CN111461489A - Route generation method and device, electronic equipment and readable storage medium - Google Patents
Route generation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111461489A CN111461489A CN202010147489.0A CN202010147489A CN111461489A CN 111461489 A CN111461489 A CN 111461489A CN 202010147489 A CN202010147489 A CN 202010147489A CN 111461489 A CN111461489 A CN 111461489A
- Authority
- CN
- China
- Prior art keywords
- travel
- users
- stopping point
- starting
- preset
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the specification provides a route generation method, a route generation device, electronic equipment and a route generation medium.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a route generation method and apparatus, an electronic device, and a readable storage medium.
Background
A custom bus, also known as a custom bus or business class, is a one-stop direct class from cell to unit, and from unit to cell. Citizens can put forward their own demands through a special website, and a public transport group designs a public transport line according to the demands and the passenger flow conditions. In a commuting scene, a line generated by the customized bus is generally a dumbbell-shaped line, namely, two ends are provided with a plurality of up-down stations, and the middle is a long-distance station-free direct line. At present, the generation of a new line for customizing a bus is based on a mode that a user actively reports requirements, and if the requirements of a starting point and an end point reported by the user do not reach a line-forming standard, the line-forming is not performed.
Disclosure of Invention
The embodiment of the specification provides a route generation method and device, electronic equipment and a readable storage medium.
In a first aspect, an embodiment of the present specification provides a route generation method, where the method includes: the method comprises the steps of obtaining travel characteristic information of all users, wherein the all users are a user set belonging to a preset area, and the travel characteristic information of each user comprises historical travel starting and stopping point pairs of the user in the preset area; screening out a potential user set from the full users according to the travel characteristic information of the full users; and generating a customized bus route according to the historical travel starting and stopping point pairs of all the potential users in the potential user set.
In a second aspect, an embodiment of the present specification provides a route generation apparatus, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring travel characteristic information of all users, the all users are user sets belonging to a preset area, and the travel characteristic information of each user comprises historical travel starting and stopping point pairs of the user in the preset area; the screening module is used for screening out a potential user set from the full-volume users according to the travel characteristic information of the full-volume users; and the generating module is used for generating a customized bus route according to the historical travel starting and stopping point pairs of all the potential users in the potential user set.
In a third aspect, an embodiment of the present specification provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor performs the steps of the method according to the first aspect.
In a fourth aspect, embodiments of the present specification provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to the first aspect.
The embodiment of the specification has the following beneficial effects:
according to the route generation method provided by the embodiment of the specification, the travel characteristic information of all users is obtained, a potential user set, namely a user set with potential requirements for riding the customized bus, is screened from all users according to the travel characteristic information of all users, and then the customized bus route is generated according to historical travel starting and stopping point pairs of all potential users in the potential user set in a preset area. Therefore, the riding requirements do not need to be actively reported by the users, more potential users with the riding customized bus requirements are automatically excavated by analyzing the travel characteristic information of the total number of users, the problems of low line generation quality and low efficiency caused by the fact that some users have riding requirements but do not report are solved, and the generation quality and the efficiency of the customized bus line are favorably improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart of a route generation method provided in a first aspect of an embodiment of the present specification;
FIG. 2 is a flowchart illustrating model training steps provided in a first aspect of embodiments of the present disclosure;
fig. 3 is a schematic diagram of a route generation device provided in a second aspect of the embodiments of the present disclosure;
fig. 4 is a schematic diagram of an electronic device provided in a third aspect of an embodiment of the present specification.
Detailed Description
The starting point and the end point of the customized bus are actively reported by the user, only a small part of the user is always reported, and the obtained demand data is only a small part of the potential demand of the customized bus, so that a demand blind area easily exists, and the efficiency of generating the customized bus route is not improved. In view of this, embodiments of the present disclosure provide a route generation method, an apparatus, an electronic device, and a readable storage medium, which do not require a user to actively report a riding demand, and can effectively avoid the problem of low route generation quality and efficiency caused by the fact that some users have riding demands but do not report the riding demands, and are beneficial to improving the generation quality and efficiency of a customized bus route.
In order to better understand the technical solutions, the technical solutions of the embodiments of the present specification are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and are not limitations of the technical solutions of the present specification, and the technical features of the embodiments and embodiments of the present specification may be combined with each other without conflict.
In the embodiments of the present specification, the term "plurality" means "two or more", that is, includes two or more cases; the term "and/or" is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In the embodiments of the present specification, a start-stop point pair, that is, an Origin-Destination (OD) pair, "O" is derived from english Origin, and indicates a starting point of a trip, "D" is derived from english Destination, and indicates a Destination of the trip. For the sake of uniform description, the following pairs of start and end points are all expressed as OD pairs. In addition, "distance" mentioned in the embodiments of the present specification is a straight-line distance between two points.
In a first aspect, an embodiment of the present specification provides a route generation method. As shown in fig. 1, the method includes at least the following steps S101 to S103.
Step S101, obtaining travel characteristic information of all users, wherein the all users are user sets belonging to a preset area, and the travel characteristic information of each user comprises historical travel OD pairs of the user in the preset area.
In the embodiment of the present specification, an area in which a customized bus route needs to be generated by the route generation method provided in the present embodiment is taken as a preset area. The full-size user refers to a user set composed of a plurality of users belonging to a preset area. For example, the preset area is a city, such as Chengdu or Hangzhou, and the users who live in the city can be collected as the total users. For example, in one application scenario, assuming that there are 10 thousands of people recorded in a certain preset area, the entire number of users may include the 10 thousands of people. In the specific implementation process, the user set forming the full amount of users can be determined according to the needs of the actual application scene.
