Document processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a document processing method and device, equipment and a storage medium so as to create a target template for document generation. In the method, an editing request for a target document is received, and the editing request indicates a modification requirement for at least one part of the target document. Based on the editing request and at least one part of the target document, one or more machine learning models are utilized to generate indication information for the target content, the indication information at least indicates at least one of the starting position or the ending position of the target content in the target document, and the target content is the content to be edited. And updating the target document based on the indication information. In this way, part of content in the target document can be modified according to the indication information, namely, a user is allowed to finely adjust the target document.

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 processing. 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 an edit request for a target document, the edit request indicating a modification requirement for at least a portion of the target document; based on the edit request and at least a portion of the target document, using one or more machine learning models, generating indication information for target content, the indication information at least indicating at least one of a starting position or an ending position of the target content in the target document, the target content being content to be edited; and updating the target document based on the indication information.

[0004] In a second aspect of the present disclosure, a device for template creation is provided. The device includes: receiving a template, configured to receive an edit request for a target document, the edit request indicating a modification requirement for at least a portion of the target document; generating a template, configured to generate indication information for target content based on the edit request and at least a portion of the target document using one or more machine learning models, the indication information at least indicating at least one of a starting position or an ending position of the target content in the target document, the target content being content to be edited; and updating the template, configured to update the target document based on the indication information.

[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 editing according to some embodiments of the present disclosure;

[0011] Figure 3 A schematic diagram showing another example interface for initiating document editing according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A schematic diagram showing another example interface for initiating document editing according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A schematic diagram showing an example architecture for generating target content according to an embodiment of the present disclosure is shown;

[0014] Figure 6 A schematic diagram showing an example interface for presenting editing results according to some embodiments of the present disclosure is shown;

[0015] Figure 7 A flowchart showing an example process of a document processing method according to some embodiments of the present disclosure;

[0016] Figure 8 A schematic structural block diagram showing an example apparatus for document processing according to some embodiments of the present disclosure; and

[0017] Fig. 9 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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 obtain and use 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[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, if the generated document does not meet user expectations, the user has to spend more time and energy to modify the generated document or regenerate the document. This undoubtedly reduces the efficiency of document modification.

[0030] In view of this, an embodiment of the present disclosure provides a document processing solution. In the solution, an edit request for a target document is received, and the edit request indicates a modification requirement for at least a portion of the target document. Based on the edit request and at least a portion of the target document, one or more machine learning models are used to generate indication information for the target content. The target content can be content to be updated or deleted in the target document, or content to be added to the target document. The indication information at least indicates at least one of the starting position or the ending position of the target content in the target document, and the target content is the content to be edited. Based on the indication information, the target document is updated.

[0031] It will be more clearly understood from the following description that according to the scheme of the present disclosure, based on the editing request and at least a part of the target document, the machine learning model can be used to generate indication information for the target content. In this way, part of the content in the target document can be modified according to the indication information, that is, the user is allowed to make fine adjustments to the target document, thereby improving the efficiency of document modification. At the same time, the indication information indicates at least one of the starting position or the ending position of the content to be edited in the target document, without giving the specific content to be modified in the document. This can further help improve the efficiency of document modification.

[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 1 In 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 1In 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] In some embodiments, for the target document generated by the application management platform 110, the terminal user 145 can modify the target document according to the requirements. For example, the terminal user 145 can input an edit request for the target document to the application management platform 110 through the target application 120. In some embodiments, the edit request can include a modification request for the text, image or table in the target document. In some embodiments, the application management platform 110 can support updating part of the content in the target document based on the edit request. For example, the terminal user 145 can input an edit request for part of the content in the target document (such as deleting or replacing the specified content in the target document, adding content to the target document, etc.), so as to edit part of the content in the target document. In some embodiments, if the target document is too far from the expectations of the terminal user 145, the application management platform 110 can regenerate the target document based on the edit request after receiving the edit request, so that the target document meets the user's expectations. For example, the terminal user 145 can input an edit request for the target document to initiate a document generation process to regenerate the target document.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] Example Interaction

[0053] The following will continue to refer to the attached Figures 2 to 6 Some example embodiments of the present disclosure are described.

[0054] The terminal user 145 can generate the desired target document through the target application 120. In some embodiments, the terminal management platform receives the document generation request sent by the terminal user 145 to generate the corresponding target document based on the document generation request. Subsequently, the terminal management platform 110 can present the target document to the terminal user 145 through the target application 120. The terminal user 145 can view the target document through the target application 120. In the case where the target document does not meet the user's expectations, an edit request for the target document is input in the interactive window 142. The edit request indicates a modification request for at least a portion of the target document. Exemplarily, the edit request can indicate a modification request for a certain paragraph or part of the text in the target document. The edit request can indicate a modification request for the entire text of the target document.

[0055] In some embodiments, the edit request for the target document includes, but is not limited to, modifying the description method of at least a portion of the content in the target document, modifying a portion of the content in the target document (e.g., modifying erroneous data existing in the target document), adding content to the target document, or deleting a portion of the content in the target document. The description method refers to writing and organizing the document content, including the logical order and style of the document. In some embodiments, the edit request may be an edit request input by the terminal user 145 based on the difference between the terminal user 145's own expectations and the target document. In some embodiments, the edit request may be an edit request generated by evaluating the target document using a language model (e.g., a large language model).

[0056] In some embodiments, the application management platform 110 may present an edit initiation interface to the end user 145 to receive an edit request for the target document. Exemplarily, the edit request acquisition interface may be independent of the target document presentation page. The application management platform 110 may present the edit initiation interface in a new session or interactive interface, or in an interface for presenting the target document, when the target document has been presented to the end user 145. The application management platform 110 may present the edit initiation interface for the target document to the end user 145. Figure 2 FIG. 2 is a schematic diagram showing an example interface 200 for initiating document editing according to some embodiments of the present disclosure. Figure 2 As shown, the interface 200 includes a dialogue area 210 and a document presentation area 230. The dialogue area 210 is used for the terminal user 145 to interact with the target application 120. The dialogue area 210 includes at least a first entry 240 for obtaining natural language input. If a selection operation (e.g., a click operation) of the terminal user 145 for the first entry 240 is received, an edit request input by the terminal user 145 through the first entry 240 is received. In some embodiments, the received edit request can be processed using a language model to more accurately obtain the user's modification requirements.

[0057] In some embodiments, a historical conversation 220 between the terminal user 145 and the target application 120 may be presented in the conversation area 210. The historical conversation 220 includes the historical editing requests of the terminal user 145 for the target document and the reply content of the target application 120 for the historical editing requests. The reply content of the target application 120 includes the execution feedback of the editing request. In this way, it is convenient for the terminal user to view the editing history of the target document, so as to provide a more accurate editing request to the application management platform 110 with reference to the historical editing request.

[0058] In some embodiments, the end user 145 may provide an editing request to the application management platform 110 through an interactive element included in the document presentation area 230 . Figure 3FIG. 3 is a schematic diagram showing another example interface 300 for initiating document editing according to some embodiments of the present disclosure. Figure 3 As shown, the target document can be presented in the interface 300. If a selection operation of the terminal user 145 for at least a part of the target document is detected, a second entry 310 for natural language input is presented. The second entry 310 is used to obtain user input of natural language type. Subsequently, based on the user input and the part selected by the terminal user 145 in the target document, the editing request of the terminal user 145 is determined. Exemplarily, the modification requirements indicated by the editing request can be only for the content selected by the terminal user 145 in the target document, or can include other content indicated by the user input. Exemplarily, if the content selected by the terminal user 145 in the target document is a part of paragraph 1.2 in the target document, and "make the content and description method in this paragraph closer to the industry growth trend" is input in the second entry 310, then the modification requirements indicated by the editing request are for paragraph 1.2 of the target document. If the content selected by the terminal user 145 is a certain sentence of text in the target document, and "optimize this sentence" is input in the second entry 310, then the modification requirements indicated by the editing request are only for the content selected by the terminal user 145.

[0059] In some embodiments, if a selection operation of the terminal user 145 on at least a portion of the target document is detected, a third entry 320 may be presented to the terminal user 145. The third entry 320 includes a plurality of document editing controls (such as bold, italic, underline, etc.), and the terminal user 145 may quickly edit the target document through each document editing control in the third entry 320.

[0060] In some embodiments, the application management platform 110 may present the editing history of the target text by the end user 145 through the second portal 310 and feedback on the editing operation of the end user 145 in different areas of the user interface. Figure 4 FIG. 4 is a schematic diagram of another example interface 400 for initiating document editing according to some embodiments of the present disclosure. Figure 4As shown, the example interface 400 includes a dialogue area 410 and a document presentation area 420. The document presentation area 420 is used to present the target document. If a selection operation of the terminal user 145 for the target document is detected, the second entrance 310 and the third entrance 320 are presented in the document presentation area 420 to receive the editing request of the terminal user 145 for the target document. The dialogue area 410 is used to present the feedback of the target application 120 for the editing request (for example, the execution result of the editing request, etc.). In some embodiments, the dialogue area 410 may include an entrance for obtaining natural language to obtain the editing request input by the terminal user 145 through natural language. In some embodiments, the content in the target document indicated by the indication information is at least partially different from the selected content. In this embodiment, a machine learning model can be used to understand the user input and the selected content, so as to locate the part that the user expects to modify, rather than mechanically modifying only the content selected by the user.

[0061] In some embodiments, the application management platform 110 generates indication information for the target content based on the edit request and at least a part of the target document using one or more machine learning models. The target content is the content to be edited in the target document. Exemplarily, the target content can be the content to be replaced or deleted in the target document, or the content to be added to the target document. The indication information indicates at least one of the starting position or the ending position of the target content in the target document. In some embodiments, the indication information can be expressed as a sequence number or a paragraph number of characters in the document. For example, the indication information can indicate that the starting position of the target content is the third character of the 10th line in the target document, and the ending position of the target position is the fourth character of the 20th line in the target document. In some embodiments, the indication information can be expressed in the form of a text segment. For example, the indication information includes a starting text segment indicating the starting position of the target content or an ending text segment indicating the ending position of the target content. In some embodiments, the indication information also indicates a target editing operation for the target content. The target editing operation can correspond to the edit request, for example, it can include adding, replacing and deleting.

[0062] In some embodiments, the target editing operation corresponding to the editing request can be determined from a plurality of predetermined editing operations (i.e., add, replace, and delete). Exemplarily, a machine learning model can be used to determine the target editing operation corresponding to the editing request, and the target editing operation can be determined from a plurality of predetermined editing operations using model matching. Subsequently, the machine learning model is used to generate indication information based on the target editing operation and at least a portion of the target document.

[0063] Exemplarily, the editing request for the target document may include a request to delete part of the content in the target document (e.g., delete the introduction to founder Alice in the target document), a request to replace part of the content in the target document (e.g., change the industry origin to be traceable to 2010), a request to add to the target document (e.g., add an introduction to founder Bob in the target document), or a complex request including multiple of the above requests. Accordingly, the editing operation for the target document includes a content deletion operation, a content replacement operation, or a content addition request. In some embodiments, if the editing operation is a content deletion operation, the target content is the content to be deleted in the target document, and the indication information indicates the starting position and the ending position of the target content. If the editing operation is a content addition operation, the target content is the content to be added to the target document, and the indication information indicates the starting position of the target content in the target document (i.e., the insertion position of the target content). If the editing operation is a content update operation, the target content includes the content to be replaced (i.e., deleted) in the target document and the content to be inserted into the target document, and the indication information includes the starting position and the ending position of the target content.

[0064] In some embodiments, if the edit request indicates to update part of the target document with the target content or to add the target content to the target document, the application management platform 110 can generate the target content based on the edit request and the corresponding reference information. The reference information is information obtained by the application management platform 110 from the reference data source.

[0065] In some embodiments, the reference data source may be a data source specified by the terminal user 145 through an edit request or a data object specified through an edit request. Exemplarily, the data source specified by the terminal user 145 may include a knowledge base (e.g., an internal knowledge base of an enterprise) that can be accessed by the user set to which the terminal user 145 belongs. The data object specified by the terminal user 145 may be a local document or an online document or public data uploaded by the terminal user 145 (e.g., data that can be obtained through an Internet search). In some embodiments, the reference data source may be a data source used to generate a target document. In this case, the application management platform may determine the reference data source based on the configuration information of the target document, thereby determining the reference information.

[0066] In some embodiments, if the reference data source is a knowledge base, the application management platform 110 can obtain at least one knowledge fragment that matches the generation requirements of the first text from the knowledge base as reference data. If the reference data source is a data object specified by the terminal user 145, the application management platform 110 retrieves at least one knowledge fragment that matches the generation requirements from multiple knowledge fragments for the data object as reference data, wherein the multiple knowledge fragments are obtained by vectorizing the data object. If the reference data source is text input by the terminal user 145, the application management platform 110 can determine the text as reference data.

[0067] The application management platform 110 generates target content using a machine learning model based on reference information obtained from a reference data source. In some embodiments, the application management platform 110 may generate target content based on an edit request. The application management platform may generate target content based on generation requirements for a target document (such as the genre of the target document, the document content corresponding to the target document, the application scenario of the target document, etc.) included in the configuration information of the target document.

[0068] Due to the existence of multiple reference data sources, the application management platform cannot determine the amount of reference information required in the process of generating target content. If reference information is obtained from all reference data sources, the amount of information that the application management platform needs to process may be too large. If reference information is only obtained from some reference data sources, there may be insufficient reference information, resulting in the generated target content failing to meet user expectations. In some embodiments, in order to solve this problem, the reference information used to generate the target content can be verified to determine whether the reference information meets the data requirements related to the target content. The target content is generated based on the reference information only when the reference information meets the data requirements related to the target content.

[0069] Figure 5 FIG. 5 is a schematic diagram of an example architecture 500 for generating target content according to an embodiment of the present disclosure. Figure 5 As shown, the architecture 500 can be implemented or included in the application management platform 110. The application management platform 110 determines a reference data source list 521 that can be used for target content generation, structural information 522 of the target document, and configuration information 523 corresponding to the target document portion to be modified in the target document based on the received edit request 510 and the target document. The configuration information 523 may include a reference data source corresponding to the modified portion, document description information, and dependencies between the modified portion and other document portions in the target document. In some embodiments, the application management platform 110 may generate the target document based on the document modification requirements included in the edit request. In some embodiments, the target document portion to be modified may be determined from the target document based on the starting position and the ending position indicated by the indication information.

[0070] The application management platform 110 generates prompt information 530 based on the reference data source list 521, the structure information 522, and the configuration information 523. Subsequently, the corresponding reference information 540 is obtained from at least one first data source based on the prompt information 530. In some embodiments, at least one first data source can be determined from multiple reference data sources using a machine learning model or a pattern matching method. Subsequently, the reference information 540 is provided to the first machine learning model 550 to determine whether the current reference information 540 meets the data requirements corresponding to the editing request. If the reference information 540 meets the data requirements, the reference information 540 is provided to the second machine learning model 560 to generate the target content 570 using the second machine learning model 560.

[0071] In some embodiments, if the reference information 540 does not meet the data requirements, the data source status 580 corresponding to the reference information 540 (used to indicate the reference data source associated with the reference information 540) is added to the prompt information 530, so as to determine the second data source from the multiple reference data sources based on the updated prompt information 530. The data source status 580 indicates whether the information of each reference data source is included in the reference information 540. If the information of a certain reference data source has been included in the reference information 540, the identification of the reference data source is "already called". Otherwise, the identification of the reference data source is "not called". In some embodiments, the data source status 580 may include the situation of the information obtained from each reference data source (including the type of information obtained and the content of the information). Subsequently, the reference information 540 is updated using the second data source, and it is determined again whether the updated reference information 540 meets the data requirements. If the updated reference information 540 meets the data requirements, the target content is generated based on the updated reference information 540. If the number of times the reference information 540 is updated is greater than the threshold, it indicates that the current reference data source cannot meet the user's expectations, and the terminal user 145 may be prompted to supplement the reference data source or regenerate the target document. In this way, by verifying the reference information and generating the target content only when the reference information meets the data requirements corresponding to the editing request, it is ensured that the generated target content meets the user's expectations. Thus, the modification efficiency of the target document is improved.

[0072] In some embodiments, the second data source may be determined using a machine learning model. Exemplarily, prompt information for the machine learning model may be generated based on the reference information and the description information of at least one data source configured by the target document portion. The prompt information is provided to the machine learning model to obtain an output of the machine learning model. Subsequently, the second data source is determined based on the output of the machine learning model.

[0073] In some embodiments, the first machine learning model 550 and the second machine learning model can be different models. The first machine learning model is trained to determine whether the reference information meets the required scenario, and the second machine learning model is trained to generate target content. The reference amount of the first machine learning model is less than the parameter amount of the second machine learning model. Figure 5 The process of generating content by multi-step planning described is not limited to the modification of the target document. When generating the content of each document part in the target document according to the configuration information, the multi-step planning method can also be used. For a certain document part in the target document, if it is detected that the reference data used to generate the content of the document part does not meet the data requirements, the reference data is updated.

[0074] In some embodiments, the application management platform 110 updates the target document based on the indication information. The application management platform 110 can determine the target position in the target document based on the indication information. Subsequently, the target editing operation is performed on the target position. That is, the application management platform 110 uses different editing operations to update the target document based on different types of editing requests. Exemplarily, if the editing request is an add operation, the generated target content can be added to the target position. If the editing request is a delete operation, the document content at the target position is deleted. If the editing request is a replace operation, the content at the target position in the target document is deleted, and the generated target content is added to the target position. Figure 6 FIG. 6 is a schematic diagram showing an example interface 600 for presenting editing results according to some embodiments of the present disclosure. Figure 6 As shown, the interface 600 includes a dialogue area 610 and a document presentation area 620. The dialogue area 610 is used to present the interactive dialogue between the terminal user 145 and the target application. The document presentation area 620 is used to present the modified target document. In the document presentation area 620, the target position 630 corresponding to the indication information in the target document is replaced with the target content.

[0075] If the target template currently being created is far from the user's expectations, there are many document contents to be modified, or multiple modifications are made to a certain document part of the target document, it will affect the efficiency of the terminal user 145 in modifying the target document. Therefore, the terminal user 145 can abandon the current target document and create a new target document. In some embodiments, if the generated target document can meet the expectations of the terminal user 145, the terminal user 145 can export the generated target document through the export control.

[0076] It can be seen that through the solution provided by the present application, one or more machine learning models can be used to generate indication information for the content to be edited (i.e., the target content) based on the editing request and at least a part of the target document. In this way, part of the content in the target document can be modified according to the indication information, that is, the user is allowed to make fine adjustments to the target document. At the same time, at least one of the starting position or the ending position in the target document is used to modify the target document without providing the content to be modified in the document, thereby improving the efficiency of document modification. Furthermore, by verifying the reference information used to generate the target content, it is ensured that the reference information used to generate the target content can meet the data requirements corresponding to the editing request. As a result, the generated target content meets the expectations of the end user, further improving the efficiency of document modification.

[0077] Example Process

[0078] Figure 7 1 is a flowchart showing an example process 700 of a document processing method according to some embodiments of the present disclosure. The process 700 may be implemented at the application management platform 110. Figure 1 700 is described below.

[0079] like Figure 7 As shown, in block 710 , the application management platform 110 receives an edit request for a target document, where the edit request indicates a modification requirement for at least a portion of the target document.

[0080] In some embodiments, receiving an edit request for a target document includes: presenting the target document and a first portal for natural language input in different areas of a user interface; and receiving the edit request via the first portal.

[0081] In some embodiments, an editing request is received in the following manner: in response to a selection of content in a target document, presenting a second entry for natural language input; determining the editing request based on user input received via the second entry and the selected portion, and wherein the content in the target document indicated by the indication information is at least partially different from the selected content.

[0082] In box 720, the application management platform 110 generates indication information for the target content based on the editing request and at least a portion of the target document using one or more machine learning models. The indication information at least indicates at least one of the starting position or the ending position of the target content in the target document, and the target content is the content to be edited.

[0083] In some embodiments, generating indication information includes: based on the editing request, determining a target editing operation corresponding to the editing request from multiple editing operations; and based on the target editing operation and at least a portion of the target document, generating indication information using a machine learning model.

[0084] In some embodiments, the plurality of editing operations include at least one of the following: a content deletion operation, a content replacement operation, or a content addition operation.

[0085] In some embodiments, the target content is generated by: using a first machine learning model among one or more machine learning models to determine that reference information obtained from at least one first data source meets the data requirements indicated by the editing request; in response to determining that the reference information meets the data requirements, using a second machine learning model among one or more machine learning models to generate the target content based on the reference information; in response to the reference information not meeting the data requirements, using the first machine learning model to update the reference information based on the second data source; and in response to determining that the updated reference information meets the data requirements using the first machine learning model, using the second machine learning model to generate the target content based on the updated reference information.

[0086] In some embodiments, at least one first data source is determined in the following manner: based on indication information, determining a target document part where the target content is located from one or more document parts of the target document; and based on an editing request and configuration information of the target document part, determining at least one first data source from at least one data source configured for the target document part.

[0087] In some embodiments, the second data source is determined in the following manner: based on reference information and descriptive information of at least one data source configured in the target document portion, generating prompt information for the machine learning model to obtain the output of the machine learning model; and determining the second data source based on the output of the machine learning model.

[0088] In some embodiments, the first machine learning model has fewer parameters than the second machine learning model.

[0089] In some embodiments, the indication information includes at least one of the following: a start text segment indicating a start position, or an end text segment indicating an end position.

[0090] In block 730 , the application management platform 110 updates the target document based on the instruction information.

[0091] In some embodiments, the indication information also indicates a target editing operation for the target content, and updating the target document includes: determining a target position in the target document based on the indication information, the target position being represented by at least one item: a starting character number corresponding to the starting position, or an ending character number corresponding to the ending position; and performing a target editing operation on the target position.

[0092] Example devices and equipment

[0093] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 8 A schematic structural block diagram of an example apparatus 800 for document processing according to some embodiments of the present disclosure is shown. The apparatus 800 may be implemented as or included in the application management platform 110. Each module / component in the apparatus 800 may be implemented by hardware, software, firmware, or any combination thereof.

[0094] like Figure 8 As shown, the device 800 includes: a receiving module 810, configured to receive an editing request for a target document, the editing request indicating a modification requirement for at least a portion of the target document. The device 800 also includes a generating module 820, configured to generate indication information for the target content based on the editing request and at least a portion of the target document using one or more machine learning models, the indication information at least indicating at least one of the starting position or the ending position of the target content in the target document, and the target content is the content to be edited. The device 800 also includes an updating module 830, configured to update the target document based on the indication information.

[0095] In some embodiments, the receiving module 810 is further configured to present the target document and a first entry for natural language input in different areas of the user interface; and receive an editing request via the first entry.

[0096] In some embodiments, the receiving module 810 is also configured to present a second entry for natural language input in response to a selection of content in the target document; determine an editing request based on the user input received via the second entry and the selected portion, and wherein the content in the target document indicated by the indication information is at least partially different from the selected content.

[0097] In some embodiments, the generation module 820 is also configured to determine, based on the editing request, a target editing operation corresponding to the editing request from multiple editing operations; and generate indication information based on the target editing operation and at least a portion of the target document using a machine learning model.

[0098] In some embodiments, the plurality of editing operations include at least one of the following: a content deletion operation, a content replacement operation, or a content addition operation.

[0099] In some embodiments, the generation module 820 is also configured to determine, using a first machine learning model among one or more machine learning models, that reference information obtained from at least one first data source meets the data requirements indicated by the editing request; in response to determining that the reference information meets the data requirements, generate target content based on the reference information using a second machine learning model among the one or more machine learning models; in response to the reference information not meeting the data requirements, update the reference information based on the second data source using the first machine learning model; and in response to the first machine learning model determining that the updated reference information meets the data requirements, generate target content based on the updated reference information using the second machine learning model.

[0100] In some embodiments, the generation module 820 is also configured to determine, based on the indication information, the target document part where the target content is located from one or more document parts of the target document; and to determine, based on the editing request and the configuration information of the target document part, at least one first data source from at least one data source configured for the target document part.

[0101] In some embodiments, the generation module 820 is also configured to generate prompt information for the machine learning model based on the reference information and the description information of at least one data source configured by the target document part to obtain the output of the machine learning model; and determine the second data source based on the output of the machine learning model.

[0102] In some embodiments, the first machine learning model has fewer parameters than the second machine learning model.

[0103] In some embodiments, the indication information includes at least one of the following: a start text segment indicating a start position, or an end text segment indicating an end position.

[0104] In some embodiments, the indication information also indicates a target editing operation for the target content, and the update module 830 is also configured to determine a target position in the target document based on the indication information, where the target position is represented by at least one item: a starting character number corresponding to the starting position, or an ending character number corresponding to the ending position; and perform a target editing operation on the target position.

[0105] Fig. 9 A block diagram of an electronic device capable of implementing multiple embodiments of the present disclosure is shown. Fig. 9As shown, the electronic device 900 is in the form of a general electronic device. The components of the electronic device 900 may include, but are not limited to, one or more processors or processing units 910, a memory 920, a storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. The processing unit 910 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 900.

[0106] The electronic device 900 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 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 930 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 900.

[0107] The electronic device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig. 9 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. Memory 920 may include a computer program product 925 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0108] The communication unit 940 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 900 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 900 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.

[0109] The input device 950 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 960 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 900 may communicate with one or more external devices (not shown) through the communication unit 940 as needed, such as a storage device, a display device, etc., with one or more devices that enable a user to interact with the electronic device 900, or with any device that enables the electronic device 900 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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 processing method, comprising: receiving an edit request for a target document, the edit request indicating a modification requirement for at least a portion of the target document; Based on the edit request and at least a portion of the target document, using one or more machine learning models, generate indication information for target content, wherein the target content is content to be edited, and the indication information at least indicates at least one of a starting position or an ending position of the target content in the target document; as well as Based on the indication information, the target document is updated.

2. The method according to claim 1, wherein generating the indication information comprises: Based on the editing request, determining a target editing operation corresponding to the editing request from a plurality of editing operations; as well as The indication information is generated based on the target editing operation and at least a portion of the target document using a machine learning model.

3. The method according to claim 1, wherein the instruction information further indicates a target editing operation for the target content, and updating the target document comprises: Determining a target position in the target document based on the indication information, the target position being represented by at least one of: a starting character sequence number corresponding to the starting position, or an ending character sequence number corresponding to the ending position; and The target editing operation is performed on the target position.

4. The method according to claim 1, wherein the target content is generated by: Determining, using a first machine learning model among the one or more machine learning models, whether reference information obtained from at least one first data source satisfies a data requirement indicated by the edit request; In response to determining that the reference information satisfies the data requirement, generating the target content based on the reference information using a second machine learning model among the one or more machine learning models; In response to the reference information not satisfying the data requirement, updating the reference information based on a second data source using the first machine learning model; as well as In response to determining using the first machine learning model that the updated reference information meets the data requirement, using the second machine learning model, the target content is generated based on the updated reference information.

5. The method according to claim 4, wherein the at least one first data source is determined by: Based on the indication information, determining the target document part where the target content is located from one or more document parts of the target document; and Based on the editing request and the configuration information of the target document part, the at least one first data source is determined from at least one data source configured in the target document part.

6. The method according to claim 5, wherein the second data source is determined by: Based on the reference information and the description information of at least one data source configured in the target document portion, generating prompt information for the machine learning model to obtain an output of the machine learning model; and Based on an output of the machine learning model, determine the second data source.

7. The method of claim 4, wherein the first machine learning model has fewer parameters than the second machine learning model.

8. The method of claim 1, wherein receiving an edit request for a target document comprises: Presenting the target document and the first entry for natural language input in different areas of the user interface; as well as The edit request is received via the first portal.

9. The method of claim 1, wherein the edit request is received by: In response to a selection of content in the target document, presenting a second entry for natural language input; determining the edit request based on the user input received via the second portal and the selected portion, and The content in the target document indicated by the indication information is at least partially different from the selected content.

10. The method according to claim 1, wherein the indication information comprises at least one of the following: the starting text segment indicating the starting position of said segment, or The ending text segment indicating the end position.

11. The method of claim 2, wherein the plurality of editing operations comprises at least one of the following: Content removal operations, a content replacement operation, or Content adding operation.

12. An apparatus for document processing, comprising: A receiving template configured to receive an edit request for a target document, wherein the edit request indicates a modification requirement for at least a portion of the target document; Generate a template, configured to generate indication information for target content based on the edit request and at least a portion of the target document using one or more machine learning models, wherein the target content is content to be edited, and the indication information at least indicates at least one of a starting position or an ending position of the target content in the target document; as well as An update template is configured to update the target document based on the indication information.

13. 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 11 when executed by the at least one processing unit.

14. 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 11.

Images