CN110008413A - A kind of traffic trip problem querying method and device - Google Patents
A kind of traffic trip problem querying method and device Download PDFInfo
- Publication number
- CN110008413A CN110008413A CN201910192761.4A CN201910192761A CN110008413A CN 110008413 A CN110008413 A CN 110008413A CN 201910192761 A CN201910192761 A CN 201910192761A CN 110008413 A CN110008413 A CN 110008413A
- Authority
- CN
- China
- Prior art keywords
- entity
- traffic
- information
- checked
- knowledge map
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000014509 gene expression Effects 0.000 claims abstract description 35
- 239000000284 extract Substances 0.000 claims description 6
- 230000005055 memory storage Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 9
- 238000012545 processing Methods 0.000 description 36
- 230000008569 process Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 18
- 238000013507 mapping Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000012546 transfer Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to technical field of transportation more particularly to a kind of traffic trip problem querying methods and device, and the accuracy being intended to for improving identification user reduces human-computer interaction number.Receive traffic information to be checked；Identify the corresponding query intention of traffic information to be checked；According to the corresponding description information type of query intention, corresponding first description information of description information type, including location expression information and relationship description information are extracted from traffic information to be checked；The point entity from lookup location expression information in Traffic knowledge map is corresponding；Traffic knowledge map includes each layer entity in transportation network and the connection relationship between entity；Connection relationship between the entity for including according to relationship description information, point entity and Traffic knowledge map, determines target entity；According to Traffic knowledge map, play point entity and target entity, the corresponding objective result of reasoning query intention.In this way, the accuracy that identification user is intended to can be improved, human-computer interaction number is reduced.
Description
Technical field
The invention relates to technical field of transportation more particularly to a kind of traffic trip problem querying methods and device.
Background technique
Common electronic map in electronic equipment at present, the mode of *** maps group organization data are the position on map
Point, without being described to the relationship between any two location points.So user is in the inquiry using existing electronic map
It when function, needs to input specified starting point, terminal and trip mode, can just cook up route.This query function may be only available for
The simple problem scene of user's input.In addition to above-mentioned simple problem scene, it is defeated to can be potentially encountered user in other cases
Enter the scene of challenge, for example, inquiry Fuzzy Geographical position scene, inquiry route transfer scene, the ground for inquiring environs
Point etc. scenes, challenge scene include but is not limited to it is above-mentioned several, be also not necessarily limited to the various combinations of above-mentioned several scenes.
Existing electronic map, the front and back of challenge of the existing *** maps due to being unable to association user input
It is intended to, so the query function for the challenge that user can not be supported to input.If inquired using existing electronic map multiple
Miscellaneous problem, it is necessary to which user resolves into challenge multiple, then can just obtain final inquiry by multiple inquiry operation
As a result.For example, challenge " how the KFC near HaiXin Building goes " inquired using existing electronic map, realize
Detailed process is as follows: firstly the need of HaiXin Building is searched in Baidu map, then clicking on search nearby, then input willing moral
Base finally realizes this query function.
To sum up, how in the inquiry scene of challenge, realize that improving precisely identification user is intended to, and reduces human-computer interaction
Number need further to study.
Summary of the invention
The embodiment of the present application provides a kind of traffic trip problem querying method and device, is intended to for improving identification user
Accuracy reduces human-computer interaction number.
In a first aspect, the embodiment of the present application provides a kind of traffic trip problem querying method, this method comprises: receiving to be checked
Ask traffic information；Identify the corresponding query intention of traffic information to be checked；According to the corresponding description information type of query intention, from
Corresponding first description information of description information type is extracted in traffic information to be checked；First description information includes location expression letter
Breath and relationship description information；The point entity from lookup location expression information in Traffic knowledge map is corresponding；Traffic knowledge map
Including each layer entity in transportation network and the connection relationship between entity；According to relationship description information, rise point entity and
Connection relationship between the entity that Traffic knowledge map includes, determines target entity；According to the Traffic knowledge map, described
Point entity and the target entity infer the corresponding objective result of the query intention.
Through the above scheme, query intention can be identified from traffic information to be checked, but also can be according to inquiry
It is intended to corresponding description information type, the corresponding first description letter of the description information type is extracted from traffic information to be checked
Breath, such as location expression information and relationship description information.And Traffic knowledge map includes each layer entity and entity in transportation network
Between connection relationship, it is possible to realized by Traffic knowledge map association user front and back be intended to, from Traffic knowledge map
Middle corresponding point entity of lookup location expression information and find out target entity.It then can be according to Traffic knowledge map
According to the Traffic knowledge map, described point entity and the target entity, the corresponding target of the query intention is inferred
As a result.As it can be seen that scheme provided by the present application can identify the query intention of user, and realizes and pass through Traffic knowledge map starting point
Entity and target entity and the corresponding objective result of query intention is inferred, user is needed to come unlike the prior art
Traffic information to be checked is decomposed, so as to improve the accuracy that identification user is intended to, reduces human-computer interaction number.
Second aspect, the embodiment of the present application provide a kind of traffic trip problem inquiry unit, including memory and processor；
The memory is for storing instruction；The processor is used to execute the instruction of the memory storage, when the processor is held
When the instruction of the row memory storage, so that described device executes following operation:
Receive traffic information to be checked；Identify the corresponding query intention of the traffic information to be checked；According to the inquiry
It is intended to corresponding description information type, the corresponding first description letter of the description information type is extracted from traffic information to be checked
Breath；First description information includes location expression information and relationship description information；Institute's rheme is searched from Traffic knowledge map
Set corresponding point entity of description information；The Traffic knowledge map includes between each layer entity and entity in transportation network
Connection relationship；Between the entity for including according to the relationship description information, described point entity and the Traffic knowledge map
Connection relationship, determine target entity；According to the Traffic knowledge map, described point entity and the target entity, push away
Manage out the corresponding objective result of the query intention.
The third aspect, the embodiment of the present application provide a kind of traffic trip problem inquiry unit, including receiving unit and processing
Unit；Wherein, receiving unit, for receiving traffic information to be checked；
Processing unit, for identification corresponding query intention of the traffic information to be checked；According to the query intention pair
The description information type answered extracts corresponding first description information of the description information type from traffic information to be checked；Institute
Stating the first description information includes location expression information and relationship description information；The location expression is searched from Traffic knowledge map
Corresponding point entity of information；The Traffic knowledge map includes each layer entity in transportation network and the connection between entity
Relationship；Connection between the entity for including according to the relationship description information, described point entity and the Traffic knowledge map
Relationship determines target entity；According to the Traffic knowledge map, described point entity and the target entity, institute is inferred
State the corresponding objective result of query intention.
Fourth aspect, the embodiment of the present application provide a kind of computer storage medium, finger are stored in computer storage medium
It enables, when run on a computer, so that computer executes any possible implementation of first aspect or first aspect
In method.
5th aspect, the embodiment of the present application provides a kind of computer program product comprising instruction, when its on computers
When operation, so that computer executes the method in any possible implementation of first aspect or first aspect.
Detailed description of the invention
Fig. 1 is a kind of data structure schematic diagram that the embodiment of the present application is applicable in；
Fig. 2 is a kind of Traffic knowledge map structural schematic diagram that the embodiment of the present application is applicable in；
Fig. 3 is a kind of traffic trip search engine architecture schematic diagram that the embodiment of the present application is applicable in；
Fig. 4 is a kind of flow diagram of traffic trip problem querying method provided by the embodiments of the present application；
Fig. 5 is a kind of entity relationship schematic diagram provided by the embodiments of the present application；
Fig. 6 is another entity relationship schematic diagram provided by the embodiments of the present application；
Fig. 7 is another entity relationship schematic diagram provided by the embodiments of the present application；
Fig. 8 is route planning schematic diagram of a scenario provided by the embodiments of the present application；
Fig. 9 is a kind of structural schematic diagram of traffic trip problem inquiry unit provided by the embodiments of the present application；
Figure 10 is the structural schematic diagram of the device of another route planning provided by the embodiments of the present application.
Specific embodiment
In order to keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application make into
One step it is described in detail.Concrete operation method in embodiment of the method also can be applied to Installation practice or system embodiment
In.
In order to solve the problems, such as that existing electronic map can not precisely identify that the intention of the complicated way to put questions of user, the present invention are real
It applies example and a kind of traffic trip problem querying method is provided, the knowledge representation to transportation network is realized using knowledge mapping technology,
Traffic knowledge map is obtained, then identifies query intention, and precisely identification user is intended in conjunction with Traffic knowledge map to realize, subtracts
The effect of few interaction times.
Knowledge mapping is a kind of semantic network of large size, for describing the entitative concept and conceptual entity thing of objective world
Relationship between part, specifically, using entitative concept as node, using relationship as side, the one kind provided generation from the viewpoint of relationship
The mode on boundary.For Knowledge Extraction mainly towards open link data, usually typical input is natural language text or more
Media content document etc..Then available blocks of knowledge, blocks of knowledge are extracted by the technology of automation or semi-automation
It mainly include 3 entity, relationship and attribute knowledge elements, and based on this, a series of the fact that form high quality expression.
In order to realize method provided by the embodiments of the present application, need using Traffic knowledge map.Optionally, traffic is known
Knowing map can be when needing using Traffic knowledge map electronic equipment to construct, for example, using Traffic knowledge map it
Before, Traffic knowledge map is first constructed according to transportation network, Traffic knowledge map is also possible in advance match Traffic knowledge map
It sets in the electronic device, either presets Traffic knowledge map or electronic equipment and construct traffic again when need to use and know
Know map, the building process of Traffic knowledge map can refer to the building process of Traffic knowledge map provided by the present application.
It describes in detail below to the building process of Traffic knowledge map, specifically includes process one and process two.
Process one describes transportation network using data structure.By in transportation network (map space) road, crossing,
Each category information in the information such as position, region division is managed, the entity for describing the information, such as road entity " gold are all abstracted as
Water route " entity, " 215 tunnel " bus entity, " HaiXin Building " entity etc..
Classify to the entity being abstracted by transportation network, can include but is not limited to following five classes entity information: handing over
Access net, transport node, point of interest, regional network, multidate information.As shown in Figure 1, the data content that the five classes entity information includes
It is as follows respectively:
Traffic network, this kind of entity information describe the line information of traffic network, such as underground route, bus routes, road
Road network, road section, the entity for wherein including in road network can describe the minimum particle sizes such as lane, road direction, entire road
It can not careful this information of description for an entity.
Transport node, this kind of entity information describe the critical entities information in transportation network, can be real for traffic network layer
Body is mutually related key node, such as subway platform, bus platform, intersection.
Point of interest, this kind of entity information describe the geographical location entity that user in transportation network is concerned about, such as food and drink, live
Place, shopping, hygienic social security, science and education culture, Leisure Sport, tourist attractions, incorporated business, place name etc., are used in transportation network
Starting point, terminal, the approach point etc. of user are described.
Regional network, this kind of entity information describe area information, such as commercial circle, administrative area etc. in transportation network.
Multidate information, this kind of entity information tissue describe congestion in road, dynamic event, dynamic section in transportation network
Information.
Process two constructs Traffic knowledge map according to the data structure of process one.Specifically, with entity information traffic road
Net is knowledge mapping bottom, is believed in conjunction with entities such as point of interest (Point of Interest, POI), regional network and multidate informations
Breath, constructs five layers of Traffic knowledge map structure.A series of group of entities that each layer of Traffic knowledge map is classified by belonging to this layer
At connection type uses parallel link mode between entity and entity, that is to say, that two entities in same layer do not connect specifically
Connect relationship.
As shown in Fig. 2, the Traffic knowledge map includes five layers, respectively administrative region layer (being referred to as area level), POI
Layer, intersection layer, road network layer-section (being referred to as section layer), road network layer-road (being referred to as section layer).
Any two entities on same layer do not have connection relationship, and administrative region layer may be with POI layers, intersection layer, road network layer-
The entity of section any layer has connection relationship.
Wherein, administrative region layer can be a commercial circle or administrative area etc..For example there are commercial circle A, commercial circle B and administration in administrative area
The road etc. that area C, commercial circle A and administrative area C include may have overlapping, and the road etc. that commercial circle B and administrative area C include may also have weight
It is folded, but there is no connection relationship between commercial circle A, the commercial circle B and administrative area C three on the layer of administrative area, it only can be with administrative region layer
Following layer has connection relationship.Certainly, two different entities for belonging to same layer may also connect other layers same simultaneously
A entity, such as commercial circle A and administrative area C may connect the same POI entity in POI layers.
POI layers, including multiple POI entities, in GIS-Geographic Information System, a POI entity can be a house, one
Retail shop, a mailbox, a bus station etc..
Intersection layer includes multiple entities, for example, intersection layer shown in Fig. 2 includes 5 entities, respectively
Entity a, entity b, entity c, entity d, entity e.Shandong road 1, mountain by taking entity b as an example, in entity b link road stratum reticulare-section
East Road 2, Yanji road 1, Yanji road 2.
Road network layer can be divided into road network layer-section and road network layer-road, and a road may include multiple sections, such as
Shandong road includes Shandong road 1 and Shandong road 2, as shown in Fig. 2, the Shandong road entity in road network floor-road respectively with road network floor-road
Shandong road 1 and Shandong road 2 in section connect, the Yanji road entity in road network floor-road respectively with the Yanji in road network floor-section
Road 1 and Yanji road 2 connect.
In transportation network knowledge mapping, following several connection types can be used, realize knowledge mapping building:
The first connection type, road network and road, section are connected according to attaching relation, as Shandong road 1, Shandong road 2 and
Shandong road is connected, using " entity-relationship-entity " connection type in Traffic knowledge map.Shandong road 1, Shandong road 2 are Shan Donglu
Section mark above, Shandong road are the specific road for including in road network.
Second of connection type, road section can be connected with intersection, according to locating for the road traffic network Zhong Ciduan
Position, starting point intersection, the terminal intersection on this section of way, on-link mode (OLM) use " entity-relationship-entity ", characterization
The connection relationship on the road road network Zhong Ciduan and crossing.
The third connection type, interest point information are connected with road section, are characterized in road network this point of interest in which Duan Lu
On, connection type uses " entity-relationship-entity ".Same interest point can be connect with a plurality of section, such as in intersection
Neighbouring point of interest, using the connection type of this point of interest and adjacent two road " entity-relationship-entity ".
4th kind of connection type, regional network are connected with interest point information, intersection, road section, describe point of interest
Belong to city South with the attaching information of intersection, such as HaiXin Building.
5th kind of connection type, underground route, bus routes are respectively depicted as entity, subway platform, public transport with description
Platform connection, using " entity-relationship-entity " connection type.
6th kind of connection type, subway platform, bus platform are connected with road section, even using " entity-relationship-entity "
Mode is connect, characterization subway platform, bus platform are on which road.Multichannel public bus network is associated with for identical bus platform, is used
The mode that multichannel public transport is connect with this bus platform " entity-relationship-entity " characterizes；Identical subway platform is located at different Roads
It in section (A, B, C, D mouthfuls), is connect respectively with a plurality of section " entity-relationship-entity " using this platform, the locating tool in difference outlet
Body section characterizes this bus platform entity attributes information by the way of " entity-attribute-attribute value ".
The specific information of each entity described, for example, link length, subway platform longitude and latitude, the public bus network time of departure,
Attribute value is connect with entity by the way of " entity-attribute-attribute value ", is described this entity by shopping square business hours etc.
Detailed attribution information.
Based on above-mentioned Traffic knowledge map, Fig. 3 is a kind of traffic trip search engine architecture provided by the embodiments of the present application
Schematic diagram.
As shown in figure 3, the traffic trip search engine may include the webpage front end (web) or application APP, host interface
(tkg_core) module, speech recognition (voice_recognition) module, Duolun semantic computation (semantic) module, more
(real_ is searched in task control (multi_task_ctl) module, alarm identification (alarm_place) module, real-time road reasoning
Time_traffic) (query_ is searched in module, trip mode reasoning search (path_planning) module, geographical location reasoning
Information) module, extensive semantic computation (generalize_semantic) module, data-interface handle (data_
Driven_port) module and other data interface modules.Wherein, host interface module, speech recognition module and Duolun language
Adopted computing module is mainly used for completing the pretreatment of user's way to put questions and way to put questions delineation of activities, and Duolun semantic computation module is according to business
Divide other of scheduling business processing algorithm, extensive semantic computation module and data interface processing module finishing service processing result
Processing.It describes in detail below to the function of each business module.
Host interface module, on the one hand, can be used for receiving web front-end or user and inputted in electronic map application APP
Information to be checked and the order triggered, certain order are also possible to what user directly inputted in electronic map application APP, this
Host interface module calls speech recognition module or Duolun semantic computation module according to the data content carried in order, if should
The data content that order carries is voice data, then host interface module calls speech recognition module, will pass through voice knowledge
Language data process is text data by other module, is then recalled Duolun semantic computation module and is realized that identification user is intended to；Such as
The data content that the fruit order carries is text data, then host interface module calls semantic computation module in Duolun to realize identification
User is intended to.On the other hand, it can be also used for receiving the processing result from data interface processing module, such as route planning knot
Fruit, and processing result is returned into web front-end or electronic map application APP.
Speech recognition module, for being text data by language data process.
Duolun semantic computation module, for carrying out Duolun semantic computation and way to put questions storage, delineation of activities etc., wherein more wheels
Semantic computation be in order to identify that user is intended to, such as it is candidate be intended to identify with having alarm, real-time road inquiry, trip mode are looked into
Ask, geographical location inquiry etc. it is any or appoint it is a variety of, below by candidate be intended to include above-mentioned four kinds for, Duolun semantic computation use
It calculates user in the traffic information to be checked inputted according to user to be intended to be respectively the above-mentioned four kinds candidate probability being intended to, then
Each candidate is intended to corresponding probability and is sent to multitask control module.
Multitask control module calls alarm identification module, real-time road to push away for the probability results according to semantic computation
Manage the business modules such as search module, trip mode reasoning search module and geographical location reasoning search module.A kind of optional side
In formula, according to the sequence of probability from big to small, candidate is intended to be intended to as user to call corresponding business module, if any
Business module cannot reason about out meet the corresponding condition of the business module as a result, just calling next business according to probability sequence
Module, until some business module is available meet the corresponding condition of the business module as a result, four business moulds
Block is all not met for the result of the corresponding condition of corresponding business module.Specifically, the maximum candidate intention of select probability
It is intended to as user, traffic information to be checked is then sent to corresponding module and carries out subsequent rationale.If maximum probability
When candidate is intended to be intended to as user, can not infer as a result, then from it is remaining it is several it is candidate be intended in select a probability
Maximum candidate intention is intended to as user, and traffic information to be checked is then sent to corresponding module and carries out subsequent rationale.
As an example, for example, determining that user is intended to trip mode inquiry, then Duolun semantic computation module is just
The traffic information to be checked is sent to trip mode reasoning search module.For another example, determine that user is intended to real-time road
Inquiry, then the traffic information to be checked is sent to real-time road reasoning search module by Duolun semantic computation module.
If whole business modules all cannot reason about out as a result, if call extensive semantic computation module determine one recommendation
Way to put questions return to host interface module.
Separately below to identified with alarm, real-time road inquiry, trip mode inquiry, geographical location inquiry etc. is candidate anticipates
Scheme corresponding business module to be introduced.
Alarm identification module, for alarm identify, output the result is that user input way to put questions geographical location
Coordinate points longitude and latitude.
Real-time road reasoning search module, the reasoning for carrying out real-time road is searched for, for example, in conjunction with Traffic knowledge map
The way to put questions inputted with user, the road section information to be inquired of reasoning user, and the return of real-time road interface is requested to need to inquire
The road congestion information of section road conditions.
Trip mode reasoning search module is searched in conjunction with the reasoning of knowledge mapping, is completed under certain trip mode of user, than
Such as certain vehicles, the route planning that user is intended to is completed.For example, " how is the KFC driven near HaiXin Building
Walk ", the vehicles of this way to put questions are vehicles, a plurality of driving route can be finally inferred, wherein may recommend shortest path
Route, used time minimal path, high speed preferential route etc..
(query_information) module is searched in geographical location reasoning, for carrying out the details to geographical location
Search, module output is the information such as title, phone, better address, type that user inputs way to put questions.
If processing result can be inferred by corresponding business module after the above-mentioned user determined is intended to, that
Extensive semantic computation module is entered from corresponding reasoning module.If whole business modules all cannot reason about out as a result, if adjust
Determine that the way to put questions of a recommendation returns to host interface module with extensive semantic computation module.
Extensive semantic computation (generalize_semantic) module, for there are one in above-mentioned several business modules
A business module can be returned the result correctly, then result is occurred to data interface processing module；Above-mentioned several business modules all
It cannot correctly return the result, return and recommend way to put questions to data interface processing module, be asked recommendation by data interface processing module
Method is sent to host interface module.
Data-interface handles (data_driven_port) module, for being standardized to processing result, such as
It is packaged into fixed format, then content after encapsulation is returned into host interface module, so that host interface module is defeated by processing result
Out to web front-end or electronic map application APP.In addition, can also pass through for other external systems to the additional demand of data
Data interface processing module does unified output processing.
Traffic trip question and answer engine based on transportation network knowledge mapping technology, human-computer interaction is more natural, more acurrate, compares
Compared with traditional inquiry system based on engine map technology and database technology, have the advantages that on the one hand, traffic road
The knowledge mapping expression on road, route, geographical location, may be implemented map space data digital, topologizes, deposit convenient for data
Storage, retrieval.On the other hand, using the transportation network of knowledge mapping technological expression, the question and answer that can go on a journey for user, which provide, to be based on opening up
Flutter Fuzzy Geographical position, the route transfer, the inquiry such as place of environs of relationship；Another aspect, data maintenance is convenient, uses
The transportation network of knowledge mapping technical description, for increasing public transport, subway line newly, the data maintenances such as new added road are newly-increased real
Body or the link of newly-increased relation on attributes；Route change is relation on attributes link change.
In the embodiment of the present application, optionally, transportation network knowledge mapping be can integrate in above-mentioned traffic trip search engine
Alarm identification module, real-time road reasoning search module, trip mode reasoning search module, geographical location reasoning search for mould
In block.
Based on above content, Fig. 4 illustrates a kind of traffic trip problem issuer provided by the embodiments of the present application
Method, this method can be executed by above-mentioned traffic trip search engine shown in Fig. 3, can also be by including that above-mentioned traffic trip is searched for
The electronic equipment of engine executes.As shown in figure 4, this method comprises:
Step 401, traffic information to be checked is received.
Wherein, traffic information to be checked can be simple way to put questions, be also possible to complicated way to put questions.
Illustrate in conjunction with Fig. 3, traffic information to be checked can be user and answer in the front end of electronic equipment or electronic map
With what is inputted on APP.
Traffic information to be checked can be voice data, be also possible to text data, if traffic information to be checked is text
Notebook data, host interface module send more wheel semantic computation modules for the traffic information to be checked received and handle, with
It can determine query intention.If traffic information to be checked is voice data, host interface module is to be checked by what is received
It askes traffic information to be sent to speech recognition module and handled, so as to be processed into text data, then text data be sent
At most take turns semantic computation module.
Step 402, the corresponding query intention of traffic information to be checked is identified.
Herein, the corresponding query intention of traffic information to be checked can include but is not limited to one of the following contents or more
Kind: the identification of alarm ground, real-time road inquiry, trip mode inquiry, geographical location inquiry.
Illustratively, can be directed to traffic information to be checked, using short text sorting algorithm to traffic information to be checked into
Row classification determines that query intention is the probability that certain above-mentioned one kind is intended to.
Step 403, according to the corresponding description information type of query intention, description information is extracted from traffic information to be checked
Corresponding first description information of type, the first description information include location expression information and relationship description information.
Optionally, description information type can include but is not limited to location expression type, region description type, choice for traveling
Description type.For example, the corresponding description information type of query intention is location expression type, the first description information in step 403
It can be location expression information；For another example, the corresponding description information type of query intention is region description type in step 403,
First description information can be region blur information.
Below with reference to illustrating the corresponding description information type of query intention and description information type corresponding first
Description information.
For example, query intention is the identification of alarm ground or geographical location inquiry, the description type that can be extracted includes position
Set description type and region description type, wherein the corresponding location expression information of location expression type can for building, cell,
The location expressions such as company, road, intersection, parking lot, villagers' committee point, the corresponding region blur information of region description type
Can for region, nearby, 50 meters eastwards, which downstairs, doorway etc..
For another example, query intention is trip mode inquiry, and the description type that can be extracted includes location expression type, area
Domain description type and trip mode description type, wherein the corresponding location expression information of location expression type can for building,
The places such as the starting points such as cell, company, road, intersection, parking lot, villagers' committee, terminal, transit point description information, region
The corresponding region blur information of description type can for region, nearby, 50 meters eastwards, which downstairs, the region blurs such as doorway letter
Breath；It rides, public transport, subway, taxi, self-driving, the modes of transportation such as walking；The corresponding choice for traveling description of trip mode description type
Information can for nearest, approach, visit, it is most economical, most save time, walking is few etc..
For another example, query intention is real-time road inquiry, and the description type that can be extracted includes road description type, position
Description type and region description type trip mode description type are set, wherein the corresponding link description information of road description type can
With road, section etc.；The corresponding location expression information of location expression type can be building, cell, company, road, road
The location expressions such as intersection, parking lot, villagers' committee point；The corresponding region blur information of region description type can be region, attached
Closely, doorway etc..
In a kind of optional embodiment, it can be realized using algorithm and extract corresponding first description of description information type
Information, such as clause matching algorithm, participle decision making algorithm, part of speech parser.Wherein clause matching algorithm can determine to
Inquire the way to put questions type of traffic information, such as rhetorical question clause.Participle decision making algorithm is used to traffic information to be checked splitting into word.
Part of speech parser analyzes the description that word belongs to any description type for integrating the word and clause that first two algorithm obtains
Information.
Step 404, the point entity from lookup location expression information in Traffic knowledge map is corresponding；Traffic knowledge map packet
Include each layer entity in transportation network and the connection relationship between entity.
In conjunction with Fig. 2 as it can be seen that may include five layer entities in Traffic knowledge map in the transportation network for including, difference administrative area
Layer, point of interest layer, intersection layer, road layer and section layer.Optionally, before being retrieved to Traffic knowledge map,
It can be to building search index between position description information and entity, to accelerate according to location expression information searching correspondent entity
Speed.
Step 405, according to relationship description information, play connection between the entity that point entity and Traffic knowledge map include
Relationship determines target entity.
Below with reference to specific example to determining that target entity is illustrated.
By taking relationship description information is connection relationship as an example, it can be handled for following problem: for example, which 26 road car have
A little websites, everything city have which shop, 26 road car to change to the processing of the ways to put questions such as 214 tunnels where, are specifically not limited to the several of above-mentioned offer
Kind way to put questions.As shown in figure 5, target entity is entity 2 to play point entity as entity 1, the connection according to entity and other entities is closed
System carries out knowledge mapping reasoning.It further, can be with if including also needing to obtain entity 3 from 2 reasoning of entity in customer problem
Entity 3 is obtained by 2 reasoning of relationship.
It is illustrated so which shop everything city has as an example, playing point entity is everything city, and target entity is shop, and the two connects
The relationship of connecing be include relationship.
By taking relationship description information is range information as an example, for example, how the KFC near HaiXin Building goes to wait at ways to put questions
Reason, as shown in fig. 6, target entity is entity 2 to play point entity as entity 1, it can be according to the geographical position between entity and entity
The relationship of closing on is set, is made inferences.By taking how the KFC near HaiXin Building goes as an example, playing point entity is HaiXin Building, target
Entity is KFC, near range information is.
By taking relationship description information is syntagmatic as an example, such as the syntagmatic of connection relationship and range information, such as south
The processing of the ways to put questions such as the McDonald near the road crossing of the Ningxia Jing Lu.It is first depending on connection relationship, reasoning has obtained point entity, then root
According to point entity and other entities are played, made inferences according to range information.As shown in fig. 7, using connecting simultaneously with entity 2 and entity 3
The entity connect, positioning target entity are entity 1, and combination range reasoning obtains entity 4.With the wheat near the Ningxia road crossing of Nanjing Road
For labor, Nanjing Road is entity 1, and Ningxia road is entity 2, and Nanjing Road Ningxia road crossing is entity 3, and McDonald is entity 4, model
It is neighbouring for enclosing information.
Certainly, combination of the syntagmatic in above-mentioned example in addition to can be connection relationship and range information, is also possible to
The combination of connection relationship and connection relationship between entity 3 and entity 4 is also by connection relationship come reasoning in i.e. Fig. 7.It is optional
, be also possible to the combination of connection relationship and attribute information, i.e. in Fig. 7 between entity 4 and entity 3 be relation on attributes, than strictly according to the facts
Body 4 is the attribute information of entity 3.
Step 406, according to Traffic knowledge map, point entity and target entity, the corresponding target of query intention is inferred
As a result.
Through the above scheme, query intention can be identified from traffic information to be checked, but also can be according to inquiry
It is intended to corresponding description information type, the corresponding first description letter of the description information type is extracted from traffic information to be checked
Breath, such as location expression information and relationship description information.And Traffic knowledge map includes each layer entity and entity in transportation network
Between connection relationship, it is possible to realized by Traffic knowledge map association user front and back be intended to, from Traffic knowledge map
Middle corresponding point entity of lookup location expression information and find out target entity.Then can according to Traffic knowledge map,
Point entity and target entity are played, the corresponding objective result of query intention is inferred.As it can be seen that scheme provided by the present application can identify
The query intention of user out, and realize and point entity and target entity are played by Traffic knowledge map and infer query intention
Corresponding objective result needs user unlike the prior art to decompose traffic information to be checked, knows so as to improve
The accuracy that other user is intended to reduces human-computer interaction number.
In a kind of optional mode, Traffic knowledge map can be constructed to obtain by following manner: be extracted in transportation network
All kinds of traffic informations and all kinds of traffic informations between incidence relation；Using the corresponding entity of all kinds of traffic informations as node,
Using the incidence relation between any two classes traffic information as side, Traffic knowledge map is constructed.Exemplary, all kinds of traffic informations can be with
The entity informations such as including but not limited to above-mentioned traffic network, transport node, point of interest, regional network, multidate information are handed over for constructing
The traffic information of logical knowledge mapping can also be that above-mentioned all kinds of traffic informations are any one or more of.Specific building process
Referring to the associated description of two processes of above-mentioned Traffic knowledge map construction, details are not described herein again.
Based on the above embodiment, query intention includes trip mode inquiry, and the embodiment of the present application is provided on a kind of can be achieved
The mode for stating step 406 determines the corresponding target trip mode of traffic information to be checked, determines target according to target trip mode
Transportation network infers the corresponding target route of query intention according to point entity, target entity and target transportation network is played.
In a kind of optional implementation, target route can be determined in the following way: firstly, determining that target is handed over
In open network with rise point entity it is closest first closest with target entity the in entity and target transportation network
Two adjacent to entity；Then, according to target transportation network, cooked up point entity and first the first route between entity,
And first adjacent to the second route and second between entity of entity and second between entity and target entity
Third route, wherein the first route, the second route and third route combination are target route.
In one example, it may include trip mode in information to be checked, and when trip mode decision programme path
Used transportation network, such as trip mode are walking, ride, self-driving, taxi, are needed using road network come programme path；
Trip mode is public transport for another example, is needed using bus-route network；Trip mode is subway for another example, is needed using MTR network.
Illustratively, by taking public transport, subway etc. change to scene as an example, by starting point to bus-route network and by bus-route network to terminal,
It needs to switch using based on road network.For example the route planning that place A takes pubic transport to place B, centre need to take 12 tunnels
Bus, then transfer to No. 18 buses.
S1 carries out reasoning by circumscription to starting point, terminal and neighbouring target mode of transportation network node using knowledge mapping, obtains
To nearest target mode of transportation network entity.Wherein, starting point is place A, and terminal is place B, and target trip mode is public transport
Vehicle is first looked for 12 road bus stop C near the A of place, 18 road bus stop F near the B of place.
S2, by starting point, terminal, use road network realize starting point and the route planning of target transportation network adjacent node, with
And terminal and the adjacent node route planning of target transportation network.Using road network planning place A to its neighbouring 12 tunnel bus stop
The route of the route of point C and 18 road bus stop F to place B near the B of place.
S3 carries out the head and the tail route reasoning of target transportation network in target transportation network, and there are mainly two types of situations:
Situation one between No. 12 buses and No. 18 buses, does not need walking transfer or walking is no more than certain threshold
The same station transfer route planning of value, this threshold value determine according to actual needs, for example can be set as 20m, that is to say, that walking
Distance is no more than 20m and just belongs to station transfer；It is set as 5m for another example, herein with no restriction.In this case, known according to traffic
Map is known, using the route between bus-route network planning 12 road bus stop C and 18 road bus stop F.
Situation two between No. 12 buses and No. 18 buses, needs walking transfer or walking is more than certain threshold value
With station transfer route planning.In this case, it is unable to complete direct route reasoning, superposition road network carries out route reasoning.Assuming that
12 road bus stop C get off to 12 road bus stop D, and 18 road bus stop E of Zai Cong changes to No. 18 buses to 18 tunnels
Bus stop F, according to Traffic knowledge map, using bus-route network planning 12 road bus stop C to 12 road bus stop D it
Between route, using the route between road network planning 12 road bus stop D to 18 road bus stop E and using public
Network planning is handed over to draw the route between 18 road bus stop E to 18 road bus stop F.
Illustrate route planning process below with reference to specific example.
Does as shown in figure 8, for following problem: how Zhejiang road Hubei road crossing walk to happy happiness visitor come shopping square? into
Professional etiquette is drawn.Address reasoning is carried out first, analyzes beginning and end, and wherein starting point is Zhejiang road Hubei road crossing, and terminal is happy
Happiness visitor comes shopping square.Then position mapping is carried out in Traffic knowledge map, Zhejiang road Hubei road crossing is mapped to starting point reality
Body a, happy happiness visitor come shopping square and are mapped to target entity d.Route reasoning, available d-c-a and d-b-a two are carried out later
Route.
Based on any of the above-described embodiment, if can be cooked up more in traffic information to be checked without providing trip mode
The corresponding route of kind trip mode, so that user can voluntarily select a route.
Further, it after playing the route between point entity and target entity, can also be pushed away according to the query intention of user
Recommend a qualified route.Illustratively, if how much traffic information to be checked needs to location point B for location point A,
So after cooking up the route between location point A and location point B, a plurality of route may be cooked up, then can be recommended
One generally the least expensive route.If traffic information to be checked is which way to go is most short by location point A to location point B, planning
After route between out position point A and location point B, the route of a shortest path can also be recommended.
In a kind of possible embodiment, the corresponding relationship of Traffic knowledge map also included entity and attribute value.This Shen
Please embodiment a kind of mode of achievable above-mentioned steps 406 is provided, the entity and attribute value for including according to Traffic knowledge map
Corresponding relationship plays point entity and target entity, infers the attribute value of the corresponding target entity of query intention.For example, than
The service calls in the first department store are such as inquired, target entity is the first department store, and attribute value is the phone number of service calls
Code.
Based on any of the above-described embodiment, in a kind of possible embodiment, looked into identifying that traffic information to be checked is corresponding
It askes before being intended to, can also be intended to for each of N number of candidate intention is candidate, determine the corresponding intention of traffic information to be checked
For the probability that candidate is intended to, wherein N is the integer greater than 0.It then can be according to the corresponding N of traffic information to be checked determined
A probability, determines query intention.
Further, it is possible to realize according to the corresponding N number of probability of traffic information to be checked determined, query intention is determined
Mode there are many., can be by the corresponding N number of probability of traffic information to be checked in a kind of possible implementation, probability is most
It is worth corresponding candidate greatly to be intended to as query intention.Then proceed to execute step 403 to step 406.
In another possible embodiment, N number of candidate intention can be arranged according to the sequence of probability from big to small,
I-th of candidate intention is determined from N number of candidate intention, as query intention, i is the integer less than N.It then proceedes to execute step
Rapid 403 to step 406.
It is pushed away based on above-mentioned second possible embodiment according to Traffic knowledge map, point entity and target entity
After managing out the corresponding objective result of query intention, it is corresponding can also to determine whether objective result meets i-th of candidate intention
Condition.
Herein, the case where being unsatisfactory for i-th of candidate intention corresponding condition for objective result is illustrated.For example it goes on a journey
Mode is bus, but the route exported is not to use bus as the route of trip mode；For another example, according to upper one
The information that business module is sent, operation is abnormal, can not handle semantic information currently entered.For another example, there is route exception, such as
From the coffee-house of HaiXin Building to the KFC of HaiXin Building, together due to beginning and end, just met the requirements without planning,
In this case above-mentioned condition can be also unsatisfactory for.
Further, it after determining whether target route meets the corresponding condition of i-th of candidate's intention, specifically includes following
Two kinds of situations:
Situation one, however, it is determined that objective result is unsatisfactory for i-th of candidate and is intended to corresponding condition, then selects i+1 candidate
It is intended to be used as query intention；
Situation two, however, it is determined that objective result meets i-th of candidate and is intended to corresponding condition, then exports objective result.
Further, it is intended to be used as query intention if any of N number of candidate intention is candidate, determining objective result is not
Meet the corresponding condition of candidate intention, then exports prompt information；Prompt information is used to that user to be prompted to input the friendship to be checked recommended
Communication breath, so that the traffic information to be checked according to recommendation determines target entity.
Through the foregoing embodiment, it is set in conjunction with user's intention assessment, trip question and answer engine based on Traffic knowledge graphical spectrum technology
Meter, may be implemented following effect: for example, solving operational issue complicated when user's trip, realize that in short identification user is intended to
And provide result；For another example, by taking turns interaction, user is intended to precisely identification more.When user's proposition problem, a function is not supported
When being able to achieve, user is prompted to input missing information.Such as " how to get to is new research and development centre from May Fourth Square to Hisense ", it can prompt to use
Family inputs travel modal；For another example, extensive way to put questions map reasoning.Such as " near what southern road and Ningxia road intersection
KFC ", with according to knowledge mapping reasoning, obtain be Nanjing Road and Ningxia road boundary crossing, then identify in crossroad
KFC near mouthful；For another example, input association identification user is intended to before and after user, then defeated for the place of user query
After the way to put questions for entering " how going ", it can identify route planning of the user from origin-to-destination, be compared to the engine maps such as Baidu,
It can not be intended to before and after association user；For another example, information, Data Integration may be implemented, cover all around user's trip question and answer.
Based on same idea, Fig. 9 illustrates a kind of traffic trip problem inquiry dress provided by the embodiments of the present application
The structural schematic diagram set, as shown in figure 9, the device 900 can be used for executing above-mentioned any one scheme shown in Fig. 4.The device
900 include receiving unit 901 and processing unit 902.
Receiving unit 901, for receiving traffic information to be checked；
Processing unit 902, for identification corresponding query intention of traffic information to be checked；It is retouched according to query intention is corresponding
Information type is stated, corresponding first description information of description information type is extracted from traffic information to be checked；First description information
Including location expression information and relationship description information；It is real that the corresponding starting point of location expression information is searched from Traffic knowledge map
Body；Traffic knowledge map includes each layer entity in transportation network and the connection relationship between entity；Believed according to relationship description
Connection relationship between the entity that breath, point entity and Traffic knowledge map include, determines target entity；Known according to traffic
Know map, play point entity and target entity, infers the corresponding objective result of query intention.
In a kind of optionally embodiment, query intention includes trip mode inquiry；Processing unit is used for: being determined to be checked
Ask the corresponding target trip mode of traffic information；Target transportation network is determined according to target trip mode；According to a point entity, mesh
Entity and target transportation network are marked, the corresponding target route of query intention is inferred.
In a kind of optionally embodiment, the corresponding relationship of Traffic knowledge map also included entity and attribute value；Place
Reason unit is used for: the corresponding relationship of the entity and attribute value that include according to Traffic knowledge map plays point entity and target entity, pushes away
Manage out the attribute value of the corresponding target entity of query intention.
In a kind of optionally embodiment, processing unit is also used to: being anticipated for each of N number of candidate intention is candidate
Figure determines the corresponding probability for being intended to candidate intention of traffic information to be checked；N is the integer greater than 0；Processing unit is specifically used
In: according to the corresponding N number of probability of the traffic information to be checked determined, determine query intention.
In a kind of optionally embodiment, processing unit is used for: candidate being intended to N number of according to probability from big to small suitable
I-th of candidate intention is determined in sequence arrangement from N number of candidate intention, and as query intention, i is the integer less than N；Processing is single
Member is also used to:
If it is determined that objective result be unsatisfactory for i-th it is candidate be intended to corresponding condition, then select the candidate intention of i+1 as
Query intention；If it is determined that objective result, which meets i-th of candidate, is intended to corresponding condition, then objective result is exported.
In a kind of optionally embodiment, processing unit is specifically used for: being intended to if any of N number of candidate intention is candidate
As query intention, the corresponding condition of candidate intention is not satisfied in determining objective result, then exports prompt information；Prompt information
The traffic information to be checked recommended for prompting user to input, so as to determine target reality according to the traffic information to be checked of recommendation
Body.
In a kind of optionally embodiment, processing unit is specifically used for: extract all kinds of traffic informations in transportation network,
And the incidence relation between all kinds of traffic informations；Using the corresponding entity of all kinds of traffic informations as node, with any
Incidence relation between two class traffic informations is side, constructs the Traffic knowledge map.
In a kind of optionally embodiment, all kinds of traffic informations include any one of the following contents or multinomial:
Traffic network, transport node, point of interest, regional network, multidate information.
It should be understood that the division of above each unit is only a kind of division of logic function, it in actual implementation can be whole
Or be partially integrated on a physical entity, it can also be physically separate.In the embodiment of the present application, receiving unit 901 and processing
Unit 902 can be realized by the processor 1002 in following Figure 10.
Based on same idea, Figure 10 illustrates another traffic trip problem inquiry provided by the embodiments of the present application
The structural schematic diagram of device, as shown in Figure 10, device 1000 can be used for executing above-mentioned any one scheme shown in Fig. 4.Device
1000 include memory 1001 and processor 1002.
Memory 1001 may include volatile memory (volatile memory), such as random access memory
(random-access memory, RAM)；Memory also may include nonvolatile memory (non-volatile
), such as flash memory (flash memory), hard disk (hard disk drive, HDD) or solid state hard disk memory
(solid-state drive, SSD)；Memory 1001 can also include the combination of the memory of mentioned kind.
Processor 1002 can be central processing unit (central processing unit, CPU), network processing unit
The combination of (network processor, NP) or CPU and NP.Processor 1002 can further include hardware chip.On
Stating hardware chip can be specific integrated circuit (application-specific integrated circuit, ASIC), can
Programmed logic device (programmable logic device, PLD) or combinations thereof.Above-mentioned PLD can be complex programmable and patrol
It collects device (complex programmable logic device, CPLD), field programmable gate array (field-
Programmable gate array, FPGA), Universal Array Logic (generic array logic, GAL) or its any group
It closes.Optionally, together with above-mentioned memory 1001 also can integrate with processor 1002.
Optionally, memory 1001 can be used for storing program instruction, and processor 1002 calls to be deposited in the memory 1001
The instruction of storage, can execute one or more steps in embodiment shown in above scheme (method as shown in Figure 4) or its
In optional embodiment so that device 1000 realize the above method in traffic trip problem inquiry unit function.
Processor 1002, for executing the instruction of the memory storage, when the processor 1002 executes the storage
When the instruction of device storage, so that described device 1000 executes following operation: receiving traffic information to be checked；It identifies described to be checked
The corresponding query intention of traffic information；According to the corresponding description information type of the query intention, from traffic information to be checked
Extract corresponding first description information of the description information type；First description information includes location expression information and relationship
Description information；From searched in Traffic knowledge map the location expression information it is corresponding point entity；The Traffic knowledge map
Including each layer entity in transportation network and the connection relationship between entity；It is real according to the relationship description information, the starting point
Connection relationship between the entity that body and the Traffic knowledge map include, determines target entity；According to the Traffic knowledge
Map, described point entity and the target entity, infer the corresponding objective result of the query intention.
In a kind of optionally embodiment, the query intention includes trip mode inquiry；The processor 1002, tool
Body is used for so that described device executes following operation: determining the corresponding target trip mode of the traffic information to be checked；According to
The target trip mode determines target transportation network；It is handed over according to described point entity, the target entity and the target
Open network infers the corresponding target route of the query intention.
In a kind of optionally embodiment, the also included entity of Traffic knowledge map is corresponding with attribute value to be closed
System；The processor 1002 is specifically used for so that described device executes following operation: including according to the Traffic knowledge map
The corresponding relationship of entity and attribute value, described point entity and the target entity infer the corresponding institute of the query intention
State the attribute value of target entity.
In a kind of optionally embodiment, the processor 1002 is also used to so that described device executes following operation:
It is intended to for each of N number of candidate intention is candidate, determines that the traffic information to be checked is corresponding and be intended to the candidate meaning
The probability of figure；The N is the integer greater than 0；According to the corresponding N number of probability of the traffic information to be checked determined, determine
The query intention out.
In a kind of optionally embodiment, processor 1002 is specifically used for so that device executes following operation: will be N number of
Candidate is intended to arrange according to probability sequence from big to small, from it is N number of it is candidate be intended in determine i-th it is candidate be intended to, as looking into
It askes and is intended to, i is the integer less than N；According to Traffic knowledge map, point entity and target entity, query intention pair is inferred
After the objective result answered, however, it is determined that objective result is unsatisfactory for i-th of candidate and is intended to corresponding condition, then i+1 is selected to wait
Choosing is intended to be used as query intention；If it is determined that objective result, which meets i-th, candidate is intended to corresponding condition, it is determined that the first route is
Objective result.
In a kind of optionally embodiment, the processor 1002 is also used to so that described device executes following operation:
It is intended to be used as the query intention if any of N number of candidate intention is candidate, determining objective result is not satisfied described
Candidate is intended to corresponding condition, then exports prompt information；The prompt information is used to that user to be prompted to input the friendship to be checked recommended
Communication breath, so that the traffic information to be checked according to the recommendation determines the target entity.
In a kind of optionally embodiment, the processor 1002 is also used to so that described device executes following operation:
Extract the incidence relation between all kinds of traffic informations and all kinds of traffic informations in transportation network；With all kinds of friendships
It is node, using the incidence relation between any two classes traffic information as side that communication, which ceases corresponding entity, constructs the Traffic knowledge
Map.
In a kind of optionally embodiment, all kinds of traffic informations include any one of the following contents or multinomial:
Traffic network, transport node, point of interest, regional network, multidate information.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
Now, it when being realized using software program, can entirely or partly realize in the form of a computer program product.The computer
Program product includes one or more instructions.When loading on computers and executing the computer program instructions, whole or portion
Ground is divided to generate according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated computing
Machine, computer network or other programmable devices.Described instruction can store in computer storage medium, or from one
A computer storage medium is transmitted to another computer storage medium, for example, described instruction can be from a web-site, meter
Calculation machine, server or data center are (such as red by wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless
Outside, wirelessly, microwave etc.) mode transmitted to another web-site, computer, server or data center.The calculating
Machine storage medium can be any usable medium that computer can access or include that one or more usable mediums are integrated
The data storage devices such as server, data center.The usable medium can be magnetic medium, (for example, floppy disk, hard disk, magnetic
Band, magneto-optic disk (MO) etc.), optical medium (for example, CD, DVD, BD, HVD etc.) or semiconductor medium (such as ROM, EPROM,
EEPROM, nonvolatile memory (NAND FLASH), solid state hard disk (Solid State Disk, SSD)) etc..
The embodiment of the present application is referring to the method, equipment (system) and computer program product according to the embodiment of the present application
Flowchart and/or the block diagram describe.It should be understood that can be by each process in instruction implementation flow chart and/or block diagram
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.These instructions be can provide to general meter
Calculation machine, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate a machine, make
It obtains and is generated by the instruction that computer or the processor of other programmable data processing devices execute for realizing in flow chart one
The device for the function of being specified in a process or multiple processes and/or one or more blocks of the block diagram.
These instructions also can be loaded onto a computer or other programmable data processing device so that computer or other
Series of operation steps are executed on programmable device to generate computer implemented processing, thus in computer or other are programmable
The instruction that executes in equipment is provided for realizing in one box of one or more flows of the flowchart and/or block diagram or more
The step of function of being specified in a box.
Obviously, those skilled in the art can carry out various modification and variations without departing from this Shen to the embodiment of the present application
Spirit and scope please.In this way, if these modifications and variations of the embodiment of the present application belong to the claim of this application and its wait
Within the scope of technology, then the application is also intended to include these modifications and variations.
Claims (10)
1. a kind of traffic trip problem querying method characterized by comprising
Receive traffic information to be checked；
Identify the corresponding query intention of the traffic information to be checked；
According to the corresponding description information type of the query intention, the description information type is extracted from traffic information to be checked
Corresponding first description information；First description information includes location expression information and relationship description information；
From searched in Traffic knowledge map the location expression information it is corresponding point entity；The Traffic knowledge map includes handing over
Each layer entity in open network and the connection relationship between entity；
Connection between the entity for including according to the relationship description information, described point entity and the Traffic knowledge map
Relationship determines target entity；
According to the Traffic knowledge map, described point entity and the target entity, it is corresponding to infer the query intention
Objective result.
2. the method as described in claim 1, which is characterized in that the query intention includes trip mode inquiry；
It is described according to the Traffic knowledge map, described point entity and the target entity, infer the query intention pair
The objective result answered, comprising:
Determine the corresponding target trip mode of the traffic information to be checked；
Target transportation network is determined according to the target trip mode；
According to described point entity, the target entity and the target transportation network, it is corresponding to infer the query intention
Target route.
3. the method as described in claim 1, which is characterized in that the also included entity of the Traffic knowledge map and attribute value
Corresponding relationship；
It is described according to the Traffic knowledge map, described point entity and the target entity, infer the query intention pair
The objective result answered, comprising:
According to corresponding relationship, described point entity and the target reality of entity and attribute value that the Traffic knowledge map includes
Body infers the attribute value of the corresponding target entity of the query intention.
4. method as claimed in any one of claims 1-3, which is characterized in that the identification traffic information pair to be checked
Before the query intention answered, further includes:
It is intended to for each of N number of candidate intention is candidate, determines that the traffic information to be checked is corresponding and be intended to the time
Select the probability being intended to；The N is the integer greater than 0；
It is described to identify the corresponding query intention of the traffic information to be checked, comprising:
According to the corresponding N number of probability of the traffic information to be checked determined, the query intention is determined.
5. method as claimed in claim 4, which is characterized in that the traffic information to be checked that the basis is determined is corresponding
N number of probability, determine the query intention, comprising:
By N number of candidate sequence arrangement being intended to according to probability from big to small, i-th is determined from N number of candidate intention
A candidate intention, as the query intention, the i is the integer less than the N；
It is described according to the Traffic knowledge map, described point entity and the target entity, infer the query intention pair
After the objective result answered, further includes:
If it is determined that the objective result, which is unsatisfactory for i-th of candidate, is intended to corresponding condition, then select i+1 is candidate to be intended to
As the query intention；
If it is determined that the objective result, which meets i-th of candidate, is intended to corresponding condition, then the objective result is exported.
6. method as claimed in claim 5, which is characterized in that further include:
It is intended to be used as the query intention if any of N number of candidate intention is candidate, determining objective result is not satisfied
The candidate is intended to corresponding condition, then exports prompt information；The prompt information is used to that user to be prompted to input the to be checked of recommendation
Traffic information is ask, so that the traffic information to be checked according to the recommendation determines the target entity.
7. as the method according to claim 1 to 6, which is characterized in that the Traffic knowledge map is constructed by following manner
It obtains:
Extract the incidence relation between all kinds of traffic informations and all kinds of traffic informations in transportation network；
Using the corresponding entity of all kinds of traffic informations as node, using the incidence relation between any two classes traffic information as side,
Construct the Traffic knowledge map.
8. the method for claim 7, which is characterized in that all kinds of traffic informations include any one of the following contents
Or it is multinomial:
Traffic network, transport node, point of interest, regional network, multidate information.
9. a kind of traffic trip problem inquiry unit, which is characterized in that including memory and processor；
The memory is for storing instruction；
The processor is used to execute the instruction of the memory storage, when the processor executes the finger of the memory storage
When enabling, so that described device executes the method according to claim 1.
10. a kind of computer storage medium, which is characterized in that instruction is stored in the computer storage medium, when it is being counted
When being run on calculation machine, so that the computer executes the method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192761.4A CN110008413B (en) | 2019-03-14 | 2019-03-14 | Traffic travel problem query method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192761.4A CN110008413B (en) | 2019-03-14 | 2019-03-14 | Traffic travel problem query method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008413A true CN110008413A (en) | 2019-07-12 |
| CN110008413B CN110008413B (en) | 2023-11-10 |
Family
ID=67167047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910192761.4A Active CN110008413B (en) | 2019-03-14 | 2019-03-14 | Traffic travel problem query method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008413B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413886A (en) * | 2019-07-17 | 2019-11-05 | 海信集团有限公司 | A kind of point of interest methods of exhibiting and device |
| CN110609903A (en) * | 2019-08-01 | 2019-12-24 | 华为技术有限公司 | Information presentation method and device |
| CN110674371A (en) * | 2019-09-24 | 2020-01-10 | Oppo广东移动通信有限公司 | Bus information query method and device, electronic equipment and storage medium |
| CN110799973A (en) * | 2019-09-27 | 2020-02-14 | 京东方科技集团股份有限公司 | Information query method and display device |
| CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
| CN111198933A (en) * | 2020-01-03 | 2020-05-26 | 北京明略软件***有限公司 | Method, device, electronic device and storage medium for searching target entity |
| CN111538815A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Text query method, device, equipment and storage medium |
| CN112416984A (en) * | 2019-08-21 | 2021-02-26 | 华为技术有限公司 | Data processing method and device |
| CN112685544A (en) * | 2020-12-25 | 2021-04-20 | 中国联合网络通信集团有限公司 | Telecommunication information query method, device, equipment and medium |
| CN112818071A (en) * | 2021-02-09 | 2021-05-18 | 青岛海信网络科技股份有限公司 | Traffic management field knowledge graph construction method and device based on unified road network |
| CN115344707A (en) * | 2022-08-01 | 2022-11-15 | 南京航空航天大学 | Urban traffic knowledge map construction method |
| US20230306321A1 (en) * | 2022-03-24 | 2023-09-28 | Chengdu Qinchuan Iot Technology Co., Ltd. | Systems and methods for managing public place in smart city |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407333A (en) * | 2016-09-05 | 2017-02-15 | 北京百度网讯科技有限公司 | Artificial intelligence-based spoken language query identification method and apparatus |
| CN107358315A (en) * | 2017-06-26 | 2017-11-17 | 深圳市金立通信设备有限公司 | A kind of information forecasting method and terminal |
| CN107451230A (en) * | 2017-07-24 | 2017-12-08 | 宗晖（上海）机器人有限公司 | A kind of answering method and question answering system |
| WO2018006469A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Knowledge graph-based human-robot interaction method and system |
| CN107832414A (en) * | 2017-11-07 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108509563A (en) * | 2018-03-23 | 2018-09-07 | 深圳狗尾草智能科技有限公司 | Robot reasoning association method, device, equipment and the medium of knowledge based collection of illustrative plates |
| CN108664472A (en) * | 2018-05-08 | 2018-10-16 | 腾讯科技（深圳）有限公司 | Natural language processing method, apparatus and its equipment |
| CN109002516A (en) * | 2018-07-06 | 2018-12-14 | 国网电子商务有限公司 | A kind of searching method and device |
| CN109033063A (en) * | 2017-06-09 | 2018-12-18 | 微软技术许可有限责任公司 | The machine inference of knowledge based map |
| CN109213844A (en) * | 2018-08-13 | 2019-01-15 | 腾讯科技（深圳）有限公司 | A kind of text handling method, device and relevant device |
| CN109271504A (en) * | 2018-11-07 | 2019-01-25 | 爱因互动科技发展（北京）有限公司 | The method of the reasoning dialogue of knowledge based map |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
-
2019
- 2019-03-14 CN CN201910192761.4A patent/CN110008413B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018006469A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Knowledge graph-based human-robot interaction method and system |
| CN106407333A (en) * | 2016-09-05 | 2017-02-15 | 北京百度网讯科技有限公司 | Artificial intelligence-based spoken language query identification method and apparatus |
| CN109033063A (en) * | 2017-06-09 | 2018-12-18 | 微软技术许可有限责任公司 | The machine inference of knowledge based map |
| CN107358315A (en) * | 2017-06-26 | 2017-11-17 | 深圳市金立通信设备有限公司 | A kind of information forecasting method and terminal |
| CN107451230A (en) * | 2017-07-24 | 2017-12-08 | 宗晖（上海）机器人有限公司 | A kind of answering method and question answering system |
| CN107832414A (en) * | 2017-11-07 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108509563A (en) * | 2018-03-23 | 2018-09-07 | 深圳狗尾草智能科技有限公司 | Robot reasoning association method, device, equipment and the medium of knowledge based collection of illustrative plates |
| CN108664472A (en) * | 2018-05-08 | 2018-10-16 | 腾讯科技（深圳）有限公司 | Natural language processing method, apparatus and its equipment |
| CN109002516A (en) * | 2018-07-06 | 2018-12-14 | 国网电子商务有限公司 | A kind of searching method and device |
| CN109213844A (en) * | 2018-08-13 | 2019-01-15 | 腾讯科技（深圳）有限公司 | A kind of text handling method, device and relevant device |
| CN109271504A (en) * | 2018-11-07 | 2019-01-25 | 爱因互动科技发展（北京）有限公司 | The method of the reasoning dialogue of knowledge based map |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413886A (en) * | 2019-07-17 | 2019-11-05 | 海信集团有限公司 | A kind of point of interest methods of exhibiting and device |
| CN110609903A (en) * | 2019-08-01 | 2019-12-24 | 华为技术有限公司 | Information presentation method and device |
| CN110609903B (en) * | 2019-08-01 | 2022-11-11 | 华为技术有限公司 | Information presentation method and device |
| CN112416984B (en) * | 2019-08-21 | 2024-06-04 | 华为技术有限公司 | Data processing method and device |
| CN112416984A (en) * | 2019-08-21 | 2021-02-26 | 华为技术有限公司 | Data processing method and device |
| CN110674371A (en) * | 2019-09-24 | 2020-01-10 | Oppo广东移动通信有限公司 | Bus information query method and device, electronic equipment and storage medium |
| CN110799973A (en) * | 2019-09-27 | 2020-02-14 | 京东方科技集团股份有限公司 | Information query method and display device |
| CN110799973B (en) * | 2019-09-27 | 2024-04-19 | 京东方科技集团股份有限公司 | Information query method and display device |
| US11782976B2 (en) | 2019-09-27 | 2023-10-10 | Boe Technology Group Co., Ltd. | Method for querying information and display device |
| CN110909159B (en) * | 2019-09-29 | 2022-09-16 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
| CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
| CN111198933A (en) * | 2020-01-03 | 2020-05-26 | 北京明略软件***有限公司 | Method, device, electronic device and storage medium for searching target entity |
| CN111538815B (en) * | 2020-04-27 | 2023-09-22 | 北京百度网讯科技有限公司 | Text query method, device, equipment and storage medium |
| CN111538815A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Text query method, device, equipment and storage medium |
| CN112685544A (en) * | 2020-12-25 | 2021-04-20 | 中国联合网络通信集团有限公司 | Telecommunication information query method, device, equipment and medium |
| CN112818071A (en) * | 2021-02-09 | 2021-05-18 | 青岛海信网络科技股份有限公司 | Traffic management field knowledge graph construction method and device based on unified road network |
| US20230306321A1 (en) * | 2022-03-24 | 2023-09-28 | Chengdu Qinchuan Iot Technology Co., Ltd. | Systems and methods for managing public place in smart city |
| US11868926B2 (en) * | 2022-03-24 | 2024-01-09 | Chengdu Qinchuan Iot Technology Co., Ltd. | Systems and methods for managing public place in smart city |
| CN115344707A (en) * | 2022-08-01 | 2022-11-15 | 南京航空航天大学 | Urban traffic knowledge map construction method |
| CN115344707B (en) * | 2022-08-01 | 2023-10-24 | 南京航空航天大学 | Urban traffic knowledge graph construction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008413B (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008413A (en) | A kind of traffic trip problem querying method and device | |
| US11663378B2 (en) | Method, apparatus, and system for providing traffic simulations in a smart-city infrastructure | |
| JP6637054B2 (en) | Method and system for providing on-demand service information | |
| EP3410348A1 (en) | Method and apparatus for building a parking occupancy model | |
| EP3293489A1 (en) | Method and apparatus for providing trajectory bundles for map data analysis | |
| CN112133090A (en) | Multi-mode traffic distribution model construction method based on mobile phone signaling data | |
| Chang et al. | A vanet-based a* route planning algorithm for travelling time-and energy-efficient gps navigation app | |
| US11663912B2 (en) | Method, apparatus, and system for automatic road closure detection | |
| CN109754594A (en) | A kind of road condition information acquisition method and its equipment, storage medium, terminal | |
| CN112447041B (en) | Method and device for identifying operation behavior of vehicle and computing equipment | |
| CN106875670A (en) | Taxi concocting method based on gps data under Spark platforms | |
| US20200167575A1 (en) | Method and system of a machine learning model for detection of physical dividers | |
| Lv et al. | Outlier trajectory detection: A trajectory analytics based approach | |
| CN104025075A (en) | Method and system for fleet navigation, dispatching and multi-vehicle, multi-destination routing | |
| US20220179882A1 (en) | Method, apparatus, and system for combining location data sources | |
| CN110413886A (en) | A kind of point of interest methods of exhibiting and device | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| US20200334246A1 (en) | Information processing device, combination condition generation method, and combination condition generation program | |
| CN107389085A (en) | A kind of determination method, apparatus, computer and the storage medium of road attribute | |
| US10497256B1 (en) | Method, apparatus, and system for automatic evaluation of road closure reports | |
| CN109859505B (en) | Early warning processing method, device, server and medium for high-speed station | |
| US20200200543A1 (en) | Method, apparatus, and system for providing road closure graph inconsistency resolution | |
| Chen et al. | An analysis of movement patterns between zones using taxi GPS data | |
| Bin et al. | A heuristic algorithm based on leaf photosynthate transport | |
| Ermagun et al. | Multiple-drones-multiple-trucks routing problem for disruption assessment |
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 |