CN110887501B - Traffic navigation method and device for variable destination - Google Patents
Traffic navigation method and device for variable destination Download PDFInfo
- Publication number
- CN110887501B CN110887501B CN201911120743.1A CN201911120743A CN110887501B CN 110887501 B CN110887501 B CN 110887501B CN 201911120743 A CN201911120743 A CN 201911120743A CN 110887501 B CN110887501 B CN 110887501B
- Authority
- CN
- China
- Prior art keywords
- regret
- destination
- user
- path
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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"
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention discloses a traffic navigation method and device for variable destinations, and belongs to the technical field of intelligent traffic services. The method comprises the following steps: acquiring the regret level of a user; determining a destination primary selection set through the POI classification code information; sorting the primary destination set according to the regret level, and recommending a destination to a user; and searching the path by taking the minimum regret impedance of the destination and the path as a decision criterion to determine the navigation route information. The application of the invention can reasonably guide the user to change the decision, effectively improve the existing travel efficiency, reduce traffic jam, avoid the waste of commercial resources, and solve the problem that the user does not have reasonable guidance for changing the destination due to road jam and other reasons during travel.
Description
Technical Field
The invention relates to the field of intelligent traffic service, in particular to a traffic navigation method and device for variable destinations.
Background
With the economic growth, the number of private cars in operation has increased dramatically. The user can not determine the reception condition of the destination because the user does not rationally arrange a trip plan or does not timely obtain information such as trip, parking, dining and the like, thereby causing queuing congestion and influencing personal trip experience. When the users know that the initial destination reception capacity is saturated in traveling such as tourism or shopping, the remorse mind is generated and the users want to change the traveling destination to plan a path again.
At present, although there are many methods for path planning, the method is limited to finding the shortest motion trajectory between the change start point and the determined destination. For the case where both the destination and the path are uncertain, the path planning needs to be further developed.
Disclosure of Invention
In order to further solve the problems, the invention provides a variable-destination-oriented traffic navigation method and device, which are used for establishing a random regret model based on the quantification and grading of the regret degree of a user, and recommending and sequencing a front destination to the user on a congested road section through big data and a vehicle networking technology based on the principle of random regret minimization; and then determining navigation route information by taking the minimum regret impedance of the destination-path as a decision criterion through improving an ant colony algorithm. The invention not only greatly improves the travel experience of the user, but also effectively improves the existing travel efficiency of the public, reduces traffic jam and avoids the waste of commercial resources.
The invention provides a traffic navigation method facing to a variable destination, which specifically comprises the following steps:
s1, acquiring the regret level of the user;
s2, determining a destination primary selection set through the POI classification code information;
s3, calculating and sorting the selection probability of the destination primary selection set according to the regret level through a random regret model, and recommending the destination to a user;
and S4, searching a path by taking the minimum regret impedance of the destination and the path as a decision criterion, and determining navigation route information.
Preferably, the process of obtaining the remorse level of the user includes:
the regret degree index is obtained through survey data statistics, and the regret grade is divided according to the regret degree index;
and according to the current position of the user, pre-judging the regret level of the user at the current position.
Preferably, through statistics on the survey data, the regret index is calculated according to the ratio of the expected loss time of the position where the decision maker is located to the maximum loss time of the psychological bearing when the emotion is stable. And according to the pareto rule, dividing the actual regret degree of a decision maker into four grades through a regret degree index, wherein the regret degree index is respectively as follows: the regret is I, the light regret is II, the heavy regret is III, and the extreme regret is IV.
The regret index calculation formula is as follows:
in the formula:
Xm(ii) an mth attribute prediction loss representing an impact decision; dmaxIndicating the maximum loss of mental capacity at emotional stability.
Preferably, the current position of the user is taken as the user decision point r.
According to the current position of the user and the road condition of the current position, the regret level of the user at the current position is judged in advance, and the specific process comprises the following steps:
the current expected loss time of the user is calculated through a variable user decision point r by acquiring the road condition information of the current position of the user, and the expected loss time is usually set as the difference value between the current predicted arrival time at the destination and the arrival time at the destination under the average road condition.
Optionally, the expected loss time may also be set as a difference between the time of any one of the current predicted arrival paths and the time of arrival at the current predicted arrival path under the average road condition, and in this case, the calculation method of the maximum loss time of the psychological bearing when the emotion of the user is stable may also be changed accordingly.
Preferably, the process of determining the initial destination set according to the POI classification code information includes:
sequentially screening by using an initial destination (PD), a same-name Subclass (SD), a different-name subclass (DD) and a middle class (MD) of the initial destination as screening conditions through the POI classification code information;
taking more than one destination as the primary destination collection G in the order from near to far according to the distance from the current position of the user in the screened destination collection0Including the initial destination.
Preferably, the initial destination (PD) is divided into a plurality of types according to the kind of service provided, and candidate destinations of corresponding types are obtained, the types include but are not limited to restaurants, malls, tourist and leisure attractions, parking lots, and the types are further subdivided into subclasses, and the screening is performed according to the above screening conditions, wherein:
a same-name subclass, i.e., a different location that is the same name as the original destination;
a heterogeneous subclass, i.e., a place having a name different from that of the original destination but belonging to the same subclass;
medium class, i.e. the same type of place to which the original destination belongs.
Preferably, the primary destination set G0The following 3 conditions need to be satisfied:
condition 1: g0The candidate destinations in (2) may all obtain geographic location information from the API;
condition 2: g0Most of the destination names have a correlation with the initially decided destination name;
condition 3: g0The candidate destinations in (1) only consider the destination types that the user may select, and exclude destination types that the user does not consider selecting, such as school, home address, office, and the like.
Preferably, the process of calculating and ranking the selection probability of the destination primary set according to the regret level through a random regret model, and recommending a destination to a user includes:
predicting the repentance level generated by the user, and judging whether the user changes the current destination according to the repentance level;
when the user will changeWhen the current destination is changed, calculating the primary destination set G selected by the user according to the principle of minimum decision remorse and through a random remorse model of the variable destination0And (4) sorting all destinations in the primary destination selection set from large to small according to the selection probability of the destinations in the primary destination selection set, and recommending a preset number of destinations to the user.
Optionally, according to the calculation condition of the actual probability or a preset numerical value of the user, the top n destinations in the sorted destination set are recommended to the user.
Preferably, after recommending the destination to the user, the method further includes:
when the user does not change the current destination, the recommendation is stopped.
Optionally, if the user is at the regret level i or iv, a new destination is not recommended to the user, and navigation is performed according to the original destination and the path. If the user is at regret levels II and III, the destination is recommended to the user.
Optionally, the policy of the merchant for pushing the advertisement is mainly determined by the distance between the user decision point r and each destination, and different recommendation schemes are adopted when the decision point r is at different regret levels.
Preferably, the process of searching for a path with minimum repentance impedance of a destination-path as a decision criterion includes:
calculating the regret value of the destination through the random regret model;
multiplying the proportion of all path impedances shared by each road section by the destination regret value of each overlapped road section to obtain the regret impedance, wherein the path impedance is calculated by adopting an impedance (BPR) function developed by the U.S. road bureau;
searching a path according to the regret impedance using an improved ant colony algorithm.
Preferably, after searching for a path according to the regret impedance by using the improved ant colony algorithm, the method further includes:
and calculating the state transition probability according to the concentration of the pheromone on the path and heuristic information of the path, taking the minimum path regret value as a search criterion of the pheromone, and determining navigation information through an pheromone updating function with preset iteration times.
The invention also provides a traffic navigation device facing the variable destination, which comprises the following modules:
the analysis module is used for acquiring the regret level of the user;
the screening module determines a destination primary selection set through the POI classification code information;
the sorting module calculates and sorts the selection probability of the destination primary selection set according to the regret level through a random regret model, and recommends a destination to a user;
and the navigation module searches a path by taking the minimum regret impedance of the destination and the path as a decision criterion and determines navigation route information.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a variable destination oriented traffic navigation method as set forth in the above method embodiments when executing the computer program.
The present invention also provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the steps of a variable destination oriented traffic navigation method described in the above method embodiments.
Compared with the prior art, the invention has the following beneficial effects:
(1) the degree of regret can be used for measuring the degree of psychological regret of a decision maker, the regret stage of the user in a congested road section can be pre-judged, the user can be reasonably guided to change the decision, and a more detailed scheme can be provided for a recommended destination when a decision point r is in different regret stages.
(2) The constructed random regret model facing the variable destination can calculate the regret value of each destination selected by the user, ensure the minimum regret perception of the user after changing the destination, recommend the user according to the probability of destination selection and induce the user, effectively improve the existing travel efficiency, reduce traffic jam and avoid the waste of commercial resources.
(3) And improving the ant colony algorithm search path by taking the minimum regret impedance of the destination-path as a decision criterion, and distributing the calculated destination regret value to each road section according to the path impedance to obtain the regret impedance of each road section. The path navigation when the destination and the path are not clear is comprehensively considered, the path search with only a fixed OD in the prior art can be supplemented, and the variable destination path navigation technology is not considered.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a logical block diagram of a traffic navigation method in an embodiment of the present invention;
FIG. 2 is a flow chart of a traffic navigation method in an embodiment of the present invention;
FIG. 3 is a plot of the cumulative frequency distribution function of the repentance index value in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a regret area in an embodiment of the present invention;
FIG. 5 is a logic diagram of an improved ant colony algorithm in an embodiment of the present invention;
FIG. 6 is a schematic diagram of an actual application of the improved ant colony algorithm in an embodiment of the invention;
FIG. 7 is a schematic structural diagram of a traffic navigation device according to an embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a traffic navigation apparatus in an embodiment of the present invention;
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The embodiment of the invention provides a traffic navigation method facing to a variable destination, the overall logic block diagram of the method is shown in fig. 1, the specific method flowchart is shown in fig. 2, and referring to fig. 2, the method specifically comprises the following steps:
s1, acquiring the regret level of the user;
s2, determining a destination primary selection set through the POI classification code information;
s3, calculating and sorting the selection probability of the destination primary selection set according to the regret level through a random regret model, and recommending the destination to a user;
and S4, searching a path by taking the minimum regret impedance of the destination and the path as a decision criterion, and determining navigation route information.
Preferably, the process of obtaining the remorse level of the user includes:
the regret degree index is obtained through survey data statistics, and the regret grade is divided according to the regret degree index;
and according to the current position of the user, pre-judging the regret level of the user at the current position.
Preferably, through statistics on the survey data, the regret index is calculated according to the ratio of the expected loss time of the position where the decision maker is located to the maximum loss time of the psychological bearing when the emotion is stable. And according to the pareto rule, dividing the actual regret degree of a decision maker into four grades through a regret degree index, wherein the regret degree index is respectively as follows: the regret is I, the light regret is II, the heavy regret is III, and the extreme regret is IV.
In a specific embodiment, the regret level is divided according to a regret index, and the regret index is defined as the ratio of the expected loss of a decision maker to the maximum loss of psychological bearing when the emotion is stable. Typically, the user will generate a regret when the predicted loss is greater than the maximum loss sustained by the mind. Taking the expected loss T1 of 20% bit ratio as the regret demarcation point, the expected loss T2 of 50% bit ratio as the mild regret and the severe regret demarcation point, and the expected loss T3 of 80% bit ratio as the severe regret and the extreme regret demarcation point (T1< T2< T3) through the cumulative frequency distribution curve of the ratios, please refer to FIG. 3.
The regret index calculation formula is as follows:
in the formula:
Xm(ii) an mth attribute prediction loss representing an impact decision; dmaxIndicating the maximum loss of mental capacity at emotional stability.
Preferably, the current position of the user is taken as the user decision point r.
According to the current position of the user and the road condition of the current position, the regret level of the user at the current position is judged in advance, and the specific process comprises the following steps:
the current expected loss time of the user is calculated through a variable user decision point r by acquiring the road condition information of the current position of the user, and the expected loss time is usually set as the difference value between the current predicted arrival time at the destination and the arrival time at the destination under the average road condition.
Optionally, the expected loss time may also be set as a difference between the time of any one of the current predicted arrival paths and the time of arrival at the current predicted arrival path under the average road condition, and in this case, the calculation method of the maximum loss time of the psychological bearing when the emotion of the user is stable may also be changed accordingly.
The regret level is divided into four levels according to the ratio between the expected loss and the maximum loss of psychological bearing, see in particular fig. 4. The red point represents the destination PD of the original trip, and the regret index from the variable decision point r to the original destination divides the psychological regret perception of the user into 4 stages. Decision points within the time of square circle loss T1 from the original destination belong to non-regret stages, a mild regret stage within the time of square circle loss T2, a severe regret stage within the time of square circle loss T3, an extreme regret stage outside the range, and the four regret stages divided by regret perception correspond to obtain the current regret level of the user.
Preferably, the process of determining the initial destination set according to the POI classification code information includes:
sequentially screening by using an initial destination (PD), a same-name Subclass (SD), a different-name subclass (DD) and a middle class (MD) of the initial destination as screening conditions through the POI classification code information;
taking more than one destination as the primary destination collection G in the order from near to far according to the distance from the current position of the user in the screened destination collection0Including the initial destination.
In a particular embodiment, the initial set of destinations is determined by point of interest POI category code information. Acquiring a congested road section of a road network through the traffic situation information of the Goodpastel API, and submitting a destination name PD initially decided by a user i at a road condition k stage and a decision point r at the position to a terminal; the terminal obtains a plurality of related destination names, takes more than one destination in the set of related destinations and includes the primary decision as a primary selection set G0。
The screening conditions are explained below:
a same-name subclass, i.e., a different location that is the same name as the original destination;
a heterogeneous subclass, i.e., a place having a name different from that of the original destination but belonging to the same subclass;
medium class, i.e. the same type of place to which the original destination belongs.
In a specific embodiment, G0The screened destinations take user i initial destination PD as Kendeji, same-name SD (S1 Kendeji 2), same-class DD (S2 McDonald, S3 hamburg king), and same-class MD (S4 dinner), and the actual loss time from decision point r to each type of destination is TPD>TS4>TS1>TS3>TS2。
Preferably, the probability rankings are different when the decision points are at different regret levels, that is, when the user has different regret indexes, in the above embodiment, if the user i is at other regret levels, a more appropriate candidate destination is recommended to the user according to the ranking after the change.
Preferably, the initial destination (PD) is divided into a plurality of types according to the kind of service provided, and candidate destinations of corresponding types are obtained, the types including but not limited to restaurants, malls, tourist and leisure attractions, parking lots, and the screening is performed according to the above screening conditions.
Preferably, the primary destination set G0The following 3 conditions need to be satisfied:
condition 1: g0The candidate destinations in (2) may all obtain geographic location information from the API;
condition 2: g0Most of the destination names have a correlation with the initially decided destination name;
condition 3: g0The candidate destinations in (1) only consider the destination types that the user may select, and exclude destination types that the user does not consider selecting, such as school, home address, office, and the like.
Preferably, the process of calculating and ranking the selection probability of the destination primary set according to the regret level through a random regret model, and recommending a destination to a user includes:
predicting the repentance level generated by the user, and judging whether the user changes the current destination according to the repentance level;
when the user changes the current destination, the primary destination set G selected by the user is calculated through a random regret model of the variable destination according to the principle of minimum decision regret0And (4) sorting all destinations in the primary destination selection set from large to small according to the selection probability of the destinations in the primary destination selection set, and recommending a preset number of destinations to the user.
In a specific embodiment, the minimum regret after the user changes the destination is ensured, so the random regret model facing the variable destination with the minimum regret as the target is calculated as follows:
in the formula, Xjm,XsmThe mth attribute value, M being 1,2, …, M, for the other destination j and the selected destination s, respectively. Wherein the content of the first and second substances,sis the regret degree fingerThe regret degree of a decision-making by a runner can be measured. PsIndicating the probability of the traveler changing the selection destination s.
Optionally, according to the calculation condition of the actual probability or a preset numerical value of the user, the top n destinations in the sorted destination set are recommended to the user.
Preferably, after recommending the destination to the user, the method further includes:
when the user does not change the current destination, the recommendation is stopped.
Optionally, if the user is at the regret level i or iv, a new destination is not recommended to the user, and navigation is performed according to the original destination and the path. If the user is at regret levels II and III, the destination is recommended to the user.
Optionally, the policy of the merchant for pushing the advertisement is mainly determined by the distance between the user decision point r and each destination, and different recommendation schemes are adopted when the decision point r is at different regret levels.
Preferably, the process of searching for a path with minimum repentance impedance of a destination-path as a decision criterion includes:
calculating the regret value of the destination through the random regret model;
multiplying the proportion of all path impedances shared by each road section by the destination regret value of each overlapped road section to obtain the regret impedance;
searching a path according to the regret impedance using an improved ant colony algorithm.
With the minimum regret impedance of the destination-path as a decision criterion, the specific flow of searching the path by the ant colony algorithm is improved, referring to fig. 5, the regret value of the calculated destination is distributed to each road section according to the path impedance, and the regret impedance of each road section is obtained. And calculating the state transition probability according to the information concentration on the path and heuristic information of the path, improving an updating formula of the pheromone of the ant colony algorithm, and determining navigation information by taking a road section regret value as a search criterion.
In an embodiment of the present invention, the path impedance is calculated using a developed impedance (BPR) function by the U.S. road agency.
In the embodiment of the present invention, fig. 6 is a road network topology diagram of 12 road segments and 6 paths. The 6 paths are respectively <1,2,5,10>, <1,4,7,10>, <1,4,9,12>, <3,6,7,10>, <3,6,9,12>, <3,8,11,12>, and the optimal path is <3,6,7,10> by improving the ant colony algorithm calculation.
Preferably, after searching for a path according to the regret impedance by using an improved ant colony algorithm, the method further includes:
and calculating the state transition probability according to the concentration of the pheromone on the path and heuristic information of the path, taking the minimum path regret value as a search criterion of the pheromone, and determining navigation information through an pheromone updating function with preset iteration times.
The introduction to the improved ant colony algorithm is as follows:
state transition probability P: probability of ant colony transition from node a to node b at time t.
In the formula: allowedkRepresenting the set of nodes which the ant allows to select next; tau isab(t) represents a link at time t<a,b>α are the heuristic pheromone importance degree and the pheromone importance degree, ηab(t) represents the expected degree of transfer of ants from node a to node b, and is expressed as:is a road section between two nodes a and b<a,b>The regret value of. Repentance of road sectionThe method comprises the steps of calculating a random regret model facing a variable destination to obtain a regret value of the destination, distributing the regret value to each road section according to path impedance, and obtaining the regret impedance of each road section.
Pheromone: the ants release certain "pheromones" which gradually decrease over time and generate a certain amount of pheromones when passing through the path, and new ants determine the next action according to the concentration of the previous pheromones.
Heuristic information: ants are transferred from node a to the desired extent of node b.
Pheromone concentration: ants are on road section at time t<a,b>Concentration of released pheromone, tauab(t) of (d). The ant pheromone updating formula is as follows:
whereinRepresenting the path of the kth ant between the time t and the time t +1<a,b>With increasing pheromone concentration, Q is a constant that represents the total amount of pheromone concentration released by each ant.
The embodiment of the invention also provides a traffic navigation device facing to the variable destination, the structural schematic diagram of the traffic navigation device is shown in fig. 7, and the traffic navigation device comprises the following modules:
an analysis module 71, configured to obtain a regret level of the user;
the screening module 72 determines a destination primary selection set according to the POI classification code information;
a sorting module 73, which calculates and sorts the selection probability of the destination primary set according to the regret level through a random regret model, and recommends the destination to the user;
and the navigation module 74 searches for a path by taking the minimum regret impedance of the destination and the path as a decision criterion, and determines navigation route information.
An embodiment of the present invention further provides an electronic device, a schematic structural diagram of a traffic navigation device is shown in fig. 8, the device includes a memory 81, a processor 82, and a computer program 83 stored in the memory and executable on the processor, and is characterized in that the processor implements the steps of the traffic navigation method for variable destinations described in the above method embodiments when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium 82, storing a computer program 83, wherein the computer program is configured to, when executed by a processor 81, implement the steps of the traffic navigation method for variable destinations described in the above method embodiment.
All the above optional technical solutions may be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
Those of ordinary skill in the art will appreciate that the method steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of clearly illustrating the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. A traffic navigation method facing a variable destination is characterized by comprising the following steps:
s1, acquiring the regret level of the user;
s2, determining a destination primary selection set through the POI classification code information;
s3, calculating and sorting the selection probability of the destination primary collection according to the regret level through a random regret model, and recommending the destination to a user;
s4, searching a path by taking the minimum regret impedance of the destination and the path as a decision criterion, and determining navigation route information;
before the process of obtaining the regret level of the user, the method comprises the following steps:
the regret degree index is obtained through survey data statistics, and the regret grade is divided according to the regret degree index;
according to the current position of the user, pre-judging the regret level of the user at the current position;
the regret index calculation method comprises the following steps:
in the formula:
Xm(ii) an mth attribute prediction loss representing an impact decision; dmaxRepresents the maximum loss of mental ability in emotional stability;
the random regret model calculation method comprises the following steps:
in the formula, G0Initial set of destinations, Xjm,XsmThe mth attribute value, M ═ 1,2, …, M, for the other destination j and the selected destination s, respectively; wherein the content of the first and second substances,sthe regret index is used for measuring the regret degree of a runner for making a decision; psIndicating the probability of the traveler changing the selection destination s.
2. The traffic navigation method according to claim 1, wherein the process of determining the initial set of destinations from the POI class code information comprises:
sequentially screening by using an initial destination, a same-name subclass, a different-name subclass and a middle class of the initial destination as screening conditions through the POI classification code information;
taking at least one destination from the screened set of destinations according to the distance from the current position of the user in the order from near to far as the primary destination set G0The destination primary set G0Including the initial destination.
3. The traffic navigation method according to claim 2, wherein said process of calculating and ranking selection probabilities for the primary destination set according to regret levels and recommending destinations to users through a random regret model comprises:
predicting the remorse level generated by the user, and judging whether the user changes the current destination according to the remorse level;
when the user changes the current destination, the user selects the destination primary collection G according to the regret level by a random regret model of the variable destination according to the principle of minimum decision regret0And (4) sorting all destinations in the primary destination selection set from large to small according to the selection probability of the destinations in the primary destination selection set, and recommending a preset number of destinations to the user.
4. The traffic navigation method according to claim 3, further comprising, after recommending the destination to the user:
when the user does not change the current destination, the recommendation is stopped.
5. A traffic navigation method according to claim 3, wherein the process of searching for a path with the minimum regret impedance of the destination-path as a decision criterion comprises:
calculating the regret value of the destination through the random regret model;
multiplying the proportion of all path impedances shared by each road section by the destination regret value of each overlapped road section to obtain the regret impedance;
searching a path according to the regret impedance using an improved ant colony algorithm.
6. The traffic navigation method according to claim 5, wherein after searching for a path according to the regret impedance using the improved ant colony algorithm, further comprising:
and calculating the state transition probability according to the concentration of the pheromone on the path and heuristic information of the path, taking the minimum path regret value as a search criterion of the pheromone, and determining navigation information through an pheromone updating function with preset iteration times.
7. A variable destination-oriented traffic navigation device, comprising:
the analysis module is used for acquiring the regret level of the user;
the screening module determines a destination primary selection set through the POI classification code information;
the sorting module calculates and sorts the selection probability of the destination primary selection set according to the regret level through a random regret model, and recommends a destination to a user;
the navigation module searches a path by taking the minimum regret impedance of the destination and the path as a decision criterion and determines navigation route information;
before the process of obtaining the regret level of the user, the method comprises the following steps:
the regret degree index is obtained through survey data statistics, and the regret grade is divided according to the regret degree index;
according to the current position of the user, pre-judging the regret level of the user at the current position;
the regret index calculation method comprises the following steps:
in the formula:
Xmmth attribute prediction loss representing impact decisionLosing; dmaxRepresents the maximum loss of mental ability in emotional stability;
the random regret model calculation method comprises the following steps:
in the formula, G0Initial set of destinations, Xjm,XsmThe mth attribute value, M ═ 1,2, …, M, for the other destination j and the selected destination s, respectively; wherein the content of the first and second substances,sthe regret index is used for measuring the regret degree of a runner for making a decision; psIndicating the probability of the traveler changing the selection destination s.
8. An electronic device, characterized in that the device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of a variable destination oriented traffic navigation method according to any of claims 1 to 6.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method for variable destination oriented traffic navigation according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911120743.1A CN110887501B (en) | 2019-11-15 | 2019-11-15 | Traffic navigation method and device for variable destination |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911120743.1A CN110887501B (en) | 2019-11-15 | 2019-11-15 | Traffic navigation method and device for variable destination |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110887501A CN110887501A (en) | 2020-03-17 |
CN110887501B true CN110887501B (en) | 2020-10-02 |
Family
ID=69747609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911120743.1A Active CN110887501B (en) | 2019-11-15 | 2019-11-15 | Traffic navigation method and device for variable destination |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110887501B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898793B (en) * | 2020-06-08 | 2021-03-09 | 东南大学 | Path selection method considering user perception difference in combined travel mode |
CN111854781A (en) * | 2020-06-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Navigation path recommendation method and device and electronic equipment |
CN115292362A (en) * | 2022-07-07 | 2022-11-04 | 深圳计算科学研究院 | Data query method based on two-dimensional space |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331743A (en) * | 2014-10-11 | 2015-02-04 | 清华大学 | Electric vehicle travel planning method based on multi-target optimization |
CN107368991A (en) * | 2017-08-01 | 2017-11-21 | 大连理工大学 | A kind of Emergency Logistics addressing arrangement path method for averagely exceeding regret value based on α reliabilitys |
CN107702729A (en) * | 2017-09-06 | 2018-02-16 | 东南大学 | A kind of automobile navigation method and system for considering expected road conditions |
CN108106626A (en) * | 2017-12-18 | 2018-06-01 | 浙江工业大学 | A kind of electric vehicle trip route planing method based on driving cycle |
CN108592938A (en) * | 2018-06-11 | 2018-09-28 | 百度在线网络技术(北京)有限公司 | Navigation route planning method, apparatus and storage medium |
CN108615095A (en) * | 2018-05-08 | 2018-10-02 | 东南大学 | Method is determined based on the congestion-pricing robust optimal rate dynamically distributed day by day at random |
CN109726336A (en) * | 2018-12-21 | 2019-05-07 | 长安大学 | A kind of POI recommended method of combination trip interest and social preference |
JP2019139784A (en) * | 2019-03-22 | 2019-08-22 | 株式会社ナビタイムジャパン | Information processing system, information processing program, information processor, information processing method, output data, and storage medium |
CN110348628A (en) * | 2019-07-08 | 2019-10-18 | 重庆交通大学 | A kind of multimodal transport service network optimization method based on preference |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7206608B2 (en) * | 2018-03-26 | 2023-01-18 | 株式会社デンソー | Stop position controller |
-
2019
- 2019-11-15 CN CN201911120743.1A patent/CN110887501B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331743A (en) * | 2014-10-11 | 2015-02-04 | 清华大学 | Electric vehicle travel planning method based on multi-target optimization |
CN107368991A (en) * | 2017-08-01 | 2017-11-21 | 大连理工大学 | A kind of Emergency Logistics addressing arrangement path method for averagely exceeding regret value based on α reliabilitys |
CN107702729A (en) * | 2017-09-06 | 2018-02-16 | 东南大学 | A kind of automobile navigation method and system for considering expected road conditions |
CN108106626A (en) * | 2017-12-18 | 2018-06-01 | 浙江工业大学 | A kind of electric vehicle trip route planing method based on driving cycle |
CN108615095A (en) * | 2018-05-08 | 2018-10-02 | 东南大学 | Method is determined based on the congestion-pricing robust optimal rate dynamically distributed day by day at random |
CN108592938A (en) * | 2018-06-11 | 2018-09-28 | 百度在线网络技术(北京)有限公司 | Navigation route planning method, apparatus and storage medium |
CN109726336A (en) * | 2018-12-21 | 2019-05-07 | 长安大学 | A kind of POI recommended method of combination trip interest and social preference |
JP2019139784A (en) * | 2019-03-22 | 2019-08-22 | 株式会社ナビタイムジャパン | Information processing system, information processing program, information processor, information processing method, output data, and storage medium |
CN110348628A (en) * | 2019-07-08 | 2019-10-18 | 重庆交通大学 | A kind of multimodal transport service network optimization method based on preference |
Non-Patent Citations (4)
Title |
---|
Expanding the applicability of random regret minimization for route choice analysis;Prato Carlo Giacomo,etc;《TRANSPORTATION》;20140331;第41卷(第2期);第351-375页面 * |
New insights on random regret minimization models;van Cranenburgh Sander,etc;《Transportation Research Part A-POLICY AND PRACTICE》;20150430;第74卷;第91-109页 * |
出行路径选择的随机后悔最小化模型;栾琨,等;《交通信息与安全》;20120630;第30卷(第6期);第77-80页 * |
考虑心理距离的随机后悔最小化出行选择模型;徐媛,等;《系统管理学报》;20190731;第28卷(第4期);第679-686页 * |
Also Published As
Publication number | Publication date |
---|---|
CN110887501A (en) | 2020-03-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110887501B (en) | Traffic navigation method and device for variable destination | |
US10317219B1 (en) | System and method for the calculation and use of travel times in search and other applications | |
CN104165634B (en) | Path planning method based on use habit of user | |
CN101329183B (en) | Route searching method and route searching system | |
CN109556622B (en) | Interest point searching method and device | |
US8589073B2 (en) | Distributed traffic navigation using vehicular communication | |
JP2022037197A (en) | Parking lot guidance navigation method and system | |
CN105674994A (en) | Driving route acquisition method and device and navigation equipment | |
US20080262710A1 (en) | Method and system for a traffic management system based on multiple classes | |
CN108444486B (en) | Navigation route sorting method and device | |
CN110222277B (en) | Big data analysis-based travel information recommendation method and device | |
Younes et al. | An intelligent path recommendation protocol (ICOD) for VANETs | |
CN104636457B (en) | A kind of method and device of location finding cognition | |
Wang et al. | An adaptive and VANETs-based Next Road Re-routing system for unexpected urban traffic congestion avoidance | |
CN112819659B (en) | Tourist attraction development and evaluation method | |
CN110095134B (en) | Method and system for planning and navigating path by taking preference of user as core | |
CN108650656A (en) | A kind of distributed urban car networking method for routing based on intersection | |
CN110796308A (en) | Travel route optimization method based on fuzzy ant colony algorithm | |
CN106656814A (en) | Routing method for power line carrier communication network | |
JP4625335B2 (en) | Congestion alleviation support system and in-vehicle terminal | |
Alowish et al. | Stabilized clustering enabled V2V communication in an NDN-SDVN environment for content retrieval | |
CN108717640B (en) | Data processing method of travel information and electronic equipment | |
CN101552719A (en) | Routing selection method and routing selection device | |
Meuser et al. | Relevance-aware information dissemination in vehicular networks | |
CN110674990A (en) | Instant delivery path selection method and system with sliding window updating mechanism |
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 |