CN109949800B - Voice taxi taking method and system - Google Patents

Voice taxi taking method and system Download PDF

Info

Publication number
CN109949800B
CN109949800B CN201711384195.4A CN201711384195A CN109949800B CN 109949800 B CN109949800 B CN 109949800B CN 201711384195 A CN201711384195 A CN 201711384195A CN 109949800 B CN109949800 B CN 109949800B
Authority
CN
China
Prior art keywords
information
voice
module
taxi
taking
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711384195.4A
Other languages
Chinese (zh)
Other versions
CN109949800A (en
Inventor
于治武
袁晓春
赵成旺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201711384195.4A priority Critical patent/CN109949800B/en
Priority to PCT/CN2018/109010 priority patent/WO2019119927A1/en
Publication of CN109949800A publication Critical patent/CN109949800A/en
Application granted granted Critical
Publication of CN109949800B publication Critical patent/CN109949800B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Abstract

The invention discloses a voice taxi taking method and a voice taxi taking system, wherein the voice taxi taking method comprises the following steps: acquiring voice information of passengers; extracting destination information from the voice information; judging whether the address information corresponding to the destination information is unique or not, and if not, generating prompt information; the prompt message is used for prompting that the voice supplementary information of the passenger is acquired again; acquiring voice supplementary information of a passenger; extracting destination supplementary information from the voice supplementary information; determining unique corresponding address information according to the destination information and the destination supplementary information; and generating a taxi taking order according to the unique corresponding address information. On the basis of analyzing the voice information of the passenger, when the address information extracted from the voice information is not unique, the voice information extraction method guides the passenger to input the supplementary voice information, further confirms the address information, generates an accurate order and improves the experience of the passenger on the requirement of taking a car through voice.

Description

Voice taxi taking method and system
Technical Field
The invention belongs to the field of intelligent terminal application, and particularly relates to a voice taxi taking method and system.
Background
With the development of the internet, the taxi taking trip is just needed by modern people, and the process is simplified more and more. The taxi booking system for unified dispatching of taxi companies is available in the market, and taxi-taking software based on the handheld intelligent terminal is also available. People are used to use a network to use a taxi taking service, only a departure place and a destination place need to be input at a passenger end, a server generates an order and sends a push notice to a driver end meeting conditions, and the driver selects to receive the order according to the operation condition of the driver so as to enable the passenger and the driver to complete taxi taking transaction. However, for the passengers, the starting points and the destinations need to be manually input, and the starting points and the destinations are completed by manual filling, so that the convenience is not high; for the driver, the order needs to be manually confirmed on the vehicle-mounted mobile terminal, which is very inconvenient and dangerous for the driver in driving.
Based on the above problems, in the prior art, some attempts are made to voice taxi taking, but there is no mechanism for the user to confirm, especially under the technical background that the accuracy of ASR (Automatic Speech Recognition) cannot reach 100%, a Recognition error will inevitably cause trouble to passengers and drivers, besides, in the taxi taking request sent by a passenger, if the destination information result is not unique, for example, the passenger says "i want to go to the seabed to take", in the solution of the prior art, only the geographical location information is packed and sent to the driver end, and the accurate information cannot be screened out, so that in the actual use, the experience is difficult to be guaranteed.
Disclosure of Invention
The invention provides a voice taxi taking method and system, aiming at overcoming the defect that in the prior art, when address information is not unique, an accurate taxi taking order is difficult to determine.
The invention solves the problems through the following technical scheme:
a voice taxi taking method comprises the following steps:
acquiring voice information of passengers;
extracting destination information from the voice information;
judging whether the address information corresponding to the destination information is unique or not, and if not, generating prompt information; the prompt message is used for prompting to acquire the voice supplementary information of the passenger again;
acquiring voice supplementary information of the passenger;
extracting destination supplementary information from the voice supplementary information;
determining unique corresponding address information according to the destination information and the destination supplementary information;
and generating a taxi taking order according to the unique corresponding address information.
Preferably, the step of determining whether the address information corresponding to the destination information is unique is performed, and if not, the step of generating the prompt information is performed, and if yes, the step of determining that the address information corresponding to the destination is the unique corresponding address information is performed, and then the step of generating the taxi taking order according to the unique corresponding address information is performed.
Preferably, before the step of extracting the destination information from the voice information, the voice taxi taking method further includes:
and judging whether the voice information is taxi taking information or not, if so, extracting destination information from the voice information.
Preferably, the determining whether the voice message is taxi taking information, and if so, the step of extracting destination information from the voice message includes:
presetting a semantic library, wherein a taxi taking standard text is stored in the semantic library;
converting the voice information into text information;
comparing the text information with the taxi taking standard text, and calculating the matching degree of the text information and the taxi taking standard text;
and judging whether the matching degree is greater than a preset matching threshold value, if so, confirming that the voice information is taxi taking information, and then extracting destination information from the voice information.
Preferably, the step of extracting destination information from the voice information further comprises:
detecting whether the voice information comprises departure place information or not, if so, extracting the departure place information, and if not, taking the current position information of the passenger as the departure place information;
and in the step of generating the order of taking the car according to the unique corresponding address information, the order of taking the car is generated according to the departure place information and the unique corresponding address information.
Preferably, the step of determining whether the address information corresponding to the destination information is unique, and if not, the step of generating the prompt information further includes:
prestoring an address library, wherein the address library stores mapping between place name information and geographical position information;
detecting whether the destination information comprises the place name information, if so, acquiring geographic position information corresponding to the place name information from the address library, taking the geographic position information corresponding to the place name information as the unique corresponding address information, and then executing the step of generating a taxi-taking order according to the unique corresponding address information; if not, judging whether the address information corresponding to the destination information is unique.
Preferably, the voice taxi taking method further comprises the following steps:
generating a confirmation request of the taxi taking order;
acquiring response information sent by the passenger according to the confirmation request;
identifying the response information, and if the response information is a confirmed taxi taking order, sending the taxi taking order to a driver end; and if the response information is that the taxi taking order is canceled, canceling the taxi taking order.
A voice taxi taking system comprises a voice information acquisition module, an information extraction module, a destination information judgment module, a prompt module, an address information generation module and a taxi taking order generation module;
the voice information acquisition module is used for acquiring voice information of passengers;
the information extraction module is used for extracting destination information from the voice information;
the destination information judging module is used for judging whether the address information corresponding to the destination information is unique or not, and if not, the prompting module is called;
the prompt module is used for generating prompt information; the prompt message is used for prompting to acquire the voice supplementary information of the passenger again;
the voice information acquisition module is also used for acquiring voice supplementary information of the passenger;
the information extraction module is also used for extracting destination supplementary information from the voice supplementary information;
the address information generating module is used for determining unique corresponding address information according to the destination information and the destination supplementary information;
and the taxi taking order generating module is used for generating a taxi taking order according to the unique corresponding address information.
Preferably, the destination information determining module is further configured to, when the determination is yes, confirm that the address information corresponding to the destination is the unique corresponding address information, and then call the taxi-taking order generating module.
Preferably, the voice taxi taking system further comprises a taxi taking information judging module;
the taxi taking information judging module is used for judging whether the voice information is taxi taking information or not, and if yes, the information extracting module is called to extract the destination information.
Preferably, the taxi taking information judging module comprises a semantic library, a text information conversion module, a calculation module and a matching degree judging module;
the semantic library stores taxi taking standard texts;
the text information conversion module is used for converting the voice information into text information;
the calculation module is used for comparing the text information with the taxi taking standard text and calculating the matching degree of the text information and the taxi taking standard text;
the matching degree judging module is used for judging whether the matching degree is larger than a preset matching threshold value or not, if yes, the voice message is confirmed to be taxi taking information, and then the information extracting module is called to extract the destination information.
Preferably, the voice taxi taking system further comprises an information detection module and a departure place information confirmation module;
the information detection module is used for detecting whether the voice information comprises departure place information, if so, the information extraction module is called to extract the departure place information, and if not, the departure place information confirmation module is called;
the departure place information confirmation module is used for taking the current position information of the passenger as the departure place information;
the taxi taking order generating module is further used for generating the taxi taking order according to the departure place information and the unique corresponding address information.
Preferably, the destination information judging module comprises an address base and a geographic position information obtaining module;
the address bank stores mapping between place name information and geographical position information;
the information detection module is further used for detecting whether the destination information comprises the place name information, if so, the geographic position information acquisition module is called, and if not, the destination information judgment module is called;
the geographic position information acquisition module is used for acquiring geographic position information corresponding to the place name information from the address library, taking the geographic position information corresponding to the place name information as the unique corresponding address information, and calling the taxi taking order generation module.
Preferably, the voice taxi taking system further comprises a confirmation request generating module, a response information acquiring module, a response information identifying module, an information sending module and an order canceling module;
the confirmation request generation module is used for generating a confirmation request of the taxi taking order;
the response information acquisition module is used for acquiring response information sent by the passenger according to the confirmation request;
the response information identification module is used for identifying the response information, if the response information is a confirmed taxi taking order, the information sending module is called, and if the response information is a taxi taking canceling order, the order canceling module is called;
the information sending module is used for sending the taxi taking order to a driver end;
the order canceling module is used for canceling the order of taking the car.
The positive progress effects of the invention are as follows: on the basis of analyzing the voice information of the passenger, address information in the voice information is extracted, if the address information is not unique, the passenger is guided to input supplementary voice information, the address information is further clarified, an accurate order is generated, and the experience of the passenger on the requirement of taking a car through voice is improved.
Drawings
Fig. 1 is a flowchart of a voice taxi taking method according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a voice taxi taking method according to embodiment 2 of the present invention.
Fig. 3 is a flowchart illustrating step 111 of the voice taxi-taking method according to embodiment 2 of the present invention.
Fig. 4 is a flowchart illustrating step 120 of the voice taxi-taking method according to embodiment 3 of the present invention.
Fig. 5 is a partial flowchart of step 130 in the voice taxi-taking method according to embodiment 4 of the present invention.
Fig. 6 is a flowchart of a voice taxi taking method according to embodiment 5 of the present invention.
Fig. 7 is a block diagram of a voice taxi-taking system according to embodiment 6 of the present invention.
Fig. 8 is a block diagram of a voice taxi-taking system according to embodiment 7 of the present invention.
Fig. 9 is a block diagram of a taxi-taking information determining module of the voice taxi-taking system according to embodiment 7 of the present invention.
Fig. 10 is a block diagram of a voice taxi-taking system according to embodiment 8 of the present invention.
Fig. 11 is a block diagram of a destination information determination module of the voice taxi-taking system according to embodiment 9 of the present invention.
Fig. 12 is a block diagram of a voice taxi-taking system according to embodiment 10 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
A voice taxi taking method, specifically as shown in fig. 1, the voice taxi taking method includes:
step 110, obtaining voice information of passengers;
step 120, extracting destination information from the voice information;
step 130, judging whether the address information corresponding to the destination information is unique, if not, executing step 140;
step 140, generating prompt information; the prompt message is used for prompting that the voice supplementary information of the passenger is acquired again;
step 150, acquiring voice supplementary information of the passenger;
step 160, extracting destination supplementary information from the voice supplementary information;
step 170, determining unique corresponding address information according to the destination information and the destination supplementary information;
and 180, generating a taxi taking order according to the unique corresponding address information.
For example, a passenger says that the party calls taxies to remove the seabed for fishing, the extracted destination information is seabed fishing, the address information corresponding to the seabed fishing is multiple, prompt information is generated, the prompt information is inquired at multiple places, you can ask the seabed fishing nearby the place of the party, such as the seabed fishing of the western door, the passenger says that the party needs to remove the seabed fishing nearby four hui bridges, the destination supplementary information is extracted as four hui bridges according to the supplementary voice information of the passenger, the only corresponding address information is determined as seabed fishing hot pot red temple shop according to the destination information and the supplementary destination information, and a taxi taking order is generated according to the only corresponding address information, namely the seabed fishing hot pot red temple shop;
or a prompt message "is you nearest the sea floor and banker hualian shop, and whether the sea floor and banker hualian shop is confirmed as a destination address? The passenger says 'confirmed address', extracts 'Jizhuang Hualian shop' corresponding to destination supplementary information 'confirmed' according to the supplementary voice information of the passenger, determines that the only corresponding address information is 'seabed salvage' Jizhuang Hualian shop 'according to the destination information and the supplementary destination information, and generates a car-taking order according to the only corresponding address information' seabed salvage 'Jizhuang Hualian shop'.
The voice taxi taking method further comprises the following steps:
if yes in step 130, confirming that the address information corresponding to the destination is the only corresponding address information, and then executing step 180;
for example, when the passenger says that the passenger helps me call a taxi to go to a seabed red temple fishing shop near the four hui bridges, the extracted destination information is the seabed red temple fishing shop, and the address information corresponding to the destination address information is unique, so that the taxi taking order is directly generated.
In the embodiment, address information in the voice information is extracted on the basis of analyzing the voice information of the passenger, if the address information is not unique, the passenger is guided to input the supplementary voice information, the address information is further clarified, an accurate order is generated, and the experience of the passenger on the requirement of taking a car through voice is improved.
Example 2
As shown in fig. 2-3, the voice taxi taking method of the present embodiment is further improved on the basis of embodiment 1, and before step 120, the voice taxi taking method further includes:
and step 111, judging whether the voice information is taxi taking information, if so, executing step 120, and if not, determining that the voice information is not taxi taking information.
Specifically, step 111 includes:
step 111a, presetting a semantic library, wherein a taxi taking standard text is stored in the semantic library;
step 111b, converting the voice information into text information;
111c, comparing the text information with the taxi taking standard text, and calculating the matching degree of the text information and the taxi taking standard text;
and step 111d, judging whether the matching degree is greater than a preset matching threshold value, if so, confirming that the voice information is taxi taking information, then executing step 120, and if not, confirming that the voice information is not taxi taking information.
In this embodiment, the voice taxi taking process all adopts multiple rounds of conversations, each section of conversation is processed in a fuzzy mode, fuzzy quantization can be performed in the fuzzy mode through fuzzy mathematics, and the membership degree is represented by real numbers between 0 and 1. Accordingly, in semantic recognition, the dependent function value of a standard sentence satisfying a predetermined criterion can be set to 1, and then other words and sentences which are similar and can express similar ideas (semantics) can be represented by a continuous number between 0 and 1 to indicate the degree of membership of the standard sentence to the "correct sentence". In this way, after the voice information of the passenger is acquired, the sentence information is compared with the taxi taking standard text prestored in the semantic library, and if the matching degree of the comparison meets the preset requirement (if the matching degree is more than 0.7), the comparison is passed. In this embodiment, the voice information of the passenger is analyzed in advance, and when the voice information of the passenger is determined to be the taxi-taking information, a taxi-taking order is further generated according to the voice information.
Example 3
The voice taxi taking method of the embodiment is further improved on the basis of the embodiment 1, and as shown in fig. 4 in particular, the step 120 further includes:
step 1201, detecting whether the voice information comprises departure place information, if so, executing step 1202, otherwise, executing step 1203;
step 1202, extracting departure place information;
step 1203, taking the current position information of the passenger as departure place information;
in step 180, a taxi taking order is generated according to the departure place information and the unique corresponding address information.
In this embodiment, generating the taxi taking order requires not only destination information but also departure place information, when the voice information sent by the passenger includes the departure place information, the departure place information is extracted from the voice information, and if the address information corresponding to the departure place information is not unique, the unique address information corresponding to the departure place information can be acquired by referring to the manner of acquiring the unique address information; and if the voice information sent by the passenger does not contain the departure place information, taking the current position information of the passenger as the departure place information.
Example 4
The voice taxi taking method of the embodiment is further improved on the basis of the embodiment 1, specifically as shown in fig. 5, the step 130 further includes:
step 1301, pre-storing an address library, wherein the address library stores mapping between place name information and geographical position information;
step 1302, detecting whether the destination information includes place name information, if yes, executing step 1303, and if not, judging whether the address information corresponding to the destination information is unique;
and step 1303, obtaining the geographical position information corresponding to the place name information from the address library, taking the geographical position information corresponding to the place name information as unique corresponding address information, and then executing step 180.
In this embodiment, the passenger may preset common location information, such as "home" and "company" information. When the voice information of the passenger includes the common location information, the geographic position information corresponding to the location name information is directly acquired from the address library, and the geographic position information corresponding to the location name information is used as the uniquely corresponding address information.
Example 5
The voice taxi taking method of the embodiment is further improved on the basis of the embodiment 1, and specifically as shown in fig. 6, the voice taxi taking method further includes:
step 190, generating a confirmation request of the taxi taking order;
1100, acquiring response information sent by a passenger according to the confirmation request;
step 1110, identifying the response information, if the response information is a confirmation order for taking a car, executing step 1110a, and if the response information is a cancellation order for taking a car, executing step 1110 b.
Step 1110a, sending the taxi-taking order to a driver end;
and step 1110b, canceling the order for placing the car.
In this embodiment, after the taxi-taking order is generated, a confirmation request needs to be generated and sent to the passenger for further confirmation, and if the passenger answers: when there is a word of order cancellation intention such as "cancel", it will automatically recognize and answer: "order cancelled" (or similar words) and end this service, and if the passenger answers an order-confirming intention, such as "confirm", it will automatically recognize and answer: "order confirmed" (or similar words) and send the order to the driver's end.
Example 6
A voice taxi taking system, as shown in fig. 7, specifically, the voice taxi taking system includes a voice information obtaining module 1, an information extracting module 2, a destination information judging module 3, a prompting module 4, an address information generating module 5 and a taxi taking order generating module 6;
the voice information acquisition module 1 is used for acquiring voice information of passengers;
the information extraction module 2 is used for extracting destination information from the voice information;
the destination information judging module 3 is configured to judge whether address information corresponding to the destination information is unique, and if not, invoke the prompting module 4;
the prompt module 4 is used for generating prompt information; the prompt message is used for prompting to acquire the voice supplementary information of the passenger again;
the voice information acquisition module 1 is further configured to acquire voice supplementary information of the passenger;
the information extraction module 2 is further configured to extract destination supplementary information from the voice supplementary information;
the address information generating module 5 is configured to determine unique corresponding address information according to the destination information and the destination supplemental information;
and the taxi taking order generating module 6 is used for generating a taxi taking order according to the unique corresponding address information.
The destination information judging module 3 is further configured to, when the determination is yes, confirm that the address information corresponding to the destination is the unique corresponding address information, and then call the taxi taking order generating module 6.
For example, a passenger says that the passenger helps me to call taxis to remove the submarine for fishing, destination information extracted by the information extraction module is submarine fishing, the destination information judgment module judges that address information corresponding to the submarine fishing is multiple, the prompt module generates prompt information that multiple places are inquired, you can ask for the submarine fishing nearby my places, such as the submarine fishing of the western door accessories, the passenger says that the passenger wants to remove the submarine fishing nearby four hui bridges, the information extraction module extracts destination supplementary information as the four hui bridges according to the supplementary voice information of the passenger, the taxi order generation module determines the only corresponding address information as a submarine chafing dish red temple shop according to the destination information and the supplementary destination information, and generates a taxi order according to the only corresponding address information, namely the submarine chafing dish red temple shop;
or the prompt module generates a prompt message "is the nearest one to you the sea floor shoal hualian shop, and whether the sea floor shoal hualian shop is confirmed as the destination address? The passenger says 'confirmed address', the information extraction module extracts 'Jizhuang Hualian shop' corresponding to destination supplementary information 'confirmed' according to the supplementary voice information of the passenger, the taxi taking order generation module determines that the only corresponding address information is 'seabed fishing and Jizhuang Hualian shop' according to the destination information and the supplementary destination information, and generates a taxi taking order according to the only corresponding address information 'seabed fishing and Jizhuang Hualian shop'.
In the embodiment, address information in the voice information is extracted on the basis of analyzing the voice information of the passenger, if the address information is not unique, the passenger is guided to input the supplementary voice information, the address information is further clarified, an accurate order is generated, and the experience of the passenger on the requirement of taking a car through voice is improved.
Example 7
As shown in fig. 8-9, the voice taxi taking system of the present embodiment is a further improvement on the basis of embodiment 6, and further includes a taxi taking information determining module 7;
the taxi taking information judging module 7 is configured to judge whether the voice information is taxi taking information, and if so, invoke the information extracting module 2 to extract the destination information.
Specifically, the taxi taking information judgment module 7 comprises a semantic library 71, a text information conversion module 72, a calculation module 73 and a matching degree judgment module 74;
the semantic library 71 stores taxi taking standard texts;
the text information conversion module 72 is configured to convert the voice information into text information;
the calculation module 73 is configured to compare the text information with the taxi taking standard text, and calculate a matching degree between the text information and the taxi taking standard text;
the matching degree judging module 74 is configured to judge whether the matching degree is greater than a preset matching threshold, and if so, determine that the voice message is taxi taking information, and then call the information extracting module 2 to extract the destination information.
In this embodiment, the voice taxi taking process all adopts multiple rounds of conversations, each section of conversation is processed in a fuzzy mode, fuzzy quantization can be performed in the fuzzy mode through fuzzy mathematics, and the membership degree is represented by real numbers between 0 and 1. Accordingly, in semantic recognition, the dependent function value of a standard sentence satisfying a predetermined criterion can be set to 1, and then other words and sentences which are similar and can express similar ideas (semantics) can be represented by a continuous number between 0 and 1 to indicate the degree of membership of the standard sentence to the "correct sentence". In this way, after the voice information of the passenger is acquired, the sentence information is compared with the taxi taking standard text prestored in the semantic library, and if the matching degree of the comparison meets the preset requirement (if the matching degree is more than 0.7), the comparison is passed. In this embodiment, the voice information of the passenger is analyzed in advance, and when the voice information of the passenger is determined to be the taxi-taking information, a taxi-taking order is further generated according to the voice information.
Example 8
The voice taxi taking system of the embodiment is further improved on the basis of the embodiment 6, and particularly as shown in fig. 10, the voice taxi taking system further comprises an information detection module 8 and a departure place information confirmation module 9;
the information detection module 8 is configured to detect whether the voice information includes departure location information, if so, invoke the information extraction module 2 to extract the departure location information, and if not, invoke the departure location information confirmation module 9;
the departure place information confirming module 9 is configured to use the current position information of the passenger as the departure place information;
the taxi taking order generating module 6 is further configured to generate the taxi taking order according to the departure place information and the unique corresponding address information.
In this embodiment, the taxi taking order is generated to require not only destination information but also departure place information, when the voice information sent by the passenger includes the departure place information, the information extraction module extracts the departure place information from the voice information, and if the address information corresponding to the departure place information is not unique, the unique address information corresponding to the departure place information can be acquired by referring to the manner of acquiring the unique address information; and if the voice information sent by the passenger does not contain the departure place information, taking the current position information of the passenger as the departure place information.
Example 9
The voice taxi taking system of the embodiment is further improved on the basis of the embodiment 8, specifically as shown in fig. 11, the destination information judging module 3 includes an address base 31 and a geographic position information obtaining module 32;
the address library 31 stores mapping between place name information and geographical location information;
the information detection module 11 is further configured to detect whether the destination information includes the place name information, if so, invoke the geographic position information obtaining module 32, and if not, invoke the destination information determining module 3;
the geographic position information obtaining module 32 is configured to obtain geographic position information corresponding to the place name information from the address library 31, use the geographic position information corresponding to the place name information as the unique corresponding address information, and call the taxi-taking order generating module 6.
In this embodiment, the passenger may preset common location information, such as "home" and "company" information. When the voice information of the passenger includes the common location information, the geographic position information corresponding to the location name information is directly acquired from the address library, and the geographic position information corresponding to the location name information is used as the uniquely corresponding address information.
Example 10
The voice taxi taking system of the present embodiment is further improved on the basis of the embodiment 6, and specifically, as shown in fig. 12, the voice taxi taking system further includes a confirmation request generating module 10, a response information acquiring module 11, a response information identifying module 12, an information sending module 13, and an order canceling module 14;
the confirmation request generating module 10 is configured to generate a confirmation request of the taxi taking order;
the response information obtaining module 11 is configured to obtain response information sent by the passenger according to the confirmation request;
the response information identification module 12 is configured to identify the response information, call the information sending module 13 if the response information is a confirmation order for taking a car, and call the order cancellation module 14 if the response information is a cancellation order for taking a car;
the information sending module 13 is used for sending the taxi taking order to a driver end;
the cancel order module 14 is configured to cancel the taxi taking order.
In this embodiment, after the taxi-taking order is generated, a confirmation request needs to be generated and sent to the passenger for further confirmation, and if the passenger answers: when there is a word of order cancellation intention such as "cancel", it will automatically recognize and answer: "order cancelled" (or similar words) and end this service, and if the passenger answers an order-confirming intention, such as "confirm", it will automatically recognize and answer: "order confirmed" (or similar words) and send the order to the driver's end.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.

Claims (14)

1. A voice taxi taking method is characterized by comprising the following steps:
acquiring voice information of passengers;
extracting destination information from the voice information;
judging whether the address information corresponding to the destination information is unique or not, and if not, generating prompt information; the prompt message is used for prompting to acquire the voice supplementary information of the passenger again;
acquiring voice supplementary information of the passenger;
extracting destination supplementary information from the voice supplementary information;
determining unique corresponding address information according to the destination information and the destination supplementary information;
and generating a taxi taking order according to the unique corresponding address information.
2. The voice taxi-taking method according to claim 1, wherein the step of determining whether the address information corresponding to the destination information is unique, and if not, generating the prompt information, and if yes, confirming that the address information corresponding to the destination is the unique address information, and then executing the step of generating the taxi-taking order based on the unique address information.
3. The voice taxi-taking method according to claim 1, wherein, prior to the step of extracting the destination information from the voice information, the voice taxi-taking method further comprises:
and judging whether the voice information is taxi taking information or not, if so, extracting destination information from the voice information.
4. The voice taxi-taking method according to claim 3, wherein the step of judging whether the voice message is taxi-taking information or not, and if so, the step of extracting destination information from the voice message specifically includes:
presetting a semantic library, wherein a taxi taking standard text is stored in the semantic library;
converting the voice information into text information;
comparing the text information with the taxi taking standard text, and calculating the matching degree of the text information and the taxi taking standard text;
and judging whether the matching degree is greater than a preset matching threshold value, if so, confirming that the voice information is taxi taking information, and then extracting destination information from the voice information.
5. The voice taxi-taking method according to claim 1, wherein the step of extracting destination information from the voice information further comprises:
detecting whether the voice information comprises departure place information or not, if so, extracting the departure place information, and if not, taking the current position information of the passenger as the departure place information;
and in the step of generating the order of taking the car according to the unique corresponding address information, the order of taking the car is generated according to the departure place information and the unique corresponding address information.
6. The voice taxi-taking method according to claim 1, wherein the step of judging whether the address information corresponding to the destination information is unique, and if not, generating the prompt message further comprises:
prestoring an address library, wherein the address library stores mapping between place name information and geographical position information;
detecting whether the destination information comprises the place name information, if so, acquiring geographic position information corresponding to the place name information from the address library, taking the geographic position information corresponding to the place name information as the unique corresponding address information, and then executing the step of generating a taxi-taking order according to the unique corresponding address information; if not, judging whether the address information corresponding to the destination information is unique.
7. The voice taxi-taking method of claim 1, further comprising:
generating a confirmation request of the taxi taking order;
acquiring response information sent by the passenger according to the confirmation request;
identifying the response information, and if the response information is a confirmed taxi taking order, sending the taxi taking order to a driver end; and if the response information is that the taxi taking order is canceled, canceling the taxi taking order.
8. A voice taxi taking system is characterized by comprising a voice information acquisition module, an information extraction module, a destination information judgment module, a prompt module, an address information generation module and a taxi taking order generation module;
the voice information acquisition module is used for acquiring voice information of passengers;
the information extraction module is used for extracting destination information from the voice information;
the destination information judging module is used for judging whether the address information corresponding to the destination information is unique or not, and if not, the prompting module is called;
the prompt module is used for generating prompt information; the prompt message is used for prompting to acquire the voice supplementary information of the passenger again;
the voice information acquisition module is also used for acquiring voice supplementary information of the passenger;
the information extraction module is also used for extracting destination supplementary information from the voice supplementary information;
the address information generating module is used for determining unique corresponding address information according to the destination information and the destination supplementary information;
and the taxi taking order generating module is used for generating a taxi taking order according to the unique corresponding address information.
9. The voice taxi-taking system according to claim 8, wherein the destination information judging module is further configured to, when the judgment is yes, confirm that the address information corresponding to the destination is the unique corresponding address information, and then call the taxi-taking order generating module.
10. The voice taxi-taking system according to claim 8, further comprising a taxi-taking information judging module;
the taxi taking information judging module is used for judging whether the voice information is taxi taking information or not, and if yes, the information extracting module is called to extract the destination information.
11. The voice taxi-taking system according to claim 10, wherein the taxi-taking information judgment module comprises a semantic library, a text information conversion module, a calculation module and a matching degree judgment module;
the semantic library stores taxi taking standard texts;
the text information conversion module is used for converting the voice information into text information;
the calculation module is used for comparing the text information with the taxi taking standard text and calculating the matching degree of the text information and the taxi taking standard text;
the matching degree judging module is used for judging whether the matching degree is larger than a preset matching threshold value or not, if yes, the voice message is confirmed to be taxi taking information, and then the information extracting module is called to extract the destination information.
12. The voice taxi-taking system of claim 8, further comprising an information detection module and a departure location information confirmation module;
the information detection module is used for detecting whether the voice information comprises departure place information, if so, the information extraction module is called to extract the departure place information, and if not, the departure place information confirmation module is called;
the departure place information confirmation module is used for taking the current position information of the passenger as the departure place information;
the taxi taking order generating module is further used for generating the taxi taking order according to the departure place information and the unique corresponding address information.
13. The voice taxi-taking system according to claim 12, wherein the destination information judging module includes an address base and a geographical location information obtaining module;
the address bank stores mapping between place name information and geographical position information;
the information detection module is further used for detecting whether the destination information comprises the place name information, if so, the geographic position information acquisition module is called, and if not, the destination information judgment module is called;
the geographic position information acquisition module is used for acquiring geographic position information corresponding to the place name information from the address library, taking the geographic position information corresponding to the place name information as the unique corresponding address information, and calling the taxi taking order generation module.
14. The voice taxi-taking system according to claim 8, further comprising a confirmation request generation module, a response information acquisition module, a response information recognition module, an information transmission module and an order cancellation module;
the confirmation request generation module is used for generating a confirmation request of the taxi taking order;
the response information acquisition module is used for acquiring response information sent by the passenger according to the confirmation request;
the response information identification module is used for identifying the response information, if the response information is a confirmed taxi taking order, the information sending module is called, and if the response information is a taxi taking canceling order, the order canceling module is called;
the information sending module is used for sending the taxi taking order to a driver end;
the order canceling module is used for canceling the order of taking the car.
CN201711384195.4A 2017-12-20 2017-12-20 Voice taxi taking method and system Active CN109949800B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201711384195.4A CN109949800B (en) 2017-12-20 2017-12-20 Voice taxi taking method and system
PCT/CN2018/109010 WO2019119927A1 (en) 2017-12-20 2018-09-30 Speech taxi calling method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711384195.4A CN109949800B (en) 2017-12-20 2017-12-20 Voice taxi taking method and system

Publications (2)

Publication Number Publication Date
CN109949800A CN109949800A (en) 2019-06-28
CN109949800B true CN109949800B (en) 2021-08-10

Family

ID=66994395

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711384195.4A Active CN109949800B (en) 2017-12-20 2017-12-20 Voice taxi taking method and system

Country Status (2)

Country Link
CN (1) CN109949800B (en)
WO (1) WO2019119927A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112163685A (en) * 2020-09-11 2021-01-01 广州宸祺出行科技有限公司 Intelligent trip matching method and system based on voice AI
CN113011198B (en) * 2021-03-05 2022-07-22 北京嘀嘀无限科技发展有限公司 Information interaction method and device and electronic equipment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103680135A (en) * 2013-12-31 2014-03-26 北京东方车云信息技术有限公司 Method, device and system of providing taxi calling service
CN104216972A (en) * 2014-08-28 2014-12-17 小米科技有限责任公司 Method and device for sending taxi business request
KR101617595B1 (en) * 2015-09-10 2016-05-03 주식회사 에세텔 Smart Cab application system operating method
KR102112814B1 (en) * 2015-10-21 2020-05-19 구글 엘엘씨 Parameter collection and automatic dialog generation in dialog systems
CN106951468B (en) * 2017-03-02 2018-12-28 腾讯科技（深圳）有限公司 Talk with generation method and device

Also Published As

Publication number Publication date
CN109949800A (en) 2019-06-28
WO2019119927A1 (en) 2019-06-27

Similar Documents

Publication Publication Date Title
US7933399B2 (en) System and method for utilizing virtual agents in an interactive voice response application
US8364486B2 (en) Speech understanding method and system
US10354478B2 (en) Method, apparatus, and system for automatic refueling of driverless vehicle
US8352273B2 (en) Device, method, and program for performing interaction between user and machine
US7751551B2 (en) System and method for speech-enabled call routing
US8145494B2 (en) Voice response system
US20050276395A1 (en) Systems and methods for gathering information
CN109949800B (en) Voice taxi taking method and system
WO2011059433A1 (en) Methods and systems for routing calls at a call center based on spoken languages
CN110570867A (en) Voice processing method and system for locally added corpus
CN109285541A (en) Speech recognition system and audio recognition method
CN111094924A (en) Data processing apparatus and method for performing voice-based human-machine interaction
CN105338204A (en) Interactive voice response method and device
CN102623006A (en) Mapping obstruent speech energy to lower frequencies
CN111801667A (en) Vehicle operation assisting device
CN111225115B (en) Information providing method and device
US20210241755A1 (en) Information-processing device and information-processing method
CN111089603B (en) Navigation information prompting method based on social application communication content and vehicle
EP3402176A1 (en) Telephone reservation system
KR100912194B1 (en) Method for providing ars service
CN113822029A (en) Customer service assistance method, device and system
KR102259569B1 (en) Call taxi unmanned brokerage service system and method of the same
CN112217934A (en) Voice recognition processing method and system in real-time communication system
CN113011198B (en) Information interaction method and device and electronic equipment
CN111277717A (en) Voice outbound method, device, storage medium and computer equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant