Digital workflow application generation

Converting textual workflows to a data interchange format with interactive step-by-step confirmation addresses the challenges of labor-intensive conversion and human error, ensuring consistent language and best practices in digital workflow applications.

WO2025264925A1PCT designated stage Publication Date: 2025-12-26DOW GLOBAL TECHNOLOGIES LLC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
PCT/US2025/034376
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-06-20
Filing Date
2025-06-19
Publication Date
2025-12-26

AI Technical Summary

Technical Problem

Converting unstructured text workflows to application program formats for digital workflow applications is labor-intensive, prone to human error, and often results in inconsistent language and best practices across different organizations.

Method used

A method to convert textual workflow documents into a data interchange format, using machine learning and subject matter expert input to generate an application program format that includes interactive images requiring step-by-step confirmation, ensuring consistent language and best practices.

Benefits of technology

This approach reduces human error and ensures uniformity in workflow execution, enabling accurate metadata collection and adherence to organizational standards.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2025034376_26122025_PF_FP_ABST
    Figure US2025034376_26122025_PF_FP_ABST
Patent Text Reader

Abstract

In at least one example, a method for that includes receiving, by a machine, a plurality of documents, each in an unstructured text format that includes a respective workflow description with a respective plurality of steps, converting, by the machine, the plurality of documents in the unstructured text format to a data interchange format, extracting, by the machine, respective textual information and respective position information associated with the textual information from each of the plurality of documents in the data interchange format based on a dictionary for the plant including a plurality of rules for the extraction, determining, by the machine, a respective workflow function associated with the respective extracted textual information based on the respective position information, and generating, by the machine, a respective application program format of the respective workflow description utilizing the respective textual information and corresponding respective workflow function.
Need to check novelty before this filing date? Find Prior Art

Description

DIGITAL WORKFLOW APPLICATION GENERATIONTechnical Field

[0001] The present disclosure relates to digital workflow application generation by converting a text document to an application program format that can be executed by a digital workflow application. Such techniques can be particularly useful to generate digital workflows that can be utilized to run an industrial facility, troubleshoot issues, repair equipment or perform other types of workflows.Background

[0002] Digitalization enables new ways of working. Procedures and checklists can be used to ensure proper steps are followed for performing various activities. One of the challenges in adoption of digital procedures is that it is a labor intensive process to take a procedure and author it in digital procedures that are executable by digital workflow applications. In some cases, the procedure can be provided on printed substrates (e.g., paper) to record processes performed. The printed substrates can be useful for recording particular steps and what was performed during the process, however, particular data may be lost or may not be accurately captured by the user (e g., human user, etc.).

[0003] Non-digital or non-interactive procedures can lead to human error when completing or submitting the procedures. In some cases, a human user may not be restricted from making contradictory statements or providing contradictory data when filling out a non-digital or non-interactive workflow, which can lead to misinterpretations at the organization level.Summary of the Disclosure

[0004] The present disclosure is directed to generating digital workflows for a digital workflow application based on workflows in an unstructured text format. The unstructured text format can be utilized by an organization to instruct and record performance of the workflows. Converting the workflows from the unstructured text format to an application program format can be time consuming with a relatively high rate of human error. In addition, multiple different organizations may want to conform to a more uniform set of workflow instructions for the application program format. It may not be possible for the organizations to convert the quantityof workflows from the unstructured text format to the application program format uniformly without significant human error.

[0005] In some examples, the application program format of the workflow can be executed by a digital workflow application. During the execution of the application program format, a graphical user interface can display a series of interactive images corresponding to steps of the workflow. In some embodiments, at least one of the series of interactive images requires a human user to confirm completion of one of the plurality of steps corresponding to the at least one image before a successive image of the series of interactive images is displayed. Thus, the graphical user interface can require that the human user progress through the series of images and / or the series of steps. In this way, additional meta data can be collected at each of the plurality of steps and steps that are dependent on non-selected steps can be prevented from being displayed. In this way, the digital workflow application can ensure higher quality workflow completion and / or more accurate data collection compared to the workflow completed utilizing the unconstructed text format.

[0006] The above summary of the present disclosure is not intended to describe each disclosed embodiment or every implementation of the present disclosure. The description that follows more particularly exemplifies illustrative embodiments. In several places throughout the application, guidance is provided through lists of examples, which examples can be used in various combinations. In each instance, the recited list serves only as a representative group and should not be interpreted as an exclusive list.Brief Description of the Drawings

[0007] Figure 1 illustrates one example of a textual workflow document that can be utilized to generate an application program format for a digital workflow application.

[0008] Figure 2 illustrates one example of a table of position information extracted from a workflow document that can be utilized to generate an application program format for a digital workflow application.

[0009] Figure 3 illustrates one example flow diagram of a method to generate a digital workflow for a digital workflow application.

[0010] Figure 4 illustrates an example of a machine readable medium to generate a digital workflow for a digital workflow application.

