Document generation method, apparatus, device, and storage medium

Abstract

According to an embodiment of the present disclosure, a document generation method, apparatus, device and storage medium are provided. The method comprises determining a plurality of document parts included in a target document to be generated and document configuration information for the target document, the document configuration information at least comprising respective configuration information of the plurality of document parts; determining a generation mode of the target document based on a relationship between the plurality of document parts, the generation mode at least indicating a generation order of the plurality of document parts; and generating respective main body contents of the plurality of document parts based on the respective configuration information of the plurality of document parts respectively according to the generation mode. Thus, by determining the configuration of the plurality of document parts of the target document and the generation mode to generate the main body contents of the plurality of document parts, the needs of different users for document generation can be fully met, the flexibility and convenience of document generation are improved, and the quality and efficiency of document generation can be improved.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a document generation method, apparatus, device and computer readable storage medium. BACKGROUND

[0002] Currently, a machine learning model can be utilized to generate document content. Through training on a large amount of document data, the machine learning model can learn language rules and patterns, thereby being able to automatically generate new document content. Such machine learning models have been widely applied in content creation, data analysis and other fields, thereby providing users with convenient and efficient document generation services. SUMMARY

[0003] In a first aspect of the present disclosure, a document generation method is provided. The method comprises: determining a plurality of document parts included in a target document to be generated and document configuration information for the target document, the document configuration information at least including respective configuration information of the plurality of document parts; determining a generation mode of the target document based on a relationship between the plurality of document parts, the generation mode at least indicating a generation order of the plurality of document parts; and generating respective subject content of the plurality of document parts based on the respective configuration information of the plurality of document parts, respectively, in accordance with the generation mode.

[0004] In a second aspect of the present disclosure, a document generation apparatus is provided. The apparatus comprises: a configuration information determination module configured to determine a plurality of document parts included in a target document to be generated and document configuration information for the target document, the document configuration information at least including respective configuration information of the plurality of document parts; a generation mode determination module configured to determine a generation mode of the target document based on a relationship between the plurality of document parts, the generation mode at least indicating a generation order of the plurality of document parts; and a subject content generation module configured to generate respective subject content of the plurality of document parts based on the respective configuration information of the plurality of document parts, respectively, in accordance with the generation mode.

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

[0006] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The computer readable storage medium has stored thereon a computer program, the computer program being executable by a processor to implement the method of the first aspect.

[0007] It is to be understood that the content described in this section is not intended to limit key or important features of the embodiments of the present disclosure nor restrict the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0008] The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0009] FIG. 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented is shown;

[0010] FIG. 2 A flowchart showing an example process of document generation according to some embodiments of the present disclosure is shown;

[0011] FIGS. 3A-3C A schematic diagram showing an example interface for creating a document template according to some embodiments of the present disclosure is shown;

[0012] FIGS. 4A-4D A schematic diagram showing an example interface for generating a document using a template according to some embodiments of the present disclosure is shown;

[0013] FIG. 5 A schematic block diagram showing an example apparatus for document generation according to certain embodiments of the present disclosure is shown; and

[0014] FIG. 6 A block diagram showing an electronic device in which one or more embodiments of the present disclosure can be implemented is shown. DETAILED DESCRIPTION

[0015] It can be understood that, before using the technical solutions disclosed by the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the scope of use, the scenario of use, etc. should be informed to the user and the authorization of the user should be obtained in accordance with relevant laws and regulations.

[0016] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the electronic device, application program, server or storage medium, etc. software or hardware performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0017] As an optional but non-limiting implementation, in response to receiving the active request of the user, the manner of sending the prompt information to the user may be, for example, a pop-up window manner, in which the prompt information may be presented in the form of text. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0018] It can be understood that the above notification and user authorization obtaining process is only illustrative, and does not limit the implementation of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0019] It can be understood that the data involved in the technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the scope of protection of the present disclosure.

[0021] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiment described in the same section / subsection and / or a different section / subsection in any manner.

[0022] 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 can include one or more intermediate steps.

[0023] In the description of embodiments of the present disclosure, the term "comprising" and similar terms are to be understood as open-ended, i.e., "including but not limited to". The term "based on" is to be understood as "based at least in part on". The term "one embodiment" or "the embodiment" is to be understood as "at least one embodiment". The term "some embodiments" is to be understood as "at least some embodiments". Other explicit and implicit definitions can also be included below. The terms "first", "second", etc. can refer to different or the same objects. Other explicit and implicit definitions can also be included below.

[0024] As used herein, the term "component" can refer to any suitable model, module, unit, etc. used for implementing a specific effect. Such a component can provide a corresponding output based on the provided input, and can include any suitable operation, operation, etc. One example of a component is an algorithm. In the following, some embodiments of the present disclosure will be mainly described with reference to an algorithm, but it should be understood that such embodiments are also applicable to other types of components.

[0025] It can be understood that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, the obtaining, use, storage or deletion of the data) should comply with the requirements of the corresponding laws and regulations and relevant provisions.

[0026] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the information involved in the present disclosure should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means according to relevant laws and regulations, wherein the relevant user can include any type of right subject, such as an individual, an enterprise or a group.

[0027] For example, in response to receiving the active request of the user, the prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require the information of the relevant user to be obtained and used, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0028] As an optional but non-limiting implementation manner, in response to receiving the active request of the relevant user, the prompt information is sent to the relevant user in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0029] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure. The enabling of the digital assistant related functions of the embodiments of the present disclosure, the data obtained, the processing and storage manner of the data, etc. should be authorized in advance by the user and other right subjects associated with the user, and should comply with the relevant laws and regulations, the agreement rules between the right subjects.

[0030] As used herein, the term “model” can learn the relationship between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes input and provides a corresponding output by using multiple layers of processing units. Neural network model is one example of a model based on deep learning. In this document, “model” can also be referred to as “machine learning model”, “learning model”, “machine learning network” or “learning network”, which are used interchangeably herein.

[0031] As used herein, 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 in a web page, a word document, a portable document format (PDF) document, etc. In embodiments of the present disclosure, a document can have any suitable type of content, including but not limited to text, tables, pictures, formulas, and the like.

[0032] As used herein, the term “document section” can refer to a portion of a document used to organize content. Depending on the specific implementation, a document section can have different granularity. For example, a document section can be a chapter. As another example, a document section can be a paragraph. Furthermore, although both are referred to as document sections, multiple document sections in the same document can have a hierarchy. For example, one document section can be a next level of another document section. A document section can have a title, a body, and optionally auxiliary text (e.g., annotations, footnotes, etc.). In particular, if document section A is a next level of document section B, then document section A can be considered as at least a portion of the body of document section B.

[0033] As used herein, “document template” or “template” can refer to an electronic, computer- processable file that describes how to generate a document.

[0034] As briefly described above, machine learning models can be applied in the field of content creation, data analysis, etc. In document generation, one common way is to generate each chapter of a document sequentially. However, this approach can cause long overall generation time of the document, long waiting time for the user, etc. Another possible way is to generate each chapter of a document concurrently. Although this approach can speed up the generation of the document, it ignores the possible association between different chapters. Therefore, doing so can result in the generated document lacking association or coherence between different chapters.

[0035] To this end, in embodiments of the present disclosure, a scheme for document generation is provided. In the scheme, a plurality of document parts included in a target document to be generated and document configuration information for the target document are determined, the document configuration information at least including respective configuration information of the plurality of document parts. Based on relationships between the plurality of document parts, a generation mode of the target document is determined, the generation mode at least indicating a generation order of the plurality of document parts. According to the generation mode, respective subject contents of the plurality of document parts are generated based on respective configuration information of the plurality of document parts.

[0036] In this way, by determining the configuration and generation mode of the plurality of document parts of the target document, the subject contents of the plurality of document parts are generated. In this way, in the document generation, the association that can exist between different document parts is considered. The generation mode of the document is determined according to this association. In this way, a balance between the generation quality and the generation efficiency of the document can be achieved.

[0037] Example Environment

[0038] FIG. 1 A schematic diagram showing an example environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 involves an application management platform 110, which can support the creation of applications and / or the running of applications. In some embodiments, the part of the application management platform 110 for supporting the creation of applications can also be referred to as an application creation part. In some embodiments, the part of the application management platform 110 for supporting the running of applications can also be referred to as an application running part.

[0039] As shown, the application creation part can provide a creation and publishing environment for applications for users 105. The users 105 can be referred to as application creation users, creators. In some embodiments, the application creation part can be a low-code platform, which provides a collection of tools for application creation. The application creation part can support the visual development of various types of applications, so that developers can skip the process of manual coding, and accelerate the development cycle and cost of applications. The application creation part can support any suitable platform for users to develop one or more types of applications, which can include, for example, a platform based on application platform as a service (aPaaS). Such a platform can enable efficient development of applications by users, enabling operations such as application creation, adjustment of application functions, etc.

[0040] The application creation portion can be deployed locally at the terminal device of the user 105, and / or can be supported by a server device. For example, the terminal device of the user 105 can run a client of the application creation portion, which can support the user's interaction with the application creation portion provided by the server. In the case that the application creation portion is run locally at the terminal device of the user, the user 105 can directly interact with the local application creation portion using the terminal device. In the case that the application creation portion is run at the server device, the server device can implement the service provision to the client run at the terminal device based on the communication connection between the server device and the terminal device. The application creation portion can present a corresponding interface 130 to the user 105 based on the operation of the user 105, to output and / or receive information related to the application creation to / from the user 105.

[0041] In some embodiments, the application creation portion can be associated to a corresponding database, in which data or information required by the application creation process supported by the application creation portion is stored. For example, the database can store the code and description information corresponding to each functional module used to compose the application, etc. The application creation portion can also perform operations such as calling, adding, deleting, updating, etc. on the functional modules in the database. The database can also store operations executable on different functional blocks. For example, in the scenario of creating an application, the application creation portion can call the corresponding functional blocks from the database to build the application.

[0042] In embodiments of the present disclosure, the user 105 can create a target application 120 on the application creation portion as needed, and publish the target application 120. The target application 120 can be published to any suitable application running portion, as long as the application running portion can support the running of the target application 120. After publication, the target application 120 can be used for operation by one or more terminal users 145. The terminal user 145 can operate the target application 120 through the associated terminal device 146, and further interact with the application management platform 110. The terminal user 145 can be referred to as a terminal user of the target application 120. In some embodiments, the target application 120 can include or be implemented as a digital assistant 122.

[0043] The digital assistant 122 can be configured to have the ability of intelligent conversation. In FIG. 1In the illustrated example, the digital assistant 122 can be integrated within the target application 120 as part of the target application 120 to assist in performing task processing within the target application 120. In other examples, the digital assistant 122 can be configured as a standalone application, such as a web application or other type of application. In such examples, the digital assistant 122 and the target application 120 can be considered as the same application. The digital assistant 122 is provided to assist users in various task processing needs in different applications, scenarios. During the interaction with the digital assistant 122, the user inputs an interaction message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 is capable of supporting the user to input a query in a natural language manner, and perform a task and provide a reply based on the understanding of the natural language input and logical reasoning capability.

[0044] In some embodiments, the digital assistant 122 can interact with the end user 145 as a contact of the end user 145. 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 with the end user 145. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0045] For each end user 145, the application runtime portion of the client can present various interfaces of the target application 120 in a client interface. In FIG. 1 In the illustrated example, an interaction window 142 of the end user 145 with the digital assistant 122 is shown, such as a conversation window with the digital assistant 122. The end user 145 can input a conversation message in the conversation window, and the target application 120 can determine a reply message of the digital assistant 122 based on the created configuration information and present to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 can include messages in multiple modalities, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0046] Similar to the application creation part, the application running part can be deployed locally at the terminal device of each end user 145, and / or can be supported by the service end device. For example, the terminal device of the end user 145 can run a client of the application running part, which can support the interaction of the user with the application running part provided by the service end. In the case that the application running part is run locally at the terminal device of the user, the end user 145 can directly interact with the local application running part by using the terminal device. In the case that the application running part is run at the service end device, the service end device can implement the service provision to the client run in the terminal device based on the communication connection between the terminal device. The application running part can present a corresponding application page to the end user 145 based on the operation of the end user 145, to output and / or receive information related to the application use to / from the end user 145.

[0047] In some embodiments, the implementation of at least part of the functions of the target application 120, and / or the implementation of at least part of the functions of the digital assistant 122 in the target application 120 can be implemented based on a machine learning model (referred to as model for short). During the creation or running of the target application 120, one or more models 155, such as the capabilities of the model 155, can be invoked. In the target application 120, the digital assistant 122 can utilize the model 155 to understand the user input, and respond to the user input based on the output of the model 155, such as providing a reply to the user input.

[0048] During the creation process, the test of the target application 120 by the application management platform 110 needs to utilize the model 155 to determine that the running result of the target application 120 meets the expectation. During the running process, in response to different operation requests of the user of the target application 120, the application running part can need to utilize the model 155 to determine the response result to the user.

[0049] Although shown as being independent of the application management platform 110, one or more models 155 can be run on the application management platform 110, or other remote servers. In some embodiments, the model 155 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). The language model can have the ability of question and answer by learning from a large amount of corpus. The model 155 can also be based on other appropriate models.

[0050] In some embodiments, the target application 120 can provide a writing function, e.g., the target application 120 can be a writing application or can include a writing component. Such a writing function can be implemented with the aid of one or more models 155, and thus also referred to as "intelligent writing." In some embodiments, a user 105 can generate or create a document template for writing through the application management platform 110. The created document template can be distributed to end users 145 of the target application 120. In some embodiments, the application management platform 110 can support a template creation mode from scratch. For example, a user 105 can input requirements for a template to be generated to initiate a template creation process. In some embodiments, the application management platform 110 can support a template creation mode based on an existing document (also referred to as a sample or reference document). For example, a user 105 can specify an existing document to initiate a template creation process.

[0051] In some embodiments, an end user 145 can write, i.e., generate a document, through the target application 120. The application management platform 110 can support various suitable document generation modes. In some embodiments, the application management platform 110 can support a template-based document generation mode. For example, an end user 145 can generate a document with a template created and distributed by a user 105. In some embodiments, the application management platform 110 can support an existing document-based document generation mode. For example, an end user 145 can specify an existing document as a reference to generate a target document. In some embodiments, the application management platform 110 can support a document generation mode from scratch. For example, an end user 145 can input requirements for a document to be generated to initiate a document generation process.

[0052] The application management platform 110 can run on a suitable electronic device. An electronic device herein can be any type of device with computing capability, including an end device or a server device. An end device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices or any combination thereof. A server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. In some embodiments, the application management platform 110 can be implemented based on a cloud service.

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

[0056] Example Process

[0057] FIG. 2 A flowchart of a document generation process 200 according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to... FIG. 1 The environment 100 is used to describe process 200. Process 200 can be implemented in... FIG. 1The application management platform 110 is located there. As discussed above, the application management platform 110 has an application creation section and an application execution section. The application creation section allows user 105 to generate or create document templates for writing through the application management platform 110. In the application execution section, the application management platform 110 can support document generation based on document templates. In some examples, process 200 can be implemented in the process of generating or creating document templates. In such examples, the user described by referring to process 200 can be the creator of the template, such as user 105. In other examples, process 200 can be a document generation process based on document templates. In such examples, the user described by referring to process 200 can be the user of the template, such as end user 145.

[0058] refer to FIG. 2 In box 210, the application management platform 110 determines the multiple document sections included in the target document to be generated and the document configuration information for the target document. The document configuration information includes at least the corresponding configuration information for the multiple document sections. In some embodiments, the application management platform 110 may determine the multiple document sections (e.g., multiple chapters, etc.) and corresponding configuration information by receiving an operation from user 105 through an interface presented in the application creation section. In other embodiments, the application management platform 110 may determine the multiple document sections and corresponding configuration information by receiving an operation from end user 145 through an interface presented in the application running section. These two implementation methods will be described in detail below with reference to example interface diagrams.

[0059] FIGS. 3A-3C Example interfaces 300A, 300B, and 300C generated from documentation according to some embodiments of this disclosure are shown. In embodiments of this disclosure, interfaces 300A, 300B, and 300C can be generated by... FIG. 1 The application creation section of the application management platform 110 shown is provided.

[0060] like FIGS. 3A-3C As shown, during the creation of the document template, the application management platform 110 can receive modifications to the corresponding configuration information of multiple document sections from user 105. The following will describe in detail the configuration for multiple document sections on user 105's side.

[0061] refer to FIG. 3ADuring the document template generation process, an editing area 310 for the document structure can be presented on the interface 300A. The document structure may include one or more document sections. The document sections discussed herein may refer to chapters or paragraphs of a document. In some embodiments, each document section may have a corresponding title, also known as a chapter title or paragraph title. As an example, the editing area 310 may present titles for multiple document sections, such as "Industry Development Overview," "Industry Origins," ..., "Industry Consumer Behavior Analysis," etc. The editing area 310 includes multiple editable items corresponding to the multiple document sections, and the title of each document section can be presented in each editable item. Editable items may, for example, include editable item 311 with the title "Industry Development Overview," editable item 312 with the title "Industry Origins," ..., editable item 319 with the title "Industry Consumer Behavior Analysis," etc. Through the editable items, the corresponding document sections can be edited and configured.

[0062] In some embodiments, each editable item corresponding to a document section may include a configuration entry 320 for that document section. The configuration entry 320 can be any suitable type of entry for configuring the corresponding document section. In one example, as shown in the figure, the configuration entry 320 can be presented in an editable item after receiving a preset operation from user 105 for that editable item. The preset operations discussed herein may include any suitable type of operation such as click operations (e.g., single-click, double-click, etc.), long-press operations, swipe operations, etc., and are not limited here. In another example, the configuration entry can be presented directly in each editable item. It should be understood that the presentation method of the configuration entry can be set according to actual needs and is not limited here. In some embodiments, after receiving a preset operation from user 105 on the configuration entry 320, the application management platform 110 can present a configuration panel 325. The configuration panel 325 can also be a configuration window, configuration page, etc. Through the configuration panel 325, the configuration of the corresponding document section by user 105 can be received.

[0063] In some embodiments, configuration panel 325 may include content description information for a corresponding document section, which may indicate the generation requirements for the main content of that document section (e.g., the generation requirement example in box 326). Based on user input regarding the content description information, application management platform 110 may update the content description information as at least a part of the configuration information for that corresponding document section. Here, user input may be content description information entered by user 105 in text or voice. In some embodiments, configuration panel 325 may also include a reference entry 330. Application management platform 110 may receive a preset operation from user 105 on entry 330, thereby presenting a reference data source interface 300B. In addition, application management platform 110 may also receive a preset operation from user 105 on the add control 332 in the reference data source interface 300B, thereby presenting at least one reference data source for generating partial configuration information of the target document.

[0064] refer to FIG. 3C In some embodiments, the application management platform 110 may also present document preview information on the interface 300C after receiving a preview instruction from user 105. This document preview information may indicate document generation requirements. For example, upon receiving a preset operation (e.g., trigger) from user 105 on the document preview control 340, panel 342 is presented to receive document generation requirements. Document generation requirements may include, for example, the subject of the target document or supplementary information. As an example, the application management platform 110 may receive supplementary information from user 105 through entry point 344 for uploading text, entry point 345 for uploading URL links, entry point 346 for uploading attachments, etc., as configuration information for the target document. It should be understood that supplementary information may also include any other suitable information, without limitation.

[0065] Furthermore, at least through the various configurations described above, the application management platform 110 can receive a document template generation instruction from user 105 and execute the generation of the target document. For example, upon receiving a preset operation (e.g., triggering) of the generate button 348 by user 105, the target document is generated. It should be understood that in other embodiments, the document configuration information may also include other configuration information regarding the target document. Reference will be made below. FIG. 2 Let's discuss in detail the specific process of generating the target document.

[0066] FIGS. 4A-4D Example interfaces 400A to 400D generated from documentation according to some embodiments of this disclosure are shown. In embodiments of this disclosure, interfaces 400A to 400D can be generated by... FIG. 1 The application management platform 110 shown is provided by the application operation section.

[0067] like FIGS. 4A-4D As shown, after end user 145 selects a document template, based on the multiple document sections presented, application management platform 110 can receive modifications to the corresponding configuration information of the multiple document sections by end user 145. The following will describe in detail the configuration of the multiple document sections on the end user 145 side.

[0068] refer to FIG. 4A After end user 145 selects a document template (such as the document template already created as discussed above), interface 400A can display an editing area 410 and a navigation area 420 for the document structure. The document structure may include one or more document sections. Navigation area 420 may include navigation information about the document structure, such as the titles and hierarchical relationships of multiple document sections. Similar to editing area 310 on interface 300A, editing area 410 may include multiple editable items corresponding to multiple document sections, and each editable item may contain a configuration entry 420 for the corresponding document section. Configuration functions similar to configuration entry 320 can be implemented through configuration entry 420. For example, combined with... FIG. 4B After receiving a preset operation from the end user 145 on the configuration entry 420, the application management platform 110 can display a configuration panel 425, similar to the configuration panel 325, on the interface 400B. Through the configuration panel 425, the application management platform 110 can receive similar configurations from the end user 145 for corresponding document sections, which will not be elaborated further here. In some embodiments, the configuration panel 325 may also include a reference material entry 430. The application management platform 110 can receive a preset operation from the end user 145 on the entry 430, thereby displaying a configuration panel 425, similar to the configuration panel 325. FIG. 3B The reference data source interface 300B shown is used to provide end user 145 with the option to configure the target document.

[0069] Furthermore, at least through the various configurations described above, the application management platform 110 can receive document generation instructions from the end user 145 and execute the generation of the target document. For example, upon receiving a preset operation (e.g., trigger) from the end user 145 on the document generation control 440, the target document is generated. It should be understood that in other embodiments, the document configuration information may also include other configuration information regarding the target document. Reference will be made below. FIG. 2 Let's discuss in detail the specific process of generating the target document.

[0070] By configuring multiple document portions of the target document in the above embodiments, the document generation needs of different users can be flexibly met, and the quality and efficiency of document generation can be effectively improved.

[0071] Return to reference FIG. 2In box 220, based on the relationships between multiple document parts, the application management platform 110 determines a generation pattern for the target document. The generation pattern at least indicates the generation order of the multiple document parts. In some embodiments, the relationships between the multiple document parts may include hierarchical relationships and / or dependency relationships. For example, one document part may be a level below another document part. As another example, one document part may depend on another document part. It should be understood that in other embodiments, any other suitable relationships may exist between the multiple document parts. In some embodiments, in addition to the generation order of the multiple document parts, the generation pattern may also indicate other information about how the target document is generated, such as the reuse of reference data sources (e.g., whether a reference data source for one document part is applicable to another document part), etc.

[0072] In some embodiments, the relationship between multiple document sections may include dependencies indicated by the corresponding configuration information of the multiple document sections. (See reference) FIG. 3B The application management platform 110 can receive relationship configuration instructions for multiple document parts, such as receiving a preset operation from user 105 or end user 145 on the dependency configuration entry 338 on interface 300B. If the application management platform 110 receives the relationship configuration instruction, it can present information about at least one of the multiple document parts. Based on the selection of a target document part by user 105 or end user 145, the application management platform 110 can determine that the generation of a certain document part will depend on the target document part as at least part of the configuration information of that document part. Thus, user 105 or end user 145 can flexibly configure the dependencies of multiple document parts according to specific needs.

[0073] 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.

[0074] In some embodiments, to determine the generation mode of a target document, if the application management platform 110 determines that there is no dependency between a group of document parts among multiple document parts, it can determine the generation order of the group of document parts as a concurrent generation order. As an example, a group of document parts that are determined to need to be generated concurrently can be displayed on the interface 130 or the client interface in a concurrent presentation manner. Exemplarily, in such an embodiment, the hierarchical relationship between 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.

[0075] In some embodiments, if the application management platform 110 determines that a first document portion among multiple document portions depends on a second document portion, it can determine that the second document portion is generated before the first document portion. As an example, for a second document portion and a first document portion that need to be generated sequentially, the second document portion can be presented before the first document portion on the interface 130 or the client interface. Exemplarily, in such an embodiment, the hierarchical relationship of the multiple document portions can still be disregarded, and the corresponding generation mode can be determined based on the dependency relationship. In other words, regardless of whether the first document portion and the second document portion belong to the same level or different levels, the second document portion is determined to be generated before the first document portion because the first document portion depends on the second document portion.

[0076] 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 the 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 was 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. For example, refer to... FIG. 3A The document portion corresponding to edit item 312 is a sub-part of the document portion corresponding to edit item 311. The application management platform 110 can determine that the document portion corresponding to edit item 311 is generated after the document portion corresponding to edit item 312. However, if dependencies need to be considered, the priority of hierarchical relationships and dependencies can be preset. That is, if a conflict arises when determining the generation mode based on the hierarchical relationships and dependencies of certain document portions, the priority of which hierarchical relationship or dependency should be prioritized can be determined based on the preset priority.

[0077] In some embodiments, the fourth document portion may be generated as follows: based on the main content generated for at least one third document portion, the application management platform 110 may determine prompting information for a machine learning model, the prompting information instructing the machine learning model to summarize the main content of at least one third document portion. The application management platform 110 may provide the prompting information to the machine learning model to obtain the output of the machine learning model, and determine the main content of the fourth document portion based on the output of the machine learning model. For example, refer to... FIG. 4C Document portions 453 and 454 are sub-parts of document portion 452. The application management platform 110 can determine prompts for the machine learning model based on the main content of document portions 453 and 454. For example, the prompts can instruct the machine learning model to summarize the content of document portions 453 and 454. Then, the prompts can be given to the machine learning model, which can generate content based on the prompts, which can serve as the main content of document portion 452. It should be understood that this is merely an example; in other embodiments, the main content of the fourth document portion can be generated in conjunction with the main content of at least one third document portion.

[0078] refer to FIG. 2 In box 230, according to the generation mode, the application management platform 110 generates the corresponding main content of multiple document parts based on the corresponding configuration information of each document part. In some embodiments, the application management platform 110 can utilize a machine learning model to generate the corresponding main content of multiple document parts. Here, based on the corresponding configuration information of multiple document parts, and according to the concurrent generation order and sequential generation order of multiple document parts related to dependencies and hierarchical relationships discussed above, the corresponding main content of multiple document parts can be generated.

[0079] In some embodiments, to generate corresponding body content for multiple document portions, for a target document portion (or any document portion) among the multiple document portions, the application management platform 110 can determine a target data source from at least one reference data source indicated by the target configuration information of the target document portion. In some embodiments, the application management platform 110 can utilize a machine learning model to determine the target data source from at least one reference data source indicated by the target configuration information. In some embodiments, the at least one reference data source may include a data object specified by the target user. For example, a reference... FIG. 3B Through local data entry point 334, the target user can select a data object. In this embodiment, the target user can be user 105 or end user 145. The data object may include, for example, documents uploaded by user 105 or end user 145 to the local device, online documents, or other data objects, etc., without limitation.

[0080] Alternatively or additionally, in some embodiments, at least one reference data source may include a knowledge base to which the target user's user set has access permissions. The user set may, for example, include users from the same enterprise, users from the same department of the enterprise, or user sets from other organizations. In this embodiment, the target user with access permissions to the knowledge base may be user 105 or end user 105, while the user with configuration permissions for the knowledge base may be user 105. It should be understood that for the same user set, there may be one or more knowledge bases to which access permissions are granted.

[0081] refer to FIG. 3B In some embodiments, the application management platform 110 may receive a knowledge configuration instruction for a target document portion among multiple document portions, and then present information about one or more candidate knowledge bases that can be used for the target template. For example, upon receiving a preset operation (e.g., trigger) on data and knowledge entry 336 by user 105 or end user 145, a panel 337 is presented to select a knowledge base. Based on the selection of a target knowledge base among one or more candidate knowledge bases, the application management platform 110 may determine that the generation of the target document portion will reference the target knowledge base as at least part of the configuration information for the target document portion.

[0082] Alternatively or additionally, in some embodiments, at least one reference data source may include a public data source. For example, the application management platform 110 may receive a preset operation from user 105 or end user 145 on the network search portal 333, thereby accessing a public data source. Public data sources may include not only data sources searchable via the Internet, but also other data sources publicly accessible, without limitation.

[0083] In some embodiments, each reference data source in at least one reference data source has a different priority for the generation of the target document, and the priority is related to the degree of association between each reference data source and the target user. In some embodiments, the priorities of each reference data source in at least one reference data source, from high to low, can be: data objects specified by the target user, knowledge bases with access permissions for the user set to which the target user belongs, and public data sources. For example, when using a machine learning model to determine the target data source, priority information for each type of data source can be set in the prompts provided to the machine learning model, so that the machine learning model can select the target data source according to the priority. It should be understood that the priorities of each reference data source can also be set in other different ways, depending on the actual situation. In this embodiment, by setting the priorities of each reference data source in this way, the flexibility of the configuration of the target document to be generated can be improved, and the user experience can be enhanced.

[0084] Furthermore, the application management platform 110 can obtain target data matching the target configuration information from the target data source, and generate the main content of the target document based on the obtained target data. In some embodiments, in order to obtain target data from the target data source, based on the target configuration information, the application management platform 110 can utilize a machine learning model to generate a data query instruction matching the target data source, and obtain the target data by executing the data query instruction on the target data source. For example, a machine learning model can be used to query data matching the target configuration information from the target data source through a data query instruction, and obtain the queried data as the target data. In some embodiments, the application management platform 110 can utilize a machine learning model to generate the main content of the target document based on the target data. In this embodiment, the generation of the main content is divided into two or more steps. Each step focuses on the execution of a subtask, such as determining the target data source, generating a query instruction, and generating content based on the queried data. In this way, the complex task of content generation can be broken down, thereby generating content that is more consistent with the configuration information.

[0085] In some embodiments, at least one reference data source is configured for a target document portion, and the priority of the at least one reference data source can influence the process of selecting a target data source from the at least one reference data source. For example, when selecting a target data source using a machine learning model, a priority indicator of the priority of the at least one reference data source can be included in the prompts provided to the machine learning model. The priority indicator can include explicit indicators, such as text describing the corresponding priority of the at least one reference data source. Alternatively or additionally, the priority indicator can include implicit indicators, such as the order of the descriptive information of the at least one reference data source in the prompts. Exemplarily, the descriptive information from the parameter data source with higher priority is listed first in the prompts. In this way, the priority of the reference data source can influence the target data acquisition process, thereby affecting the generation of the main content of the target document portion. For example, the application management platform 110 can preferentially acquire data from the reference data source with higher priority.

[0086] In some embodiments, the priority of data sources can affect or influence the generation of the main content. For example, multiple target data sources can be selected for a target document portion. When generating the main content of a target document portion based on the output of a machine learning model, the priority of multiple target data sources can affect the model application process, thereby influencing the generation of the main content of the target document portion. In some embodiments, the application management platform 110 can provide prompts to the machine learning model based on the target data obtained from multiple target data sources and the corresponding priorities of the multiple target data sources, in order to obtain the output of the machine learning model. Based on the output of the machine learning model, the application management platform 110 can generate the main content of the target document portion. In this way, when the machine learning model generates the main content based on the data obtained from each data source, data from data sources with higher priority can receive higher weight.

[0087] To enable machine learning models to perceive the priority of multiple target data sources, in some embodiments, the prompt information may include priority indicators for the respective priorities of the multiple target data sources. In some embodiments, the priority indicator may include explicit indicators, such as text describing the respective priorities of the multiple target data sources. Alternatively or additionally, in some embodiments, the priority indicator may include implicit indicators, such as the order in which the target data obtained from the multiple target data sources is presented in the prompt information. Exemplarily, target data obtained from the higher-priority target data source is presented first in the prompt information.

[0088] The above embodiments provide users with different reference data sources through an application management platform and utilize machine learning models to perceive the priority of multiple target data sources. This allows users to be configured with multiple reference sources of different priorities when generating documents, thus bringing greater convenience. Furthermore, based on multiple reference data sources, the quality of the generated target documents can be improved, meeting user needs.

[0089] refer to FIG. 4D In some embodiments, after the main content of multiple document sections has been generated, the configuration information of multiple document sections can be changed. As an example, the application management platform 110 can also receive preset operations from user 105 or end user 145 on the configuration entry 420 on the interface 400D, and present a configuration panel 425. Through the configuration panel 425, the application management platform 110 can receive corresponding configurations from user 105 or end user 145 for the corresponding document sections, which will not be elaborated further here.

[0090] In the embodiments described above, the implementation of some operations or steps may rely on machine learning models. It should be understood that different operations or steps may use the same or different machine learning models. The embodiments of this disclosure are not limited in this respect.

[0091] This disclosure generates the main content of multiple document parts by determining the configuration and generation mode for multiple document parts of the target document, which can fully meet the document generation needs of different users. This can improve the flexibility and convenience of document generation, and also improve the quality and efficiency of document generation.

[0092] Example Devices and Apparatus

[0093] FIG. 5 A schematic structural block diagram of a document generation apparatus 500 according to certain embodiments of the present disclosure is shown. The apparatus 500 may be implemented as or included in a terminal device 110. The various modules / components in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0094] As shown in the figure, the device 500 includes a configuration information determination module 510, which is configured to determine multiple document parts included in the target document to be generated and document configuration information for the target document. The document configuration information includes at least the corresponding configuration information of the multiple document parts.

[0095] The apparatus 500 also includes a generation mode determination module 520, configured to determine a generation mode of a target document based on the relationship between multiple document parts, wherein the generation mode indicates at least the generation order of the multiple document parts.

[0096] The device 500 also includes a main content generation module 530, which is configured to generate the corresponding main content of multiple document parts according to the generation mode and based on the corresponding configuration information of multiple document parts.

[0097] In some embodiments, the generation mode determination module 520 is further configured to determine the generation order of a set of document parts as concurrent generation order in response to determining that there is no dependency between a set of document parts among a plurality of document parts.

[0098] In some embodiments, the generation mode determination module 520 is further configured to determine that the second document portion is generated before the first document portion in response to determining that a first document portion among a plurality of document portions depends on a second document portion.

[0099] In some embodiments, the generation pattern determination module 520 is further configured to determine that the fourth document portion is generated after at least one third document portion in response to a hierarchical relationship between a plurality of document portions indicating that at least one third document portion among the plurality of document portions is a sub-part of a fourth document portion.

[0100] In some embodiments, the apparatus 500 further includes a document portion content generation module configured to determine prompting information for a machine learning model based on the main content generated for at least one third document portion, the prompting information instructing the machine learning model to summarize the main content of at least one third document portion; provide the prompting information to the machine learning model to obtain the output of the machine learning model; and determine the main content of a fourth document portion based on the output of the machine learning model.

[0101] 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.

[0102] In some embodiments, the main content generation module 530 is further configured to, for a target document portion among a plurality of document portions, determine a target data source from at least one reference data source indicated by the target configuration information of the target document portion; obtain target data matching the target configuration information from the target data source; and generate the main content of the target document portion based on the obtained target data.

[0103] In some embodiments, the apparatus 500 further includes a target data acquisition module, configured to generate a data query instruction matching the target data source based on target configuration information and using a machine learning model; and to acquire target data by executing the data query instruction on the target data source.

[0104] In some embodiments, at least one reference data source includes at least one of the following: a data object specified by the target user, a knowledge base to which the user set to which the target user belongs has access, or a public data source.

[0105] In some embodiments, each of the at least one reference data source has a different priority for the generation of the target document, and the priority is related to the degree of association between each reference data source and the target user.

[0106] In some embodiments, the target data source is one of a plurality of target data sources, and the apparatus 500 is further configured to provide prompting information to the machine learning model based on the target data obtained from the plurality of target data sources respectively and the corresponding priorities of the plurality of target data sources, so as to obtain the output of the machine learning model, the prompting information including priority indications for the corresponding priorities of the plurality of target data sources; and to generate the main content of the target document portion based on the output of the machine learning model.

[0107] In some embodiments, the priority indication includes: text describing the corresponding priorities of multiple target data sources, or the order of target data obtained from the multiple target data sources in the prompt message.

[0108] FIG. 6 A block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... FIG. 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. FIG. 6 The electronic device 600 shown can be used to achieve FIG. 1 Electronic devices 110.

[0109] like FIG. 6 As shown, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0110] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 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 630 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 600.

[0111] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... FIG. 6As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0112] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0113] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 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 600, or with any device that enables electronic device 600 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).

[0114] 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.

[0115] 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.

[0116] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0117] 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.

[0118] 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.

[0119] 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 method for generating a document, comprising: determining a plurality of document portions included in a target document to be generated and document configuration information for the target document, the document configuration information including at least respective configuration information of the plurality of document portions; determining a generation mode of the target document based on a relationship among the plurality of document portions, the generation mode indicating at least a generation order of the plurality of document portions; and generating respective main content of the plurality of document portions based on the respective configuration information of the plurality of document portions, respectively, in the generation mode, wherein generating the respective main content of the plurality of document portions comprises, for a target document portion of the plurality of document portions: determining a target data source from at least one reference data source indicated by target configuration information of the target document portion, wherein the target data source is one of a plurality of target data sources; providing prompt information to a machine learning model based on target data obtained from the plurality of target data sources, respectively, and respective priority of the plurality of target data sources, to obtain an output of the machine learning model, the prompt information including priority indication of the respective priority of the plurality of target data sources; and generating main content of the target document portion based on the output of the machine learning model.

2. The method of claim 1, wherein determining the generation mode of the target document comprises: in response to determining that there is no dependency relationship among a group of document portions of the plurality of document portions, determining a generation order of the group of document portions as a concurrent generation order.

3. The method of claim 1, wherein determining the generation mode of the target document comprises: in response to determining that a first document portion of the plurality of document portions depends on a second document portion, determining that the second document portion is generated before the first document portion.

4. The method of claim 1, wherein determining the generation mode of the target document comprises: in response to a hierarchical relationship among the plurality of document portions indicating that at least one third document portion of the plurality of document portions is a sub-portion under a fourth document portion, determining that the fourth document portion is generated after the at least one third document portion.

5. The method of claim 4, wherein the fourth document portion is generated by: determining prompt information for a machine learning model based on main content generated for the at least one third document portion, respectively, the prompt information indicating the machine learning model to summarize the main content of the at least one third document portion; providing the prompt information to the machine learning model to obtain an output of the machine learning model; and determining main content of the fourth document portion based on the output of the machine learning model.

6. The method of claim 1, wherein the relationship among the plurality of document portions comprises at least one of: a dependency relationship indicated by the respective configuration information of the plurality of document portions, a hierarchical relationship indicated by a document structure of the target document, or a dependency relationship determined based on titles of the plurality of document portions using a machine learning model. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 7. The method of claim 1, further comprising: acquiring the target data from the plurality of target data sources respectively, which matches the target configuration information.

8. The method of claim 7, wherein acquiring the target data from the plurality of target data sources respectively comprises: generating, based on the target configuration information, a data query instruction which matches the target data source, by using a machine learning model; and acquiring the target data by executing the data query instruction on the target data source.

9. The method of claim 7, wherein the at least one reference data source comprises at least one of: a data object specified by a target user, a knowledge base which a user set to which the target user belongs has access to, or a public data source.

10. The method of claim 7, wherein each of the at least one reference data source has a different priority for the generation of the target document, and the priority is related to an association degree of the each of the at least one reference data source to the target user.

11. The method of claim 1, wherein the priority indication comprises: a text which describes a respective priority of the plurality of target data sources, or an order of the target data acquired from the plurality of target data sources respectively in the prompt information.

12. A document generation apparatus comprising: a configuration information determination module configured to determine a plurality of document parts included in a target document to be generated and document configuration information for the target document, the document configuration information comprising at least respective configuration information of the plurality of document parts; a generation mode determination module configured to determine a generation mode of the target document based on a relationship between the plurality of document parts, the generation mode indicating at least a generation order of the plurality of document parts; and a body content generation module configured to generate respective body contents of the plurality of document parts based on respective configuration information of the plurality of document parts respectively in accordance with the generation mode, wherein the body content generation module is further configured to: for a target document part of the plurality of document parts, determine a target data source from at least one reference data source indicated by the configuration information of the target document part, wherein the target data source is one of a plurality of target data sources; provide, based on target data acquired from the plurality of target data sources respectively and respective priorities of the plurality of target data sources, a prompt information to a machine learning model to obtain an output of the machine learning model, the prompt information comprising a priority indication of the respective priorities of the plurality of target data sources; and generate a body content of the target document part based on the output of the machine learning model.

13. An electronic device comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit cause the electronic device to perform the method according to any one of claims 1 to 11. ​ ​ ​ 14. A computer-readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement the method according to any one of claims 1 to 11.

Images