US-12619954-B2 - Systems and methods to generate records within a collaboration environment based on a machine learning model trained from a text corpus

Abstract

Systems and methods to generate records within a collaboration environment are described herein. Exemplary implementations may perform one or more of: manage environment state information maintaining a collaboration environment; effectuate presentation of a user interface through which users upload digital assets representing recorded audio and/or video content; obtain input information defining the digital assets input via the user interface; generate transcription information characterizing the recorded audio and/or video content of the digital assets; provide the transcription information as input into a trained machine-learning model; obtain the output from the trained machine-learning model, the output defining one or more new records based on the transcripts; and/or other operations.

Inventors

• Steve B. Morin

Assignees

• Asana, Inc.

Dates

Publication Date

20260505

Application Date

20240725

Claims (20)

1. 1 . A system configured to generate work unit records within a collaboration environment, the system comprising: one or more physical processors configured by machine-readable instructions to: manage, by a server, electronically stored environment state information maintaining a collaboration environment, the collaboration environment being configured to facilitate interaction by users with the collaboration environment, the server communicating with remotely located client computing platforms associated with the users over one or more network connections to provide access to the collaboration environment through instances of a graphical user interface, the environment state information including work unit records, the work unit records including work information characterizing units of work created within the collaboration environment, managed by the users within the collaboration environment, and/or assigned within the collaboration environment to the users who are expected to accomplish one or more actions to complete the units of work; establish the one or more network connections between the server and the remotely located client computing platforms; obtain, by the server, input information defining a digital asset for recorded audio content including a set of utterances; generate, by the server, a transcript of the set of utterances; train, by the server, a machine-learning model based on a text corpus to generate a trained machine-learning model, the text corpus comprising user-generated text that makes up pages of the graphical user interface of the collaboration environment through which the users access the work unit records, the trained machine-learning model being configured to provide output including new work information defining new work unit records; provide, by the server, the transcript as input into the trained machine-learning model; obtain, by the server, first output of the trained machine-learning model, the first output including first new work information of a first new work unit record based on the input of the transcript; generate, by the server, user interface information defining a new page of the graphical user interface of the collaboration environment through which the users access the first new work information of the first new work unit record; effectuate communication of the user interface information from the server to a remotely located client computing platform over the one or more network connections to cause the remotely located client computing platform to present the new page through which the first new work information is accessed; obtain, by the server, further input information conveying user input into the new page that corrects and/or validates the first new work information appearing on the new page; and refine, by the server, the trained machine-learning model based on whether the first new work information has been corrected and/or validated through the user input into the new page.
2. 2 . The system of claim 1 , wherein the digital asset includes a video file comprising the recorded audio content and visual content.
3. 3 . The system of claim 1 , wherein generating the transcript is based on performing speech processing on the recorded audio content and semantic natural language processing to determine meaning of individual utterances, wherein the meaning of the individual utterances is included in the transcript.
4. 4 . The system of claim 1 , wherein the one or more physical processors are further configured by the machine-readable instructions to: compile, by the server, the text corpus and the work information of the work unit records into input/output training pairs to train the machine-learning model.
5. 5 . The system of claim 1 , wherein the one or more physical processors are further configured by the machine-readable instructions to: provide context information as part of the input into the trained machine-learning model, the context information specifying context of the digital asset, the context identifying one or more users linked to the digital asset.
6. 6 . The system of claim 5 , wherein a user linked to the digital asset includes a creator of the digital asset or an uploader of the digital asset.
7. 7 . The system of claim 1 , wherein the first new work information includes a value for a work unit parameter of the first new work unit record.
8. 8 . The system of claim 7 , wherein the work unit parameter is a title parameter, a work assignment parameter, or a due date parameter user.
9. 9 . The system of claim 7 , wherein the value is a text string within the transcript.
10. 10 . The system of claim 9 , wherein the value further includes a meaning of the text string.
11. 11 . A method to generate work unit records within a collaboration environment, the method comprising: managing, by a server, electronically stored environment state information maintaining a collaboration environment, the collaboration environment being configured to facilitate interaction by users with the collaboration environment, the server communicating with remotely located client computing platforms associated with the users over one or more network connections to provide access to the collaboration environment through instances of a graphical user interface, the environment state information including work unit records, the work unit records including work information characterizing units of work created within the collaboration environment, managed by the users within the collaboration environment, and/or assigned within the collaboration environment to the users who are expected to accomplish one or more actions to complete the units of work; establishing the one or more network connections between the server and the remotely located client computing platforms; obtaining, by the server, input information defining a digital asset for recorded audio content including a set of utterances; generating, by the server, a transcript of the set of utterances; training, by the server, a machine-learning model based on a text corpus to generate a trained machine-learning model, the text corpus comprising user-generated text that makes up pages of the graphical user interface of the collaboration environment through which the users access the work unit records, the trained machine-learning model being configured to provide output including new work information defining new work unit records; providing, by the server, the transcript as input into the trained machine-learning model; obtaining, by the server, first output of the trained machine-learning model, the first output including first new work information of a first new work unit record based on the input of the transcript; generating, by the server, user interface information defining a new page of the graphical user interface of the collaboration environment through which the users access the first new work information of the first new work unit record; effectuating communication of the user interface information from the server to a remotely located client computing platform over the one or more network connections to cause the remotely located client computing platform to present the new page through which the first new work information is accessed; obtaining, by the server, further input information conveying user input into the new page that corrects and/or validates the first new work information appearing on the new page; and refining, by the server, the trained machine-learning model based on whether the first new work information has been corrected and/or validated through the user input into the new page.
12. 12 . The method of claim 11 , wherein the digital asset includes a video file comprising the recorded audio content and visual content.
13. 13 . The method of claim 11 , wherein the generating the transcript is based on performing speech processing on the recorded audio content and semantic natural language processing to determine meaning of individual utterances, wherein the meaning of the individual utterances is included in the transcript.
14. 14 . The method of claim 11 , further comprising: compiling, by the server, the text corpus and the work information of the work unit records into input/output training pairs to train the machine-learning model.
15. 15 . The method of claim 11 , further comprising: providing context information as part of the input into the trained machine-learning model, the context information specifying context of the digital asset, the context identifying one or more users linked to the digital asset.
16. 16 . The method of claim 15 , wherein a user linked to the digital asset includes a creator of the digital asset or an uploader of the digital asset.
17. 17 . The method of claim 11 , wherein the first new work information includes a value for a work unit parameter of the first new work unit record.
18. 18 . The method of claim 17 , wherein the work unit parameter is a title parameter, a work assignment parameter, or a due date parameter user.
19. 19 . The method of claim 17 , wherein the value is a text string within the transcript.
20. 20 . The method of claim 19 , wherein the value further includes a meaning of the text string.

Description

FIELD OF THE DISCLOSURE The present disclosure relates to systems and methods to generate records within a collaboration environment, in particular using a machine learning model trained from a text corpus that generates records from asynchronously recorded audio and/or video content. BACKGROUND Web-based collaboration environments, sometimes referred to as work management platforms, may enable users to assign projects, tasks, or other assignments to assignees (e.g., other users) to complete. A collaboration environment may comprise an environment in which individual users and/or a virtual team of users does its work and enables the users to work in a more organized and efficient manner when remotely located from each other. SUMMARY Hosting a web-based collaboration environment poses many challenges. For example, operating the collaboration environment may require precise ways of creation, storage, management, and/or provision of information that makes up the collaboration environment. One way that operators look to improve the operation of the collaboration environment is to improve parts of the collaboration environment involving substantial human-machine interaction. For example, users may traditionally manually generate work unit records for units of work within the collaboration environment. The operators of the collaboration environment were traditionally tasked with finding ways to design and configure user interfaces which would provide user-friendly and intuitive ways to receive this manual input. However, even with improved user interfaces that walk through manual generation of work unit records, the requirement for human-machine interactions is time consuming, may cause decreased workflow efficiency, and/or may be prone to user error. The inventors of the present disclosure have also identified that work unit records are often created by the users from some reference material. For example, after a recorded video or audio meeting or dictation, a user may generate one or more work unit records that reflect the work to be done following the recording. This translation from one format (recorded audio/video) to manually providing precise definitions of information that makes up the collaboration environment further compounds these existing problems. To address these and/or other problems, one or more implementations presented herein propose a technique to automatically generate records from a recording of audio and/or video. The audio and/or video may have been recorded asynchronously with respect to the creation of one or more records. The recorded audio and/or video may be referred to as “asynchronous audio and/or video.” The records may be automatically generated from digital assets the user uploads which represent the asynchronous audio and/or video. By way of non-limiting illustration, a user may upload a digital asset (e.g., video files, audio file, and/or other assets) into a user interface. The system may carry out one or more processing techniques to extract the content from the digital assets, and structure the content into a format that facilitates creation of a record, such as a work unit record. By way of non-limiting illustration, the content may be parsed to identify values of parameters that make up a work unit record. In some implementations, when a work unit record is generated, one or more fields may be automatically filled based on context surrounding the uploaded asset(s). In some implementations, a text corpus may be utilized as training data for a machine-learning model which performs the extraction and/or structuring of the content. In some implementations, the text corpus may comprise text that makes up one or more existing work unit records (and/or other records) present in the collaboration environment. These along with other features and/or functionality presented herein, may be recognized by persons of ordinary skill in the art as providing improvements upon the operation of a collaboration environment including, among others, increased efficiency and accuracy in the creation and management of the information making up records of the collaboration environment. One or more implementations of a system to generate records within a collaboration environment may include one or more hardware processors configured by machine-readable instructions and/or other components. Executing the machine-readable instructions may cause the one or more hardware processors to facilitate generating records within a collaboration environment. The machine-readable instructions may include one or more computer program components. The one or more computer program components may include one or more of an environment state component, a user interface component, a content component, a work creation component, and/or other components. The environment state component may be configured to manage environment state information maintaining a collaboration environment. The collaboration environment may be co