[0011] Figure 5 illustrates an example of a device to generate a digital workflow for a digital workflow application.Detailed Description

[0012] The present disclosure relates to methods and devices for converting a textual workflow document into a digital workflow that can be executed by a digital workflow application. As used herein, a workflow can refer to a description of a process with a plurality of steps that are performed at least in part by a human user at a plant (e.g., production facility, organization facility, etc.). The textual workflow documents can be unstructured text format documents that can include a description of a workflow with a plurality of steps. The textual workflow documents can include, but are not limited to: text documents (e.g., .txt files, doc files, .docx files, etc ), spreadsheets (e.g., xls files, xlsx files, etc.), presentation documents (e.g., .ppt files), and / or image documents that include text (e.g., pdf files). These textual workflow documents can be displayed on a user interface and / or printed on to a substrate such that a human user can utilize the textual workflow documents to record performance of particular workflows. For example, the textual workflow documents can be filled out as a human user performs a plurality of steps of the workflow.

[0013] Textual workflow documents can be limited by a number of factors. For example, the textual workflow documents may not be able to collect metadata while the textual workflow document is being filled out. As used herein, metadata is additional data that is collected in addition to data provided by the human user. For example, metadata, such as timestamps, location data, and / or other data, can be collected while the human user is providing information utilizing the digital workflow application. In addition, the textual workflow documents may not be dynamically updated based on tasks that are completed or tasks that are not applicable to complete the particular workflow. Furthermore, the textual workflow documents may allow a human user to incorrectly fill out or incorrectly complete the workflow without indicating that there was an error associated with the performance of the workflow.

[0014] Due to these drawbacks, digital workflows that are executed by digital workflow applications executing an application program format can be utilized to collect metadata, dynamically update during the workflow, and / or prevent the workflow from being completed incorrectly. In some embodiments, a digital workflow application can display a series ofinteractive images corresponding to the respective plurality of steps on a graphical user interface of the digital workflow. In these embodiments, a portion of the series of interactive images can require a human user to confirm completion of one of the plurality of steps corresponding to the at least one image before a successive image of the series of interactive images is displayed. In this way, a human user can be prevented from interacting with the successive image prior to confirming completion of a prior step. The interactive images can include objects, texts, and / or other features that can be displayed through a graphical user interface. In this way, the interactive images can provide visual and / or textual instructions for performing one or more of the plurality of steps.

[0015] However, a corresponding application program format for these digital workflow applications can be difficult and / or time consuming to generate. In addition, these digital workflows or application program formats may be generated with language that is different from the textual workflow documents that were historically utilized by a particular organization. Furthermore, the application program formats for the digital workflows may be generated without utilizing the determined best practices for a particular organization. Thus, utilizing the previous textual workflow documents to generate the application program formats for the digital workflows that can be executed by a digital workflow application can allow an organization to utilize digital workflows that implement the same language and / or best practices of an organization.

[0016] The present disclosure relates to converting a textual workflow document into an application program format that can be executed by a digital workflow application to generate the digital workflow. In some embodiments, the present disclosure can utilize a textual workflow document to generate a data interchange format that includes the textual data, position data, and / or metadata of the textual workflow document. In some embodiments, the data interchange format of the workflow can be utilized to determine workflow functions for the plurality of steps of the workflow and utilize the workflow functions to generate a digital workflow in an application program format that can be executed by a digital workflow application. As used herein, the workflow functions refer to the plurality of steps to be performed associated with the workflow. In this way, the digital workflow can utilize the same terminology associated with the textual workflow document and implement specific selectable inputs for each of the plurality of steps of the workflow based on the information extracted from the textual workflow document.

[0017] As used herein, the singular forms “a”, “an”, and “the” include singular and plural referents unless the content clearly dictates otherwise. Furthermore, the word “may” is used throughout this application in a permissive sense (e.g., having the potential to, being able to), not in a mandatory sense (e.g., must). The term “include,” and derivations thereof, mean “including, but not limited to.”

[0018] As will be appreciated, elements shown in the various embodiments herein can be added, exchanged, and / or eliminated so as to provide a number of additional embodiments of the present disclosure. In addition, as will be appreciated, the proportion and the relative scale of the elements provided in the figures are intended to illustrate certain embodiments of the present invention and should not be taken in a limiting sense.

[0019] Figure 1 illustrates one example of a textual workflow document 100 that can be utilized to generate an application program format for a digital workflow application. In some embodiments, the textual workflow document 100 can be in an unstructured text format. As used herein, an unstructured text format can refer to a document that includes formatted text or other elements like images and tables, typically used for documentation, reports, letters, and other formatted text documents. As described herein, the unstructured text format can include, but are not limited to: text documents, spreadsheets, presentation documents, and / or image documents, among other word processing formats.

[0020] The textual workflow document 100 can include a plurality of portions that can be utilized to inform a human user, utilized to record information, utilized to describe one or more of a plurality of steps, and / or utilized to confirm that one or more of the plurality of steps are completed. Although specific features of a specific workflow are illustrated by the textual workflow document 100, the present disclosure is not so limited. For example, a plurality of other types of steps or other types of workflows can have similar workflows as illustrated by the textual workflow document 100.

