Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Other

Ernst & Young U.s.llp

Hamid Reza Motahari Nezhad

Claudio Bartolini

Dan G Tecuci

Ravi Kiran Reddy Palla

Vincent Poon

Joseph Nipko

Sven Graupner

Nigel Duffy

Parag Mulendra Joshi

Jun Zeng

Sharad Singhal

Ram Swaminathan

Fabio Casati

Sujoy Basu

Yin Wang

Nigel Paul Duffy

Anup Kumar Kalia

Boualem Benatallah

An object-extraction method includes generating multiple partition objects based on an electronic document, and receiving a first user selection of a data element via a user interface of a compute device. In response to the first user selection, and using a machine learning model, a first subset of partition objects from the multiple partition objects is detected and displayed via the user interface. A user interaction, via the user interface, with one of the partition objects is detected, and in response, a weight of the machine learning model is modified, to produce a modified machine learning model. A second user selection of the data element is received via the user interface, and in response and using the modified machine learning model, a second subset of partition objects from the multiple partition objects is detected and displayed via the user interface, the second subset different from the first subset.

Machine learning based extraction of partition objects from electronic documents

In one embodiment, a method of recommending a production plan includes calculating a similarity score between an incoming order and each historical order in a historical order database, providing a list of most similar historical orders and corresponding historical production plans ranked according to highest similarity scores, receiving an election indicating a historical production plan as a selected production plan, and admitting the selected historical production plan to fulfill the incoming order.

Recommending production plans

Suggesting email tags. A non-transitory machine-readable storage device includes executable instructions that, when executed, cause one or more processors to provide a suggestion for at least one suggested tag based on content of an email, receive a selection of a selected tag, store the email in a computer database, thus creating a stored email, and associate the selected tag with the stored email in the computer database.

Email tags

A particular case is matched to further cases, where the matching is based on plural attributes contained in the particular case and in the further cases, wherein one of the plural attributes relates to a flow of activities taken to address the respective case.

Matching of cases based on attributes including an attribute relating to flow of activities

An electronic document is accessed. A structural definition that defines a structural convention according to which information within the electronic document is arranged also is accessed. Based on the accessed structural definition, at least some of the information is extracted from the electronic document. A machine-understandable representation of the extracted information then is generated.

Generating machine-understandable representations of content

An example of identifying tasks and commitments can include receiving a communication message. A task and a parameter can be identified in the communication message. Information related to the task can be extracted from the communication message using natural language processing (NLP) and machine learning (ML). A commitment related to the task can be identified using NLP extracted information. A state of the commitment can be identified using NLP and ML based on the extracted information.

Identifying tasks and commitments using natural language processing and machine learning

Display screen with graphical user interface

A method of generating a set of composite services is provided herein. The method includes receiving standardized service descriptions of a set of component services from service providers. The standardized description of a component service may be translated to an automaton-based description. A specified goal associated with the set of component services may be received. The set of composite services may be generated based on the automaton-based description and the specified goal. Each of the generated composite services may accomplish the specified goal.

Composition of services

Provided are systems, methods and techniques for discovering protocols of a network-provided service by initially collecting interaction data that pertain to messages between a plurality of devices across a network. Metrics that indicate frequencies of occurrence for different message sequences within the interaction data are calculated, and a protocol structure based on the interaction data and the metrics is generated. Finally, the protocol structure, which describes permitted conversations for a particular service implemented across the network, is output.

Growing community of inventors

Los Altos, CA, United States of America

Hamid Reza Motahari Nezhad