[ ] SIENA

Stimulation Initiative for European Neural Applications

Esprit Project 9811



Case Studies of Successful Applications



Neural OCR Processing of Employment Demands

Company Background

El Corte Ingles is the major department store in Spain, with an annual income of more than one trillion pesetas and more than 50.000 employees.

Description of the problem

As one of the largest companies in Spain, El Corte Ingles receives a large amount of job demands in its central personnel offices. Its large volume makes necessary an agile processing of the information of any prospective employee. To do so, El Corte Ingles has designed an abbreviate form in which the most relevant information about the qualifications of a person demanding a job can be entered. Once that information has been incorporated to its databases, the recruiting personnel at El Corte Ingles can easily analyse it to demand more detailed information to the smaller number of persons that may fit best the company's need at a given moment. In any case, the initial basic personnel information processing remains the major bottleneck in the whole process.

Neural Network Techniques application

Neural OCR is becoming the mainstream way of optically recognising printed material. In the case of El Corte Ingles, the own company has designed an abbreviate form with the basic information they need to start the evaluation of a prospective employee. Moreover, when a more specific centre demands have to be met, that basic form has to be modified so that it incorporates the new relevant information. The PC-based, off-the-shelf system RAMA (developed by the Instituto de Ingenier=EDa del Conocimiento-IIC) is particularly well suited to El Corte Ingles' demands. Besides its excellent OCR capabilities, RAMA makes possible the definition and redesign of recognition masks especially tailored for specific forms. This, together with the name and surname dictionaries, its capacities to incorporate validation checks and the possibility of incorporating user defined dictionaries, gives to RAMA a very high versatility for a company that has to deal with different forms for different tasks.

Benefits

RAMA ensures a prompt and precise processing of the basic information that El Corte Ingles has deemed interesting for its personnel selection. Besides the modest hardware requirements, RAMA's ability to the design and editing of recognition masks associated to different forms allows El Corte Ingles to target best its employment information.

Generalisation

The OCR application described here is typical of the OCR requirements of personnel selection processing in large companies. They need a moderate cost system with modest hardware requirements (a PC and a lower segment scanner), and the ability to use it for different forms. As El Corte Ingles' case shows, RAMA is an ideal choice for these companies.

Contact person

Jose Luis Piqueras - R+D Projects Chief - Informatica El Corte Engles,= c/ Doctor Zamenhof, 22 - 28027 Madrid Spain.