In step S101, the travel characteristic information of the total users is obtained, that is, the travel characteristic information of each user in the user set forming the total users is obtained. In this embodiment, the travel characteristic information of the user includes a historical travel OD pair of the user in a preset area. The historical travel OD pair is an OD pair contained in the historical travel information of the user. Generally, each user's historical travel information includes a plurality of OD pairs, that is, each user typically has a plurality of historical travel OD pairs. The historical travel information refers to travel information of the user within a preset historical time period, wherein the historical time period can be set according to requirements of an actual application scene, and for example, the historical time period can be the previous week, the previous 30 days, the previous 100 days, and the like.
In an alternative embodiment of the present specification, in addition to the historical travel OD pairs of the user in the preset area, the travel characteristic information of the user may include, but is not limited to, any one or more combinations of the following information: distance information of a historical trip OD pair; travel efficiency information of historical travel OD pairs; and historical travel preference information of the user.
The distance information of the historical travel OD pair may include, but is not limited to: the distance statistical information of the OD pairs in the historical travel information of the user, such as the longest distance, the shortest distance, the median of the distance of each OD pair, the average of the distance of each OD pair, and the travel frequency of the long-distance OD pairs, i.e. the ratio of the OD pairs whose distance exceeds a preset threshold value to all the OD pairs in the historical travel information of the user. The preset threshold is set according to the requirements of the actual application scenario, and may be set to 15km, for example. Further, the distance statistic information may further include: for the long-distance OD pairs, the distance average, the longest distance, the shortest distance, the median, and the like are counted.
The historical travel efficiency information of the historical travel OD pair may include data in multiple dimensions, for example, may include, but is not limited to, one or more combinations of the following three dimensions: distance of historical trip OD pairs; in the historical travel route planning of the historical travel OD pair, the distance between a departure place O and a destination D and a bus/subway station respectively; and the number of times of bus and/or subway exchange in the historical travel route planning of the historical travel OD pair. Of course, in addition to these data, other data related to the travel efficiency, such as the walking time of the user, the total travel time, and the like, may be included.
The historical travel preference information of the user may include: and in the historical travel information of the user, the times of taking various vehicles account for the ratio and the consumption amount are counted. For example, in a commuting scenario, the user takes statistical information such as the number of times of taking a bus, the maximum value, the minimum value and the average value of the amount of consumed bus, and the user takes statistical information such as the number of times of taking a net appointment, the maximum value, the minimum value and the average value of the amount of consumed net appointment.
Of course, the travel characteristic information may include other information of the user in addition to the above information, for example, the place of employment of the user and user figures such as the age, sex, practice, school calendar, and monthly consumption amount of the user.
And S102, screening out a potential user set from the full-volume users according to the travel characteristic information of the full-volume users.
In this embodiment, the potential user refers to a user who has a potential need to ride the customized bus and does not ride the customized bus. Potential users are mined from the full-volume users by analyzing the travel characteristic information of the full-volume users, and a potential user set is obtained.
In an optional embodiment, the above process of screening out the set of potential users from the full-volume users according to the travel characteristic information of the full-volume users may include: for each user in the total number of users, inputting the travel characteristic information of the user into a preset user screening model, and predicting whether the user is a candidate user; and determining candidate users who do not take the customized bus in the preset area as potential users in the predicted candidate users to obtain a potential user set.
The user screening model is a pre-trained two-classification model and is used for predicting whether the user is a candidate user with customized bus riding requirements or not according to the travel characteristic information of the user. For example, the prediction result output by the user screening model may be a probability value or a score that the user belongs to the candidate user, and if the probability value or the score is higher than a specified threshold, it is determined that the user belongs to the candidate user.
For the candidate user predicted by the user screening model, it is further determined whether the candidate user is a potential user, that is, whether the candidate user has a record of riding the customized bus in the preset area. If the candidate user has a record of buying the ticket in the preset area for taking the customized bus, the candidate user is the user needing to take the customized bus, but the candidate user has an applicable customized bus route and is not a potential user. If the candidate user does not have the record of buying the ticket in the preset area for taking the customized bus, the candidate user is indicated to have the requirement of taking the customized bus, but does not have an applicable customized bus route, and therefore the candidate user can be used as a potential user.
As shown in fig. 2, as an embodiment, the user screening model may be obtained by training according to the following steps S201 and S202.
Step S201, obtaining a training sample, wherein the training sample comprises a positive sample and a negative sample, the positive sample is a user who takes the customized bus in a preset area for more than a preset number of times, and the negative sample is a user who does not take the customized bus in the preset area and does not meet a preset condition on historical travel information.
It can be understood that training the supervised two-class model requires obtaining training samples first and constructing a training sample set, i.e. labeling positive and negative samples. In this embodiment, a batch of users may be selected, and through analyzing historical travel information of the users, a user who takes the customized bus more than a preset number of times is selected as a positive sample, and a user who does not take the customized bus and does not meet a preset condition in the preset area is selected as a negative sample. The preset times can be set according to the requirements of the actual application scene and multiple tests, for example, the preset times can be set to 2 times.
As an embodiment, after the marking of the positive samples is completed, users having the same magnitude as the number of the positive samples may be randomly drawn as the negative samples from among users who have not taken the customized bus and have not satisfied the preset condition on the historical travel information of the preset area. This is beneficial to avoiding the problem of poor model generalization due to sample imbalance. For example, in one application scenario, the positive and negative sample sizes may be about 1 ten thousand.
In the step S201, the preset condition may include any one or more combinations of the following three conditions. Of course, in the implementation process, the preset condition may include other conditions besides the three conditions, and is not limited herein.
The first condition is as follows: the distance between the places where the users are located in the preset area exceeds a first preset distance threshold. The distance between places exceeds a first predetermined distance threshold, indicating that the user's places are spaced farther apart, and thus the probability of having a demand for riding the customized bus is relatively high.
The first preset distance threshold may be set according to the needs of the actual application scenario and multiple experiments, and may be set to 10km, for example.
And a second condition: in the historical travel OD pairs of the user, the ratio of a first characteristic OD pair exceeds a first preset ratio threshold value, wherein the first characteristic OD pair is an OD pair of which the historical travel efficiency information meets a first preset efficiency condition.
In this embodiment, if the percentage of the first characteristic OD pair in the historical travel OD pairs of the user exceeds the first preset percentage threshold, it may be considered that the OD travel efficiency of the user is relatively low, and accordingly, the probability of taking the demand of the customized bus is relatively high; on the contrary, the OD travel efficiency of the user is considered to be relatively high, and the probability of having the demand of riding the customized bus is relatively low. The first preset duty ratio threshold may be set according to the needs of the actual application scenario and multiple tests, and may be set to 30%, for example.
Specifically, the historical trip efficiency information of each OD pair may include data of a plurality of dimensions, and the first preset efficiency condition is set according to the data of the dimensions included in the historical trip efficiency information. For example, the historical trip efficiency information includes a distance between an OD pair and a distance between an O pair and a bus/subway station, and an O pair and a D pair are respectively located at a bus/subway station, and the first preset efficiency condition may include an OD pair distance condition and an O/D off-station distance condition associated with the OD pair distance condition. For example, in one application scenario, the first preset efficiency condition includes: the OD distance is greater than or equal to 10km, and the O/D distance is greater than or equal to 1.5km from the public transport/subway station. The distance between the O/D and the bus/subway station refers to the distance between the OD centering and the bus/subway station or the distance between the D and the bus/subway station.
And (3) carrying out a third condition: in the historical travel OD pairs of the user, the proportion of a second characteristic OD pair exceeds a second preset proportion threshold, wherein the second characteristic OD pair is an OD pair with travel time within a preset time period and the distance exceeding a second preset distance threshold. The second preset duty ratio threshold may be set according to the needs of the actual application scenario and multiple trials, and may be set to 50%, for example. If the occupancy of the second characteristic OD pair exceeds a second preset occupancy threshold in the historical travel OD pairs of the user, it can be considered that the long-distance OD frequency of the user is relatively high in the morning and evening peaks, and accordingly, the probability of taking the customized bus is relatively high; on the contrary, the long-distance OD frequency of the user is considered to be relatively low in the morning and evening, and the probability of having the demand of riding the customized bus is relatively low.
In the historical travel information of the user, each OD pair corresponds to a travel time. In a specific implementation, the preset time period is set according to the morning and evening peak time periods, for example, the preset time period may be set to 8:00 to 10:00 am and 17:00 to 19:00 pm. The second preset distance threshold may be set according to the requirements of the actual application scenario and a plurality of experiments, for example, may be set to 15 km.
In an alternative embodiment of the present specification, a user who does not take the customized bus in the preset area and does not have the historical travel information satisfying the first, second, and third conditions may be used as a negative example.
Step S202, taking the travel characteristic information of the training sample as training data, and training a preset machine learning model to obtain the user screening model.
In a specific implementation process, the preset machine learning model may adopt an XGBoost model. XGBoost is one of Boosting algorithms, and the Boosting algorithm integrates a plurality of weak classifiers together to form a strong classifier. Because the XGboost is a lifting tree model, a plurality of tree models are integrated together to form a strong classifier. The XGboost model can adaptively process the characteristic missing value and is beneficial to accurately mining potential users.
Of course, in addition to the XGBoost model, in other embodiments of the present disclosure, the preset machine learning model may also adopt other two-class machine learning models, for example, a neural network, a support vector machine, a decision tree, and the like may be adopted.
And predicting the total number of users through the trained user screening model, wherein the users which are predicted to be positive samples, namely the users which are predicted to be candidate users with the customized bus riding requirements in the preset area and do not ride the customized bus in the preset area are potential users.
In another alternative embodiment, in the potential user mining stage, a clustering algorithm or a similarity calculation method may be used to find out people in the total number of users who have portrait features and travel features similar to those of the user who takes the customized bus, based on the user-related features, that is, the potential users are mined by the user who determines to take the customized bus among the total number of users.
Specifically, the total users can be clustered according to the trip characteristic information of the total users in a preset area to obtain a plurality of clusters, wherein each cluster comprises a plurality of users; counting the total number of users riding the customized bus in a preset area in the total number of users in the preset area; and acquiring the proportion of the number of the users who determine to take the customized bus in the cluster in the total number of the users for each cluster, and if the proportion exceeds a preset proportion, taking other users who do not take the customized bus in the preset area in the cluster as potential users. The preset proportion is set according to the actual application scene needs and multiple tests.
For example, the total number of users in a predetermined area includes 10000 users, and there are 100 users who determine to ride the customized bus. According to the travel characteristic information of the 10000 users, clustering is carried out on the 10000 users to obtain 6 clusters. And counting the proportion of the number of the users who determine to take the customized bus in the 6 clusters in the 100 users according to each cluster in the 6 clusters, and if the proportion exceeds a preset proportion, taking other users who do not take the customized bus in the preset area in the clusters as potential users. For example, a cluster includes 1000 users, wherein 50 users take the customized bus, the ratio of the number of users who take the customized bus in the cluster to the 100 users is determined to be 0.5, and the other 950 users in the cluster are considered as potential users assuming that the preset ratio is 0.3.
Step S103, generating a customized bus route according to the historical travel OD pairs of all the potential users in the potential user set.
After the potential users are determined, a custom bus route may be further generated. Specifically, the implementation of generating the customized bus route according to the historical travel OD pairs of all potential users may include: determining the number of users of the historical travel starting and stopping point pairs aiming at each historical travel OD pair of the potential user set, and taking the historical travel OD pairs with the number of the users exceeding the preset number as alternative OD pairs; generating a custom bus route from the alternative pair of ODs. For each historical travel OD pair, the number of users is the number of potential users including the OD pair in the travel characteristic information, for example, if the travel characteristic information of 100 users in the potential user set includes the historical travel OD pair, it indicates that the number of users in the historical travel OD pair is 100. If the number of users in a certain historical travel OD pair exceeds the preset number, the number of potential users covered by the historical travel OD pair is relatively large, and thus the number of users in a bus is more guaranteed after the OD pair is generated into a customized bus line. In a specific implementation process, the preset number may be set according to the needs of an actual application scenario and multiple times of experiments, for example, may be set to 500.
In an alternative embodiment of the present disclosure, the determined alternative OD pairs are multiple, and in order to generate a more reliable customized bus route, the determined alternative OD pairs may be filtered before the customized bus route is generated according to the alternative OD pairs, and then the customized bus route is generated according to the filtered alternative OD pairs. Two filtering manners are mainly described below, and in the specific implementation process, other applicable filtering manners may be adopted according to the needs of the actual application scenario, which is not limited herein.
The first filtration mode: obtaining the predicted trip efficiency information of the determined alternative OD pairs; and removing the determined alternative OD pairs, and predicting alternative OD pairs with the trip efficiency information meeting a second preset efficiency condition.
In one embodiment, the travel efficiency information of the alternative OD pairs includes a linear distance of the OD pairs. The second preset efficiency condition includes: OD distance condition. The OD distance conditions include: and if the linear distance of the alternative OD pair is smaller than or equal to the preset distance, judging that the predicted trip efficiency information of the alternative OD pair meets a second preset efficiency condition. At this time, it is shown that the travel efficiency of the alternative OD pair is relatively high, and the probability that the user takes the customized bus at the alternative OD pair is small, so that the alternative OD pair needs to be filtered out, which is beneficial to improving the generation quality of the customized bus route. The preset distance may be set according to the needs of the actual application scenario and multiple tests, and may be set to 20km, for example.
In another embodiment, the implementation process of obtaining the predicted travel efficiency information of the determined alternative OD pairs may include: planning a bus and/or subway travel route for the determined alternative OD pair through a preset path planning algorithm to obtain the bus and/or subway travel route of the alternative OD pair; and obtaining the predicted travel efficiency information of the alternative OD pairs according to the bus and/or subway travel routes of the alternative OD pairs. The route planning algorithm is used for planning public transportation and/or subway travel routes for the departure place "O" and the destination place "D" in each candidate OD pair, for example, route planning services provided by common navigation and location services such as an existing map may be adopted, and details are not described here.
It can be understood that there may be a plurality of bus and/or subway travel routes of the candidate OD pairs planned above, and in an implementation, an optimal travel route with the highest travel efficiency may be screened from the plurality of planned bus and/or subway travel routes, and the predicted travel efficiency information of the candidate OD pair may be determined according to the optimal travel route. Specifically, the travel route with the shortest total time under the same transfer times can be used as the optimal travel route, or the travel route with the smallest transfer times can be used as the optimal travel route from the travel routes with the total time difference within 5 min.
At this time, the predicted trip efficiency information of the alternative OD pairs may include, but is not limited to: in the optimal travel route, the number of times of bus and/or subway transfer, and/or the distance between the departure place O and the destination D and the bus or subway station. On this basis, predicting the travel efficiency information may further include: OD versus linear distance. Or, other data related to the travel efficiency, such as the walking time of the user, the total travel time, etc., may also be included.
It can be understood that the distance between the departure place "O" and the destination "D" in the travel route and the bus or subway station, the number of times of bus and/or subway transfer, and the straight-line distance of the OD pairs are all important factors affecting the travel efficiency. The farther the distance between the departure place "O" and the destination place "D" and the bus or subway station is, the more the number of times of bus and/or subway transfers is increased, or the farther the straight distance of the OD pair is, the lower the travel efficiency of the bus/subway travel route of the OD pair is.
In the first filtering manner, the second preset efficiency condition is associated with the predicted trip efficiency information of the alternative OD pair, and is specifically set according to the dimension included in the predicted trip efficiency information of the alternative OD pair. For example, if the predicted travel efficiency information of the alternative OD pairs includes: the straight-line distance of the OD pairs, the number of times of bus and/or subway transfers, and the distances between the departure place 'O' and the destination 'D' and the bus or subway stations. Accordingly, the second preset efficiency condition may include: OD distance condition, transfer number condition, and off-station distance condition.
The OD distance condition is described above, and is not described herein again. The transfer number condition may be: in the optimal travel route, the number of times of bus and/or subway transfer is less than or equal to a first specified threshold value. The first specific threshold may be set according to the needs of the actual application scenario and multiple trials, and may be set to 1, for example. The off-station distance condition may be: in the optimal travel route, the distances between the departure place O and the destination D and the public transport or subway station are less than or equal to a second specified threshold. The second designated threshold may be set according to the needs of the actual application scenario and multiple trials, and may be set to 1.5km, for example.
And if the predicted trip efficiency information of the alternative OD pair simultaneously meets the OD distance condition, the transfer times condition and the distance-from-station condition, judging that the predicted trip efficiency information of the alternative OD pair meets a second preset efficiency condition. It should be noted that the predicted travel efficiency information of the alternative OD pair meets the second preset efficiency condition, which indicates that the predicted travel efficiency of the alternative OD pair is relatively high, and the probability that the user takes the customized bus at the alternative OD pair is small, so that the alternative OD pair needs to be filtered out, which is beneficial to improving the generation quality of the customized bus route.
Of course, in other embodiments of the present description, the optimal travel route may not be screened, but the predicted travel efficiency information of the alternative OD pairs may be determined based on each planned bus and/or subway travel route. In this case, if the predicted trip efficiency information of the candidate OD pairs includes: in each planned bus and/or subway travel route, the number of times of bus and/or subway transfer, and the distances between the departure place 'O' and the destination 'D' and the bus or subway station. At this time, if at least one transfer number of travel routes exists in the planned public transport and/or subway travel routes for a certain candidate OD pair, the number of times of transfer of the travel routes is smaller than or equal to the first specified threshold, and the distances between the departure place "O" and the destination place "D" and the public transport or subway station are smaller than or equal to the second specified threshold, it is determined that the predicted travel efficiency information of the candidate OD pair meets a second preset efficiency condition.
The second filtering mode is as follows: and removing the determined alternative OD pairs, wherein the alternative OD pairs are covered by the existing regular bus route.
In this embodiment, the existing regular bus may be a fixed regular bus already installed, such as a park regular bus and an enterprise regular bus. If a certain alternative OD pair is already covered by the existing buses, it is not beneficial to open a customized bus route for the alternative, and the existing buses will greatly affect the passenger flow volume of the customized bus, so that the alternative OD pairs covered by the existing bus route need to be eliminated, so as to further improve the generation quality of the customized bus route. In one embodiment, alternative OD pairs covered by an existing regular bus route may be screened by: for each alternative OD pair, calculating the occupation ratio of the enterprise POI in all POIs (points of Information) contained in the departure place "O" or the destination "D", and determining the alternative OD pair with the occupation ratio larger than or equal to a third preset occupation ratio threshold as the alternative OD pair covered by the existing bus route. The third preset duty ratio threshold is set according to the needs of the actual application scenario and multiple times of experiments, and may be set to 80%, for example. It is understood that in the geographic information system, one POI may be a house, a shop, a mailbox, a bus station, or the like.
The two filtration methods may be used alone or in combination. For example, in an application scenario, after filtering out part of the candidate OD pairs by using the first filtering method, the remaining candidate OD pairs may be filtered by using the second filtering method. Of course, other filtering manners may be included besides the two filtering manners, for example, the filtered alternative OD pairs, that is, the alternative OD pairs that already have the customized bus route, may be eliminated.
After the filtering is completed, a customized bus route can be generated according to the eliminated alternative OD pairs. Specifically, after determining the alternative OD pairs for generating the customized bus route, several upper and lower stations may be set at the O end and the D end of the alternative OD pairs according to the actual situation, and a path of the intermediate long-distance nonstop direct route of the customized bus may be planned according to the route making manner of the existing customized bus route, which is not described in detail herein.
According to the route generation method provided by the embodiment of the specification, users do not need to report riding requirements actively, more potential users with riding customized bus requirements are automatically excavated by analyzing travel characteristic information of a whole number of users, the problem that the generation quality and efficiency of routes are low due to the fact that some users have riding requirements but do not report is solved, and the generation quality and efficiency of the customized bus routes are improved.
In a second aspect, an embodiment of the present disclosure provides a route generating device, please refer to fig. 3, where the route generating device 30 includes:
an obtaining module 31, configured to obtain travel characteristic information of all users, where the all users are a set of users belonging to a preset area, and the travel characteristic information of each user includes a historical travel starting point pair and a historical travel ending point pair of the user in the preset area;
the screening module 32 is configured to screen out a potential user set from the full amount of users according to the trip characteristic information of the full amount of users;
a generating module 33, configured to generate a customized bus route according to the historical travel starting and stopping point pairs of all the potential users in the set of potential users.
In an alternative embodiment, the screening module 32 includes:
the prediction sub-module 321 is configured to, for each user in the full amount of users, input the travel characteristic information of the user into a preset user screening model, and predict whether the user is a candidate user;
the determining sub-module 322 is configured to determine, as a potential user, a candidate user who does not take the customized bus in the preset area among the predicted candidate users, so as to obtain the set of potential users.
In an alternative embodiment, the user screening model is trained according to the following steps:
obtaining training samples, wherein the training samples comprise positive samples and negative samples, the positive samples are users who ride the customized bus in the preset area for more than a preset number of times, and the negative samples are users who do not ride the customized bus in the preset area and have historical travel information not meeting preset conditions;
and taking the travel characteristic information of the training sample as training data, training a preset machine learning model, and obtaining the user screening model.
In an alternative embodiment, the preset condition includes any one or more of the following conditions:
the distance between the users in the places of employment in the preset area exceeds a first preset distance threshold;
in the historical trip start-stop point pairs of the user, the ratio of a first characteristic start-stop point pair exceeds a first preset ratio threshold, wherein the first characteristic start-stop point pair is a start-stop point pair of which the historical trip efficiency information meets a first preset efficiency condition; and
in the historical travel starting and stopping point pairs of the user, the ratio of a second characteristic starting and stopping point pair exceeds a second preset ratio threshold, wherein the second characteristic starting and stopping point pair is a starting and stopping point pair with travel time within a preset time period and the distance exceeding a second preset distance threshold.
In an alternative embodiment, the generating module 33 includes:
an alternative submodule 331, configured to determine, for each historical travel starting-stopping point pair of the potential user set, the number of users of the historical travel starting-stopping point pair, and use a historical travel starting-stopping point pair whose number of users exceeds a preset number as an alternative starting-stopping point pair;
and the route generation submodule 332 is used for generating a customized bus route according to the alternative starting-stopping point pairs.
In an alternative embodiment, the route generation submodule 332 is configured to:
obtaining the predicted trip efficiency information of the determined alternative starting-stopping point pairs;
and rejecting the determined alternative starting and stopping point pairs, predicting the alternative starting and stopping point pairs of which the travel efficiency information meets a second preset efficiency condition, and generating a customized bus route according to the rejected alternative starting and stopping point pairs.
In an alternative embodiment, the route generation submodule 332 is configured to:
planning a bus and/or subway travel route for the alternative starting and stopping point pairs through a preset path planning algorithm to obtain the bus and/or subway travel route of the alternative starting and stopping point pairs;
and obtaining the predicted travel efficiency information of the alternative starting-stopping point pairs according to the bus and/or subway travel routes of the alternative starting-stopping point pairs.
In an alternative embodiment, the route generation submodule 332 is configured to: and removing the determined alternative starting and stopping point pairs, namely the alternative starting and stopping point pairs covered by the existing regular bus route, and generating a customized bus route according to the removed alternative starting and stopping point pairs.
In an optional embodiment, the travel characteristic information further includes any one or more of the following information:
distance information of the historical trip starting and stopping point pairs;
historical trip efficiency information of the historical trip starting and stopping point pairs; and
historical travel preference information of the user.
With regard to the above-mentioned apparatus, specific functions of each module have been described in detail in the method embodiment provided in the first aspect of the embodiment of the present invention, and will not be described in detail herein, and the specific implementation process may refer to the method embodiment provided in the first aspect.
In a third aspect, based on the same inventive concept as the route generation method in the foregoing embodiment, an embodiment of the present invention further provides an electronic device, as shown in fig. 4, including a memory 404, a processor 402, and a computer program stored on the memory 404 and executable on the processor 402, where the processor 402 implements the steps of any one of the foregoing route generation methods when executing the program.
Where in fig. 4 a bus architecture (represented by bus 400) is shown, bus 400 may include any number of interconnected buses and bridges, and bus 400 links together various circuits including one or more processors, represented by processor 402, and memory, represented by memory 404. The bus 400 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 405 provides an interface between the bus 400 and the receiver 401 and transmitter 403. The receiver 401 and the transmitter 403 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 402 is responsible for managing the bus 400 and general processing, while the memory 404 may be used for storing data used by the processor 402 in performing operations.
It is to be understood that the structure shown in fig. 4 is merely an illustration, and that the electronic device provided by the embodiments of the present description may further include more or less components than those shown in fig. 4, or have a different configuration than that shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
In a fourth aspect, based on the same inventive concept as the route generation method in the foregoing embodiments, embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of any one of the route generation methods described above.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, 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. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (20)
1. A route generation method, the method comprising:
the method comprises the steps of obtaining travel characteristic information of all users, wherein the all users are a user set belonging to a preset area, and the travel characteristic information of each user comprises historical travel starting and stopping point pairs of the user in the preset area;
screening out a potential user set from the full users according to the travel characteristic information of the full users;
and generating a customized bus route according to the historical travel starting and stopping point pairs of all the potential users in the potential user set.
2. The method of claim 1, wherein the screening out a set of potential users from the full-volume users according to the travel characteristic information of the full-volume users comprises:
for each user in the total users, inputting the trip characteristic information of the user into a preset user screening model, and predicting whether the user is a candidate user;
and determining candidate users who do not take the customized bus in the preset area in the predicted candidate users as potential users to obtain the potential user set.
3. The method of claim 2, wherein the user screening model is trained according to the following steps:
obtaining training samples, wherein the training samples comprise positive samples and negative samples, the positive samples are users who ride the customized bus in the preset area for more than a preset number of times, and the negative samples are users who do not ride the customized bus in the preset area and have historical travel information not meeting preset conditions;
and taking the travel characteristic information of the training sample as training data, training a preset machine learning model, and obtaining the user screening model.
4. The method of claim 3, wherein the preset conditions comprise any one or more of the following conditions in combination:
the distance between the users in the places of employment in the preset area exceeds a first preset distance threshold;
in the historical trip start-stop point pairs of the user, the ratio of a first characteristic start-stop point pair exceeds a first preset ratio threshold, wherein the first characteristic start-stop point pair is a start-stop point pair of which the historical trip efficiency information meets a first preset efficiency condition; and
in the historical travel starting and stopping point pairs of the user, the ratio of a second characteristic starting and stopping point pair exceeds a second preset ratio threshold, wherein the second characteristic starting and stopping point pair is a starting and stopping point pair with travel time within a preset time period and the distance exceeding a second preset distance threshold.
5. The method of claim 1, the generating a custom bus route from historical travel starting and ending point pairs for all potential users in the set of potential users, comprising:
determining the number of users of each historical trip starting and stopping point pair of the potential user set, and taking the historical trip starting and stopping point pairs with the number of users exceeding a preset number as alternative starting and stopping point pairs;
and generating a customized bus route according to the alternative starting-stopping point pairs.
6. The method of claim 5, the generating a customized bus route from the alternate starting-stopping point pairs comprising:
obtaining the predicted trip efficiency information of the determined alternative starting-stopping point pairs;
and rejecting the determined alternative starting and stopping point pairs, predicting the alternative starting and stopping point pairs of which the travel efficiency information meets a second preset efficiency condition, and generating a customized bus route according to the rejected alternative starting and stopping point pairs.
7. The method of claim 6, wherein the obtaining of the predicted travel efficiency information of the determined candidate starting-stopping point pairs comprises:
planning a bus and/or subway travel route for the alternative starting and stopping point pairs through a preset path planning algorithm to obtain the bus and/or subway travel route of the alternative starting and stopping point pairs;
and obtaining the predicted travel efficiency information of the alternative starting-stopping point pairs according to the bus and/or subway travel routes of the alternative starting-stopping point pairs.
8. The method of claim 5, the generating a customized bus route from the alternate starting-stopping point pairs comprising:
and removing the determined alternative starting and stopping point pairs, namely the alternative starting and stopping point pairs covered by the existing regular bus route, and generating a customized bus route according to the removed alternative starting and stopping point pairs.
9. The method of claim 1, wherein the travel characteristic information further comprises any one or more of the following:
distance information of the historical trip starting and stopping point pairs;
historical trip efficiency information of the historical trip starting and stopping point pairs; and
historical travel preference information of the user.
10. A route generation apparatus, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring travel characteristic information of all users, the all users are user sets belonging to a preset area, and the travel characteristic information of each user comprises historical travel starting and stopping point pairs of the user in the preset area;
the screening module is used for screening out a potential user set from the full-volume users according to the travel characteristic information of the full-volume users;
and the generating module is used for generating a customized bus route according to the historical travel starting and stopping point pairs of all the potential users in the potential user set.
11. The apparatus of claim 10, the screening module comprising:
the prediction sub-module is used for inputting the travel characteristic information of the user into a preset user screening model aiming at each user in the total number of users and predicting whether the user is a candidate user;
and the determining submodule is used for determining candidate users which do not take the customized bus in the preset area in the predicted candidate users as potential users to obtain the potential user set.
12. The apparatus of claim 11, the user screening model trained according to the following steps:
obtaining training samples, wherein the training samples comprise positive samples and negative samples, the positive samples are users who ride the customized bus in the preset area for more than a preset number of times, and the negative samples are users who do not ride the customized bus in the preset area and have historical travel information not meeting preset conditions;
and taking the travel characteristic information of the training sample as training data, training a preset machine learning model, and obtaining the user screening model.
13. The apparatus of claim 12, wherein the preset conditions comprise any one or more of the following conditions:
the distance between the users in the places of employment in the preset area exceeds a first preset distance threshold;
in the historical trip start-stop point pairs of the user, the ratio of a first characteristic start-stop point pair exceeds a first preset ratio threshold, wherein the first characteristic start-stop point pair is a start-stop point pair of which the historical trip efficiency information meets a first preset efficiency condition; and
in the historical travel starting and stopping point pairs of the user, the ratio of a second characteristic starting and stopping point pair exceeds a second preset ratio threshold, wherein the second characteristic starting and stopping point pair is a starting and stopping point pair with travel time within a preset time period and the distance exceeding a second preset distance threshold.
14. The apparatus of claim 10, the generating module comprising:
the alternative submodule is used for determining the number of users of each historical travel starting-stopping point pair of the potential user set, and taking the historical travel starting-stopping point pairs with the number of users exceeding the preset number as alternative starting-stopping point pairs;
and the route generation submodule is used for generating a customized bus route according to the alternative starting-stopping point pairs.
15. The apparatus of claim 14, the route generation submodule to:
obtaining the predicted trip efficiency information of the determined alternative starting-stopping point pairs;
and rejecting the determined alternative starting and stopping point pairs, predicting the alternative starting and stopping point pairs of which the travel efficiency information meets a second preset efficiency condition, and generating a customized bus route according to the rejected alternative starting and stopping point pairs.
16. The apparatus of claim 15, the route generation submodule to:
planning a bus and/or subway travel route for the alternative starting and stopping point pairs through a preset path planning algorithm to obtain the bus and/or subway travel route of the alternative starting and stopping point pairs;
and obtaining the predicted travel efficiency information of the alternative starting-stopping point pairs according to the bus and/or subway travel routes of the alternative starting-stopping point pairs.
17. The apparatus of claim 14, the route generation submodule to:
and removing the determined alternative starting and stopping point pairs, namely the alternative starting and stopping point pairs covered by the existing regular bus route, and generating a customized bus route according to the removed alternative starting and stopping point pairs.
18. The apparatus of claim 10, wherein the travel characteristic information further comprises any one or more of the following:
distance information of the historical trip starting and stopping point pairs;
historical trip efficiency information of the historical trip starting and stopping point pairs; and
historical travel preference information of the user.
19. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-9 when executing the program.
20. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010147489.0A CN111461489A (en) | 2020-03-05 | 2020-03-05 | Route generation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010147489.0A CN111461489A (en) | 2020-03-05 | 2020-03-05 | Route generation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111461489A true CN111461489A (en) | 2020-07-28 |
Family
ID=71682638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010147489.0A Pending CN111461489A (en) | 2020-03-05 | 2020-03-05 | Route generation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461489A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329989A (en) * | 2020-10-19 | 2021-02-05 | 北京中恒云科技有限公司 | Bus route planning method and device based on cloud computing and storage medium |
| CN112381472A (en) * | 2021-01-15 | 2021-02-19 | 深圳市城市交通规划设计研究中心股份有限公司 | Subway connection bus route optimization method and device and storage medium |
| CN114387042A (en) * | 2022-03-22 | 2022-04-22 | 北京骑胜科技有限公司 | Travel demand determination method and device |
| CN114739418A (en) * | 2022-04-26 | 2022-07-12 | 长安大学 | Method and system for selecting travel mode of taxi booking user |
| CN115731734A (en) * | 2022-11-09 | 2023-03-03 | 支付宝(杭州)信息技术有限公司 | Method and system for planning travel route based on traffic travel data processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7469827B2 (en) * | 2005-11-17 | 2008-12-30 | Google Inc. | Vehicle information systems and methods |
| CN109102332A (en) * | 2018-08-06 | 2018-12-28 | 北京小度信息科技有限公司 | A kind of method, apparatus and electronic equipment of data processing |
| CN110175691A (en) * | 2019-04-09 | 2019-08-27 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of planning region traffic operation route |
| CN110264250A (en) * | 2019-05-30 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Determine product peers amount in the method and device of the distributed data of multiple regions |
-
2020
- 2020-03-05 CN CN202010147489.0A patent/CN111461489A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7469827B2 (en) * | 2005-11-17 | 2008-12-30 | Google Inc. | Vehicle information systems and methods |
| CN109102332A (en) * | 2018-08-06 | 2018-12-28 | 北京小度信息科技有限公司 | A kind of method, apparatus and electronic equipment of data processing |
| CN110175691A (en) * | 2019-04-09 | 2019-08-27 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of planning region traffic operation route |
| CN110264250A (en) * | 2019-05-30 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Determine product peers amount in the method and device of the distributed data of multiple regions |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329989A (en) * | 2020-10-19 | 2021-02-05 | 北京中恒云科技有限公司 | Bus route planning method and device based on cloud computing and storage medium |
| CN112381472A (en) * | 2021-01-15 | 2021-02-19 | 深圳市城市交通规划设计研究中心股份有限公司 | Subway connection bus route optimization method and device and storage medium |
| CN114387042A (en) * | 2022-03-22 | 2022-04-22 | 北京骑胜科技有限公司 | Travel demand determination method and device |
| CN114387042B (en) * | 2022-03-22 | 2022-06-10 | 北京骑胜科技有限公司 | Travel demand determination method and device |
| CN114739418A (en) * | 2022-04-26 | 2022-07-12 | 长安大学 | Method and system for selecting travel mode of taxi booking user |
| CN115731734A (en) * | 2022-11-09 | 2023-03-03 | 支付宝(杭州)信息技术有限公司 | Method and system for planning travel route based on traffic travel data processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461489A (en) | Route generation method and device, electronic equipment and readable storage medium | |
| CN111768030B (en) | Bank transportation distribution line planning method, device, equipment and medium | |
| US20160129787A1 (en) | Methods, Circuits, Devices, Systems & Associated Computer Executable Code for Driver Decision Support | |
| CN110543999A (en) | Method and device for store site selection | |
| Liu et al. | Exploiting heterogeneous human mobility patterns for intelligent bus routing | |
| CN104884900A (en) | Travel time information providing apparatus and travel time information providing method | |
| CN110390415A (en) | A kind of method and system carrying out trip mode recommendation based on user's trip big data | |
| US20230215272A1 (en) | Information processing method and apparatus, computer device and storage medium | |
| WO2019003672A1 (en) | Transit demand forecasting device and transit demand forecasting method | |
| CN107392389A (en) | Taxi dispatching processing method based on ARIMA models | |
| CN111192090A (en) | Seat allocation method and device for flight, storage medium and electronic equipment | |
| CN106897801A (en) | Method, device, equipment and storage medium that driver classifies | |
| CN110459050B (en) | Short-term bus passenger flow prediction method based on mixed decision tree | |
| CN110570656B (en) | Method and device for customizing public transport line | |
| Ma et al. | Public transportation big data mining and analysis | |
| CN114443303A (en) | Resource allocation method, device, equipment and medium | |
| CN116772877B (en) | Method, system, device and medium for predicting endurance mileage of new energy automobile | |
| Chuwang et al. | Short-term urban rail transit passenger flow forecasting based on fusion model methods using univariate time series | |
| CN106295868A (en) | Traffic trip data processing method and device | |
| CN110222892A (en) | The get-off stop prediction technique and device of passenger | |
| CN111582527A (en) | Travel time estimation method and device, electronic equipment and storage medium | |
| CN110796301B (en) | Passenger flow prediction method and device based on IC card data | |
| CN116562574A (en) | Inter-city customized passenger transport collaborative optimization method, device, equipment and storage medium | |
| Rodrigues et al. | Hybrid context-aware multimodal routing | |
| CN111079008B (en) | Scheme recommendation method and system for taxi driver to leave in storage pool |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |