TWI434024B - The use of voice recognition input and multi-mode output technology to query the geographic information system latitude and longitude coordinates of the system - Google Patents

Description

A system for querying latitude and longitude coordinates of geographic information systems using speech recognition input and multi-mode output technology

The present invention relates to a system and method for querying GIS latitude and longitude coordinates by using voice recognition input and multi-mode output technology, in particular, a method for translating a voice query message input by a remote user through a large vocabulary voice recognition technology. GIS latitude and longitude coordinate information, the query results can be transmitted to the user terminal device by means of multi-mode output technology (such as voice, text message or instant data transmission).

With the increasing popularity of satellite navigation devices, many new factory vehicles have already listed satellite navigation as an optional device, and will become one of the standard equipment for vehicles in the future. When using the navigation system to find destinations that are not significant or remote, it is common practice to first find a landmark (such as a train station) that is more obvious near the destination. After reaching the preset landmark, ask the local person the exact destination. Location, but as a result, satellite navigation has only played some functions.

Furthermore, the user's terminal equipment has become more and more diversified with the advancement of technology. From the traditional local telephone to the current multimedia mobile phone with navigation and PDA functions, the remote message output method has also relied on voice or fax. It evolved into a terminal device that can be transmitted to users through voice, text, pictures and video. Although the above coordinate information query method has been applied to various navigation devices separately, the destination query message (for example, inputting the name of the merchant, institution, scenic spot or home, address or local telephone number information) is transmitted through the remote servo. The name, address, local telephone number and GIS latitude and longitude coordinates of the query destination are translated and converted back to the user end. Although some patents are mentioned, none of them has a complete set of voice recognition input. Multi-mode output technology to query GIS latitude and longitude coordinate information system and method.

It can be seen that there are still many shortcomings in the above-mentioned methods of use, which is not a good design, but needs to be improved.

In view of the shortcomings derived from the above-mentioned conventional methods, the present inventors have improved and innovated, and after years of painstaking research, finally successfully developed and completed the present invention using voice recognition input and multi-mode output technology to query GIS latitude and longitude coordinates. System and method.

[Object of the Invention]

The object of the present invention is to provide a system and method for querying GIS latitude and longitude coordinates by using speech recognition input and multi-mode output technology, and applying the large vocabulary speech recognition technology to identify and process the audio signal input by the remote user, and After confirming, the name, address or local telephone number information identification result of the destination (merchant, institution, scenic spot or home) is converted into the corresponding GIS latitude and longitude coordinate information (for example, the latitude and longitude coordinates of the Taipei 101 building is [East 121 degrees 33 minutes 51.1 Seconds, north latitude 25 degrees 02 minutes 01.6 seconds], can be applied to the Global Positioning System (GPS) coordinate format), and can query results (including the destination name, address) by voice, SMS or instant data transmission The local telephone number and the GIS latitude and longitude coordinate information are transmitted to the user's terminal device, so that the user can input the latitude and longitude coordinates or address, telephone and other related information into the vehicle or the portable navigation device, and quickly and correctly reach the purpose. Ground.

The system and method for querying GIS latitude and longitude coordinates by using voice recognition input and multi-mode output technology to achieve the above object, wherein the system comprises the following four modules: (1) a dialogue module, which is a remote user. The transmitted voice query message is sent to the voice recognition module of the system for processing. The query result can also be transmitted to the user terminal device through the module.

(2) The voice recognition module processes the voice query message received by the dialog module. The module includes a large vocabulary speech recognition unit for recognizing the content of the speech signal input by the user.

(3) The database module includes a database unit for storing the address, name, local telephone number, voice recognition grammar and GIS latitude and longitude coordinate field of the query destination.

(4) The multi-mode output module uses the voice synthesis, the short message or the data transmission mode to perform the dialogue function with the user through the dialogue module of the present invention. The module comprises a speech synthesis unit, a multimedia message system (MMS) unit and an instant data transmission unit: (1) the speech synthesis unit is configured to generate a speech for broadcasting the query result, and can be used according to the present invention. The dialog module is transmitted to the user's mobile phone or the local telephone device; (2) the multimedia newsletter system unit uses the short message type to query the name, address, local telephone number and GIS latitude and longitude coordinate information of the destination through the dialogue mode of the present invention. The group is transmitted to the user's mobile phone; (3) the instant data transfer unit uses IP (Internal Protocol) packet, and transmits the name, address, local telephone number and GIS latitude and longitude coordinate information of the query destination through the dialog module of the present invention to On the user's mobile phone, PDA or personal computer.

The above four modules make it easy for the system to adjust the system size according to the flexibility of the traffic capacity.

Please refer to FIG. 1 , which is a system architecture diagram of a system and method for querying GIS latitude and longitude coordinates by using voice recognition input and multi-mode output technology. The system includes a dialog module 101; a voice recognition module 102, including a large vocabulary voice recognition unit 105; a database module 103, including a database unit 109; and a multi-mode output module 104, including a voice The synthesizing unit 106, a multimedia messaging system unit 107, and an instant data transmitting unit 108; the user 122, the customer service staff 119, and the satellite navigation device 120 utilize a telephone CPE (Customer Premises Equipment) end device, such as a mobile phone (mobile phone) 115. And a local telephone set 116; or a data CPE end device, such as a personal digital assistant 117 and a personal computer 118, via a telecommunications network access interface, including a digital switch device 110, a 3G/GPRS gateway 111, and an action The telephone base station 121; or an internet access interface includes a router 112, a wireless network base station 113, and a firewall 114 connected to the system. The dialog module 101 is a computer device, including a telephone interface card, a network interface card, and a user interface software program; the type of the interface card and the communication protocol used need to match the communication protocol settings of the switch. The phone interface card can recognize the content of the DTMF signal. The dialog module 101 receives and processes the voice query message transmitted by the remote user 122, and transmits the query result to the user terminal device through the telephone interface card or the network interface card.

The voice recognition module 102 processes the voice query message received by the dialog module 101 through the large vocabulary voice recognition unit 105. The processing result is sent to the database module 103 for search and conversion processing, and the name, address, local telephone number and GIS latitude and longitude coordinate information of the query destination can be obtained.

The large vocabulary speech recognition unit 105 is a software program for recognizing the input of the speech signal content by the user 122 and converting it into a text message. The content of the voice signal input by the user 122 may be the destination (business, institution, scenic spot or home) name, address or local telephone number information, and the best one or more results (candidate) generated by the identification result may be transmitted through the dialogue mode. Group 101 is selected by user 122 using a button or voice input to select a correct identification result.

The database module 103 is a storage device, which can be a memory, such as a flash disk, a hard disk, or the like, or a remote server (server). device. The module includes a database unit 109 for storing and processing the address including the destination (business, institution, scenic spot or home), the local telephone number, the voice recognition grammar and the GIS latitude and longitude coordinate field information, and the use thereof is The system voice recognition module 102 processes the formatted text message of the obtained destination name, address or local telephone number into the database system for retrieval and conversion to obtain the name, address, local telephone number and GIS of the query destination. The latitude and longitude coordinate information is sent to the multi-mode output module 104 for transmission to the user terminal device through the dialog module 101 in different media output formats.

The multi-mode output module 104 transmits the name, address, local telephone number, and GIS latitude and longitude coordinates of the query destination to the user terminal device through the dialog module 101 in different media output formats. The media output type is voice, text message or instant data. The user terminal device can be a mobile phone 115, a local telephone 116, a PDA 117 or a personal computer 118.

The voice synthesizing unit 106 is responsible for the voice output portion of the system, and can convert the text message query result obtained by the system database module 103 into a corresponding voice signal and pass through a PSTN (Public Switched Telephone Network) or a PLMN (Public Land Mobile Network). The telecommunication network plays to the user 122 to listen. The speech signal output by this unit can be pre-recorded or generated using text-to-speech technology.

The multimedia newsletter system unit 107 transmits the name, address, local telephone number and GIS latitude and longitude coordinate information of the query destination to the user's mobile phone terminal in the short message mode. The destination name, address, local telephone number, and coordinate information can be presented in plain text or in a folder format so that the user 122 can transfer the coordinate information into the satellite navigation device. The transmission mode of this newsletter is asynchronous, and the query result has to wait for a short time before being transmitted to the user's mobile phone.

The instant data transfer unit 108 instantly transmits the name, address, local telephone number and GIS latitude and longitude coordinate information of the query destination to the user terminal device by using the IP packet. The user terminal device can be a cell phone 115, a PDA 117 or a personal computer 118.

The digital switch 110, the 3G/GPRS gateway 111 and the mobile phone base station 121 are telecommunication devices, and the inquiry message sent by the CPE end device of the telephone is sent to the dialog module of the present invention via the PSTN or PLMN telecommunication network. 101 for processing. The telephone CPE end device includes a mobile phone 115 and a local telephone 116.

The router 112, the wireless network base station 113, and the firewall 114 are Internet devices, and the voice over packet switch sent by the data CPE device is transmitted to the wired or wireless network access technology. The dialog module 101 of the present invention performs processing. The data CPE end device includes a mobile phone 115, a personal digital assistant 117, or a personal computer 118.

The GIS latitude and longitude coordinate query results can be transmitted to the user terminal device through the dialog module 101 and the telecommunication network or the Internet through the voice, short message or instant data media type. The voice signal message may be generated by the voice synthesizing unit 106 and transmitted to the mobile phone 115 or the local telephone 116 CPE device through the telecommunication network; the short message message may be transmitted by the multimedia message system unit 107 to the mobile phone through the dialogue module 101 and the telecommunication network. 115CPE end; real-time data transfer can be transmitted by the real-time data transfer unit 108 using a network protocol (such as HTTP), through the dialog module 101 and the Internet to the mobile phone 115, the personal digital assistant 117, and the personal computer 118 data CPE. On the end device. After receiving the query result, the user 122 can input the result to the satellite navigation device 120.

Please refer to FIG. 2, which is a flowchart of a method for querying a system architecture diagram of a system and method for querying GIS latitude and longitude coordinates by using voice recognition input and multi-mode output technology. After receiving the inquiry request message transmitted by the user 122, the system dialogue module 101 transmits the inquiry request message to the voice recognition module, and the module recognizes the received voice message through the large vocabulary speech recognition unit 105 and performs data retrieval and conversion. The multi-mode output module 104 of the system can be used to output the query results in different media output formats and transmitted to the user CPE device through the dialog module 101 and the telecommunication network or the Internet.

Please refer to FIG. 3, which is a flowchart of the large vocabulary speech recognition unit 105 of the system and method for querying GIS latitude and longitude coordinates by using speech recognition input and multi-mode output technology. The unit can be composed of the dialogue module 101 and the large vocabulary speech recognition unit 105 in the first figure of the present invention. After the user 122 dials into the query servo system, the user voice is recorded by the dialog module 101, and the recorded data is transmitted to the large vocabulary voice recognition unit 105. After the identification result is confirmed by the user 122, the system database module can be utilized. The 103 and the multi-mode output module 104 transmit the query result to the user CPE device through the dialog module 101 and the telecommunication network or the Internet; if the recognition result is incorrect, the user 122 can re-record the recording or through the dialogue. The module 101 directly talks with the agent 119.

[Features and effects]

The system and method for querying GIS latitude and longitude coordinates by using voice recognition input and multi-mode output technology provided by the invention have the following advantages when compared with other conventional technologies: 1. The invention can allow users to query information through voice input. And the query information is transmitted to the remote server by wired or wireless access technology for processing, and the processing result is converted into the name, address, local telephone number and GIS latitude and longitude coordinate information of the query destination, and through voice synthesis, newsletter Or an instant data transfer pattern that passes the processing result back to the user terminal device.

2. The voice input message content of the present invention uses the name, address or local telephone number of the destination to query the GIS latitude and longitude coordinate information, and accelerates the search time of the satellite navigation system destination coordinates.

The detailed description of the present invention is intended to be illustrative of a preferred embodiment of the invention, and is not intended to limit the scope of the invention. Within the scope of the patent of the present invention.

In summary, the present invention is not only innovative in terms of technical thinking, but also has the above-mentioned plurality of functions that are not in the conventional methods of the conventional use, and has fully complied with the statutory invention patent requirements of novelty and progressiveness, and applied for it according to law. The bureau approved the application for the invention patent, in order to invent the invention, to the sense of virtue.

101. . . Dialogue module

102. . . Speech recognition module

103. . . Database module

104. . . Multi-mode output module

105. . . Large vocabulary speech recognition unit

106. . . Speech synthesis unit

107. . . Multimedia newsletter system unit

108. . . Instant data transfer unit

109. . . Database unit

110. . . Digital switch

1113G/GPRS. . . Gateway

112. . . router

113. . . Wireless network base station

114. . . Firewall

115. . . Mobile phone (mobile phone)

116. . . Local telephone

117. . . Personal Digital Assistant (PDA, Personal Digital Assistant)

118. . . personal computer

119. . . Customer service

120. . . Satellite navigation device

121. . . Mobile phone base station

122. . . user

Please refer to the detailed description of the present invention and its accompanying drawings, which can further understand the technical content of the present invention and its effects. The related drawings are: FIG. 1 is a schematic diagram for querying GIS latitude and longitude by using voice recognition input and multi-mode output technology. System architecture diagram of the system and method of coordinates; Figure 2 is a flow chart of the method and method for querying GIS latitude and longitude coordinates using voice recognition input and multi-mode output technology; and Figure 3 is the voice recognition input and multi-mode output A flow chart of a large vocabulary speech recognition unit for a system and method for querying GIS latitude and longitude coordinates.

101. . . Dialogue module

102. . . Speech recognition module

103. . . Database module

104. . . Multi-mode output module

105. . . Large vocabulary speech recognition unit

106. . . Speech synthesis unit

107. . . Multimedia newsletter system unit

108. . . Instant data transfer unit

109. . . Database unit

110. . . Digital switch

111. . . 3G/GPRS gateway

112. . . router

113. . . Wireless network base station

114. . . Firewall

115. . . Mobile phone (mobile phone)

116. . . Local telephone

117. . . Personal Digital Assistant (PDA, Personal Digital Assistant)

118. . . personal computer

119. . . Customer service

120. . . Satellite navigation device

121. . . Mobile phone base station

122. . . user

Claims (23)

A system for querying latitude and longitude coordinates of a geographic information system by using a voice recognition input and a multi-mode output technology, comprising: a, a dialog module, receiving a destination query message transmitted by a remote user, sending the query message Handed over to the speech recognition module for processing, and the query result from the database module is transmitted to the user terminal device through the dialog module and the telecommunication network or the internet; b, a speech recognition module, which processes the dialog mode The destination voice query message received by the group; c. a database module for storing the latitude and longitude coordinate related information of the target object requested by the multi-mode output module; d, a multi-mode output module, The query result of the database module is transmitted to the user terminal device through the dialogue module by using different media types; wherein the voice recognition module includes a large vocabulary speech recognition unit for recognizing the voice signal input by the user. Converting the identification result into a text message, and the large vocabulary speech recognition unit can generate one or more recognition results, and the large vocabulary speech recognition When the identification unit generates multiple identification results, the user selects a correct identification result. The use of speech recognition input and multi-mode output technology to query the latitude and longitude coordinates of the geographic information system as described in claim 1 The system, wherein the dialog module includes more than one computer device depending on the size and capacity of the system. A system for querying a latitude and longitude coordinate of a geographic information system using a voice recognition input and a multi-mode output technology as described in claim 2, wherein the computer device includes a telephone interface card, a network interface card, and a user interface software program. . The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology as described in claim 3, wherein the communication protocol of the telephone interface card needs to match the communication protocol of the switch and the signals can communicate with each other. The firmware program in the phone interface card can recognize the DTMF (Dual-Tone Multi-Frequency) signal content. For example, the system for querying the latitude and longitude coordinates of a geographic information system using voice recognition input and multi-mode output technology as described in claim 2, wherein the dialog module includes multiple computer devices, the regional network between the computer devices (LAN) is connected to each other. The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology as described in claim 1, wherein the user selects a DTMF (Dual-Tone Multi-Frequency) button or a voice input method. A correct identification result is produced. The system for querying latitude and longitude coordinates of a geographic information system by using a voice recognition input and a multi-mode output technology as described in claim 1, wherein the database module includes a database unit for storing and processing the query destination. Address, local phone number, voice recognition grammar and GIS latitude and longitude coordinates. The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology as described in claim 7 of the patent application scope, wherein the storage device of the database module is the flash memory of the local end (Flash) A disk or a Hard Disk or a remote server (Server). The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology, as described in claim 1, wherein the multi-mode output module comprises a voice synthesis unit and a multimedia message system (MMS, The Multimedia Message System unit and an instant data transfer unit. The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology according to claim 9 of the patent application scope, wherein the voice synthesis unit is configured to broadcast the voice of the query result. Querying the geographic information system latitude and longitude seat using speech recognition input and multi-mode output technology as described in claim 10 The subject system, wherein the speech signal output by the speech synthesis unit is pre-recorded or generated using a text-to-speech technique. The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology, as described in claim 9, wherein the multimedia message system unit can transmit the address, name, and local address of the query destination by using a text message type. Phone number and GIS latitude and longitude coordinates information. A system for querying a latitude and longitude coordinate of a geographic information system by using a voice recognition input and a multi-mode output technology according to claim 9 of the patent application scope, wherein the multimedia message system (MMS) transmits a query destination by using a multimedia message type Address, name, local phone number and GIS latitude and longitude coordinates information. The system for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology as described in claim 13 of the patent application scope, wherein the multimedia message type transmits the address, name, and city of the query destination by using the short message folder mode. Phone number and GIS latitude and longitude coordinates information. Querying the latitude and longitude coordinates of the geographic information system using voice recognition input and multi-mode output technology as described in claim 9 The system, wherein the instant data transfer unit transmits the address, name, local telephone number, and GIS latitude and longitude coordinate information of the query destination by using an IP packet. A system for querying latitude and longitude coordinates of a geographic information system using voice recognition input and multi-mode output technology as described in claim 1, wherein the user terminal device is a mobile phone or a local telephone or a personal digital assistant (PDA, Personal Digital) Assistant) or a personal computer. A method for querying latitude and longitude coordinates of a geographic information system by using voice recognition input and multi-mode output technology, comprising the following steps: a, transmitting a user input voice signal to a server end of the system via a dialog module for large-word voice Identification processing; b, the identification result is retrieved through the database to output the name, address, local telephone number and geographic information system latitude and longitude coordinate information of the query destination, wherein the database storage includes the destination (business, institution, scenic spot or home) The address, the local telephone number, the voice recognition grammar and the GIS latitude and longitude coordinate field information; c, the query result is transmitted to the user's terminal device via the dialogue module. The method for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology, as described in claim 17, wherein the voice signal content in the step a is the name, address, and Local phone number and GIS latitude and longitude coordinates information. The method for querying a latitude and longitude coordinate of a geographic information system by using a voice recognition input and a multi-mode output technology, as described in claim 17, wherein the input voice signal in the step a is a voice signal of a mobile phone or a local telephone. The method for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology, as described in claim 17, wherein the remote user input voice signal in the step a is transmitted through the PSTN (Public Switched Telephone Network) ) or the PLMN (Public Land Mobile Network) telecommunications network is transmitted to the server side of the system. The method for querying the latitude and longitude coordinates of the geographic information system by using the voice recognition input and the multi-mode output technology as described in claim 17, wherein the voice recognition result in the step b is using the database unit for data retrieval and output query. The name, address, local phone number and GIS latitude and longitude coordinates of the destination. The method for querying a latitude and longitude coordinate of a geographic information system by using a voice recognition input and a multi-mode output technology, as described in claim 17, wherein the terminal device of the user in the step c is a mobile phone or a local telephone or a personal digital device. Assistant or personal computer. The method for querying latitude and longitude coordinates of a geographic information system by using a voice recognition input and a multi-mode output technology as described in claim 17, wherein the step c uses a PSTN or PLMN telecommunication network to transmit the query result in a synthesized voice pattern. To the user's terminal device.