Abstract: A document management system performs name matching operations to validate an identity claimed by a recipient of a document. To validate a claimed identity the document management system compares name data obtained from an identity data source with name data corresponding to a recipient entity of a document to determine whether name features of the identity source name data match recipient name data. The name matching operations may include applying a set of name matching rules to the identity source name data and the recipient name data to determine whether features that differ between the identity source name data and the recipient name data are acceptable alternative representations. Responsive to successfully validating the identity, the system may authorize the recipient to perform actions on the document. Identity source name data may be received from a variety of identity data sources, such as an identity document or a trusted service provider.

Abstract: Techniques for obtaining electronic signatures via word processing applications are described. One approach utilizes a code module, also referred to as a “markup module,” that executes within a word processing application and that facilitates the preparation of a document for electronic signature. A user can operate the word processing application together with the markup module in order to add signature tag markers to the document and to provide recipient information about intended signers, such as names and email addresses. Once the document has been prepared, the code module transmits the document (including the added signature tag markers) and the recipient information to a digital transaction service. The digital transaction service then manages the signing of the document, such as by notifying the recipient, receiving the recipient's signature and securely storing the signature in association with the document.

Abstract: A document management system can include an artificial intelligence-based document manager that can perform one or more predictive operations based on characteristics of a user, a document, a user account, or historical document activity. For instance, the document management system can apply a machine-learning model to determine how long an expiring agreement document is likely to take to renegotiate and can prompt a user to begin the renegotiation process in advance. The document management system can detect a change to language in a particular clause type and can prompt a user to update other documents that include the clause type to include the change. The document management system can determine a type of a document being worked on and can identify one or more actions that a corresponding user may want to take using a machine-learning model trained on similar documents and similar users.

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: 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 system configures, executes, and monitors document workflows executing using workflow engines executing on cloud platforms. The system generates a platform independent document workflow specification that describes a document workflow configured for execution on any of a plurality of workflow engines, each workflow engine executing on a cloud platform. The system compiles the platform independent document workflow specification to generate a platform specific document workflow specification configured for execution on a target workflow engine executing on a target cloud platform. A document workflow orchestration runtime executes and monitors the execution of the platform specific document workflow specification.

Abstract: A computing system remotely trains a public ensemble model of an artificial intelligence model management system. The system receives, by the model management system, an encrypted representation of a private data value from a client system. The encrypted representation includes annotation information provided by the client system. The system determines, using the encrypted representation and the annotation information, a data value cluster that corresponds to the private data value. Data value clusters are generated using encrypted representations of a private data values provided by client systems. The system obtains, based on the assigned data value cluster, an encrypted representation of a model. The model is trained remotely by the client system using the private data value. The system adds the encrypted representation of the model to the public ensemble model. The public ensemble model is generated using a plurality of encrypted representations of models remotely trained by the client systems.

Abstract: A centralized document system integrates online document execution and conferencing. Creation of a conference event is detected. The conference event associated with an electronic signature envelope and a plurality of participants. A plurality of actions to be taken with respect to the electronic signature envelope during a conference corresponding to the conference event are determined. For each of one or more actions of the plurality of actions, a corresponding participant is determined based on metadata of the plurality of participants. An agenda comprising a sequence of the plurality of actions is generated. Each action of the sequence has its assigned corresponding participant. Control permissions during the conference corresponding to the conference event are dynamically driver based on the agenda.

Abstract: A system and a method are disclosed where a server determines parameters for establishing a remote online notarization session, the remote online notarization session including participants, the participants including at least a signer and a notary. The server establishes the session according to the parameters, and monitors, during the session, information from the signer client device and the notary client device. The server detects a failure from the information based on at least one of the signer client device and the notary client device having failed to comply with a parameter of the parameters. Responsive to detecting the failure, the server pauses the remote online notarization session and outputting a selectable cure option to at least one of the participants that, when selected initiates a workflow that, when concluded, cures the failure and enables the remote online notarization session to proceed.

Abstract: A centralized document system receives a request to merge a first document package associated with a first party and a second document package associated with a second party. The first document package includes a first set of documents and the second document package includes a second set of documents. In response to the request, the centralized document system identifies a first subset of documents included in both the first and second sets of documents and identifies a second subset of documents with conflicts between the first and second sets of documents. The centralized document system rectifies the second subset of documents to cure the conflicts between the first and second sets of documents. The centralized document system generates a merged document package including the first subset of documents and the rectified second subset of documents for execution by the first and second parties.

