowledge base that matches the generation requirements of the first document portion as reference data; in response to the target data source including a user-specified data object, retrieving at least one knowledge fragment that matches the generation requirements from a plurality of knowledge fragments for the data object as reference data, wherein the plurality of knowledge fragments are obtained by vectorization processing of the data object; or in response to the target data source including text input by the user, determining the text as reference data.

[0109] In some embodiments, determining at least one target data source includes: presenting a data source configuration entry in response to a data source configuration instruction for one or more reference data sources; receiving first user input specifying one or more data objects through the data source configuration entry; and determining one or more data objects as at least a portion of at least one target data source in response to the first user input.

[0110] In some embodiments, determining at least one target data source includes: presenting a data source configuration entry in response to a data source configuration instruction for one or more reference data sources; receiving second user input through the data source configuration entry to deselect at least one of the one or more reference data sources; and removing at least one reference data source from at least one target data source in response to the second user input.

[0111] In some embodiments, process 900 further includes receiving a generation instruction for a third document portion of one or more document portions; and, in response to the generation instruction, presenting a preview of the generated content for the third document portion based on configuration information of the third document portion, wherein determining the corresponding configuration information for one or more document portions includes: receiving a configuration update instruction for the third document portion in response to the presentation of the preview content of the third document portion; and updating the configuration information for the third document portion based on the configuration update instruction.

[0112] In some embodiments, process 900 further includes, in response to selection of a target document portion in one or more document portions, presenting an identifier of one or more reference data sources configured for the target document portion.

[0113] In some embodiments, the document generation request is initiated by the target user, and the process 900 further includes: updating the configuration information of the target template based on receiving an adjustment instruction for the target template; and creating a document template that can be used by the target user based on the updated configuration information of the target template.

[0114] Example devices and equipment

[0115] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. FIG10 shows a schematic structural block diagram of an example apparatus 1000 for document generation according to certain embodiments of this disclosure. Apparatus 1000 may be implemented as or included in application management platform 110. The various modules / components in apparatus 1000 may be implemented by hardware, software, firmware, or any combination thereof.

[0116] As shown in Figure 10, the apparatus 1000 includes a receiving module 1010 configured to receive a document generation request for a target document. The document generation request at least indicates generation requirements for the target document and a target template for generating the target document. The apparatus 1000 also includes a rendering module 1020 configured to render structural information of the target document, indicating the document structure generated based on the document generation request. The apparatus 1000 further includes a determining module 1030 configured to determine corresponding configuration information for one or more document portions included in the target document based on interaction with the structural information. The apparatus 1000 also includes a generating template 1040 configured to generate the target document based on the corresponding configuration information of one or more document portions.

[0117] In some embodiments, the generation template 1040 is further configured to determine a generation mode of the target document based on the relationship between one or more document parts, the generation mode indicating at least the generation order of one or more document parts; and to generate corresponding main content of one or more document parts according to the generation mode, based on the corresponding configuration information of one or more document parts respectively.

[0118] In some embodiments, determining the generation mode of the target document includes at least one of the following: in response to determining that there is no dependency between a set of document parts among a plurality of document parts, determining that the generation order of the set of document parts is concurrent generation order, or in response to determining that a first document part among a plurality of document parts depends on a second document part, determining that the second document part was generated before the first document part.

[0119] In some embodiments, the relationship between multiple document sections includes at least one of the following: a dependency relationship indicated by the corresponding configuration information of the multiple document sections, a hierarchical relationship indicated by the document structure of the target document, or a dependency relationship determined by a machine learning model based on the titles of the multiple document sections.

[0120] In some embodiments, the receiving module 1010 is further configured to present a template selection interface indicating one or more candidate document templates; and in response to the selection of a target template among the one or more candidate document templates, to determine a target template that can be used for the generation of a target document.

[0121] In some embodiments, the determining module 1030 is further configured to receive a configuration editing instruction for a second document portion of one or more document portions; in response to the configuration editing instruction, present content description information for the second document portion, the content description information indicating the generation requirements for the main content of a third document portion and being generated based on a target template; and update the content description information as at least a part of the configuration information for the second document portion based on user input for the content description information.

[0122] In some embodiments, the generation module 1040 is further configured to, in response to determining that dynamic generation is not enabled for a first group of document portions indicated by the target template, determine the title of the first group of document portions based on generation requirements; and in response to determining that dynamic generation is enabled for a second group of document portions indicated by the target template, determine the title of one or more sub-parts included in the document portions in the second group of document portions based on data retrieval results for the document portions.

[0123] In some embodiments, the apparatus 1000 further includes a reference data source information presentation template configured to receive a data source configuration instruction for a first document portion of one or more document portions; and in response to the data source configuration instruction, to present information about one or more reference data sources, which are configured by the target template for the first document portion.

[0124] In some embodiments, the reference data source information presentation template is further configured to determine, based on update indications related to one or more reference data sources, at least one target data source that will be referenced when generating the main content of the first document portion, as at least part of the configuration information of the first document portion.

[0125] In some embodiments, the generation module 1040 is further configured to, for at least one target data source, obtain reference data for the first document portion from the target data source according to a data query mode corresponding to the target data source; and generate the main content of the first document portion as part of the target document based on the reference data obtained for each of the at least one target data source.

[0126] In some embodiments, obtaining reference data for the first document portion from the target data source includes one of the following: in response to the target data source including a knowledge base, obtaining at least one knowledge fragment from the knowledge base that matches the generation requirements of the first document portion as reference data; in response to the target data source including a user-specified data object, retrieving at least one knowledge fragment that matches the generation requirements from a plurality of knowledge fragments for the data object as reference data, wherein the plurality of knowledge fragments are obtained by vectorization processing of the data object; or in response to the target data source including text input by the user, determining the text as reference data.

[0127] In some embodiments, the reference data source information presentation template is further configured to, in response to a data source configuration instruction for one or more reference data sources, present a data source configuration entry; receive first user input specifying one or more data objects through the data source configuration entry; and, in response to the first user input, identify one or more data objects as at least a portion of at least one target data source.

[0128] In some embodiments, the reference data source information presentation template is further configured to present a data source configuration entry in response to a data source configuration instruction for one or more reference data sources; receive second user input through the data source configuration entry to deselect at least one of the one or more reference data sources; and remove at least one reference data source from at least one target data source in response to the second user input.

[0129] In some embodiments, the apparatus 1000 further includes a preview module configured to include receiving a generation instruction for a third document portion of one or more document portions; and, in response to the generation instruction, presenting preview content generated for the third document portion based on configuration information of the third document portion, wherein determining the corresponding configuration information of the one or more document portions includes: receiving a configuration update instruction for the third document portion in response to the presentation of the preview content of the third document portion; and updating the configuration information for the third document portion based on the configuration update instruction.

[0130] In some embodiments, the apparatus 1000 further includes an identifier presentation module configured to present an identifier of one or more reference data sources configured for the target text portion in response to the selection of a target document portion in one or more document portions.

[0131] In some embodiments, the apparatus 1000 further includes a template creation module configured to update the configuration information of a target template based on receiving an adjustment instruction for the target template; and to create a document template that can be used by a target user based on the updated configuration information of the target template.

[0132] As shown in Figure 11, electronic device 1100 is in the form of a general-purpose electronic device. Components of electronic device 1100 may include, but are not limited to, one or more processors 1110, memory 1120, storage device 1130, one or more communication units 1140, one or more input devices 1150, and one or more output devices 1160. Processor 1110 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1120. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 1100.

[0133] Electronic device 1100 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 1100, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1120 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 1130 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 1100.

[0134] Electronic device 1100 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG11, disk drives for reading or writing from removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading or writing from removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 1120 may include computer program product 1125 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0135] Communication unit 1140 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 1100 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 1100 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0136] Input device 1150 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1160 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 1100 can also communicate with one or more external devices (not shown) via communication unit 1140 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 1100, or with any device that enables electronic device 1100 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).

[0137] 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.

[0138] 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.

[0139] These computer-readable program instructions can be provided to a processor 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 processor 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.

[0140] 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.

[0141] 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.

[0142] 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 document generation method, comprising: Receive a document generation request for a target document, the document generation request indicating at least the generation requirements for the target document and a target template for generating the target document; Present the structural information of the target document, the structural information indicating the document structure generated based on the document generation request; Based on the interaction with the structural information, the corresponding configuration information of one or more document portions included in the target document is determined; and The target document is generated based on the corresponding configuration information of the one or more document portions.

2. The method according to claim 1, further comprising: Receive a data source configuration instruction for a first document portion of the one or more document portions; as well as In response to the data source configuration instruction, information about one or more reference data sources is presented, which are configured by the target template for the first document portion.

3. The method according to claim 2, wherein determining the corresponding configuration information of one or more document portions included in the target document comprises: Based on update instructions related to the one or more reference data sources, at least one target data source that will be referenced in generating the main content of the first document portion is determined as at least a part of the configuration information of the first document portion.

