Brief Summary of the Invention:

1. Present state of Geographical Information and Guidance System without the introduction of Speech Recognition

Twenty first century witnessed the development of various geographical navigation and guidance systems. Two dedicated and prevalent technologies which helped to realize these technological advancements are:

a. Global Positioning System (GPS)

b. Geographical Information System (GIS)

Global Positioning System or GPS is a technology that can give accurate position (latitude /longitude) of an object on earth's surface. The position information when blended with a Geographical Information System or GIS provides a physical address and becomes the basis for guidance and navigation. Technologically GPS is a fully operational and sophisticated system which makes use of twenty four satellites (NAVSTAR GPS) that transmit microwave signals. The user is equipped with a GPS receiver, capable of receiving signals from multiple satellites and predicts the latitude and longitude of the current location.

In real time systems, recorded location data (latitude and longitude) can either be stored within the tracking unit, or it may be transmitted to a central location data base, or internet-connected computer, using a cellular (GPRS), radio, or satellite modem embedded in the unit. The next task is to pull physical and sensible location information using a GIS system.

By definitions a Geographic Information System (GIS) is a computer based information system that represents, inter-relates and analyzes various geographic and spatial features. A GIS system comprises of a database with a set of points which refers to various Geographical coordinates. More than cartographic representation, a GIS system statistically analyzes the data for explaining events, predicting outcomes, planning strategies and for various management decision making.

A real time tracking and guidance system is a complex system which uses multiple technology arenas such as Global Positioning System, Geographical Information System and various mobile communication systems and their underlying technologies. The data or information generated out of the above operations is logically used for tracking, measurement navigations and for a bunch of other applications.

In most of the tracking and guidance systems the data or information is represented in a visual format. The user's handset uses electronic maps with coordinates in a map or by some other audio visual indications. Even though the visual representation does a fairly good job, if the system is enabled with speech / voice, it will benefit a greater number of people. This includes blind people as well as the common man who is unable to follow the visual indications during activities like driving, walking etc. The device will also be useful to people who cannot easily understand the visual data in real time such as people who are new in a locality.

2. Present state of awareness in geographical information and guidance systems in which the Invention is sought to be patented

Day by day GPS systems are getting popular across the globe. More and more mobile service providers already launched various GPS enabled services for tracking and guidance like tracking employees, children, friends or pets using the existing mobile network. Also many mobile equipment manufacturers started integrating GPS based devices on mobile phones as a standard feature. Usage of GIS systems started in the 20th century. Today GIS has reached its maturity and has been integrated with various electronic devices.

In many developed countries GPS tracking, supported with GIS, is used in areas such as fleet control, vehicle tracking, animal control, in certain sports (like marathon, gliding), environmental systems, certain surveillance systems and in various guidance systems. Broadly the services can be classified into two broad categories.

1. Tracking services, where the subject is monitored electronically by a third party

2. Guidance services, where the subject uses the data for movement and other control functions.

Following are the prominent patents already issued, for GPS, GIS Automatic Speech Recognition (ASR) and magnetometer navigation systems

3. Description of how LatticeBridge Infotech is trying to apply Speech Recognition technology in Geographical Information and Guidance Systems

LatticeBridge Infotech (LBIT) teams up with International Institute of Information Technology, Bangalore (IIITB) to develop a new contrivance which provides location and position based information and guidance with a voice /speech interface.
Other than relying only on directions indicated in visual displays, the proposed service - "Where Am I Services" makes use of speech components and speech recognition technology to provide appropriate data. The system provides the following information:

a. The current location (location name) of the user in earth's surface in a vocal format.

b. Step by step voice based guidance to reach a target location or establishment from the current location

The system acts like a human guide, who could able to communicate to the user in English and guide the user in a step by step manner.

System Description:

"LBIT Where Am I Services" makes use of five independent components / systems in a predefined way for providing the functionality

a. GPS system
b. GPS based mobile handset (Voice based handset with or without display)
c. Telecommunication system (GSM or CDMA)
d. Speech System
e. GIS system

High Level Architecture:

Fig. 1 LBIT Where Am I Services Architecture

Fig.l explains the high level functional architecture for the "LBIT Where Am I Services".

The working of the system is explained below:

1. The GPS enabled device senses the GPS signals from GPS satellites and calculates the latitude and longitude of the current location continuously.

2. The user can initiate the service by pressing a button in the GPS enabled mobile handset attached to his / her body.

3. The device sends the longitude, latitude, his current direction and user details to a preprogrammed central server using the communication link (GSM or CDMA), either as an SMS or using GPRS.

4. The telecom service provider passes the data to the centralized "LBIT Where Am I Services" data center.

5. In data center, the system parses the coordinates to a real location with the help of Geographic Information System (GIS).

6. System makes an outbound voice call to the user handset using mobile network.

7. System translates the location to voice and plays it to the user.

8. Once the basic information (location services) is delivered, the system prompts for further services (guidance).

9. The user can either hang the call by pressing a button (or some timeouts) or opts for the guidance services.

10. User can request the required information such as directions to reach a particular place or establishment.

11. The system identifies the input using Speech Recognition, identifies the shortest way to reach the destination.

12. System takes care of the latest direction data available and start guiding the user in a step by step manner.

4. How Fidelity of Geographical Information System will be improved after "LBIT Where Am I Services" (which is sought to be hereby patented) is applied to Location and Guidance Systems

Today most of the tracking systems provide their output using a visual device. Even though some of them give output in an audio visual format, the voice part is one sided from device to the user, at the same time the user needs to interact with the system using some buttons. The proposed system enhances the fidelity of the location and guidance system in following ways:

a. Easily understandable information by Voice
b. Interaction by voice
c. Dynamic guidance according to the current direction of the user.

Visual communication tools are very sophisticated systems, but for a blind man or a person who is walking or driving, voice based instructions gives better fidelity. In a conventional system, the data is represented visually in English, where the brain does the following process - view, read, interpret and understand the data. For a common person who is indulged in another activity, visual instructions consume more time and effort to understand, which makes it a questionable aspect of efficiency. In "LBIT Where Am I Services" the guiding information is split up into various steps and represented in an easily understandable audio format in the preferred language. So the effort taken by the user to understand the instructions is much less.

Fig. 2 Interpretation of data using a Guidance System with visual display

Fig. 3 Interpretation of data using "LBIT Where Am I Services"

The second enhancement the "LBIT Where Am I Services" brings up is its support to speech based interactions. Other than the call initiation, the user navigation is hands free since the User communicates to the systems using voice commands. Again this is a boon for blind people as well as people who are involved in activities like driving, walking or in some other work.

But in conventional systems, generally the interaction happens by physically touching some buttons or controls (Hard or Soft). Normally the touch systems (especially soft switches) require the usage of vision for keeping up the accuracy. But in "LBIT Where Am I Services" the user can interact by voice which is much effortless compared to touch based interactions.

Fig. 4 Communication by Touch

Fig. 5 Communication by Voice

Finally, most of the communication and guidance systems are ignorant about the direction in which the user stands / moves while he communicates. This information is more relevant for a blind person. But most of the tracking systems are ignorant about this aspect, as for the user himself / herself it is difficult to give correct and reliable inputs. Any wrong indications in the direction, can lead the user in the wrong direction and sometimes to dangers. (For example: leading a blind man to a pit or railway track)

The handheld device proposed for "LBIT Where Am I Services" will have a Direction Control Unit (DCU) that will continuously sense and monitor the direction of the customer and sends it to the customer via an SMS / GPRS data. The GIS system also makes use of this data while guiding the user.

5. Description of "LBIT Where Am I Services" that achieve the objective of delivering Information through Voice channel.

The heart of the "LBIT Where Am I Services" is a server based data center which takes care of all location and guidance requests. The high level System Architecture for the Data center setup for "LBIT Where Am I Services" is as given in Fig.6.
Fig. 6 LBIT Where am I Services Data Center Architecture

The system comprises of

1. CTI Server enabled with Automatic Speech Recognition connected to a telecom line from a Telecom Service Provider.
2. An SMS server connected to a SMPP port of a Telecom Service Provider
3. A GIS server

Basic Working

This SMS server receives incoming requests forwarded by the Telecom Service Provider, process the inputs from the user device, and pass it to a GIS system. GIS server manages the geo-database which would translate the latitudes and longitudes to real-time locations. Depending on the reply, the ASR server makes an outbound call to the User and informs the user either using a Text to Speech (TTS) Engine or using a set of recorded prompts. During the voice call the system recognizes the voice of the user, recognizes it using automatic speech recognition (ASR), communicates with GIS system and provides the guidance required. Server will log all the requests for report generation and other MIS purposes.

6. Internal details of "LBIT Where Am I Services"

"LBIT Where Am I Services" is developed on five independent components / systems. Based on the management and their internal details, it can be broadly classified into three groups:

a. Third Party Systems
b. Commercial Handsets (with GPS and Direction Control Systems)
c. LatticeBridge Managed Systems
a. Third Party Systems

While implementing "LBIT Where Am I Services", LBIT relies on two third party services - GPS and Telecommunication Network (GSM or CDMA).

• GPS systems are developed and maintained by United States Department of Defense

• The telecommunication services are hired from GSM or CDMA operator in that region.
While using these third party systems, the technology as well as communication standards are as per the international standards. LBIT makes use of these services, subject to the license and legality of the operations.

b. Commercial Handsets

"LBIT Where Am I Services" propose a GPS enabled mobile handset which is the fulcrum of all the operations. It can either be a
• Commercially available GPS enabled mobile phone

• A GPS unit which can be communicated to a Commercial mobile phone using one of the near field technologies (E.g., Bluetooth)

• A dedicated, cost-effective and integrated handheld device as recommended by

"LBIT Where Am I Services"

In all three options, a software application will be loaded to the handset, which controls and coordinates various units and their operations. While providing a cost effective and integrated solution, especially for the blind, the preferred solution is a dedicated cost effective and integrated device.

The high level architecture for the proposed handset for "LBIT Where am I services" is given in Figure 7.

The proposed device will be an integration of five functional units:

a. GPS Unit which can calculate the latitude and longitude by sensing GPS signals
b. GSM unit with a SIM or a CDMA unit which can communicate to one of the service provider
c. Direction calculation unit driven by an electronic magnetometer
d. A software application to control and synchronize various functions
e. A simple and user interface (with or without a visual unit)

Fig. 7 High level architecture for the proposed handset for "LBIT Where am I Services" Functioning

The basic functioning of the handset is as follows (Figure 8):

1. User initiates a request by pressing a button in the handset

2. The GPS Interface calculates the current lattitude and longitude and passes the information to the Software Platform

3. The direction calculator unit calculates the position of the person and pass it to the Software Platform

4. The Software platform formats the data in a predefined format and pass it to the GSM / CDMA interface

5. The GSM / CDMA interface sends the data to the Where Am I Services data center, either as an SMS or using GPRS.

6. System receives a voice call from the datacenter.

Fig. 8 Process Flow in the Handset c. LatticeBridge Managed Systems

In "LBIT Where Am I Services", LBIT manages the data center comprising of a Speech Recognition based System and a Geographical Information System (GIS). The data process flow is as follows:

Fig. 9 Process Flow in user System For LatticeBridge Infotech Private Limited

The data process flow of the system is explained below.

• System receives the request as an SMS or through GPRS

• System parse the requests to GPS data, user data and direction data

• GPS data (Latitude and Longitude) is passed to the GIS System which provides the location details

• System takes care of the direction information along with the location information
• Based on the location details, textual messages are generated.

• System makes an outbound call to the user who requested data

• Once the call is connected, the system plays the message using a Text to Speech Engine

• If the phone is busy, the system will make a maximum of three attempts to reach the customer

• System plays the location information and prompts the user for any guidance information

• The user can interact with the system using voice. He can request for information like services, places, institutions, etc.

• System recognizes the user input using Automatic Speech Recognition (ASR) engine.

• Based on user inputs, the system interacts with GIS system, find the directions and provide the shortest and safest way to reach the destination from the current location.

• Once the user reached the destination, the system informs the user.

• The voice based guidance continues for more locations till the call is halted or a system time out happens.

Claims:

LatticeBridge Infotech Private Limited, the original and sole inventor of the Contrivance, LBIT Where Am I Services, as defined in this detailed specification, hereby claim that to the best of knowledge and belief, there is no other inventor in the world has invented such a Contrivance as above for being able to perform "Location Based Services" on the mobile phone that provide,

a. The current location (location name) of the user in earth's surface in a vocal format.

b. Step by step voice based guidance to reach a target location or establishment from
the current location