Abstract: A central networking system supports efficient identification and analysis of problems that occur at associated nodes on the network. Using network monitoring rules, the central networking system samples data from a subset of nodes in response to an indication that an error or problem has occurred on the network. If the collected sample data is determined to satisfy certain network conditions, the central networking system proceeds to perform network operations on nodes of the entire network, as appropriate. Thus, the system does not need to collect data from every node in a large network to address potential network threats. The central networking system also defines rules for detecting when a node experiencing a problem violates safety conditions such that it is impossible or inadvisable to pull analytical data from the node. The system performs appropriate remedial actions to address the node problems prior to requesting data for analysis.

Abstract: A centralized document system integrates online document execution and conferencing to control access to precipitant information. Precipitant information includes access codes, personal identification numbers, sensitive information, or any other secured information for which execution of an online document is a prerequisite for access to the secured information. The centralized document system detects precipitant information that is presented during a conference and controls access to the detected precipitant information (e.g., by generating permission rules that specify a type of online document to be executed to gain access). The centralized document system may determine whether a user has executed one or more online documents and thus, has authorization to access the detected precipitant information. Responsive to determining that the user has not executed the online documents, the centralized document system can control access to the precipitant information by modifying the conference (e.g.

Abstract: A document management system generates and validates online documents. The document management system enables the customization of an online document through various rendering parameters for customizing the appearance of agreement content rendered to a receiving entity. The document management system may validate the rendering parameters of customized online documents to determine a likelihood that the documents are valid. For example, the system may determine a likelihood that an online document generated with prechecked checkbox is invalid. The document management system may recommend custom templates for online documents or modifications to an online document that may increase a likelihood of achieving an originating entity's objective. For example, the document management system can apply a machine-learned model to recommend a target rendering parameter for inclusion that would increase the likelihood of a receiving entity clicking an “Agree” button.

Abstract: A document management system utilizes document models for querying, validating, and customizing electronic agreement documents. Document models can be a data structure including document attributes that represent an agreement document. Examples of document attributes include customizable data values, conditions related to the operation of the agreement document and satisfiable by certain values of the customized data values, and rendering parameters for the appearance of the electronic agreement document. The document management system enables a user to create custom document models for generating electronic agreement documents that can be queried, validated, and customized through querying, validating, and customizing the corresponding document models.

Abstract: A document management system can include an artificial intelligence-based document manager that can perform one or more predictive operations based on characteristics of a user, a document, a user account, or historical document activity. For instance, the document management system can apply a machine-learning model to determine how long an expiring agreement document is likely to take to renegotiate and can prompt a user to begin the renegotiation process in advance. The document management system can detect a change to language in a particular clause type and can prompt a user to update other documents that include the clause type to include the change. The document management system can determine a type of a document being worked on and can identify one or more actions that a corresponding user may want to take using a machine-learning model trained on similar documents and similar users.

Abstract: A system configures, executes, and monitors document workflows executing using workflow engines executing on cloud platforms. The system generates a platform independent document workflow specification that describes a document workflow configured for execution on any of a plurality of workflow engines, each workflow engine executing on a cloud platform. The system compiles the platform independent document workflow specification to generate a platform specific document workflow specification configured for execution on a target workflow engine executing on a target cloud platform. A document workflow orchestration runtime executes and monitors the execution of the platform specific document workflow specification.

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: Systems and methods are disclosed for receiving readout requests associated with reading the content of an electronic document by a screen reader application of a client device. In response, an electronic document system applies a document component identification model to the electronic document to generate indicia of at least one conventional segment for conventional readout using left-to-right, top-to-bottom readout and indicia of an unconventional segment to be read out in a manner different from the conventional readout. A document tree, representing a readout sequence, is constructed based on the at least one conventional segment and unconventional segments. The electronic document system provides the document tree to a screen reader, which may perform a readout based on the document tree.

Abstract: Techniques for electronic signature process management are described. Some embodiments provide an electronic signature service (“ESS”) configured to associate third-party content with electronic signature documents by way of dynamic form fields. A dynamic form field is associated with a data store and an electronic signature document. The ESS may automatically populate the dynamic form field with data obtained from the associated data store. If a signer changes the data of the dynamic form field, the ESS may write back the changed data to the data store.

Abstract: Systems and methods for distributed electronic signature documents. A method for distributed electronic signature documents includes creating a signing template that contains information about how a signable document is to be signed. A signable document is created to be distributed to a signer for signing. The signable document is electronically transmitted to the signer. A message is sent using an activatable control in the signing document to a web signing server to invoke the signing process. A browser window is opened on a signer's computer in order to execute the signing process.