4. The method of claim 3, wherein determining the at least one target data source comprises: In response to a data source configuration instruction for one or more reference data sources, a data source configuration entry is presented; The data source configuration entry receives first user input specifying one or more data objects. as well as In response to the first user input, the one or more data objects are identified as at least a portion of the at least one target data source.

5. The method of claim 3, wherein determining the at least one target data source comprises: In response to a data source configuration instruction for one or more reference data sources, a data source configuration entry is presented; The data source configuration entry receives second user input to deselect at least one of the one or more reference data sources. as well as In response to the second user input, the at least one reference data source is removed from the at least one target data source.

6. The method of claim 3, wherein generating the target document comprises: For the target data source in the at least one target data source, reference data for the first document portion is obtained from the target data source according to the data query mode corresponding to the target data source; as well as Based on the reference data obtained for each of the at least one target data source, the main content of the first document portion is generated as part of the target document.

7. The method of claim 6, wherein obtaining reference data for the first document portion from the target data source comprises one of the following: In response to the target data source including a knowledge base, at least one knowledge fragment matching the generation requirements of the first document portion is retrieved from the knowledge base as the reference data. In response to the target data source including a user-specified data object, at least one knowledge fragment matching the generation requirement is retrieved from a plurality of knowledge fragments for the data object as reference data, wherein the plurality of knowledge fragments are obtained through vectorization processing of the data object, or In response to the target data source including text entered by the user, the text is identified as the reference data.

8. The method of claim 1, wherein determining the corresponding configuration information for the one or more document portions includes: Receive configuration editing instructions for the second document section of one or more document sections; In response to the configuration editing instruction, content description information for the second document portion is presented, the content description information indicating the generation requirements for the main content of the third document portion, and is generated based on the target template; 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 for the second document section.

9. The method according to claim 1, wherein the document structure is determined in the following manner: In response to determining that dynamic generation is not enabled for the first group of document portions indicated by the target template, the title of the first group of document portions is determined based on the generation requirements; and In response to determining that dynamic generation is enabled for the second set of document portions indicated by the target template, for a document portion in the second set of document portions, the title of one or more sub-parts included in the document portion is determined based on the data retrieval results for that document portion.

10. The method according to claim 1, further comprising: Receive a generation instruction for a third document portion of the one or more document portions; as well as In response to the generation instruction, based on the configuration information of the third document portion, a preview of the generated content for the third document portion is presented, and The configuration information for determining the one or more document portions includes: In response to the presentation of the preview content of the third document section, receive a configuration update instruction for the third document section; as well as Based on the configuration update instruction, update the configuration information for the third document section.

11. The method according to claim 1, further comprising: In response to the selection of a target document portion among the one or more document portions, the identifiers of one or more reference data sources configured for the target document portion are presented.

12. The method of claim 1, wherein the target template is determined by the following manner: Presents a template selection interface indicating one or more candidate document templates; and In response to the selection of a target template from the one or more candidate document templates, a target template that can be used for the generation of the target document is determined.

13. The method of claim 1, wherein the document generation request is initiated by the target user, and the method further comprises: Based on the received adjustment instruction for the target template, update the configuration information of the target template; as well as Based on the updated configuration information of the target template, a document template that can be used by the target user is created.

14. The method of claim 1, wherein generating the target document comprises: Based on the relationship between the one or more document parts, a generation pattern for the target document is determined, wherein the generation pattern at least indicates the generation order of the one or more document parts; as well as According to the generation mode, the corresponding main content of the one or more document parts is generated based on the corresponding configuration information of the one or more document parts.

15. The method of claim 14, wherein determining the generation mode of the target document comprises at least one of the following: In response to determining that there is no dependency between a group of document portions among the plurality of document portions, the generation order of the group of document portions is determined to be either sequential or concurrent generation order. In response to determining that a first document portion of the plurality of document portions depends on a second document portion, it is determined that the second document portion was generated before the first document portion.

16. The method of claim 14, wherein the relationship between the plurality of document portions includes at least one of the following: The dependencies indicated by the corresponding configuration information in the multiple document sections. The hierarchical relationship indicated by the document structure of the target document, or Dependencies are determined using a machine learning model based on the headings of the multiple document sections.

17. An apparatus for document generation, comprising: The template receiving method is configured to receive a document generation request for a target document, the document generation request indicating at least generation requirements for the target document and a target template for generating the target document; A presentation template is configured to present structural information of the target document, the structural information indicating the document structure generated based on the document generation request; The template is determined and configured to determine the corresponding configuration information of one or more document portions included in the target document based on the interaction with the structural information. as well as A template is generated, configured to generate the target document based on the corresponding configuration information of the one or more document portions.

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

19. 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 16.

20. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 16.

Images