CN-114659534-B - Navigation path transit time processing method, device, equipment, medium and product

Abstract

The disclosure provides a navigation path transit time processing method, a navigation path transit time processing device, navigation path transit time processing equipment, navigation path transit time processing media and navigation path transit time processing products, and relates to the field of artificial intelligence, in particular to the field of intelligent traffic. The method comprises the steps of determining positioning tracks corresponding to at least one road in a road network respectively, extracting positioning features of the road according to the positioning tracks of the road, determining the passing time of the road by utilizing the positioning features of the road and combining the historical passing features of the road to obtain at least one passing time corresponding to the road respectively, determining the passing time corresponding to at least one target road in a navigation path respectively based on the passing time corresponding to the at least one road respectively, and adding the passing time corresponding to the at least one target road respectively to obtain the target passing time of the navigation path. The technical scheme of the navigation route passing time accuracy is improved.

Inventors

• LIU ZIHAO
• YUAN HAITAO
• ZHANG YAN
• YANG LINGLING

Assignees

• 北京百度网讯科技有限公司
• 北京百度网讯科技有限公司

Dates

Publication Date

20260421

Application Date

20220228

Priority Date

20220228

Claims (20)

1. 1. A navigation path transit time processing method, comprising: Acquiring at least one positioning point acquired by the road network during a target time period; Determining a plurality of locating point categories; Classifying the locating points based on a plurality of locating point categories to obtain at least one locating point category corresponding to each locating point; Determining a target locating point category meeting locating point selection conditions in a plurality of locating point categories; Determining at least one locating point corresponding to the target locating point type as at least one effective locating point; extracting at least one running track from at least one effective locating point according to user identification information respectively corresponding to the at least one effective locating point; Determining target roads with the matched driving tracks from at least one road, and obtaining target roads with at least one positioning track respectively corresponding to the at least one positioning track; Determining at least one positioning track corresponding to at least one road according to the target road corresponding to the at least one positioning track respectively; Extracting positioning features of the road according to the positioning track of the road, wherein the positioning features are extracted from at least one road feature parameter, and the road feature parameter comprises the running speed of each user, the running speed average value of all users, the track number and the track change rate; determining the traffic time of the road by utilizing the positioning characteristics of the road and combining the historical traffic characteristics of the road so as to obtain at least one traffic time corresponding to the road respectively; determining the passing time corresponding to at least one target road in the navigation path based on the passing time corresponding to at least one road respectively; And adding the passing time corresponding to at least one target road respectively to obtain the target passing time of the navigation path.
2. 2. The method of claim 1, wherein the determining the transit time of the link using the location feature of the link in combination with the historical transit feature of the link comprises: Carrying out feature fusion on the positioning features of the road and the historical traffic features of the road to obtain road driving features of the road; and inputting the road driving characteristics into a time sequence model obtained through training to obtain the traffic time of the road.
3. 3. The method of claim 1 or 2, the method further comprising: Dividing the whole time period into at least one candidate time period, wherein the candidate time period comprises a start time and a stop time, and the acquisition start time and the acquisition stop time of the whole time period are determined based on an acquisition period; Responding to a navigation request sent by user equipment, and determining a navigation path and navigation time corresponding to the navigation request; and determining a target time period corresponding to the navigation time from at least one candidate time period.
4. 4. The method of claim 3, wherein the navigation path corresponding to the navigation request includes at least one, the method further comprising: determining at least one target passing time corresponding to each navigation path; Generating navigation prompt information based on at least one target passing time corresponding to each navigation path; and sending the navigation prompt information to the user equipment.
5. 5. The method according to claim 3, wherein the determining the traffic time of the road by using the positioning feature of the road in combination with the historical traffic feature of the road to obtain at least one traffic time corresponding to the road respectively further comprises: determining a target start time and a target end time of the target time period; determining a previous acquisition period of the acquisition period in which the target time period is located; Acquiring a historical time period corresponding to the target starting time and the target ending time of a previous acquisition period; and determining the historical traffic characteristics corresponding to the road network in the historical time period.
6. 6. The method of claim 5, wherein the determining the historical traffic characteristics of the road network for the historical time period comprises: Determining at least one historical driving track corresponding to the road network in the historical time period; Determining at least one historical traffic parameter; Based on at least one historical driving track, extracting historical traffic data corresponding to at least one historical traffic parameter respectively; And determining the history passing characteristics according to the history passing data corresponding to at least one history passing parameter respectively.
7. 7. The method of claim 1, wherein the determining the target link for which the travel track matches from at least one of the links comprises: and inputting the driving track into a hidden Markov model corresponding to the road network, and determining a target road with highest matching degree with the driving track from at least one road by using the hidden Markov model.
8. 8. The method of any of claims 1-2, 4-7, wherein the corresponding positioning track of the road includes at least one, the extracting positioning features of the road from the positioning track of the road includes: determining at least one road driving parameter; extracting parameter data corresponding to at least one road driving parameter respectively according to at least one positioning track corresponding to the road; And determining the positioning characteristics of the road based on the parameter data corresponding to at least one road driving parameter respectively.
9. 9. The method of claim 8, wherein after the determining the at least one road-travel parameter, further comprising: determining an individual driving parameter and an overall driving parameter of at least one road driving parameter; Extracting parameter data corresponding to at least one road driving parameter according to at least one positioning track corresponding to the road, including: extracting individual data of the individual running parameters according to the positioning track of the road to obtain individual data of the individual running parameters corresponding to at least one positioning track; And extracting the whole data of the whole driving parameters according to at least one positioning track of the road.
10. 10. The method of claim 9, wherein the determining the location feature of the road based on the parameter data corresponding to at least one of the road driving parameters, respectively, comprises: Determining individual sub-features corresponding to the individual running parameters according to the individual data respectively corresponding to the individual running parameters in at least one positioning track; Determining integral sub-features corresponding to the integral running parameters according to the integral data corresponding to the integral running parameters; and carrying out feature fusion on the individual sub-features and the integral sub-features to obtain the positioning features of the road.
11. 11. The method of any one of claims 1-2, 4-7, 9-10, further comprising: Determining an associated road with a road connection relation with the road and positioning features corresponding to the associated road; the determining the traffic time of the road by utilizing the positioning feature of the road and combining the historical traffic feature of the road comprises the following steps: and determining the traffic time of the road by using the positioning characteristics of the road, the positioning characteristics of the associated road and the historical traffic characteristics of the road.
12. 12. A navigation time processing apparatus comprising: the track determining unit is used for determining positioning tracks corresponding to at least one road in the road network respectively; The device comprises a feature extraction unit, a road feature parameter extraction unit and a road feature analysis unit, wherein the feature extraction unit is used for extracting the positioning feature of the road according to the positioning track of the road, and the positioning feature is extracted and obtained by at least one road feature parameter, and the road feature parameter comprises the running speed of each user, the running speed average value of all users, the track number and the track change rate; The characteristic calculation unit is used for determining the traffic time of the road by utilizing the positioning characteristic of the road and combining the historical traffic characteristic of the road so as to obtain at least one traffic time corresponding to the road respectively; The time matching unit is used for determining the passing time corresponding to at least one target road in the navigation path based on the passing time corresponding to at least one road respectively; The time adding unit is used for adding the passing time corresponding to at least one target road respectively to obtain the target passing time of the navigation path; the trajectory determination unit includes: The track determining module is used for determining the positioning track corresponding to at least one road in the road network respectively during the target time period; the trajectory determination unit includes: the effective determining module is used for determining at least one effective positioning point corresponding to the road network; the identification positioning module is used for extracting at least one running track from at least one effective positioning point according to the user identification information respectively corresponding to the at least one effective positioning point; The road matching module is used for determining target roads with matched driving tracks from at least one road and obtaining at least one target road with corresponding positioning tracks respectively; the track positioning module is used for determining at least one positioning track corresponding to at least one road according to at least one target road corresponding to the positioning track respectively; The validity determination module includes: A positioning acquisition sub-module, configured to acquire at least one positioning point acquired by the road network during the target time period; A positioning selection sub-module, configured to select at least one valid positioning point from at least one positioning point based on a positioning point selection condition; the positioning selection submodule is specifically used for: The category determination submodule is used for determining a plurality of locating point categories; the positioning classification sub-module is used for classifying the positioning points based on a plurality of positioning point categories to obtain at least one positioning point category corresponding to each positioning point; a category selection sub-module, configured to determine a target anchor point category that satisfies an anchor point selection condition from a plurality of anchor point categories; and the positioning acquisition sub-module is used for determining at least one positioning point corresponding to the target positioning point type as at least one effective positioning point.
13. 13. The apparatus of claim 12, wherein the feature calculation unit comprises: The first extraction module is used for carrying out feature fusion on the positioning features of the road and the historical traffic features of the road to obtain road driving features of the road; and the time calculation module is used for inputting the road driving characteristics into the time sequence model obtained through training to obtain the road passing time.
14. 14. The apparatus according to claim 12 or 13, the apparatus further comprising: the time dividing unit is used for dividing the whole time period into at least one candidate time period, wherein the candidate time period comprises a start time and a stop time; A request response unit, configured to determine a navigation path and a navigation time corresponding to a navigation request sent by a user equipment in response to the navigation request; And the target determining unit is used for determining a target time period corresponding to the navigation time from at least one candidate time period.
15. 15. The apparatus of claim 14, wherein the navigation path corresponding to the navigation request comprises at least one, the apparatus further comprising: the time determining unit is used for determining at least one target passing time corresponding to each navigation path; the navigation generating unit is used for generating navigation prompt information based on at least one target passing time corresponding to each navigation path; and the information prompt unit is used for sending the navigation prompt information to the user equipment.
16. 16. The apparatus of claim 14, further comprising: a first determining unit configured to determine a target start time and a target end time of the target time period; the second determining unit is used for determining a previous acquisition period of the acquisition period where the target time period is located; A historical time unit, configured to obtain a historical time period corresponding to the target start time and the target end time in a previous acquisition period; and the history feature unit is used for determining the history passing feature corresponding to the road network in the history time period.
17. 17. The apparatus of claim 16, wherein the historical time unit comprises: the first determining module is used for determining at least one historical driving track corresponding to the historical time period of the road network; a second determining module for determining at least one historical traffic parameter; The parameter determining module is used for extracting historical traffic data corresponding to at least one historical traffic parameter respectively based on at least one historical driving track; and the second extraction module is used for determining the history traffic characteristics according to the history traffic data corresponding to at least one history traffic parameter respectively.
18. 18. The apparatus of claim 12, wherein the road matching module comprises: and the road matching sub-module is used for inputting the driving track into a hidden Markov model corresponding to the road network, and determining a target road with the highest matching degree with the driving track from at least one road by utilizing the hidden Markov model.
19. 19. The apparatus according to any one of claims 12-13, 15-18, wherein the road-corresponding positioning trajectory comprises at least one, the feature extraction unit comprising: the driving determining module is used for determining at least one road driving parameter; the data acquisition module is used for extracting parameter data corresponding to at least one road driving parameter respectively according to at least one positioning track corresponding to the road; And the data conversion module is used for determining the positioning characteristics of the road based on the parameter data corresponding to at least one road driving parameter respectively.
20. 20. The apparatus of claim 19, wherein the travel determination module comprises: the individual determining module is used for determining individual driving parameters and overall driving parameters in at least one road driving parameter; the data acquisition module comprises: The first obtaining submodule is used for extracting the individual data of the individual running parameters according to the positioning track of the road and obtaining the individual data of the individual running parameters corresponding to at least one positioning track respectively; and the second obtaining submodule is used for extracting the whole data of the whole driving parameters according to at least one positioning track of the road.

Description

Navigation path transit time processing method, device, equipment, medium and product Technical Field The disclosure relates to the field of intelligent traffic in the technical field of artificial intelligence, in particular to a navigation path transit time processing method, a device, equipment, a medium and a product. Background In electronic map navigation, a user device may detect a navigation request input by the user device in an electronic map, where the navigation request may include a start location and a destination. The electronic map corresponding server can conduct navigation planning according to the starting place and the destination in the navigation request, and at least one navigation path is obtained. In order to accurately prompt the navigation paths, the traffic time of each navigation path can be predicted, and the traffic time when a user runs through the whole path is obtained. However, in practical application, the accuracy of the passing time is not high, which results in not high accuracy of the navigation prompt of the electronic map. Disclosure of Invention The disclosure provides a navigation path transit time processing method, a device, equipment, a medium and a product for a map navigation scene. According to a first aspect of the present disclosure, there is provided a navigation path transit time processing method, including: Determining positioning tracks corresponding to at least one road in a road network respectively; Extracting the positioning characteristics of the road according to the positioning track of the road; determining the traffic time of the road by utilizing the positioning characteristics of the road and combining the historical traffic characteristics of the road so as to obtain at least one traffic time corresponding to the road respectively; determining the passing time corresponding to at least one target road in the navigation path based on the passing time corresponding to at least one road respectively; And adding the passing time corresponding to at least one target road respectively to obtain the target passing time of the navigation path. According to a second aspect of the present disclosure, there is provided a navigation time processing apparatus including: the track determining unit is used for determining positioning tracks corresponding to at least one road in the road network respectively; The feature extraction unit is used for extracting the positioning features of the road according to the positioning track of the road; The characteristic calculation unit is used for determining the traffic time of the road by utilizing the positioning characteristic of the road and combining the historical traffic characteristic of the road so as to obtain at least one traffic time corresponding to the road respectively; The time matching unit is used for determining the passing time corresponding to at least one target road in the navigation path based on the passing time corresponding to at least one road respectively; And the time adding unit is used for adding the passing time corresponding to at least one target road respectively to obtain the target passing time of the navigation path. According to a third aspect of the present disclosure, there is provided an electronic device comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect. According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect. According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program stored in a readable storage medium, the computer program being readable from the readable storage medium by at least one processor of an electronic device, the at least one processor executing the computer program causing the electronic device to perform the method of the first aspect. According to the technology disclosed by the invention, the problem of low accuracy of the passing time of the navigation path is solved, the positioning characteristics of the road are extracted through the positioning track of the road, and the passing time of the road is accurately determined through the extracted positioning characteristics and the historical passing characteristics of the road. By accurately determining the traffic time of the road, the accuracy of the obtained target traffic time of the navigation path is higher. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present