Method and system for facilitating an editing of a digital document

Abstract

The present disclosure relates to method(s) and system(s) for facilitating an editing of a digital document The method comprises receiving the digital document. The method further comprises capturing, using a sub-system, a context from the digital document based on a set of data. Further, the method comprises extracting, using data extraction technique(s), a data from the digital document. The method then comprises enabling, using the sub-system, an editing of the extracted data based on execution of data processing function(s) on the extracted data, and the captured context. Further, method comprises providing simultaneously, on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Thereafter, the method comprises facilitating the editing of the digital document based on the receiving of the user feedback and the captured context.

Description

METHOD AND SYSTEM FOR FACILITATING AN EDITING OF A DIGITAL DOCUMENTTECHNICAL FIELD

[0001] Embodiment of the present disclosure generally relates to document editing techniques. More particularly, the present disclosure relates to a method and a system for facilitating an editing of a digital document.BACKGROUND

[0002] The following description of the related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as an admission of the prior art.

[0003] The field of publication has always been driven by the essence of storytelling. However, the narrative is incomplete without a touch of editing. The editing plays an indispensable role in the publishing process as it involves the critical assessment and enhancement of the content, structure, and style of a manuscript to render it more compelling, informative, and marketable. Therefore, it may be understood that editing goes beyond being just another step in the journey of publishing. It is a vital component that dives into the intricacies of word choices, narrative context, and the author's artistic vision. In a competitive landscape, it is essential that an author's manuscript is not only free of errors but also captivating, in order to captivate a broad readership.

[0004] Currently, this responsibility has rested upon human editors who draw upon their expertise, experience, and intuition to identify and rectify errors,discrepancies, and weaknesses within the manuscript. However, this conventional approach is marred by several drawbacks. It is a time-consuming endeavor that incurs significant cost and is inherently subjective, thereby susceptible to errors, biases, and misunderstandings.

[0005] To overcome such issues, tools are developed in the art to aid in editing documents by leveraging techniques. However, existing solutions have their own set of challenges. For instance, traditional editing tools lack the ability to grasp the broader context within a document, such as a book or a novel. This leads to less effective editing and a higher likelihood of inconsistencies. Additionally, extracting text from PDFs or other formats for editing purposes has been a cumbersome process with existing technologies, often resulting in formatting issues and loss of data that further result in poor performance. The process of notetaking and annotation is largely manual in traditional editing systems, which is time-consuming and prone to errors. Storing and retrieving textual data efficiently is often a challenge with existing technologies, thereby leading to slower editing processes.SUMMARY

[0006] This section is provided to introduce certain aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

[0007] An aspect of the present disclosure may relate to a method for facilitating an editing of a digital document. The method comprises receiving, by a processing unit, the digital document. The method further comprises capturing, by the processing unit using a sub-system, a context from the digital document based on a set of data. Further, the method comprises extracting, by the processing unit using one or more data extraction techniques, a data from the digitaldocument. Next, the method comprises enabling, by the processing unit using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context. Further, the method comprises providing simultaneously, by the processing unit on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Thereafter, the method comprises facilitating, by the processing unit, the editing of the digital document based on the receiving of the user feedback and the captured context.

[0008] In an exemplary aspect of the present disclosure, the digital document is associated with a document type and a document format.

[0009] In an exemplary aspect of the present disclosure, the sub-system is an Artificial Intelligence (Al) based module.

[0010] In an exemplary aspect of the present disclosure, the set of data is received from one or more data sources, and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents.

[0011] In an exemplary aspect of the present disclosure, the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents.

[0012] In an exemplary aspect of the present disclosure, the contextual data comprises at least one of a system generated contextual data and a manually determined contextual data.

[0013] In an exemplary aspect of the present disclosure, the extracted data comprises a textual data.

[0014] In an exemplary aspect of the present disclosure, the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a data amending function, a data omitting function, a data adding function, and a data deleting function.

[0015] In an exemplary aspect of the present disclosure, for said enabling the editing of the extracted data, the sub-system utilizes the plurality of vector datasets.

[0016] In an exemplary aspect of the present disclosure, said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types.

[0017] In an exemplary aspect of the present disclosure, the user interface is a real time preview interface.

[0018] In an exemplary aspect of the present disclosure, the method comprises: 1) providing, by the processing unit on the user interface, one or more prompt based options, 2) receiving, by the processing unit via the user interface, a user selection of the one or more prompt based options, and 3) facilitating, by the processing unit, a prompt based automatic editing of the digital document based on the received user selection of the one or more prompt based options.

[0019] In an exemplary aspect of the present disclosure, the method further comprises: 1) updating, by the processing unit, the set of data based on the user feedback; and 2) facilitating, by the processing unit, the editing of the digital document based on the updated set of data.

[0020] Another aspect of the present disclosure may relate to a system for facilitating an editing of a digital document. The system comprises a processing unit and a storage unit connected to at least the processing unit. The processingunit is configured to receive the digital document. The processing unit is further configured to capture, using a sub-system, a context from the digital document based on a set of data. Next, the processing unit is configured to extract, using one or more data extraction techniques, a data from the digital document. Also, the processing unit is configured to enable, using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context. Further, the processing unit is configured to provide simultaneously, on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Thereafter, the processing unit is configured to facilitate the editing of the digital document based on the receiving of the user feedback and the captured context.

[0021] In an exemplary aspect of the present disclosure, the digital document is associated with a document type and a document format.

[0022] In an exemplary aspect of the present disclosure, the sub-system is an Artificial Intelligence (Al) based module.

[0023] In an exemplary aspect of the present disclosure, the set of data is received from one or more data sources, and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents.

[0024] In an exemplary aspect of the present disclosure, the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents.

[0025] In an exemplary aspect of the present disclosure, the contextual data comprises at least one of a system generated contextual data and a manually determined contextual data.

[0026] In an exemplary aspect of the present disclosure, the extracted data comprises a textual data.

[0027] In an exemplary aspect of the present disclosure, the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a data amending function, a data omitting function, a data adding function, and a data deleting function.

[0028] In an exemplary aspect of the present disclosure, for said enabling the editing of the extracted data, the sub-system utilizes the plurality of vector datasets.

[0029] In an exemplary aspect of the present disclosure, said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types.

[0030] In an exemplary aspect of the present disclosure, the user interface is a real time preview interface.

[0031] In an exemplary aspect of the present disclosure, the processing unit is further configured to: 1) provide, on the user interface, one or more prompt based options, 2) receive, via the user interface, a user selection of the one or more prompt based options, and 3) facilitate, a prompt based automatic editing of the digital document based on the received user selection of the one or more prompt based options.

[0032] In an exemplary aspect of the present disclosure, the processing unit is further configured to: 1) update the set of data based on the user feedback and 2) facilitate the editing of the digital document based on the updated set of data.OBJECTS OF THE DISCLOSURE

[0033] Some of the objects of the present disclosure which at least one embodiment disclosed herein satisfies are listed herein below.

[0034] It is an object of the present disclosure to provide a system and a method for facilitating an editing of a digital document.

[0035] It is another object of the present disclosure to provide a solution for comprehensive and efficient editing of digital documents, such as novels, storybooks, journals, and other lengthy manuscripts.

[0036] It is yet another object of the present disclosure to provide a solution to significantly enhance the editing process.

[0037] It is yet another object of the present disclosure to provide a solution to make the editing process quicker and more precise.

[0038] It is yet another object of the present disclosure to provide a solution to assist human editors in their document editing tasks.

[0039] It is yet another object of the present disclosure to provide a solution that provides an editing system that is configured to identify errors, inconsistencies, and areas for improvement in a document by using artificial intelligence (Al), thereby enhancing the quality of editing.

[0040] It is yet another object of the present disclosure to provide a solution for a real-time collaborative editing environment that fosters communication and collaboration among human editors and other stakeholders.

[0041] It is yet another object of the present disclosure to provide a solution that allows for instant feedback and enhances the overall editing process.BRIEF DESCRIPTION OF DRAWINGS

[0042] The accompanying drawings, which are incorporated herein, constitute a part of this disclosure. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes disclosure of electrical components or circuitry commonly used to implement such components. Although exemplary connections between sub -components have been shown in the accompanying drawings, it will be appreciated by those skilled in the art that other connections may also be possible, without departing from the scope of the invention. All sub -components within a component may be connected to each other, unless otherwise indicated.

[0043] FIG. 1 illustrates an exemplary block diagram of a system for facilitating an editing of a digital document, in accordance with the exemplary embodiments of the present invention.

[0044] FIG. 2 illustrates another exemplary block diagram of an environment depicting an interaction between computing unit(s) and an application server for facilitating an editing of a digital document, in accordance with the exemplary embodiments of the present invention.

[0045] FIG. 3 illustrates an exemplary flow diagram of a method for facilitating an editing of a digital document, in accordance with the exemplary embodiments of the present invention.

[0046] The foregoing shall be more apparent from the following more detailed description of the invention.DETAILED DESCRIPTION

[0047] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter may each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above.

[0048] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0049] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail.

[0050] Also, it is noted that individual embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a data flow diagram, astructure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations may be performed in parallel or concurrently. In addition, the order of the operations may be rearranged. A process is terminated when its operations are completed but could have additional steps not included in a figure.

[0051] The word “exemplary” and / or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and / or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word without precluding any additional or other elements.

[0052] As used herein, a “processing unit” or “processor” or “operating processor” includes one or more processors, wherein processor refers to any logic circuitry for processing instructions. A processor may be a general -purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. The processor may perform signal coding, data processing, input / output processing, and / or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor or processing unit is a hardware processor.

[0053] As used herein, “a user equipment”, “a user device”, “a smart-user- device”, “a smart device”, “an electronic device”, “a mobile device”, “a handheld device”, “a wireless communication device”, “a mobile communication device”, “a communication device” may be any electrical, electronic and / or computing device or equipment, capable of implementing the features of the present disclosure. The user equipment / device may include, but is not limited to, a mobile phone, smart phone, laptop, a general -purpose computer, desktop, personal digital assistant, tablet computer, wearable device or any other computing device which is capable of implementing the features of the present disclosure. Also, the user device may contain at least one input means configured to receive an input from at least one of a processing unit, a storage unit, and any other such unit(s) which are required to implement the features of the present disclosure.

[0054] As used herein, “storage unit” or “memory unit” refers to a machine or computer readable medium including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer- readable medium includes read-only memory (“ROM”), random access memory (“RAM”), magnetic disk storage media, optical storage media, flash memory devices or other types of machine-accessible storage media. The storage unit stores at least the data that may be required by one or more units of the system to perform their respective functions.

[0055] The present invention relates to a system and a method for editing document(s) using generative artificial intelligence (Al) models as current editing processes and tools do not provide a fast, economical and accurate editing. Further, the existing solutions lack the ability to grasp the broader context within a document such as a digital book etc.

[0056] The present disclosure aims to overcome the above-mentioned and other existing challenges in editing of extensive documents, addressing the current limitations in the editing process and tools, which often fall short in terms ofspeed, cost-effectiveness, and precision. Additionally, these existing solutions tend to lack the capacity to comprehend the broader context within a document, which the present invention aims to overcome. Particularly, the disclosure of the current invention surmounts the aforementioned issues and other prevailing deficiencies by providing an Al-assisted editing capabilities, efficient text extraction methods, and a real-time collaborative editing environment for human intervention within the editing process, thereby optimizing the editing process while enhancing the overall efficiency and consistency of the document.

[0057] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0058] Referring to FIG. 1, an exemplary block diagram of a system

[0100] for facilitating an editing of a digital document, in accordance with the exemplary embodiments of the present invention is illustrated. The system

[0100] comprises at least one processing unit

[0102] and at least one storage unit

[0104] , Also, all of the components / units of the system

[0100] are assumed to be connected to each other unless otherwise indicated below. Also, in FIG. 1 only a few units are shown, however, the system

[0100] may comprise multiple such units or the system

[0100] may comprise any such numbers of said units, as required to implement the features of the present disclosure.

[0059] Referring to FIG. 2, another exemplary block diagram of an environment

[0200] depicting an interaction between computing unit(s)

[0210] and an application server

[0212] for facilitating the editing of the digital document, in accordance with the exemplary embodiments of the present invention is illustrated. The environment

[0200] comprises one or more computing units

[0210] , at least one application server

[0212] , at least one communication interface

[0213] , and at least one data source

[0215] , In a preferred implementation of the present disclosure the system

[0100] is configured at the application server

[0212] for facilitating the editing of the digital document. However, the present disclosure isnot limited thereto, and the system

[0100] may be configured in the environment

[0200] in a manner as appreciated by a person skilled in the art in light of the present disclosure. Also, in FIG. 2 only a few units are shown, however, the environment

[0200] may comprise multiple such units or the environment

[0200] may comprise any such numbers of said units, as required to implement the features of the present disclosure.

[0060] Further, the application server

[0212] is a back-end server connected to the one or more computing units

[0210] (or referred herein as one or more user devices) through the communication interface

[0213] , In an implementation the application server

[0212] in addition to the system

[0100] also comprises at least one document editing module

[0220] , one or more programming instructions

[0250] , and one or more chat interfaces

[0280] , The document editing module

[0220] comprises one or more sub-modules

[0230] , Further, the one or more sub-modules

[0230] comprises at least one data capturing module

[0231] , at least one text extraction module

[0232] , at least one text processing module

[0233] , at least one note taking module

[0234] , at least one chat module

[0235] , and at least one artificial intelligence (Al) module

[0236] , Further, the storage unit

[0104] , of the system

[0100] , comprises one or more first data-sets

[0214] , and one or more second data-sets

[0216] ,

[0061] In an implementation the system

[0100] may utilize processing unit

[0102] and the storage unit

[0104] to implement the features as disclosed in the present disclosure. In another implementation the system

[0100] utilizes one or more units / components of the application server

[0212] to implement the features of the present disclosure. Also, it may be noted that FIG. 1 and FIG. 2 have been explained simultaneously and may be read in conjunction with each other.

[0062] Therefore, the system

[0100] is configured to facilitate the editing of the digital document, with the help of the interconnection between the components / units of the system

[0100] or with the help of the interconnectionbetween the system

[0100] and the one or more components of the application server

[0212] ,

[0063] Particularly for facilitating the editing of the digital document, the processing unit

[0102] is initially configured to receive the digital document. Also, in an implementation, the processing unit

[0102] is configured to receive the digital document utilizing the document editing module

[0220] , In such implementation, the document editing module

[0220] may receive the digital document from the one or more computing units

[0210] , However, the present disclosure in not limited thereto and the document editing module

[0220] may receive the digital document from the storage unit

[0104] or from any other unit as appreciated by a person skilled in the art in light of the present disclosure. Further, the processing unit

[0102] via the document editing module

[0220] is configured to process the received digital document in accordance with the one or more programming instructions

[0250] to produce an edited version of the digital document, by using at least one of the one or more first data-sets

[0214] and the one or more second data-sets

[0216] , The digital document is associated with a document type and a document format. In an exemplary implementation, the document may be of any type and format such as, but not limited to, PDFs, scanned word / PDF files, word documents, e- books, or e-documents.

[0064] It is to be noted that the document type and the document format mentioned above are only exemplary and in no manner intended to limit the scope of the present disclosure. The document type and the document format may include any type or format as obvious to a person skilled in the art, to implement the features of the present disclosure.

[0065] More specifically, after receiving the digital document, the processing unit

[0102] is configured to capture, using a sub-system, a context from the digital document based on a set of data (herein the set of data may also be referred to as a second data-set

[0216] ). Also, the processing unit

[0102] may usethe data capturing module

[0231] to capture the context of the digital document. Further, the sub-system is an Artificial Intelligence (Al) based module (for e.g., Al module

[0236] ). Also, the set of data is received from one or more data sources (herein a data source may also be referred to as the data source

[0215] ), and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents. The contextual data may include at least one of a system generated contextual data and a manually determined contextual data. In an implementation, the system generated contextual data includes information that is automatically determined by a processing unit (say for example the processing unit

[0102] ) from a plurality of documents related to a plurality of use cases. For example, in a scenario where the plurality of documents are related to environment protection, then in such scenarios the processing unit may automatically determine an information related to environment protection from such plurality of documents and stores the automatically determined information as a system generated contextual data. Further, in an implementation, said automatically determined information may be stored in a prompt library as one or more prompts. Moreover, in an implementation, the manually determined contextual data includes information that is manually determined from a plurality of documents related to a plurality of use cases. For example, in a scenario where the plurality of documents are related to enhancements in electric vehicles, then in such scenarios an information related to enhancements in electric vehicles is determined manually, and such manually determined information is then stored as a manually determined contextual data. Further, in an implementation, said manually determined information may be stored in a prompt library as one or more prompts.

[0066] Further, the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents. In an exemplary implementation, the context captured, using the sub-system, includes such as, but not limited to, a structure, a style, and oneor more nuances of the digital document, etc. for deeper understanding of content present in the digital document.

[0067] Further, the structure of the digital document may comprise details related to a framework or an order in which the content of the digital document is arranged. For example, the structure of the digital document may suggest that the digital document includes, say, a heading and 5 (five) sub-headings. The heading may include the title of the of the digital document and the sub-headings may include such as, but not limited to, introduction, table of content, summary, analysis, and conclusion.

[0068] Further, the style of the digital document may include details such as, but not limited to, a genre, a language of writing, a type (e.g., a newspaper, a marksheet etc.) of the digital document etc. For example, the use of complex language and vocabulary (such as use specific terminology) in the digital document may suggest that the digital document is for, say, academic purposes.

[0069] Furthermore, the one or more nuances may include one or more hidden, secondary or implicit meaning of, say, a line, a paragraph or the entire digital document.

[0070] Continuing further, the processing unit

[0102] is also configured to extract, using one or more data extraction techniques, a data from the digital document. The extracted data comprises a textual data. Also, the processing unit

[0102] may use the text extraction module

[0232] to extract the data from the digital document. The text extraction module

[0232] to extract the data may implement a plurality of text extraction techniques such as, but not limited to, a PDF extraction technique, an OCR extraction technique, etc.

[0071] It is to be noted that the abovementioned plurality of text extraction techniques are only exemplary and in no manner are intended to limit the scopeof the present disclosure. A text extraction technique may include any other text extraction technique as obvious to the person skilled in the art to implement the features of the present disclosure.

[0072] Further, the processing unit

[0102] is configured to enable, using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context. Also, the processing unit

[0102] may use the text processing module

[0233] to enable the editing of the digital document. The editing of the digital document may be enabled for various use cases such as including but not limited to facilitate proofreading of the digital document, a developmental editing of the digital document, an editing of the digital document based on specialized genre(s) like historical fantasy or cookbook editing etc., and the like. Further, the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a data amending function, a data omitting function, a data adding function, and a data deleting function.

[0073] Further, the data editing function may involve function(s) such as, but not limited to, reviewing, revising, and / or refining the data for better accuracy, clarity, and readability. The data removing function may involve removing or eliminating certain piece(s) of the data from the digital document for improved clarity, relevance, or brevity. Next, the data inserting function may involve placing or introducing specific data at specific position(s) in the existing digital document. Further, the data amending function may involve changing or correcting the data in the digital document to remove any error, update the data and / or enhance the data for accuracy, clarity, and relevance. The data omitting function may involve not including some specific data in the digital document at the first place itself i.e., intentionally not adding the data in the digital document. Further, the data adding function involves adding a completely new information in the digital document which was originally not added. Furthermore, the data deleting function mayinvolve permanently removing some specific data from the digital document leaving no scope of retrieving back the data.

[0074] Further, for said enabling the editing of the extracted data, the subsystem utilizes the plurality of vector datasets. Particularly, the sub-system utilizes the one or more second data-sets

[0216] in the form of embedded vector representation(s) for enabling the editing of the extracted data and to gain a comprehensive understanding of the data in the digital document. In an implementation, the sub-system utilizes a large language model (LLM) to facilitate an efficient editing of the digital document. Further, in an implementation, for enabling the editing of the extracted data and to gain the comprehensive understanding of the data in the digital document, the sub-system, based on a context of the digital document, determines and utilizes embedded vector representation(s) related to at least one of a system generated contextual data and a manually determined contextual data. Depending on use case(s), in such implementation, the sub-system may utilize embedded vector representation(s) related to one or more prompts that are determined based on at least one of 1) the system generated contextual data related to the context of the digital document, and 2) the manually determined contextual data related to the context of the digital document. Therefore, in such implementation, as the sub-system utilizes the system generated contextual data and / or the manually determined contextual data based on the context of the digital document, the sub-system is optimized to focus on particular aspect(s) of the editing process.

[0075] Furthermore, said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types. The classification of the elements may be performed on one or more components of the extracted text for example, including but not limited to, one or more architectural components, one or more structural components, one or more mechanical components, one or more electrical components, one or more plumbing components, one or more firefighting components, one or more interiorcomponents, and / or the like components as obvious to a person skilled in the art in light of the present disclosure.

[0076] Considering an example, an article is written about Taj Mahal. The text from the article is extracted for editing. Upon the extraction of the text from the article, the classification of the elements is performed on one or more components of the extracted text. The extracted text includes one or more architectural components related to the Taj Mahal such as, the dimensions of the Taj Mahal, material used to build it, etc. The one or more elements classified may include such as, but not limited to, the sangmarmar marble through which the Taj Mahal was built.

[0077] Continuing further, the processing unit

[0102] is configured to provide simultaneously, on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Further, the user interface is a real time preview interface, and the user interface may be facilitated via the chat interface

[0280] , Also, the processing unit

[0102] may use the chat module

[0235] to provide the user interface on the set of user devices. The user interface is designed for swift and immediate communication and collaboration among a set of users of the set of user devices to receive the user feedback for editing the extracted data. The set of users includes one or more editors, and / or one or more stakeholders involved in the editing of the digital document.

[0078] In an implementation, the processing unit

[0102] is configured to provide on the user interface, one or more prompt based options to activate a prompt based editing of the digital document. A user selection of such one or more prompt based options is received by the processing unit

[0102] , and then based on said received user selection the processing unit

[0102] activates a prompt based automatic editing of the digital document. This prompt based automatic editing of the digital document in an event may be terminated by the processing unit

[0102] upon receiving an automatic request and / or a manual request for terminating said automatic editing. More specifically, once the one or more prompt based options are provided / displayed on the user interface for user selection, the processing unit

[0102] triggers API call(s) upon receiving user selected one or more prompt based options. The processing unit

[0102] then provide response(s) based on the API call(s) by utilizing the sub-system, and the response(s) are then displayed directly in a rich text editor via the real time preview interface, enabling user(s) to refine content of the digital document seamlessly.

[0079] This prompt based automatic editing not only saves time but also reduces the friction often associated with navigating complex editing interfaces or reformatting prompt(s) to fit a particular use case. As, the prompt based automatic editing may be enabled for various use cases (such as including but not limited to facilitate proofreading of the digital document, the developmental editing of the digital document, and the editing of the digital document based on the specialized genre(s), etc.), this further enhances user experience, as the user(s) can effortlessly browse through and select from categories such as including but not limited to copy-editing, developmental editing, and academic papers etc., accessing exactly what the users need without leaving the document environment. Therefore, the functionalities as disclosed in the present disclosure provide the user(s) with a running prompt library that overcomes the limitations related to requirement of manual efforts from the user(s) and continuously adapts to a context and preference(s) of an editing task at hand, making the solution in the present disclosure technically advanced over the existing solutions.

[0080] Further, the processing unit

[0102] , via the document editing module

[0212] , provides to the set of users an access to the note taking module

[0234] for dynamic editing in the digital document. The note taking module

[0234] allows the set of users to make instant changes in the digital document and may foster the efficient collaboration among the set of users. The note taking module

[0234] allows the set of users to annotate the data using one or more user-friendly editorsfor local note-taking. Further, the set of the users may add one or more comments, one or more suggestions, and one or more feedback as the set of users edit the digital document in real-time.

[0081] Continuing further, the processing unit

[0102] is configured to facilitate the editing of the digital document based on the receiving of the user feedback and the captured context. The processing unit

[0102] may use the Al module

[0236] to facilitate the editing of the digital document. The Al module

[0236] combines all the contexts and notes for processing and producing the edited version of the digital document. Further, the Al module

[0236] may improvise the one or more programming instructions

[0250] in accordance with an updated data set (the updated data set herein may also be referred to as a first data-set

[0214] ) received from plurality of other data sources.

[0082] Therefore, in an implementation, the processing unit

[0102] updates the set of data based on the user feedback and facilitates the editing of the digital document based on the updated set of data. More specifically, the one or more programming instructions

[0250] for each sub-module

[0230] may be specifically updated based on the user feedback, of the set of users, so as to constantly upgrade the document editing module

[0220] , Also, in an exemplary implementation, the one or more programming instructions

[0250] may be configured to learn and improvise in accordance with one or more Al based models, such as, but not limited to, a heuristic models (e.g., neural networks, fuzzy logic models, machine learning, expert system models, state vector machine models).

[0083] Referring to FIG. 3 an exemplary flow diagram of a method for facilitating an editing of a digital document, in accordance with the exemplary embodiments of the present invention. In an implementation the method

[0300] is performed by a system

[0100] , The system

[0100] performs the method

[0300] with the help of the interconnection between the components / units of the system

[0100] or with the help of the interconnection between the system

[0100] and one or morecomponents of the application server

[0212] as depicted in the FIG. 2. The method

[0300] as depicted in FIG. 3 starts at step

[0302] ,

[0084] At step

[0304] , the method

[0300] comprises receiving, by a processing unit

[0102] , the digital document. Also, in an implementation, the processing unit

[0102] receives the digital document utilizing the document editing module

[0220] , In such implementation, the document editing module

[0220] may receive the digital document from the one or more computing units

[0210] , However, the present disclosure in not limited thereto and the document editing module

[0220] may receive the digital document from the storage unit

[0104] or from any other unit as appreciated by a person skilled in the art in light of the present disclosure. Further, the processing unit

[0102] via the document editing module

[0220] processes the received digital document in accordance with the one or more programming instructions

[0250] to produce an edited version of the digital document, by using at least one of the one or more first data-sets

[0214] and the one or more second data-sets

[0216] , The digital document is associated with a document type and a document format. In an exemplary implementation, the document may be of any type and format such as, but not limited to, PDFs, scanned word / PDF files, word documents, e-books, or e-documents.

[0085] It is to be noted that the document type and the document format mentioned above are only exemplary and in no manner intended to limit the scope of the present disclosure. The document type and the document format may include any type or format as obvious to a person skilled in the art, to implement the features of the present disclosure.

[0086] Next, at step

[0306] , the method

[0300] comprises capturing, by the processing unit

[0102] using a sub-system, a context from the digital document based on a set of data. Also, the processing unit

[0102] may use the data capturing module

[0231] to capture the context of the digital document. Further, the subsystem is an Artificial Intelligence (Al) based module. Also, the set of data isreceived from one or more data sources (herein a data source may also be referred to as the data source

[0215] ), and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents. The contextual data may include at least one of a system generated contextual data and a manually determined contextual data. In an implementation, the system generated contextual data includes information that is automatically determined by a processing unit (say for example the processing unit

[0102] ) from a plurality of documents related to a plurality of use cases. For example, in a scenario where the plurality of documents are related to environment protection, then in such scenarios the processing unit may automatically determine an information related to environment protection from such plurality of documents and stores the automatically determined information as a system generated contextual data. Further, in an implementation, said automatically determined information may be stored in a prompt library as one or more prompts. Moreover, in an implementation, the manually determined contextual data includes information that is manually determined from a plurality of documents related to a plurality of use cases. For example, in a scenario where the plurality of documents are related to enhancements in electric vehicles, then in such scenarios an information related to enhancements in electric vehicles is determined manually, and such manually determined information is then stored as a manually determined contextual data. Further, in an implementation, said manually determined information may be stored in a prompt library as one or more prompts.

[0087] Further, the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents. In an exemplary implementation, the context captured, using the sub-system, includes such as, but not limited to, a structure, a style, and one or more nuances of the digital document, etc. for deeper understanding of content present in the digital document. Further, the structure of the digital document may comprise details related to a framework or an order in which the content of the digital document is arranged. Further, the style of the digital document mayinclude details such as, but not limited to, a genre, a language of writing, a type of the digital document etc. Furthermore, the one or more nuances may include one or more hidden, secondary or implicit meaning of, say, a line, a paragraph or the entire digital document.

[0088] Further, at step

[0308] , the method

[0300] comprises extracting, by the processing unit

[0102] using one or more data extraction techniques, a data from the digital document. The extracted data comprises a textual data. Also, the processing unit

[0102] may use the text extraction module

[0232] to extract the data from the digital document. The text extraction module

[0232] to extract the data may implement a plurality of text extraction techniques such as, but not limited to, a PDF extraction technique, an OCR extraction technique, etc.

[0089] It is to be noted that the abovementioned plurality of text extraction techniques are only exemplary and in no manner are intended to limit the scope of the present disclosure. A text extraction technique may include any other text extraction technique as obvious to the person skilled in the art to implement the features of the present disclosure.

[0090] Further, at step

[0310] , the method

[0300] comprises enabling, by the processing unit

[0102] using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context. Also, the processing unit

[0102] may use the text processing module

[0233] to enable the editing of the digital document. The editing of the digital document may be enabled for various use cases such as including but not limited to facilitate proofreading of the digital document, a developmental editing of the digital document, an editing of the digital document based on specialized genre(s) like historical fantasy or cookbook editing etc., and the like. Further, the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a dataamending function, a data omitting function, a data adding function, and a data deleting function.

[0091] Further, the data editing function may involve functions such as, but not limited to, reviewing, revising, and / or refining the data for better accuracy, clarity, and readability. The data removing function may involve removing or eliminating certain piece(s) of the data from the digital document for improved clarity, relevance, or brevity. Next, the data inserting function may involve placing or introducing specific data at specific position(s) in the existing digital document. Further, the data amending function may involve changing or correcting the data in the digital document to remove any error, update the data and / or enhance the data for accuracy, clarity, and relevance. The data omitting function may involve not including some specific data in the digital document at the first place itself i.e., intentionally not adding the data in the digital document. Further, the data adding function involves adding a completely new information in the digital document which was originally not added. Furthermore, the data deleting function may involve permanently removing some specific data from the digital document leaving no scope of retrieving back the data.

[0092] Further, for said enabling the editing of the extracted data, the subsystem utilizes the plurality of vector datasets. Particularly, the sub-system utilizes the one or more second data-sets

[0216] in the form of embedded vector representation(s) for enabling the editing of the extracted data and to gain a comprehensive understanding of the data in the digital document. In an implementation, the sub-system utilizes a large language model (LLM) to facilitate an efficient editing of the digital document. Further, in an implementation, for enabling the editing of the extracted data and to gain the comprehensive understanding of the data in the digital document, the sub-system, based on a context of the digital document, determines and utilizes embedded vector representation(s) related to at least one of a system generated contextual data and a manually determined contextual data. Depending on use case(s), in suchimplementation, the sub-system may utilize embedded vector representation(s) related to one or more prompts that are determined based on at least one of: 1) the system generated contextual data related to the context of the digital document, and 2) the manually determined contextual data related to the context of the digital document. Therefore, in such implementation, as the sub-system utilizes the system generated contextual data and / or the manually determined contextual data based on the context of the digital document, the sub-system is optimized to focus on particular aspect(s) of the editing process.

[0093] Furthermore, said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types. The classification of the elements may be performed on one or more components of the extracted text for example, including but not limited to, one or more architectural components, one or more structural components, one or more mechanical components, one or more electrical components, one or more plumbing components, one or more firefighting components, one or more interior components, and / or the like components as obvious to a person skilled in the art in light of the present disclosure.

[0094] Further, at step

[0312] , the method

[0300] comprises providing simultaneously, by the processing unit

[0102] on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Further, the user interface is a real time preview interface, and the user interface may be facilitated via the chat interface

[0280] , Also, the processing unit

[0102] may use the chat module

[0235] to provide the user interface on the set of user devices. The user interface is designed for swift and immediate communication and collaboration among a set of users of the set of user devices to receive the user feedback for editing the extracted data. The set of users includes one or more editors, and / or one or more stakeholders involved in the editing of the digital document.

[0095] In an implementation, the processing unit

[0102] provides on the user interface, one or more prompt based options to activate a prompt based editing of the digital document. A user selection of such one or more prompt based options is received by the processing unit

[0102] , and then based on said received user selection the processing unit

[0102] activates a prompt based automatic editing of the digital document. This prompt based automatic editing of the digital document in an event may be terminated by the processing unit

[0102] upon receiving an automatic request and / or a manual request for terminating said automatic editing. More specifically, once the one or more prompt based options are provided / displayed on the user interface for user selection, the processing unit

[0102] triggers API call(s) upon receiving user selected one or more prompt based options. The processing unit

[0102] then provide response(s) based on the API call(s) by utilizing the sub-system, and the response(s) are then displayed directly in a rich text editor via the real time preview interface, enabling user(s) to refine content of the digital document seamlessly.

[0096] This prompt based automatic editing not only saves time but also reduces the friction often associated with navigating complex editing interfaces or reformatting prompt(s) to fit a particular use case. As, the prompt based automatic editing may be enabled for various use cases (such as including but not limited to facilitate proofreading of the digital document, the developmental editing of the digital document, and the editing of the digital document based on the specialized genre(s), etc.), this further enhances user experience, as the user(s) can effortlessly browse through and select from categories such as including but not limited to copy-editing, developmental editing, and academic papers etc., accessing exactly what the users need without leaving the document environment. Therefore, the functionalities as disclosed in the present disclosure provide the user(s) with a running prompt library that overcomes the limitations related to requirement of manual efforts from the user(s) and continuously adapts to a context and preference(s) of an editing task at hand, making the solution in the present disclosure technically advanced over the existing solutions.

[0097] Further, the processing unit

[0102] , via the document editing module

[0212] , provides to the set of users an access to the note taking module

[0234] for dynamic editing in the digital document. The note taking module

[0234] allows the set of users to make instant changes in the digital document and may foster the efficient collaboration among the set of users. The note taking module

[0234] allows the set of users to annotate the data using one or more user-friendly editors for local note-taking. Further, the set of the users may add one or more comments, one or more suggestions, and one or more feedback as the set of users edit the digital document in real-time.

[0098] Furthermore, at step

[0314] , the method

[0300] comprises facilitating, by the processing unit

[0102] , the editing of the digital document based on the receiving of the user feedback and the captured context. Also, the processing unit

[0102] may use the Al module

[0236] to facilitate the editing of the digital document. The Al module

[0236] combines all the contexts and notes for processing and producing the edited version of the digital document. Further, the Al module

[0236] may improvise the one or more programming instructions

[0250] in accordance with an updated data set (the updated data set herein may also be referred to as a first data-set

[0214] ) received from plurality of other data sources.

[0099] Therefore, in an implementation, the processing unit

[0102] updates the set of data based on the user feedback and facilitates the editing of the digital document based on the updated set of data. More specifically, the one or more programming instructions

[0250] for each sub-module

[0230] may be specifically updated based on the user feedback, of the set of users, so as to constantly upgrade the document editing module

[0220] , Also, in an exemplary implementation, the one or more programming instructions

[0250] may be configured to learn and improvise in accordance with one or more Al based models, such as, but not limited to, a heuristic models (e.g., neural networks, fuzzy logic models, machine learning, expert system models, state vector machine models).

[0100] Yet another aspect of the present disclosure may relate to a non- transitory computer readable storage medium storing one or more instructions for facilitating an editing of a digital document, the instructions include executable code which, when executed by one or more units of a system

[0100] , causes a processing unit

[0102] of the system

[0100] to receive the digital document. The executable code when further executed causes the processing unit

[0102] to capture, using a sub-system, a context from the digital document based on a set of data. Further, the executable code when executed causes the processing unit

[0102] to extract, using one or more data extraction techniques, a data from the digital document. Also, the executable code when executed causes the processing unit

[0102] to enable, using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context. Further, the executable code when executed causes the processing unit

[0102] to provide simultaneously, on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data. Furthermore, the executable code when executed causes the processing unit

[0102] to facilitate the editing of the digital document based on the receiving of the user feedback and the captured context.

[0101] Therefore, the present disclosure provides a technical solution for facilitating an editing of a digital document. More specifically, the present disclosure overcomes the existing problems in the field of technology by providing Al assisted editing of digital documents. Further, the present disclosure offers a comprehensive and efficient approach for editing documents, such as books, e-books, stories, articles novels, journals, and lengthy manuscripts in a variety of formats such as for example, including but not limited to PDF, Images, Docx, and the like. Further, the real-time collaborative editing environment offered by the present disclosure encourages communication and collaboration among human editors and stakeholders. This fosters dynamic editing and instant feedback, thereby making the editing process more efficient. Further, the solutionas disclosed in the present disclosure enhances efficiency by streamlining the editing tasks, reducing manual efforts, and expediting document preparation. Also, the implementation of artificial intelligence elevates the quality of editing, identifying errors and inconsistencies, thereby resulting in refined documents. Furthermore, the present disclosure provides advanced text extraction techniques that ensure text availability for editing, thereby saving time and effort. Moreover, the present disclosure provides user-friendly annotation that allows easy notetaking, which further facilitates interactive editing.

[0102] While considerable emphasis has been placed herein on the disclosed implementations, it will be appreciated that many implementations can be made and that many changes can be made to the implementations without departing from the principles of the present disclosure. These and other changes in the implementations of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.

Claims

We Claim:

1. A method for facilitating an editing of a digital document, the method comprises:- receiving, by a processing unit [102], the digital document;- capturing, by the processing unit [102] using a sub-system, a context from the digital document based on a set of data;- extracting, by the processing unit [102] using one or more data extraction techniques, a data from the digital document;- enabling, by the processing unit [102] using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context;- providing simultaneously, by the processing unit [102] on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data; and- facilitating, by the processing unit [102], the editing of the digital document based on the receiving of the user feedback and the captured context.

2. The method as claimed in claim 1, wherein the digital document is associated with a document type and a document format.

3. The method as claimed in claim 1, wherein the sub-system is an Artificial Intelligence (Al) based module.

4. The method as claimed in claim 1, wherein the set of data is received from one or more data sources, and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents.

5. The method as claimed in claim 4, wherein the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents.

6. The method as claimed in claim 4, wherein the contextual data comprises at least one of a system generated contextual data and a manually determined contextual data.

7. The method as claimed in claim 1, wherein the extracted data comprises a textual data.

8. The method as claimed in claim 1, wherein the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a data amending function, a data omitting function, a data adding function, and a data deleting function.

9. The method as claimed in claim 4, wherein for said enabling the editing of the extracted data, the sub-system utilizes the plurality of vector datasets.

10. The method as claimed in claim 1, wherein said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types.

11. The method as claimed in claim 1, wherein the user interface is a real time preview interface.

12. The method as claimed in claim 1, the method comprises: providing, by the processing unit [102] on the user interface, one or more prompt based options, receiving, by the processing unit [102] via the user interface, a user selection of the one or more prompt based options, and facilitating, by the processing unit [102], a prompt based automatic editing of the digital document based on the received user selection of the one or more prompt based options.

13. The method as claimed in claim 1, the method comprises:- updating, by the processing unit [102], the set of data based on the user feedback, and- facilitating, by the processing unit [102], the editing of the digital document based on the updated set of data.

14. A system for facilitating an editing of a digital document, the system comprises:- a processing unit [102]; and- a storage unit [104] connected to at least the processing unit [102], wherein the processing unit [102] is configured to: o receive the digital document, o capture, using a sub-system, a context from the digital document based on a set of data, o extract, using one or more data extraction techniques, a data from the digital document, o enable, using the sub-system, an editing of the extracted data based on an execution of one or more data processing functions on the extracted data, and the captured context, o provide simultaneously, on a set of user devices, a user interface for receiving a user feedback for editing the extracted data, based on the enabling the editing of the extracted data, and o facilitate, the editing of the digital document based on the receiving of the user feedback and the captured context.

15. The system as claimed in claim 14, wherein the digital document is associated with a document type and a document format.

16. The system as claimed in claim 14, wherein the sub-system is an Artificial Intelligence (Al) based module.

17. The system as claimed in claim 14, wherein the set of data is received from one or more data sources, and the set of data comprises a plurality of vector datasets related to a contextual data associated with a plurality of digital documents.

18. The system as claimed in claim 17, wherein the plurality of vector datasets comprises a plurality of textual embeddings related to the contextual data associated with the plurality of digital documents.

19. The system as claimed in claim 17, wherein the contextual data comprises at least one of a system generated contextual data and a manually determined contextual data.

20. The system as claimed in claim 14, wherein the extracted data comprises a textual data.

21. The system as claimed in claim 14, wherein the one or more data processing functions comprises at least one of a data editing function, a data removing function, a data inserting function, a data amending function, a data omitting function, a data adding function, and a data deleting function.

22. The system as claimed in claim 17, wherein for said enabling the editing of the extracted data, the sub-system utilizes the plurality of vector datasets.

23. The system as claimed in claim 14, wherein said enabling the editing of the extracted data is further based on a classification of one or more elements of the extracted data into one or more element types.

24. The system as claimed in claim 14, wherein the user interface is a real time preview interface.

25. The system as claimed in claim 14, wherein the processing unit [102] is further configured to: provide, on the user interface, one or more prompt based options, receive, via the user interface, a user selection of the one or more prompt based options, and facilitate, a prompt based automatic editing of the digital document based on the received user selection of the one or more prompt based options.

26. The system as claimed in claim 14, wherein the processing unit [102] is further configured to:- update the set of data based on the user feedback, and facilitate the editing of the digital document based on the updated set of data.

Images