A method may include applying, to a content associated with a first supplier, a machine learning model to determine one or more objectives of an enterprise affected by an incident associated with the content. A change in a first risk associated with the first supplier may be detected based on the objectives affected by the incident. In response to detecting the change in the first risk of the first supplier, a cost associated with replacing the first supplier with the second supplier may be determined by applying the machine learning model to analyze a first electronic document associated with the first supplier. If the cost of replacing the first supplier with the second supplier and/or a second risk of the second supplier satisfy one or more thresholds, a second electronic document associated with the second supplier may be generated to address the second risk of the second supplier.

A computerized method and system for electronic management of input content provides for summary document generation. The method and system determines section lines for each of multiple content sections. Therein, field lines are determined for each field within the content section, including dividing up the number of section lines amongst the plurality of fields. The method and system updates an electronic user interface indicating fields and number of lines for each of fields. Via the user interface, the method and system includes receiving user input for each of the plurality of fields and tracking the user input for each of the plurality of fields relative to the number of field lines for each of the plurality of fields. Thereby, the method and system manages summary documentation generation by interacting with the user to modify the user input and available field lines, as well as updating corresponding content sections.

A method of operating a machine via a display device user interface includes generating a text tree display control comprising a tree of text blocks on a first portion of a machine display interface, generating a term control comprising individual terms identified in the text tree display control on a second portion of the machine display interface, generating a navigation control comprising a visual representation of each branch of the text tree display control on a third portion of the machine display interface, operating an individual area of the term control comprising an individual term, to highlight and change all instances of the individual term in the text tree display control, and operating the navigation control to reorder branches of the text tree display control.

Examples relate to citation explanations. A process to provide citation explanation is provided herein. The process analyzes a primary document to extract a citation claim. The process generates a set of candidate segments of a cited document that may correspond to the citation claim. The process also analyzes the set of candidate segments.

The present invention discloses a method for identifying PDF document. wherein, it comprises the following steps: S1: analyzing the path objects in the PDF document, and identifying the forms in PDF document; S2: analyzing the text objects outside the form regions in the PDF document, and recognizing the text contents in the PDF document; S3: writing the identified results into a temporary file, or writing them into the PDF document as an attachment. The method for identifying PDF document provided by the present invention could identify the tables, the paragraphs, titles, the tabulations and so on in the PDF document, thereby, the PDF document can be edited with the paragraph as a unit, and be tagged conveniently to confirm the reading order, so as to facilitate the reading of people with visual impairment; in the same time, it also can derive document in other forms according to the identified results, which thereby greatly facilitates users to read and edit the PDF document.

A computer system includes a natural language processing (NLP) unit, a storage unit, a user interface and a search engine. The NLP unit analyzes a content source to identify one or more sections containing searchable content and generate section metadata respective to each identified section included in the content source. The storage unit stores the section metadata and the user interface receives a section-scoped query aimed at searching an identified section corresponding to the at least one first section metadata stored in the storage unit without searching an identified section corresponding to at least one second section metadata stored in the storage unit. Based on the section-scoped query, the search engine analyzes the at least one first section metadata stored in the storage unit without analyzing the at least one second section metadata.

A method is provided for message pre-processing. The method compares a topic of a received message to previous messages to determine if the topic has already been addressed using a processor that assigns answer weights. Each of the answer weights represents a likelihood a previous message addresses the topic. The likelihood is determined by comparing each answer weight to a threshold such that at least a given one of the previous messages having the highest weight above the threshold is considered to have addressed the topic. The method automatically generates a draft response that addresses the topic if the topic has not already been addressed, based on a prior discussion having a highest one of the answer weights from among a set of prior discussions in the previous messages. The method automatically sends the draft response to a sender of the message.

A method is provided for message pre-processing. The method compares a topic of a received message to previous messages to determine if the topic has already been addressed using a processor that assigns answer weights. Each of the answer weights represents a likelihood a previous message addresses the topic. The likelihood is determined by comparing each answer weight to a threshold such that at least a given one of the previous messages having the highest weight above the threshold is considered to have addressed the topic. The method automatically generates a draft response that addresses the topic if the topic has not already been addressed, based on a prior discussion having a highest one of the answer weights from among a set of prior discussions in the previous messages. The method automatically sends the draft response to a sender of the message.

A method and system for classifying document data is described. An exemplary method includes identifying a markup language document having a plurality of portions, determining a set of substantive content metrics and a set of noise metrics for each of the plurality of portions, calculating a noise-to-content ratio for each of the plurality of portions based on a corresponding set of substantive content metrics and a corresponding set of noise metrics, and removing noise from the markup language document using the noise-to-content ratio.

A system and method for characterizing textual data by generating a first data abstraction based on a set of textual data. The first data abstraction can be presented to a user, and the user can provide instructions to make changes to the first data abstraction to generate a second data abstraction. The textual data can be extracted and characterized from the set of textual data using the second data abstraction.