Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Los términos de búsqueda han de ser en inglés.

Software de análisis de datos y textos

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOCZ20150504001
Publicado:
14/07/2015
Caducidad:
13/07/2016
Resumen:
Una universidad checa ha desarrollado un software para analizar grandes cantidades de datos y textos obtenidos de internet o bases de datos corporativas. Gracias al procesamiento de aprendizaje automático, el software no necesita actualizar los glosarios constantemente. El procesamiento de datos es independiente del idioma y permite trabajar con distintas lenguas. Se buscan empresas informáticas que trabajen con análisis de datos, centros de llamadas (centros o proveedores de electricidad y operadores de telefonía), bancos o empresas de relaciones públicas con el fin de establecer acuerdos de licencia o servicio.

Details

Tittle:
Software tool for text data analysis
Summary:
A Czech university has developed software tool for analysing large amounts of text data obtained from the Internet or from corporate databases. The university is looking for large IT companies working with text data, call centres (e.g. centres of suppliers of electricity, telephone operators), banks or PR companies interested in license agreement or services agreement.
Description:
Text mining (also text data mining) is a process of deriving of high quality information text from data. High quality information in text mining refers to certain combination of relevance, novelty and interestingness. Text mining methods and software are widely used in many areas such as marketing, online media, security, etc. for better and effective understanding of information from large amounts of data.

Current text analysis comprises information retrieval, lexical analysis to study word frequency distributions, pattern recognition, tagging or annotation, information extraction and data mining techniques. This analysis requires definitions of various kinds of lexicons (dictionaries of words with task specific labels). Those are language dependent and require regular updates for its proper function. Regular updates can be very difficult when the lexicons become large (e.g. analysis of big data).

The Czech university has developed software tool based on machine learning for processing of natural languages and for text mining for text analysis of large amounts of unstructured or semi-structured data from Internet or corporate databases. Due to machine learning processing, software tool does not require regular updates of the lexicons for its function. Moreover processing data with machine learning methods can be language independent and enables to work with different languages such as English and morphologically complicated languages (so-called inflected languages that change the form or ending of some words when the way in which they are used in sentences changes) such as Spanish, Slovak, Hungarian, Czech, Polish, Arabic and Russian. Another key feature of software tool is statistical semantic analysis of content similar texts that are expressed in different words. Therefore software tool achieves very accurate results in tasks where use of keywords (common practice) is not sufficient.

The university is looking for large IT companies working with text data, call centres (e.g. centers of suppliers of electricity, telephone operators), banks or PR companies. The university is offering services of text analysis of large amount of data including information extraction, intelligent search of key information, text analysis, clustering semantically similar documents or document tagging. If the partner sought should be interested in deeper and complex text analysis or would like to implement software tool to own existing programmes, the university is ready to license offered software tool.
Advantages and Innovations:
In comparison with current text mining tools, offered tool is much more precise, language independent and does not require hand-crafted lexicons for its function. It can be easily adapted to different languages. It copes well with inflected languages such as Spanish, Slovak, Hungarian, Czech, Polish, Arabic and Russian. Naturally, English is supported as well.

Another key feature of the software tool is statistical semantic analysis of content similar texts that are expressed in different words.
Stage of Development:
Available for demonstration
IPs:
Secret Know-how,Copyright

Partner sought

Type and Role of Partner Sought:
Type of partner sought: large IT companies working with text data, call centres (e.g. centres of suppliers of electricity, telephone operators), banks or PR companies

Role of partner sought: Providing large amounts of data for text data analysis under services agreement. Implementation of software tool into own existing software for text analysis under license agreement.

Client

Type and Size of Client:
University
Already Engaged in Trans-National Cooperation:
Si
Languages Spoken:
English
French
German

Keywords

Technology Keywords:
01005003 Contenidos digitales, publicidad electrónica
01005005 Filtrado de información, semántica, estadística
01003006 Software