WO2002048650A1

WO2002048650A1 - System and procedure for a voice-controlled telephone service for providing position-related information associated with an object

Info

Publication number: WO2002048650A1
Application number: PCT/SE2001/002621
Authority: WO
Inventors: Patrik Niklasson
Original assignee: Telia Ab (Publ)
Priority date: 2000-12-14
Filing date: 2001-11-27
Publication date: 2002-06-20
Also published as: NO20032493D0; SE0004636L; SE518173C2; NO20032493L; EE200300285A; EP1342052A1; SE0004636D0

Abstract

A system and a procedure for a telephone service to provide a user (1) with route description to, and information about, a geographical object, for instance a company, a type of company, an address or the like. The procedure includes the steps that the user (1) establishes a connection via a communication system (20, 50), preferably a mobile telephone system (20), with a speech service device (40) including a speech service server. The user (1) states/gives a spoken command to the speech service device (40), which command includes an inquiry regarding type of geographical object. The speech service device (40) a that derives, from one to the communication system (20) connected database (70), position related information associated with said object, and presents, by synthesized speech, said position related information to the user (1).

Description

System and procedur for a Voice-Controlled Telephone

Service for providing position-related information associated with an object

FIELD OF THE INVENTION

The present invention relates to a system for voice-/ speech-controlled telephone services, and especially such a system which integrates positioning/position finding information with object information for different geographical objects.

TECHNICAL BACKGROUND

The information society of today tends to become more and more mobile. In addition, the communication terminals, for instance mobile telephones and PDAs are becoming smaller and smaller to make them convenient to carry. Even if the electronical development in no way has stagnated, the storage capacity is still limited in the small portable terminals, and their displays are normally not large enough, or sufficiently advanced, to show advanced pictures in a clear way. One way of overcoming this disadvantage is to transmit/transfer information from an information center by speech, via the loudspeaker of the terminal. Further, more and more services are developed where these services in addition can be controlled by pronounced commands from the user, so called voice-/speech-controlled services. By a voice-controlled service, or voice service, and an insert earphone or the like connected to the mobile telephone, advanced services can be transferred/transmitted to and from the user without any need for him/her to touch the mobile telephone at all. This is of specific advantage when the visual attention is more needed elsewhere, for instance while driving a car. A service which is obviously of advantage just while driving a car, is provision of position information. In EP935123 in the name of Hatano and others, a device to get information in a voice-controlled navigation system which utilizes GPS for position finding is shown. The navigation system, however, does not include a mobile telephone system, but information exchange is made within the vehicle in which the system is arranged. In EP1024476 in the name of Minamino and others, an arrangement similar to the one in the above mentioned document is shown. In this, there is describing text on a voice- control procedure for mobile telephones, however not related to the navigation problem. US5,956,684 in the name of Ishii and others, shows a system similar to that in EP1024476, in which the system also is arranged to manage mispronounced names of places.

In DE19717601 in the name of Ito and others, is further presented a voice recognition system which is arranged to select words from a dictionary, depending on detected pronunciation. The system is at that arranged to repeat selected word in form of a question. The solution is applied to navigation systems.

It, however, would be to advantage with a solution to get aid to find places without for that purpose having the need to procure advanced equipment.

SUMMARY

The present invention relates to a system and a procedure for a telephone service, in order to provide a user with description of route to, and information about, a geographical object, for instance a company, a type of company, an address or the like. The procedure includes the steps that the user establishes connection via a communication system, preferably a mobile telephone system, with a speech-/voice service device including a speech-/ voice service server. The user gives/states a voice/spoken command to the speech service device, which command includes an inquiry regarding a type of geographical object. The speech service device at that derives, from one to the communication system connected object database, position related information belonging to said object, and presents, by synthesized speech, said position related information to the user.

Characteristic of the system according to the present invention is that all data and all intelligence to manage the speech service is arranged centrally in a communication network. By combining position information with object information and map information the possibilities for a reliable speech service is created, which does not require that the user procures expensive and advanced equipment.

BRIEF DESCRIPTION OF THE DRAWINGS

Preferred embodiments of the invention is described below with reference to the enclosed drawings, in which Figure 1 schematically shows the components, and how these relate to each other, for an embodiment of the system according to the present invention.

Figure 2-4 show flow charts for some different embodiments of procedures according to the present invention.

Figure 2:

1. User calls speech service device.

2. Speech service device answers user.

3. Speech service device presents services. 4. User states object type and inquiry.

5. Pronounced/spoken position information or detected coordinate data from position sensor, related to inquiry ?

6. Translate coordinate data to address data. 7. Interpret position information into address data.

8. Select object depending on address data, object type and inquiry.

9. Inform the user about selected objects, and inquire if more information about these is wanted. 10. Detect answer from the user. 11. Transmit further information. Figure 3: l.User calls speech service device. 2. Speech service device answers user. 3. Speech service device presents services. 12. User states object type and inquiry.

13. Pronounced/spoken position information or detected coordinate data from position sensor, related to inquiry ? 14. Translate coordinate data into address data. 15. Request to state/specify position information. 16. Position information is stated/specified. 17. Interpret position information into address data. 18. Select object address depending on address data, object type and inquiry. 19. Calculate distance between user position and object address, and select nearest object. 20. Produce/derive route description to selected object from user address. 21. Inform the user about the route description.

Figure 4 : l.User calls speech service device. 2. Speech service device answers user. 3. Speech service device presents services. 22. User states object and inquiry.

23. Pronounced/spoken position information or detected coordinate data from position sensor, related to inquiry ?

24. Translate coordinate data into address data. 25. Request to state/specify position information.

26. Position information is stated/specified.

27. Interpret position information into address data.

28. Select object address depending on specified object.

29 . Produce /derive route description to selected object address from user address.

21. Inform the user about the route description. DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

The present invention relates, in a voice-controlled telephone service, to integrate positioning/position finding, map information and data bases with object content for different types of objects, such as drugstores, hotels, companies etc.

The positioning can be done by different technologies, for instance can finding of the position of the user' s terminal be done via satellite systems, such as GPS, or the positioning can be done directly by means of near located base stations for mobile telephony by which the terminal is registered. Another possibility is that the user himself/ herself provides the position information. If the person in question is in a first town and wants to know how to reach a second town, it may be necessary to know the name of these towns to make it possible to provide essential information about, for instance, routing. To find out the position in a town or a district, one further can specify street name, alternatively in combination with the name of the town or the district, and the object name or place name of the destination.

The aim of the present invention consequently is, in a voice-controlled telephone service, to integrate three different parameters, position information, map information and object information for different types of objects. This further shall be achieved by a voice-controlled service which requires minimal effort from the user. As has been mentioned above, the positioning can be achieved by means of, for instance, a GPS-receiver arranged in a mobile telephone or a vehicle.

Map information can be obtained as an internet service, at which the map information can be saved in one in the system arranged database which includes addresses, distances, suitable routes etc. The information about different objects can be obtained from various internet and telephone services, at which this information is stored in a separate database included in the system according to the invention. This information can, for instance, include street address, telephone number and opening hours for different object types, for instance drugstores, hotels, companies etc. In its simplest form an object can consist of an address only.

In Figure 1 is schematically shown an embodiment of the present invention. A user 1 can by his/her mobile telephone 10 establish a connection to a mobile telephone system 20, via a base station 21, according to known technology. In order to make it possible for the user 1 to use the services of the mobile telephone system 20 in a convenient way, the mobile telephone further is equipped with so called hands free equipment, including an insert earphone 11. This equipment makes it possible for the user to talk on the telephone without the need to hold or even touch the handset 10. This is of particular advantage when a telephone service shall be utilized at the same time as the user 1 is driving a car 30. In order to further facilitate for a user 1 to utilize telephone services, for instance while driving a car, a network connected voice-/ speech service device 40 is, according to the present invention, connected to the mobile telephone system 20.

The speech-/voice service device preferably includes a server 40 and a database 41, and is arranged, on the one hand, to recognize and act depending on pronounced/spoken commands, and on the other to, by speech, preferably synthesized, transmit/transfer information or options to a user so that he/she need not watch a possible display on the handset. In the database 41, for that reason word data for speech intelligibility are stored, for instance meaning of words, but also data already stored for play back of, for instance, files with recorded words or phrases.

According to the present invention, the speech service device 40 is further connected to a second communication network 50, for instance Internet, to make it possible to transmit/transfer information which is stored in to that connected databases 60, 70, to the user 1 via speech. Different companies can have different speech service devices 40, but in one embodiment services for specific companies can be arranged to utilize the same speech service device 40.

Whenever applicable, the present invention also can be associated with the procuring of position data from a positioning/position finding system. In one embodiment said positioning system is the satellite based Global

Positioning System, GPS, at which a GPS-receiver (not shown) is arranged to, via suitable antenna 12,31 receive signals from one or more GPS-satellites 80, which signals comprise position information. The GPS-receiver can, for instance, be arranged in the mobile telephone 10, or in the vehicle 30. In one embodiment, the mobile telephone system 20,21 constitutes/creates the positioning system. Different technologies have been shown/presented to utilize information about which base station the mobile station is registered in to find the position of the mobile telephone, for instance by examining the so called timing advance in GSM. By GSM the position can be presented with a degree of accuracy of about 10 m, and by means of base stations 100- 300 m, depending on the density of base stations in the area.

The present invention consequently combines position information, map information and object information in a voice-/speech-controlled telephone service. Below, some different embodiments of the invention are described, where it is evident how the user 1 by means of position information benefits from both map information and object information in a speech service. Different scenarios will occur, depending on which aid the user 1 needs, and how much the user knows. All scenarios below are preceded by the steps l)-3), and are suitably followed by the speech service being finished, alternatively that a new question/inquiry, or a new command, is given by the user 1. It should also be noted that the speech service device 40 and other included elements in the system according to Figure 1 include means to perform the indicated steps of procedure .

1) The user 1 calls the speech service device 40, preferably by calling a predetermined telephone number, or enter a predetermined WAP-address. If also the mobile telephone 10 is arranged for voice control, the initial number to the speech service device 40 also can be given by a voice command.

2) The speech service device 40 answers the user's 1 call by a message of welcome. 3) If the speech service device 40 can offer different types of services, these are preferably read aloud as one in advance in the database 41 stored voice message. For all scenarios below is of course presupposed that the speech service device 40 in this step has indicated that the service in question is offered, i.e. that current question can be asked from the user 1.

A. POSITION INFORMATION ABOUT UNKNOWN OBJECT OF KNOWN TYPE This service can, for instance, be useful for objects such as gas stations or banks. Preferably, a company or the like has a telephone number of its own, or equivalent, which its customers can use. In one embodiment, which only shall be regarded as an example, the object type consists of the gas station company Petrol Ltd's gas stations, where each station is an object. Alternatively, the object type can comprise all competing gas stations. In the preferred example, the user 1 has a gas credit card for the gas stations of "Petrol Ltd". The user 1, however, is in unfamiliar surroundings and need to fill up the car 30. The procedure is also exemplified by the flow chart according to Figure 2. The user 1 then establishes a connection to the speech service device 40 of Petrol Ltd according to the steps l)-3), whereupon

4) The user 1 transmits/transfers position information of a type of object to the speech service device 40, and inquires if there is any object of the type in question, associated with said position information. Concretely it may be about that the user 1 knows that he/she is the town of Alpha. Since the town of Alpha is in a virtual place, the name of the town alone can constitute the position information. This town name then can be transmitted/transferred to the speech service device 40 via speech from user. Alternatively, the position information can be transmitted/transferred automatically to the speech service device 40 from a position sensor arranged at the user's 1.

5) The speech service device 40 senses if the inquiry from the user 1 is followed by position information from a position sensor.

6) If the position information is transmitted/ transferred to the speech service device 40 from a position sensor, the speech service device 40 receives position information in form of coordinate data, relating to map information. The speech service device 40 is at that arranged to use said coordinate data as input parameter to a map database 60, and to from the map database 60 derive address data, depending on said coordinate data, which address data relate to address related position information. Said address related position data can, for instance, be the town of Alpha, or a specific street in the town of Alpha, depending on accuracy of the positioning system. 7) If the speech service device 40 receives the position information as address related information, thus, for instance, the town of Alpha, directly as a spoken information from the user, the speech service device 40 is arranged to interpret the pronounced/spoken position information into corresponding address data.

8) The speech service device 40 further uses said address data as an input parameter to an object database 70, on which object database 70 object information which belongs to the specific objects is stored. Schematically can be said that one combines the search criteria "the town of Alpha" and "gas station belonging to Petrol Ltd". The object database 70 at that selects the objects which match the search criteria. 9) The speech service device 40 receives from the object database 70 object information about the selected objects. In one embodiment, the speech service device 40 informs, via speech, the user 1 that x objects have been found which match the search criteria. For instance: "There are three gas stations in the town of Alpha, belonging to Petrol Ltd". The speech service device 40 further inquires the user 1 if the addresses of the found objects shall be read aloud. 10) The speech service device 40 detects if the user

1 answers yes or no to the inquiry if he/she wants to have the addresses read aloud, 11) at which the speech service device 40, in case of reply in the affirmative, derives address information, if that has not been done in step 9) , which relates to the selected objects, and reads said address information aloud.

B. ROUTE INFORMATION TO UNKNOWN OBJECT OF KNOWN TYPE This service can be both an alternative and a complement to the service according to A above. For the sake of simplicity, the service scenario B therefore is described by an example corresponding to that in the scenario A. The procedure is also exemplified by the flow chart according to Figure 3. 12) The user 1 transmits/transfers position information to the speech service device 40 , and inquires about/asks for description of route to that object of the object type in question which is nearest said user's position. A concrete question consequently can be:

"How do I reach the nearest gas station belonging to Petrol Ltd" ?.

13) The speech service device 40 senses if the inquiry from the user 1 is followed by position information from a position sensor, in form of coordinate data.

14) If coordinate data have been received, the speech service device 40 uses said coordinate data as input parameter to the map database 60 to from there receive address data.

15) If the speech service device 40 does not detect that coordinate data have been received, the speech service device 40 gives a spoken order to the user 1 to inform about his/her position, if that has not already been done in connection with step 12.

16) As a consequence of step 15, the user 1 informs about his/her position by pronouncing address related position information, for instance town or a street.

17) The speech service device 40 at that interprets the pronounced position information into corresponding address data.

18) The speech service device 40 uses pronounced, and interpreted, object type, in this case gas station, as an input parameter to the object database 70, and derives from the object database 70 address data for different objects.

19) The speech service device 40 at that applies the from the object database 70 derived address data, relating to the object address, and the for the user current address data, that is the user address, to said map database 60, which map database 60 includes a database manager, to calculate the distances between the address data of the objects and the user's 1 current position, and select nearest object.

20) The map database further derives/produces route description data to selected object and informs the speech service device 40 about said route description data.

21) The speech service device 40 provides, via speech, the user 1 with route description information, based on said route description data. If the user' s position has been stated/indicated as "dalvagen", the route description information can, for instance, be presented as:" Go to "dalvagen", westward at "skogsstigen", northward at "sveagatan", 250 m ahead is the gas station".

C. ROUTE INFORMATION TO KNOWN OBJECT

If the object is specific, i.e. it is not an undefined object belonging to a certain object type, the procedure according to the above described is considerably simplified. Suppose that the user wants a route description to a given position. This scenario then will be according to the following, which is also exemplified by the flow chart according to Figure 4 :

22) The user 1 transmits/transfers position information to the speech service device 40 and inquires about/asks for route description to a specific goal position. A concrete question then consequently can be: "How do I reach the Swedish Patent and Registration Office"? Alternatively, the question might concern a street address, for instance "Valhallavagen 136". 23) The speech service device 40 senses if the inquiry from the user 1 is followed by position information for the user 1 from a position sensor, in form of coordination data.

24) If coordination data have been received, the speech service device 40 uses said coordinate data as input parameter to the map database 60 in order to from there receive address data.

25) If the speech service device 40 does not detect that coordinate data have been received, the speech service device 40 gives a spoken order to the user 1 to inform about his/her position.

26) As a consequence of step 14, the user 1 informs about his/her position by pronouncing address related position information, for instance town or a street.

27) The speech service device 40 at that interprets the pronounced position information into corresponding address data.

28) The speech service device 40 uses pronounced goal position, in this case "the Swedish Patent and

Registration Office", as an input parameter to the object database 70, in which object database 70 the object corresponding to said goal position is selected. The speech service device 4 at that derives, from the object database 70, address data for the selected object which correspond to the stated/indicated goal position.

29) The speech service device 40 at that applies the from the object database 70 derived address data, and the for the user current address data, to said map database 60, which map database 60 includes a database manager, and at that produce/derive route description data to selected object. Said route description data is informed about to the speech service device 40. 30) The speech service device 40 gives/states, via speech, to the user 1, route description information, based on said route description data.

By a system according to the invention, a user can, by means of his/her mobile telephone or his/her fixed telephone, get, for instance, a route description to reach optional place, provided that position information about the place exists in the object database. By the construction of the system, route description information also can be given without aid from a positioning system, for instance GPS. The present information has been described with reference to figures, exemplified in various embodiments. The expert, however, realizes that more variants of the embodiments are conceivable within the scope of the enclosed patent claims. So far the telephone service of course also can be applied to a fixed telephone system, as well as the indicated databases 60, 70 can be arranged in direct connection to the telephone system 20.

Claims

PATENT CLAIMS

1. Procedure for a telephone service, to provide a user (1) with route description to, and information about, a geographical object, including the steps that: the user (1) establishes a connection via a communication system (20,50) with a speech service device (40) ; the user (1) gives/states a spoken command to the speech service device (40), which command includes an inquiry regarding a type of geographical object; the speech service device (40) derives, from one to the communication system (20,50) connected object database (70), position related information related to said object; the speech service device (40) presents, by a spoken command, said position related information to the user (1) •

2. Procedure as claimed in patent claim 1, further including the step that: the user (1) transmits information which relates to his/her position.

3. Procedure as claimed in patent claim 2, where the user (1) transmits said information which relates to his/her (1) position by a spoken command.

4. Procedure as claimed in patent claim 2, where coordinate data received from a positioning system are transmitted by the user (1) to the speech service device (40) , which coordinate data relate to the user's (1) position.

5. Procedure as claimed in any of the patent claims 1-5, further including the steps that: the user in said inquiry states/indicates a given object type in combination with position information to which the object type shall be related; the speech service device (40), with said given object type, said position information as search criteria, searches for posts in said object database which corresponds with the search criteria; the speech service device (40) presents, by a spoken command, data from detected posts which match the search criteria.

6. Procedure as claimed in patent claim 5, where the position information to which the object type shall be related refers to a district/area, and the data from the detected posts relate to positions of objects which belong to said object type, and where said positions are located within said district/area.

7. Procedure as claimed in patent claim 2, further including the steps that: the user in said inquiry asks for route description to an unknown object of given object type, for a given district/area; the speech service device (40) selects an object in said object database (70); the speech service device (40) detects the object address of the object in said object database (70); the speech service device (40) derives, from one to the communication system (20,50) connected map database (60), route description information for the route between said user(l) and said object address; the speech service device (40) presents, by a spoken command, the route description information to said user (1) .

8. Procedure as claimed in patent claim 2, further including the steps that : the user in said inquiry asks for route description to a known object; - the speech service device (40) derives, from one to the communication system (20,50) connected map database (60), route description information for the route between said user (1) and said object address; the speech service device (40) presents, by a spoken command, the route description information to said user (1) .

9. Procedure as claimed in patent claim 8, further including the steps that: - the speech service device (40) detects the object address of the object in said object database (70) .

10. System for a voice-/speech-controlled telephone service, including a communication network with at least one communication terminal, and connected to the communication network (20) a speech service device (40), an object database (70) stored with geographical information about different objects, a map database (60) stored with map data, at which said speech service device (40) includes means to, depending on a spoken inquiry from said terminal, derive object data from said object database (70) and map data from said map database (60), and to, depending on derived data, transmit/transfer spoken information about a given object to said terminal.

11. System for a voice-/speech-controlled telephone service, including means to execute each of the steps according to patent claims 1-9.