CN115523931A - Historical navigation route updating method for map navigation cache database - Google Patents
Historical navigation route updating method for map navigation cache database Download PDFInfo
- Publication number
- CN115523931A CN115523931A CN202110704336.6A CN202110704336A CN115523931A CN 115523931 A CN115523931 A CN 115523931A CN 202110704336 A CN202110704336 A CN 202110704336A CN 115523931 A CN115523931 A CN 115523931A
- Authority
- CN
- China
- Prior art keywords
- navigation
- abstract
- updating
- historical
- route
- 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.)
- Pending
Links
Images
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
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- 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
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- 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
-
- 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
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Navigation (AREA)
Abstract
The invention discloses a historical navigation route updating method of a map navigation cache database, which comprises the following steps: step 1, obtaining historical navigation lines in a map navigation cache database and establishing a corresponding abstract map model; step 2, determining a historical navigation line needing to be updated through deep learning fitting by combining the abstract graph model with the introduced riding line and the historical navigation line; step 3, obtaining the latest navigation route corresponding to the historical navigation route needing to be updated: inquiring a third-party map service provider to obtain a corresponding current latest navigation route according to a historical navigation route needing to be updated; and 4, updating the historical navigation route: and (4) replacing and updating the corresponding historical navigation route in the map navigation cache database according to the current latest navigation route acquired in the step (3), and updating the corresponding navigation distance. The method can accurately find the navigation route needing to be updated, reduce the number of the updated route and reduce the updating cost.
Description
Technical Field
The invention relates to the field of electronic map navigation, in particular to a historical navigation route updating method for a map navigation cache database.
Background
At present, for an enterprise requiring a large amount of map-related services, navigation data (such as a navigation line between two points) is acquired from a third-party professional map service provider and then stored in a map navigation cache database. Because the access to the third party can bring about the increase of time delay, in order to improve the corresponding time, the map navigation cache database stores a large amount of navigation data obtained historically, so as to ensure that when an application accesses the map navigation cache database, a corresponding piece of historical navigation data is used as a return result. However, this has the following problems: in the map navigation cache database, a large amount of historical navigation data acquired from a third party is stored, and due to road condition changes (such as road repair, temporary construction and the like) in the real world, the shortest distance navigation route of most of the historical caches does not accord with the current latest navigation route. The obsolescence of navigation data affects the quality of downstream traffic, such as: in the takeaway delivery scene, a navigation line which can not be passed through actually is given, so that the takeaway delivery staff can be influenced to deliver dishes in time.
The problem that the cache data is outdated is solved under a static cache framework, and the update is usually performed by combining the access times and the last update date at present:
in an off-line stage, a path with high query frequency is counted from a query log; the third-party map service provider is accessed to update the head navigation line which is not updated for the access times in three months;
updating the navigation route with the most influence on the number of orders and high query frequency;
since the probability that three months of non-updated data is outdated is greater, the probability of an effective update can be increased.
However, in the existing method, the condition of the navigation route is not considered, only the time latitude is considered from the non-update, and the routes which are changed before and after the update are inquired and updated are less, so that a large amount of non-updated outdated navigation data still exist in the map navigation cache database.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a historical navigation route updating method for a map navigation cache database, which can solve the problem that the existing method for updating the outdated historical navigation route only considers from the non-updating time latitude because the condition of the navigation route is not considered, and the number of the navigation routes which are changed before and after the updating is inquired is less during the updating, so that a large number of the outdated navigation routes which are not updated still exist in a local database.
The purpose of the invention is realized by the following technical scheme:
the embodiment of the invention provides a historical navigation route updating method of a map navigation cache database, which comprises the following steps:
step 1, establishing an abstract graph model: obtaining historical navigation lines in a map navigation cache database, and establishing an abstract map model according to the historical navigation lines;
step 3, obtaining the latest navigation route corresponding to the historical navigation route needing to be updated: inquiring a third-party map service provider to obtain a corresponding current latest navigation route according to a historical navigation route needing to be updated;
and 4, updating a historical navigation route: and (4) replacing and updating the corresponding historical navigation route in the map navigation cache database according to the current latest navigation route acquired in the step (3), and updating the corresponding navigation distance.
According to the technical scheme provided by the invention, the historical navigation route updating method of the map navigation cache database provided by the embodiment of the invention has the beneficial effects that:
the method comprises the steps of modeling a historical navigation line as an abstract map, introducing a riding line, fitting the edge right of an abstract edge by utilizing the abstract map and the historical navigation line, determining the abstract edge to be updated according to a fitting result, further determining the corresponding historical navigation line to be updated, and updating the historical navigation line to be updated in a mode of inquiring a third-party map service provider, so that not only can the map historical navigation line library be effectively updated, but also the validity of the updating quantity can be ensured and the updating data volume can be reduced due to the fact that only the selected historical navigation line is updated, so that the navigation line obtained by accessing a database is consistent with the current best navigation line.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a method for updating a history navigation route of a map navigation cache database according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an edge weight fitting deep learning model in the method provided by the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the specific contents of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides a method for updating a historical navigation route of a map navigation cache database, including:
step 1, establishing an abstract graph model: obtaining historical navigation lines in a map navigation cache database, and establishing an abstract map model according to the historical navigation lines; the historical navigation route is navigation data stored in a GPS point sequence;
step 3, obtaining the latest navigation route corresponding to the historical navigation route needing to be updated: inquiring a third-party map service provider to obtain a corresponding current latest navigation route according to a historical navigation route needing to be updated;
and 4, updating the historical navigation route: and (4) replacing and updating the corresponding historical navigation route in the map navigation cache database according to the current latest navigation route acquired in the step (3), and updating the corresponding navigation distance.
Step 3 of the above method further comprises:
and selecting a group of navigation lines which are preferentially updated from the historical navigation lines which need to be updated, and inquiring a third-party map service provider through the navigation lines to obtain the corresponding current latest navigation line. The mode of selecting the group of navigation lines which are preferentially updated can reduce the number of the updated historical navigation lines and reduce the updating cost and the calculation expense.
In the step 3, selecting a group of navigation links with priority update from the history navigation links needing update according to the following mode, including:
step 31, calculating the updating benefit of each abstract edge according to the use frequency and the variation of the abstract edge of the abstract graph model;
step 32, selecting paths from the abstract edges of the abstract graph model, and enabling the sum of the updating benefits of the abstract edges contained in the selected paths to be maximum;
step 33, calculating the sum of the updating gains of the edges contained in each path, sorting each path according to the gains from large to small, and selecting the paths in turn according to the path sorting, and skipping the path and continuously selecting the next path when the edges contained in the selected path are contained in the path selected in the step 32; the way of selecting the path is to cover more edges which are not included by other selected paths as far as possible on the basis of considering the updating benefit;
and 34, repeating the steps 32-33 until the number of the picking paths reaches the number of the updating budgets.
Step 4 of the above method further comprises:
and updating the corresponding historical navigation route in the map navigation cache database according to different preset periods according to the obtained current latest navigation route.
In the step 4, the map navigation cache database is respectively updated according to a first period and a second period, wherein,
the duration of the first period is less than the second period;
the first cycle update is: when the navigation route reaches the first period and needs to be updated, if the abstract side contained in the historical navigation route is unchanged, using the obtained latest edge weight of the abstract side to update the navigation distance of the historical navigation route;
the second period is updated as follows: when the updating is needed when the second period is reached, recalculating the latest navigation distances of all historical navigation lines on the abstract graph model in a shortest path mode according to the edge weights of the abstract edges obtained by updating all first periods after the updating of the previous second period, and updating the corresponding historical navigation lines by using the obtained new navigation distances.
In the step 4, the shortest path mode adopts a Dijsktra shortest path algorithm to calculate the shortest path;
the first period is one day;
the second period is one week.
It can be known that the first and second periods can also be set to different durations as required, as long as the first period is ensured to be shorter than the second period.
The updating mode with different periods can reduce the updating times and the updating cost on the premise of keeping the timely and effective updating of the historical navigation line.
In step 1 of the above method, the establishing of the historical navigation route as an abstract map model in the following manner includes:
and establishing an abstract graph model by using intersection points in the historical navigation line, mapping the historical navigation line into an abstract node sequence of the abstract graph model, and taking the navigation distance of the historical navigation line as the edge weight of an abstract edge of the abstract graph model.
In the step 1, the intersection points in the historical navigation line are obtained, and core nodes in the intersection points are extracted through clustering processing and serve as abstract nodes to establish an abstract graph model; preferably, the clustering process adopts a DB-SCAN clustering algorithm to process;
taking a historical navigation line passing through at least two abstract nodes of the abstract graph model as an abstract edge, wherein the edge weight of the abstract edge is the navigation distance of the navigation line between the abstract nodes;
and mapping the historical navigation route into an abstract node sequence of the abstract graph model according to the passed abstract nodes.
In step 2 of the method, the effective riding route is obtained in the following way, including:
the method comprises the steps that an original riding line ridden by a rider is obtained, abnormal point detection and filtering are conducted on the original riding line based on a preset threshold value to remove invalid riding lines, and therefore an effective riding line is obtained;
the method comprises the following steps of carrying out deep learning by the following mode, fitting and clustering the effective riding line and the historical navigation line corresponding to each abstract edge of the abstract graph model, and obtaining a fitting result of the optimal route distance of the current abstract edge, wherein the fitting result comprises the following steps:
performing fitting processing on the effective riding line and the historical navigation line corresponding to each abstract edge of the abstract graph through deep learning to obtain a fitting result of the optimal route distance of the current abstract edge;
and clustering the fitting results output by the abstract edges with the multiple riding lines obtained by the fitting process, and taking the most numerous classes as the fitting results. Preferably, the clustering process adopts a DB-SCAN clustering algorithm to process;
referring to fig. 2, in the step 2, the deep learning adopts an edge-weight fitting deep learning model composed of a first preprocessing module, a first LSTM network, a second preprocessing module, a second LSTM network, a Bi-LSTM network, a first MLP network, a Fast-DTW module, a similarity measurement module, a basic feature module, and a second MLP network, wherein,
the input of the first preprocessing module is a historical navigation line, and the output of the first preprocessing module is connected with the first LSTM network;
the input of the second preprocessing module is a riding line, and the output of the second preprocessing module is connected with the second LSTM network;
the outputs of the first LSTM network and the second LSTM network are connected with the Bi-LSTM network, and the output of the Bi-LSTM network is connected with the first MLP network;
the input of the Fast-DTW module is a historical navigation line and a riding line, and the output of the Fast-DTW module is sequentially connected with the similarity measurement module and the basic characteristic module;
and the outputs of the first MLP network and the basic feature module are connected with the second MLP network, and the output of the second MLP network is the predicted navigation distance.
In the side weight fitting simulation, a Fast-DTW module runs a Fast-DTW algorithm, and a similarity measurement module runs a similarity measurement algorithm; the edge weight fitting simulation mainly comprises LSTM and Bi-LSTM, clustering results and model intermediate results are aggregated, and a full-connection model is used for outputting a final predicted navigation distance.
The method can effectively update the historical navigation route database, so that the navigation route obtained by accessing the database is consistent with the current optimal navigation route, is a light-weight effective method for updating the map navigation cache database, can be deployed in a navigation database of hundreds of millions of scales, and provides real-time update. Compared with the prior art, the method obviously improves the accuracy of the historical navigation route in the map navigation cache database.
The embodiments of the present invention are described in further detail below.
The embodiment of the invention provides a historical navigation route updating method of a map navigation cache database, which is a method for modeling a historical navigation route as an abstract map, introducing a riding route to predict a navigation distance, determining a historical navigation route needing to be updated according to the predicted navigation distance, and updating the historical navigation route of the map historical navigation route database, and comprises the following steps:
step 1, establishing an abstract graph model: establishing an abstract map model according to historical navigation lines in a map navigation cache database, and mapping the historical navigation lines into an abstract node sequence on the abstract map model, so as to facilitate subsequent processing of updating the historical navigation lines, wherein the historical navigation lines are navigation data stored by GPS points;
step 3, acquiring a corresponding navigation route for updating: inquiring a third-party map service provider according to the determined historical navigation route needing to be updated, and acquiring the current latest navigation route corresponding to the third-party map service provider;
and 4, updating the historical navigation route, and updating the corresponding historical navigation route and the corresponding navigation distance in the map navigation cache database by using the obtained current latest navigation route.
Further, in step 3, a group of navigation links with priority to be updated is selected from the determined historical navigation links needing to be updated, and the group of navigation links with priority to be updated is used for querying a third-party map service provider to obtain the corresponding current latest navigation link. The method can reduce the number of the updating lines, reduce the updating cost, and is more suitable for scenes which are limited by budget and can not update all the lines.
In the step 3, since the historical navigation route is updated by inquiring the current and latest accurate navigation route acquired by the third-party map service provider instead of updating the historical navigation route directly according to the riding route, the problem that the accuracy of updating the historical navigation route is influenced due to inaccurate and compliant riding route caused by the condition that the collected riding route violates the traffic rules such as retrograde motion and the like is avoided.
Further, in the step 4, a two-cycle update is adopted: namely, after the current latest navigation route is obtained, the corresponding historical navigation data is updated in a large-small period mode. The updating timeliness can be guaranteed, and the calculation expense is saved. In actual processing, after the latest edge weight information of the abstract graph model is obtained, the shortest path information between the abstract node pairs is updated in a large-small period mode.
The process of establishing the abstract graph model in the step 1 specifically comprises the following steps: acquiring intersection points in historical navigation lines in a map navigation cache database, and extracting core nodes by using a DB-SCAN clustering algorithm to serve as abstract nodes of an abstract graph model; if two abstract nodes which are passed by the historical navigation line successively exist, the abstract nodes are recorded as the existence of an abstract edge, the edge weight of the abstract edge is the navigation distance of the historical navigation line in the two abstract nodes, and the historical navigation line is mapped into an abstract node sequence of an abstract graph model according to the passed abstract nodes.
The edge weight fitting process in the step 2 specifically includes: firstly, abnormal point detection based on a threshold value and filtering of an original riding route of a rider are carried out to remove an invalid riding route, so that an effective riding route is obtained, then effective rider track data and historical navigation routes corresponding to each abstract side of the abstract graph model obtained in the step 1 are input into a deep learning side weight fitting deep learning model for deep learning estimation processing, and the deep learning side weight fitting deep learning model outputs a fitting result of the current abstract side optimal route distance; and for abstract edges with a plurality of riding lines, clustering the fitting results output by the deep learning edge weight fitting deep learning model by using a DB-SCAN clustering algorithm, and taking the class with the largest number as the final fitting result.
The path selection in the step 3 is specifically as follows: and selecting a group of navigation lines which are updated preferentially for re-querying the third-party map service provider to obtain the corresponding current latest navigation line. The pseudo code of the specific selection algorithm of the navigation route is as follows, and specifically comprises the following steps (all are path selection realized based on the operation of the abstract graph model):
step 31, calculating the updating benefit of each edge based on the using frequency and the variation of the edge;
step 32, selecting a path so that the sum of the updating yields of the edges included in the selected path is maximum;
step 33, calculating the sum of the updating gains of the edges contained in each path, sorting each path from large to small according to the gains, and selecting the paths in turn according to the path sorting, and skipping the path and continuously selecting the next path when the edges contained in the selected path are contained in the path selected in the step 32; the way of selecting the path covers more edges which are not included by other selected paths as far as possible on the basis of considering the updating benefit, and can avoid the situation that the selected path includes too many common edges and one edge is subjected to updating query for many times;
and 34, repeating the steps 32-33 until the number of the picking paths reaches the number of the updated budgets.
The two-cycle updating in the step 4 specifically includes: the method comprises the following steps that two types of updating are adopted, wherein the first type of updating is a first period (short period updating, such as daily updating), and when the updating is needed in the first period, if the abstract edges contained in the historical navigation lines are not changed, the obtained edge weights of the latest abstract edges are used for updating the navigation distance of the corresponding historical navigation lines in a map navigation cache database;
the second update is a second periodic (long periodic, e.g., weekly) update: when the updating is needed when the second period is reached, recalculating the latest navigation distances of all historical navigation lines on the abstract graph by using a Dijsktra shortest path algorithm according to the abstract side weights obtained by updating all first periods after the updating of the last second period, and updating all historical navigation lines by using the obtained latest navigation distances.
The method can be deployed in a large-scale database server and can be deployed in a software mode.
Those of ordinary skill in the art will understand that: all or part of the processes of the methods for implementing the embodiments may be implemented by a program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods as described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A historical navigation route updating method of a map navigation cache database is characterized by comprising the following steps:
step 1, establishing an abstract graph model: obtaining historical navigation lines in a map navigation cache database, and establishing an abstract map model according to the historical navigation lines;
step 2, determining a historical navigation route needing to be updated through the abstract graph model: obtaining effective riding lines, fitting and clustering the effective riding lines and the historical navigation lines corresponding to each abstract edge of the abstract graph model through deep learning to obtain a fitting result of the optimal line distance of the current abstract edge, determining the abstract edge to be updated according to the fitting result, and determining the navigation line to be updated according to the determined abstract edge;
step 3, obtaining the latest navigation route corresponding to the historical navigation route needing to be updated: inquiring a third-party map service provider to obtain a corresponding current latest navigation route according to a historical navigation route needing to be updated;
and 4, updating the historical navigation route: and updating the corresponding historical navigation route in the map navigation cache database according to the current latest navigation route acquired in the step 3.
2. The method for historical navigation route updating of the map navigation cache database according to claim 1, wherein the step 3 further comprises:
and selecting a group of navigation routes which are updated preferentially from the historical navigation routes which need to be updated, and inquiring a third-party map service provider through the navigation routes to obtain the corresponding current latest navigation route.
3. The method for updating the historical navigation routes of the map navigation cache database according to claim 1, wherein the step of selecting a group of navigation routes with priority for updating from the historical navigation routes needing updating comprises the following steps:
step 31, calculating the updating benefit of each abstract edge according to the use frequency and the variation of the abstract edge of the abstract graph model;
step 32, selecting paths from the abstract edges of the abstract graph model, and enabling the sum of the updating benefits of the abstract edges contained in the selected paths to be maximum;
step 33, calculating the sum of the updating profit of the edges contained in each path, sorting each path from large to small according to the profit, and selecting the path in turn according to the path sorting, when the edges contained in the selected path are contained in the path selected in the step 32, skipping the path and continuously selecting the next path;
and 34, repeating the steps 32-33 until the number of the picking paths reaches the number of the updating budgets.
4. The historical navigation route updating method of the map navigation cache database according to any one of claims 1 to 3, wherein the step 4 further comprises:
and updating the corresponding historical navigation route in the map navigation cache database according to different preset periods according to the obtained current latest navigation route.
5. The historic navigation route updating method for the map navigation cache database according to claim 4, wherein in the step 4, the map navigation cache database is respectively updated for a first period and a second period according to a preset first period and a preset second period, wherein,
the duration of the first period is less than the second period;
the first cycle update is: when the navigation route reaches the first period and needs to be updated, if the abstract side contained in the historical navigation route is unchanged, using the obtained latest edge weight of the abstract side to update the navigation distance of the historical navigation route;
the second period update is: when the updating is needed when the second period is reached, recalculating the latest navigation distances of all historical navigation lines on the abstract graph model in a shortest path mode according to the edge weights of the abstract edges obtained by updating all first periods after the updating of the previous second period, and updating the corresponding historical navigation lines by using the obtained new navigation distances.
6. The historical navigation route updating method for the map navigation cache database according to claim 5, wherein the shortest path method adopts Dijsktra shortest path algorithm to calculate the shortest path;
the first period is one day;
the second period is one week.
7. The method for updating the historical navigation route of the map navigation cache database according to any one of claims 1 to 3, wherein in the step 1, the historical navigation route is established as an abstract map model in the following way, including:
and establishing an abstract graph model by using intersection points in the historical navigation line, mapping the historical navigation line into an abstract node sequence of the abstract graph model, and taking the navigation distance of the historical navigation line as the edge weight of an abstract edge of the abstract graph model.
8. The historical navigation route updating method for the map navigation cache database according to claim 7, wherein in the step 1, the intersection points in the historical navigation route are obtained, and core nodes in the intersection points are extracted through clustering processing and used as abstract nodes to establish an abstract graph model;
taking a historical navigation line passing through at least two abstract nodes of the abstract graph model as an abstract edge, wherein the edge weight of the abstract edge is the navigation distance of the navigation line between the abstract nodes;
and mapping the historical navigation route into an abstract node sequence of the abstract graph model according to the passed abstract nodes.
9. The method for updating the historical navigation route of the map navigation cache database according to claim 1, wherein in the step 2, the effective riding route is obtained by the following steps:
the method comprises the steps that an original riding line ridden by a rider is obtained, abnormal point detection and filtering are conducted on the original riding line based on a preset threshold value, an invalid riding line is removed, and an effective riding line is obtained;
the method comprises the following steps of carrying out deep learning by the following method, fitting and clustering effective riding lines and historical navigation lines corresponding to each abstract edge of an abstract graph model, and obtaining a fitting result of the optimal path distance of the current abstract edge, wherein the fitting result comprises the following steps:
performing fitting processing on the effective riding route and the historical navigation route corresponding to each abstract side of the abstract image through deep learning to obtain a fitting result of the optimal route distance of the current abstract side;
and clustering the fitting results output by the abstract edges with the multiple riding lines obtained by the fitting process, and taking the most classes as the fitting results.
10. The historical navigation route updating method for the map navigation cache database according to claim 1 or 2, wherein in the step 2, the deep learning adopts an edge-weight fitting deep learning model composed of a first preprocessing module, a first LSTM network, a second preprocessing module, a second LSTM network, a Bi-LSTM network, a first MLP network, a Fast-DTW module, a similarity measurement module, a basic feature module and a second MLP network, wherein,
the input of the first preprocessing module is a historical navigation line, and the output of the first preprocessing module is connected with the first LSTM network;
the input of the second preprocessing module is a riding line, and the output of the second preprocessing module is connected with the second LSTM network;
the outputs of the first LSTM network and the second LSTM network are connected with the Bi-LSTM network, and the output of the Bi-LSTM network is connected with the first MLP network;
the input of the Fast-DTW module is a historical navigation line and a riding line, and the output of the Fast-DTW module is sequentially connected with the similarity measurement module and the basic characteristic module;
and the outputs of the first MLP network and the basic feature module are connected with the second MLP network, and the output of the second MLP network is the predicted navigation distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110704336.6A CN115523931A (en) | 2021-06-24 | 2021-06-24 | Historical navigation route updating method for map navigation cache database |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110704336.6A CN115523931A (en) | 2021-06-24 | 2021-06-24 | Historical navigation route updating method for map navigation cache database |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115523931A true CN115523931A (en) | 2022-12-27 |
Family
ID=84693473
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110704336.6A Pending CN115523931A (en) | 2021-06-24 | 2021-06-24 | Historical navigation route updating method for map navigation cache database |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115523931A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115858549A (en) * | 2023-02-27 | 2023-03-28 | 西安索格亚航空科技有限公司 | Navigation database of aviation navigation equipment and air route updating method |
-
2021
- 2021-06-24 CN CN202110704336.6A patent/CN115523931A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115858549A (en) * | 2023-02-27 | 2023-03-28 | 西安索格亚航空科技有限公司 | Navigation database of aviation navigation equipment and air route updating method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | A feature selection and multi-model fusion-based approach of predicting air quality | |
CN111210093B (en) | Daily water consumption prediction method based on big data | |
US20200334246A1 (en) | Information processing device, combination condition generation method, and combination condition generation program | |
CN102099803A (en) | Method and computer system for automatically answering natural language questions | |
KR20150043338A (en) | Updating cached database query results | |
CN109902213B (en) | Real-time bus service line recommendation method and device and electronic equipment | |
CN106023588A (en) | Traffic big data-based travel time extraction, prediction and query method | |
CN110874702B (en) | Model training method and device under logistics sorting scene and electronic equipment | |
CN111831704B (en) | Determination method and device of abnormal data, storage medium and electronic equipment | |
US20180192245A1 (en) | Extraction and Representation method of State Vector of Sensing Data of Internet of Things | |
CN107153656A (en) | A kind of information search method and device | |
CN112541638B (en) | Method for estimating travel time of vehicle connected with Internet | |
CN116386336B (en) | Road network traffic flow robust calculation method and system based on bayonet license plate data | |
CN112597389A (en) | Control method and device for realizing article recommendation based on user behavior | |
CN115523931A (en) | Historical navigation route updating method for map navigation cache database | |
CN108664605B (en) | Model evaluation method and system | |
CN114090898A (en) | Information recommendation method and device, terminal equipment and medium | |
CN112307151A (en) | Navigation data processing method and device | |
US11514062B2 (en) | Feature value generation device, feature value generation method, and feature value generation program | |
CN112215453A (en) | Inventory information processing method and device, electronic equipment and storage medium | |
CN116629425A (en) | Method and device for calculating vehicle energy consumption, computer readable medium and electronic equipment | |
CN114626766B (en) | Shared electric vehicle scheduling method, device, equipment and medium based on big data | |
CN115691140A (en) | Analysis and prediction method for space-time distribution of automobile charging demand | |
CN112380443B (en) | Guide recommendation method, device, computer equipment and storage medium | |
CN110177339B (en) | OD matrix construction 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 |