Document generation method and device, equipment, storage medium and product

Abstract

The embodiment of the invention provides a document generation method and device, equipment, a storage medium and a product. The method comprises the steps that configuration information of a target document is determined, the configuration information indicates generation requirements of the target document and one or more reference data sources used for document generation, and at least one reference data source in the one or more reference data sources has access authority within a preset range; in response to a generation request for a target document, obtaining reference information by using one or more reference data sources; and generating the target document based on the reference information. Therefore, the reference information for document generation can be obtained by using different types of reference data sources according to actual requirements. And particularly, the reference data source with certain access authority is utilized to obtain more targeted and more accurate reference information, so that the quality of the generated document is improved.

Description

Technical Field

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

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

[0003] In a first aspect of the present disclosure, a document generation method is provided. The method includes: determining configuration information of a target document, the configuration information indicating generation requirements of the target document and one or more reference data sources for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights; in response to a generation request for the target document, obtaining reference information using the one or more reference data sources; and generating the target document based on the reference information.

[0004] In a second aspect of the present disclosure, a device for document generation is provided. The device includes: a configuration information determination module configured to determine configuration information of a target document, the configuration information indicating generation requirements of the target document and one or more reference data sources used for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights; a reference information acquisition module configured to obtain reference information using one or more reference data sources in response to a generation request for the target document; and a document generation module configured to generate the target document based on the reference 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] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions, wherein the computer executable instructions implement the method of the first aspect when executed by a processor.

[0008] 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

[0009] 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:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart showing an example process of document generation according to some embodiments of the present disclosure;

[0012] FIG. 3A to FIG. 3F A schematic diagram showing an example interface for creating a document template according to some embodiments of the present disclosure;

[0013] FIG. 4A to FIG. 4C A schematic diagram showing an example interface for generating a document using a document template according to some embodiments of the present disclosure;

[0014] Figure 5 A schematic structural block diagram showing an example apparatus for document generation according to some embodiments of the present disclosure; and

[0015] Figure 6 A block diagram illustrating an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] As used herein, a "document template" or "template" may refer to an electronic, computer-processable file that describes how to generate a document.

[0028] As briefly described above, machine learning models can be applied to content creation, data analysis and other fields. At present, conventional intelligent writing methods usually generate documents based on data retrieved from public data sources. Since the data sources used in this way usually have certain limitations, the retrieved data is incomplete and inaccurate, resulting in low quality of generated documents. Especially in business-oriented (ToB) scenarios, it is necessary to use data that is highly relevant to the business, but this type of data is often non-public data. In this scenario, if document generation is implemented based on data retrieved from public data sources, it will be difficult to meet the requirements of document generation. Therefore, it is worth exploring how to use appropriate data sources to generate documents.

[0029] According to an embodiment of the present disclosure, an improved solution for document generation is provided. In this solution, the configuration information of the target document is first determined, and the configuration information indicates the generation requirements of the target document and one or more reference data sources used for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights. Then, in response to a generation request for the target document, reference information is obtained using one or more reference data sources. Finally, the target document is generated based on the reference information. In this way, different types of reference data sources can be used to obtain reference information for document generation according to actual needs. In particular, more targeted and accurate reference information is obtained using reference data sources with certain access rights, thereby improving the quality of the generated document. Example Environment

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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 that constitutes the application. The application creation part can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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 of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect.

[0047] 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. Example Process

[0048] Figure 2 200 is a flowchart showing an example process 200 of document generation according to some embodiments of the present disclosure. Figure 1 The process 200 is described with reference to the environment 100 of FIG. The process 200 may be implemented in Figure 1 The application management platform 110 is located at .

[0049] like Figure 2As shown, in box 210, the application management platform 110 determines the configuration information of the target document. The configuration information of the target document at least indicates the generation requirements of the target document and one or more reference data sources used for document generation. The generation requirements of the target document represent the description of the content of the target document to be generated, and may include, for example, the subject, field, structure, style, word count, etc. of the target document. For example, the generation requirements may be "introducing the definition, scope, and development history of the pet industry." The reference data source of the target document represents the source of the data referenced in generating the target document. For example, the reference data source may include a knowledge base, various types of data objects (e.g., local files, online documents, etc.), a public data source, etc.

[0050] In an embodiment of the present disclosure, 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 user set with access rights, such as an internal knowledge base of an enterprise, a local file uploaded by a user, etc.

[0051] In some embodiments, the target document may include one or more document parts. The reference data source may include a reference data source for the entire target document and may also include a reference data source for a document part. In the case of using a document template to generate the target document, the reference data source for the target document and the reference data source for the document part may be configured by a creator of the document template (e.g., user 105) and / or a user of the document template (e.g., end user 145).

[0052] In order to more clearly understand the use of data sources in the embodiments of the present disclosure, the following reference will be made to FIG. 3A to FIG. 3F as well as FIG. 4A to FIG. 4C The following describes an example configuration method for a reference data source.

[0053] As discussed above, the application management platform 110 has an application creation part and an application running part. The application creation part can support the user 105 to generate or create a document template for writing, and the user 105 can configure a reference data source for the document template in the process of generating or creating the document template. In the application running part, the application management platform 110 can support the terminal user 145 to generate a target document based on the document template, and the user 145 can configure the reference data source in the process of generating the target document. In some embodiments, the application management platform 110 can receive the operation of the user 105 via the interface presented in the application creation part, and determine the configuration information of the document template and each document part therein. In other embodiments, the application management platform 110 can receive the operation of the terminal user 145 via the interface presented in the application running part, and determine the configuration information of the target document and each document part therein. The following will refer to the example interface diagram to describe these two implementation methods in detail.

[0054] FIG. 3A to FIG. 3F Example interfaces 300A to 300F for creating document templates according to some embodiments of the present disclosure are shown. In an embodiment of the present disclosure, interfaces 300A to 300F may be composed of Figure 1 Provided by the application creation portion of the application management platform 110 shown.

[0055] In some embodiments, if it is detected that the user 105 initiates template creation, the application management platform 110 may present an interface for the user 105 to provide a template generation request. Figure 3A , the interface 300A may present an editing area 302 for the generation requirements of the document template and a configuration area 304 for the reference data source. Exemplarily, the user 105 may configure the generation requirements of the template by operating the editing area 302 for the generation requirements, and may configure one or more reference data sources of the template by operating the configuration area 304 for the reference data source. The reference data source specified by the configuration area 304 may be applied to the entire document, and is not limited to one or more specific document parts.

[0056] If the template creation process is initiated, the application management platform 110 may first generate the structure information of the target template and present it to the user 105. Figure 3B, an editing area 310 for the document structure may be presented on the interface 300B. The document structure may include one or more document parts. The document parts discussed herein may refer to chapters or paragraphs of a document. In some embodiments, each document part may have a corresponding title, which may also be referred to as a chapter title or a paragraph title. As an example, the titles of multiple document parts may be presented in the editing area 310, such as "Overview of Industry Development", "Origin of the Industry", ..., "Industry Consumer Behavior Analysis", etc. The editing area 310 includes multiple editable items corresponding to the multiple document parts, and the title of each document part may be presented in each editable item. For example, an editable item may be an editable item 311 including the title "Overview of Industry Development". Through the editable item, the corresponding document part can be edited and configured.

[0057] In some embodiments, the editable item corresponding to each document part may include a configuration entry 320 for the document part. The configuration entry 320 can be any appropriate type of entry for configuring the corresponding document part. In one example, as shown in the figure, after receiving a preset operation of the user 105 for a certain editable item, the configuration entry 320 can be presented in the editable item. The preset operations discussed herein may, for example, include any appropriate type of operations such as click operations (such as single-click operations, double-click operations, etc.), long press operations, sliding operations, etc., without limitation. In another example, the configuration entry can be directly presented in each editable item. It should be understood that the presentation method of the configuration entry can be set according to actual needs, without limitation here.

[0058] If the configuration process for the document part is initiated, the application management platform 110 may present a configuration panel for the document part to the user 105. Figure 3C , after receiving the preset operation of the user 105 on the configuration entry 320, the application management platform 110 can present a configuration panel 325. The configuration panel 325 can also be a configuration window, a configuration page, etc. Through the configuration panel 325, the configuration of the corresponding document part by the user 105 can be received. In some embodiments, the configuration panel 325 may include content description information for the corresponding document part, and the content description information may indicate the generation requirements for the main content of the corresponding document part (for example, the generation requirement example in box 326). Based on the user input for the content description information, the application management platform 110 can update the content description information as at least a part of the configuration information of the corresponding document part. Here, the user input can be the user 105 inputting the content description information in the form of text or voice.

[0059] In some embodiments, the configuration panel 325 may include a configuration area 330 for reference data. The application management platform 110 may receive a preset operation of the user 105 on the configuration area 330, thereby presenting a configuration interface of the corresponding reference data source. For example, the application management platform 110 may receive a preset operation of the user 105 on the add control 332 in the configuration area 330, thereby presenting a configuration interface 300D or 300E of the reference data source for specific configuration of the reference data source.

[0060] If a specific configuration process for the reference data source is initiated, the application management platform 110 may present a configuration interface for the reference data source to the user 105. Figure 3D , the application management platform 110 may receive the operation of the user 105 on the configuration interface 300D to receive the configuration of the knowledge base by the user 105. For example, when configuring the document part in the industry analysis report template, the user 105 may select the industry analysis knowledge base. Figure 3E , the application management platform 110 can receive the operation of the user 105 on the configuration interface 300E to receive the configuration of the data object by the user 105. For example, the user 105 can specify the data object by uploading a local file, adding a URL (Uniform Resource Locator), adding text, etc. In addition, although not specifically shown in the present disclosure, other reference data sources such as public data sources can also be configured in a similar manner to the above. For example, a data source searched by a specific search engine, a data source in a specific network platform, etc. can be configured.

[0061] In some embodiments, the application management platform 110 may present document preview information after receiving a preview instruction from the user 105. The document preview information may indicate document generation requirements. The document generation requirements may include, for example, the subject of the target document or supplementary information. Figure 3F After receiving the preset operation of the user 105 on the document preview control 340, the application management platform 110 presents the document preview information in a box 342. In some embodiments, the application management platform 110 can receive the user 105's supplementary information through an entry 344 for inputting text, an entry 345 for inputting a website link, an entry 346 for uploading an attachment, etc., so as to serve as at least a part of the reference data source of the target document.

[0062] References FIG. 3A to FIG. 3FAn example of configuring a parameter data source in a template creation process is described. After the template is created, the user 105 can publish the created template. For example, the template can be published in a target application 120 so that a user of the target application 120 can select and use the template. In the process of using the template to generate a target document, the user of the template can at least partially modify the configuration of the reference data source in the template. FIG. 4A to FIG. 4C 400A to 400C are shown as example interfaces for generating documents using document templates according to some embodiments of the present disclosure. In an embodiment of the present disclosure, interfaces 400A to 400C may be composed of Figure 1 The application management platform 110 shown is provided by the application running part.

[0063] In some embodiments, if the end user 145 triggers document generation, the application management platform 110 may present a relevant interface to the end user 145 for the end user 145 to indicate the document generation requirement and select the template to be used. Figure 4A The interface 400A may include a configuration area 402 for generating requirements of a target document and a template selection area 404. For example, the terminal user 145 may input generation requirements for a target document in the configuration area 402 and may select a template for the target document in the selection area 404.

[0064] In some embodiments, reference Figure 4B , after the terminal user 145 selects a template, an editing area 410 and a navigation area 415 for the document structure may be presented on the interface 400B. The document structure may include one or more document parts. The navigation area 415 may include navigation information about the document structure, such as titles and hierarchical relationships of multiple document parts. Similar to the editing area 310 on the interface 300B, the editing area 410 may include multiple editable items corresponding to multiple document parts, and each editable item may include a configuration entry 420 for the corresponding document part. The configuration entry 420 may implement a configuration function similar to the configuration entry 320. In some embodiments, after receiving the preset operation of the terminal user 145 on the configuration entry 420, the application management platform 110 may present a configuration panel 425 similar to the configuration panel 325 on the interface 400B. Through the configuration panel 425, the application management platform 110 may receive similar configurations of the corresponding document part by the terminal user 145, which will not be repeated here.

[0065] In some embodiments, after the terminal user 145 completes the configuration of the document part, the configuration of the target document can be supplemented before the target document is generated. Figure 4CThe interface 400C may include a configuration area 430 of the target document. The terminal user 145 may further supplement the generation requirements of the target document, reference data sources, etc. by performing preset operations on the configuration area 430.

[0066] The configuration of the reference data source can be achieved by, for example, the methods described above. However, it should be understood that the configuration process described above is only exemplary and is not intended to be limiting. In the embodiments of the present disclosure, the reference data source can be configured in any appropriate manner in various appropriate processes. For example, in the process of creating a template using a reference document or generating a target document using a reference document, the reference data source can be specified.

[0067] Continue to refer Figure 2 In box 220, the application management platform 110 obtains reference information using one or more reference data sources in response to a request to generate a target document. Reference information refers to part of the information in the reference data source that matches the generation requirements of the target document. In box 230, the application management platform 110 generates the target document based on the reference information. In some embodiments, the application management platform 110 can generate the target document using a machine learning model (e.g., model 155). In the case of generating a document using a model, the reference information can be vectorized data. The method of obtaining the reference information will be described in detail below.

[0068] In some embodiments, a request to generate a target document may be initiated by a target user, and at least one reference data source may include a knowledge base to which the user set to which the target user belongs has access rights. For example, if the target user is an employee of an enterprise, the corresponding knowledge base may be an internal knowledge base of the enterprise, and all or part of the employees of the enterprise have access rights to the knowledge base. In some embodiments, the knowledge base may include multiple knowledge fragments. The knowledge in the knowledge base is usually in the form of text, images, sounds, etc., and various forms of knowledge can be vectorized to obtain multiple knowledge fragments. For example, a knowledge fragment can be vectorized data of a sentence or a paragraph in an article. The vectorized data can be directly provided to the model as input data.

[0069] In some embodiments, based on the context information and subject information corresponding to multiple knowledge fragments, the application management platform 110 can obtain at least one knowledge fragment that matches the generation requirements from the knowledge base as at least a part of the reference information. The context information of a knowledge fragment can characterize the knowledge set to which the knowledge fragment belongs. For example, the context information of a paragraph can characterize the article described in the paragraph. The subject information of a knowledge fragment can characterize the content contained in the knowledge fragment. Supplementing the context information for the knowledge fragment can enable the knowledge fragment to have the global information of the knowledge set to which it belongs, so that the knowledge in the knowledge base can be more fully utilized, thereby improving the accuracy of retrieval.

[0070] In some embodiments, the context information of the knowledge fragment can be obtained in the following manner: the application management platform 110 extracts the content dimension features related to the target knowledge fragment from the target knowledge set to which the target knowledge fragment belongs, and generates the context information of the target knowledge fragment based on the content dimension features. In some embodiments, the content dimension features can be used to characterize the title of the knowledge set, the subtitle of the part of the knowledge set corresponding to the knowledge fragment, the abstract of the knowledge set, or the keywords of the knowledge set. For example, a paragraph in an article can be supplemented with the title, subtitle, abstract, or keywords of other paragraphs of the article as metadata (i.e., the above-mentioned context information), so that the paragraph has the global information of the entire article.

[0071] The application management platform 110 can retrieve the required knowledge fragments from the knowledge base in any suitable manner. In some embodiments, the application management platform 110 can determine one or more keywords related to the main content of the target document according to the generation requirements of the target document. Then, the knowledge fragment whose context information or main information matches at least one of the one or more keywords can be retrieved from the knowledge base, and the retrieved knowledge fragment is determined as at least one knowledge fragment. For example, when generating a pet industry analysis report, a keyword can be "pet". In this case, the knowledge fragment whose context information or main information matches "pet" is retrieved from the knowledge base as the knowledge fragment for document generation. For example, in an example article in the knowledge base, the body part (i.e., the main information part) of a paragraph does not contain the retrieved keyword "pet", but the keyword is contained in its context and title. In this case, the above-mentioned supplementary metadata method can be used to enable the knowledge fragment of the body part to be retrieved according to the keyword to provide it to the model for use.

[0072] In some embodiments, the target document generation request is initiated by a target user, and at least one reference data source may include a data object specified by the target user. For example, the target user (such as the terminal user 145) may upload or specify a document.

[0073] In order to retrieve knowledge from such a data object, in some embodiments, the application management platform 110 can obtain multiple knowledge fragments for the data object by performing vectorization processing on multiple parts of the above-mentioned data object. For example, an article uploaded or specified by a user can be vectorized into multiple knowledge fragments for model consumption. In some embodiments, the vectorization processing of the data object can be in response to receiving a document generation request. For example, if the terminal user 145 initiates the document generation process, the above-mentioned vectorization processing can be started on the specified data object. In some embodiments, the data object can be vectorized in advance without waiting for the document generation request. For example, after the user 105 or the terminal user 145 configures the data object, the data object can be vectorized. In this way, after receiving the document generation request, the knowledge fragments that have been pre-vectorized can be directly used, thereby improving the document generation efficiency. In some embodiments, the application management platform 110 can retrieve at least one knowledge fragment that matches the generation requirements from multiple knowledge fragments as at least part of the reference information. Similar to the search in the knowledge base, the application management platform 110 can determine one or more keywords based on the generation requirements, and then retrieve the knowledge fragments whose context information or subject information matches at least one of the one or more keywords from the multiple knowledge fragments contained in the user-specified data object, and determine the retrieved knowledge fragments as at least one knowledge fragment.

[0074] In some embodiments, the target document may include one or more document parts, and the configuration information of the target document part in the one or more document parts indicates a set of reference data sources for the target document part. Figure 4B For the document section "Overview of the Development of the Pet Industry", a set of reference data sources can be configured for it. For the document section "Analysis of the Industrial Chain of the Pet Industry", another set of reference data sources can be configured for it. Since different document sections of the target document have different focuses, configuring different data sources can make the content generation more targeted.

[0075] In some embodiments, for a target document portion, the application management platform 110 can obtain reference data for the target document portion from a set of reference data sources corresponding to the target document portion, and based on the reference data, generate the main content of the target document portion as part of the target document. For example, the target document "Pet Industry Analysis Report" contains several chapters. The application management platform 110 can first obtain reference data for each chapter from a set of reference data sources corresponding to each chapter. Then, the application management platform 110 can provide the reference data of each chapter to the model separately to generate the main content of the chapter. Finally, the application management platform 110 can merge the main contents of each chapter to obtain the analysis report. In some embodiments, the reference data source configured for the target document can be used for one or more document parts of the target document. When retrieving reference information for a target document paragraph, it can be retrieved from the reference data source of the target document, or it can be retrieved from the reference data source of the target document paragraph.

[0076] In some embodiments, each of the one or more reference data sources has a different priority for the generation of the target document. In the case of using a model to generate a target document, the reference information obtained from different reference data sources has different weights in the model application. In some embodiments, the priority is related to the degree of association between each reference data source and the target user. In some embodiments, the higher the degree of association between the reference data source and the target user, the higher its priority. For example, the priorities of the following reference data sources are from high to low: the data object specified by the target user, the knowledge base to which the user set to which the target user belongs has access rights, and the public data source. Since the generation of the target document is closely related to the needs of the target user, the document uploaded or specified by the target user can have the highest priority, followed by the knowledge base to which the user set to which the target user belongs has access rights, and the public data source has the lowest priority because it has the lowest association with the target user. It should be understood that the priority of each reference data source can also have other different setting methods, which can be set according to actual conditions.

[0077] In some embodiments, the priority of each reference data source may affect the process of obtaining reference information, thereby affecting the generation of the target document. For example, the application management platform 110 may preferentially obtain reference information from a reference data source with a high priority.

[0078] In the case of generating documents based on machine learning models, the priorities of various reference data sources can act on the process of model application, thereby affecting the generation of target documents. In some embodiments, the application management platform 110 can provide prompt information to the machine learning model based on the reference information obtained from one or more data sources and the corresponding priorities of one or more reference data sources to obtain the output of the machine learning model. In some embodiments, if different document parts are generated separately, for the target document part (for example, any document part) of the target document, the application management platform 110 can provide prompt information to the machine learning model based on the reference information of the target document part and the configured priority of the reference data source to obtain the output of the document part. In some embodiments, the application management platform 110 can generate the corresponding main content of one or more document parts of the target document based on the output of the machine learning model.

[0079] In order to make the machine learning model aware of the priority of each reference data source, in some embodiments, the prompt information may include a priority indication for the corresponding priority of one or more reference data sources. In some embodiments, the priority indication may include an explicit indication, such as text used to describe the corresponding priority of one or more reference data sources. Alternatively or additionally, in some embodiments, the priority indication may include an implicit indication, such as the order of information related to one or more reference data sources in the prompt information. Exemplarily, the reference information obtained from a reference data source with a high priority is in the front order in the prompt information.

[0080] In the embodiments described above, the implementation of some operations or steps may rely on a machine learning model. It should be understood that the machine learning models used in different operations or steps may be the same or different. The embodiments of the present disclosure are not limited to this.

[0081] The embodiments of the present disclosure can utilize different types of reference data sources to obtain reference information for document generation according to actual needs, and in particular utilize reference data sources with certain access rights to obtain more targeted and accurate reference information, thereby improving the quality of the generated document. Example devices and equipment

[0082] Figure 5 A schematic structural block diagram of an example apparatus 500 for document generation according to some embodiments of the present disclosure is shown. The apparatus 500 may be implemented as or included in the application management platform 110. Each module / component in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0083] As shown in the figure, the device 500 includes a configuration information determination module 510, which is configured to determine the configuration information of the target document, the configuration information indicating the generation requirements of the target document and one or more reference data sources for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights.

[0084] The apparatus 500 further includes a reference information acquisition module 520 configured to acquire reference information using one or more reference data sources in response to a request for generating a target document.

[0085] The apparatus 500 further includes a document generating module 530 configured to generate a target document based on the reference information.

[0086] In some embodiments, a generation request is initiated by a target user, at least one reference data source includes a knowledge base to which a user set to which the target user belongs has access rights, the knowledge base includes multiple knowledge fragments, and the reference information acquisition module 520 is further configured to obtain at least one knowledge fragment matching the generation requirement from the knowledge base based on the context information and subject information corresponding to the multiple knowledge fragments, as at least a part of the reference information, the context information of a knowledge fragment among the multiple knowledge fragments representing the knowledge set to which the knowledge fragment belongs.

[0087] In some embodiments, the device 500 also includes a context information generating device, which is configured to extract content dimension features related to the target knowledge fragment from the target knowledge set to which the target knowledge fragment belongs; and generate context information of the target knowledge fragment based on the content dimension features.

[0088] In some embodiments, the content dimension feature is used to characterize at least one of the following: a title of the knowledge set, a subtitle of a portion of the knowledge set corresponding to a knowledge fragment, a summary of the knowledge set, or keywords of the knowledge set.

[0089] In some embodiments, the reference information acquisition module 520 is also configured to determine one or more keywords related to the main content of the target document according to the generation requirements; retrieve knowledge fragments from the knowledge base whose context information or main information matches at least one of the one or more keywords; and determine the retrieved knowledge fragment as at least one knowledge fragment.

[0090] In some embodiments, the device 500 also includes a vectorization module, which is configured to obtain multiple knowledge fragments for the data object by performing vectorization processing on multiple parts of the data object; and the reference information acquisition module 520 is also configured to retrieve at least one knowledge fragment that matches the generation requirements from the multiple knowledge fragments as at least part of the reference information.

[0091] In some embodiments, the target document includes one or more document parts, and the configuration information of the target document part in the one or more document parts indicates a set of reference data sources for the target document part, and the reference information acquisition module 520 is also configured to obtain reference data for the target document part from a set of reference data sources, and the document generation module 530 is also configured to generate the main content of the target document part based on the reference data of the target document part as part of the target document.

[0092] In some embodiments, each of the one or more reference data sources has a different priority for generating a target document, and the priority is related to the degree of association between each reference data source and the target user.

[0093] In some embodiments, the priorities of the one or more reference data sources are as follows from high to low: data objects specified by the target user, knowledge bases to which the user set to which the target user belongs has access rights, and public data sources.

[0094] In some embodiments, the document generation module 530 is also configured to provide prompt information to the machine learning model based on the reference information and the corresponding priorities of one or more reference data sources to obtain the output of the machine learning model, the prompt information including a priority indication for the corresponding priorities of one or more reference data sources; and based on the output of the machine learning model, generate the corresponding main content of one or more document parts of the target document.

[0095] In some embodiments, the priority indication includes: text for describing the corresponding priority of the one or more reference data sources, or the order of the information related to the one or more reference data sources in the prompt information.

[0096] Figure 6 1 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 6 The electronic device 600 shown can be used to implement Figure 1 Application management platform 110.

[0097] like Figure 6As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0098] The electronic device 600 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 may be a volatile memory (e.g., registers, caches, 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 630 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 600.

[0099] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 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 620 may include a computer program product 625 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0100] The communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 600 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.

[0101] The input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate with any device that allows the electronic device 600 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).

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 generation method, comprising: Determining configuration information of a target document, the configuration information indicating generation requirements of the target document and one or more reference data sources used for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights; In response to a request for generating the target document, obtaining reference information using the one or more reference data sources; as well as The target document is generated based on the reference information.

2. The method according to claim 1, wherein the generation request is initiated by a target user, the at least one reference data source comprises a knowledge base to which a user set to which the target user belongs has access rights, the knowledge base comprises a plurality of knowledge fragments, and obtaining the reference information comprises: Based on the context information and subject information corresponding to the multiple knowledge fragments, at least one knowledge fragment matching the generation requirements is obtained from the knowledge base as at least a part of the reference information, and the context information of the knowledge fragment among the multiple knowledge fragments represents the knowledge set to which the knowledge fragment belongs.

3. The method according to claim 2, wherein the context information of the target knowledge fragment among the plurality of knowledge fragments is obtained by: Extracting content dimension features related to the target knowledge fragment from the target knowledge set to which the target knowledge fragment belongs; and Based on the content dimension features, the context information of the target knowledge fragment is generated.

4. The method according to claim 3, wherein the content dimension feature is used to characterize at least one of the following: the title of the knowledge collection, the subtitle of the part of the knowledge set corresponding to the knowledge fragment, a summary of said knowledge set, or Keywords of the knowledge set.

5. The method according to claim 2, wherein acquiring at least one knowledge segment matching the generation requirement of the target document from the knowledge base comprises: Determining one or more keywords related to the main content of the target document according to the generation requirement; Retrieving from the knowledge base a knowledge fragment in which the context information or the subject information matches at least one of the one or more keywords; as well as The retrieved knowledge fragment is determined as the at least one knowledge fragment.

6. The method according to claim 1, wherein the generation request is initiated by a target user, the at least one reference data source includes a data object specified by the target user, and the method further comprises: By performing vectorization processing on multiple parts of the data object, multiple knowledge fragments for the data object are obtained, and Wherein obtaining the reference information comprises: At least one knowledge fragment matching the generation requirement is retrieved from the plurality of knowledge fragments as at least a part of the reference information.

7. The method according to claim 1, wherein the target document comprises one or more document parts, configuration information of a target document part in the one or more document parts indicates a set of reference data sources for the target document part, and obtaining the reference information comprises: obtaining reference data for the target document portion from the set of reference data sources, and Generating the target document based on the reference information includes: Based on the reference data of the target document portion, the main body content of the target document portion is generated as a part of the target document.

8. The method according to claim 1, wherein each of the one or more reference data sources has a different priority for generating the target document, and the priority is related to the degree of association between each reference data source and the target user.

9. The method according to claim 8, wherein the priorities of the reference data sources in the one or more reference data sources are, from high to low, the following: data objects specified by the target user, knowledge bases to which the user set to which the target user belongs has access rights, and public data sources.

10. The method according to claim 8, wherein generating the target document based on the reference information comprises: Based on the reference information and the respective priorities of the one or more reference data sources, providing prompt information to the machine learning model to obtain an output of the machine learning model, the prompt information including a priority indication for the respective priorities of the one or more reference data sources; as well as Based on the output of the machine learning model, corresponding body content of one or more document parts of the target document is generated.

11. The method of claim 10, wherein the priority indication comprises: text describing the respective priorities of the one or more reference data sources, or The order of the information related to the one or more reference data sources in the prompt information.

12. A device for document generation, comprising: a configuration information determination module, configured to determine configuration information of a target document, wherein the configuration information indicates generation requirements of the target document and one or more reference data sources used for document generation, wherein at least one of the one or more reference data sources has a predetermined range of access rights; A reference information acquisition module, configured to acquire reference information using the one or more reference data sources in response to a generation request for the target document; as well as The document generation module is configured to generate the target document based on the reference information.

13. An electronic device comprising: at least one processing unit; as well as 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, the instructions, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1-11.

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.

15. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 11.

Images