CN106157651A - A kind of traffic radio traffic information broadcasting system based on voice semantic understanding - Google Patents
A kind of traffic radio traffic information broadcasting system based on voice semantic understanding Download PDFInfo
- Publication number
- CN106157651A CN106157651A CN201610596596.5A CN201610596596A CN106157651A CN 106157651 A CN106157651 A CN 106157651A CN 201610596596 A CN201610596596 A CN 201610596596A CN 106157651 A CN106157651 A CN 106157651A
- Authority
- CN
- China
- Prior art keywords
- information
- road
- name
- control
- subsystem
- 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.)
- Granted
Links
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 23
- 239000000284 extract Substances 0.000 claims description 13
- 238000001816 cooling Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000002123 temporal effect Effects 0.000 claims description 8
- 230000003203 everyday effect Effects 0.000 claims description 7
- 230000000977 initiatory effect Effects 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 238000010304 firing Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 208000030251 communication disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The present invention discloses a kind of traffic radio traffic information broadcasting system based on voice semantic understanding, including report information flag based on speech recognition and map control subsystem, carries out reporting information flag and map control by the way of sound inputs;Intelligent way asking subsystem, for identifying user's input information and carrying out the information feedback of inquired about road conditions;Visual history data query subsystem, for the road conditions of historical period of inquiry roads and carry out visual presentation;The present invention facilitates traffic radio host and reports information flag and map control, facilitates road condition query and the inquiry of historical data of user.
Description
Technical field
The present invention relates to information processing and natural language processing field, particularly relate to a kind of based on voice semantic understanding
Traffic radio traffic information broadcasting system.
Background technology
Automatization refers to that machinery equipment, system or process (produce, management process) are in nobody or the direct ginseng of less people
Under with, according to the requirement of people, judge through detection automatically, information processing, analysis, handle control, it is achieved the mistake of the set goal
Journey.Intelligent: refer to be collected by modern communications and information technology, computer networking technology, industry technology, intelligent control technology and
Become for the application in terms of some.
Along with network technology and the development of natural language processing technique, people get used to utilizing various instant messaging
Software exchanges, and can be obtained the information oneself wanted in time by these media, wherein, wechat be exactly one all well and good i.e.
Time means of communication, spatially communication disorder can be overcome by these instruments people, home-confined just can get real time information, as
News information, traffic information etc. are by such mode, at the aspect that spreads news, can give user messages meant in real time, solve
The shortcomings such as the hysteresis quality of conventional information of having determined transmission.Bring for the life of people and facilitate significantly.
Along with the development of society, the quantity of private car gets more and more, and traffic jam issue has become as each large, medium and small city
The significant problem that city is faced.So, road condition analyzing and real-time road condition information report, predicted the jam situation of future trajectory
Through becoming taxi driver, private car car owner, the important basis of traveler selection route.
Native system plays an important role in parties concerned such as mediating big city congestion in road promotion the coast is clear;To governments at all levels
Department reduce human and material resources fund input, alleviate traffic pressure, environment purification, reduction haze, the aspect such as promote social development
There is positive effect.This intelligent information broadcasting system, merges intellectuality, automatization, human oriented design, facilitates broadcasting station to report
While, it is possible to achieve the report function of multiple channel, such as wechat intelligent answer etc., allow user obtain traffic letter accurately
Breath, effectively to utilize road resources, alleviates popular trip situation.
Summary of the invention
In order to allow user obtain the data of traffic more easily, the present invention proposes a kind of semantic based on voice
The traffic radio traffic information broadcasting system understood, facilitates traffic radio host and reports information flag and map control, side
The road condition query of user and the inquiry of historical data.
A kind of based on voice semantic understanding the traffic radio traffic information broadcasting system that the present invention proposes, including based on language
The report information flag of sound identification and map control subsystem, this subsystem include sound identification module, message processing module and
Information display module, this subsystem carries out reporting information flag and map control for user by the way of phonetic entry;
Sound identification module is for being identified the voice messaging of user's input and export recognition result;
Information display module is the display device with human-computer interaction interface;
Message processing module, for processing the recognition result of sound identification module output, specifically includes following step
Rapid:
Step A1: the recognition result of traversal sound identification module output, detects whether have map control order, if having,
Go to step A3, if without, enter step A2;
Step A2: the recognition result of sound identification module output is done fuzzy with current interpersonal interactive interface display content
Pairing ratio, finds out the traffic information of the corresponding road of user speech input, and does with read flag processes with reporting labelling;
Step A3: carry out map control order pretreatment, the Control Cooling of detection map control order and control parameter, will
Control command is sent to map end and carries out relevant control.
A kind of based on voice semantic understanding the traffic radio traffic information broadcasting system of the present invention, also includes intelligent way asking
Subsystem, this system is for identifying user's input information and carrying out the information feedback of inquired about road conditions;This system includes temporary
Data base, for recording the temporary information of each ID;
In this system, the method for information processing specifically includes following steps:
Step B1: submit the request of asking the way to by wechat platform;
Step B2: record ID, and solicited message of asking the way is processed and information retrieval, the information extracted includes
Road name, place name, direction;Place name is mapped to road name;
Step B3: if not having road name and direction in the information extracted, and perform step B1 request user pass through wechat
Platform carries out the information completion of the request of asking the way;If the information extracted comprises road name, but do not comprise direction, then perform step
B4;If the information extracted comprises direction, but do not comprise place name, then perform step B5;If the information extracted is wrapped
Containing road name, place name, direction, then perform step B6;
Step B4: the temporary information of the corresponding ID of retrieval, if comprising direction in temporary information, performs step B6, if
Do not comprise direction and then the information that be extracted is added temporal data storehouse, and perform step B1 request user and carried out by wechat platform
The information completion of the request of asking the way;
Step B5: the temporary information of the corresponding ID of retrieval, if containing place name in temporary information, performing step B6, if
Do not comprise place name and then the information that be extracted is added temporal data storehouse, and perform step B1 request user and carried out by wechat platform
The information completion of the request of asking the way;
Step B6: the information extracted according to corresponding ID and temporary information, carries out the inspection of up-to-date traffic road condition data
Rope, and generate natural language reply user according to word masterplate.
A kind of based on voice semantic understanding the traffic radio traffic information broadcasting system of the present invention, also includes that visualization is gone through
History data query subsystem, this system is used for the road conditions of the historical period of inquiry roads and carries out visual presentation, concrete grammar
Comprise the following steps:
Step C1: input inquiry information, and the Query Information of input is carried out pretreatment, extract road name, query time section
Extract road entitled multiple time, if wherein one with other two as starting point, then be judged as the road of non-initiating terminal
For road to be checked;The most multiple roads are road to be checked;
When road to be checked is multiple, perform following steps respectively for each road to be checked;
Step C2: the Lu Mingyu standard road famous-brand clock of the road to be checked obtained in step C1 is carried out fuzzy matching, and leads to
Cross mapping table and retrieve inquiry Lu Mingyu road chain number;
Step C3: use the information of the road chain number of step C2 acquisition, extracts storage ID corresponding to road chain number as index, profit
Index of reference goes to retrieve in data base the historical data of institute's query time section;
Step C4: historical data inquiry obtained is classified by road chain number, splices in chronological order, and by broken line graph
Mode carries out the visual presentation of historical data.
Wherein, report information flag based on speech recognition and map control subsystem also include user-oriented dictionary module, should
Module is used for storing everyday words and mating identified voice messaging for sound identification module, and described everyday words includes
Conventional control command key word, Beijing road name.
Wherein, in step B2 extract road entitled multiple time, if wherein one with other two as starting point, then be judged as
The road of non-initiating terminal is road to be checked;The most multiple roads are road to be checked;
When road to be checked is multiple, perform step B3 respectively for each road to be checked.
Wherein, step A1 detects whether have map control order by control command detection decision tree, described control
The major control node of order detection decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate is more than threshold value
β;
Whether it is more than threshold θ with the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road.
Wherein, in step A2, the method for fuzzy matching is by history report order weighting to interpersonal interactive interface display content
Fuzzy matching, its formula is as follows:
Wherein Tnow、TbroadcastIt is respectively and reports, with corresponding history, the time that record broadcasts now, with minute be
Unit, TpFor time coefficient;Count () is counting function, and VRR is voice identification result collection.
Wherein, step A3 is detected Control Cooling by Control Cooling and control parameter detecting decision tree and is controlled parameter,
The major control node of described Control Cooling and control parameter detecting decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate is more than threshold value
β';
With the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road whether more than threshold θ '.
Wherein, threshold value beta, θ, β ', the determination method of θ ' be: use information gain-ratio, select optimal classification threshold value, formula is such as
Shown in lower:
Δ Gini (A)=Gini (D)-GiniA(D)
Wherein piFor assuming that under conditions of given classification thresholds, in D, element belongs to order key word or controls parameter
Probability, uses | Ci,D|/| D | estimate;D1、D2It is respectively the two class sample sets that sample space is divided under given threshold value.
The present invention propose a kind of based on voice semantic understanding traffic radio traffic information broadcasting system, contain based on
The report information flag of speech recognition and map control subsystem, intelligent way asking subsystem, visual history data query subsystem
System, it is achieved that traffic radio host carries out reporting information flag and map control by the way of voice, facilitates user
Road condition query and the inquiry of historical data.
Accompanying drawing explanation
Fig. 1: overall system of the present invention composition block schematic illustration;
Fig. 2: report information flag based on speech recognition and map control subsystem information handling process schematic diagram;
Fig. 3: intelligent way asking subsystem information handling process schematic diagram.
Fig. 4: visual history data query subsystem information handling process schematic diagram.
Detailed description of the invention
So that advantages of the present invention, technical scheme, goal of the invention will be apparent from clear, below in conjunction with example and attached
Figure, further divides the present invention and elaborates.Wherein, the used herein example that is embodied as is used only for explaining this
Bright, it is not intended to limit the present invention.
In order to realize the inventive method, embodiment is considered to process step and the number of users related to and resource quantity,
If realizing preferably ensureing processor 16 core at unit, internal memory is not less than 32GB, any language can be used to write, this example
Java language is used to realize.
A kind of based on voice semantic understanding the traffic radio traffic information broadcasting system of the present embodiment, uses optimum side
Case is described in detail, and the system of the present embodiment includes it is characterized in that as shown in Figure 1, believes including report based on speech recognition
Breath labelling and map control subsystem, intelligent way asking subsystem, visual history data query subsystem.
1, report information flag based on speech recognition and map control subsystem, at sound identification module, information
Reason module and information display module, this subsystem carries out reporting information flag and map for user by the way of phonetic entry
Control;
Sound identification module is for being identified the voice messaging of user's input and export recognition result;
Information display module is the display device with human-computer interaction interface;
Message processing module is for processing, as in figure 2 it is shown, specifically wrap the recognition result of sound identification module output
Include following steps:
Step A1: the recognition result of traversal sound identification module output, detects whether have map control order, if having,
Go to step A3, if without, enter step A2;
Step A2: the recognition result of sound identification module output is done fuzzy with current interpersonal interactive interface display content
Pairing ratio, finds out the traffic information of the corresponding road of user speech input, and does with read flag processes with reporting labelling;
Step A3: carry out map control order pretreatment, the Control Cooling of detection map control order and control parameter, will
Control command is sent to map end and carries out relevant control.
In the present embodiment, audio recognition method uses University of Science and Technology news to fly speech recognition open platform.
In the present embodiment, report information flag based on speech recognition and map control subsystem also include user-oriented dictionary mould
Block, this module is used for storing everyday words and mating identified voice messaging for sound identification module, and described is conventional
Word includes control command key word, Beijing road name commonly used.
In the present embodiment, step A1 detects whether have map control order by control command detection decision tree, institute
The major control node stating control command detection decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate is more than threshold value
β;
Whether it is more than threshold θ with the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road.
In the present embodiment, in step A2, the method for fuzzy matching is to report suitable to interpersonal interactive interface display content by history
Sequence weighted fuzzy matching, shown in its formula such as formula (1):
Wherein Tnow,TbroadcastIt is respectively and reports, with corresponding history, the time that record broadcasts now, with minute be
Unit, TpFor time coefficient;Count () is counting function, and VRR is voice identification result collection.
In the present embodiment, by Control Cooling and control parameter detecting decision tree detection Control Cooling and control in step A3
Parameter,
The major control node of described Control Cooling and control parameter detecting decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate is more than threshold value
β';
With the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road whether more than threshold θ '.
In the present embodiment, threshold value beta, θ, β ', the determination method of θ ' be: use information gain-ratio, select optimal classification threshold value,
Shown in formula such as formula (2), (3), (4):
Δ Gini (A)=Gini (D)-GiniA(D) (4)
Wherein piFor assuming that under conditions of given classification thresholds, in D, element belongs to order key word or controls parameter
Probability, uses | Ci,D|/| D | estimate;D1,D2It is respectively the two class sample sets that sample space is divided under given threshold value.
2, intelligent way asking subsystem, for identifying user's input information and carrying out the information feedback of inquired about road conditions,;This is
System includes temporal data storehouse, for recording the temporary information of each ID;
As it is shown on figure 3, the method for information processing specifically includes following steps in this system:
Step B1: submit the request of asking the way to by wechat platform;
Step B2: record ID, and solicited message of asking the way is processed and information retrieval, the information extracted includes
Road name, place name, direction;And place name is mapped to road name;
Step B3: if not having road name and direction in the information extracted, and perform step B1 request user pass through wechat
Platform carries out the information completion of the request of asking the way;If the information extracted comprises road name, but do not comprise direction, then perform step
B4;If the information extracted comprises direction, but do not comprise place name, then perform step B5;If the information extracted is wrapped
Containing road name, place name, direction, then perform step B6;
Asking the way request in this step is the voice that sends to intelligent way asking subsystem of wechat user or word request, system
Identify the information such as road name and direction that user is to be inquired, if incomplete, i.e. lack road name and/or place name and/or directional information, be
System can generate voice according to identification situation or Word message is inquired to user, and the same voice of user or word are in wechat
Platform is answered, and system can identify the relevant information of the inside.
Step B4: the temporary information of the corresponding ID of retrieval, if comprising direction in temporary information, performs step B6, if
Do not comprise direction and then the information that be extracted is added temporal data storehouse, and perform step B1 request user and carried out by wechat platform
The information completion of the request of asking the way;
Step B5: the temporary information of the corresponding ID of retrieval, if containing place name in temporary information, performing step B6, if
Do not comprise place name and then the information that be extracted is added temporal data storehouse, and perform step B1 request user and carried out by wechat platform
The information completion of the request of asking the way;
Step B6: the information extracted according to corresponding ID and temporary information, carries out the inspection of up-to-date traffic road condition data
Rope, and generate natural language reply user according to word masterplate.
In the present embodiment, in step B2 extract road entitled multiple time, if wherein one with other two as starting point, then
The road being judged as non-initiating terminal is road to be checked;The most multiple roads are road to be checked;
When road to be checked is multiple, perform step B3 respectively for each road to be checked.
In the present embodiment, solicited message of asking the way is processed by step B2 and the method for information retrieval is: use participle
System carries out participle and part-of-speech tagging to the request of asking the way, and extracts road name, place name, direction.If wechat platform is submitted to ask the way and is asked
Ask as voice messaging, then processed by Words partition system again and extract after needing advanced row speech recognition.
3, visual history data query subsystem, for the road conditions of historical period of inquiry roads and carry out visualization exhibition
Showing, as shown in Figure 4, concrete grammar comprises the following steps:
Step C1: input inquiry information, and the Query Information of input is carried out pretreatment, extract road name, query time section
Extract road entitled multiple time, if wherein one with other two as starting point, then be judged as the road of non-initiating terminal
For road to be checked;The most multiple roads are road to be checked;
When road to be checked is multiple, perform following steps respectively for each road to be checked;
Step C2: the Lu Mingyu standard road famous-brand clock of the road to be checked obtained in step C1 is carried out fuzzy matching, and leads to
Cross mapping table and retrieve inquiry Lu Mingyu road chain number;
Step C3: use the information of the road chain number of step C2 acquisition, extracts storage ID corresponding to road chain number as index, profit
Index of reference goes to retrieve in data base the historical data of institute's query time section;
Step C4: historical data inquiry obtained is classified by road chain number, splices in chronological order, and by broken line graph
Mode carries out the visual presentation of historical data.
In the present embodiment, owing to data volume is huge, store historical data when, traffic information is divided into by the hour 24
Individual tables of data, corresponding storage information database is made up of 24 tables, corresponding 24 hours every days, corresponding one little of each table record
Load conditions data time in.This is used to be mainly designed to owing to data volume is big, data base's effect when historical data is excavated
Rate is relatively low, in order to reduce data base's length, it is simple between data timesharing, end is analyzed, and beneficially parallel processing, therefore according to every day
24 hours, data base being designed as 24 tables, the data of each table record this hour of every day, system uses latest data to have only to
Found the tables of data of its correspondence by current time, then read up-to-date data.Therefore adopt in step C4 of the present embodiment
With a point table querying method, from different tables of data, carry out many table searches and data fusion according to query time segment information.
The present embodiment have also been devised report based on traffic information rule, according to user's listening situation and forget situation, letter
Breath propagates range, different brackets traffic information is limited difference and broadcasts frequency, it is characterised in that: one-level information was reported in 3 minutes
For the first time, second time is reported in 10 minutes;Second-level message was reported once in 10 minutes;Three grades of information were reported once in 15 minutes.
Particular embodiments described above, has been carried out the purpose of the present invention, technical scheme and beneficial effect the most in detail
Describe in detail bright, be it should be understood that the specific embodiment that the foregoing is only the present invention, be not limited to the present invention, all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. done, should be included in the guarantor of the present invention
Within the scope of protecting.
Claims (9)
1. a traffic radio traffic information broadcasting system based on voice semantic understanding, it is characterised in that include based on voice
The report information flag identified and map control subsystem, this subsystem includes sound identification module, message processing module and letter
Breath display module, this subsystem carries out reporting information flag and map control for user by the way of phonetic entry;
Sound identification module is for being identified the voice messaging of user's input and export recognition result;
Information display module is the display device with human-computer interaction interface;
Message processing module, for processing the recognition result of sound identification module output, specifically includes following steps:
Step A1: the recognition result of traversal sound identification module output, detecting whether have map control order, if having, turning step
Rapid A3, if without, enter step A2;
Step A2: the recognition result of sound identification module output is done fuzzy matching pair with current interpersonal interactive interface display content
Ratio, finds out the traffic information of the corresponding road of user speech input, and does with read flag processes with reporting labelling;
Step A3: carry out map control order pretreatment, the Control Cooling of detection map control order and control parameter, will control
Order is sent to map end and carries out relevant control.
2. the system as claimed in claim 1, it is characterised in that also include intelligent way asking subsystem, this system is used for identifying use
Family inputs information and carries out the information feedback of inquired about road conditions;This system includes temporal data storehouse, is used for recording each ID
Temporary information;
In this system, the method for information processing specifically includes following steps:
Step B1: submit the request of asking the way to by wechat platform;
Step B2: record ID, and solicited message of asking the way is processed and information retrieval, the information extracted includes road
Name, place name, direction;
Step B3: if not having road name and direction in the information extracted, and perform step B1 request user by wechat platform
Carry out the information completion of the request of asking the way;If the information extracted comprises road name, but do not comprise direction, then perform step B4;
If the information extracted comprises direction, but do not comprise place name, then perform step B5;If the information extracted comprises road
Name, place name, direction, then perform step B6;
Step B4: the temporary information of the corresponding ID of retrieval, if comprising direction in temporary information, performs step B6, if not wrapping
Then the information that be extracted is added temporal data storehouse containing direction, and perform step B1 request user and asked the way by wechat platform
The information completion of request;
Step B5: the temporary information of the corresponding ID of retrieval, if containing place name in temporary information, performing step B6, if not wrapping
Then the information that be extracted is added temporal data storehouse containing place name, and perform step B1 request user and asked the way by wechat platform
The information completion of request;
Step B6: the information extracted according to corresponding ID and temporary information, carries out the retrieval of up-to-date traffic road condition data, and
Generate natural language according to word masterplate and reply user.
3. system as claimed in claim 2, it is characterised in that also include visual history data query subsystem, this system
For the road conditions of historical period of inquiry roads and carry out visual presentation, concrete grammar comprises the following steps:
Step C1: input inquiry information, and the Query Information of input is carried out pretreatment, extract road name, query time section
Extract road entitled multiple time, if wherein one with other two as starting point, then be judged as that the road of non-initiating terminal is for treating
Inquiry roads;The most multiple roads are road to be checked;
When road to be checked is multiple, perform following steps respectively for each road to be checked;
Step C2: the Lu Mingyu standard road famous-brand clock of the road to be checked obtained in step C1 is carried out fuzzy matching, and by reflecting
Firing table retrieves inquiry Lu Mingyu road chain number;
Step C3: use the information of road chain number that step C2 obtains, extracts storage ID corresponding to road chain number as index, utilizes rope
It is directed toward in data base the historical data of retrieval institute query time section;
Step C4: historical data inquiry obtained is classified by road chain number, splices in chronological order, and by the way of broken line graph
Carry out the visual presentation of historical data.
4. the system as according to any one of claims 1 to 3, it is characterised in that report information flag based on speech recognition
Also including user-oriented dictionary module with map control subsystem, this module is used for storing everyday words and for sound identification module to being known
Not going out voice messaging to mate, described everyday words includes control command key word, Beijing road name commonly used.
5. system as claimed in claim 2, it is characterised in that the road extracted in step B2 entitled multiple time, if wherein one
With other two as starting point, then it is judged as that the road of non-initiating terminal is road to be checked;The most multiple roads are to be checked
Road;
When road to be checked is multiple, perform step B3 respectively for each road to be checked.
6. the system as according to any one of claims 1 to 3, it is characterised in that in step A1 by control command detection certainly
Plan tree detects whether have map control order, and the major control node of described control command detection decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate is more than threshold value beta;
Whether it is more than threshold θ with the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road.
7. system as claimed in claim 6, it is characterised in that in step A2, the method for fuzzy matching is to interpersonal interactive interface
Display content is by history report order weighted fuzzy matching, and its formula is as follows:
Wherein Tnow、TbroadcastBe respectively and report, with corresponding history, the time that record broadcasts the most now, by minute in units of,
TpFor time coefficient;Count () is counting function, and VRR is voice identification result collection.
8. system as claimed in claim 7, it is characterised in that by Control Cooling and control parameter detecting decision-making in step A3
Tree detection Control Cooling and control parameter,
The major control node of described Control Cooling and control parameter detecting decision tree is as follows:
String length to be identified is less than n;
Whether contain the key word in order keywords database (Command dictionary), and its matching rate more than threshold value beta ';
With the matching rate of the keyword controlled in parameter dictionary or the road name in the name dictionary of road whether more than threshold θ '.
9. system as claimed in claim 8, it is characterised in that threshold value beta, θ, β ', the determination method of θ ' be: use information gain
Rate, selects optimal classification threshold value, and formula is as follows:
Δ Gini (A)=Gini (D)-GiniA(D)
Wherein piFor assuming that under conditions of given classification thresholds, in D, element belongs to order key word or controls the probability of parameter,
Use | Ci,D|/| D | estimate;D1,D2It is respectively the two class sample sets that sample space is divided under given threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610596596.5A CN106157651B (en) | 2016-07-26 | 2016-07-26 | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610596596.5A CN106157651B (en) | 2016-07-26 | 2016-07-26 | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106157651A true CN106157651A (en) | 2016-11-23 |
CN106157651B CN106157651B (en) | 2019-06-14 |
Family
ID=58060719
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610596596.5A Active CN106157651B (en) | 2016-07-26 | 2016-07-26 | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106157651B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109217885A (en) * | 2018-09-21 | 2019-01-15 | 恒大法拉第未来智能汽车(广东)有限公司 | Vehicle-mounted radio tuning device and method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0321817A (en) * | 1989-06-20 | 1991-01-30 | Tokico Ltd | On-vehicle travel path guide device |
CN1779673A (en) * | 2004-11-25 | 2006-05-31 | 株式会社电装 | Information service system |
CN101109641A (en) * | 2006-07-21 | 2008-01-23 | 英华达(上海)电子有限公司 | Voice controlling and interacting device and method used for GPS device |
CN101939740A (en) * | 2007-12-11 | 2011-01-05 | 声钰科技 | In integrating language navigation Service environment, provide the natural language speech user interface |
CN102184641A (en) * | 2011-05-09 | 2011-09-14 | 浙江大学 | Running information based road condition management method and system |
CN103778797A (en) * | 2012-10-25 | 2014-05-07 | 北京掌城科技有限公司 | Multimode response method of voice transportation information |
CN104183144A (en) * | 2013-05-20 | 2014-12-03 | 北京百度网讯科技有限公司 | Real-time traffic condition information generating method and system thereof |
-
2016
- 2016-07-26 CN CN201610596596.5A patent/CN106157651B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0321817A (en) * | 1989-06-20 | 1991-01-30 | Tokico Ltd | On-vehicle travel path guide device |
CN1779673A (en) * | 2004-11-25 | 2006-05-31 | 株式会社电装 | Information service system |
CN101109641A (en) * | 2006-07-21 | 2008-01-23 | 英华达(上海)电子有限公司 | Voice controlling and interacting device and method used for GPS device |
CN101939740A (en) * | 2007-12-11 | 2011-01-05 | 声钰科技 | In integrating language navigation Service environment, provide the natural language speech user interface |
CN102184641A (en) * | 2011-05-09 | 2011-09-14 | 浙江大学 | Running information based road condition management method and system |
CN103778797A (en) * | 2012-10-25 | 2014-05-07 | 北京掌城科技有限公司 | Multimode response method of voice transportation information |
CN104183144A (en) * | 2013-05-20 | 2014-12-03 | 北京百度网讯科技有限公司 | Real-time traffic condition information generating method and system thereof |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109217885A (en) * | 2018-09-21 | 2019-01-15 | 恒大法拉第未来智能汽车(广东)有限公司 | Vehicle-mounted radio tuning device and method |
CN109217885B (en) * | 2018-09-21 | 2022-07-12 | 法法汽车(中国)有限公司 | Vehicle-mounted radio channel searching device and method |
Also Published As
Publication number | Publication date |
---|---|
CN106157651B (en) | 2019-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104820629B (en) | A kind of intelligent public sentiment accident emergent treatment system and method | |
CN103955505B (en) | A kind of event method of real-time and system based on microblogging | |
CN108491378B (en) | Intelligent response system for operation and maintenance of electric power information | |
CN107679224B (en) | Intelligent question and answer method and system for unstructured text | |
CN111460125A (en) | Intelligent question and answer method and system for government affair service | |
CN103593412B (en) | A kind of answer method and system based on tree structure problem | |
Chung et al. | A practical QA system in restricted domains | |
CN106407208A (en) | Establishment method and system for city management ontology knowledge base | |
CN104252507B (en) | A kind of business data matching process and device | |
CN109657063A (en) | A kind of processing method and storage medium of magnanimity environment-protection artificial reported event data | |
Klaithin et al. | Traffic information extraction and classification from Thai Twitter | |
CN103886020A (en) | Quick search method of real estate information | |
CN111914141B (en) | Public opinion knowledge base construction method and public opinion knowledge base | |
Alsaedi et al. | A combined classification-clustering framework for identifying disruptive events | |
CN101794304B (en) | Industry information service system and method | |
CN106157651A (en) | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding | |
CN113407734B (en) | Method for constructing knowledge graph system based on real-time big data | |
CN113177164B (en) | Multi-platform collaborative new media content monitoring and management system based on big data | |
CN109064191A (en) | Vehicle source data analytic method, device and electronic equipment | |
CN114490992A (en) | Intelligent answer system for legal affair consultation | |
CN109446424B (en) | Invalid address webpage filtering method and system | |
CN114117078A (en) | Electric power heterogeneous knowledge fusion method based on D-S evidence theory | |
CN106777124A (en) | Semantic knowledge method, apparatus and system | |
CN112905797A (en) | Scenic spot multi-dimensional vulnerability assessment method based on MNLP | |
Appling et al. | Deriving disaster-related information from social media |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |