CN113535871B - Travel map-based vehicle destination prediction method, device, equipment and medium - Google Patents
Travel map-based vehicle destination prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN113535871B CN113535871B CN202110712391.XA CN202110712391A CN113535871B CN 113535871 B CN113535871 B CN 113535871B CN 202110712391 A CN202110712391 A CN 202110712391A CN 113535871 B CN113535871 B CN 113535871B
- Authority
- CN
- China
- Prior art keywords
- travel
- markov
- traffic
- map
- network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000005065 mining Methods 0.000 claims abstract description 14
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000546 chi-square test Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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 travel map-based vehicle destination prediction method, a device, equipment and a medium, wherein the method comprises the following steps: acquiring a bayonet; constructing a traffic trip map according to the data of the bayonets; converting the entity relation in the traffic travel map into a Markov logic network; mining from the traffic travel map to obtain traffic travel time-space association rules; converting the Markov logic network into an instantiated Markov network; and determining a destination prediction result of the individual vehicle according to the traffic travel space-time association rule and the Markov network. The method and the device can improve the accuracy of individual vehicle travel destination estimation, improve the estimation efficiency and can be widely applied to the technical field of traffic data processing.
Description
Technical Field
The invention relates to the technical field of traffic data processing, in particular to a travel pattern-based vehicle destination prediction method, a travel pattern-based vehicle destination prediction device, travel pattern-based vehicle destination prediction equipment and a travel pattern-based vehicle destination prediction medium.
Background
The estimation of the travel destination of the individual vehicles is one of the core parts of the intelligent traffic system at present, and plays an important supporting and guiding role in the management and decision of the whole traffic system. Based on accurate and effective individual vehicle travel destination presumption results, through traffic decision-making, traffic guidance and urban integral road network condition interaction and close matching of actual conditions of people, vehicles and roads, the traffic transportation efficiency can be effectively improved, traffic jam is relieved, traffic capacity, road section driving speed and traffic experience of the road network are improved, and further a paving is provided for subsequent vehicle-road cooperation and automatic driving.
How to infer a new travel destination of an individual vehicle is a problem to be solved.
The current state of research and technology at home and abroad mainly comprises:
1. and analyzing and predicting travel rules. Scholars at home and abroad have made a great deal of researches 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 travel occurrence stages. The method comprises the steps of carrying out static or dynamic analysis on travel characteristics from the angles of time and space, wherein the analysis comprises the analysis on travel flow direction, travel time, travel distance, transfer mode, travel track and other characteristics. However, the research lacks the research on the characteristic of trip time and rapid change, and the research from space-time multi-granularity segmentation is less, so that the space-time key points of trip time and rapid change are difficult to obtain. The result-oriented travel analysis analyzes the overall space-time state of residents after traveling is completed from a macroscopic or mesoscopic angle, and comprises the analysis of travel total amount, travel mode composition, travel purpose and special travel area. However, the analysis results of such studies are difficult to form a hierarchical semantic knowledge network, so that the results are fragmented and discretized, and meanwhile, effective and accurate prediction for individual vehicles is basically unavailable.
2. Data organization basis aspects. At present, related researches and applications are mainly based on a relational database (for example oracle, sqlServer) to actively discover association and organize data by using association relation among the data, and in this way, some hidden and imperceptible relations are easily ignored. In addition, some scholars and application machines based on the machine learning algorithm organize and analyze the data, but a large amount of marking data is needed to cooperate with complex characteristic engineering.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method, apparatus, device, and medium for predicting a vehicle destination based on a travel map with high efficiency and accuracy.
One aspect of the invention provides a travel pattern-based vehicle destination prediction method, which comprises the following steps:
acquiring bayonet data;
constructing a traffic trip map according to the bayonet data;
converting the entity relation in the traffic travel map into a Markov logic network;
mining from the traffic travel map to obtain traffic travel time-space association rules;
converting the Markov logic network into an instantiated Markov network;
and determining a destination prediction result of the individual vehicle according to the traffic travel space-time association rule and the Markov network.
Preferably, in the acquiring 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, malls, and offices.
Preferably, the constructing a traffic trip map according to the bayonet data includes:
taking license plate numbers, vehicle places, place attributes, travel times and travel time in the bayonet data as nodes of the traffic travel map;
and taking the travel starting time, the departure place, the travel ending time and the destination of the vehicle as the sides of the traffic travel map.
Preferably, the converting the entity relationship in the traffic travel map into a markov logic network includes:
converting the triplets in the traffic travel map into nodes of the Markov logic network;
acquiring all nodes in the traffic travel map, and connecting any two nodes in a rule;
and adding all the nodes into the Markov logic network.
Preferably, the mining of the traffic travel time-space association rule from the traffic travel map includes:
taking the triples in the traffic travel map as elements constructed by rule clauses;
connecting the elements according to entity association relations among different triples, and further constructing a Markov network template;
searching in the Markov network template to generate candidate rule clauses;
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 an instantiation sentence knot according to the map relation in the traffic travel map and all constant entities in the definition domain;
determining edges in the Markov network through the instantiated first-order rule clauses;
and connecting sentence segments under the same clause by edges to obtain the instantiated Markov network.
Preferably, in the step of determining the destination prediction result of the individual vehicle according to the traffic space-time association rule and the markov network, a calculation formula of the destination prediction result is as follows:
wherein P (query=q|evaluation=e) represents the conditional probability size that q holds under observation e; p (evolution=e) represents the probability that the existing observation e is true; p (query=q, event=e) represents the probability that the observation e and the relation q to be predicted are established together.
The embodiment of the invention also provides a travel map-based vehicle destination prediction device, which comprises:
the acquisition module is used for acquiring the bayonet data;
the construction module is used for constructing a traffic travel map according to the bayonet 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 the traffic travel time-space association rule from the traffic travel map;
a second conversion module, configured to convert the markov logic network into an instantiated markov network;
and the determining module is used for determining the destination prediction result of the individual vehicle according to the traffic travel time-space association rule and the Markov network.
The embodiment of the invention also provides 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.
The embodiment of the invention also provides a computer readable storage medium storing a program, which is executed by a processor to implement the method as described above.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
The embodiment of the invention firstly acquires the bayonet data; constructing a traffic trip map according to the bayonet data; converting the entity relation in the traffic travel map into a Markov logic network; mining from the traffic travel map to obtain traffic travel time-space association rules; converting the Markov logic network into an instantiated Markov network; and determining a destination prediction result of the individual vehicle according to the traffic travel space-time association rule and the Markov network. The method and the device can improve the accuracy of individual vehicle travel destination estimation and improve the estimation efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating the overall steps of an embodiment of the present invention;
fig. 2 is a schematic 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 will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Aiming at the problems existing in the prior art, the invention utilizes the bayonet data (the passing vehicles are detected, the detection content comprises license plate numbers, passing time and passing places) which are widely existed at present, firstly constructs a traffic travel map based on a knowledge map technology, then converts the entity relation of the traffic travel knowledge map into a Markov logic network, adopts a bottom-up structure learning method to mine the space-time association rule of the traffic travel, then firstly converts the traffic travel time association rule into an instantiated Markov network according to the Markov logic network, and then loads the mined space-time association rule to infer the probability of establishment of unknown facts, thereby realizing the final aim of estimating the travel destination of the individual vehicles.
Referring to fig. 1, an embodiment of the present invention provides a travel pattern-based vehicle destination prediction method, which includes the steps of:
acquiring bayonet data;
constructing a traffic trip map according to the bayonet data;
converting the entity relation in the traffic travel map into a Markov logic network;
mining from the traffic travel map to obtain traffic travel time-space association rules;
converting the Markov logic network into an instantiated Markov network;
and determining a destination prediction result of the individual vehicle according to the traffic travel space-time association rule and the Markov network.
Preferably, in the acquiring 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, malls, and offices.
Preferably, the constructing a traffic trip map according to the bayonet data includes:
taking license plate numbers, vehicle places, place attributes, travel times and travel time in the bayonet data as nodes of the traffic travel map;
and taking the travel starting time, the departure place, the travel ending time and the destination of the vehicle as the sides of the traffic travel map.
Preferably, the converting the entity relationship in the traffic travel map into a markov logic network includes:
converting the triplets in the traffic travel map into nodes of the Markov logic network;
acquiring all nodes in the traffic travel map, and connecting any two nodes in a rule;
and adding all the nodes into the Markov logic network.
Preferably, the mining of the traffic travel time-space association rule from the traffic travel map includes:
taking the triples in the traffic travel map as elements constructed by rule clauses;
connecting the elements according to entity association relations among different triples, and further constructing a Markov network template;
searching in the Markov network template to generate candidate rule clauses;
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 an instantiation sentence knot according to the map relation in the traffic travel map and all constant entities in the definition domain;
determining edges in the Markov network through the instantiated first-order rule clauses;
and connecting sentence segments under the same clause by edges to obtain the instantiated Markov network.
Preferably, in the step of determining the destination prediction result of the individual vehicle according to the traffic space-time association rule and the markov network, a calculation formula of the destination prediction result is as follows:
wherein P (query=q|evaluation=e) represents the conditional probability size that q holds under observation e; p (evolution=e) represents the probability that the existing observation e is true; p (query=q, event=e) represents the probability that the observation e and the relation q to be predicted are established together.
The following describes in detail a specific implementation procedure 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 organized again by utilizing the advantages of the structure of the node-edge of the knowledge map so as to more fully mine and utilize the hidden knowledge in the traffic information.
In the embodiment of the invention, considering that a one-to-one, one-to-many or many-to-many relation can exist among nodes of the attribute map model (attribute map), the actual scene requirements of a vehicle in transportation to a plurality of places and the like can be better met, therefore, the attribute map model is adopted as a modeling tool of a transportation map data structure, as shown in fig. 2, license plate numbers, places, place attributes (interest point attributes such as schools, hospitals, markets and offices), travel times and time are respectively selected as nodes in the attribute map model structure, and the travel start time, travel end time, departure place and destination are used as edges for map construction and storage.
(2) Markov logic network conversion
A Markov Logic Network (MLN) is composed of a series of first-order clauses, each clause having an associated weight value representing the confidence that the clause is trueA degree level. A markov logic network can be regarded as a way to soften the first order logic such that the probability of violating a clause that does not result in the whole world being true is 0. Let X denote the complete set of propositions describing a certain world,omega is the set of all clauses in a Markov logic network i For clauses->Is used for the weight of the (c),to all relate to clause f within the constant of the domain i Is an example of (a). Thus, a probability that a specific statement of X holds that X may be given by:
wherein Z is a normalization term; the value of g (x) is 1 or 0, depending on whether g is true. Thus (2)Statistics of clause f i Number of holds true under a given instance. The Markov logic network is not a network in nature, but is a set of weighted first-order logic clauses, which is a structure of rules. A markov logic network may be regarded as a template for generating a markov network. A commonly used first order logical clause is the Huo En clause (HornClause), which can be expressed in the form:
the logical meaning is a conditional sentence segment alpha 1 ,α 2 ,…,α n Together, beta is derived, where the sentence fragments are in the form of alpha: pred (e 1 ,e 2 )。
Therefore, the embodiment of the invention comprises the following specific steps of converting the entity relationship in the traffic travel map into a Markov logic network:
the first step: converting the map triplet (o-r-o) into a node of the MLN;
and a second step of: adding the first step node into the MLN, and connecting the two nodes if the two nodes are in the same rule;
and a third step of: repeat until all triples of the original map are added to the MLN.
(3) Traffic travel time-space association rule learning
Different sets of constants can be instantiated into different Markov networks by rule clauses of the Markov logic network. In order to learn the traffic travel space-time association rule, i.e. learn the structure of the Markov logic network, firstly, a Markov network template needs to be automatically generated according to the existing traffic travel pattern. The nodes in the template correspond to the entity relationship triples in the travel pattern and are to be constructed as elements of the rule clause. 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 calculated from the probabilities inside the subgraph. Therefore, by searching only TNs within subgraphs under the templates, the search space for rule clauses can be effectively limited.
Specifically, the traffic travel time-space association rule generation algorithm of the embodiment of the invention comprises the following steps 1) -5):
1) Based on tripletsConstructing a corresponding TN;
2) Connecting TNs according to the triplet entity association to construct a Markov network template;
3) Generating candidate rule clauses on the Markov network template through searching;
4) Deleting the repeated candidate rule;
5) Evaluating the merits of the candidate rules and preferentially adding the merits to the final Markov logic network.
Wherein,and representing a set of all predicate relationships in the traffic travel map definition domain, and traversing one by one in a generation algorithm. Each predicate relation T generates a respective one of the markov network templates. The generation of templates involves two steps, namely creating a generalized TN and deciding the edges between them. To find a rule clause, embodiments of the present invention focus on each maximum subgraph and generate all possible rules consistent with that subgraph. Thereafter, screening was performed by evaluating each candidate rule using the WPLL score.
In the embodiment of the invention, each TN is converted from a triplet in the traffic map, so that one TN is generally coupled from two general variables representing map entities and serves as a module for creating rule clauses. In general, all possible triplet forms in the traffic map are obtained in the knowledge pattern diagram of the map, and the entity of the triplet is replaced by a variable of a corresponding type and converted into a sentence-segment form to generate TN. The conversion mode is shown as the following formula:
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 searching for the relationship edges of TNs is converted into a structure learning problem of the Markov network. The establishment of the connecting edges can be determined by means of the existing traffic pattern data and the obtained TN nodes by using a Grow-ShrinkMarkovNetwork (GSMN) algorithm. The GSMN algorithm uses a chi-square test to decide whether the conditions are independent between two TN nodes.
After the Markov network template is generated, all possible rule clauses can be found out by performing a traversal search on the template. In order to limit the search space and filter clauses with weak semantic relevance, the following rules need to be specified in the searching process: (1) Each TN contains at most m sentence segments, and in general, m is less than or equal to 2, so that a rule clause with very rich information can be formed; (2) Each TN contains at most one free variable (at most one occurrence in TN); (3) A rule clause contains at most one multi-sentence TN node.
By way of example, assume that the individual travel rule is "if a workday 6 starts from home, its destination is school", at which time the predicate logic form is:
based on the above constraints, all possible candidate clause rules can be quickly searched out, wherein duplicate clauses are deleted. In order to calculate the WPLL score to evaluate the availability of each rule, it is therefore necessary to assign a corresponding weight thereto. For weight calculation, an L-BFGS algorithm is adopted, and calculation results are added into a Markov logic network according to the high-to-low order of the weights. To avoid overfitting and speed up the subsequent inference process, embodiments of the present invention provide for a threshold w 'as the minimum allowable weight, considering only rules with weights greater than w'.
(4) Individual travel destination speculation by combining Markov logic network
The invention aims to infer unknown facts (unknown travel knowledge of any individual) on the basis of a given known travel map, and in the process, a priori travel space-time association rule, namely the work completed in the step (3) is required to be introduced. The above problem can be expressed in mathematical form using a conditional probability formula of bayesian theory:
where e represents the content of the currently known traffic travel pattern (observed entities and relationships), i.e. evidence variables, and q represents unknown pattern facts (possibly established entity relationships, such as the possible passing places of an individual on a trip, the possible destinations of a trip), i.e. query variables. The problem is thus translated into an inference problem of the markov logic network when both the rules and their weights are known. From the above formula, the probability inference of a Markov logic network requires calculation of a joint probability distribution. In order to infer on a given Markov logic network, embodiments of the present invention need to first instantiate it into the corresponding Markov network, which can be accomplished by the following two steps: (1) Whether the sentence segments are established or not, all constant entities in the definition domain generate an instantiation sentence segment according to the existing graph relationship and serve as nodes of the Markov network; (2) Edges in the Markov network are determined by instantiated first order rule clauses: the sentence fragments under the same clause will be connected by edges. Thus, typically an instance node formed of an instance clause will form a sub-graph in a Markov network, at which point the Gibbs sampling algorithm may be loaded onto the Markov network for model inference.
In summary, the present invention utilizes the existing widely existing bayonet data (the vehicles passing through are detected, the detection content comprises license plate numbers, the time of the vehicles passing through and the places of the vehicles passing through), firstly constructs a traffic travel map based on a knowledge map technology, then converts the entity relation of the traffic travel knowledge map into a Markov logic network, adopts a bottom-up structure learning method to mine the traffic travel time-space association rule, then firstly converts the traffic travel time-space association rule into an instantiated Markov network according to the Markov logic network, and then loads the mined time-space association rule to infer the probability of establishment of unknown facts, thereby realizing the final purpose of estimating the travel destination of the individual vehicles.
The embodiment of the invention also provides a travel map-based vehicle destination prediction device, which comprises:
the acquisition module is used for acquiring the bayonet data;
the construction module is used for constructing a traffic travel map according to the bayonet 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 the traffic travel time-space association rule from the traffic travel map;
a second conversion module, configured to convert the markov logic network into an instantiated markov network;
and the determining module is used for determining the destination prediction result of the individual vehicle according to the traffic travel time-space association rule and the Markov network.
The embodiment of the invention also provides 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.
The embodiment of the invention also provides a computer readable storage medium storing a program, which is executed by a processor to implement the method as described above.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
In some 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 flowcharts 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 a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, 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 separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement 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 and are not intended to be limiting upon the scope of the invention, which is to be defined in 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 this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform 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, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing 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). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may 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 is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means 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 present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. 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 present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments described above, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are included in the scope of the present invention as defined in the appended claims.
Claims (6)
1. The travel map-based vehicle destination prediction method is characterized by comprising the following steps of:
acquiring bayonet data;
constructing a traffic trip map according to the bayonet data;
converting the entity relation in the traffic travel map into a Markov logic network;
mining from the traffic travel map to obtain traffic travel time-space association rules;
converting the Markov logic network into an instantiated Markov network;
determining a destination prediction result of an individual vehicle according to the traffic travel space-time association rule and the Markov network;
the converting the entity relationship in the traffic travel map into a markov logic network comprises the following steps:
converting the triplets in the traffic travel map into nodes of the Markov logic network;
acquiring all nodes in the traffic travel map, and connecting any two nodes in a rule;
adding all the nodes into the Markov logic network;
the mining of the traffic travel time-space association rule from the traffic travel map comprises the following steps:
taking the triples in the traffic travel map as elements constructed by rule clauses;
connecting the elements according to entity association relations among different triples, and further constructing a Markov network template;
searching in the Markov network template to generate candidate rule clauses;
screening the candidate rule clauses to determine the traffic travel space-time association rule;
the converting the markov logic network into an instantiated markov network includes:
generating an instantiation sentence knot according to the map relation in the traffic travel map and all constant entities in the definition domain;
determining edges in the Markov network through the instantiated first-order rule clauses;
connecting sentence segments under the same clause by edges to obtain the instantiated Markov network;
in the step of determining the destination prediction result of the individual vehicle according to the traffic travel space-time association rule and the markov network, the calculation formula of the destination prediction result is as follows:
wherein P (query=q|evaluation=e) represents the conditional probability size that q holds under observation e; p (evolution=e) represents the probability that the existing observation e is true; p (query=q, event=e) represents the probability that the observation e and the relation q to be predicted are established together.
2. The travel pattern-based vehicle destination prediction method according to claim 1, wherein the acquired bayonet data comprises a license plate number, a vehicle location, a location attribute, a travel number and travel time;
wherein the location attributes include schools, hospitals, malls, and offices.
3. The travel pattern-based vehicle destination prediction method according to claim 2, wherein the constructing a travel pattern according to the bayonet data includes:
taking license plate numbers, vehicle places, place attributes, travel times and travel time in the bayonet data as nodes of the traffic travel map;
and taking the travel starting time, the departure place, the travel ending time and the destination of the vehicle as the sides of the traffic travel map.
4. An apparatus applying the travel pattern-based vehicle destination prediction method as claimed in any one of claims 1 to 3, comprising:
the acquisition module is used for acquiring the bayonet data;
the construction module is used for constructing a traffic travel map according to the bayonet 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 the traffic travel time-space association rule from the traffic travel map;
a second conversion module, configured to convert the markov logic network into an instantiated markov network;
and the determining module is used for determining the destination prediction result of the individual vehicle according to the traffic travel time-space association rule and the Markov network.
5. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program to implement the method of any one of claims 1-3.
6. A computer readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method of any one of claims 1-3.
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 CN113535871A (en) | 2021-10-22 |
| CN113535871B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9436183B2 (en) * | 2015-01-15 | 2016-09-06 | Nissan North America, Inc. | Associating passenger docking locations with destinations using vehicle transportation network partitioning |
| EP3214406A1 (en) * | 2016-03-04 | 2017-09-06 | Volvo Car Corporation | Method and system for utilizing a trip history |
| US10527437B2 (en) * | 2017-03-27 | 2020-01-07 | International Business Machines Corporation | Cognitive journey companion system |
-
2021
- 2021-06-25 CN CN202110712391.XA patent/CN113535871B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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)
| 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》.2009,190–195. * |
| 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》.2016,729–739. * |
| 基于百度指数的我国体育旅游网络关注度研究;舒丽;《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》(第03期);H134-2 * |
| 基于神经网络的车辆轨迹目的地预测方法的研究;宋作华;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第08期);C034-192 * |
| 数据挖掘中关联规则算法研究;冯有礼;《中国优秀硕士学位论文全文数据库 信息科技辑》(第12期);I138-762 * |
| 面向知识图谱的可视化分析系统设计与实现;王宗超;《中国优秀硕士学位论文全文数据库 信息科技辑》(第02期);I138-669 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113535871A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | New automated BIM object classification method to support BIM interoperability | |
| Mustière et al. | Matching networks with different levels of detail | |
| CN112612902A (en) | Knowledge graph construction method and device for power grid main device | |
| CN113535871B (en) | Travel map-based vehicle destination prediction method, device, equipment and medium | |
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| Du et al. | Geospatial information integration for authoritative and crowd sourced road vector data | |
| CN110119449A (en) | A kind of criminal case charge prediction technique based on sequence enhancing capsule net network | |
| US11620453B2 (en) | System and method for artificial intelligence driven document analysis, including searching, indexing, comparing or associating datasets based on learned representations | |
| CN117744784B (en) | Medical scientific research knowledge graph construction and intelligent retrieval method and system | |
| Owais | Deep learning for integrated origin–destination estimation and traffic sensor location problems | |
| CN103957116A (en) | Decision-making method and system of cloud failure data | |
| Zhu et al. | Transportation routing map abstraction approach: Algorithm and numerical analysis | |
| Ruas et al. | Conception of a GIS-Platform to simulate urban densification based on the analysis of topographic data | |
| Lei et al. | Ontology-based information integration: A state-of-the-art review in road asset management | |
| Clarizia et al. | A multilevel graph approach for road accidents data interpretation | |
| Martino et al. | Semantic techniques for discovering architectural patterns in building information models | |
| Costes et al. | A hidden Markov model for matching spatial networks | |
| Lisi et al. | A System for Learning GCI Axioms in Fuzzy Description Logics. | |
| CN114896353A (en) | Geocoding method, storage medium and system | |
| Lamiroy et al. | Analysis and interpretation of graphical documents | |
| Rezaeipanah et al. | Providing a new method for link prediction in social networks based on the meta-heuristic algorithm | |
| Colace et al. | A multiexpert approach for Bayesian network structural learning | |
| CN112181978A (en) | Address storage structure, address resolution method, device, medium and computer equipment | |
| Zhou et al. | MBFP generalized association rule mining and classification in traffic volume prediction | |
| Stypa et al. | Improving the semantic accuracy and consistency of OpenStreetMap using machine learning techniques |
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 |