International Business Machines Corporation

John Arthur Medicke

Feng-wei Chen Russell

Ashish Sureka

Ameet M Kini

Betsy M Plunket

Samuel R McHan, Jr

Christopher H L Wicher

William Edward Hutson

David Glenn George

Feng-wei Chen

Sudhanshu Shekhar Singh

Ray Zhong Tan

Michael William Smith

Scott N Gerard

Ramasuri Narayanam

Gyana Ranjan Parija

William Donald Reed

Julius Goth, Iii

Shweta Garg

Joydeep Mondal

Stephen Mitchell

Sarthak Ahuja

Stephen H Rutledge

Marcelo Cunha Loureiro

Matthew Morehouse

Amanda Klabzuba

Paul Posharow

Methods, systems, and computer program products for designing conflict minimizing outreach strategies are provided herein. A computer-implemented method includes obtaining data from a job matching service corresponding to jobs listed on the job matching service and candidates; generating job clusters for the jobs based on clustering criteria; identifying, for each respective one of the job clusters, a set of candidates from among the candidates to reduce inter-cluster conflict; selecting, for each of the jobs in a given one of the job clusters, individual candidates from among the set of candidates corresponding to the given job cluster to reduce intra-cluster conflict with respect to the plurality of candidates; and outputting one or more optimized lists of the candidates for the jobs based on the identifying and the selecting.

Designing conflict reducing outreach strategies to mitigate inefficiencies in proactive sourcing process

A computer-implemented method, a computer program product, and a computer system for determining skill adjacencies using a machine learning model. A computer calculates first similarity scores between first skill vectors obtained from one or more training datasets and second similarity scores between the first skill vectors and skill category vectors pre-calculated from job requisitions, using both a reference corpus word embedding model and a target corpus word embedding model. The computer generates features extracted from the first similarity scores and the second similarity scores. Based on the features, the computer trains a machine learning model for classifying combinations of skills as adjacent and non-adjacent. The machine learning model is used to determine skill adjacencies between skills extracted from the job requisitions and skills extracted from resumes.

Determining skill adjacencies using a machine learning model

A method, system and computer program product for assessing similarity between two job description documents. Job description documents consist of sentences framed in a particular manner, where the sentences are represented as a set of actions, an object corresponding to each action and a set of attributes corresponding to the object. The two job description documents are parsed to generate a first and a second set of an action-object-attribute triplet representation, where the first set of the action-object-attribute triplet representation is associated with the first job description document and the second set of the action-object-attribute triplet representation is associated with the second job description document. A similarity score between the first and second sets of action-object-attribute triplet representations is then calculated by hierarchically matching the first and second sets of action-object-attribute triplet representations across the job description documents. In this manner, similar job positions/job descriptions may be more accurately identified.

Creating and using triplet representations to assess similarity between job description documents

A system to identify database triggers in a data processing system. A request is received to create a database monitor for a specific application event and in response to receiving the request to create the database monitor, the database monitor is created. Then, a request is received to monitor the specific application event within a database and in response to receiving the request to monitor the specific application event, a replicate database of the database is created. Subsequently, the database is compared to the replicate database after the specific application event occurs to identify changes in the database associated with the specific application event. A best candidate is identified for a database trigger based upon the identified changes in the database associated with the specific application event.

Identifying database triggers

An automated incremental solution deployment strategy created for an enterprise organization based upon evaluation of a set of possible information technology solution alternatives within an automated architectural framework is received. An information technology solution is incrementally deployed and incrementally selected from the set of possible information technology solution alternatives during the incremental deployment using the automated incremental solution deployment strategy.

Adaptive information technology solution design and deployment

In some embodiments, a method comprises receiving a tag cloud including tags that hyperlink to web content. The method can also comprise separating the tags into different linguistic categories, assigning a weight to each tag, and grouping the tags into clusters, wherein tags in a cluster are associated with a context. The method can also include determining one or more domains for the tag clusters, wherein a domain is a broadest class that defines one or more of the tags in a linguistic category, determining a hierarchy for the tags based on the weights of the tags, and identifying linguistic relationships between the tags. The method can also comprise determining properties associated with one or more of the tags and one or more of the domains, wherein the tag's properties are determined using linguistic analysis and storing the tags, the hierarchies, the linguistic relationships, and the properties.

Deriving ontology based on linguistics and community tag clouds

A method, computer system and/or computer program product pre-highlight text that is located in a search. A text highlight and a triple statement semantic annotation based on the text highlight of a first document are received. The triple statement semantic annotation comprises a subject, a relationship and an object. A natural language processing (NLP) pattern based on the triple statement semantic annotation is generated. The NLP pattern is representative of a linguistic pattern between the text highlight and the triple statement semantic annotation. A multi-dimensional linguistic profile is generated based on the text highlight, the triple statement semantic annotation and the NLP pattern, wherein the multi-dimensional linguistic profile defines entities, relationships and attributes associated with document text. Text in a second document is compared with the multi-dimensional linguistic profile, and text in the second document is highlighted based on the comparison.

Pre-highlighting text in a semantic highlighting system

Information technology solution alternatives for an enterprise organization are evaluated within an automated architectural framework based upon one or more information technology evaluation metrics. An automated incremental solution deployment strategy is created based upon the evaluated plurality of information technology solution alternatives. An information technology solution is selected from the set of information technology solution alternatives for deployment based upon the automated incremental solution deployment strategy.

A set of information technology solution alternatives is generated for an enterprise organization. The information technology solution alternatives are evaluated within an automated architectural framework based upon one or more information technology evaluation metrics. An automated incremental solution deployment strategy is created based upon the evaluated plurality of information technology solution alternatives. An information technology solution is selected from the set of information technology solution alternatives for deployment based upon the automated incremental solution deployment strategy.

A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.

Computerized method, system and program product for generating a data mining model

Computations included in analytics of a multi-dimensional cube are generated by analyzing a spreadsheet corresponding to data downloaded from the multi-dimensional cube so as to automatically convert a formula utilizing the downloaded data contained in the spreadsheet into a language of the multi-dimensional cube so as to provide a converted formula. The converted formula is incorporated into the multi-dimensional cube as a computed member.

Incorporation of spreadsheet formulas of multi-dimensional cube data into a multi-dimensional cube

Under the present invention, a data exploration system, a customized model system and an existing model system are provided. The data exploration system analyzes user data to identify statistical information such as data distribution, data relationships, data outliners and invalid or missing data values. The customized model center iteratively generates customized data mining models in parallel based on permutations of the user data, user-provided business parameters and/or a set of model generation algorithms. The existing model system provides users with a library of existing data mining models, assembled based on the business parameters, from which they can choose one or more. In any event, any customized or existing data mining models selected can be run against the user data in parallel.

Computerized data mining system, method and program product

A method to identify database triggers in a data processing system. A request is received to create a database monitor for a specific application event and in response to receiving the request to create the database monitor, the database monitor is created. Then, a request is received to monitor the specific application event within a database and in response to receiving the request to monitor the specific application event, a replicate database of the database is created. Subsequently, the database is compared to the replicate database after the specific application event occurs to identify changes in the database associated with the specific application event. A best candidate is identified for a database trigger based upon the identified changes in the database associated with the specific application event.

Growing community of inventors

Raleigh, NC, United States of America

John Arthur Medicke