What is Natural Language Based Service Portal

Information services accessed via mobile phones provide information directly relevant to subscribers’ daily lives and are an area of dynamic market growth worldwide. Although many information services are currently offered by mobile operators, existing solutions usually require a unique gateway for each service, and it is inconvenient for subscribers to remember a large number of such gateways. Furthermore, the Short Message Service (SMS) is very popular in China, and Chinese subscribers would prefer to access these services in natural language via SMS. This chapter describes a Natural Language based Service Portal (NLSP) for use with a large number of mobile information services. The system can accept a subscriber query in natural language and navigate it to the required service. Because it is difficult for general natural language processing methods to achieve high processing accuracy, the NLSP is based on a Multi-service Ontology (MO) and Multi-service Query Syntax (MQS). The MO and MQS provide semantic and linguistic knowledge, respectively, to facilitate service selection for a subscriber query. The MO and MQS building solutions are also presented in this chapter. A trial involving navigation of 30 different mobile services shows that the NLSP can provide a viable commercial solution for mobile operators.