CN112710323B - Vehicle navigation method and device - Google Patents
Vehicle navigation method and device Download PDFInfo
- Publication number
- CN112710323B CN112710323B CN202011541372.7A CN202011541372A CN112710323B CN 112710323 B CN112710323 B CN 112710323B CN 202011541372 A CN202011541372 A CN 202011541372A CN 112710323 B CN112710323 B CN 112710323B
- Authority
- CN
- China
- Prior art keywords
- route
- information
- target
- determining
- selection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 22
- 230000006399 behavior Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 12
- 238000010187 selection method Methods 0.000 claims 1
- 238000012790 confirmation Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000003993 interaction Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013145 classification model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The embodiment of the invention provides a vehicle navigation method and device, wherein the method comprises the following steps: upon detection of a navigation event, determining a plurality of candidate route information for the navigation event; judging whether to automatically select a route for the navigation event; and when the automatic route selection of the navigation event is judged, determining target route information from the plurality of candidate route information, and performing navigation by adopting the target route information. According to the embodiment of the invention, the automatic selection of the navigation route is realized, and the target route information is determined from the plurality of candidate route information when the automatic selection of the route is judged to be carried out, so that the navigation is carried out, the route selection is more efficient and intelligent, the password confirmation link is reduced for a user, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a vehicle navigation method and device.
Background
At present, aiming at route selection of a route calculation result in navigation, the following experience problems exist: after confirming the destination of the user navigation, the user needs to enter a road calculation process, and the user needs to confirm the selection result for navigation every time aiming at the returned road calculation result, so that the user experience is affected.
Disclosure of Invention
In view of the above, a method and apparatus for vehicle navigation is proposed to overcome or at least partially solve the above problems, comprising:
a method of vehicle navigation, the method comprising:
upon detection of a navigation event, determining a plurality of candidate route information for the navigation event;
judging whether to automatically select a route for the navigation event;
and when the automatic route selection of the navigation event is judged, determining target route information from the plurality of candidate route information, and performing navigation by adopting the target route information.
Optionally, when determining that the navigation event is automatically routed, determining target route information from the plurality of candidate route information includes:
when the automatic route selection of the navigation event is judged, determining a target selection mode;
and determining target route information from the plurality of candidate route information by adopting the target selection mode.
Optionally, when determining that the route is automatically selected for the navigation event, determining a target selection mode includes:
acquiring judgment information;
when the judgment information is detected to be met, determining that the first selection mode is a target selection mode; the first selection mode is a mode of automatically selecting a route according to the judgment information;
when the judgment information is detected to be not satisfied, determining the second selection mode as a target selection mode; the second selection mode is a mode of automatically selecting a route by adopting a pre-trained route selection model.
Optionally, the determining, by using the target selection manner, target route information from the plurality of candidate route information includes:
and when the target selection mode is a second selection mode, adopting a pre-trained route selection model to perform model processing on the plurality of candidate route information, and determining target route information.
Optionally, the method further comprises:
acquiring sample route data and user behavior data for the sample route data;
determining a plurality of feature type information;
and carrying out model training by combining the sample route data, the user behavior data and the plurality of feature type information to obtain a route selection model.
Optionally, the method further comprises:
acquiring navigation feedback information; the navigation feedback information is user feedback information generated in the process of navigating by adopting the target route information;
and carrying out model training on the route selection model according to the navigation feedback information.
Optionally, the plurality of feature type information includes a plurality of:
route tag information, tag frequency information, route attribute information, own vehicle attribute information, history selection information.
An apparatus for vehicle navigation, the apparatus comprising:
a plurality of candidate route information determining modules for determining a plurality of candidate route information for a navigation event when the navigation event is detected;
the automatic route selection judging module is used for judging whether the automatic route selection is carried out on the navigation event or not;
and the target route information determining module is used for determining target route information from the plurality of candidate route information when determining to automatically select the route of the navigation event, and navigating by adopting the target route information.
A vehicle comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor implements a method of in-vehicle navigation as described above.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of car navigation as described above.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, when the navigation event is detected, a plurality of candidate route information aiming at the navigation event is determined, then whether the navigation event is automatically selected is judged, further when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, and navigation is carried out by adopting the target route information, so that the automatic selection of the navigation route is realized, and when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, so as to carry out navigation, the route selection is more efficient and intelligent, the password confirmation link is reduced for a user, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for vehicle navigation according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of another method for vehicle navigation according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an example of a vehicle navigation process according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps of another method for vehicle navigation according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a model training process in vehicle navigation according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a vehicle navigation device according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart illustrating steps of a method for vehicle navigation according to an embodiment of the present invention may specifically include the following steps:
step 101, when a navigation event is detected, determining a plurality of candidate route information aiming at the navigation event;
the navigation event may be a voice interaction operation for navigation triggered by a user, for example, the user may send a voice interaction request for navigation through the voice interaction operation, and then the vehicle-mounted system may perform navigation processing according to the voice interaction request.
In a vehicle navigation scene, whether a user triggers a navigation event or not can be detected through the vehicle-mounted system, and then when the navigation event is detected, a plurality of candidate route information aiming at the navigation event can be determined so as to further adopt the plurality of candidate route information to carry out subsequent navigation processing.
In an example, a POI keyword (such as a destination keyword) may be identified by receiving a voice interaction request of a user for navigation, then performing semantic understanding on the voice interaction request, further, destination information for the navigation may be determined from a destination list to be selected by searching for a destination, and a route calculation process may be performed to obtain a route candidate list for the navigation (i.e. a navigation event), where a plurality of candidate route information may be included in the route candidate list.
For example, destination search processing may be performed by a third-party map application, destination information for a navigation event may be determined from a list of destination to be selected, and then a plurality of candidate route information for the navigation event may be acquired by route calculation processing.
102, judging whether to automatically select a route for the navigation event;
after determining the plurality of candidate route information, whether the navigation event is automatically selected for route can be judged to perform subsequent navigation processing, for example, the navigation event can be automatically selected for route by judging through an on-vehicle system.
In an example, whether to automatically select a route for the navigation event may be determined by presetting a determination condition, and then the vehicle-mounted system may determine whether to automatically select a route for the navigation event according to the determination condition, for example, a distance threshold may be set, and when the distance threshold is exceeded, it may be determined that the route for the navigation event is automatically selected, where the distance threshold may be a minimum value (e.g. 1 Km) of a distance from a starting point to a destination of navigation; it may be determined that the route is not automatically selected for the navigation event when it is detected that the route calculation process is performed twice in succession for the same destination.
And step 103, when determining that the route of the navigation event is automatically selected, determining target route information from the plurality of candidate route information, and performing navigation by adopting the target route information.
In a specific implementation, when the route automatic selection of the navigation event is determined, the target route information can be determined from a plurality of candidate route information, and then the navigation can be performed by adopting the target route information, for example, in the process of performing the route automatic selection of the navigation event, the target route information can be obtained by a mode of determining through preset self-defining information, and the intelligent route selection can also be performed by adopting model processing so as to automatically select the target route information.
In an example, by adopting the vehicle-mounted system to judge whether to automatically select a route for a navigation event, and automatically screening target route information from a plurality of candidate route information when judging to automatically select the route, the optimal route automatic selection of vehicle-mounted navigation can be performed, and a more efficient and intelligent route selection effect is achieved.
In the embodiment of the invention, when the navigation event is detected, a plurality of candidate route information aiming at the navigation event is determined, then whether the navigation event is automatically selected is judged, further when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, and navigation is carried out by adopting the target route information, so that the automatic selection of the navigation route is realized, and when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, so as to carry out navigation, the route selection is more efficient and intelligent, the password confirmation link is reduced for a user, and the user experience is improved.
Referring to fig. 2, a flowchart illustrating steps of another method for vehicle navigation according to an embodiment of the present invention may specifically include the following steps:
step 201, when a navigation event is detected, determining a plurality of candidate route information for the navigation event;
step 202, judging whether to automatically select a route for the navigation event;
step 203, determining a target selection mode when determining to automatically select a route for the navigation event;
in a specific implementation, when the route automatic selection of the navigation event is determined, the target selection mode is determined to further determine the target route information by adopting the target selection mode, for example, in the process of automatically selecting the route of the navigation event, the target route information can be obtained by presetting a mode of determining the user-defined information, and the route intelligent selection can also be performed by adopting model processing to automatically select the target route information.
In an embodiment of the present invention, step 203 may include the following sub-steps:
step 11, obtaining judgment information;
in practical applications, the determination information may be preset custom information, such as custom rules or policies, which may be used for automatic route selection processing based on the determination information.
A sub-step 12 of determining that the first selection mode is a target selection mode when the satisfaction of the judgment information is detected; the first selection mode is a mode of automatically selecting a route according to the judgment information;
in a specific implementation, when the satisfaction of the judgment information is detected, the first selection mode may be determined as a target selection mode, and the first selection mode may be a mode of automatically selecting a route according to the judgment information, for example, the route may be automatically selected (i.e., the first selection mode) based on a custom rule or a policy, and then, when the policy is hit, the target route information may be automatically selected from a plurality of candidate route information.
In an example, a threshold may be preset for the time difference between candidate routes as a custom rule, and automatic route selection may be performed based on the custom rule, for example, when three candidate routes exist in the candidate route list, if the total time consumed by route 2 is 20 minutes greater than the total time consumed by route 3, route 1 may be used as the automatic route for this navigation; other judgment information can be preset, and the invention is not limited to this.
A sub-step 13 of determining the second selection mode as a target selection mode when the judgment information is detected to be not satisfied; the second selection mode is a mode of automatically selecting a route by adopting a pre-trained route selection model.
In a specific implementation, when the unsatisfied judgment information is detected, the second selection mode may be determined as a target selection mode, where the second selection mode may be a mode of performing route automatic selection by using a pre-trained route selection model, for example, in a process of performing route automatic selection based on a custom rule or policy, in a case of missing the policy, the target route information may be automatically selected from multiple candidate route information by using the pre-trained route selection model.
And 204, determining target route information from the plurality of candidate route information by adopting the target selection mode, and navigating by adopting the target route information.
After determining the target selection mode, the target selection mode may be adopted to determine target route information from a plurality of candidate route information, and then the target route information may be adopted to perform navigation, for example, in a process of performing route automatic selection on a navigation event, intelligent route selection may be performed through the first selection mode or the second selection mode, so as to automatically select the target route information.
In an example, as shown in fig. 3, a voice interaction request (query) of a user for navigation may be received, then the voice interaction request may be subjected to semantic understanding, a POI keyword (such as a destination keyword) may be identified, destination information for the navigation may be determined from a destination list to be selected by searching for a destination, a route calculation process may be performed to obtain a route candidate list for the navigation (i.e. a navigation event), for example, the route candidate list may include three candidate routes (i.e. a plurality of candidate route information), whether route automatic selection is performed may be determined by an on-board system, in a case that route automatic selection is determined, automatic selection (i.e. a first selection manner) may be performed based on a custom rule to obtain a target route (i.e. target route information), and in a case of a miss policy, automatic selection (i.e. a second selection manner) may be performed through a classification model (i.e. a route selection model) to obtain a target route, so as to start navigation according to the target route.
In yet another example, a route list may be displayed for the user in the event that the in-vehicle system determines that automatic route selection is not performed, to navigate according to the user-selected route, or may be displayed for the user as well when automatic selection is not performed for the classification model processing result.
Referring to fig. 4, a flowchart illustrating steps of another method for vehicle navigation according to an embodiment of the present invention may specifically include the following steps:
step 401, acquiring sample route data and user behavior data for the sample route data;
in a specific implementation, for the case of adopting the second selection mode, that is, performing route automatic selection by pre-training a route selection model, model training can be further performed by acquiring sample route data and user behavior data for the sample route data.
In an example, multiple route data (i.e., sample route data) for a specified destination may be acquired through a third party map application, and raw behavior data (i.e., user behavior data) for a user may be acquired through an in-vehicle system, and further subsequent model training may be performed according to the obtained data.
Step 402, determining a plurality of feature type information;
as an example, the plurality of feature type information may include the following:
route tag information, tag frequency information, route attribute information, own vehicle attribute information, history selection information.
In the process of pre-training the model, after the sample route data and the user behavior data for the sample route data are acquired, model training can be performed by determining a plurality of feature type information to extract route features.
Step 403, performing model training by combining the sample route data, the user behavior data and a plurality of feature type information to obtain a route selection model;
in a specific implementation, model training can be performed by combining sample route data, user behavior data and a plurality of feature type information, so that a route selection model can be obtained.
In an example, model training may be performed by way of offline learning, and route features may be extracted as follows:
1. route tag features
The method comprises the steps that a third party map application obtains a plurality of route data and characteristic names of routes for a destination (such as not going high speed, giving priority to a large route and the like), a characteristic group can be extracted according to the characteristic names, such as marking the characteristic names contained in the routes as 1 and marking the characteristic names not contained as 0, further, the characteristic group can be obtained for each route, the characteristic groups of the plurality of route data of the same destination can be subjected to characteristic splicing to obtain route tag characteristics, the route tag characteristics can be represented in a form of identification-characteristic values, such as ID (identity) can be track_id, session_id, the characteristic values can be characteristics for completing splicing, and the route tag characteristics can be stored, such as storage ID (identity) can be track_id and use_id.
2. Each user selects a tag distribution feature
By acquiring user behavior data of sample route data, for a route selected by a user, a feature group can be extracted according to feature names (such as not going high speed, road priority, etc.), for example, the feature names contained in the route are marked as 1, the feature names not contained in the route are marked as 0, so that tag distribution features of a plurality of routes can be obtained, the total number of times of each tag can be selected according to statistics of the user, the time period setting can be from the first time to the last time of selecting the route according to current navigation, the processed data can be stored through normalization processing of the number of times of selecting the tag according to the user, and for example, the storage ID can be trace_id and use_id.
3. Route attribute feature
By acquiring the user behavior data of the sample route data, for the route selected by the user, features can be extracted according to feature names (such as the number of traffic lights, the total mileage and the like), so that route attribute feature sets corresponding to a plurality of routes can be obtained and stored, and if the storage ID can be trace_id.
4. Self-propelled feature
By acquiring user behavior data of sample route data, for a route selected by a user, features can be extracted according to feature names (such as residual electric quantity, whether a weekend is or not, and the like), so that a self-vehicle feature set can be obtained, and storage can be performed, for example, a storage ID (identity) can be trace_id and use_id.
5. Current destination history selection tag feature
By acquiring user behavior data of sample route data, for a route selected by a user, a feature group can be extracted according to feature names (such as not going high speed, road priority, etc.), for example, the feature names contained in the route are marked as 1, the non-contained feature names are marked as 0, so that history selection tag features of a current destination can be obtained, the total number of times of selecting each tag can be counted according to the user and the destination, the time period setting can be from the first time to the last time of navigating the selected route, the processed data can be stored through normalization processing of the number of times of selecting the tags, for example, the storage ID can be trace_id, use_id and poi_id.
In yet another example, the offline training model (i.e., the routing model) may be performed in the following manner:
1. extracting relevant route characteristics, such as route label characteristics, each user selection label distribution characteristics, route attribute characteristics, vehicle characteristics, current destination historical selection label characteristics and classification standard answers set for the user selection routes, such as classification scheme numbers 1,2 and 3;
2. feature stitching can be performed on the extracted route features and the classification standard answers;
3. the training set/test set may be segmented;
4. through the LigthBGM training model, a classification model file can be obtained, and then the offline training model is completed.
For example, the LigthBGM training model is adopted, and can be based on the gradient lifting tree (GBDT) principle and a histogram algorithm, so that the training model is fast in speed, high in accuracy, capable of processing large-scale data, supporting category attributes and further capable of being interpreted.
Step 404, when a navigation event is detected, determining a plurality of candidate route information for the navigation event;
step 405, judging whether to automatically select a route for the navigation event;
step 406, determining a target selection mode when determining to automatically select a route for the navigation event;
and step 407, when the target selection mode is the second selection mode, performing model processing on the plurality of candidate route information by adopting a pre-trained route selection model, determining target route information, and performing navigation by adopting the target route information.
In practical application, in the process of automatically selecting the route through the second selection mode, a pre-trained route selection model can be adopted to perform model processing on a plurality of candidate route information, so that target route information can be determined, and navigation is performed by adopting the target route information.
In an example, for a plurality of candidate route information, a route selection model may be used, and the score may be calculated by selecting a feature and combining the plurality of selected features, such as a route tag feature, a user selected tag distribution feature, a route attribute feature, a scheme number distribution feature of current destination history selection, and the like, so that the target route information, such as a route with a highest score, may be determined from the plurality of candidate route information according to the feature score as the target route information.
For example, based on the gradient boost tree (GBDT) principle, features may be selected from a plurality of candidate route information and feature scores may be calculated, and then, based on the result of the feature score calculation, target route information may be determined, for example, f (route 1) =2+0.9=2.9, f (route 2) = -1-0.9 = -1.9, f (route 3) = xx, (not automatically selected) = xx, and then route 1 may be used as the target route information.
In yet another example, as shown in fig. 5, the model is trained by means of offline learning, so that sample route data and user behavior data for the sample route data can be obtained, then offline training data or offline test data can be performed by extracting route features to obtain a pre-trained route selection model, further, a received voice interaction request (query) of a user for navigation can be further obtained, and in the case that route automatic selection is determined to be performed, route intelligent selection can be performed through the pre-trained route selection model, so that target route information to be navigated can be obtained, and thus, by using multi-feature model training, such as adding route labels of map operators, traffic information in routes, and information personalized by the user, the intelligentization degree of route selection is enhanced.
In an embodiment of the present invention, the method may further include the following steps:
acquiring navigation feedback information; the navigation feedback information is user feedback information generated in the process of navigating by adopting the target route information; and carrying out model training on the route selection model according to the navigation feedback information.
In practical application, after route automatic selection is performed on a navigation event, navigation feedback information can be acquired, the navigation feedback information can be user feedback information generated in the process of navigating by adopting target route information, and further model training can be performed on a route selection model according to the navigation feedback information, so that the route selection model can be continuously trained, the user behavior can be further confirmed through the target route information obtained through the route automatic selection, for example, the driving condition of the user in the navigation process can be added into the model training, and the route automatic selection is more efficient and intelligent.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Referring to fig. 6, a schematic structural diagram of a vehicle navigation device according to an embodiment of the present invention may specifically include the following modules:
a plurality of candidate route information determining modules 601 for determining a plurality of candidate route information for a navigation event when the navigation event is detected;
a route automatic selection judging module 602, configured to judge whether to automatically select a route for the navigation event;
the target route information determining module 603 is configured to determine target route information from the plurality of candidate route information when determining to automatically select a route for the navigation event, and navigate using the target route information.
In an embodiment of the present invention, the target route information determining module 603 includes:
the target selection mode determining submodule is used for determining a target selection mode when determining that the route of the navigation event is automatically selected;
and the target route information determining sub-module is used for determining target route information from the plurality of candidate route information by adopting the target selection mode.
In an embodiment of the present invention, the target selection mode determining submodule includes:
a judgment information acquisition unit configured to acquire judgment information;
the first selection mode determining unit is used for determining that the first selection mode is a target selection mode when the judgment information is detected to be met; the first selection mode is a mode of automatically selecting a route according to the judgment information;
a second selection mode determining unit configured to determine that the second selection mode is a target selection mode when the judgment information is detected to be not satisfied; the second selection mode is a mode of automatically selecting a route by adopting a pre-trained route selection model.
In an embodiment of the present invention, the target route information determining submodule includes:
and the target route information determining unit is used for performing model processing on the plurality of candidate route information by adopting a pre-trained route selection model when the target selection mode is the second selection mode, and determining target route information.
In an embodiment of the present invention, further includes:
the data acquisition module is used for acquiring sample route data and user behavior data aiming at the sample route data;
a plurality of feature type information determining modules for determining a plurality of feature type information;
and the route selection model obtaining module is used for carrying out model training by combining the sample route data, the user behavior data and the plurality of characteristic type information to obtain a route selection model.
In an embodiment of the present invention, further includes:
the navigation feedback information acquisition module is used for acquiring navigation feedback information; the navigation feedback information is user feedback information generated in the process of navigating by adopting the target route information;
and the model training module is used for carrying out model training on the route selection model according to the navigation feedback information.
In an embodiment of the present invention, the plurality of feature type information includes:
route tag information, tag frequency information, route attribute information, own vehicle attribute information, history selection information.
In the embodiment of the invention, when the navigation event is detected, a plurality of candidate route information aiming at the navigation event is determined, then whether the navigation event is automatically selected is judged, further when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, and navigation is carried out by adopting the target route information, so that the automatic selection of the navigation route is realized, and when the navigation event is automatically selected, the target route information is determined from the plurality of candidate route information, so as to carry out navigation, the route selection is more efficient and intelligent, the password confirmation link is reduced for a user, and the user experience is improved.
An embodiment of the present invention also provides a vehicle that may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program implementing the method of on-board navigation as described above when executed by the processor.
An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements a method for vehicle navigation as above.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above description of a method and apparatus for vehicle navigation provided in detail, specific examples are applied to illustrate the principles and embodiments of the present invention, and the above examples are only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (6)
1. A method of vehicle navigation, the method comprising:
upon detection of a navigation event, determining a plurality of candidate route information for the navigation event;
judging whether to automatically select a route for the navigation event;
when the automatic route selection of the navigation event is judged, determining a target selection mode; determining target route information from the plurality of candidate route information by adopting the target selection mode, and navigating by adopting the target route information;
when determining that the route of the navigation event is automatically selected, determining a target selection mode comprises the following steps:
acquiring judgment information;
when the judgment information is detected to be met, determining that the first selection mode is a target selection mode; the first selection mode is a mode of automatically selecting a route according to the judgment information;
when the judgment information is detected to be not satisfied, determining the second selection mode as a target selection mode; the second selection mode is a mode of automatically selecting a route by adopting a pre-trained route selection model;
wherein the determining, by using the target selection method, target route information from the plurality of candidate route information includes:
when the target selection mode is a second selection mode, a pre-trained route selection model is adopted to perform model processing on the plurality of candidate route information, and target route information is determined;
acquiring sample route data and user behavior data for the sample route data;
determining a plurality of feature type information;
and carrying out model training by combining the sample route data, the user behavior data and the plurality of feature type information to obtain a route selection model.
2. The method as recited in claim 1, further comprising:
acquiring navigation feedback information; the navigation feedback information is user feedback information generated in the process of navigating by adopting the target route information;
and carrying out model training on the route selection model according to the navigation feedback information.
3. The method of claim 1, wherein the plurality of feature type information comprises a plurality of:
route tag information, tag frequency information, route attribute information, own vehicle attribute information, history selection information.
4. A vehicle navigation device, the device comprising:
a plurality of candidate route information determining modules for determining a plurality of candidate route information for a navigation event when the navigation event is detected;
the automatic route selection judging module is used for judging whether the automatic route selection is carried out on the navigation event or not;
the target route information determining module is used for determining target route information from the plurality of candidate route information when determining that the navigation event is automatically selected in a route, and navigating by adopting the target route information;
wherein the target route information determining module includes:
the target selection mode determining submodule is used for determining a target selection mode when determining that the route of the navigation event is automatically selected;
a target route information determining sub-module, configured to determine target route information from the plurality of candidate route information by using the target selection manner;
wherein, the target selection mode determining submodule comprises:
a judgment information acquisition unit configured to acquire judgment information;
the first selection mode determining unit is used for determining that the first selection mode is a target selection mode when the judgment information is detected to be met; the first selection mode is a mode of automatically selecting a route according to the judgment information;
a second selection mode determining unit configured to determine that the second selection mode is a target selection mode when the judgment information is detected to be not satisfied; the second selection mode is a mode of automatically selecting a route by adopting a pre-trained route selection model;
wherein the target route information determination submodule further includes:
the target route information determining unit is used for performing model processing on the plurality of candidate route information by adopting a pre-trained route selection model when the target selection mode is a second selection mode, and determining target route information;
the data acquisition module is used for acquiring sample route data and user behavior data aiming at the sample route data;
a plurality of feature type information determining modules for determining a plurality of feature type information;
and the route selection model obtaining module is used for carrying out model training by combining the sample route data, the user behavior data and the plurality of characteristic type information to obtain a route selection model.
5. A vehicle comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing a method of on-board navigation as claimed in any one of claims 1 to 3.
6. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements a method of vehicle navigation according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011541372.7A CN112710323B (en) | 2020-12-23 | 2020-12-23 | Vehicle navigation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011541372.7A CN112710323B (en) | 2020-12-23 | 2020-12-23 | Vehicle navigation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112710323A CN112710323A (en) | 2021-04-27 |
| CN112710323B true CN112710323B (en) | 2023-11-03 |
Family
ID=75543748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011541372.7A Active CN112710323B (en) | 2020-12-23 | 2020-12-23 | Vehicle navigation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112710323B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105973255A (en) * | 2016-06-17 | 2016-09-28 | 北京奇虎科技有限公司 | Route recommendation method and terminal |
| WO2017015882A1 (en) * | 2015-07-29 | 2017-02-02 | Bayerische Motoren Werke Aktiengesellschaft | Navigation device and navigation method |
| CN107745711A (en) * | 2017-09-05 | 2018-03-02 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus that route is determined under automatic driving mode |
| CN108182273A (en) * | 2018-01-23 | 2018-06-19 | 成都信达智胜科技有限公司 | Network data processing method based on cloud storage |
| CN108444486A (en) * | 2017-02-16 | 2018-08-24 | 高德信息技术有限公司 | A kind of navigation routine sort method and device |
| CN109115236A (en) * | 2018-07-10 | 2019-01-01 | 上海博泰悦臻电子设备制造有限公司 | Vehicle, vehicle device equipment and its stroke automatic navigation method based on condition triggering |
| CN109154509A (en) * | 2016-05-10 | 2019-01-04 | 微软技术许可有限责任公司 | The user's efficiency improved in route planning using route preferences |
| CN110375760A (en) * | 2019-07-29 | 2019-10-25 | 北京百度网讯科技有限公司 | Route determination method, apparatus, equipment and medium |
| CN110617830A (en) * | 2014-03-04 | 2019-12-27 | 谷歌有限责任公司 | Navigation directions between an automatically determined start point and a selected end point |
| CN110864701A (en) * | 2019-12-17 | 2020-03-06 | 上海博泰悦臻电子设备制造有限公司 | Navigation route recommendation method, vehicle-mounted terminal and computer storage medium |
| CN112050824A (en) * | 2020-09-17 | 2020-12-08 | 北京百度网讯科技有限公司 | Route planning method, device and system for vehicle navigation and electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10895465B2 (en) * | 2017-10-12 | 2021-01-19 | Toyota Jidosha Kabushiki Kaisha | Optimizing a route selection for a highly autonomous vehicle |
| CN108061558A (en) * | 2017-11-30 | 2018-05-22 | 深圳中兴网信科技有限公司 | intelligent route navigation method, device, server, mobile terminal and storage medium |
-
2020
- 2020-12-23 CN CN202011541372.7A patent/CN112710323B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110617830A (en) * | 2014-03-04 | 2019-12-27 | 谷歌有限责任公司 | Navigation directions between an automatically determined start point and a selected end point |
| WO2017015882A1 (en) * | 2015-07-29 | 2017-02-02 | Bayerische Motoren Werke Aktiengesellschaft | Navigation device and navigation method |
| CN107850447A (en) * | 2015-07-29 | 2018-03-27 | 宝马股份公司 | Guider and air navigation aid |
| CN109154509A (en) * | 2016-05-10 | 2019-01-04 | 微软技术许可有限责任公司 | The user's efficiency improved in route planning using route preferences |
| CN105973255A (en) * | 2016-06-17 | 2016-09-28 | 北京奇虎科技有限公司 | Route recommendation method and terminal |
| CN108444486A (en) * | 2017-02-16 | 2018-08-24 | 高德信息技术有限公司 | A kind of navigation routine sort method and device |
| CN107745711A (en) * | 2017-09-05 | 2018-03-02 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus that route is determined under automatic driving mode |
| CN108182273A (en) * | 2018-01-23 | 2018-06-19 | 成都信达智胜科技有限公司 | Network data processing method based on cloud storage |
| CN109115236A (en) * | 2018-07-10 | 2019-01-01 | 上海博泰悦臻电子设备制造有限公司 | Vehicle, vehicle device equipment and its stroke automatic navigation method based on condition triggering |
| CN110375760A (en) * | 2019-07-29 | 2019-10-25 | 北京百度网讯科技有限公司 | Route determination method, apparatus, equipment and medium |
| CN110864701A (en) * | 2019-12-17 | 2020-03-06 | 上海博泰悦臻电子设备制造有限公司 | Navigation route recommendation method, vehicle-mounted terminal and computer storage medium |
| CN112050824A (en) * | 2020-09-17 | 2020-12-08 | 北京百度网讯科技有限公司 | Route planning method, device and system for vehicle navigation and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112710323A (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10642268B2 (en) | Method and apparatus for generating automatic driving strategy | |
| US8229666B2 (en) | Generating and using pattern keys in navigation systems to predict user destinations | |
| CN106289296B (en) | Road navigation method and device | |
| US11294372B2 (en) | Driving mode decision support | |
| CN108444486B (en) | Navigation route sorting method and device | |
| US20180149488A1 (en) | Guide route setting apparatus and guide route setting method | |
| CN114162140B (en) | Optimal lane matching method and system | |
| CN107745711B (en) | Method and device for determining route in automatic driving mode | |
| CN106101168A (en) | Car-mounted terminal, cloud service equipment, onboard system and information processing method and device | |
| CN112905849A (en) | Vehicle data processing method and device | |
| CN111611402B (en) | Driving behavior knowledge graph generation method, device and system based on position | |
| DE112020003033T5 (en) | Method and apparatus for improving a geolocation database | |
| CN110843768B (en) | Automatic parking control method, device and equipment for automobile and storage medium | |
| CN110909907A (en) | Method and device for predicting fuel consumption of truck and storage medium | |
| CN112508310B (en) | Driving track simulation method and device and storage medium | |
| CN112710323B (en) | Vehicle navigation method and device | |
| CN109919293B (en) | Dangerous driving judgment method and device | |
| CN109945883B (en) | Information processing method and device and electronic equipment | |
| CN111561945B (en) | Navigation path generation method and device based on Internet of vehicles | |
| CN111382370A (en) | Route recommendation method and device, vehicle-mounted equipment and storage medium | |
| CN115683139A (en) | Vehicle-mounted map path planning method, system, electronic equipment and storage medium | |
| CN114722931A (en) | Vehicle-mounted data processing method and device, data acquisition equipment and storage medium | |
| CN115062204A (en) | Content push processing method and processing device based on vehicle navigation | |
| CN111380548A (en) | Route recommendation method and device, vehicle-mounted equipment and storage medium | |
| CN110837518B (en) | Track data processing method and device |
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 |