CN112446406A - Emergency point determination method and device and storage medium - Google Patents

Emergency point determination method and device and storage medium Download PDF

Info

Publication number
CN112446406A
CN112446406A CN201910838703.4A CN201910838703A CN112446406A CN 112446406 A CN112446406 A CN 112446406A CN 201910838703 A CN201910838703 A CN 201910838703A CN 112446406 A CN112446406 A CN 112446406A
Authority
CN
China
Prior art keywords
related information
terminal
scenic spot
emergency
determining
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.)
Pending
Application number
CN201910838703.4A
Other languages
Chinese (zh)
Inventor
徐海勇
孙琼
陶涛
黄岩
尚晶
柯亮
江勇
陈钰
卜尧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Suzhou Software Technology Co Ltd
China Mobile Information Technology Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Suzhou Software Technology Co Ltd
China Mobile Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Suzhou Software Technology Co Ltd, China Mobile Information Technology Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN201910838703.4A priority Critical patent/CN112446406A/en
Publication of CN112446406A publication Critical patent/CN112446406A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • G06Q50/14—Travel agencies

Abstract

The invention discloses an emergency point determination method, an emergency point determination device and a storage medium. The method comprises the following steps: acquiring historical related information of a terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot; for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot; and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm. By adopting the scheme of the invention, a plurality of non-centralized distributed emergency points and the positions thereof can be determined in the scenic spot, so that the scenic spot emergency points are reasonably distributed.

Description

Emergency point determination method and device and storage medium
Technical Field
The invention relates to the technical field of communication, in particular to an emergency point determination method, an emergency point determination device and a storage medium.
Background
With the change of economy and people consumption concept, the tourism market is continuously developed and prosperous in recent years, and the rapid increase of the number of visitors in scenic spots brings certain challenges to scenic spot supervision and emergency plan formulation. Especially, in the high peak period such as holidays, the number of visitors in scenic spots can be increased explosively. Therefore, the location of the emergency points in the scenic spot is very important.
However, in the related art, the determination of the emergency point needs to be optimized.
Disclosure of Invention
In order to solve the existing technical problem, embodiments of the present invention provide a method, an apparatus, and a storage medium for determining an emergency point.
The technical scheme of the embodiment of the invention is realized as follows:
the embodiment of the invention provides an emergency point determining method, which comprises the following steps:
acquiring historical related information of a terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot;
for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot;
and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
In the above scheme, determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm includes:
and determining the number and the positions of emergency points in the first scenic spot by using the obtained at least one crowd density and combining a K-means algorithm.
In the foregoing solution, the acquiring historical related information of the terminal includes:
and acquiring the terminal history related information from the database.
In the above scheme, before obtaining the history related information of the terminal from the database, the method further includes:
acquiring terminal history related information from operator equipment;
filtering the terminal history related information acquired from the operator equipment to obtain effective terminal history related information;
and storing the obtained history related information of the effective terminal to the database.
In the above scheme, the method further comprises:
acquiring historical weather data and historical holiday data;
determining a people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data; the determined people number prediction model is used for predicting the people number in the first scenic spot.
In the above scheme, determining a people number prediction model by using the acquired terminal history related information, history weather data and history holiday data includes:
and determining the people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data and combining a Least Absolute Shrinkage and Selection algorithm (LASSO).
In the above scheme, the method further comprises:
aiming at each base station, determining the crowd characteristics in the first coverage range of the corresponding base station by using the historical related information of the terminal to which the base station belongs; generating a data label by using the determined crowd characteristics and the corresponding emergency point position; the generated data label is used for determining the quantity and the type of the reserve materials of the emergency point;
and storing the generated data label.
An embodiment of the present invention further provides an emergency point determining apparatus, including:
the first acquisition module is used for acquiring historical related information of the terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot;
the first determining module is used for determining the number of the terminals of the corresponding base station based on the acquired historical related information of the terminals aiming at each base station; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot;
and the second determining module is used for determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
An embodiment of the present invention further provides an emergency point determination device, where the emergency point determination device includes: a processor and a memory for storing a computer program capable of running on the processor;
wherein the processor is configured to perform the steps of any of the above methods when running the computer program.
An embodiment of the present invention further provides a storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the above methods are implemented.
According to the technical scheme provided by the embodiment of the invention, historical related information of the terminal is obtained; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot; for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot; and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm. The number and the positions of the emergency points are determined based on the crowd density and combined with a clustering algorithm, and the determined emergency points can meet the requirements of crowd dense areas in scenic spots on the emergency points due to the fact that the crowd density is considered, so that the scenic spot emergency points are reasonably distributed; meanwhile, the clustering algorithm has the characteristic of classifying objects according to the similarity degree, so that a plurality of non-centrally distributed emergency points and positions thereof can be determined in a scenic spot by adopting the scheme.
Drawings
FIG. 1 is a schematic flow chart of a method for determining an emergency point according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of determining the number and positions of emergency points in a first scenic spot by combining a K-mediads algorithm according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an emergency site location system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an emergency point determination device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of an emergency point determination device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
In the related art, emergency response is carried out through a scenic spot intensity regulation and control platform, and the basic idea of an emergency response mode is as follows: a tourist connects a public wireless internet access (WI-FI) hotspot of a scenic spot nearest to the position of the tourist through a terminal (such as a mobile phone); the scenic spot density regulating and controlling platform determines the crowd density of the scenic spot by counting the number of terminals connected to the public WI-FI hotspot of the scenic spot, displays the crowd density of the scenic spot on the terminals and reminds visitors of avoiding the crowd density area. In addition, the scenic spot intensity regulation and control platform can also carry out short message reminding on the tourists through Mobile Communication networks such as a Global System for Mobile Communication (GSM), a fourth generation Mobile Communication technology (4G) network and the like; and finally, the scenic spot density regulating and controlling platform regulates and controls entrance, ticket selling and transportation tools based on the determined scenic spot crowd density, so that dense crowd is quickly dredged.
As can be seen from the above description, in the related art, although emergency response of a scenic spot is realized by reminding people of the scenic spot population density of visitors and scheduling entrance, ticketing and transportation means of the scenic spot, a plurality of reasonably distributed emergency points are not set in the scenic spot, and the problem of untimely emergency response still occurs in the scenic spot.
In addition, since there is a case where the visitor uses other network connection methods such as a second generation mobile communication technology (2G) network, a third generation mobile communication technology (3G) network, or a 4G network without connecting to the scenic spot common WI-FI, there is a limitation that the result of the scenic spot crowd density is inaccurate in a method of determining the scenic spot crowd density by counting the number of terminals connected to the scenic spot common WI-FI.
Based on this, in various embodiments of the present invention, selection of a meeting point of a scenic spot is made dependent on terminal history related information.
The embodiment of the invention provides an emergency point determining method, as shown in fig. 1, the method comprises the following steps:
step 101: acquiring historical related information of a terminal;
here, the acquired terminal history related information includes at least related information when the terminal is in the first scenic spot.
In practical application, the terminal history related information may include: the mobile phone number of the user, the gender of the user, the age of the user, the communication time between the terminal and the base station, signaling data of interaction between the terminal and the base station corresponding to the communication time between the terminal and the base station, the position of the terminal corresponding to the communication time between the terminal and the base station, and the like.
In practical application, the history related information of the terminal can be stored in the database in advance, and when the scheme of the embodiment of the invention is implemented, the history related information of the terminal is acquired from the database.
Based on this, in an embodiment, the acquiring the history related information of the terminal includes:
and acquiring the terminal history related information from the database.
In practical application, a Spark distributed processing technology can be specifically adopted to acquire historical related information of the terminal from a Hive database; the Spark distributed processing technology can rapidly process large-scale data, and in the embodiment of the invention, a large amount of terminal history related information can be rapidly acquired from the Hive database by adopting the Spark distributed processing technology.
In the embodiment of the invention, the historical relevant data of the terminal is used for determining the crowd density in the scenic spot, and the relevant data of the terminal is generally managed by an operator, so the operator is required to provide the relevant data of the terminal.
Based on this, in an embodiment, before obtaining the terminal history related information from the database, the method may further include:
acquiring terminal history related information from operator equipment;
filtering the terminal history related information acquired from the operator equipment to obtain effective terminal history related information;
and storing the obtained history related information of the effective terminal to the database.
In actual application, the operator device stores terminal history related information, and the stored terminal history related information may include: the mobile phone number of the user, the gender of the user, the age of the user, the communication time between the terminal and the base station, signaling data of interaction between the terminal and the base station corresponding to the communication time between the terminal and the base station, the position of the terminal corresponding to the communication time between the terminal and the base station, and the like.
In practical application, the Flume component may be used to obtain the terminal history related information from the operator device (such as a server, etc.), the Kafka component may be used to perform cache processing on the terminal history related information obtained from the operator device, and the Spark distributed processing technology may be used to filter the terminal history related information obtained from the operator device, that is, to delete incomplete information (such as terminal history related information missing data of the age of the user or the time of communication between the terminal and the base station) in the obtained terminal history related information and related information when the terminal is not in the first scene area, which is determined according to the location of the terminal, and then, the Hive database is used to store the filtered effective terminal history related information.
Among other things, the Flume component provides a log collection function, which can collect log information (i.e. terminal history related information) from other devices such as a server, process the log information and store the log information in a distributed file system or a database.
The Kafka component provides a distributed message flow platform that is capable of storing information without passing through memory.
The Spark distributed processing technology supports the rapid processing of large-scale data, and the data cached by the Kafka component can be directly read and rapidly processed by using the Spark distributed processing technology.
Because the operator equipment can store comprehensive, real and reliable terminal history related information, compared with common statistical modes in the related technology, such as a manual statistical mode, a satellite image acquisition mode, a data acquisition mode based on scenic spot public WI-FI and the like, the method for acquiring the terminal history related information stored in the operator equipment is adopted, and has the advantages of low cost, comprehensive information, high reliability and high convenience.
Step 102: for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density;
here, the first coverage area belongs to the first scenic spot.
That is to say, in each base station of the embodiment of the present invention, at least a part of the coverage area of the base station belongs to the first scenic spot, and the first coverage area is an overlapping area of the coverage area of the base station and the first scenic spot.
Specifically, the number of terminals interacting with the base station may be determined according to signaling data of the terminals interacting with the base station in the history related information of the terminals, and accordingly, the number of terminals belonging to the corresponding base station may be determined.
When the crowd density of the first coverage range of the corresponding base station on the corresponding date is determined, a date (namely the corresponding date) is selected first, when the crowd density of each base station on the selected date is determined, the number of terminals to which the base station belongs per hour can be determined by taking one hour as a time unit, the number of the terminals to which the base station belongs per hour is divided by the first coverage range of the base station to obtain the crowd density per hour, and the maximum value is selected from all the obtained crowd densities per hour to be used as the crowd density of the first coverage range of the base station on the selected date.
When the method is actually applied, when the crowd density of the first coverage area of each base station on the selected date is determined, a peak threshold value can be set; the crowd density of the first coverage area of each base station in each day in the year is calculated firstly through the mode, then the number of days (generally corresponding to holiday days) in which the crowd density is larger than or equal to the peak threshold value in the year is determined, the average value of the crowd density of the days is calculated (the sum of the crowd densities corresponding to the days is divided by the sum of the days), and finally the obtained average value is used as the crowd density of the first coverage area of the base station on the selected date.
Here, the crowd density of the first coverage area of the base station on the selected date can be determined in different modes according to the situation.
Step 103: and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
Specifically, the obtained at least one crowd density can be used in combination with a K-mediads algorithm to determine the number and the positions of the emergency points in the first scenic spot.
In practical application, the crowd density of the first coverage area of the corresponding date base station determined in the step 102 is used for determining the data of the point in the unit area of the first scenic spot, and the number and the positions of the emergency points in the first scenic spot are determined by using the obtained data of the point in the unit area and combining the K-mediads algorithm.
Specifically, the area of the first scenic spot may be assumed to be a square meters, and the first scenic spot may be divided into a unit area points (the area of each unit area point is one square meter) in units of one square meter; the unit area point data includes a unit area point longitude, a unit area point latitude, a first date (i.e., corresponding date), and a first date unit area of people (i.e., crowd density of a first coverage area of a base station where the unit area point on the corresponding date is located).
Through the above steps, a unit area points and corresponding a groups of unit area point data in the first scenic spot are determined. And determining the number and the positions of emergency points in the first scenic spot by using the determined a unit area points in the first scenic spot and the corresponding a group of unit area point data and combining a K-mediads algorithm.
Here, as shown in fig. 2, determining the number and the positions of the emergency points in the first scenic spot by using a determined a unit area points and a corresponding a group of unit area point data in combination with a K-mediads algorithm specifically includes the following steps:
step 201: b unit area points are selected from the a unit area points as central points (which can be understood as emergency points), and a central point set is obtained; step 202 is executed after each central point corresponds to a cluster (which can be understood as a service range of an emergency point);
here, the center point may be regarded as the center of its corresponding cluster.
Step 202: determining the cost from each unit area point except the central point to each central point in the central point set, putting a-b unit area points into a cluster corresponding to the central point with the minimum cost, determining b clusters, and then executing step 203;
here, the cost of each of the other unit area points to the central point set can be determined using equation (1), the cost representing the cost of moving the material transportation stream from one point to another at the emergency point.
Figure BDA0002193002400000081
In the formula (1), CijRepresents the cost, u, per unit area point i to center point jiNumber of persons in unit area, x, representing a point i in unit areaiAnd xjLongitude, y, representing points i and j, respectivelyiAnd yjThe latitude of the point i and the point j are respectively represented.
Step 203: for each cluster in the b determined clusters, calculating the total cost from each unit area point in the cluster to other unit area points except the point, and taking the unit area point with the minimum total cost as the new center point of the cluster; obtaining a new center point set, and then executing step 204;
here, the total cost of each unit area point in the cluster to other unit area points except for the point is calculated using formula (2).
Figure BDA0002193002400000082
In equation (2), k represents the new center point to be determined, m represents other unit area points within the cluster except k, n represents the total number of unit area points within the cluster, CmkRepresents the total cost, u, of other unit area points in the cluster to the new center point kmNumber of persons in unit area, x, representing a point m in unit areamAnd xnDenotes the longitude of m-point and n-point, ymAnd ynRespectively representing the latitudes of the m-point and the n-point.
Step 204: judging whether the new central point set is the same as the original central point set or not, if so, terminating the algorithm and outputting the new central point set; if not, returning to step 202, re-determining the corresponding cluster of each central point in the new central point set, i.e. re-determining b clusters.
Here, for the output new center point set, the b new center points in the new center point set are the determined b emergency points, and the cluster corresponding to each new center point is the service range of the determined emergency point.
By adopting the scheme, the formula (2) is used for determining the total cost in the determination process of the emergency point, so that the determined emergency point can ensure that the total distance from the visitor to the emergency point in the service range of each emergency point is shortest; the emergency points are determined based on all unit area points of the first scenic spot, and the scenic spot is considered in a total amount; the emergency points are determined by determining the service range of the emergency points and then determining the emergency points, so that the emergency points are not distributed in a centralized manner, and the arrangement of the emergency points in the scenic spot is reasonable.
In practical application, emergency materials need to be stored in each emergency point of a scenic spot, and even if the scenic spot is provided with a plurality of emergency points which are reasonably distributed, the problem of untimely emergency response caused by insufficient emergency material storage of the emergency points can occur; that is, to prevent the occurrence of a situation where the emergency material supply in the scenic spot is insufficient, it is necessary to make a prediction on the number of visitors in the future scenic spot.
Based on this, in an embodiment, the method may further include:
acquiring historical weather data and historical holiday data;
determining a people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data; the determined people number prediction model is used for predicting the people number in the first scenic spot.
In an embodiment, the determining a people number prediction model by using the acquired terminal history related information, the acquired historical weather data, and the acquired historical holiday data includes:
and determining the people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data and combining with LASSO.
Specifically, the number of terminals interacting with the base station during the historical holiday can be determined by using the time of the terminal communicating with the base station in the terminal history related information and the signaling data of the terminal interacting with the base station corresponding to the time of the terminal communicating with the base station, so that the number of terminals belonging to the corresponding base station during the historical holiday can be determined, and the total number of visitors in the first scenic spot during the historical holiday can be determined based on the number of terminals belonging to each base station during the historical holiday; and determining a people number prediction model for predicting the number of people in the first scenic spot by using the total number of visitors in the first scenic spot during the historical holidays, the historical weather data and the historical holiday data in combination with LASSO.
In practical application, historical related information of the scenic spot terminal is analyzed through technical means, and prediction of future number of people in the scenic spot has certain significance for making emergency plans in the scenic spot in advance, particularly during the peak periods of five-one, eleven and other tourism.
Specifically, when the total number of visitors in the first scenic spot during the historical holiday, the historical weather data and the historical holiday data are used in combination with the LASSO to determine the number prediction model of the first scenic spot, the historical weather data can be obtained from the china weather bureau, and the historical weather data can include: air temperature, air pressure, wind speed, rainfall, etc.; acquiring historical holiday data from historical calendar data, wherein the historical holiday data can comprise historical holiday dates and historical holiday days; taking the acquired historical weather data and historical holiday data as independent variables of the people number prediction model; and obtaining a functional relation between the total number of visitors in the first scenic spot and an independent variable during the historical holidays by using LASSO, namely determining the number prediction model for predicting the number of people in the first scenic spot.
Wherein LASSO is a biased estimation algorithm for processing data with complex collinearity, which can determine a model by constructing penalty function, and its basic idea is: under the constraint that the sum of the absolute values of the regression coefficients is less than a constant, the sum of the squares of the residuals is minimized, resulting in some regression coefficients that are strictly equal to 0, resulting in a model. The mathematical expression of LASSO is shown in formulas (3) and (4). Wherein, formula (4) is a constraint condition of formula (3), and, as shown in formula (5), the adjustment parameter t is greater than or equal to 0; the formula (6) is a human number prediction model formula, and the human number prediction model for predicting the number of people in the first scenic spot can be determined by substituting the coefficients corresponding to the respective variables determined by the formulas (3) and (4) into the formula (6).
Figure BDA0002193002400000101
Figure BDA0002193002400000102
t≥0 (5)
Figure BDA0002193002400000103
In practical application, the embodiment of the present invention determines the coefficients of the respective variables of the prediction model by using equations (3) and (4).
XjThe argument representing the prediction model, j represents the number of the argument (e.g., X)1Is the air temperature, X2Is air pressure, X3Is the wind speed, X4Is rainfall and X5Days on historical holidays) and j is 1, 2, … P, BjIs an independent variable XjY represents the total number of visitors to the first scenic spot during the historical holidays, Y represents the predicted total number of visitors to the first scenic spot,
Figure BDA0002193002400000111
representing under the constraint that the sum of the absolute values of the independent variable coefficients is less than or equal to the tuning parameter t,
Figure BDA0002193002400000112
each X when taking the minimum valuejCorresponding to BjA value of (d); that is, the sum of the absolute values of the independent variable coefficients can be compressed by controlling the value of t, thereby making it possible to reduce the number of bits required for the compression
Figure BDA0002193002400000113
Infinitely close to 0 (which can be understood as making the people number prediction model more accurate).
In practical applications, the LASSO may be implemented by various programs, such as the program package Lars of the R language.
In practical application, after a plurality of emergency points and service ranges thereof in a first scenic spot are determined, for each emergency point, the total number of visitors in the service range of the emergency points during the historical holidays can be determined by utilizing the time of communication between the terminal and the base station in the terminal historical related information, the signaling data of interaction between the terminal and the base station corresponding to the time of communication between the terminal and the base station, and the position of the terminal corresponding to the time of communication between the terminal and the base station; and determining a number prediction model of the emergency point by using the total number of tourists, the historical weather data and the historical holiday data in the service range of the emergency point during the historical holiday period and combining with the LASSO.
The method for determining the people number prediction model of the emergency point by specifically combining the LASSO is the same as the method for determining the people number prediction model of the first scenic spot, and is not repeated here.
Therefore, for each emergency point in the scenic spot, the number of future tourists in the service range of the emergency point can be predicted according to the number prediction model of the emergency point, corresponding number of emergency materials are stored in the emergency point according to the predicted number of the future tourists, the emergency plan of the scenic spot is further perfected, and the level of the emergency plan of the scenic spot is set according to the predicted number of the tourists.
In practical application, the scenic spot emergency points need to prepare different types of emergency supplies for different types of tourists (such as male and female tourists or tourists of different ages), and at this moment, even if the number of the tourists in the service range of the emergency points is predicted and the emergency supplies are stored according to the number of the tourists, the scenic spot still has the problem that emergency response is not timely due to the fact that the emergency supplies are not stored for different types of the tourists in the future, namely, in order to prevent the occurrence of certain emergency supplies shortage, the emergency supplies in the scenic spot emergency points need to be stored for the crowd characteristics of the tourists in the scenic spot.
Based on this, in an embodiment, the method may further include:
aiming at each base station, determining the crowd characteristics in the first coverage range of the corresponding base station by using the historical related information of the terminal to which the base station belongs; generating a data label by using the determined crowd characteristics and the corresponding emergency point position; the generated data label is used for determining the quantity and the type of the reserve materials of the emergency point;
and storing the generated data label.
In practical applications, the crowd characteristics may include: the number of people, the density of people, the distribution proportion of age groups of people, the sex proportion of people and other parameters.
When the crowd characteristics in the first coverage range of the corresponding base station are determined, a date can be selected first, the number of terminals interacting with the base station on the selected date is determined according to the communication time between the terminal and the base station in the terminal history related information and the signaling data of the interaction between the terminal and the base station corresponding to the communication time between the terminal and the base station, and accordingly the number of terminals belonging to the corresponding base station on the selected date can be determined, namely the number of crowds in the first coverage range of the corresponding base station on the selected date is determined; dividing the determined number of the crowds in the first coverage range of the base station corresponding to the selected date by the first coverage range of the base station, so as to determine the crowd density in the first coverage range of the base station corresponding to the selected date; according to the user gender, the user age, the communication time between the terminal and the base station and the interactive signaling data between the terminal and the base station corresponding to the communication time between the terminal and the base station in the historical related information of the terminal, the distribution proportion of the age groups of the crowd and the gender proportion of the crowd in the first coverage range of the corresponding base station at the selected date can be determined.
In practical application, the data label is generated by utilizing the determined crowd characteristics and the corresponding emergency point position, a base station to which the emergency point belongs can be judged according to the determined emergency point position, and the crowd characteristics of the corresponding date in the first coverage range of the base station and the determined emergency point position are associated in a database to generate the data label; when the emergency point needs to store materials, the materials can be stored for people of different ages or different sexes according to the crowd characteristics in the associated data tags. So, can carry out multiple type's goods and materials deposit to the visitor of different grade type in the emergent point in scenic spot, further perfect the emergent scheme in scenic spot.
According to the emergency point determining method provided by the embodiment of the invention, historical relevant information of a terminal is obtained; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot; for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot; determining the number and the positions of emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm; the crowd density of the scenic spot is utilized, the quantity and the positions of the emergency points of the scenic spot are determined by using a clustering algorithm, the shortest total distance from the tourists in the service range of each determined emergency point to the emergency points is ensured, the scenic spot is considered in full, the emergency points are not distributed in a centralized manner, and the arrangement of the emergency points of the scenic spot is reasonable.
In addition, the number prediction model of the scenic spot is determined, the number of visitors in the future scenic spot can be predicted, and the prediction result can be used as a reference for setting the reserve material quantity and the emergency capacity of the scenic spot emergency points and can also be used as reference data for setting the emergency plan level of the scenic spot.
Besides, the data label of the scenic spot is determined, so that the data label can be used as reference data of the quantity and the type of the reserve materials of the scenic spot emergency points.
The present invention will be described in further detail with reference to the following application examples.
As shown in fig. 3, the emergency site selection system provided in this embodiment includes: the system comprises a data acquisition module 301, a data storage module 302, a data calculation and analysis module 303, a data tag calculation module 304 and a data tag storage module 305. Wherein the content of the first and second substances,
the data acquisition module 301 is configured to acquire historical related information of a terminal from operator equipment; and filtering the terminal history related information acquired from the operator equipment to obtain effective terminal history related information.
The data storage module 302 is configured to store the history related information of the valid terminals obtained by the data acquisition module 301.
The data calculation and analysis module 303 is configured to obtain historical related information of the terminal from the data storage module 302, and analyze the information to select an address for the emergency point in the scenic spot.
The data tag calculation module 304 is configured to analyze crowd characteristics, i.e., crowd characteristics, in the service range according to the emergency point and the service range of the emergency point and the terminal history related information read from the data storage module 302, and bind the crowd characteristics with the corresponding emergency point to generate a data tag.
A data tag storage module 305, configured to store the generated data tag of the data tag calculation module 304, so as to serve as reference data of the quantity and the type of the emergency point stock materials.
Based on the system, the method for site selection of the scenic spot in the embodiment of the application comprises the following steps:
step 1: calculating the user density (i.e. crowd density) of the scenic spot;
specifically, first, the data calculation and analysis module 303 reads the terminal history related information stored in the Hive database of the data storage module 302 by using Spark distributed processing technology (big data processing technology);
the data acquisition module 301 acquires historical related information of the terminal from operator equipment by using a flash component; that is to say, the terminal history related information is provided by the operator device, and compared with the traditional data acquisition modes such as user survey data and electronic device collected data, the reliability and convenience of the data provided by the operator are higher. The terminal history related information can comprise information such as the mobile phone number, the gender, the age and the position of the user; the data acquisition module 301 caches the historical relevant information of the terminal by adopting a Kafka component to improve the access speed of the data; filtering the terminal history related information by using a Spark distributed processing technology to obtain effective terminal history related information; finally, the history-related information of the valid terminals is stored in the data storage module 302.
Here, due to the huge amount of user information, the part is stored by using a distributed database of Hadoop, namely a Hive database.
It should be noted that, the historical terminal information acquired by the data acquisition module 301 from the operator device is information that has undergone data desensitization processing; the data desensitization is used for carrying out data deformation on sensitive information of a user through a desensitization rule, and reliable protection of the sensitive private data of the user is achieved.
Then, the data calculation and analysis module 303 calculates the user density of the scenic spot.
The method for calculating the user density in the scenic spot comprises the following steps: and counting all terminals in the coverage range of each base station of the scenic spot within one hour by taking one hour as a time node, and then dividing the total users in the coverage range of each base station by the coverage range of the total users to obtain the number of the scenic spots in the unit area of the current one hour, namely the user density of the scenic spots. And selecting the maximum value of user density calculation which is carried out on the current day by taking one hour as a time node as the user density of the current day scene area.
Or, when calculating the user density in the scenic spot, the peak data of the holiday and the festival can be selected; the method comprises the steps of determining the user density of scenic spots every day during peak periods of holiday tourists, calculating the average value of the user density of the scenic spots of a plurality of holidays, and using the calculated average value of the user density of the scenic spots for subsequent calculation. Therefore, the problem of the peak time of tourists is considered in the determination of the emergency point, so that the emergency point is reasonably selected and the maximum user requirement is met.
Step 2: the data calculation and analysis module 303 selects scenic spot emergency points by using the obtained scenic spot user density and combining a K-mediads algorithm.
Here, the process of selecting the scenic spot emergency point includes:
step a: randomly selecting a group of sample points as a central point set; and each central point (i.e. sample point) in the central point set corresponds to one cluster;
here, the sample point means a certain unit area point data; the set of sample points refers to a plurality of unit area points determined according to the area of the first scenic region.
Step b: calculating the cost from other sample points except the central point (namely the selected sample point) to each central point in the scenic spot, and putting other sample points into the cluster corresponding to the central point with the minimum cost to determine a plurality of clusters;
here, the cost is calculated using equation (1).
Step c: for each cluster, calculating a point with the minimum total cost from the cost of each sample point in the cluster as a new central point;
here, the total cost is calculated using equation (2).
Step d: if the new center point set is the same as the original center point set, the algorithm is terminated; and if the new central point set is not identical to the original central point set, returning to the step b, namely, re-determining a plurality of clusters.
And finishing the calculation step to output a central point set, wherein the central point in the central point set is the determined emergency point, and the cluster corresponding to each central point is the service range of each determined emergency point.
The calculation process of the K-mediads algorithm ensures that the total distance between the user in the area corresponding to each central point and the central point is minimum. The set of center points can be used as a reference for the scenic spot emergency point selection location.
In addition, the future number of people in the scenic spot is predicted by analyzing the terminal historical related information of the scenic spot through a technical means, and the method has certain significance for the advanced formulation of emergency plans in the scenic spot, particularly during the peak periods of travel such as five-one and eleven. In the embodiment of the application, the LASSO is used for analyzing the terminal historical information to obtain a people number prediction model for predicting the number of people in a future scenic spot, and the method obtains a relatively refined model by constructing a penalty function, and is a biased estimation for processing complex collinearity data.
The method for obtaining the people number prediction model by using the LASSO in the application embodiment comprises the following steps:
first, independent and dependent variables are determined.
Wherein the determined argument (x) may comprise: weather factors (available from the central weather service) and holiday factors obtained from weather history data.
Here, the weather factors may include: air temperature, air pressure, wind speed, rainfall, etc. Holiday factors may include: the duration of a festival (e.g., days, etc.), a particular festival, etc.
And determining the dependent variable (y) as the number of the scenic spots.
And then, obtaining a functional relation between the number of people in the scenic spot and the independent variable, namely a scenic spot number prediction model through the LASSO in machine learning.
Specifically, the coefficients corresponding to the respective variables (weather factor and holiday factor) are determined by the formula (3) and the formula (4), and the determined coefficients corresponding to the respective variables are substituted into the formula (6), so that the people number prediction model of the scenic spot can be determined.
Wherein t is an adjusting parameter, and the compression of the overall regression coefficient can be realized by controlling the adjusting parameter t.
In practical applications, there are many program implementations of LASSO, such as the package Lars of the R language, and the specific rendering code thereof is not shown here.
The functional relationship between the independent variables (air temperature, air pressure, holidays, etc.) and the number of scenic spots can be determined by the LASSO in the machine learning. The function relation is a scenic spot number prediction model, and the function can be used for predicting the future number of people in the scenic spot and used as a reference for setting the reserve material quantity and the emergency capacity of the scenic spot emergency points. In addition, the prediction data of the future number of people in the scenic spot can also be used as reference data for setting the emergency plan level of the scenic spot.
The data tag calculation module 304 acquires terminal history related information from the data storage module 302, and acquires the determined emergency point and emergency point service range from the data calculation and analysis module 303; and analyzing the crowd characteristics in the service range of each emergency point, and predicting the people appearing in the future scenic spot according to the crowd characteristics.
The crowd characteristics obtained through the terminal history related information comprise: the number of persons in a specific area, the crowd density, the crowd age distribution proportion, the individual gender and other parameters; the data label calculation module 304 binds the parameters with the selected emergency points to generate data labels as reference data of the quantity and the types of reserve materials of the emergency points in the scenic spot.
Specifically, the data tag calculation module 304 analyzes the crowd characteristics in the service range of each emergency point, and determines the number of visitors (such as the number of middle-aged visitors or the number of female visitors) of a specific crowd in the service range of the emergency point during the historical holidays by using the parameters such as the distribution ratio of the age groups of the crowd in the crowd characteristics, the individual sex and the like when predicting the presence of people in the future scenic spots according to the crowd characteristics; and combining with the LASSO regression algorithm to obtain a people number prediction model (such as a middle-aged visitor number prediction model or a female visitor number prediction model) for the specific population.
Here, the determination of the number of people prediction model for a certain specific group in combination with the LASSO regression algorithm is the same as the above-described determination of the number of people prediction model for predicting the number of people in the future scenic spot, where Y in formula (3) represents the number of visitors of the specific group in the emergency point service range during the historical holidays, and Y in formula (6) represents the number of visitors of the specific group in the predicted emergency point service range; therefore, more accurate reference data can be provided for the types and the quantity of the materials stored in the emergency points based on the number prediction model aiming at the crowd with different characteristics.
Meanwhile, the data tag calculation module 304 stores the generated data tag into the data tag storage module 305, so as to be used as a reference for locating emergency points in scenic spots and as reference data for the type and quantity of reserve materials of the emergency points.
The emergency point addressing system provided by the application embodiment has the following advantages:
firstly, the terminal history related information is used for emergency point addressing in scenic spots, so that the application field of the terminal history related information is expanded, and the application value of the terminal history related information is improved;
secondly, compared with the traditional single-point site selection, the application embodiment adopts a K-mediads algorithm to carry out site selection on the scenic spot emergency points, so that the scenic spot is considered in a total amount; a plurality of emergency points can be determined; in addition, the self-attribute of the K-mediads algorithm ensures that the point sets of the calculation results are not distributed in a centralized way, and ensures that the emergency points are distributed reasonably.
Thirdly, the emergency point of the scenic spot is determined based on the historical related information of the terminal acquired from the operator equipment, the cost is lower than that of the traditional method for acquiring the user information of the scenic spot by manual statistics, satellite images and the like, and the acquired data contain more comprehensive information. In addition, the terminal history related information is utilized, and a new idea is provided for the application of the terminal history related information.
And fourthly, providing the crowd characteristic information in the service range for the emergency points, and taking the crowd characteristic information as an effective reference for the types and the quantity of emergency material reserves.
And fifthly, analyzing historical data of the scenic spot by adopting LASSO in machine learning, determining a prediction model of the future number of people in the scenic spot, and predicting the future number of people in the scenic spot.
In order to implement the method according to the embodiment of the present invention, an embodiment of the present invention further provides an emergency point determining apparatus, as shown in fig. 4, where the apparatus includes: a first obtaining module 401, a first determining module 402 and a second determining module 403; wherein the content of the first and second substances,
the first obtaining module 401 is configured to obtain history related information of a terminal; the acquired terminal history related information at least comprises related information when the terminal is in the first scenic spot.
The first determining module 402 is configured to determine, for each base station, the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot.
The second determining module 403 is configured to determine, by using the obtained at least one crowd density, the number and the location of the emergency points in the first scenic spot in combination with a clustering algorithm.
In an embodiment, the second determining module 403 is specifically configured to:
and determining the number and the positions of emergency points in the first scenic spot by using the obtained at least one crowd density and combining a K-means algorithm of a K central point.
In an embodiment, the first obtaining module 401 is specifically configured to:
and acquiring the terminal history related information from the database.
In one embodiment, the apparatus further comprises: the device comprises a second acquisition module, a filtering module and a first storage module; wherein the content of the first and second substances,
the second obtaining module is configured to obtain historical related information of the terminal from the operator device.
And the filtering module is used for filtering the terminal history related information acquired from the operator equipment to obtain the effective terminal history related information.
And the first storage module is used for storing the obtained historical relevant information of the effective terminal to the database.
In one embodiment, the apparatus further comprises: a third obtaining module and a third determining module; the third acquisition module is used for acquiring historical weather data and historical holiday data.
The third determining module is used for determining a people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data; the determined people number prediction model is used for predicting the people number in the first scenic spot.
In an embodiment, the third determining module is specifically configured to:
and determining the people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data and combining with LASSO.
In one embodiment, the apparatus further comprises: a fourth determining module and a second storing module; the fourth determining module is configured to determine, for each determined emergency point, the crowd characteristics within the service range of the corresponding emergency point by using the historical related information of the terminal; generating a data label by using the determined crowd characteristics and the corresponding emergency point position; the generated data label is used for determining the quantity and the type of the reserve materials of the emergency point.
The second storage module is used for storing the generated data label.
The functions of the first obtaining module 401, the first determining module 402 and the second determining module 403 are equivalent to the functions of the data calculating and analyzing module 303 in the above application embodiment; the functions of the second obtaining module and the filtering module are equivalent to the functions of the data acquisition module 301 in the above application embodiment; the function of the first storage module is equivalent to that of the data storage module 302 in the above application embodiment; the functions of the third obtaining module, the third determining module and the fourth determining module are equivalent to the functions of the data tag calculating module 304 in the above application embodiment; the function of the second storage module is equivalent to the function of the data tag storage module 305 in the above application embodiment.
In practical applications, the first obtaining module 401, the first determining module 402, the second determining module 403, the second obtaining module, the filtering module, the first storing module, the third obtaining module, the third determining module, the fourth determining module, and the second storing module may be implemented by a processor in the emergency point determining device.
It should be noted that: the emergency point determining device provided in the above embodiment is only illustrated by the division of the program modules when determining the emergency point, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the emergency point determination device and the method embodiment provided by the above embodiments belong to the same concept, and the specific implementation process thereof is described in the method embodiment and is not described herein again.
Based on the hardware implementation of the program module, and in order to implement the method according to the embodiment of the present invention, an embodiment of the present invention further provides an emergency point determining apparatus, as shown in fig. 5, where the emergency point determining apparatus 50 includes:
a processor 51, configured to execute the emergency point determination methods provided in the foregoing technical solutions when running a computer program;
a memory 52 for storing a computer program capable of running on the processor 51.
In particular, the processor 51 is configured to perform the following operations:
acquiring historical related information of a terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot;
for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot;
and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
In an embodiment, the processor 51 is specifically configured to perform the following operations:
and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a K-means algorithm.
In an embodiment, the processor 51 is specifically configured to perform the following operations:
and acquiring the terminal history related information from the database.
In an embodiment, before obtaining the terminal history related information from the database, the processor 51 is further configured to:
acquiring terminal history related information from operator equipment;
filtering the terminal history related information acquired from the operator equipment to obtain effective terminal history related information;
and storing the obtained history related information of the effective terminal to the database.
In an embodiment, the processor 51 is further configured to perform the following operations:
acquiring historical weather data and historical holiday data;
determining a people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data; the determined people number prediction model is used for predicting the people number in the first scenic spot.
In an embodiment, the processor 51 is specifically configured to perform the following operations:
and determining the people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data and combining with LASSO.
In an embodiment, the processor 51 is further configured to perform the following operations:
aiming at each base station, determining the crowd characteristics in the first coverage range of the corresponding base station by using the historical related information of the terminal to which the base station belongs; generating a data label by using the determined crowd characteristics and the corresponding emergency point position; the generated data label is used for determining the quantity and the type of the reserve materials of the emergency point;
and storing the generated data label.
It should be noted that: the specific process of executing the operation by the processor 51 is detailed in the method embodiment, and is not described herein again.
Of course, in practice, the various components of the emergency point determination device 50 are coupled together by a bus system 53. It will be appreciated that the bus system 53 is used to enable communications among the components. The bus system 53 includes a power bus, a control bus, and a status signal bus in addition to the data bus. For clarity of illustration, however, the various buses are labeled as bus system 53 in fig. 5.
The memory 52 in embodiments of the present invention is used to store various types of data to support the operation of the emergency point determination device 50. Examples of such data include: any computer program for operating on the emergency point determination device 50.
The method disclosed in the above embodiments of the present invention may be applied to the processor 51, or implemented by the processor 51. The processor 51 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by integrated logic circuits of hardware or instructions in the form of software in the processor 51. The Processor 51 may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor 51 may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the memory 52, and the processor 51 reads the information in the memory 52 and performs the steps of the aforementioned method in conjunction with its hardware.
In an exemplary embodiment, the emergency point determination Device 50 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the aforementioned methods.
It will be appreciated that the memory (memory 52) of embodiments of the invention may be either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The described memory for embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.
In an exemplary embodiment, the present invention further provides a storage medium, i.e. a computer storage medium, in particular a computer readable storage medium, for example, including a memory 52 storing a computer program, which is executable by the processor 51 of the emergency point determination device 50 to perform the steps of the foregoing method. The computer readable storage medium may be Memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface Memory, optical disk, or CD-ROM.
It should be noted that: "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
In addition, the technical solutions described in the embodiments of the present invention may be arbitrarily combined without conflict.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.

Claims (10)

1. An emergency point determination method, comprising:
acquiring historical related information of a terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot;
for each base station, determining the number of terminals to which the corresponding base station belongs based on the acquired historical related information of the terminals; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot;
and determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
2. The method of claim 1, wherein the determining the number and location of emergency points within the first scenic spot using the obtained at least one crowd density in combination with a clustering algorithm comprises:
and determining the number and the positions of emergency points in the first scenic spot by using the obtained at least one crowd density and combining a K-means algorithm of a K central point.
3. The method of claim 1, wherein the obtaining terminal history related information comprises:
and acquiring the terminal history related information from the database.
4. The method of claim 3, wherein before obtaining the terminal history related information from the database, the method further comprises:
acquiring terminal history related information from operator equipment;
filtering the terminal history related information acquired from the operator equipment to obtain effective terminal history related information;
and storing the obtained history related information of the effective terminal to the database.
5. The method of claim 1, further comprising:
acquiring historical weather data and historical holiday data;
determining a people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data; the determined people number prediction model is used for predicting the people number in the first scenic spot.
6. The method of claim 5, wherein determining a people number prediction model using the obtained terminal history related information, historical weather data and historical holiday data comprises:
and determining the people number prediction model by using the acquired terminal historical related information, historical weather data and historical holiday data and combining a minimum absolute shrinkage and selection algorithm LASSO.
7. The method of claim 1, further comprising:
aiming at each base station, determining the crowd characteristics in the first coverage range of the corresponding base station by using the historical related information of the terminal to which the base station belongs; generating a data label by using the determined crowd characteristics and the corresponding emergency point position; the generated data label is used for determining the quantity and the type of the reserve materials of the emergency point;
and storing the generated data label.
8. An emergency point determination device, comprising:
the first acquisition module is used for acquiring historical related information of the terminal; the acquired historical related information of the terminal at least comprises related information when the terminal is positioned in a first scenic spot;
the first determining module is used for determining the number of the terminals of the corresponding base station based on the acquired historical related information of the terminals aiming at each base station; determining the crowd density of the first coverage range of the corresponding base station on the corresponding date by using the determined number of the terminals to obtain at least one crowd density; the first coverage area belongs to the first scenic spot;
and the second determining module is used for determining the number and the positions of the emergency points in the first scenic spot by using the obtained at least one crowd density and combining a clustering algorithm.
9. An emergency point determination apparatus, comprising: a processor and a memory for storing a computer program capable of running on the processor;
wherein the processor is adapted to perform the steps of the method of any one of claims 1 to 7 when running the computer program.
10. A storage medium storing a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by a processor.
CN201910838703.4A 2019-09-05 2019-09-05 Emergency point determination method and device and storage medium Pending CN112446406A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910838703.4A CN112446406A (en) 2019-09-05 2019-09-05 Emergency point determination method and device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910838703.4A CN112446406A (en) 2019-09-05 2019-09-05 Emergency point determination method and device and storage medium

Publications (1)

Publication Number Publication Date
CN112446406A true CN112446406A (en) 2021-03-05

Family

ID=74733385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910838703.4A Pending CN112446406A (en) 2019-09-05 2019-09-05 Emergency point determination method and device and storage medium

Country Status (1)

Country Link
CN (1) CN112446406A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113159397A (en) * 2021-03-31 2021-07-23 上海城市地理信息系统发展有限公司 Disaster relief material pre-storage management method and device and electronic equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013121073A (en) * 2011-12-07 2013-06-17 Ntt Docomo Inc Position information analysis device and position information analysis method
US20150324812A1 (en) * 2014-05-08 2015-11-12 Baidu Online Network Technology (Beijing) Co., Ltd Method and device for obtaining customer traffic distribution
KR20160044704A (en) * 2014-10-15 2016-04-26 에스케이텔레콤 주식회사 Method and Apparatus for Identifying Actual Location of Terminal and Apparatus Therefor
WO2017202226A1 (en) * 2016-05-23 2017-11-30 中兴通讯股份有限公司 Method and device for determining crowd traffic
CN109697435A (en) * 2018-12-14 2019-04-30 重庆中科云从科技有限公司 Stream of people's quantity monitoring method, device, storage medium and equipment
US20190208365A1 (en) * 2017-12-31 2019-07-04 Bull Sas System and method for managing a mass gathering

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013121073A (en) * 2011-12-07 2013-06-17 Ntt Docomo Inc Position information analysis device and position information analysis method
US20150324812A1 (en) * 2014-05-08 2015-11-12 Baidu Online Network Technology (Beijing) Co., Ltd Method and device for obtaining customer traffic distribution
KR20160044704A (en) * 2014-10-15 2016-04-26 에스케이텔레콤 주식회사 Method and Apparatus for Identifying Actual Location of Terminal and Apparatus Therefor
WO2017202226A1 (en) * 2016-05-23 2017-11-30 中兴通讯股份有限公司 Method and device for determining crowd traffic
US20190208365A1 (en) * 2017-12-31 2019-07-04 Bull Sas System and method for managing a mass gathering
CN109697435A (en) * 2018-12-14 2019-04-30 重庆中科云从科技有限公司 Stream of people's quantity monitoring method, device, storage medium and equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DUNCAN EAST ET AL.: "Combining GPS & survey data improves understanding of visitor behaviour", 《TOURISM MANAGEMENT》, vol. 61, 31 August 2017 (2017-08-31), pages 307 - 320 *
刘耕等: "基于信令数据的旅游景区智能管控研究", 《电子科技大学学报》, vol. 44, no. 5, 30 September 2015 (2015-09-30), pages 1 - 3 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113159397A (en) * 2021-03-31 2021-07-23 上海城市地理信息系统发展有限公司 Disaster relief material pre-storage management method and device and electronic equipment

Similar Documents

Publication Publication Date Title
Tascikaraoglu et al. Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using Wavelet Transform
CN108495254B (en) Traffic cell population characteristic estimation method based on signaling data
CN110363621B (en) Order information pushing system based on artificial intelligence technology
CN110569321B (en) Grid division processing method and device based on urban map and computer equipment
CN113705959B (en) Network resource allocation method and electronic equipment
CN106878359B (en) Information pushing method and device
CN105303292A (en) Distribution data storage method and device
Yoffe et al. Towards sustainability evaluation of urban landscapes using big data: A case study of Israel’s architecture, engineering and construction industry
CN116011322A (en) Urban information display method, device, equipment and medium based on digital twinning
Xu et al. Hybrid holiday traffic predictions in cellular networks
CN115272002A (en) Building energy prediction method, device, storage medium and program product
CN114462722A (en) New energy power generation light-weight high-precision cloud prediction system, method and device
CN112446406A (en) Emergency point determination method and device and storage medium
CN112926863B (en) Six-large-early-warning-center-based comprehensive power grid disaster monitoring system
US20190164065A1 (en) Systems and Methods Venue Visitation Forecasting
CN113887917A (en) Smart city management platform based on service architecture
CN108154259B (en) Load prediction method and device for heat pump, storage medium, and processor
CN113515708A (en) Project recommendation method and device for construction land, storage medium and processor
CN117079148A (en) Urban functional area identification method, device, equipment and medium
CN116227760B (en) Method, device, storage medium and equipment for predicting influence of travel activities
Zhang et al. SolarGAN: Synthetic annual solar irradiance time series on urban building facades via Deep Generative Networks
KR20210128823A (en) Crossroads LOS Prediction Method Based on Big Data and AI, and Storage Medium Having the Same
CN105868435B (en) It is a kind of to analyze the efficient control method for realizing optical-fiber network construction based on linear dependence
CN110942353A (en) Big data based operation analysis method
CN111121806A (en) Travel mode planning method and device, computer equipment and storage medium

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