CN117787527A - Tour route intelligent planning method based on big data analysis technology - Google Patents
Tour route intelligent planning method based on big data analysis technology Download PDFInfo
- Publication number
- CN117787527A CN117787527A CN202410205926.8A CN202410205926A CN117787527A CN 117787527 A CN117787527 A CN 117787527A CN 202410205926 A CN202410205926 A CN 202410205926A CN 117787527 A CN117787527 A CN 117787527A
- Authority
- CN
- China
- Prior art keywords
- travel
- passengers
- passenger
- target passenger
- coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000005516 engineering process Methods 0.000 title claims abstract description 32
- 238000007405 data analysis Methods 0.000 title claims abstract description 26
- 230000000875 corresponding effect Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 230000002596 correlated effect Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 abstract description 2
- 230000009193 crawling Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing for management, in particular to an intelligent travel route planning method based on big data analysis technology, which comprises the following steps: the method comprises the steps of analyzing a travel data set and a tourist map structure of passengers, comprehensively considering influences of different ages, different travel modes and different people on travel path planning in the travel process, adjusting the number of the passengers selecting different travel modes under different ticket purchasing numbers, obtaining an edge weight factor, and weighting the distance between nodes in the tourist map structure by using the edge weight factor so as to further carry out travel route planning. According to the invention, the distance is weighted by the side weight factors, so that the travel route planning is more accurate and reasonable, the influence degree of different influence factors on the travel route planning result can be better reflected, and the accuracy and rationality of the travel route planning result are improved.
Description
Technical Field
The invention relates to the technical field of data processing for management, in particular to an intelligent travel route planning method based on big data analysis technology.
Background
Conventional travel route planning methods generally rely on manual experience and travel guidelines, lack of data support and personalized customization, and in order to improve the travel experience of tourists, the travel industry gradually introduces big data analysis technology to improve the travel service quality and user experience, and the travel route intelligent planning method based on the big data analysis technology provides more personalized and optimized travel route planning for users by collecting, processing and analyzing various travel related data.
In the travel path planning problem, the shortest path between different nodes is usually obtained by using the Floyd algorithm, and the conventional Floyd algorithm usually takes the distance between two places as the side weight to obtain the shortest path, but in practice, a plurality of factors influence the travel path planning, so that an accurate and reasonable travel path planning result cannot be obtained by carrying out the path planning only through the distance between the two places.
Disclosure of Invention
The invention provides an intelligent travel route planning method based on a big data analysis technology, which aims to solve the existing problems.
The intelligent travel route planning method based on the big data analysis technology adopts the following technical scheme:
the embodiment of the invention provides an intelligent travel route planning method based on big data analysis technology, which comprises the following steps:
acquiring a set formed by various travel data of a plurality of historical passengers by utilizing a web crawler technology, wherein the travel data are respectively the age of the passengers, the round trip time interval between nodes, the ticket purchasing quantity and the travel mode; the age of the passenger in various travel data is classified as youngAnd middle aged->The round trip time interval is more than three days and less than three days, the ticket purchasing quantity is divided into more than two sheets and less than two sheets, and the travel mode is divided into automobile ∈ ->Train->High-speed railway->And aircraft->Marking a passenger needing to carry out travel route planning as a target passenger, and acquiring travel time of the target passenger and a tourist map structure formed by all tourist city places to which the target passenger needs to go, wherein the tourist map structure comprises a plurality of nodes;
for any two nodes in the tourist map structure, selecting the quantity difference of different travel modes according to passengers of different ages in the travel data set to obtain an age-travel preference coefficient; according to the round trip time interval which accords with the travel time of the target passenger in the travel data set, the passenger selects the number difference of the passengers in different travel modes to obtain the round trip-travel coefficient of the target passenger; adjusting the number of passengers selecting different travel modes under different ticket purchasing numbers by using the age-travel preference coefficient and the round trip-travel coefficient of the target passenger to obtain side weight factors of the two nodes;
weighting the distance between nodes in the tourist map structure of the target passenger by using the edge weight factors to obtain edge weights between the nodes;
and planning the travel route according to the side rights among the nodes in the tourist map structure of the passenger.
Further, the specific acquisition method of the tourist map structure formed by all the tourist urban sites to which the target passengers need to go is as follows:
the method comprises the steps of obtaining a travel starting point S, a travel ending point A and a region needing to pass through of a target passenger, taking the travel starting point S, the travel ending point A and all cities or regions needing to pass through of the passenger as a node respectively, taking a connecting line between any two nodes as an edge, drawing a complete undirected graph by combining the positions of all nodes in a map, and recording the complete undirected graph as a travel graph structure of the target passenger.
Further, the method for obtaining the age-travel preference coefficient according to the difference of the number of the travel modes selected by the passengers with different ages in the travel data set comprises the following specific steps:
selecting the number of different travel modes according to passengers of different ages in the travel data set to respectively obtain young peopleSelect travel mode +.>Probability of (2), young, middle-aged +.>Select travel mode +.>And middle-aged probabilities, wherein；
According to young peopleSelect travel mode +.>The ratio of the probability of (2) to the young's probability is given by a first factor according to +.>Select travel mode +.>Obtaining a second factor from the ratio of the probability of (2) to the probability of middle aged;
the age-travel preference coefficient is positively correlated with the difference between the first factor and the second factor.
Further, the number of different travel modes is selected according to the passengers with different ages in the travel data set, so that young people are respectively obtainedSelect travel mode +.>Probability of (2), young, middle-aged +.>Select travel mode +.>The specific method comprises the following steps of:
acquiring the number of all passengers included in a travel data setAll passengers are middle-aged and young +.>And middle aged->The number of (2) is denoted by->And->Will->And->The ratio of (2) is recorded as young probability, and +.>And->The ratio of (2) is recorded as the middle-aged probability; acquiring young in a travel data set>Select travel mode +.>Number of->Acquiring middle-aged +.>Select travel mode +.>Number of->Will->And->The ratio of (2) is marked->Will->And->The ratio of (2) is marked->。
Further, under the round trip time interval according with the travel time of the target passenger in the travel data set, the passenger selects the number difference of the passengers with different travel modes to obtain the round trip-travel coefficient of the target passenger, which comprises the following specific methods:
according to the number of passengers with different travel modes selected by the passengers under the round trip time interval conforming to the travel time of the target passengers in the travel data set, the selected travel modes of the target passengers are respectively obtainedTravel coefficient of (2),Travel time factor, first age coefficient of target passenger, second age coefficient of target passenger;
the method for acquiring the round trip-trip coefficient of the target passenger comprises the following steps of:
wherein,indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (2); />Indicating the way of selecting the target passenger>Travel coefficients of (a); />Representing a travel time factor; />A first age factor representing a target passenger; />A second age factor representing a target passenger; />Representing a sigmoid normalization function; />Representing absolute value symbols.
Further, the number of passengers with different travel modes is selected by the passenger according to the round trip time interval of the travel data set, which accords with the travel time of the target passenger, and the travel modes selected by the target passenger are respectively obtainedThe specific methods of the travel coefficient, the travel time factor, the first age coefficient of the target passenger and the second age coefficient of the target passenger are as follows:
obtaining the number of passengers in the travel data set while the round trip time interval in the travel data set is the travel time of the target passengerWill->Recorded as travel time factor->Wherein->Representing the number of all passengers comprised by the data set; when acquiring the travel time of a target passenger with the round trip time interval in the travel data set, selecting a travel mode from all passengers>Is>Will->Selecting travel mode for target passenger>Travel coefficient of->The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of young passengers in all passengers +.>Will->First age factor marked as target passenger +.>The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of middle-aged passengers in all passengers is +.>Will->Second age factor marked as target passenger +.>。
Further, the method for adjusting the number of passengers selecting different travel modes under different ticket purchasing numbers by using the age-travel preference coefficient and the round trip-travel coefficient of the target passenger to obtain the side weight factors of the two nodes comprises the following specific steps:
according to the number of the passengers selecting different travel modes under different ticket buying numbers, obtaining the travel modes selected by the passengers with more than two ticket buying numbers in the travel data setThe probability of purchasing two or less passengers selecting travel mode>A first ticket purchase coefficient, and a second ticket purchase coefficient;
obtaining a selected travel mode of a target passengerThe specific calculation method of the ticket buying-traveling coefficient comprises the following steps:
wherein,indicating the way of selecting the target passenger>Ticket purchase-travel coefficient of (a); />Selecting travel mode for passenger with more than two tickets in travel data set>Probability of (2); />Indicating the passenger's selection travel mode with less than two tickets in the travel data set>Probability of (2); />Representing a first ticket purchasing coefficient; />Representing a second ticket purchasing coefficient; />Representing age and travel mode->Age-travel preference coefficient in between; />Indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (2);
and for any two nodes in the tourist map structure, selecting the maximum value in ticket buying-travel coefficients of all travel modes by a target passenger as an edge weight factor between the two nodes.
Further toThe number of the different travel modes is selected according to the number of the passengers with different ticket buying numbers, and the travel mode selected by the passengers with more than two ticket buying numbers in the travel data set is obtainedThe probability of purchasing two or less passengers selecting travel mode>The specific method comprises the following steps of:
acquiring the number of passengers with more than two tickets in the travel data setAcquiring the number of passengers with ticket purchase number less than two in the travel data set +.>The method comprises the steps of carrying out a first treatment on the surface of the Obtaining passenger with more than two tickets in the travel data set to select travel mode +.>Number of->Obtaining the passenger with the number of tickets purchased in the travel data set as less than two to select the travel mode +.>Number of->The method comprises the steps of carrying out a first treatment on the surface of the Will->Marking as the first ticket purchasing coefficient->Will->Recorded as a second ticket purchasing coefficient/>Wherein->Representing the number of all passengers comprised by the data set; will->Selecting travel mode of passenger with ticket purchasing quantity of more than two>Probability of->The method comprises the steps of carrying out a first treatment on the surface of the Will->Selecting travel mode of passenger with number of ticket purchased being less than two>Probability of->。
Further, the weighting the distance between nodes in the tourist map structure of the target passenger by using the edge weight factor to obtain the edge weight of the corresponding edge comprises the following specific steps:
taking any two nodes in the tourist map structure as a whole, and acquiring the proximity centrality of the whole in the tourist map structure by using a proximity centrality algorithm, and marking the proximity centrality as the joint proximity centrality of the two nodes corresponding to the whole;
the optimized edge weight of the edge between any two nodes in the tourist map structure of the target passenger is positively correlated with the distance between the areas corresponding to the two nodes in the tourist map structure, the joint proximity centrality of the two nodes and the edge weight factor of the edge corresponding to the two nodes respectively.
Further, the method for planning the travel route according to the side rights among the nodes in the tourist map structure of the passenger comprises the following specific steps:
the Floyd algorithm is used to obtain the optimal travel route of the target passenger from the travel starting point S to the travel ending point a in the tourist map structure.
The technical scheme of the invention has the beneficial effects that: the complexity of the selected different passengers under various factors is analyzed by applying a big data analysis technology, the age-travel preference coefficient and the round trip-travel coefficient of the target passengers are obtained to regulate the number of the passengers selecting different travel modes under different ticket buying numbers, so that the multi-aspect requirements and preferences of the passengers are comprehensively considered, the obtained side weight factors are utilized to weight the distance, the connectivity and the efficiency of the route are improved, the travel route planning is more accurate and reasonable, the influence degree of different influence factors on the travel route planning result can be reflected better, and the accuracy and the rationality of the travel route planning result are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of the intelligent travel route planning method based on big data analysis technology of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the intelligent travel route planning method based on the big data analysis technology according to the invention, and the specific implementation, structure, characteristics and effects thereof are described in detail below with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the intelligent travel route planning method based on the big data analysis technology provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a method for intelligent planning of a travel route based on big data analysis technology according to an embodiment of the present invention is shown, where the method includes the following steps:
step S001: a travel map structure is obtained from the travel data set, the travel time of the target passenger, and all the travel city sites to which the target passenger needs to travel.
It should be noted that, in order to facilitate planning of a travel route, a plurality of cities or regions to which a passenger needs to travel are generally regarded as one node, and a map structure is formed by positions of all nodes in a map; in addition, because various factors have influence on the travel planning of the passengers, the embodiment obtains the travel data of other passengers on the network through the data crawling technology based on the big data analysis technology, including the age of the passengers, the round trip time interval between the nodes of the passengers, the number of purchased tickets, the travel mode and the like, so as to analyze the influence of the travel data of all the passengers on the travel route by combining the big data analysis technology and obtain the travel route planning scheme.
Specifically, in order to implement the intelligent planning method for a tourist route based on the big data analysis technology provided in this embodiment, firstly, a tourist map structure of a passenger needs to be collected, and the specific process is as follows:
and marking the passenger needing to carry out the travel route planning as a target passenger, acquiring the travel time, the travel starting point S, the travel ending point A and the cities or regions needing to pass through of the target passenger, respectively taking the travel starting point, the travel ending point and all cities or regions needing to pass through of the passenger as a node, taking a connecting line between any two nodes as an edge, drawing a complete undirected graph by combining the positions of all the nodes in a map, and marking the complete undirected graph as a travel graph structure of the target passenger.
The method comprises the steps of acquiring a set formed by various travel data of a plurality of historical passengers by utilizing a web crawler technology, wherein the travel data are respectively the age of the passengers, the round trip time interval of the passengers between nodes, the number of purchased tickets and the travel mode.
In this embodiment, the age of the passenger in the plurality of travel data is divided into young N1 and middle N2, and the round trip time interval is more than three days for easy analysisAnd>ticket purchase quantity->Is divided into more than two pieces->And two or more pieces of->The travel mode is divided into automobile->Train->High-speed railway->And aircraft->In other embodiments or specific implementation processes, the age of the passenger, the round trip time interval between the nodes, the number of tickets purchased, and the way of dividing the travel modes of the passenger may be adjusted, and the embodiment is not limited specifically.
It should be noted that, the web crawler technology is an existing automatic web page content extraction technology, so that details are not repeated in this embodiment, in addition, in this embodiment, the web crawler technology specifically selects a focused web crawler based on a content evaluation crawling policy, and the specific type selection may be selected according to an actual implementation situation, which is not specifically limited in this embodiment.
So far, the tourist map structure and the travel data set of the passengers are obtained through the method.
Step S002: for any two nodes in the tourist map structure, selecting the quantity difference of different travel modes according to passengers of different ages in the travel data set to obtain an age-travel preference coefficient; according to the round trip time interval which accords with the travel time of the target passenger in the travel data set, the passenger selects the number difference of the passengers in different travel modes to obtain the round trip-travel coefficient of the target passenger; and adjusting the number of the passengers selecting different travel modes under different ticket purchasing numbers by using the age-travel preference coefficient and the round trip-travel coefficient of the target passenger, and obtaining the side weight factors of the two nodes.
It should be noted that, when planning a travel route, it is generally required to reduce the time on the way, so that a path planning is required, but the complexity of an actual traffic network and special requirements of passengers are ignored when the path planning process is only based on the distance between travel nodes, where the complexity of the traffic network is that the traffic flow, the speed limit and the congestion situation of different traffic modes, and the special requirements of the passengers include: the road is preferably selected in part of road sections, toll roads are avoided, attractive routes are selected, and the like, so that other factors are required to be comprehensively considered for planning the travel route of the passenger.
Because the passengers have certain relations among the ages of the passengers, the round trip time intervals of the passengers between nodes, the number of purchased tickets and the traveling modes in the traveling process, the method mainly comprises the following steps: young passengers tend to have a higher probability of selecting cars and trains due to a better exploration spirit and physical quality but a weaker economic ability, whereas middle-aged passengers tend to have a higher probability of selecting planes and high-speed trains due to a stronger economic ability and a comfortable travel; in addition, the round trip time interval reflects the stay time of the passengers in the travel area in the travel process, the ticket purchasing quantity reflects whether the passengers travel to the travel area or travel alone, and as the travel habits corresponding to young passengers and middle-aged passengers respectively, the travel modes of the passengers or the single person to different areas can be different, and various different factors can influence the travel route of the passengers in the travel.
Preferably, the method for acquiring the edge weight factor of the edge between any two nodes in the tourist map structure of the target passenger according to the travel data set specifically comprises the following steps:
for any two nodes in the travel graph structure, first, the number of all passengers included in the travel data set is obtainedAll passengers are middle-aged and young +.>And middle aged->The number of (2) is denoted by->And->Will->And->The ratio of (2) is recorded as young probability, and +.>And->The ratio of (2) is recorded as the middle-aged probability; acquiring the number of travel modes selected by young people in travel data setAcquiring the number of travel modes selected in middle-aged people in travel data set>Wherein->，/>Representing +.>Select travel mode +.>Quantity of->Representing +.>Select travel mode +.>Is the number of (3); will beAnd->The ratio of (2) is marked->Will->And->The ratio of (2) is marked->。
As an example, a specific calculation method of the age-travel preference coefficient is:
wherein,representing age and travel mode->Age-travel preference coefficient in between; />Representing +.>Select travel mode +.>Probability of (2); />Representing young age probability; />Representing +.>Select travel mode +.>Probability of (2);representing middle-aged probabilities; />Representing a sigmoid normalization function.
It should be noted that, the age-travel preference coefficient reflects the preference degree of different ages for different travel modes when traveling in the region corresponding to the two nodes, and the greater the age-travel preference coefficient, the two corresponding travelers in the tourist map structure are representedWhen the node is used as a travel area, young people select a travel modeThe greater the degree of preference; on the contrary, the smaller the age-trip preference coefficient is, the middle-aged population selects trip mode +.>The greater the degree of preference.
Then, when the travel time of the target passenger is obtained from the travel data set, the number of passengers in the travel data setWill->Recorded as travel time factor->The method comprises the steps of carrying out a first treatment on the surface of the When acquiring the travel time of a target passenger with the round trip time interval in the travel data set, selecting a travel mode from all passengers>Is>Will->Selecting travel mode for target passenger>Travel coefficient of->The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of young passengers in all passengers +.>Will->First age factor marked as target passenger +.>The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of middle-aged passengers in all passengers is +.>Will->Second age factor marked as target passenger +.>。
As an example, the specific calculation method of the round trip-trip coefficient of the target passenger is:
wherein,indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (2); />Indicating the way of selecting the target passenger>Travel coefficients of (a); />Representing a travel time factor; />A first age factor representing a target passenger; />A second age factor representing a target passenger; />Representing a sigmoid normalization function; />Representing absolute value symbols.
It should be noted that, because the round trip time interval in the travel process is one of the important factors affecting the travel mode, a shorter round trip time interval indicates that the travel mode is usually selected as a high-speed rail or an airplane when traveling at the corresponding place of two nodes, and a longer time interval indicates that the travel time is more abundant when traveling at the corresponding place of two nodes, and the selection of the specific travel mode is related to the preference of the age, the embodiment selects the travel mode by acquiring the target passengerTo reflect the travel mode of the target passenger during travel>Influence degree on travel route planning result, and target passenger selects travel mode->The greater the round-trip coefficient, the greater the degree of impact on travel route planning results and vice versa.
On the basis of obtaining the age-travel preference coefficient and the round trip-travel coefficient of the target passenger, further, obtaining the weight factors of the corresponding sides of any two nodes in the tourist map structure of the target passenger, wherein the concrete calculation method comprises the following steps:
acquiring the number of passengers with more than two tickets in the travel data setAcquiring more than two tickets in the travel data setNumber of passengers->The method comprises the steps of carrying out a first treatment on the surface of the Obtaining passenger with more than two tickets in the travel data set to select travel mode +.>Number of->Obtaining the passenger with the number of tickets purchased in the travel data set as less than two to select the travel mode +.>Number of->The method comprises the steps of carrying out a first treatment on the surface of the Will->Marking as the first ticket purchasing coefficient->Will->Marked as second ticket purchasing coefficient->Will->Marking as a second ticket purchasing coefficient; will->Selecting travel mode of passenger with ticket purchasing quantity of more than two>Probability of->The method comprises the steps of carrying out a first treatment on the surface of the Will->Selecting travel mode of passenger with number of ticket purchased being less than two>Probability of->。
As an example, the target passenger selects travel modeThe specific calculation method of the ticket buying-traveling coefficient comprises the following steps:
wherein,indicating the way of selecting the target passenger>Ticket purchase-travel coefficient of (a); />Selecting travel mode for passenger with more than two tickets in travel data set>Probability of (2); />Indicating the passenger's selection travel mode with less than two tickets in the travel data set>Probability of (2); />Representing a first ticket purchasing coefficient; />Representing a second ticket purchaseCoefficients; />Representing age and travel mode->Age-travel preference coefficient in between; />Indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (c).
And finally, for any two nodes in the tourist map structure, selecting the maximum value in ticket buying-travel coefficients of all travel modes by a target passenger as an edge weight factor of the corresponding edge of the two nodes.
It should be noted that, the number of tickets purchased in different travel modes reflects the needs of the passenger for route planning in the travel process of two areas corresponding to two nodes, and specifically, when the number of tickets purchased in different travel modes corresponding to different passengers is different, the number of tickets affects the travel route planning, because the number of tickets affects the arrangement and the cost of the travel route. If some passengers choose to ride a car and others choose to train, high speed rail, or plane, then the travel times and routing of these passengers may be different, and for passengers riding public transportation they need to follow the schedule and route of public transportation, which may limit their time and routing. For the passengers selecting the automobiles, the passengers can more freely arrange the travel time and the travel route, but the travel cost of the passengers is increased, so that the difference of the number of tickets corresponding to different travel modes purchased by different passengers needs to be considered in the travel route planning process, the travel route is reasonably arranged, the requirements of the passengers are met, and the travel cost is controlled.
Therefore, the larger the side weight factor is, the more reasonable the corresponding travel mode is selected by the target passenger in the travel process of the region corresponding to the two nodes, and the smaller the opposite is.
So far, the edge weight factors of the corresponding edges of any two nodes in the tourist map structure are obtained through the method.
Step S003: and weighting the distance between nodes in the tourist map structure of the target passenger by using the edge weight factors to obtain the edge weight of the corresponding edge.
It should be noted that, in the process of planning a travel path by using the Floyd algorithm, the path planning is usually performed according to the distance between the areas corresponding to the nodes in the structure of the travel map, but the path planning is performed according to the distance between the two places too ideally, so that the influence of different ages, different travel modes and different people on the travel path planning in the process of traveling is not fully considered.
Specifically, any two nodes in the tourist map structure are taken as a whole, the proximity centrality of the whole in the tourist map structure is obtained by using a proximity centrality algorithm, and the proximity centrality is recorded as the joint proximity centrality of the two nodes corresponding to the whole.
As an example, the specific calculation method of the optimized edge weight of the edge between any two nodes in the tourist map structure of the target passenger is as follows:
wherein,representing the optimized edge weight of the edge between two nodes in the tourist map structure; />Representing the distance between two nodes corresponding areas in the tourist map structure; />Representing two nodes in a tourist map structureIs close to centrality; />The edge weight factors of the corresponding edges of any two nodes in the tourist map structure are represented; />Representing a linear normalization function.
It should be noted that, the proximity centrality of the nodes reflects the distance between the nodes and other nodes in the tourist map structure, that is, the average shortest path degree from the nodes to other nodes, and the distance between the nodes is weighted by combining the proximity centrality of the nodes, so that a part of the node seat path with a shorter distance from other nodes can be more easily selected in path planning, the total distance of the path and the time cost of the path are reduced, and the connectivity and the efficiency of the path are improved.
In addition, the distances among the nodes are weighted by combining the edge weight factors, so that the optimized edge weight can reflect the influence degree of different influence factors of the corresponding nodes on the travel route planning result.
So far, the optimized edge weight of the edge between any two nodes in the tourist map structure of the target passenger is obtained through the method.
Step S004: and planning the travel route according to the side rights among the nodes in the tourist map structure of the passenger.
Specifically, the Floyd algorithm is utilized to obtain the optimal travel route of the target passenger from the travel starting point S to the travel ending point a in the travel chart structure.
Note that, the chinese name of the Floyd algorithm is the florid algorithm, and since the Floyd algorithm is an existing path planning algorithm, the description of this embodiment is omitted.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The intelligent travel route planning method based on the big data analysis technology is characterized by comprising the following steps of:
acquiring a set formed by various travel data of a plurality of historical passengers by utilizing a web crawler technology, wherein the travel data are respectively the age of the passengers, the round trip time interval between nodes, the ticket purchasing quantity and the travel mode; the age of the passenger in various travel data is classified as youngAnd middle aged->The round trip time interval is more than three days and less than three days, the ticket purchasing quantity is divided into more than two sheets and less than two sheets, and the travel mode is divided into automobile ∈ ->Train->High-speed railway->And aircraft->Marking a passenger needing to carry out travel route planning as a target passenger, and acquiring travel time of the target passenger and a tourist map structure formed by all tourist city places to which the target passenger needs to go, wherein the tourist map structure comprises a plurality of nodes;
for any two nodes in the tourist map structure, selecting the quantity difference of different travel modes according to passengers of different ages in the travel data set to obtain an age-travel preference coefficient; according to the round trip time interval which accords with the travel time of the target passenger in the travel data set, the passenger selects the number difference of the passengers in different travel modes to obtain the round trip-travel coefficient of the target passenger; adjusting the number of passengers selecting different travel modes under different ticket purchasing numbers by using the age-travel preference coefficient and the round trip-travel coefficient of the target passenger to obtain side weight factors of the two nodes;
weighting the distance between nodes in the tourist map structure of the target passenger by using the edge weight factors to obtain edge weights between the nodes;
and planning the travel route according to the side rights among the nodes in the tourist map structure of the passenger.
2. The intelligent tourist route planning method based on big data analysis technology according to claim 1, wherein the specific acquisition method of the tourist map structure formed by all tourist city sites to which the target passenger needs to go is as follows:
the method comprises the steps of obtaining a travel starting point S, a travel ending point A and a region needing to pass through of a target passenger, taking the travel starting point S, the travel ending point A and all cities or regions needing to pass through of the passenger as a node respectively, taking a connecting line between any two nodes as an edge, drawing a complete undirected graph by combining the positions of all nodes in a map, and recording the complete undirected graph as a travel graph structure of the target passenger.
3. The intelligent travel route planning method based on big data analysis technology according to claim 1, wherein the method for obtaining the age-travel preference coefficient according to the number difference of the travel modes selected by the passengers with different ages in the travel data set comprises the following specific steps:
selecting the number of different travel modes according to passengers of different ages in the travel data set to respectively obtain young peopleSelect travel mode +.>Probability of (2), young, middle-aged +.>Select travel mode +.>And middle-aged probabilities, wherein；
According to young peopleSelect travel mode +.>The ratio of the probability of (2) to the young's probability is given by a first factor according to +.>Select travel mode +.>Obtaining a second factor from the ratio of the probability of (2) to the probability of middle aged;
the age-travel preference coefficient is positively correlated with the difference between the first factor and the second factor.
4. The intelligent travel route planning method based on big data analysis technology according to claim 3, wherein the number of different travel modes is selected according to passengers of different ages in the travel data set, and young people are obtained respectivelySelect travel mode +.>Probability of (2), young, middle-aged +.>Select travel mode +.>The specific method comprises the following steps of:
acquiring the number of all passengers included in a travel data setAll passengers are middle-aged and young +.>And middle aged->The number of (2) is denoted by->And->Will->And->The ratio of (2) is recorded as young probability, and +.>And->The ratio of (2) is recorded as the middle-aged probability; acquiring young in a travel data set>Select travel mode +.>Number of->Acquiring middle-aged +.>Select travel mode +.>Number of->Will->And->The ratio of (2) is marked->Will->And->Is recorded as the ratio of。
5. The intelligent travel route planning method based on big data analysis technology according to claim 3, wherein the method for obtaining the round trip-trip coefficient of the target passenger by selecting the number difference of the passengers with different travel modes according to the round trip time interval of the travel data set, wherein the round trip time interval is in accordance with the travel time of the target passenger comprises the following specific steps:
according to the number of passengers with different travel modes selected by the passengers under the round trip time interval conforming to the travel time of the target passengers in the travel data set, the selected travel modes of the target passengers are respectively obtainedTravel coefficient of the target passenger, travel time factor, first age coefficient of the target passenger, second age coefficient of the target passenger;
the method for acquiring the round trip-trip coefficient of the target passenger comprises the following steps of:
wherein,indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (2); />Indicating the way of selecting the target passenger>Travel coefficients of (a); />Representing a travel time factor; />A first age factor representing a target passenger; />A second age factor representing a target passenger; />Representing a sigmoid normalization function; />Representing absolute value symbols.
6. The intelligent travel route planning method according to claim 5, wherein the number of passengers selecting different travel modes is determined according to the round trip time interval of travel time meeting the target passenger in the travel data set, and the selected travel modes of the target passenger are obtainedThe specific methods of the travel coefficient, the travel time factor, the first age coefficient of the target passenger and the second age coefficient of the target passenger are as follows:
obtaining the number of passengers in the travel data set while the round trip time interval in the travel data set is the travel time of the target passengerWill->Recorded as travel time factor->Wherein->Representing the number of all passengers comprised by the data set; when acquiring the travel time of a target passenger with the round trip time interval in the travel data set, selecting a travel mode from all passengers>Is>Will->Selecting travel mode for target passenger>Travel coefficient of->The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of young passengers in all passengers +.>Will->First age factor marked as target passenger +.>The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the travel time of the target passenger with the round trip time interval in the travel data set, the number of middle-aged passengers in all passengers is +.>Will->Second age factor marked as target passenger +.>。
7. The intelligent travel route planning method based on big data analysis technology according to claim 3, wherein the method for adjusting the number of different travel modes selected by the passengers under different ticket purchasing numbers by using the age-travel preference coefficient and the round trip-travel coefficient of the target passenger to obtain the side weight factors of the two nodes comprises the following specific steps:
according to the number of the passengers selecting different travel modes under different ticket buying numbers, obtaining the travel modes selected by the passengers with more than two ticket buying numbers in the travel data setThe probability of purchasing two or less passengers selecting travel mode>A first ticket purchase coefficient, and a second ticket purchase coefficient;
obtaining a selected travel mode of a target passengerThe specific calculation method of the ticket buying-traveling coefficient comprises the following steps:
wherein,indicating the way of selecting the target passenger>Ticket purchase-travel coefficient of (a); />Selecting travel mode for passenger with more than two tickets in travel data set>Probability of (2); />Indicating the passenger's selection travel mode with less than two tickets in the travel data set>Probability of (2); />Representing a first ticket purchasing coefficient; />Representing a second ticket purchasing coefficient;representing age and travel mode->Age-travel preference coefficient in between; />Indicating the way of selecting the target passenger>To-and-fro-travel coefficients of (2);
and for any two nodes in the tourist map structure, selecting the maximum value in ticket buying-travel coefficients of all travel modes by a target passenger as an edge weight factor between the two nodes.
8. The intelligent travel route planning method based on big data analysis technology according to claim 7, wherein the number of different travel modes is selected according to the number of different tickets purchased, and the travel mode selected by the passengers with more than two tickets purchased in the travel data set is obtainedThe probability of purchasing two or less passengers selecting travel mode>The specific method comprises the following steps of:
acquiring the number of passengers with more than two tickets in the travel data setAcquiring the number of passengers with ticket purchase number less than two in the travel data set +.>The method comprises the steps of carrying out a first treatment on the surface of the Obtaining passenger with more than two tickets in the travel data set to select travel mode +.>Number of->Obtaining the passenger with the number of tickets purchased in the travel data set as less than two to select the travel mode +.>Number of->The method comprises the steps of carrying out a first treatment on the surface of the Will->Marking as the first ticket purchasing coefficient->Will->Marked as second ticket purchasing coefficient->Wherein->Representing the number of all passengers comprised by the data set; will->Selecting travel mode of passenger with ticket purchasing quantity of more than two>Probability of (2)The method comprises the steps of carrying out a first treatment on the surface of the Will->Selecting travel mode of passenger with number of ticket purchased being less than two>Probability of->。
9. The intelligent travel route planning method based on big data analysis technology according to claim 2, wherein the weighting the distance between nodes in the tourist map structure of the target passenger by using the edge weight factor to obtain the edge weight of the corresponding edge comprises the following specific steps:
taking any two nodes in the tourist map structure as a whole, and acquiring the proximity centrality of the whole in the tourist map structure by using a proximity centrality algorithm, and marking the proximity centrality as the joint proximity centrality of the two nodes corresponding to the whole;
the optimized edge weight of the edge between any two nodes in the tourist map structure of the target passenger is positively correlated with the distance between the areas corresponding to the two nodes in the tourist map structure, the joint proximity centrality of the two nodes and the edge weight factor of the edge corresponding to the two nodes respectively.
10. The intelligent travel route planning method based on big data analysis technology according to claim 2, wherein the travel route planning is performed according to the side rights among nodes in the tourist map structure of the passenger, comprising the following specific steps:
the Floyd algorithm is used to obtain the optimal travel route of the target passenger from the travel starting point S to the travel ending point a in the tourist map structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410205926.8A CN117787527B (en) | 2024-02-26 | 2024-02-26 | Tour route intelligent planning method based on big data analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410205926.8A CN117787527B (en) | 2024-02-26 | 2024-02-26 | Tour route intelligent planning method based on big data analysis technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117787527A true CN117787527A (en) | 2024-03-29 |
| CN117787527B CN117787527B (en) | 2024-04-26 |
Family
ID=90392998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410205926.8A Active CN117787527B (en) | 2024-02-26 | 2024-02-26 | Tour route intelligent planning method based on big data analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117787527B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140236641A1 (en) * | 2013-02-20 | 2014-08-21 | Mark C. Dawkins | System for Facilitating Travel Related Transactions |
| CN105512773A (en) * | 2015-12-25 | 2016-04-20 | 中国民航信息网络股份有限公司 | Passenger travel destination prediction method and device |
| CN112419567A (en) * | 2020-11-09 | 2021-02-26 | 成都中科大旗软件股份有限公司 | Comprehensive management system based on text and travel fusion |
| CN113239269A (en) * | 2021-04-30 | 2021-08-10 | 河海大学 | Improved recommendation algorithm-based travel route customization method |
| CN113516500A (en) * | 2021-04-23 | 2021-10-19 | 深圳市威斯登信息科技有限公司 | Implementation method and system based on big data business and travel operation platform |
| CN113886699A (en) * | 2021-10-12 | 2022-01-04 | 北京交通大学 | Travel and trip integrated planning method considering travel demands and preferences of user |
| US20230325732A1 (en) * | 2020-09-09 | 2023-10-12 | Hakuhodo Dy Holdings Inc. | Planning system and planning method |
| CN116882599A (en) * | 2022-03-28 | 2023-10-13 | 中国移动通信集团江苏有限公司 | Planning method and device for travel route |
-
2024
- 2024-02-26 CN CN202410205926.8A patent/CN117787527B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140236641A1 (en) * | 2013-02-20 | 2014-08-21 | Mark C. Dawkins | System for Facilitating Travel Related Transactions |
| CN105512773A (en) * | 2015-12-25 | 2016-04-20 | 中国民航信息网络股份有限公司 | Passenger travel destination prediction method and device |
| US20230325732A1 (en) * | 2020-09-09 | 2023-10-12 | Hakuhodo Dy Holdings Inc. | Planning system and planning method |
| CN112419567A (en) * | 2020-11-09 | 2021-02-26 | 成都中科大旗软件股份有限公司 | Comprehensive management system based on text and travel fusion |
| CN113516500A (en) * | 2021-04-23 | 2021-10-19 | 深圳市威斯登信息科技有限公司 | Implementation method and system based on big data business and travel operation platform |
| CN113239269A (en) * | 2021-04-30 | 2021-08-10 | 河海大学 | Improved recommendation algorithm-based travel route customization method |
| CN113886699A (en) * | 2021-10-12 | 2022-01-04 | 北京交通大学 | Travel and trip integrated planning method considering travel demands and preferences of user |
| CN116882599A (en) * | 2022-03-28 | 2023-10-13 | 中国移动通信集团江苏有限公司 | Planning method and device for travel route |
Non-Patent Citations (3)
| Title |
|---|
| 刘士杰: "考虑个性化出行需求的多模式交通路径规划研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 01, 15 January 2023 (2023-01-15), pages 1 - 69 * |
| 张梅梅等: "北京市旅游交通方式选择行为研究", 《交通运输研究》, vol. 3, no. 02, 19 May 2017 (2017-05-19), pages 31 - 36 * |
| 肖春景等: "基于动态聚类的旅游线路推荐", 《计算机应用》, vol. 37, no. 08, 10 August 2017 (2017-08-10), pages 2395 - 2400 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117787527B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Carsharing in Shanghai, China: analysis of behavioral response to local survey and potential competition | |
| Buehler et al. | Travel behavior in aging societies: Comparison of Germany and the United States | |
| CN107680391A (en) | Two pattern fuzzy control methods of crossroad access stream | |
| CN106709591A (en) | Cooperative car-pooling route selection method with uncertain demand in Internet of Vehicles environment | |
| Shirgaokar et al. | Using Twitter to investigate responses to street reallocation during COVID-19: Findings from the US and Canada | |
| CN107220733A (en) | Optimization method is started based on the beginning and the end point set customization public transport that internet and bus or train route are cooperateed with | |
| CN111311002B (en) | Bus trip planning method considering active transfer of passengers in transit | |
| Domènech et al. | Tourists' transport modal choices in Barcelona | |
| Manifesty et al. | A case study of a 15-minute city concept in singapore’s 2040 land transport master plan: 20-minute towns and a 45-minute city | |
| Kruszyna | Investment challenges pertaining to the achievement of the goals of the Mobility Policy based on the analysis of the results of traffic surveys in Wroclaw | |
| Danilina et al. | Development of «Park-and-Ride» system as a tool for sustainable access control managing | |
| CN117787527B (en) | Tour route intelligent planning method based on big data analysis technology | |
| CN116882609A (en) | Customized bus route multi-objective optimization method based on improved track clustering algorithm | |
| CN116129651B (en) | Traffic capacity calculation method based on resident trip behavior selection | |
| Curtis | The windscreen world of land use transport integration: experiences from Perth, WA, a dispersed city | |
| CN113053156B (en) | Intelligent bus station addressing method based on bus radius method | |
| Lieberman et al. | Creating a new century of transit opportunity: Strategic planning for transit | |
| Vijayakumar | Optimal vehicle size for road‐based urban public transport in developing countries | |
| Preston | The total social cost (TSC) of public transport modes | |
| Jones | 27. Rethinking the urban arterial: from car mobility to urban liveability | |
| Calloway et al. | Complete streets and implementation in small towns | |
| Sun et al. | Measuring the influence of built environment on walking behavior: An accessibility approach | |
| Bagul et al. | Analysis of autorickshaw as an intermediate paratransit system | |
| MAKAROVA et al. | INTEGRATION OF BIKE LANES NETWORK WITH PUBLIC TRANSPORT ROUTES TO SOLVE THE LAST MILE PROBLEM | |
| Li et al. | The Integration of Public Bicycle and Metro Transit: A Case Study in Suzhou, China |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |