CN113688200B - Decision tree-based special population action track collection method and system - Google Patents
Decision tree-based special population action track collection method and system Download PDFInfo
- Publication number
- CN113688200B CN113688200B CN202111252760.8A CN202111252760A CN113688200B CN 113688200 B CN113688200 B CN 113688200B CN 202111252760 A CN202111252760 A CN 202111252760A CN 113688200 B CN113688200 B CN 113688200B
- Authority
- CN
- China
- Prior art keywords
- information
- node
- obtaining
- track
- special
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Abstract
The invention discloses a decision tree-based special population action track collection method, wherein the method comprises the following steps: obtaining a first special user; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information; acquiring first route information, first position distribution information and first traffic flow information between a first node and a second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user; and predicting and collecting the track of the first special user. The method solves the technical problem that the action tracks of special people cannot be comprehensively and accurately tracked by combining a decision tree algorithm in the prior art, so that the statistical data is incomplete and the decision issuing is influenced.
Description
Technical Field
The invention relates to the technical field of data collection, in particular to a method and a system for collecting action tracks of special crowds based on a decision tree.
Background
When epidemic diseases occur, the virus can be spread manly due to the flow of people, and the life and health of people are seriously harmed, so that all-around action track tracking and collection are carried out on special people with diseases but without symptom expression, the spreading dynamics of the epidemic diseases can be grasped in real time, and corresponding countermeasures can be taken conveniently.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the prior art has the technical problem that the action tracks of special people cannot be comprehensively and accurately tracked by combining a decision tree algorithm, so that the statistical data is incomplete, and the decision issuing is influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the application aims to solve the technical problem that the action tracks of special crowds cannot be comprehensively and accurately tracked by combining a decision tree algorithm, so that statistical data is incomplete and decision issuing is influenced in the prior art by providing a decision tree-based special crowd action track collection method and system. Based on the first route information, the first position distribution information and the first traffic flow information, a travel action track prediction and collection decision tree of a special user can be constructed, a possible action track of the special user can be found out by combining a decision tree algorithm, and the position information data of close contacts can be analyzed and judged, so that the real close contacts can be found out and tracked, the comprehensive track tracking of special crowds of epidemic diseases and the possible close contacts can be ensured, one person can not fall, the full coverage of a tracking network can be realized, the real-time control of the propagation dynamics of the epidemic diseases can be further ensured, the corresponding countermeasures can be generated conveniently, and the epidemic diseases can be in a controllable range.
In one aspect, an embodiment of the present application provides a method for collecting action tracks of a special population based on a decision tree, where the method includes: obtaining a first special user based on big data, wherein the first special user is contained in a first special group; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree.
In another aspect, the present application further provides a decision tree-based system for collecting action tracks of a special population, wherein the system includes: a first obtaining unit: the first obtaining unit is used for obtaining a first special user based on big data, wherein the first special user is included in a first special group; a second obtaining unit: the second obtaining unit is used for obtaining client payment information of the first special user; a third obtaining unit: the third obtaining unit is used for obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; a fourth obtaining unit: the fourth obtaining unit is used for obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node according to the first node payment information and the second node payment information; a fifth obtaining unit: the fifth obtaining unit is configured to use the first route information as a first trajectory prediction feature, the first position distribution information as a second trajectory prediction feature, and the first traffic flow information as a third trajectory prediction feature, respectively; a first building unit: the first construction unit is used for constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; a first collection unit: the first collection unit is used for predicting and collecting the track of the first special user according to the action track prediction and collection decision tree.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
obtaining a first special user based on big data, wherein the first special user is contained in a first special group; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree. The method has the advantages that the method can carry out all-around track tracking on special crowds of the epidemic diseases and possible close contacts, ensures that one person does not fall, realizes full coverage of a tracking network, further achieves the technical effects of ensuring that the propagation dynamics of the epidemic diseases is mastered in real time, and is convenient for generating corresponding countermeasures, so that the epidemic diseases are within a controllable range.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flowchart illustrating a method for collecting action tracks of a special population based on a decision tree according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a method for collecting action tracks of a special population based on a decision tree according to an embodiment of the present application, for constructing an action track prediction collection decision tree of the first special user;
fig. 3 is a schematic flowchart of a method for collecting action tracks of a special population based on a decision tree according to an embodiment of the present application, for predicting and collecting tracks of a first special user;
fig. 4 is a schematic flowchart illustrating a first travel mode of the first special user obtained by the decision tree-based special crowd action trajectory collection method according to the embodiment of the present application;
FIG. 5 is a schematic flowchart illustrating a method for collecting action trajectories of special populations based on decision trees according to an embodiment of the present disclosure for tracking a movement trajectory of a first set of associated people;
fig. 6 is a schematic flowchart of presetting a first security isolation area according to a data network tracked by a motion trajectory of a special population based on a decision tree in an embodiment of the present application;
FIG. 7 is a flowchart illustrating a method for collecting action tracks of a special population based on a decision tree to obtain a first training result according to an embodiment of the present application;
FIG. 8 is a schematic structural diagram of a decision tree based system for collecting action tracks of a special population according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a method and a system for collecting action tracks of special crowds based on a decision tree, and solves the technical problem that the action tracks of the special crowds cannot be comprehensively and accurately tracked by combining a decision tree algorithm in the prior art, so that statistical data is incomplete, and then decision issuing is influenced. Based on the first route information, the first position distribution information and the first traffic flow information, a travel action track prediction and collection decision tree of a special user can be constructed, a possible action track of the special user can be found out by combining a decision tree algorithm, and the position information data of close contacts can be analyzed and judged, so that the real close contacts can be found out and tracked, the comprehensive track tracking of special crowds of epidemic diseases and the possible close contacts can be ensured, one person can not fall, the full coverage of a tracking network can be realized, the real-time control of the propagation dynamics of the epidemic diseases can be further ensured, the corresponding countermeasures can be generated conveniently, and the epidemic diseases can be in a controllable range.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
When epidemic diseases occur, the virus can be spread manly due to the flow of people, and the life and health of people are seriously harmed, so that all-around action track tracking and collection are carried out on special people with diseases but without symptom expression, the spreading dynamics of the epidemic diseases can be grasped in real time, and corresponding countermeasures can be taken conveniently. The prior art has the technical problem that the action tracks of special people cannot be comprehensively and accurately tracked by combining a decision tree algorithm, so that the statistical data is incomplete, and the decision issuing is influenced.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a method for collecting action tracks of special crowds based on a decision tree, wherein the method comprises the following steps: obtaining a first special user based on big data, wherein the first special user is contained in a first special group; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
As shown in fig. 1, an embodiment of the present application provides a decision tree-based method for collecting action tracks of a special population, where the method includes:
step S100: obtaining a first special user based on big data, wherein the first special user is contained in a first special group;
specifically, when epidemic diseases occur, the virus may be spread widely due to the flow of people, and the life and health of people are seriously harmed, so that all-around movement track tracking and collection should be performed on special people with diseases but without symptom expression, so as to ensure that the spreading dynamics of the epidemic diseases can be grasped in real time, and to facilitate corresponding countermeasures. In the embodiment of the application, the first special population, namely the special population with epidemic diseases but without symptom expression, can be obtained based on big data, and the first special user is one of the first special population, and the action track of the first special population can be further tracked by collecting the dynamic state of the special population.
Step S200: obtaining client payment information of the first special user;
step S300: obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information;
specifically, when people go out, they may consume more or less using client devices such as mobile phones, and therefore, the movement track of the first special user may be tracked based on consumption records through the client payment information of the first special user, and then the first node payment information may be understood as consumption information of the first special user at a first node, which is described here by taking an attraction ticket as an example, and the second node payment information may be understood as consumption information of the first special user at a second node, which is described here by taking a return ticket after visiting the attraction as an example.
Step S400: according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node;
specifically, it is known to obtain the first node payment information and the second node payment information, where the first node may be understood as a scenic spot, the second node may be understood as a station when the first special user returns, and may be a station or an airport, and the first route information may be understood as a mileage between the scenic spot and the station, the first location distribution information may be understood as a relative azimuth between the scenic spot and the station, a specific location where the first location distribution information is located, and the first traffic flow information may be understood as a traffic flow situation between the scenic spot and the station, and whether there is a traffic jam or not.
Step S500: respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic;
step S600: constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic;
in particular, the length of the route, the distance of the distribution of the positions and the traffic flow conditions all affect the movement trajectory of the first special user, and therefore, predicting the movement track of the first special user by using the first route information as a first track prediction feature, the first position distribution information as a second track prediction feature, and the first traffic flow information as a third track prediction feature, respectively, based on the first track prediction feature, the second track prediction feature, and the third track prediction feature, a motion trajectory prediction collection decision tree for the first particular user may be constructed, based on the motion trajectory prediction collection decision tree, the travel modes and corresponding travel probability of the first special user under different track prediction characteristics can be obtained, and then the action track of the first special user is predicted. Further, a general decision tree includes a root node, a plurality of internal nodes and a plurality of leaf nodes, the leaf nodes correspond to the decision result, and each of the other nodes corresponds to an attribute test. The purpose of decision tree learning is to generate a decision tree with strong generalization ability;
step S700: and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree.
Specifically, it is known that based on the first route information, the first position distribution information, and the first traffic flow information, a decision tree for predicting and collecting travel action tracks of a special user can be constructed, and then a possible action track of the special user can be found out by combining with a decision tree algorithm, and the position information data of a close contact person can be analyzed and judged, so that a real close contact person can be found out and tracked, and the comprehensive track tracking of a special population of epidemic diseases and the possible close contact person can be ensured, and one person can not fall off, so that the full coverage of a tracking network can be realized, further, the real-time understanding of the propagation dynamics of the epidemic diseases can be ensured, the corresponding countermeasures can be generated, and the epidemic diseases can be within a controllable range.
Preferably, as shown in fig. 2, the constructing a prediction and collection decision tree of the action trajectory of the first special user, step S600 further includes:
step S610: respectively carrying out information theory encoding operation on the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic to sequentially obtain a first characteristic information entropy, a second characteristic information entropy and a third characteristic information entropy;
step S620: obtaining first root node feature information according to the first feature information entropy, the second feature information entropy and the third feature information entropy;
step S630: and classifying the historical client payment data set of the first special user by a recursion algorithm according to the characteristic information of the first root node, and constructing an action track prediction and collection decision tree of the first special user.
Specifically, to construct the action track prediction collection decision tree of the first special user, further, the first track prediction feature, the second track prediction feature, and the third track prediction feature may be respectively subjected to an information theory encoding operation, that is, through an information entropy calculation formula in the information theory encoding: and carrying out specific calculation on the information entropy value, wherein t represents a random variable, a set of all possible outputs is corresponding to the random variable and is defined as a symbol set, the output of the random variable is represented by t and represents an output probability function, and the larger the uncertainty of the variable is, the larger the entropy is. And further, comparing the numerical values of the first characteristic information entropy, the second characteristic information entropy and the third characteristic information entropy to obtain the characteristic with the minimum entropy value, namely the first root node characteristic information, preferentially classifying the characteristic with the minimum entropy value, sequentially classifying the characteristics according to a recursion algorithm from small to large according to the sequence of the entropy values, and finally constructing the action track prediction and collection decision tree of the first special user to realize the track prediction and collection of the first special user.
Preferably, as shown in fig. 3, the predicting and collecting the trajectory of the first special user, step S700 further includes:
step S710: acquiring a first weight ratio of the first route information, a second weight ratio of the first position distribution information and a third weight ratio of the first traffic flow information based on the action track prediction collection decision tree;
step S720: obtaining first travel habit information of the first special user;
step S730: according to the first trip habit information, carrying out weighted operation on the first weight proportion, the second weight proportion and the third weight proportion to obtain a first operation result;
step S740: and obtaining a first predicted action track of the first special user according to the first operation result, wherein the first predicted action track is between the first node and the second node.
Specifically, in order to predict and collect a trajectory of the first special user based on the action trajectory prediction collection decision tree, further, a first weight ratio of the first route information, a second weight ratio of the first location distribution information, and a third weight ratio of the first traffic flow information in the action trajectory prediction collection decision tree may be obtained, in other words, the first weight ratio may be understood as an influence of a distance mileage between the scenic spot and the site on a trip mode selection of the special user, the second weight ratio may be understood as an influence of a location distribution between the scenic spot and the site on a trip mode selection of the special user, and the third weight ratio may be understood as an influence of a traffic flow condition between the scenic spot and the site on a trip mode selection of the special user, thereby obtaining first trip habit information of the first special user, the first travel habit information is daily travel habits of special users, for example, if the first special user has a carsickness symptom, vehicles such as buses and taxis are preferentially excluded, and then according to the first travel habit information, weighting operation is performed on the first weight proportion, the second weight proportion and the third weight proportion to obtain a first operation result, for example, due to the influence of the travel habits, the travel modes of the special users are integrated, the first operation result is an integrated travel mode, if the distance between the scenic spot and the station is long, the user may select a bus and the like to go to the station based on a brief travel concept, but due to the carsickness, the bus may be changed to a high-speed rail to go to the station and the like, and further according to the first operation result, a first predicted action track of the first special user is obtained, the first predicted action track is an action track predicted by referring to the travel habits of the user, so that the travel track of the user is comprehensively and reasonably evaluated based on the actual condition of the user.
Preferably, as shown in fig. 4, the embodiment of the present application further includes:
step S731: according to the first trip habit information, a first preferred trip mode, a second preferred trip mode and a third preferred trip mode of the first special user are obtained;
step S732: obtaining a first trip probability of the first preferred trip mode, a second trip probability of the second preferred trip mode and a third trip probability of the third preferred trip mode according to the first weight proportion, the second weight proportion and the third weight proportion;
step S733: inputting the first trip probability, the second trip probability and the third trip probability into a probability size comparison model for training to obtain a first training result;
step S744: and obtaining a first travel mode of the first special user according to the first training result.
Specifically, in order to predict the action trajectory based on the user's travel habits, a first preferred travel mode, a second preferred travel mode, and a third preferred travel mode of the first special user may be further obtained according to the first travel habit information, that is, a travel mode suitable for the user may be obtained by matching the user's own physical condition, economic condition, and other factors, for example, the first preferred travel mode may be high-speed rail, the second preferred travel mode may be network appointment, and the third preferred travel mode may be bus, and further, according to the first weight ratio, the second weight ratio, and the third weight ratio, a first travel probability of the first preferred travel mode, a second travel probability of the second preferred travel mode, and a third travel probability of the third preferred travel mode may be obtained, namely, performing data cross operation analysis on the first weight ratio, the second weight ratio, the third weight ratio, the first preferred trip mode, the second preferred trip mode and the third preferred trip mode, wherein the first trip probability is the probability of high-speed rail trip of the user under the known weight ratios, the second trip probability is the probability of net car-saving trip of the user under the known weight ratios, the third trip probability is the probability of bus trip of the user under the known weight ratios, and the first trip probability, the second trip probability and the third trip probability are input into a probability comparison model to be trained to obtain a first training result, the first training result is the output result with the maximum probability, and finally the first trip mode of the first special user is obtained according to the first training result, the travel habit of the user is realized, and the action track of the user is predicted more specifically and scientifically.
Preferably, as shown in fig. 5, the embodiment of the present application further includes:
step S7341: obtaining a first riding vehicle of the first special user according to the first travel mode;
step S7342: acquiring images of passengers based on a first camera of the first passenger vehicle to generate a first passenger image set;
step S7343: obtaining movement trajectory information of the first ride vehicle;
step S7344: constructing a special crowd movement track tracking data network based on the first passenger image set and the movement track information;
step S7345: and tracking the movement track of the first associated personnel set according to the special population movement track tracking data network.
Specifically, in order to realize point-to-surface all-area coverage tracking of a special user, further, according to the first travel mode, a first passenger vehicle of the first special user is obtained, which is described herein by taking the first passenger vehicle as an example of a high-speed rail, and based on a camera on the high-speed rail, images of passengers can be collected, the first passenger image set is a passenger image set taken by the first special user in the same train number, generally, the high-speed rail has a train operation schedule, the movement track information can be obtained based on the train operation schedule, and further based on the first passenger image set and the movement track information, a special crowd movement track tracking data network is constructed, which clearly shows that a relevant person is at any time, a time, a, and a time, a time, a, The movement track of any station realizes the full-area coverage tracking of the movement track of the special crowd, and the movement track of a first associated personnel set can be tracked based on the special crowd movement track tracking data network, wherein the first associated personnel set can be understood as the personnel set taking the same train number as the first special user, and the full-area coverage tracking of the point-to-surface of the special user is realized through the special crowd movement track tracking data network.
Preferably, as shown in fig. 6, the embodiment of the present application further includes:
step S7346: determining whether the first ride vehicle is traversing a first area according to the movement track information, wherein the first area has a first dense feature;
step S7347: if the first vehicle approaches the first area, a first safety isolation area is preset according to the special crowd movement track tracking data network;
step S7348: and tracking the track of the first associated personnel set according to the first safety isolation area.
Specifically, in order to avoid the expansion of the special crowd, further, it may be determined whether the first passenger vehicle is routed to a first area according to the movement trajectory information, where the first area has a first dense feature, and herein, a transportation hub city is taken as an example, as is well known, the transportation hub city is a convergence and transfer hub between a plurality of urban traffics, which also causes people traffic to gather, if the first passenger vehicle is routed to the transportation hub city, the special crowd inevitably expands, and in order to reduce such an influence, a first safety isolation area may be preset according to the special crowd movement trajectory tracking data network, that is, all the special crowd is avoided in the safety isolation area, so as to avoid the expansion of the special crowd, and further, according to the first safety isolation area, track tracking the first related people set, thereby avoiding the expansion of special people.
Preferably, as shown in fig. 7, the obtaining the first training result, step S733, further includes:
step S7331: inputting the first trip probability, the second trip probability and the third trip probability into a probability magnitude comparison model for training, wherein the probability magnitude comparison model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the first trip probability, the second trip probability, the third trip probability, and identification information for identifying a first training result;
step S7332: and obtaining output information of the probability magnitude comparison model, wherein the output information comprises the first training result.
Specifically, the probabilistic magnitude matching model is a Neural network model in machine learning, and Neural Networks (NN) are complex Neural network systems formed by widely interconnecting a large number of simple processing units (called neurons), reflect many basic features of human brain functions, and are highly complex nonlinear dynamical learning systems. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (ANN), is a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And inputting the first trip probability, the second trip probability and the third trip probability into a neural network model through training of a large amount of training data, and outputting the first training result.
More specifically, the training process is substantially a supervised learning process, each set of supervised data includes the first trip probability, the second trip probability, the third trip probability, and identification information for identifying a first training result, the first trip probability, the second trip probability, and the third trip probability are input into a neural network model, the neural network model performs continuous self-correction and adjustment according to the identification information for identifying the first training result, until the obtained output information is consistent with the identification information, the set of supervised learning is ended, and the next set of supervised learning is performed; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through supervised learning of the neural network model, the neural network model can process the input information more accurately, the output first training result is more reasonable and accurate, and the travel habit based on the user is realized, and the action track of the user is predicted more specifically and scientifically.
Compared with the prior art, the invention has the following beneficial effects:
1. obtaining a first special user based on big data, wherein the first special user is contained in a first special group; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree. The method has the advantages that the method can carry out all-around track tracking on special crowds of the epidemic diseases and possible close contacts, ensures that one person does not fall, realizes full coverage of a tracking network, further achieves the technical effects of ensuring that the propagation dynamics of the epidemic diseases is mastered in real time, and is convenient for generating corresponding countermeasures, so that the epidemic diseases are within a controllable range.
Example two
Based on the same inventive concept as the method for collecting action tracks of special crowds based on decision trees in the foregoing embodiments, the present invention further provides a system for collecting action tracks of special crowds based on decision trees, as shown in fig. 8, the system includes:
the first obtaining unit 11: the first obtaining unit 11 is configured to obtain a first special user based on big data, where the first special user is included in a first special group;
the second obtaining unit 12: the second obtaining unit 12 is configured to obtain client payment information of the first special user;
the third obtaining unit 13: the third obtaining unit 13 is configured to obtain first node payment information and second node payment information according to the client payment information, where the second node payment information is later than the first node payment information;
the fourth obtaining unit 14: the fourth obtaining unit 14 is configured to obtain first route information, first position distribution information, and first traffic flow information between the first node and the second node according to the first node payment information and the second node payment information;
the fifth obtaining unit 15: the fifth obtaining unit 15 is configured to use the first route information as a first trajectory prediction feature, the first position distribution information as a second trajectory prediction feature, and the first traffic flow information as a third trajectory prediction feature, respectively;
the first building unit 16: the first constructing unit 16 is configured to construct an action trajectory prediction collection decision tree of the first special user according to the first trajectory prediction feature, the second trajectory prediction feature and the third trajectory prediction feature;
the first collecting unit 17: the first collecting unit 17 is configured to predict and collect a trajectory of the first special user according to the action trajectory prediction collection decision tree.
Further, the system further comprises:
a first arithmetic unit: the first operation unit is used for respectively carrying out information theory coding operation on the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic to sequentially obtain a first characteristic information entropy, a second characteristic information entropy and a third characteristic information entropy;
a sixth obtaining unit: the sixth obtaining unit is configured to obtain first root node feature information according to the first feature information entropy, the second feature information entropy, and the third feature information entropy;
a first classification unit: the first classification unit is used for classifying the historical client payment data set of the first special user by a recursion algorithm according to the first root node characteristic information, and constructing an action track prediction and collection decision tree of the first special user.
Further, the system further comprises:
a seventh obtaining unit: the seventh obtaining unit is configured to obtain a first weight ratio of the first route information, a second weight ratio of the first location distribution information, and a third weight ratio of the first traffic flow information based on the action trajectory prediction collection decision tree;
an eighth obtaining unit: the eighth obtaining unit is configured to obtain first travel habit information of the first special user;
a second arithmetic unit: the second operation unit is configured to perform weighting operation on the first weight ratio, the second weight ratio, and the third weight ratio according to the first travel habit information to obtain a first operation result;
a ninth obtaining unit: the ninth obtaining unit is configured to obtain a first predicted action track of the first special user according to the first operation result, where the first predicted action track is between the first node and the second node.
Further, the system further comprises:
a tenth obtaining unit: the tenth obtaining unit is configured to obtain a first preferred travel mode, a second preferred travel mode, and a third preferred travel mode of the first special user according to the first travel habit information;
an eleventh obtaining unit: the eleventh obtaining unit is configured to obtain a first trip probability of the first preferred trip manner, a second trip probability of the second preferred trip manner, and a third trip probability of the third preferred trip manner according to the first weight proportion, the second weight proportion, and the third weight proportion;
a first input unit: the first input unit is used for training the input probability comparison model of the first trip probability, the second trip probability and the third trip probability to obtain a first training result;
a twelfth obtaining unit: the twelfth obtaining unit is configured to obtain the first travel mode of the first special user according to the first training result.
Further, the system further comprises:
a thirteenth obtaining unit: the thirteenth obtaining unit is configured to obtain the first riding vehicle of the first special user according to the first travel mode;
a first acquisition unit: the first acquisition unit is used for acquiring images of passengers based on a first camera of the first passenger vehicle and generating a first passenger image set;
a fourteenth obtaining unit: the fourteenth obtaining unit is configured to obtain movement locus information of the first ride vehicle;
a second building element: the second construction unit is used for constructing a special crowd movement track tracking data network based on the first passenger image set and the movement track information;
a first tracking unit: the first tracking unit is used for tracking the movement locus of the first associated person set according to the special crowd movement locus tracking data network.
Further, the system further comprises:
a first judgment unit: the first judging unit is used for judging whether the first riding vehicle passes through a first area or not according to the movement track information, wherein the first area has a first dense characteristic;
a first preset unit: the first presetting unit is used for presetting a first safety isolation area according to the special crowd movement track tracking data network if the first vehicle approaches the first area;
a second tracking unit: the second tracking unit is used for tracking the track of the first associated people set according to the first safety isolation area.
Further, the system further comprises:
a second input unit: the second input unit is configured to train a comparison model of the first trip probability, the second trip probability, and the third trip probability input probability, where the comparison model of the probability magnitude is obtained by training multiple sets of training data, where each set of training data in the multiple sets of training data includes: the first trip probability, the second trip probability, the third trip probability, and identification information for identifying a first training result;
a fifteenth obtaining unit: the fifteenth obtaining unit is configured to obtain output information of the probability magnitude comparison model, where the output information includes the first training result.
Various variations and specific examples of the decision tree-based special population action track collection method in the first embodiment of fig. 1 are also applicable to the decision tree-based special population action track collection system of the present embodiment, and through the foregoing detailed description of the decision tree-based special population action track collection method, those skilled in the art can clearly know the implementation method of the decision tree-based special population action track collection system of the present embodiment, so for the sake of brevity of the description, details are not described again.
EXAMPLE III
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 9.
Fig. 9 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of a decision tree-based special population action track collection method in the embodiment, the invention further provides a decision tree-based special population action track collection system, on which a computer program is stored, and the computer program realizes the steps of any one of the above-mentioned decision tree-based special population action track collection systems when being executed by a processor.
Where in fig. 9 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the application provides a method for collecting action tracks of special crowds based on a decision tree, wherein the method comprises the following steps: obtaining a first special user based on big data, wherein the first special user is contained in a first special group; obtaining client payment information of the first special user; obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information; according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node; respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic; constructing an action track prediction collection decision tree of the first special user according to the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic; and predicting and collecting the track of the first special user according to the action track prediction and collection decision tree.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. A special population action track collection method based on a decision tree, wherein the method comprises the following steps:
obtaining a first special user based on big data, wherein the first special user is contained in a first special group;
obtaining client payment information of the first special user;
obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information;
according to the first node payment information and the second node payment information, obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node;
respectively taking the first route information as a first track prediction characteristic, the first position distribution information as a second track prediction characteristic and the first traffic flow information as a third track prediction characteristic;
respectively carrying out information theory encoding operation on the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic to sequentially obtain a first characteristic information entropy, a second characteristic information entropy and a third characteristic information entropy; obtaining first root node feature information according to the first feature information entropy, the second feature information entropy and the third feature information entropy;
preferentially classifying the features with the minimum entropy according to the feature information of the first root node, sequentially classifying the features by a recursion algorithm according to the sequence of the entropy from small to large, and constructing a motion trajectory prediction collection decision tree of the first special user;
acquiring a first weight ratio of the first route information, a second weight ratio of the first position distribution information and a third weight ratio of the first traffic flow information based on the action track prediction collection decision tree;
obtaining first travel habit information of the first special user; according to the first trip habit information, carrying out weighted operation on the first weight proportion, the second weight proportion and the third weight proportion to obtain a first operation result;
and obtaining a first predicted action track of the first special user according to the first operation result, wherein the first predicted action track is between the first node and the second node.
2. The method of claim 1, wherein the method further comprises:
according to the first trip habit information, a first preferred trip mode, a second preferred trip mode and a third preferred trip mode of the first special user are obtained;
obtaining a first trip probability of the first preferred trip mode, a second trip probability of the second preferred trip mode and a third trip probability of the third preferred trip mode according to the first weight proportion, the second weight proportion and the third weight proportion;
inputting the first trip probability, the second trip probability and the third trip probability into a probability size comparison model for training to obtain a first training result;
and obtaining a first travel mode of the first special user according to the first training result.
3. The method of claim 2, wherein the method further comprises:
obtaining a first riding vehicle of the first special user according to the first travel mode;
acquiring images of passengers based on a first camera of the first passenger vehicle to generate a first passenger image set;
obtaining movement trajectory information of the first ride vehicle;
constructing a special crowd movement track tracking data network based on the first passenger image set and the movement track information;
and tracking the movement track of the first associated personnel set according to the special population movement track tracking data network.
4. The method of claim 3, wherein the method further comprises:
determining whether the first ride vehicle is traversing a first area according to the movement track information, wherein the first area has a first dense feature;
if the first vehicle approaches the first area, a first safety isolation area is preset according to the special crowd movement track tracking data network;
and tracking the track of the first associated personnel set according to the first safety isolation area.
5. The method of claim 2, wherein the obtaining a first training result further comprises:
inputting the first trip probability, the second trip probability and the third trip probability into a probability magnitude comparison model for training, wherein the probability magnitude comparison model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the first trip probability, the second trip probability, the third trip probability, and identification information for identifying a first training result;
and obtaining output information of the probability magnitude comparison model, wherein the output information comprises the first training result.
6. A decision tree based crowd-specific action trajectory collection system, wherein the system comprises:
a first obtaining unit: the first obtaining unit is used for obtaining a first special user based on big data, wherein the first special user is included in a first special group;
a second obtaining unit: the second obtaining unit is used for obtaining client payment information of the first special user;
a third obtaining unit: the third obtaining unit is used for obtaining first node payment information and second node payment information according to the client payment information, wherein the second node payment information is later than the first node payment information;
a fourth obtaining unit: the fourth obtaining unit is used for obtaining first route information, first position distribution information and first traffic flow information between the first node and the second node according to the first node payment information and the second node payment information;
a fifth obtaining unit: the fifth obtaining unit is configured to use the first route information as a first trajectory prediction feature, the first position distribution information as a second trajectory prediction feature, and the first traffic flow information as a third trajectory prediction feature, respectively;
a first arithmetic unit: the first operation unit is used for respectively carrying out information theory coding operation on the first track prediction characteristic, the second track prediction characteristic and the third track prediction characteristic to sequentially obtain a first characteristic information entropy, a second characteristic information entropy and a third characteristic information entropy; obtaining first root node feature information according to the first feature information entropy, the second feature information entropy and the third feature information entropy;
a first classification unit: the first classification unit is used for preferentially classifying the features with the minimum entropy values according to the feature information of the first root node, sequentially classifying the features by a recursion algorithm according to the sequence of the entropy values from small to large, and constructing a motion trajectory prediction and collection decision tree of the first special user;
a sixth obtaining unit: the sixth obtaining unit is configured to obtain a first weight ratio of the first route information, a second weight ratio of the first location distribution information, and a third weight ratio of the first traffic flow information based on the action trajectory prediction collection decision tree;
a seventh obtaining unit: the seventh obtaining unit is configured to obtain first travel habit information of the first special user; according to the first trip habit information, carrying out weighted operation on the first weight proportion, the second weight proportion and the third weight proportion to obtain a first operation result;
an eighth obtaining unit: the eighth obtaining unit is configured to obtain a first predicted action trajectory of the first special user according to the first operation result, where the first predicted action trajectory is between the first node and the second node.
7. A decision tree based crowd-specific action trajectory collection system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252760.8A CN113688200B (en) | 2021-10-27 | 2021-10-27 | Decision tree-based special population action track collection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252760.8A CN113688200B (en) | 2021-10-27 | 2021-10-27 | Decision tree-based special population action track collection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688200A CN113688200A (en) | 2021-11-23 |
| CN113688200B true CN113688200B (en) | 2022-02-15 |
Family
ID=78588305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111252760.8A Active CN113688200B (en) | 2021-10-27 | 2021-10-27 | Decision tree-based special population action track collection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688200B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114841384A (en) * | 2022-05-06 | 2022-08-02 | 扬州市职业大学(扬州开放大学) | Express delivery package recycle's management system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110836675A (en) * | 2019-10-25 | 2020-02-25 | 北京航空航天大学 | Decision tree-based automatic driving search decision method |
| CN111079968A (en) * | 2018-10-22 | 2020-04-28 | 昆山炫生活信息技术股份有限公司 | Scenic spot playing track prediction system based on multi-feature fusion |
| CN112954603A (en) * | 2019-11-26 | 2021-06-11 | 中国移动通信集团甘肃有限公司 | Prediction method of motion trail of special crowd and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150019298A1 (en) * | 2013-07-11 | 2015-01-15 | International Business Machines Corporation | Estimating path information in business process instances when path information influences decision |
-
2021
- 2021-10-27 CN CN202111252760.8A patent/CN113688200B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079968A (en) * | 2018-10-22 | 2020-04-28 | 昆山炫生活信息技术股份有限公司 | Scenic spot playing track prediction system based on multi-feature fusion |
| CN110836675A (en) * | 2019-10-25 | 2020-02-25 | 北京航空航天大学 | Decision tree-based automatic driving search decision method |
| CN112954603A (en) * | 2019-11-26 | 2021-06-11 | 中国移动通信集团甘肃有限公司 | Prediction method of motion trail of special crowd and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688200A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ke et al. | Learning to delay in ride-sourcing systems: A multi-agent deep reinforcement learning framework | |
| Yao et al. | Short‐term traffic speed prediction for an urban corridor | |
| EP3035314A1 (en) | A traffic data fusion system and the related method for providing a traffic state for a network of roads | |
| Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
| Yan et al. | Spatial-temporal chebyshev graph neural network for traffic flow prediction in iot-based its | |
| Csikós et al. | Traffic speed prediction method for urban networks—An ANN approach | |
| George et al. | Traffic prediction using multifaceted techniques: A survey | |
| Ou et al. | Learn, assign, and search: real-time estimation of dynamic origin-destination flows using machine learning algorithms | |
| Chan et al. | Traffic flow forecasting neural networks based on exponential smoothing method | |
| CN113591380A (en) | Traffic flow prediction method, medium and equipment based on graph Gaussian process | |
| Chen et al. | A multiscale-grid-based stacked bidirectional GRU neural network model for predicting traffic speeds of urban expressways | |
| Jabamony et al. | IoT Based Bus Arrival Time Prediction Using Artificial Neural Network (ANN) for Smart Public Transport System (SPTS). | |
| CN113688200B (en) | Decision tree-based special population action track collection method and system | |
| Zhu et al. | Early identification of recurrent congestion in heterogeneous urban traffic | |
| CN113159371B (en) | Unknown target feature modeling and demand prediction method based on cross-modal data fusion | |
| Shmueli | Applications of neural networks in transportation planning | |
| Rodríguez-Rueda et al. | Origin–Destination matrix estimation and prediction from socioeconomic variables using automatic feature selection procedure-based machine learning model | |
| Teodorović et al. | A real-time road pricing system: The case of a two-link parallel network | |
| Guo | Short-term traffic prediction under normal and abnormal conditions | |
| Bae | Dynamic estimation of travel time on arterial roads by using automatic vehicle location (AVL) bus as a vehicle probe | |
| Cui et al. | A deep spatio-temporal attention-based neural network for passenger flow prediction | |
| Wang et al. | The prediction of urban road traffic congestion by using a deep stacked long short-term memory network | |
| CN110704789B (en) | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform | |
| Rahman | Applications of deep learning models for traffic prediction problems | |
| Rasouli | Trip distribution modelling using neural network |
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 |