CN113535871A - Vehicle destination prediction method, device, equipment and medium based on travel map - Google Patents

Vehicle destination prediction method, device, equipment and medium based on travel map Download PDF

Info

Publication number
CN113535871A
CN113535871A CN202110712391.XA CN202110712391A CN113535871A CN 113535871 A CN113535871 A CN 113535871A CN 202110712391 A CN202110712391 A CN 202110712391A CN 113535871 A CN113535871 A CN 113535871A
Authority
CN
China
Prior art keywords
travel
markov
map
network
traffic
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
Application number
CN202110712391.XA
Other languages
Chinese (zh)
Other versions
CN113535871B (en
Inventor
杨粤湘
汤燕生
谢嘉孟
刘岚
陈泽毅
彭伟
张文凯
叶夏雨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202110712391.XA priority Critical patent/CN113535871B/en
Publication of CN113535871A publication Critical patent/CN113535871A/en
Application granted granted Critical
Publication of CN113535871B publication Critical patent/CN113535871B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/288—Entity relationship models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Remote Sensing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a vehicle destination prediction method, a vehicle destination prediction device, vehicle destination prediction equipment and a vehicle destination prediction medium based on a travel map, wherein the method comprises the following steps: obtaining a bayonet; constructing a traffic travel map according to the checkpoint data; converting the entity relationship in the traffic travel map into a Markov logic network; mining and obtaining a travel time-space association rule from the travel map; converting the Markov logic network into an instantiated Markov network; and determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network. The method and the device can improve the accuracy of individual vehicle travel destination conjecture and conjecture efficiency, and can be widely applied to the technical field of traffic data processing.

Description

Vehicle destination prediction method, device, equipment and medium based on travel map
Technical Field
The invention relates to the technical field of traffic data processing, in particular to a vehicle destination prediction method, device, equipment and medium based on a travel map.
Background
The individual vehicle travel destination conjecture is one of the core parts of the current intelligent transportation system, and plays an important support and guidance role in the management and decision of the whole transportation system. Based on accurate and effective individual vehicle trip destination conjecture results, the traffic decision, traffic induction and the urban overall road network condition interact and closely match with actual conditions of people, vehicles and roads, so that the traffic transportation efficiency can be effectively improved, traffic jam can be relieved, the traffic capacity, the road section driving speed and the traffic experience of a road network can be improved, and further a cushion can be provided for subsequent vehicle-road cooperation and automatic driving.
How to guess the travel destination of the new individual vehicle is an urgent problem to be solved.
The current domestic and foreign research and technical current situations mainly comprise:
firstly, travel rule analysis and prediction. Scholars at home and abroad make a great deal of research on travel rule analysis and prediction algorithms, and travel analysis can be divided into process-oriented travel analysis and result-oriented travel analysis according to the travel occurrence stage. The former analyzes travel characteristics statically or dynamically from the time and space angles, and comprises analysis of characteristics such as travel flow direction, travel time, travel distance, transfer mode, travel track and the like. However, such studies lack the study on the characteristics of the trip short-time drastic changes, and the study on the time-space multi-granularity sections is less, so that the time-space key points of the trip drastic changes are difficult to obtain. The result-oriented travel analysis analyzes the overall space-time state of the resident after the travel is finished from the macroscopic or mesoscopic perspective, and comprises the analysis of the total travel amount, the travel mode composition, the travel purpose and the special travel area. However, the analysis results of such researches are difficult to form a hierarchical semantic knowledge network, so that the results are fragmented and discretized, and meanwhile, effective and accurate prediction is not performed on individual vehicles basically.
Secondly, the data organization foundation aspect. At present, relevant research and application are mostly based on a relational database (such as oracle and SqlServer), association is actively discovered and organized by using association relations among data, and some hidden and imperceptible relations are easy to ignore by using the way. In addition, some scholars and applications organize and analyze data based on machine learning algorithms, but require a large amount of labeled data and complex feature engineering.
Disclosure of Invention
In view of this, embodiments of the present invention provide an efficient and accurate travel map-based vehicle destination prediction method, apparatus, device and medium.
One aspect of the present invention provides a vehicle destination prediction method based on a travel map, including:
acquiring card port data;
constructing a traffic travel map according to the checkpoint data;
converting the entity relationship in the traffic travel map into a Markov logic network;
mining and obtaining a travel time-space association rule from the travel map;
converting the Markov logic network into an instantiated Markov network;
and determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
Preferably, in the obtaining of the gate data, the gate data includes a license plate number, a vehicle location, a location attribute, a trip number and a trip time;
wherein the location attributes include schools, hospitals, shopping malls, and office locations.
Preferably, the constructing a traffic travel map according to the checkpoint data includes:
taking the license plate number, the vehicle location, the location attribute, the trip times and the trip time in the checkpoint data as nodes of the traffic trip map;
and taking the vehicle travel starting time, the departure place, the travel ending time and the destination as the edges of the traffic travel map.
Preferably, the converting the entity relationship in the travel map into a markov logic network includes:
converting the triples in the trip graph into nodes of the Markov logic network;
acquiring all nodes in the travel map, and connecting any two nodes in the same rule;
and adding all the nodes into the Markov logic network.
Preferably, the mining of the travel time-space association rule from the travel map includes:
taking the triples in the travel map as elements for constructing rule clauses;
connecting the elements according to the entity incidence relation among different triples, and further constructing a Markov network template;
searching and generating candidate rule clauses in the Markov network template;
and screening the candidate rule clauses to determine the traffic travel time-space association rule.
Preferably, the converting the markov logic network into an instantiated markov network includes:
generating instantiated sentence sections according to all constant entities in the definition domain according to the map relation in the travel map;
determining edges in the Markov network through the instantiated first order rule clauses;
and connecting sentence sections under the same clause by using edges to obtain the instantiated Markov network.
Preferably, in the step of determining the destination prediction result of the individual vehicle according to the travel space-time association rule and the markov network, a calculation formula of the destination prediction result is as follows:
Figure BDA0003133439850000021
wherein, P (Query q | -event) represents the conditional probability size that q holds under observation e; p (existence) represents the probability that an observation e is established; p (Query ═ q, and existence ═ e) represents the probability that the observation e and the relation q to be predicted hold together.
The embodiment of the invention also provides a vehicle destination prediction device based on the travel map, which comprises the following steps:
the acquisition module is used for acquiring the data of the card port;
the construction module is used for constructing a traffic travel map according to the checkpoint data;
the first conversion module is used for converting the entity relationship in the traffic travel map into a Markov logic network;
the mining module is used for mining and obtaining a travel time-space association rule from the travel map;
the second conversion module is used for converting the Markov logic network into an instantiated Markov network;
and the determining module is used for determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
The embodiment of the invention also provides the electronic equipment, which comprises a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
An embodiment of the present invention further provides a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the method described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
The embodiment of the invention firstly obtains the data of the card port; constructing a traffic travel map according to the checkpoint data; converting the entity relationship in the traffic travel map into a Markov logic network; mining and obtaining a travel time-space association rule from the travel map; converting the Markov logic network into an instantiated Markov network; and determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network. The method and the device can improve the accuracy of the individual vehicle trip destination conjecture and improve conjecture efficiency.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flowchart illustrating the overall steps of an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an attribute map model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Aiming at the problems in the prior art, the invention utilizes the existing widely existing checkpoint data (the vehicle passing is detected, the detection content comprises the license plate number, the vehicle passing time and the vehicle passing place), firstly constructs a traffic travel map based on the knowledge map technology, then converts the entity relation of the traffic travel knowledge map into a Markov logic network, and digs out the traffic travel space-time association rule by adopting a bottom-up structure learning method, then converts the traffic travel space-time association rule into an instantiated Markov network according to the Markov logic network in the face of the information needing to be inferred, and then loads the mined space-time association rule to infer the probability of the establishment of unknown facts, thereby realizing the final purpose of inferring the individual vehicle travel destination.
Referring to fig. 1, an embodiment of the present invention provides a vehicle destination prediction method based on a travel map, including the following steps:
acquiring card port data;
constructing a traffic travel map according to the checkpoint data;
converting the entity relationship in the traffic travel map into a Markov logic network;
mining and obtaining a travel time-space association rule from the travel map;
converting the Markov logic network into an instantiated Markov network;
and determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
Preferably, in the obtaining of the gate data, the gate data includes a license plate number, a vehicle location, a location attribute, a trip number and a trip time;
wherein the location attributes include schools, hospitals, shopping malls, and office locations.
Preferably, the constructing a traffic travel map according to the checkpoint data includes:
taking the license plate number, the vehicle location, the location attribute, the trip times and the trip time in the checkpoint data as nodes of the traffic trip map;
and taking the vehicle travel starting time, the departure place, the travel ending time and the destination as the edges of the traffic travel map.
Preferably, the converting the entity relationship in the travel map into a markov logic network includes:
converting the triples in the trip graph into nodes of the Markov logic network;
acquiring all nodes in the travel map, and connecting any two nodes in the same rule;
and adding all the nodes into the Markov logic network.
Preferably, the mining of the travel time-space association rule from the travel map includes:
taking the triples in the travel map as elements for constructing rule clauses;
connecting the elements according to the entity incidence relation among different triples, and further constructing a Markov network template;
searching and generating candidate rule clauses in the Markov network template;
and screening the candidate rule clauses to determine the traffic travel time-space association rule.
Preferably, the converting the markov logic network into an instantiated markov network includes:
generating instantiated sentence sections according to all constant entities in the definition domain according to the map relation in the travel map;
determining edges in the Markov network through the instantiated first order rule clauses;
and connecting sentence sections under the same clause by using edges to obtain the instantiated Markov network.
Preferably, in the step of determining the destination prediction result of the individual vehicle according to the travel space-time association rule and the markov network, a calculation formula of the destination prediction result is as follows:
Figure BDA0003133439850000051
wherein, P (Query q | -event) represents the conditional probability size that q holds under observation e; p (existence) represents the probability that an observation e is established; p (Query ═ q, and existence ═ e) represents the probability that the observation e and the relation q to be predicted hold together.
The following describes in detail a specific implementation process of the vehicle destination prediction method of the present invention:
(1) map construction and storage
The map construction and storage means that the traffic travel information is reorganized by using the advantages of the node-edge structure of the knowledge map, so that the knowledge hidden in the traffic information can be more fully mined and utilized.
In the embodiment of the invention, considering that a one-to-one, one-to-many or many-to-many relationship can exist among nodes of an attribute graph model (property graph), and the actual scene requirements of a vehicle in a trip to reach multiple places and the like can be better met, the attribute graph model is adopted as a modeling tool of a traffic trip graph data structure, as shown in fig. 2, in the attribute graph model structure, a license plate number, a place, place attributes (interest point attributes such as schools, hospitals, markets, office places and the like), trip times and time are respectively selected as nodes, and graph construction and storage are carried out by taking trip start time, trip end time, departure place and destination as sides.
(2) Markov logic network translation
A Markov Logic Network (MLN) is composed of a series of first order clauses, each clause having an associated weight value that indicates a confidence level at which the clause is true. The markov logic network can be viewed as a way to soften first order logic so that a violation of a clause does not cause the entire world to hold with a probability of 0. Let X denote the set of all propositions describing a certain world,
Figure BDA0003133439850000052
for the set of all clauses in a Markov logic network, ωiTo relate to clauses
Figure BDA0003133439850000053
The weight of (a) is determined,
Figure BDA0003133439850000054
for all clauses f within the constants of the domainiExamples of (3). Thus, one probability that a special case statement X holds for X can be given by:
Figure BDA0003133439850000061
wherein Z is a normalization term; the value of g (x) is 1 or 0, depending on whether g holds. Thus, it is possible to provide
Figure BDA0003133439850000062
Make statistics of clause fiThe number that is true given the example. A markov logic network is not essentially a network, but is a collection of first-order logic clauses with weights, which is a structure composed of rules. A markov logic network can be viewed as a template for generating a markov network. A commonly used first-order logical clause is a HornClause (hornclass), which can be expressed in the form of:
Figure BDA0003133439850000063
its logic meaning is conditional sentence pitch alpha1,α2,…,αnJointly deducing beta, wherein the form of sentence pitch is alpha: pred (e)1,e2)。
Therefore, the concrete steps of converting the entity relationship in the traffic travel map into the markov logic network in the embodiment of the present invention are as follows:
the first step is as follows: changing the map triple (o-r-o) into a node of the MLN;
the second step is that: adding the first step node into MLN, if two nodes are in the same rule, connecting the two nodes;
the third step: this is repeated until all the triplets of the original map are added to the MLN.
(3) Learning of traffic travel time-space association rules
Different constant sets may be instantiated into different markov networks by regular clauses of the markov logic network. In order to learn the travel time-space association rule, namely learn the structure of the Markov logic network, firstly, a Markov network template is automatically generated according to the existing travel map. And the nodes in the template correspond to the entity relationship triples in the travel map and serve as elements constructed by the rule clauses. These nodes are called TNs. In a normal markov network, a TN remains independent of all other TNs given its neighbor nodes. Each independent observation about the markov network can be directly obtained by the probability calculation in the subgraph. Therefore, by searching only the TN within the subgraph under the template, the search space of the regular clause can be effectively limited.
Specifically, the traffic travel space-time association rule generation algorithm of the embodiment of the invention comprises the following steps 1) to 5):
1) based on triplets
Figure BDA0003133439850000064
Constructing a corresponding TN;
2) connecting the TN according to the association of the triple entities to construct a Markov network template;
3) generating candidate rule clauses on the Markov network template through searching;
4) deleting the repeated candidate rules;
5) and evaluating the advantages and disadvantages of the candidate rules and preferentially adding the candidate rules to the final Markov logic network.
Wherein the content of the first and second substances,
Figure BDA0003133439850000065
and representing the set of all predicate relations in the traffic travel graph definition domain, and traversing one by one in a generation algorithm. And each predicate relation T generates a Markov network template. The generation of the template includes two steps, namely creating a generalized TN and determining the edges between them. To find rule clauses, embodiments of the present invention focus on each largest subgraph and generate all possible rules that are consistent with that subgraph.Then, screening is performed by evaluating each candidate rule using the WPLL score.
In embodiments of the present invention, each TN is transformed from a triplet in the traffic map, and thus a TN is generally coupled by two general variables representing map entities and serves as a module for creating rule clauses. Generally, all possible triples in the traffic map are obtained in the knowledge mode map of the traffic map, and the entities of the triples are replaced by corresponding types of variables and converted into periods to generate the TN. The transformation mode is shown as the following formula:
Figure BDA0003133439850000071
in order to complete the construction of the markov network template, it is necessary to further find out which TNs should be connected by edges, so that finding the relationship edges of the TNs translates into the structure learning problem of the markov network. Depending on the existing traffic map data and the obtained TN node, the establishment of the connection edge can be determined by using a Grow-shrinkmarkovnetwork (GSMN) algorithm. The GSMN algorithm uses a chi-square test to determine whether conditions are independent between two TN nodes.
After the Markov network template is generated, all possible rule clauses can be found by performing traversal search on the template. In order to limit the search space and filter out clauses with weak semantic relevance, the following rules need to be specified in the search process: (1) each TN contains m sentence sections at most, and usually m is less than or equal to 2, so that a regular clause with very rich information degree can be formed; (2) each TN contains at most one free variable (occurring at most once in a TN); (3) a regular clause contains at most one multi-sentence TN node.
For example, suppose that the personal travel rule is "if a weekday starts from home at 6 points, the destination is school", and then the predicate logic form is:
Figure BDA0003133439850000072
Figure BDA0003133439850000073
based on the above limitation, all possible candidate clause rules can be quickly searched out, wherein repeated clauses can be deleted. In order to calculate the WPLL score to evaluate the availability of each rule, it is therefore necessary to assign a corresponding weight to it. For weight calculation, an L-BFGS algorithm is adopted, and calculation results are added into the Markov logic network from high to low in weight sequence. To avoid overfitting and speed up the subsequent inference process, embodiments of the present invention specify a threshold w 'as the minimum allowable weight, considering only rules with weights greater than w'.
(4) Individual trip destination estimation by combining Markov logic network
The invention aims to reason about unknown facts (unknown travel knowledge of any individual) on the basis of a given known traffic travel map, and a priori traffic travel space-time association rule needs to be introduced in the process, namely the work completed in the step (3). The above problem can be expressed in mathematical form using the conditional probability formula of bayesian theory:
Figure BDA0003133439850000074
where e represents the content of the currently known traffic travel map (observed entities and relationships), i.e. evidence variables, and q represents unknown map facts (entity relationships that may be established, such as possible passing locations of a certain individual, and possible destinations of a trip), i.e. query variables. The problem therefore translates into an inference problem for the markov logic network when both the rules and their weights are known. From the above formula, the probabilistic inference of the markov logic network requires the computation of a joint probability distribution. To make inferences on a given Markov logic network, embodiments of the present invention require first instantiating it into the corresponding Markov network, which can be accomplished by the following two steps: (1) whether the sentence section is established or not, all constant entities in the definition domain generate instantiated sentence sections according to the existing map relation and serve as nodes of the Markov network; (2) edges in a markov network are determined by instantiated first order rule clauses: the sentence sections under the same clause will be connected by edges. Thus, typically an instance node formed by an instance clause will form a sub-graph in a Markov network, where the Gibbs sampling algorithm can be loaded onto the Markov network for model inference.
In summary, the invention utilizes the existing widely existing checkpoint data (vehicle passing is detected, and the detection content includes the license plate number, the vehicle passing time and the vehicle passing location), firstly constructs the traffic trip map based on the knowledge map technology, then converts the entity relationship of the traffic trip knowledge map into the markov logic network, and adopts the bottom-up structure learning method to dig out the traffic trip spatio-temporal association rule, and then in the face of the information to be inferred, firstly converts the information into the instantiated markov network according to the markov logic network, and then loads the excavated spatio-temporal association rule to infer the probability of the establishment of the unknown fact, thereby realizing the final purpose of inferring the individual vehicle trip destination.
The embodiment of the invention also provides a vehicle destination prediction device based on the travel map, which comprises the following steps:
the acquisition module is used for acquiring the data of the card port;
the construction module is used for constructing a traffic travel map according to the checkpoint data;
the first conversion module is used for converting the entity relationship in the traffic travel map into a Markov logic network;
the mining module is used for mining and obtaining a travel time-space association rule from the travel map;
the second conversion module is used for converting the Markov logic network into an instantiated Markov network;
and the determining module is used for determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
The embodiment of the invention also provides the electronic equipment, which comprises a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
An embodiment of the present invention further provides a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the method described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, 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.

Claims (10)

1. A vehicle destination prediction method based on a travel map is characterized by comprising the following steps:
acquiring card port data;
constructing a traffic travel map according to the checkpoint data;
converting the entity relationship in the traffic travel map into a Markov logic network;
mining and obtaining a travel time-space association rule from the travel map;
converting the Markov logic network into an instantiated Markov network;
and determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
2. The travel map-based vehicle destination prediction method according to claim 1, wherein the obtained gate data includes a license plate number, a vehicle location, a location attribute, travel times, and travel time;
wherein the location attributes include schools, hospitals, shopping malls, and office locations.
3. A vehicle destination prediction method based on a travel map according to claim 2, wherein the constructing a traffic travel map according to the checkpoint data comprises:
taking the license plate number, the vehicle location, the location attribute, the trip times and the trip time in the checkpoint data as nodes of the traffic trip map;
and taking the vehicle travel starting time, the departure place, the travel ending time and the destination as the edges of the traffic travel map.
4. The travel map-based vehicle destination prediction method according to claim 1, wherein the converting the entity relationship in the travel map into a markov logic network comprises:
converting the triples in the trip graph into nodes of the Markov logic network;
acquiring all nodes in the travel map, and connecting any two nodes in the same rule;
and adding all the nodes into the Markov logic network.
5. The method for predicting vehicle destinations based on travel maps according to claim 1, wherein the mining of travel spatiotemporal association rules from the travel maps comprises:
taking the triples in the travel map as elements for constructing rule clauses;
connecting the elements according to the entity incidence relation among different triples, and further constructing a Markov network template;
searching and generating candidate rule clauses in the Markov network template;
and screening the candidate rule clauses to determine the traffic travel time-space association rule.
6. A travel map based vehicle destination prediction method according to claim 1, wherein the converting the markov logic network into an instantiated markov network comprises:
generating instantiated sentence sections according to all constant entities in the definition domain according to the map relation in the travel map;
determining edges in the Markov network through the instantiated first order rule clauses;
and connecting sentence sections under the same clause by using edges to obtain the instantiated Markov network.
7. A travel map-based vehicle destination prediction method according to claim 1, wherein in the step of determining the destination prediction result of the individual vehicle according to the travel spatiotemporal association rule and the markov network, the calculation formula of the destination prediction result is:
Figure FDA0003133439840000021
wherein, P (Query ═ q | event ═ e) represents the conditional probability magnitude that q is established under observation e; p (existence) represents the probability that an observation e is established; p (Query ═ q, and existence ═ e) represents the probability that the observation e and the relation q to be predicted hold together.
8. A travel map-based vehicle destination prediction apparatus, characterized by comprising:
the acquisition module is used for acquiring the data of the card port;
the construction module is used for constructing a traffic travel map according to the checkpoint data;
the first conversion module is used for converting the entity relationship in the traffic travel map into a Markov logic network;
the mining module is used for mining and obtaining a travel time-space association rule from the travel map;
the second conversion module is used for converting the Markov logic network into an instantiated Markov network;
and the determining module is used for determining a destination prediction result of the individual vehicle according to the travel time-space association rule and the Markov network.
9. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program realizes the method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1-7.
CN202110712391.XA 2021-06-25 2021-06-25 Travel map-based vehicle destination prediction method, device, equipment and medium Active CN113535871B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110712391.XA CN113535871B (en) 2021-06-25 2021-06-25 Travel map-based vehicle destination prediction method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110712391.XA CN113535871B (en) 2021-06-25 2021-06-25 Travel map-based vehicle destination prediction method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN113535871A true CN113535871A (en) 2021-10-22
CN113535871B CN113535871B (en) 2024-02-27

Family

ID=78125860

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110712391.XA Active CN113535871B (en) 2021-06-25 2021-06-25 Travel map-based vehicle destination prediction method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN113535871B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115257807A (en) * 2022-07-27 2022-11-01 武汉大学 Urban on-road scene automatic driving decision-making method and equipment based on knowledge graph
CN116386336A (en) * 2023-05-29 2023-07-04 四川国蓝中天环境科技集团有限公司 Road network traffic flow robust calculation method and system based on bayonet license plate data

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160209842A1 (en) * 2015-01-15 2016-07-21 Nissan North America, Inc. Associating passenger docking locations with destinations using vehicle transportation network partitioning
US20170254660A1 (en) * 2016-03-04 2017-09-07 Volvo Car Corporation Method and system for utilizing a trip history
CN108304386A (en) * 2018-03-05 2018-07-20 上海思贤信息技术股份有限公司 A kind of logic-based rule infers the method and device of legal documents court verdict
US20180274927A1 (en) * 2017-03-27 2018-09-27 International Business Machines Corporation Cognitive journey companion system
CN109902165A (en) * 2019-03-08 2019-06-18 中国科学院自动化研究所 Intelligent interactive answering method, system, device based on Markov Logic Networks
CN111260526A (en) * 2020-01-20 2020-06-09 北京明略软件系统有限公司 Figure track behavior analysis and estimation method and device
CN111444316A (en) * 2020-03-11 2020-07-24 浙江大学 Knowledge graph question-answer oriented composite question analysis method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160209842A1 (en) * 2015-01-15 2016-07-21 Nissan North America, Inc. Associating passenger docking locations with destinations using vehicle transportation network partitioning
US20170254660A1 (en) * 2016-03-04 2017-09-07 Volvo Car Corporation Method and system for utilizing a trip history
US20180274927A1 (en) * 2017-03-27 2018-09-27 International Business Machines Corporation Cognitive journey companion system
CN108304386A (en) * 2018-03-05 2018-07-20 上海思贤信息技术股份有限公司 A kind of logic-based rule infers the method and device of legal documents court verdict
CN109902165A (en) * 2019-03-08 2019-06-18 中国科学院自动化研究所 Intelligent interactive answering method, system, device based on Markov Logic Networks
CN111260526A (en) * 2020-01-20 2020-06-09 北京明略软件系统有限公司 Figure track behavior analysis and estimation method and device
CN111444316A (en) * 2020-03-11 2020-07-24 浙江大学 Knowledge graph question-answer oriented composite question analysis method

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
KOHEI TANAKA 等: "A destination prediction method using driving contexts and trajectory for car navigation systems", 《SAC \'09: PROCEEDINGS OF THE 2009 ACM SYMPOSIUM ON APPLIED COMPUTING》, pages 190 *
MENGWEN XU 等: "DESTPRE: a data-driven approach to destination prediction for taxi rides", 《UBICOMP \'16: PROCEEDINGS OF THE 2016 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING》, pages 729 *
冯有礼: "数据挖掘中关联规则算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 12, pages 138 - 762 *
宋作华: "基于神经网络的车辆轨迹目的地预测方法的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 08, pages 034 - 192 *
王宗超: "面向知识图谱的可视化分析系统设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 02, pages 138 - 669 *
舒丽: "基于百度指数的我国体育旅游网络关注度研究", 《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》, no. 03, pages 134 - 2 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115257807A (en) * 2022-07-27 2022-11-01 武汉大学 Urban on-road scene automatic driving decision-making method and equipment based on knowledge graph
CN115257807B (en) * 2022-07-27 2024-01-30 武汉大学 Urban road scene automatic driving decision-making method and device based on knowledge graph
CN116386336A (en) * 2023-05-29 2023-07-04 四川国蓝中天环境科技集团有限公司 Road network traffic flow robust calculation method and system based on bayonet license plate data
CN116386336B (en) * 2023-05-29 2023-08-08 四川国蓝中天环境科技集团有限公司 Road network traffic flow robust calculation method and system based on bayonet license plate data

Also Published As

Publication number Publication date
CN113535871B (en) 2024-02-27

Similar Documents

Publication Publication Date Title
Brakatsoulas et al. Modeling, storing and mining moving object databases
CN104239513B (en) A kind of semantic retrieving method of domain-oriented data
CN113392986B (en) Highway bridge information extraction method based on big data and management maintenance system
Gao et al. Towards Platial Joins and Buffers in Place-Based GIS
Stock et al. Geospatial reasoning with open data
CN113535871A (en) Vehicle destination prediction method, device, equipment and medium based on travel map
Zhang et al. Three-way decisions of rough vague sets from the perspective of fuzziness
Li et al. Improved Bayesian network-based risk model and its application in disaster risk assessment
Zhu et al. Transportation routing map abstraction approach: Algorithm and numerical analysis
Sheeren et al. A data‐mining approach for assessing consistency between multiple representations in spatial databases
Chelghoum et al. A decision tree for multi-layered spatial data
Farghaly et al. The evolution of ontology in AEC: a two-decade synthesis, application domains, and future directions
Tezuka et al. Extraction of cognitively-significant place names and regions from web-based physical proximity co-occurrences
Caneparo Semantic knowledge in generation of 3D layouts for decision-making
Iwanaik et al. An intelligent geoportal for spatial planning
Hadjali et al. Expressing and processing complex preferences in route planning queries: Towards a fuzzy-set-based approach
Guo et al. Construction of Knowledge Graph Based on Geographic Ontology
Wu et al. STKST-I: An Efficient Semantic Trajectory Search by Temporal and Semantic Keywords
Chen English translation template retrieval based on semantic distance ontology knowledge recognition algorithm
Trajcevski et al. Semantically augmented range queries over heterogeneous geospatial data
Honcharenko et al. Mathematical Modeling of Information System Designing Master Plan of the Building Territory Based on OLAP Technology
Kavouras et al. Ontology-based fusion of geographic databases
Taylor et al. Representation and manipulation of conceptual, temporal and geographical knowledge in a museum hypermedia system
Chen et al. Application and research on trajectory big data
Mao Urban Planning Management Information Integration Platform System Based on Big Data Analysis

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