Abstract: A document management system generates a form interface including fields that correspond to a set of document tags selected by a user. The document tags, each of which corresponds to a document term, is located in a document template. The document management system suggests fields corresponding to document terms not selected by the user, but often included in similar document templates. In response to the user's selection of at least one of the suggested fields, the document management system modifies the form interface to include the selected suggested field. After the fields in the form are completed, thus defining the document terms, the document management system generates a document with each of the terms in place of the document tags.

Abstract: A method, a system, and a computer program product for generation of templates for electronic documents. A first template is generated based on a plurality of electronic documents. The first template defines a first structural arrangement of one or more portions extracted from the electronic documents and includes one or more portions. A machine learning model determines the first structural arrangement. An update to at least one portion is received. A second template is generated based on the first template and the received update. The second template defines a second structural arrangement of the portions as determined based on the first structural arrangement and the received update. An object model representative of at least one of: the first template, the second template, and a difference between the first and second templates is stored.

Abstract: Techniques are described for a system configured to label objects of electronic documents using a plurality of user devices. The system may determine an agreement type object for an electronic document. The system may determine, based on the agreement type object, a set of possible labels for the electronic document. The system may determine, based on the set of possible labels, a preliminary label for the agreement type object. The system may receive, from the plurality of user devices, community data including at least an indication that the preliminary label is approved. The system may generate approval state information for the preliminary label based on the community data. The system may output, based on the approval state information for the preliminary label, the preliminary label, and content of the agreement type object.

Abstract: An online document system can allow users to track various amendments made over time and corresponding to an original document. The online document system accesses the original document comprising a plurality of content sections and a set of amendment documents each comprising one or more amendments to the original document. The online document system applies a machine-learned model to the original document and the set of amendment documents to identify, for each amendment, a content section of the plurality that corresponds to the amendment and a type of amendment corresponding to the amendment. The online document system generates an amended original document comprising the plurality of content sections modified to include each amendment. The online document system displays the amended original document by displaying each of the plurality of content sections and, in conjunction with each content section, any amendments corresponding to the content section are highlighted.

Abstract: A system and method for computable contracts that includes a contract management system accessible by involved parties, managing a formation stage of a contract document by obtaining object components, assembling a contract object graph from the object components, and committing the contract object graph to post formation execution; and in an execution environment during a post-formation stage, executing the contract object graph where instances of execution include receiving a contract state update, and appending at least one update object component to the contract object graph in accordance with the contract state update. Variations of the system and method may apply peer-to-peer negotiation and execution, use a cryptographic directed acyclic contract object graph, and/or interface with distributed ledgers.

Abstract: A system and a method are disclosed for providing recommendations for sets of security operations for improving security of documents created or executed within an online document system. A supplier entity may select sets of security operations to be performed for a request provided to a signing entity. The online document system computes an aggregate measure of security for the selected sets of security operations and compares it to a threshold measure of security. If the aggregate measure is less than the threshold measure, the online document system uses a machine-learned model to identify additional sets of security operations that when added, results in an updated aggregate measure of security greater than the threshold. The additional sets of security operations are presented to the supplier entity for inclusion within a security operation workflow in combination with the selected sets of security operations.

Abstract: An electronic document system can allow users to upload a document package containing multiple individual component documents. Each component document includes a subset of a plurality of pages that are included in the document package. The electronic document system identifies a page of each component document by applying a machine learning model to the document package. The electronic document system partitions the document package into the individual component documents based on the identified pages. For each individual component document, the electronic document system identifies a document topic corresponding to the component document by applying another machine learning model. The electronic document system modifies a user interface to display each component document and corresponding document topic.

Abstract: A method, an apparatus, and a computer-readable storage medium for entity resolution and mapping. A machine learning model is applied to a plurality of documents and, using the machine learning model, data associated with an entity is extracted from the plurality of electronic documents. An entity data graph structure is generated using the data extracted from the plurality of electronic documents and associated with the entity. The entity data graph structure is stored. Another data associated the entity is retrieved from a storage location. The retrieved data is modified using the entity data graph structure to generate a modified retrieved data to make the modified retrieved data consistent with the data extracted from the plurality of electronic documents.

Abstract: A system for deploying a software application includes processing circuitry obtains configuration information for the software application specifying a first widget configured to indicate a first identifier for a first string and a second widget configured to indicate a second identifier for a second string. The processing circuitry configures a client device to obtain the configuration information and localization information associated with the software application. The processing circuitry generates instructions configured to cause the client device to generate a first string value for the first string based on the first identifier and the localization information and generate a second string value for the second string based on the second identifier and the localization information. The processing circuitry outputs the instructions to the client device to render a graphical user interface based, at least in part, on the first string value and the second string value.

Abstract: A method, a system, and a computer program product for tuning a large language model. One or more first electronic documents are sampled to generate one or more sampled electronic documents. One or more portions of one or more second electronic documents are identified and extracted from the second electronic documents. The sampled electronic documents are sent to a generative artificial intelligence (AI) model to generate one or more first labels. One or more portions of the second electronic documents are sent to the generative AI model to generate one or more second labels. A large language model is trained using one or more first labels and one or more second labels to generate a trained large language model.

Abstract: A system for an electronic document that includes one or more electronic components comprising: natural language content; and a programmable component that comprises computer executable instructions that define: one or more state objects that indicate compliance with the natural language content, wherein a state object comprises a state variable; and logic that programmatically change, based on an application programming interface input, one or more state variables indicating a compliance event effect of the programmable component; an indication of one or more application programming inputs configured to cause execution, based on an input message from an external computing resource, of at least one programmable component of the one or more electronic component; and an indication of one or more contract outputs configured to indicate a value of at least one state variable to an external computing resource.

Abstract: A system for generating counterparty profiles for electronic agreements, based on an indication of a change to a pending clause of an electronic agreement, may determine, based on a second entity, a first historical document and a second historical document. The system may correlate the pending clause of the electronic agreement with a first clause of a plurality of first clauses of the first historical document and with a second clause of a plurality of second clauses of the second historical document based on first content of the first clause and second content of the second clause. Based on the correlation, the system may generate difference information between the first content of the first clause and the second content of the second clause. The system may generate a counterparty profile for the second entity based on the difference information.

Abstract: A method, a system, and a computer program product for generating and using an identifier data model. A first identifier in a plurality of identifiers is assigned to a first version in a plurality of versions of an electronic document processed by a computing system in a plurality of computing systems. A second identifier assigned to a second version the electronic document by the second computing system is received. The second computing system generates the second version of the electronic document by processing the electronic document and assigns the second identifier to the second version of the electronic document. A data model mapping the second identifier to the first identifier is generated and stored. Each identifier included in the data model is associated with a version of the electronic document processed by a computing system in the plurality of computing systems.

Abstract: A method, a system, and a computer program product for generating and capturing/certifying an interface embedding an electronic document. An electronic document and one or more presentation parameters associated with presentation of the electronic document on a graphical user interface are received. One or more electronic interfaces embedding the electronic document are generated. The electronic interfaces may capture the electronic document in accordance with one or more presentation parameters. One or more electronic interfaces are presented on the graphical user interface with the electronic document embedded in the electronic interfaces. The captured electronic document is stored in one or more storage locations.

Abstract: A document execution engine receives a training set of data including training documents that each include one or more passages associated with a passage type and a level of risk. The document execution engine trains a machine learned model based on the training set. The trained machine learned model, when applied to subsequently identified passages within documents in the document execution environment, can identify a passage with above threshold levels of risk (e.g., a high-risk passage) based on a passage type of the passage. The trained machine learned model can then provide for display the high-risk passage and a related passage of the same passage type from a second document within the document execution environment to the user via a document passage comparison interface. Differences between the passages can be highlighted, enabling a user to quickly compare and contrast the passages.

Abstract: A system, for example, a document management system stores documents and manages workflows associated with documents. The document management system allows discovery of templates based on explicit searches performed by users or automatic searches performed based on a context. The document management system allows generating new document templates based on selected versions of document component templates. The generated document template may be stored as a new version. The document management system instantiates documents based on templates by predicting values of variables used in the template based on various factors that describe the context in which the template is being used. The values used for instantiating variables may be generated using machine learning models that may be trained using historical data stored in the document management system.

Abstract: Through a workflow interface, a document management system enables a user to establish a document workflow. The document workflow establishes a set of document actions for the document management system to perform automatically in response to a request from the user. The user defines the document workflow by selecting from a set of workflow operations and specifying parameters for the selected workflow operation. The user additionally defines an approval workflow operation and a rejection workflow operation that designate document actions in the event that a document is approved or rejected, respectively. The document management system performs at least a portion of the document workflow in an order determined from the workflow interface.

Abstract: A document management system generates a form interface including fields that correspond to a set of document tags selected by a user. The document tags, each of which corresponds to a document term, is located in a document template. The document management system suggests fields corresponding to document terms not selected by the user, but often included in similar document templates. In response to the user's selection of at least one of the suggested fields, the document management system modifies the form interface to include the selected suggested field. After the fields in the form are completed, thus defining the document terms, the document management system generates a document with each of the terms in place of the document tags.

Abstract: A method, a system, and a computer program product for summarizing an electronic document. A structural representation of the document is generated and/or received. The structural representation specifies one or more elements of the document and one or more relationships between one or more elements of the document. A machine learning model is identified for the document. The model is applied, based on the structural representation, to one or more portions of the document to generate a hierarchical representation for the portions. A request to execute at least one processing task related to the document is received. At least one generated hierarchical representation of at least one portion of the document is sent to a generative artificial intelligence model to execute the processing task by generating a response to the request. The response is and presented on a graphical user interface of a user computing device.

Abstract: A document execution engine receives a training set of data including training documents that each include one or more passages associated with a passage type and a level of risk. The document execution engine trains a machine learned model based on the training set. The trained machine learned model, when applied to subsequently identified passages within documents in the document execution environment, can identify a passage with above threshold levels of risk (e.g., a high-risk passage) based on a passage type of the passage. The trained machine learned model can then provide for display the high-risk passage and a related passage of the same passage type from a second document within the document execution environment to the user via a document passage comparison interface. Differences between the passages can be highlighted, enabling a user to quickly compare and contrast the passages.