Document entity creation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a document entity creation method and device, equipment and a storage medium. In the method, a creation request for a target document entity is received, and the creation request indicates a generation requirement for the target document entity. First reference information related to the creation request is determined from one or more reference data sources. And based on the first reference information and the creation request, utilizing at least one machine learning model to generate target structure information of the target document entity. In this way, useful reference information can be obtained according to actual requirements, and therefore the document structure meeting the generation requirement is determined. The determined document structure may further be used to generate a target document entity. Therefore, the target document entity generation quality and efficiency can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for document entity creation. Background Art

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

[0003] In a first aspect of the present disclosure, a method for creating a template is provided. The method includes: receiving a creation request for a target document entity, the creation request indicating a generation requirement for the target document entity; determining first reference information related to the creation request from one or more reference data sources; and generating target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model.

[0004] In a second aspect of the present disclosure, a device for template creation is provided. The device includes: a receiving module configured to receive a creation request for a target document entity, the creation request indicating a generation requirement for the target document entity; a determining module configured to determine first reference information related to the creation request from one or more reference data sources; and a generating module configured to generate target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model.

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

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments according to the present disclosure may be implemented;

[0010] Figure 2 A schematic diagram showing an example interface for initiating document entity creation according to some embodiments of the present disclosure;

[0011] Figure 3 A schematic diagram showing a knowledge base presentation interface according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A schematic diagram showing an entry interface for a user to specify a data object according to some embodiments of the present disclosure;

[0013] Figure 5 A schematic diagram showing an example interface for presenting structure information according to some embodiments of the present disclosure is shown;

[0014] Figure 6 A flowchart showing an example process of a document entity creation method according to some embodiments of the present disclosure;

[0015] Figure 7 A schematic structural block diagram showing an example apparatus for document entity creation according to some embodiments of the present disclosure; and

[0016] Figure 8 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] 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 accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of 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.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part 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.

[0019] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0020] It is understandable 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 relevant provisions.

[0021] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0022] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0023] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0024] It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not limit the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure. The activation of the digital assistant related functions, the acquired data, the processing and storage of the data, etc. in the embodiment of the present disclosure shall obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreement rules between the rights holders.

[0025] As used herein, the term "model" can learn the association 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 technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0026] As used herein, the term "document" refers to a material used to record information. In some embodiments, a document may 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 may have any suitable type of content, including but not limited to text, tables, pictures, formulas, and the like.

[0027] As used herein, the term "document section" may refer to a portion of a document used to organize content. Depending on the specific implementation, a document section may have different granularities. For example, a document section may be a chapter. As another example, a document section may be a paragraph. In addition, although all are referred to as document sections, multiple document sections in the same document may have a hierarchy. For example, one document section may be the next level of another document section. A document section may have a title, a body, and optional auxiliary text (e.g., comments, footnotes, etc.). In particular, if document section A is the next level of document section B, then document section A may be considered to be at least a portion of the body of document section B.

[0028] As used herein, a "document template" or "template" may refer to an electronic, computer-processable file that describes how to generate a document.

[0029] As briefly described above, machine learning models can be applied to content creation, data analysis and other fields. In one scenario, a service provider can provide services such as document generation to users (such as corporate users) with the help of a machine learning model. In this scenario, the machine learning model freely generates documents based on the knowledge it has learned. However, in some scenarios (for example, in scenarios for corporate users), users may have similar or unified requirements for a certain type of document. In this scenario, if the machine learning model generates documents freely, the user may need to spend more time and energy to modify the generated document. This undoubtedly reduces the efficiency of document generation.

[0030] In view of this, an embodiment of the present disclosure provides a document entity generation scheme. In the scheme, a creation request for a target document entity is received, and the creation request indicates a generation requirement for the target document entity. First reference information related to the creation request is determined from one or more reference data sources. Based on the first reference information and the creation request, target structure information of the target document entity is generated using at least one machine learning model.

[0031] It will be more clearly understood from the following description that according to the scheme of the present disclosure, reference information related to the creation request is determined from a reference data source. Subsequently, based on the reference information and the creation request, structural information of the target document entity is generated using at least one machine learning model. In this way, useful reference information can be obtained according to actual needs, so as to determine a document structure that meets the generation requirements. The determined document structure can further be used to generate a target document entity (e.g., a new document or a template for generating a new document). As a result, the quality and efficiency of the target document entity generation can be improved.

[0032] Example Environment

[0033] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. 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 portion of the application management platform 110 that supports the creation of applications can also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that supports the running of applications can also be referred to as an application running portion.

[0034] As shown in the figure, the application creation part can provide a user 105 with an environment for creating and publishing applications. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, so that developers can skip the process of manual coding and speed up the development cycle and cost of applications. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on application platform as a service (aPaaS). Such a platform can support users to efficiently develop applications and realize operations such as application creation and application function adjustment.

[0035] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part runs on the server device, the server device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application creation part can present a corresponding interface 130 to the user 105 based on the operation of the user 105, so as to output and / or receive information related to application creation to the user 105.

[0036] In some embodiments, the application creation part can be associated with a corresponding database, which stores data or information required for the application creation process supported by the application creation part. For example, the database can store the code and description information corresponding to each functional module used to make up the application. The application creation part can perform operations such as calling, adding, deleting, and updating on the functional modules in the database. The database can store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application is to be created, the application creation part can call the corresponding functional blocks from the database to build the application.

[0037] In an embodiment of the present disclosure, a user 105 can create a target application 120 as needed on the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more terminal users 145. The terminal user 145 can operate the target application 120 through an associated terminal device 146, and then interact with the application management platform 110. The terminal user 145 can be referred to as the terminal user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0038] The digital assistant 122 may be configured to have intelligent conversation capabilities. Figure 1In the example shown, the digital assistant 122 can be integrated into the target application 120 to assist in performing task processing within the target application 120 as part of the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users with various task processing requirements in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Typically, the digital assistant 122 can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.

[0039] In some embodiments, digital assistant 122 can interact with end user 145 as a contact of end user 145. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0040] For each terminal user 145, the client of the application running part can present various interfaces of the target application 120 in the client interface. Figure 1 In the example of , an interaction window 142 between the terminal user 145 and the digital assistant 122 is shown, such as a conversation window with the digital assistant 122. The terminal user 145 can enter a conversation message in the conversation window, and the target application 120 can determine the reply 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 message with the target application 120 may include a message in a multimodal form, such as a text message (e.g., natural language text), a voice message, an image message, a video message, and the like.

[0041] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each terminal user 145, and / or can be supported by the server device. For example, the terminal device of the terminal user 145 can run a client with the application running part, and the client can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the terminal user 145 can directly use the terminal device to interact with the local application running part. In the case where the application running part runs on the server device, the server device can realize the service supply to the client running in the terminal device based on the communication connection with the terminal device. The application running part can present the corresponding application page to the terminal user 145 based on the operation of the terminal user 145, so as to output and / or receive information related to the use of the application to the terminal user 145.

[0042] 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 a model). During the creation or operation of the target application 120, one or more models 155, such as the capabilities of the model 155, can be called. In the target application 120, the digital assistant 122 can use 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.

[0043] During the creation process, the application management platform 110 needs to use the model 155 to determine whether the operation result of the target application 120 meets expectations when testing the target application 120. During the operation process, in response to different operation requests of the user of the target application 120, the application operation part may need to use the model 155 to determine the response result to the user.

[0044] Although shown as being 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, the 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). The language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 may also be based on other appropriate models.

[0045] In some embodiments, the target application 120 may provide a writing function, for example, the target application 120 may be a writing application or may include a writing component. This writing function may be implemented with the aid of one or more models 155, and is therefore also referred to as "intelligent writing". In some embodiments, the user 105 may generate or create a document template for writing through the application management platform 110. The created document template may be distributed to the end user 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 input requirements for a template to be generated to initiate a template creation process. In some embodiments, the application management platform 110 may support a template creation mode based on an existing document (also referred to as a model or reference document). For example, the user 105 may specify an existing document to initiate a template creation process.

[0046] In some embodiments, the end user 145 can write, that is, 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 document generation mode based on a template. For example, the end user 145 can generate a document using a template created and distributed by the user 105. In some embodiments, the application management platform 110 can support a document generation mode based on an existing document. For example, the 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, the end user 145 can input the requirements of the document to be generated to initiate the document generation process.

[0047] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device 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 systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The 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, and the like. In some embodiments, the application management platform 110 can be implemented based on cloud services.

[0048] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. For example, although a single user interacting with the application creation portion and a single user interacting with the application execution portion are shown, in reality multiple users can access the application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0049] Some example embodiments of the present disclosure will be described in detail below with reference to the examples of the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are only examples, and various page designs may actually exist. The various graphical elements in 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 exist. The embodiments of the present disclosure are not limited in this respect.

[0050] The process described in the embodiments of the present disclosure may 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 following examples, for the sake of discussion, the description is from the perspective of the application management platform, for example Figure 1 The application management platform 110 shown. The user interface presented by the application management platform 110 can be presented via the terminal device of the user 145, and the application management platform 110 can receive user input via the terminal device of the user 145. In some embodiments, the user 145 is a 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 the user 105, and the application management platform 110 can also receive user input via the terminal device of the user 105. In some embodiments, the user 105 is the creator, manager or maintainer of the target application 120.

[0051] Example Interaction

[0052] The following will continue to refer to the attached Figures 2 to 5 Some example embodiments of the present disclosure are described.

[0053] In some embodiments, the user 105 can generate a desired target document or document template through the target application 120. The application management platform 110 can receive a creation request for a target document entity through the target application 120. The target document entity can be a document template or a new document. The one or more document parts included in the target document entity can refer to one or more chapters (or one or more paragraphs) in the target document entity. In the target document entity, the chapter is a key part of the document skeleton. Each chapter is usually developed around a specific theme or sub-theme. They are independent of each other and closely connected through logical clues, thereby jointly constructing a complete content framework of the document. Paragraphs can be the basic units that constitute chapters, and they can contain a relatively complete idea or information point. In the target document entity, each chapter can be composed of several paragraphs, and these paragraphs can be connected through logical relationships and transition sentences to ensure the coherence and readability of the document content.

[0054] The creation request indicates the generation requirements for the target document entity. In some embodiments, the creation request is used to indicate the target document entity that the user expects to generate. Exemplarily, the creation request may include the document entity identifier of the target document entity (e.g., the document entity name or a number used to distinguish the document entity). The creation request may include document entity description information for the target document entity, and the document entity description information indicates the user's generation requirements for the target document entity (such as the genre of the target document entity, the document content corresponding to the target document entity, the application scenario of the target document entity, etc.). The creation request may also include a reference data source that can be used in the target document entity generation process. The reference data source includes internal data (e.g., the internal knowledge base of the organization where the user 105 is located), public data (e.g., data that can be obtained through Internet search), and data objects specified by the user 105 (e.g., local documents or online documents uploaded by the user 105), etc. In some embodiments, the creation request may also include the hierarchy of the target document entity, such as the outline hierarchy (e.g., 2 layers, 3 layers).

[0055] Figure 2 FIG. 2 is a schematic diagram showing an example interface 200 for initiating document entity creation according to some embodiments of the present disclosure. Figure 2 As shown, an interface 200 for obtaining a creation request is presented on the terminal device of the user 105. The application management platform 110 can obtain the creation request input by the user 105 through the presented interface 200. Figure 2 As shown, the interface 200 includes various interface elements to obtain the creation requirements for the target document entity. For example, Figure 2The control 210 for starting the generation process of the document entity, the entry 211 for obtaining the identification information of the target document entity, the entry 212 for obtaining the description information of the document entity, the entry 213 for selecting the knowledge base, and the entry 214 for setting the number of levels of the target document entity are shown. The identification component 211 is used to receive the identification of the document entity. The entry 212 is for the user to provide the generation requirements of the target document entity. The knowledge base selection entry 213 is for the user to select the knowledge base for creating the target document entity and the reference for document generation. The entry 214 is used to determine the level of the generated target template. If a selection operation for the control 210 is detected, the application management platform 110 starts the creation process for the target document entity to generate a target template based on the creation request obtained by the control 210.

[0056] refer to Figure 2 The provision of creation instructions through interface elements described is only exemplary and not intended to be limiting. User 105 can give a creation request in various suitable ways. In some embodiments, user 105 can provide a creation request by voice input or text input, and the creation request input by user 105 can be in the form of natural language. In this way, the target creation process can be further simplified, and the target creation efficiency and user experience can be improved. However, it should be understood that this is only an exemplary function and not intended to be limiting.

[0057] In some embodiments, in response to the user 105 initiating the template creation process, the application management platform 110 generates the document structure of the target template (e.g., the outline of the template) based on the acquired creation request. Exemplarily, the target application 120 can determine the outline of the target template based on the acquired template description information and template level information using a machine learning model (which can be, for example, a general language model or a trained outline generation model). For example, the template description information indicates that the generated target template is used for an industry analysis report, and the number of template levels in the creation request is 2. The generated template outline includes at least industry background, industry status analysis, industry growth trend, and the like, and the template outline is divided into two levels. The number of levels of the outline in the template outline generated by the target application 120 is determined according to user input. Exemplarily, the outline generation model can be a language model. The creation request can be provided to the outline generation model in the form of a prompt word to generate a corresponding template outline. The outline can include one or more document parts (e.g., paragraphs or chapters of a document).

[0058] The application management platform 110 determines first reference information related to the creation request from one or more reference data sources. In some embodiments, a machine learning model (e.g., a large language model) can be used to determine the reference data source from one or more reference data sources. Exemplarily, a second prompt information can be generated based on one or more keywords and corresponding descriptions corresponding to each reference data source. Subsequently, the second prompt information is provided to a fourth machine learning model to obtain the output of the fourth machine learning model. Based on the output of the fourth machine learning model, at least one reference data source is determined from one or more reference data sources. The corresponding description corresponding to each reference data source may include the type of data in the reference data source. In some embodiments, reference information can be obtained from the determined reference data source based on the above-mentioned one or more keywords.

[0059] In some embodiments, at least one of the one or more reference data sources has a predetermined range of access rights. A reference data source with a predetermined range of access rights refers to a data source that can only be accessed by a user or a set of users with access rights, such as an internal knowledge base of an enterprise, a local file uploaded by a user, etc. In some embodiments, the target document entity may include one or more document parts. The reference data source may include a reference data source for the entire target document entity, or may include a reference data source for a document part. In the process of creating a target document entity, the reference data source used to create the target document entity may include an associated data source of the application management platform 110 and a data source specified by the user 105. The reference data source may include a data object specified by the target user, a knowledge base to which the set of users to which the target user belongs has access rights, or a public data source. At least a portion of the one or more reference data sources provided by the user 105 is used to generate the target structure information of the target document entity.

[0060] In some embodiments, the user 105 can configure a reference data source for the target document entity during the process of creating the target document entity. Exemplarily, if the application management platform 110 detects the user 105's selection of the entry 213, an interface for acquiring data and knowledge can be presented to the user 105. The interface includes at least an entry for receiving data to acquire data uploaded by the user or a specified knowledge base. In some embodiments, the application management platform 110 can provide different interfaces for the user 105, respectively for receiving different types of data sources uploaded by the user 105.

[0061] Figure 3 FIG. 1 is a schematic diagram of a knowledge base presentation interface 300 according to some embodiments of the present disclosure. The application management platform 110 may present a knowledge base selection interface to the user in response to the user 105's interactive operation on the portal 213. Figure 3As shown, the interface 300 includes an entry 310 for specifying a data object, an entry 320 for adding skills in the target application 120, an entry 330 for configuring dependencies between different document parts, and an entry 340 for configuring data and knowledge (i.e., a target knowledge base for generating document part contents). The user 105 can configure one or more reference data sources for the target document entity through different entries.

[0062] Exemplarily, the application management platform 110 displays multiple candidate knowledge bases that can be used for the target document entity to the user 105 in the interface 300 (which is, for example, a panel) in response to the user's selection of the entry 310. The user 105 can select the candidate knowledge base as the target knowledge base through appropriate operations (for example, checking the selection box in front of the candidate knowledge base). Based on the selection operation of the user 105, the application management platform 110 determines the target knowledge base that can be used as the reference data source.

[0063] Figure 4 FIG. 4 is a schematic diagram showing an entry interface 400 for a user to specify a data object according to some embodiments of the present disclosure. Figure 4 As shown, in response to the user's selection of the portal 320, an interface 400 (which may be, for example, a panel) including portals for specifying different types of data objects is presented to the user. In this example, the interface 400 includes a portal 410 for uploading a local file, a portal 420 for adding a uniform resource locator (URL), and a portal 430 for adding text. The user 105 can provide different types of local materials to the application management platform 110 as reference data sources by operating different portals.

[0064] In some embodiments, the application management platform 110 generates target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model. The target structure may refer to the document framework (e.g., outline, etc.) of the target document entity. The target structure information includes the text format, text level, etc. of the target document entity.

[0065] In some embodiments, the first reference information and the creation request may be provided to the first machine learning model, and the target structure information may be determined directly based on the output of the first machine learning model. Further, in some embodiments, the generated initial structure information may be updated using the first machine learning model to generate target structure information that better meets user needs.

[0066] Therefore, in some embodiments, multiple machine learning models can be used to generate target structure information. Exemplarily, a first machine learning model can be used to generate initial structure information based on first reference information and a creation request. Subsequently, the initial structure information is updated using other machine learning models to obtain target structure information that better meets the user's generation requirements. Furthermore, the initial structure information can also be evaluated using a second machine learning model to generate an evaluation result based on the difference between the initial structure information and the creation request. Subsequently, the evaluation result and the initial structure information are provided to a third machine learning model to update the initial structure information to the target structure information using the third machine learning model.

[0067] In some embodiments, the first machine learning model, the second machine learning model, and the third machine learning model can be fine-tuned based on corresponding application scenarios. Exemplarily, the first machine learning model is fine-tuned based on training data related to content generation, the second machine learning model is fine-tuned based on training data related to content evaluation, and the third machine learning model is fine-tuned based on training data related to content modification. In this way, the performance of each machine learning model can be improved, thereby improving the quality of the generated target structure information. At the same time, the training cost of each machine learning model can be reduced.

[0068] In some embodiments, different prompt words can be configured for different machine learning models. Table 1 is a portion of example prompt information for the first machine learning model.

[0069] Table 1

[0070]

[0071] Table 2 is a portion of example prompt information for the second machine learning model.

[0072] Table 2

[0073]

[0074] Table 3 is a portion of example prompt information for the third machine learning model.

[0075] Table 3

[0076]

[0077]

[0078] In some embodiments, in order to further improve the quality of the generated target structure information, reasoning information can be introduced into the prompt information of the first machine learning model. The reasoning information indicates the process for determining the target document entity, so that the first machine learning model can simulate the thinking and reasoning process, thereby improving the quality of the target structure information. Exemplarily, the first prompt information can be generated based on the first reference information and the reasoning information. The first prompt information is provided to the first machine learning model in at least one machine learning model to obtain the output of the first machine learning model. Based on the output of the first machine learning model, the target structure information is generated. In some embodiments, the problem of generating the target structure information can be decomposed into multiple intermediate reasoning steps. The reasoning information may include a solution to the problem, intermediate reasoning steps, and any external knowledge related to the problem.

[0079] In some embodiments, the target structure information may include multiple levels of titles (e.g., first-level titles, second-level titles, etc.). One or more first-level titles correspond to one or more first parts included in the target document entity. For example, the first-level title may be "Overview of Industry Development", and the second-level titles corresponding to the first-level title may be "Origin of Industry" and "Development History of Industry". In order to improve the accuracy of low-priority titles, one or more first-level titles may be generated based on the first reference information and at least one machine learning model, and the one or more first-level titles correspond to one or more first parts included in the target document entity. For a given first part among the one or more first parts, based on a given first-level title corresponding to the given first part, second reference information related to the given first part is determined. Based on the second reference information and the given first-level title, one or more second-level titles are generated, and the one or more second-level titles correspond to one or more second parts included in the given first part. Initial structure information is generated based on one or more first-level titles and one or more second-level titles generated for one or more first parts. In some embodiments, the second reference information may include the same information as the first reference information. The above method may be used for target structure information including multiple levels of titles. For target structure information with multiple levels of titles, each level of title may be generated in sequence according to the priority of each level of title.

[0080] After the target structure information of the target document entity is generated, the target structure information may be presented to the user 105 . Figure 5 FIG. 5 is a schematic diagram showing an example interface 500 for presenting structural information according to some embodiments of the present disclosure. Figure 5 As shown in the interface 500, the user 105 can view the document structure of the target document entity to further improve the user's participation in the target document entity generation process. Figure 5As shown, the interface 500 includes a navigation area 510 for presenting navigation information related to the document structure and a structure presentation area 520 for presenting target structure information.

[0081] The multiple machine learning models mentioned in some embodiments described above (e.g., a first machine learning model, a second machine learning model, a third machine learning model, etc.) may be different machine learning models, or may be the same machine learning model but using different prompt information.

[0082] It can be seen that, through the scheme provided by the present application, reference information related to the creation request can be determined from the reference data source. Subsequently, based on the reference information and the creation request, the structural information of the target document entity is generated using at least one machine learning model. In this way, useful reference information can be obtained according to actual needs, so as to determine the document structure that meets the generation requirements. The determined document structure can further be used to generate the target document entity (such as a new document or a template for generating a new document). Thus, it can be beneficial to improve the quality and efficiency of the target document entity generation. At the same time, in the process of generating the target structure information using the machine learning model, reasoning information is added to the prompt information of the machine learning model so that the machine learning model can simulate the process of thinking and reasoning, thereby improving the quality of the target structure information. Thus, the quality of the target document entity related to the target structure information is improved. In addition, multiple machine learning models are used to respectively realize the generation of target structure information, the evaluation of target structure information and the update of target structure information, reduce the training cost of the model, and further improve the quality of the target structure information.

[0083] Example Process

[0084] Figure 6 600 is a flowchart showing an example process 600 of a document processing method according to some embodiments of the present disclosure. The process 600 may be implemented at the application management platform 110. Figure 1 600 is described below.

[0085] like Figure 6 As shown, in block 610 , the application management platform 110 receives a creation request for a target document entity, where the creation request indicates a generation requirement for the target document entity.

[0086] At block 620 , the application management platform 110 determines first reference information related to the creation request from one or more reference data sources.

[0087] In some embodiments, determining the first reference information includes: determining one or more keywords based on the creation request; and obtaining the first reference information from at least one reference data source among the one or more reference data sources based on the one or more keywords.

[0088] In some embodiments, at least one reference data source is determined in the following manner: determining second prompt information based on one or more keywords and corresponding descriptions of one or more reference data sources; providing the second prompt information to a fourth machine learning model to obtain an output of the fourth machine learning model; and determining at least one reference data source from one or more reference data sources based on the output of the fourth machine learning model.

[0089] In some embodiments, the creation request is initiated by a target user, and the one or more reference data sources include at least one of the following: a data object specified by the target user, a knowledge base to which a user set to which the target user belongs has access rights, or a public data source.

[0090] In box 630, the application management platform 110 generates target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model.

[0091] In some embodiments, generating target structural information includes: based on first reference information, using a first machine learning model among at least one machine learning model, generating initial structural information for a target document entity; and using one or more machine learning models among at least one machine learning model, updating the initial structural information to determine target structural information.

[0092] In some embodiments, updating the initial structural information to determine the target structural information includes: using a second machine learning model among one or more machine learning models to generate an evaluation result for the initial structural information; and based on the evaluation result, using a third machine learning model among one or more machine learning models to update the initial structural information to the target structural information.

[0093] In some embodiments, generating target structure information includes: based on first reference information, using at least one machine learning model, generating one or more first-level headings, the one or more first-level headings respectively corresponding to one or more first parts included in the target document entity; for a given first part among the one or more first parts, based on a given first-level heading corresponding to the given first part, determining second reference information related to the given first part; based on the second reference information and the given first-level heading, generating one or more second-level headings, the one or more second-level headings respectively corresponding to one or more second parts included in the given first part; and generating target structure information based on the one or more first-level headings and the one or more second-level headings generated for the one or more first parts.

[0094] In some embodiments, generating target structure information includes: generating first hint information based on first reference information and reasoning information, the reasoning information indicating a process for determining a target document entity; providing the first hint information to a first machine learning model among at least one machine learning model to obtain an output of the first machine learning model; and generating target structure information based on the output of the first machine learning model.

[0095] Example devices and equipment

[0096] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 7 A schematic structural block diagram of an example apparatus 700 for document processing according to some embodiments of the present disclosure is shown. The apparatus 700 may be implemented as or included in the application management platform 110. Each module / component in the apparatus 700 may be implemented by hardware, software, firmware, or any combination thereof.

[0097] like Figure 7 As shown, the apparatus 700 includes: a receiving module 710, configured to receive a creation request for a target document entity, the creation request indicating a generation requirement for the target document entity. The apparatus 700 also includes a determining module 720, configured to determine first reference information related to the creation request from one or more reference data sources. The apparatus 700 also includes a generating module 730, configured to generate target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model.

[0098] In some embodiments, the determination module 720 is further configured to determine one or more keywords based on the creation request; and obtain first reference information from at least one reference data source among the one or more reference data sources based on the one or more keywords.

[0099] In some embodiments, the determination module 720 is also configured to determine second prompt information based on one or more keywords and corresponding descriptions of one or more reference data sources; provide the second prompt information to a fourth machine learning model to obtain an output of the fourth machine learning model; and determine at least one reference data source from one or more reference data sources based on the output of the fourth machine learning model.

[0100] In some embodiments, the determination module 720 is also configured to determine second prompt information based on one or more keywords and corresponding descriptions of one or more reference data sources; provide the second prompt information to a fourth machine learning model to obtain an output of the fourth machine learning model; and determine at least one reference data source from one or more reference data sources based on the output of the fourth machine learning model.

[0101] In some embodiments, the creation request is initiated by the target user, and the determination module 720 is further configured such that the one or more reference data sources include 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 rights, or a public data source.

[0102] In some embodiments, the generation module 730 is also configured to generate initial structural information for the target document entity based on the first reference information using a first machine learning model among at least one machine learning model; and to update the initial structural information using one or more machine learning models among at least one machine learning model to determine the target structural information.

[0103] In some embodiments, the generation module 730 is also configured to generate an evaluation result for the initial structural information using a second machine learning model among the one or more machine learning models; and based on the evaluation result, update the initial structural information to the target structural information using a third machine learning model among the one or more machine learning models.

[0104] In some embodiments, the generation module 730 is also configured to generate one or more first-level headings based on the first reference information and using at least one machine learning model, and the one or more first-level headings respectively correspond to the one or more first parts included in the target document entity; for a given first part among the one or more first parts, based on a given first-level heading corresponding to the given first part, determine the second reference information related to the given first part; based on the second reference information and the given first-level heading, generate one or more second-level headings, and the one or more second-level headings respectively correspond to the one or more second parts included in the given first part; and generate target structure information based on the one or more first-level headings and the one or more second-level headings generated for the one or more first parts.

[0105] In some embodiments, the generation module 730 is also configured to generate first prompt information based on the first reference information and the reasoning information, wherein the reasoning information indicates a process for determining a target document entity; provide the first prompt information to a first machine learning model among at least one machine learning model to obtain an output of the first machine learning model; and generate target structure information based on the output of the first machine learning model.

[0106] Figure 8 1 shows a block diagram of an electronic device capable of implementing multiple embodiments of the present disclosure. Figure 8As shown, the electronic device 800 is in the form of a general electronic device. The components of the electronic device 800 may include, but are not limited to, one or more processors or processing units 88, a memory 820, a storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. The processing unit 88 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 820. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 800.

[0107] The electronic device 800 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 820 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 830 can be a removable or non-removable medium, and can include a machine-readable medium, such as a flash drive, a disk, or any other medium, which can be used to store information and / or data and can be accessed within the electronic device 800.

[0108] The electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 8 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 820 may include a computer program product 825 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0109] The communication unit 840 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 800 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 800 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0110] The input device 850 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 860 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 800 may communicate with one or more external devices (not shown) through the communication unit 840 as needed, such as a storage device, a display device, etc., with one or more devices that allow a user to interact with the electronic device 800, or with any device that allows the electronic device 800 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0111] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0112] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0113] 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 device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0114] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0115] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0116] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A document entity creation method, comprising: Receiving a creation request for a target document entity, wherein the creation request indicates a generation requirement for the target document entity; Determining first reference information related to the creation request from one or more reference data sources; as well as Based on the first reference information and the creation request, target structural information of the target document entity is generated using at least one machine learning model.

2. The method according to claim 1, wherein generating the target structure information comprises: Based on the first reference information, using a first machine learning model among the at least one machine learning model, generating initial structural information for the target document entity; as well as Using one or more machine learning models among the at least one machine learning model, the initial structure information is updated to determine the target structure information.

3. The method according to claim 2, wherein updating the initial structure information to determine the target structure information comprises: Using a second machine learning model among the one or more machine learning models, generating an evaluation result for the initial structural information; as well as Based on the evaluation result, the initial structure information is updated to the target structure information using a third machine learning model among the one or more machine learning models.

4. The method according to claim 1, wherein generating the target structure information comprises: generating first prompt information based on the first reference information and reasoning information, wherein the reasoning information indicates a process for determining the target document entity; Providing the first prompt information to a first machine learning model among the at least one machine learning model to obtain an output of the first machine learning model; as well as Based on the output of the first machine learning model, the target structure information is generated.

5. The method according to claim 1, wherein generating the target structure information comprises: Based on the first reference information, using the at least one machine learning model, one or more first-level headings are generated, wherein the one or more first-level headings respectively correspond to the one or more first parts included in the target document entity; For a given first part of the one or more first parts, Determining second reference information related to the given first part based on a given first-level title corresponding to the given first part; Based on the second reference information and the given first-level title, one or more second-level titles are generated, wherein the one or more second-level titles respectively correspond to the one or more second parts included in the given first part; as well as The target structure information is generated based on the one or more first-level headings and the one or more second-level headings respectively generated for the one or more first parts.

6. The method according to claim 1, wherein determining the first reference information comprises: Based on the creation request, determining one or more keywords; as well as Based on the one or more keywords, the first reference information is obtained from at least one reference data source among the one or more reference data sources.

7. The method according to claim 6, wherein the at least one reference data source is determined by: Determining second prompt information based on the one or more keywords and corresponding descriptions of the one or more reference data sources; Providing the second prompt information to a fourth machine learning model to obtain an output of the fourth machine learning model; and Based on the output of the fourth machine learning model, at least one reference data source is determined from the one or more reference data sources.

8. The method according to claim 1, wherein the creation request is initiated by a target user, and the one or more reference data sources include at least one of the following: The target user specifies the data object, A knowledge base to which the user set to which the target user belongs has access rights, or Public data sources.

9. A device for document entity creation, comprising: A receiving module is configured to receive a creation request for a target document entity, wherein the creation request indicates a generation requirement for the target document entity; a determination module configured to determine first reference information related to the creation request from one or more reference data sources; as well as A generation module is configured to generate target structure information of the target document entity based on the first reference information and the creation request using at least one machine learning model.

10. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images