[0021] In some embodiments, the textual workflow document 100 includes a first title 101 that can read “SCOPE”. The first title 101 can correspond to a first feature 104. In some embodiments, the first feature 104 can describe the “SCOPE” of the workflow illustrated by the textual workflow document 100. In these embodiments, the textual information and / or positional information from the textual workflow document 100 can be utilized to determine a workflow function for the first title 101 and / or the first feature 104. As described further herein, the textualinformation and / or position information of the textual information can be utilized to determine or identify corresponding titles and features such that a particular workflow function can be determined. In this specific example, the textual information of “SCOPE” from the first title 101 can be extracted with the position information and utilized to determine that the scope of the workflow refers to the textual information from the first feature 104.

[0022] In some embodiments, the textual workflow document 100 can include a second title 102 and a second feature 105. In some embodiments, the second title 102 can be at a different position than the first title 101 and the second feature 105 can be at a different position than the first feature 104. In this way, the extracted position information can be utilized to distinguish between the first title 101 and corresponding first feature 104 and similarly be utilized to distinguish between the second title 102 and corresponding second feature 105. In some embodiments, the second feature 105 can have a different workflow function than the first feature 104. In these embodiments, the first feature 104 can be a first type of workflow function that is utilized to provide information to a human user and the second feature 105 can be a second type of workflow function that allows a human user to make particular selections. For example, the second feature 105 can include selectable inputs such as checkboxes to allow a user to select a corresponding box adjacent to text to indicate that a human user has completed the step associated with the adjacent text.

[0023] In some embodiments, the checkboxes can be generated based on the text of the second feature. For example, the second feature 105 can include text related to a task that is to be completed by the human user. In this example, a checkbox can be generated without a checkbox or similar feature being provided within the textual workflow document 100. In this way, checkboxes or other types of selectable inputs can be utilized based on the function or type of task, which can allow a plurality of different textual workflow documents to be uniform when converted to the digital workflow application format.

[0024] As used herein, a selectable input can include, but is not limited to: checkboxes that can be selected or deselected, text windows to enter text, selection windows to select a value or text from preselected values or text, and / or a selection box that includes selectable text. Although specific examples of selectable inputs are discussed, other types of selectable inputs can be utilized without departing from the present disclosure. In some embodiments, a type of selectable input can be determined based on the properties of the title and / or feature. Forexample, the title and / or feature can include properties that indicate that the title and / or feature corresponds to confirming if the human user has performed a task or if the human user is instructed to enter a particular value. In this way, the properties of the title and / or feature of the textual workflow document 100 can be utilized to determine which of the plurality of selectable inputs should be utilized.

[0025] For example, the second title 102 can correspond to the second feature 105. In this example, the second feature 105 includes checkboxes adjacent to text for “categories” and “attributes”. The checkboxes can be identified as locations to select one or more of the “categories” and / or “attributes”. In this way, the format of the textual workflow document 100 can include checkboxes that can be utilized to determine that selectable inputs should be utilized with the text that corresponds to the checkboxes within the textual workflow document 100.

[0026] In contrast, the third title 103 can refer to “hazards and precautions”. The third title 103 can be adjacent to the third feature 106 and / or a fourth feature 107. In these embodiments, the third title 103 and / or the third feature 106 can indicate that text data is to be communicated to a human user. In this way, the text data from the third feature 106 can be extracted to be presented to the human user when utilizing the digital workflow application. In some embodiments, the fourth feature 107 can include a table. The table can be utilized to format the text data within the table according to a set of best practices. For example, the text data within the table may be presented with selectable inputs such that a human user has to confirm they have read the text data within the table before proceeding to the subsequent text data within the table. In this way, a particular format for a plurality of different types of textual workflow documents 100 can be uniform when converted to the digital workflow application format and / or executed by the digital workflow application.

[0027] Figure 2 illustrates one example of a table 220 of position information extracted from a workflow document that can be utilized to generate an application program format for a digital workflow application. In some embodiments, the table 220 can illustrate the text data from textual workflow document 100 with the corresponding position data from the textual workflow document 100 as illustrated in Figure 1. In some embodiments, the textual workflow document 100 from Figure 1 can be converted from an unstructured text format that includes a workflow description with a plurality of steps to a data interchange format.

[0028] As used herein, the data interchange format can be a file format that can be utilized to change data from a first format to a second format. For example, the data interchange format can be a JavaScript Object Notation (JSON) file. The text and position information can be extracted from the unstructured text format and implemented into the JSON file such that the metadata of the JSON file can be utilized to generate the table 220 or determine the information within the table 220.

[0029] The table 220 can include the extracted text 221. As illustrated in the table, the text associated with the first title 101 (e.g., “scope”, etc.), the second title 102 (e.g., “attributes and categories”, etc.), the third title 103 (e.g., “hazards and precautions”, etc.), the first feature 104, the second feature 105, the third feature 106, and / or the fourth feature 107. In these embodiments, the extracted text 221 can be the same text as the text within the textual workflow document 100 as referenced in Figure 1. In some embodiments, the language or the text that is extracted from the textual workflow document 100 can be specific to the workflow such that changes to the language or the text can be detrimental to the workflow. For example, using slightly different sentence structure can lead to miscommunication for human users that are utilizing the textual workflow document 100. Such miscommunication can likewise be detrimental for a human user of the digital workflow application.

[0030] In some embodiments, the table 220 can include position data, such as, but not limited to: a block tag 222, a column tag 223, a row tag 224, and / or a total position 225. As used herein, a block tag 222 can refer to a tag that identifies a location of text within a document to denote a specific block or section of text. In some embodiments, the block tag 222 can refer to a label for a section of text, making it easier to reference and manipulate programmatically, particularly in digital document formats. In a similar way, a column tag 223 can be utilized to identifier a particular column within the digital document. Similarly, the row tag 224 can be utilized to denote a particular row within the digital document. Lastly, the total position 225 can be utilized to denote a unique identifier for each of the extracted text identified to be separated portions of text. In this way, a digital document can be divided into blocks to designate the block tag 222, divided into columns to designate a column tag 223, and divided into rows to designate a row tag. In these embodiments, the total position 225 can be calculated utilizing a combination of the other tags to come up with the unique total position 225.

[0031] In this way, a table 220 can be generated for each of a plurality of pages for a textual workflow document. In addition, the table can be generated for each of a plurality of different textual workflow documents, which can ensure that each of the plurality of different textual workflow documents utilize a uniformed format. In contrast, manually converting such textual workflow documents into the digital document formats would not ensure uniform formats between different textual workflow documents that are converted by different human users. Furthermore, as discussed herein, human users converting textual workflow documents are prone to human errors within the digital workflows.

[0032] Figure 3 illustrates one example flow diagram of a method 330 to generate a digital workflow for a digital workflow application. In some examples, the method 330 can be executed by a computing device or a machine as described herein. As described further herein, the method 330 can represent instructions that can be stored on a non-transitory computer readable medium and executed by a processor to perform the corresponding functions.

[0033] At step 360, the method 330 can be executed to receive a plurality of documents, each in an unstructured text format that includes a respective workflow description with a respective plurality of steps, wherein the plurality of documents are associated with operation of a plant. In some embodiments, the plant can be a physical location that includes a plurality of devices or systems that require inspection from human users. In these embodiments, the workflow descriptions can be utilized to instruct the human user how to perform particular steps of the workflow and / or ways for the human user to confirm completion or performance of the particular steps of the workflow.

[0034] In some embodiments, the plurality of documents can each be different types of unstructured text format documents. For example, some of the plurality of documents can be printed documents, some of the plurality of documents can be text documents, some of the plurality of documents can be spreadsheets, and / or some of the plurality of documents can be presentation documents, and / or image documents including text.

[0035] At step 361, the method 330 can be executed to convert the plurality of documents in the unstructured text format to a data interchange format. In some examples, the unstructured text format can be a digital document generated by a word processing application or spreadsheet application. For example, the unstructured text format can be a digital document generated as text documents or spreadsheets.

[0036] The workflow description can be a description of a process to be performed by a human user. For example, the workflow can be a plurality of steps that are performed by a human user. In these examples, the workflow can be utilized to inform the human user how to perform the plurality of steps and utilized as a documentation tool to document or record that the plurality of steps were performed by the human user. In this way, the unstructured text format of the workflow description can be utilized by an organization as an informational tool and a documentation tool to ensure the workflow is executed according to best practices determined by the organization.

[0037] At step 362, the method 330 can be executed to extract respective textual information and respective position information associated with the textual information from each of the plurality of documents in the data interchange format based on a dictionary for the plant including a plurality of rules for the extraction. As described herein, the data interchange format can refer to a text document that provides metadata that can be utilized to convert the document to a different type of format.

[0038] By way of example, the data interchange format can be a JSON format file that can include the extracted textual information, extracted formatting information, extracted position or location information, among other information that can be utilized to convert the information to a different format. In this way, the textual information and position information associated with the textual information can be utilized to generate a position table (e.g., table 220 as referenced in Figure 2, etc.). In this way, the textual information can be separated into particular groups and each group can be analyzed to determine a total position associated with the group of text. In addition, the group of text can be analyzed with the position information to determine a workflow function. In some embodiments, a dictionary definition of the textual information can be utilized to identify the workflow function of the corresponding textual information. For example, the dictionary definition of “scope” can refer to “the extent of the area or subject matter that something deals with or to which it is relevant”. In this way, the dictionary definition and position information of the extracted text “scope” can be utilized to identify other text with a similar position information.

[0039] In some embodiments, the method 330 can include developing the dictionary for the plant by a machine learning algorithm operating on the plurality of documents. In some embodiments, the dictionary can be supplemented with information from a subject matter expert.For example, the subject matter expert can identify terms and / or phrases that are associated with particular functions. In these embodiments, the information from the subject matter expert can be utilized to train the machine learning algorithm to help identify the particular functions to be performed by the human user and corresponding features for the digital workflow.

[0040] In some embodiments, a machine learning algorithm can be executed on the plurality of documents to develop the dictionary by identifying phrases and / or position information associated with the textual information within the plurality of documents. In this way, similar phrases and / or context can be identified by the machine learning algorithm to contextualize the textual information within the plurality of documents. In some embodiments, the dictionary can be developed to ensure that the same language and / or phrases are utilized to generate the plurality of corresponding workflows in the application program format.

[0041] At step 363, the method 330 can be executed to determine a respective workflow function associated with the respective extracted textual information based on the respective position information. As described herein, a workflow function can be a description or an identification of the purpose of the text associated with the step of the workflow. For example, the workflow function can refer to text that is utilized to inform a human user how to perform the step, warnings to the human user to prevent accidents, selections to be made by the human user upon completion, and / or data entry to be made by the human user based on an observation.

[0042] In this way, the workflow function can be utilized to determine a type of selectable input to be provided with or adjacent to the text to allow the human user to perform the workflow function and / or perform the step of the workflow and provide information related to the performance. In some embodiments, the method 330 can utilize the textual information, position information, and / or other formatting information to determine what type of input a human user is being instructed to provide. In this way, the selectable input can be identified based on the type of input the human user is being instructed to provide.

[0043] In some embodiments, determining the workflow function associated with the extracted textual information is based on formatting of the textual information. As described herein, the formatting can include check boxes or blank spaces for providing text. In other embodiments, the formatting can include a plurality of options with corresponding check boxes, which can indicate a selection from a list of options. In specific embodiments, the formatting includes one of a table, a checklist, a question, IF-THEN statements, and / or a reference to adifferent step of the plurality of steps. In this way, the formatting options can each have a corresponding selectable input to be utilized. In some embodiments, the formatting of the textual information can indicate that a particular type of data capture is to be performed. For example, the data capture can be performed by an automatic data capture such as, but not limited to: an optical character recognition (OCR), a barcode, a web service instruction, among other types of data capturing techniques.

[0044] At step 364, the method 330 can be executed to generate a respective application program format of the respective workflow description utilizing the respective textual information and corresponding respective workflow function. In some embodiments, the respective application program format is executable by a digital workflow application to display a series of interactive images corresponding to the respective plurality of steps on a graphical user interface. In these embodiments, at least one of the series of interactive images requires a human user to confirm completion of one of the plurality of steps corresponding to the at least one image before a successive image of the series of interactive images is displayed. As described herein, the application program format for a particular digital workflow can display one or more of the plurality of steps on the graphical user interface.

[0045] In some embodiments, particular steps may only be displayed when other steps are selected as complete. As described herein, a portion of the plurality of steps can be dependent on other steps of the plurality of steps. In this way, a first step may be displayed when a particular step is selected, and a second step may be displayed when the particular step is not selected. In this way, the digital workflow can prevent the human user from selecting portions that are not dependent on each other. That is, if the first step is selected and a second step is not dependent on the first step, the second step will not be displayed by the graphical user interface. In this way, the human user is not able to make a selection within the second step when the first step is not selected because that would create an inconsistent selection. This type of inconsistent selection can occur with the previously utilized unstructured text formats of the workflows, but is prevented by the execution of the digital workflows by the digital workflow applications.

[0046] As described herein, the application program format can be a digital file that can be executed by an application. In this way, the application program format can be in a data format structured in such a way that software applications can read, interpret, and process it. These formats are designed to be understandable by computers and to facilitate the efficienttransfer and manipulation of data within or between software systems. In some specific examples, application program formats are highly structured, with clear delineations and rules for how data is organized. In this way, the application program format can be executed by a digital workflow application and perform functions (e.g., allow selections, add selectable inputs, receive data, collect metadata, etc.) without errors.

[0047] In some embodiments, the application program format of the workflow description includes the same textual information extracted from the unstructured text format. As described herein, the language (e g., English, Japanese, Spanish, etc.) can be important to maintain. In addition, the phrasing can be important to maintain when switching between the unstructured text format and the application program format since differences in the phrasing can negatively affect or change how the workflow is performed. In this way, the specific language and phrasing that is utilized by the unstructured text format is extracted and utilized in the application program format.

[0048] In some embodiments, the method 330 can include identifying a plurality of features to be utilized with each of the plurality of steps. In these embodiments, the plurality of features include data collection upon completion of one or more of the plurality of steps. In these embodiments, the plurality of features include digital signature data collection, timestamp collection, and global positioning system (GPS) data collection upon selection of one or more of the plurality of steps. In some embodiments, the plurality of features can be implemented as selectable inputs or implemented as metadata collection. For example, the digital signature data selection can be implemented as a text box to allow a human user to insert their digital signature. In addition, or alternatively, a GPS data collection and / or a timestamp can be collected as metadata when the human user inserts their digital signature such that the digital signature includes the corresponding GPS data and timestamp as metadata.

[0049] In some embodiments, the method 330 can include updating the application program format based on feedback data associated with digital workflow applications associated with a plurality of different workflow descriptions. In some embodiments, the feedback can be utilized to generate “best practices” for an organization. For example, the feedback can identify particular types of instructions or phrases that are confusing to the human users performing the workflows. In this example, the identified instructions can be removed or altered from each of the plurality of digital workflows. In some embodiments, the plurality of documents can beconverted from a plurality of different unstructured text format documents into corresponding application program formats that can be executed by a digital workflow application for each of the corresponding workflows. In some embodiments, a best practice for an application program format can be determined and the features of the best practice can be utilized when converting the plurality of documents into corresponding digital workflows.

[0050] Figure 4 illustrates an example of a machine readable medium 440 to generate a digital workflow for a digital workflow application. The machine readable medium 440 can be communicatively connected to a processor resource 471 by a communication path 472. In some examples, a communication path 472 can include a wired or wireless connection that can allow communication between devices and / or components within a single device. As used herein, the processor resource 471 can include, but is not limited to: a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a metal- programmable cell array (MPCA), a semiconductor-based microprocessor, or other combination of circuitry and / or logic to orchestrate execution of instructions 473, 474, 475, 476, 477. In a specific example, the processor resource 471 utilizes a non-transitory computer-readable medium storing instructions 473, 474, 475, 476, 477, that, when executed, cause the processor resource 471 to perform corresponding functions.

[0051] The machine readable medium 440 may be electronic, magnetic, optical, or other physical storage device that stores executable instructions. Thus, a non-transitory machine- readable medium (MRM) (e g., machine readable medium 440) may be, for example, a non- transitory MRM comprising Random-Access Memory (RAM), read-only memory (ROM), an Electrically Erasable Programmable ROM (EEPROM), a storage drive, an optical disc, and the like. The machine readable medium 440 may be disposed within a controller and / or computing device. In this example, the executable instructions 473, 475, 476, 477, can be “installed” on the device. Additionally, and / or alternatively, the machine readable medium 440 can be a portable, external, or remote storage medium, for example, which allows a computing system to download the instructions 473, 475, 476, 477, from the portable / external / remote storage medium. In this situation, the executable instructions may be part of an “installation package”.

[0052] The machine readable medium 440 includes instructions 473 to receive a workflow description with a plurality of steps in an unstructured text format. In some embodiments, the workflow description can be a textual workflow document that can provideinstructions, checklists, and / or warnings for a human user performing a particular workflow. As described herein, the workflow description in the unstructured text format can be utilized by an organization to instruct human users on performing the workflow and recording data from the performance of the workflow.

[0053] In some embodiments, the workflow description in the unstructured text format can be completed or filled out by a human user during performance of the plurality of steps of the workflow. For example, the workflow description in the unstructured text format can have a plurality of portions to allow a human user to add text, check boxes, and / or describe a performance of the workflow. In some embodiments, the plurality of portions can be completed by a human user in as a digital document in the unstructured text format and / or the plurality of portions can be completed by a human user as a printed document that can be printed on to a substrate from the unstructured text document. As described herein, there are limitations for organizations that utilize the unstructured text format of the workflow descriptions. For example, metadata that can be collected utilizing a digital workflow application may not be able to be collected utilizing the unstructured text format of the workflow description.

[0054] The machine readable medium 440 includes instructions 474 to convert the unstructured text format to a data interchange format utilizing textual information and metadata from the unstructured text format. In some embodiments, converting the unstructured text format to a data interchange format includes converting a text document or spreadsheet format into a JSON document format. The metadata from the unstructured text format can include location or position information. In this way, the position or location of the text or images extracted from the unstructured text format will be in the same or corresponding position / location within the JSON document format.

[0055] The machine readable medium 440 includes instructions 475 to extract the textual information and metadata associated with the textual information. In these embodiments, the metadata includes position information and format information associated with the extracted textual information. As described herein, the position information can refer to a block position, a column position, a row position, and / or a total position of the textual information. In this way, the extracted textual information can be implemented or utilized to generate a workflow description within the data interchange format that matches the workflow description.

[0056] The machine readable medium 440 includes instructions 476 to determine a workflow function associated with the extracted textual information based on the metadata. As described herein, the workflow function can refer to a function of a portion of the textual information and how that function relates to the workflow. For example, a first textual portion of the textual information can have a function to inform a human user and a second textual portion of the textual information can have a function to receive an input from the human user. In this example, the workflow functions for the textual information can be assigned based on the context of the textual information, format of the textual information, and / or position of the textual information.

[0057] As described herein, the workflow function can be utilized to assign a particular selectable input to the corresponding portion of the textual information. The particular selectable input can be assigned to the corresponding portion of the textual information within the application program format. Thus, when the application program format is executed by the digital workflow application, the corresponding selectable input will be utilized with the textual information. A plurality of different selectable inputs can be utilized. In some embodiments, the types of selectable inputs can be based on available selectable inputs utilized by the application program format. For example, a first type of digital workflow application can utilize a first set of selectable input types and a second type of digital workflow application can utilize a second set of selectable input types. In this way, the selectable inputs that are assigned to the portions of the textual information can be based on the type of digital workflow format and / or type of digital workflow application to be utilized.

[0058] In some embodiments, the machine readable medium 440 can include instructions to determine a function of the corresponding selectable inputs based on the determined workflow function of the textual information. In these embodiments, the function of the corresponding selectable inputs is one of a checkbox to confirm completion, an input field to receive text inputs, or a range field to select one of a plurality of values within a range of values. In this way, the determined workflow function can be converted to have the functionality of the selectable inputs when executed by the digital workflow application.

[0059] In some embodiments, the machine readable medium 440 can include instructions to determine a portion of the plurality of steps that are dependent steps. In these embodiments, the machine readable medium 440 can include instructions to identify a first portion of thedependent steps that deactivate other, different steps and a second portion of the dependent steps that activate other, different steps. In some embodiments, a particular step is only relevant when a different step is performed or selected. For example, a first step indicating if a filter was changed may need to be selected to utilize a second step of indicating the serial number or model number of the filter. In this way, the second step can depend on the first step. In some embodiments, the dependency of the plurality of steps can be utilized to activate or deactivate dependent steps based on a selection of a selectable input. For example, the second step above can be activated when the first step is selected or indicated to have been performed and the second step can be deactivated when the first step is not selected or indicated to have not been performed.

[0060] In some embodiments, activating and / or deactivating steps based on dependency can prevent human error when completing a workflow. For example, the human user may be able to fill out portions of the unstructured text format of the workflow that are not applicable to what was performed by the human user. This can cause confusion with the data that is collected and lead to errors that can be detrimental. For example, the human user may be able to insert a serial number or model number of a filter even when the human user does not select that the filter has been changed. This can cause confusion as to whether the filter was actually changed. This can lead to the filter not being changed and the machinery continuing to run with an old filter, or this can lead to the filter being changed again, which can increase maintenance costs.

[0061] The machine readable medium 440 includes instructions 477 to generate an application program format of the workflow description utilizing the textual information and corresponding workflow function that is executable by a digital workflow application to display the plurality of steps with corresponding selectable inputs. As described herein, the unstructured text format can be a word processing document, the data interchange format can be a JSON document, and the application program format can be a C-family program language document. The C-family program languages can include, but are not limited to: C, C++, Objective C, C#, and / or Java. In other embodiments, the application program format can be an interpretive program language format such as, but not limited to Python.

[0062] Figure 5 illustrates an example of a device 550 to generate a digital workflow for a digital workflow application. In some examples, the device 550 is a computing device that includes a processor resource 571 and a machine readable medium 540 to store instructions 582,583, 584, 585, 586, 587 that are executed by the processor resource 571 to perform particular functions. Figure 5 illustrates how a computing device can execute instructions to perform functions described herein.

[0063] The device 550 includes instructions 582 stored by the machine readable medium 540 that are executed by the processor resource 571 to receive a workflow description with a plurality of steps to be performed by a human user during an inspection of devices. In these embodiments, the workflow description is received in an unstructured text format. As described herein, the unstructured text format can be a document generated by a word processing application. The unstructured text format may include the workflow description that can include information utilized by the human user and / or input portions to allow the human user to provide textual or image based feedback about the workflow performed.

[0064] The device 550 includes instructions 583 stored by the machine readable medium 540 that are executed by the processor resource 571 to convert the unstructured text format to a data interchange format utilizing textual information and metadata from the unstructured text format. As described herein, the textual information, format information, and / or position information from the unstructured text format can be extracted and utilized to generate the data interchange format. In this way, the same textual information can be utilized to generate the data interchange format. As described herein, the workflow description within the unstructured text format can be utilized by a plurality of different human users throughout an organization and therefore changes to the textual information may cause confusion to the plurality of different human users utilizing the current unstructured text format of the workflow.

[0065] The device 550 includes instructions 584 stored by the machine readable medium 540 that are executed by the processor resource 571 to extract the textual information and metadata associated with the textual information. In these embodiments, the metadata includes position information and format information associated with the extracted textual information. In some embodiments, the processor resource 571 can be configured to compare the position information for the textual information from the data interchange format to determine a hierarchy associated with the textual information. In some embodiments, the hierarchy can refer to a dependency between the textual information and / or steps of the workflow description.

[0066] In some embodiments, the hierarchy refers to the total position of the textual information and corresponding workflow functions of the textual information. In this way, thehierarchy can be utilized to determine dependencies, which can be utilized to activate or deactivate steps of the workflow description based on received selections through the selectable inputs when the digital workflow application is utilizing the application format.

[0067] The device 550 includes instructions 585 stored by the machine readable medium 540 that are executed by the processor resource 571 to determine a plurality of workflow functions associated with each of the extracted textual information based on the metadata. As described herein, the plurality of workflow functions can refer to the function to be performed by the human user in response to reading the textual information. For example, the workflow function can refer to providing information to the human user or initiating a response from the human user. The workflow function can be utilized to identify one or more selectable inputs to be utilized for the corresponding textual information and / or corresponding metadata to be collected when the human user selects the one or more selectable inputs. In this way, the data of the selectable input and the metadata can be collected when the human user performs the workflow function associated with the textual information.

[0068] The device 550 includes instructions 586 stored by the machine readable medium 540 that are executed by the processor resource 571 to determine a type of selectable input for each of the plurality of workflow functions. In some embodiments, the processor resource 571 can determine the type of selectable input based on a device to be inspected by the human user. For example, the workflow description can describe a particular device or system to be inspected. In some embodiments, information can be extracted from the textual information that can be utilized to identify particular devices or systems to be inspected. In these embodiments, the type of selectable inputs can be based on these devices or systems. For example, the type of data to be collected through selectable inputs can be based on the particular devices or systems. In some embodiments, the metadata to be collected can also be based on the devices or systems described in the workflow description.

[0069] In these embodiments, the processor resource 571 can determine a type of metadata to be collected for each of the plurality of selectable inputs. In these embodiments, the metadata is collected for a particular selectable input upon selection of the particular selectable input utilizing the digital workflow application. As described herein, the metadata collected can be based on the type of selectable inputs identified for the textual information. In some embodiments, the type of metadata that is collected can be based on industry standards that arerequired during an inspection of particular systems or devices. For example, timestamp data or electronic signatures can be required for particular inspections of certain devices or systems. In this way, the application program format can be generated with instructions to collect the identified metadata upon selection of the corresponding selectable inputs.

[0070] In some embodiments, the processor resource 571 can be configured to determine input ranges for the plurality of selectable inputs to be utilized by the application program format. In these embodiments, the input ranges are based on the textual information associated with the plurality of selectable inputs. In some embodiments, the selectable inputs can correspond to inputs that have a particular range of values. For example, a selectable input corresponding to a pH value can include a specific range of values including a range of 1-14 or a more specific range. In this way, the human user may not be able to provide an input outside of the specific range. These types of mistaken inputs can cause problems for the organization trying to analyze the data or maintain compliance with the reported performance of the workflow.

[0071] The device 550 includes instructions 587 stored by the machine readable medium 540 that are executed by the processor resource 571 to generate an application program format of the workflow description utilizing the textual information, corresponding workflow function, and corresponding type of selectable input that is executable by a digital workflow application to display the plurality of steps with the same textual information, corresponding workflow function, and corresponding selectable inputs.

[0072] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even where only a single embodiment is described with respect to a particular feature. Examples of features provided in the disclosure are intended to be illustrative rather than restrictive unless stated otherwise. The above description is intended to cover such alternatives, modifications, and equivalents as would be apparent to a person skilled in the art having the benefit of this disclosure.

[0073] The scope of the present disclosure includes any feature or combination of features disclosed herein (either explicitly or implicitly), or any generalization thereof, whether or not it mitigates any or all of the problems addressed herein. Various advantages of the present disclosure have been described herein, but embodiments may provide some, all, or none of such advantages, or may provide other advantages.

[0074] In the foregoing Detailed Description, some features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the disclosed embodiments of the present disclosure have to use more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment.

Claims

ClaimsWhat is claimed is:

1. A method, comprising: receiving, by a machine, a plurality of documents, each in an unstructured text format that includes a respective workflow description with a respective plurality of steps, wherein the plurality of documents are associated with operation of a plant; converting, by the machine, the plurality of documents in the unstructured text format to a data interchange format; extracting, by the machine, respective textual information and respective position information associated with the textual information from each of the plurality of documents in the data interchange format based on a dictionary for the plant including a plurality of rules for the extraction; determining, by the machine, a respective workflow function associated with the respective extracted textual information based on the respective position information; generating, by the machine, a respective application program format of the respective workflow description utilizing the respective textual information and corresponding respective workflow function; wherein the respective application program format is executable by a digital workflow application to display a series of interactive images corresponding to the respective plurality of steps on a graphical user interface; and wherein at least one of the series of interactive images requires a user to confirm completion of one of the plurality of steps corresponding to the at least one image before a successive image of the series of interactive images is displayed.

2. The method of claim 1, further comprising identifying a plurality of features to be utilized with each of the plurality of steps, wherein the plurality of features include data collection upon completion of one or more of the plurality of steps.

3. The method of claim 1, further comprising developing the dictionary for the plant by a machine learning algorithm operating on the plurality of documents.

4. The method of claim 1, wherein the respective application program format is executable by the digital workflow application to display the series of interactive images corresponding to the respective plurality of steps on the graphical user interface as a plurality of checkboxes associated with the plurality of steps, requiring user input to the plurality of checkboxes to progress through the series of images.

5. The method of claim 1, further comprising determining the workflow function associated with the extracted textual information based on formatting of the textual information.

6. The method of claim 5, wherein the formatting includes one of a table, a checklist, a question, IF-THEN statements, and / or a reference to a different step of the plurality of steps.

7. The method of claim 1, further comprising updating the application program format based on feedback data associated with digital workflow applications associated with a plurality of different workflow descriptions.

8. The method of claim 1, wherein converting, by the machine, the plurality of documents in the unstructured text format to the data interchange format includes utilizing textual information and metadata from the unstructured text format to generate a data interchange format document and determine a workflow function associated with the extracted textual information based on the metadata.

9. The method of claim 8, further comprising generating an application program format of the workflow description utilizing the textual information and corresponding workflow function that is executable by a digital workflow application to display the plurality of steps with corresponding selectable inputs, wherein the function of the corresponding selectable inputs is one of a checkbox to confirm completion, an input field to receive text inputs, or a range field to select one of a plurality of values within a range of values.

10. The method of claim 1, further comprising: receiving a workflow description with the plurality of steps to be performed by a human user during an inspection of devices, wherein the workflow description is received in the unstructured text format; and determining metadata associated with the human user to be collected for each of a plurality of selectable inputs for each of the respective workflow function.

Citation Information

Patent Citations

  • Methods, apparatuses, and systems for human machine interface (HMI) operations

    EP3423904B1

  • Secure automation methods and systems

    EP3819836A1

  • Method and system for feature specification and dependency information extraction from requirement specification documents

    US20230229867A1