CN111768031A - Method for predicting crowd gathering tendency based on ARMA algorithm - Google Patents
Method for predicting crowd gathering tendency based on ARMA algorithm Download PDFInfo
- Publication number
- CN111768031A CN111768031A CN202010588491.1A CN202010588491A CN111768031A CN 111768031 A CN111768031 A CN 111768031A CN 202010588491 A CN202010588491 A CN 202010588491A CN 111768031 A CN111768031 A CN 111768031A
- Authority
- CN
- China
- Prior art keywords
- predicted
- day
- value
- daily
- activity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting crowd gathering tendency based on ARMA algorithm, aiming at finding more effective implementation scheme for predicting the crowd gathering tendency, comprising the following steps: acquiring the current day activity information of a day to be predicted of a preset place, and the daily aggregated people number and daily activity information in p days before the day to be predicted; obtaining a predicted aggregation person numerical value of the day to be predicted based on the activity information of the day and the daily aggregation person numerical value and daily activity information in p days; and acquiring a daily aggregation person numerical value in r days before the day to be predicted, confirming whether the predicted aggregation person numerical value is abnormal or not based on the daily aggregation person numerical value in r days and the predicted aggregation person numerical value, and if so, displaying that the predicted aggregation person numerical value is abnormal. According to the method, long-time multi-dimensional attention crowd place gathering data is adopted, the ARMA algorithm is utilized to extract the potential correlation between the event which cannot be judged manually and the time, and the defect of experience judgment on the attention crowd gathering degree in the traditional work is overcome.
Description
Technical Field
The invention relates to the field of big data, in particular to a method for predicting crowd gathering tendency based on an ARMA algorithm.
Background
When actions such as important activity prediction, public security and the like are performed, the behavior of an attention target can be reflected by the gathering of attention people, and meanwhile, the gathering degree of attention people has certain correlation with the occurrence of events in a target region. For this reason, there is a need to be able to focus on the tendency of people to gather in the interest group.
Traditional artificial experience-based research on the gathering of people of interest can be effective to some extent, but two obvious problems also exist at the same time: the first is the ability of predicting group events in advance, the gathering of attention people in traditional work often depends on the experience of researchers, and the emphasis is on controlling the places where the group events of the attention people occur frequently and the places with intensive personnel, but the method cannot effectively predict events beyond experience; secondly, for setting the aggregation threshold, the aggregation threshold for the attention crowd aggregation in the traditional work is manually set, and the criterion for judging aggregation may change along with the change of time and places, so that the manual setting cannot well divide the normal aggregation and the abnormal crowd event aggregation.
Disclosure of Invention
In order to find a more effective implementation scheme for predicting the crowd gathering tendency, the invention provides a method for predicting the crowd gathering tendency based on an ARMA algorithm, which comprises the following steps:
acquiring the current day activity information of a day to be predicted of a preset place, and a daily aggregated person number and daily activity information in p days before the day to be predicted, wherein p is a natural number;
obtaining a predicted aggregated person value of the day to be predicted based on the activity information of the day and the daily aggregated person value and daily activity information in the p days;
and acquiring a daily aggregated human value in r days before the day to be predicted, confirming whether the predicted aggregated human value is abnormal or not based on the daily aggregated human value in r days and the predicted aggregated human value, and if so, displaying that the predicted aggregated human value is abnormal, wherein r is a natural number not greater than p.
Preferably, the step of confirming the predicted aggregated people number value of the day to be predicted based on the activity information of the day and the daily aggregated people number value and daily activity information in the p days comprises the following steps:
determining the activity level N of the day to be predicted according to a preset grading rule based on the activity information of the dayt;
Based on the activity level NtAnd training the daily aggregated human value and the daily activity information in the p days to obtain a prediction function Yt:
Wherein t is a day to be predicted, p is the number of days of t forward of the day to be predicted, and p and q have the same numerical value;
y in (1)t-1For day Y to be predictedtThe number of people gathered on the day before (2),is an aggregation weight;
as error term, et-1To predict the error value predicted the day before the tth day,is the error weight;
βtNtan influence factor of the information on the activities of the day, βtAs the weight of the activity, NtIs the activity level;
based on the prediction function YtAnd obtaining the prediction aggregation human number value of the day to be predicted.
Preferably, the activity level value is an integer of 0 to 4, and the activity level N of the day to be predicted is determined according to a preset grading rule based on the activity information of the daytThe method comprises the following steps:
searching the activity participation number of the same activity in a preset database based on the activity information of the current day, and if the activity participation number cannot be searched, judging the activity level N of the day to be predictedtIs 0;
if the data is found, reading the value of the activity participant nearest to the day to be predicted, and confirming the activity level N based on a preset grading ruletWherein the preset grading rule is as follows:
when the number of the people participating in the activity is less than 500 people, the activity level N of the day to be predictedtIs 1;
when the value of the activity participants is not less than 500 and less than 2000, the activity level N of the day to be predictedtIs 2;
when the value of the activity participants is not less than 2000 and less than 5000, the activity level N of the day to be predictedtIs 3;
when the value of the activity participants is not less than 5000 persons, the activity level N of the day to be predictedtIs 4.
Preferably, the values of the aggregation weight and the error weight range from 0 to 10 integers, the values based on the activity and the likeStage NtTraining the daily aggregated human value and the daily activity information in the p days to obtain a prediction function YtThe method comprises the following steps:
converting the daily aggregated human number value and the daily activity information in p days into a matrix, respectively assigning initial RANDOM weights of the aggregated weight and the error weight to integers of 0-10 by using a RANDOM function, calculating a Loss value Loss function between the estimated value and a real value by using a least square method after calculating the estimated value by forward propagation:
iterating according to a preset termination rule and a gradient descent method to obtain the final weight parameter theta of the aggregation weight or the error weight1:
Wherein, theta0An initial random weight that is the aggregate weight or the error weight,for each descending inverse derivative of the Loss function,is the learning rate.
Preferably, the preset termination rule includes one of the following conditions:
the average Loss value of the Loss function is not more than 1;
the number of iterations reaches fifty thousand and the average loss value decreases less than 0.001 in the last ten.
Preferably, the confirming whether the predicted aggregated human number is an abnormal point based on the daily aggregated human number and the predicted aggregated human number within the r-day includes the steps of:
randomly selecting an aggregated people value from the daily aggregated people values and the predicted aggregated people values over the r-day;
performing data segmentation of isolated forests according to the daily aggregation person numerical value and the predicted aggregation person numerical value in the r day of the selected aggregation person numerical value, placing records of which the aggregation person numerical values are smaller than the selected aggregation person numerical value on a left daughter, and placing records of which the aggregation person numerical values are larger than or equal to the selected aggregation person numerical value on a right child;
recursively constructing the left and right daughter until one of the following conditions is met: the input aggregated human number value has only one record or a plurality of same records; the height of the tree reaches the preset height;
and judging whether only one predicted aggregation person numerical value is returned and whether the predicted aggregation person numerical value is larger than a preset early warning value, if so, confirming that the predicted aggregation person numerical value is an abnormal point.
Preferably, the preset height is one fourth of the total data amount of the daily aggregated human number value and the predicted aggregated human number value within the r day.
Preferably, the preset early warning value is the sum of the average value of the daily aggregated human figures in the r day and three times of the standard deviation of the daily aggregated human figures in the r day.
Preferably, r is 30 and p is 365.
Compared with the prior art, the method for predicting the crowd gathering tendency based on the ARMA algorithm has the following beneficial effects:
the method for predicting the crowd gathering trend based on the ARMA algorithm adopts long-time multi-dimensional crowd gathering data of concerned places, extracts the potential correlation between the event which cannot be judged manually and the time by utilizing the ARMA algorithm, and carries out comprehensive regression calculation by using the event dimension to predict the gathered people number at the next time point, thereby overcoming the defect of empirical judgment on the gathering degree of the concerned crowd in the traditional work. Meanwhile, according to the gathering condition of the concerned crowd places of the historical data, the abnormal points in the concerned crowd places are extracted by using an isolated forest algorithm to serve as abnormal early warning, a relatively fixed threshold value is not needed, and normal gathering and abnormal crowd event gathering can be effectively distinguished.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart of a method for predicting crowd gathering tendency based on ARMA algorithm according to an embodiment of the present invention;
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
Referring to fig. 1, the present invention provides a method for predicting crowd gathering tendency based on ARMA algorithm, which includes the following steps:
step S101: acquiring the current day activity information of a day to be predicted in a preset place, and the daily aggregated people number and the daily activity information in p days before the day to be predicted, wherein p is a natural number.
In some embodiments, the current day activity information or the daily activity information is an exhibition, an artistic performance, a large meeting, a hot event, or the like. The preset places are Internet bars, hotels, airports, railway stations, crowd monitoring points, road checkpoints and the like.
It is worth noting that the concerned crowd can be associated with the preset place gathering data by taking the identity card number as an associated field; the holiday large-scale activity data and the historical site gathering data are associated, the two data relate to the association of time and space, the time can be directly associated, but no field similar to a preset site code is associated in space (the relevant dimension of a site comprises longitude and latitude, a site name and a site address), so comprehensive association is needed, and the specific steps are as follows:
the difference between the longitude and the latitude is matched, and if the difference between the longitude and the latitude between the two places is +/-0.00001 degree (the difference is about 1.113 meters in the actual length), the two places are divided into the same place;
if some longitude and latitude do not find the matched place, keywords are extracted from the place name and the place address by utilizing a jieba word segmentation algorithm and a tf-idf algorithm, fuzzy matching is carried out on the keywords, matching scores of the place name and the place address are calculated respectively, then the scores are normalized and added, and the highest score is taken to be divided into the same place.
Meanwhile, when data is acquired, if the missing values exist, it is preferable to associate the missing values with existing data, for example, if a place code of a certain piece of data has a missing place name, the place name can be associated with the place code. If the method is not related, the KNN nearest neighbor method is used for padding, which is not described in detail in the embodiment of the present invention.
Step S103: and obtaining the predicted aggregated people value of the day to be predicted based on the activity information of the day and the daily aggregated people value and daily activity information in the p days.
Specifically, the step of confirming the predicted aggregated people number value of the day to be predicted based on the activity information of the day and the daily aggregated people number value and daily activity information in p days comprises the following steps:
determining activity level N of a day to be predicted according to a preset grading rule based on the activity information of the dayt;
Based on activity level NtAnd the daily aggregated human value and daily activity information in p days are trained to obtain the following prediction function Yt:
Wherein t is a day to be predicted, p is the number of days of t forward of the day to be predicted, and p and q have the same numerical value;
y in (1)t-1For day Y to be predictedtThe number of people gathered on the day before (2),is an aggregation weight;
as error term, et-1To predict the error value predicted the day before the tth day,is the error weight;
βtNtan influence factor of the information on the activities of the day, βtAs the weight of the activity, NtIs the activity level;
based on a prediction function YtAnd obtaining the predicted aggregated human number of the day to be predicted.
Preferably, the activity level value is an integer of 0-4, and the activity level N of the day to be predicted is determined according to a preset grading rule based on the activity information of the daytThe method comprises the following steps:
searching the activity participation number of the same activity in a preset database based on the activity information of the current day, and if the activity participation number cannot be searched, judging the activity level N of the day to be predictedtIs 0;
if the data is found, reading the value of the activity participant nearest to the day to be predicted, and confirming the activity level N based on the preset grading ruletWherein the preset grading rule is as follows:
when the number of the people participating in the activity is less than 500, the activity level N of the day to be predictedtIs 1;
when the value of the activity participants is not less than 500 and less than 2000, the activity level N of the day to be predictedtIs 2;
when the value of the activity participants is not less than 2000 but less than 5000, the activity level N of the day to be predictedtIs 3;
when the value of the activity participants is not less than 5000 persons, the activity level N of the day to be predictedtIs 4.
In some embodiments, the aggregate weight and the error weight range from an integer of 0 to 10 based on the activity level NtTraining the daily aggregated human value and daily activity information in p days to obtain a prediction function YtThe method comprises the following steps:
converting daily aggregated human number values and daily activity information in p days into a matrix, respectively assigning initial RANDOM weights of the aggregated weight and the error weight to integers of 0-10 by using a RANDOM function, calculating a Loss value Loss function between the estimated value and a real value by using a least square method after calculating the estimated value by forward propagation:
iterating according to a preset termination rule and a gradient descent method to obtain a final weight parameter theta of the aggregation weight or the error weight1:
Wherein, theta0An initial random weight that is an aggregate weight or an error weight,for each descending inverse derivative of the Loss function,is the learning rate.
Preferably, the preset termination rule comprises one of the following conditions: the average Loss value of the Loss function is not more than 1; the number of iterations reaches fifty thousand and the average loss value decreases less than 0.001 in the last ten.
Step S105: and acquiring a daily aggregated human value in r days before the day to be predicted, confirming whether the predicted aggregated human value is abnormal or not based on the daily aggregated human value in r days and the predicted aggregated human value, and if so, displaying that the predicted aggregated human value is abnormal, wherein r is a natural number not greater than p.
Specifically, confirming whether the predicted aggregated human number is an abnormal point based on the daily aggregated human number and the predicted aggregated human number within r days includes the steps of:
randomly selecting an aggregated people value from the daily aggregated people values and predicted aggregated people values over r days;
performing data segmentation of isolated forests according to the daily aggregation person numerical value and the predicted aggregation person numerical value in r days of the selected aggregation person numerical value, placing records of which the aggregation person numerical value is smaller than the selected aggregation person numerical value on a left daughter, and placing records of which the aggregation person numerical value is greater than or equal to the selected aggregation person numerical value on a right child;
recursively constructing the left and right daughter until one of the following conditions is met: the input aggregated human number value has only one record or a plurality of same records; the height of the tree reaches the preset height;
and judging whether the number of the returned predicted aggregation persons is only one and whether the number of the predicted aggregation persons is larger than a preset early warning value, if so, determining that the number of the predicted aggregation persons is an abnormal point.
Preferably, the preset height is one fourth of the total data amount of the daily aggregated human number and the predicted aggregated human number for r days. The preset early warning value is the sum of the average value of the daily aggregated human number values in r days and three times of the standard deviation of the daily aggregated human number values in r days.
In some embodiments, r is 30 and p is 365.
Compared with the prior art, the method for predicting the crowd gathering tendency based on the ARMA algorithm has the following beneficial effects:
the method for predicting the crowd gathering trend based on the ARMA algorithm adopts long-time multi-dimensional crowd gathering data of the concerned crowd, extracts the potential correlation between the event which cannot be judged manually and the time by utilizing the ARMA algorithm, and carries out comprehensive regression calculation by the event dimension to predict the gathered people at the next time point, thereby overcoming the defect of empirical judgment on the gathering degree of the concerned crowd in the traditional work. Meanwhile, according to the gathering condition of the concerned crowd places of the historical data, the abnormal points in the concerned crowd places are extracted by using an isolated forest algorithm to serve as the abnormal early warning, a relatively fixed threshold value is not needed, and normal gathering and abnormal crowd event gathering can be effectively distinguished.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for predicting the crowd gathering tendency based on an ARMA algorithm is characterized by comprising the following steps:
acquiring the current day activity information of a day to be predicted of a preset place, and a daily aggregated person number and daily activity information in p days before the day to be predicted, wherein p is a natural number;
obtaining a predicted aggregated person value of the day to be predicted based on the activity information of the day and the daily aggregated person value and daily activity information in the p days;
and acquiring a daily aggregated human value in r days before the day to be predicted, confirming whether the predicted aggregated human value is abnormal or not based on the daily aggregated human value in r days and the predicted aggregated human value, and if so, displaying that the predicted aggregated human value is abnormal, wherein r is a natural number not greater than p.
2. The method for predicting people group aggregation tendency based on ARMA algorithm as claimed in claim 1, wherein the step of confirming the predicted people group aggregation number value of the day to be predicted based on the activity information of the day and the daily people group aggregation number value and daily activity information of the p days comprises the following steps:
determining the activity level N of the day to be predicted according to a preset grading rule based on the activity information of the dayt;
Based on the activity level NtAnd training the daily aggregated human value and the daily activity information in the p days to obtain a prediction function Yt:
Wherein t is a day to be predicted, p is the number of days of t forward of the day to be predicted, and p and q have the same numerical value;
y in (1)t-1For day Y to be predictedtThe number of people gathered on the day before (2),is an aggregation weight;
as error term, et-1To predict the error value predicted the day before the tth day,is the error weight;
βtNtan influence factor of the information on the activities of the day, βtAs the weight of the activity, NtIs the activity level;
based on the prediction function YtAnd obtaining the prediction aggregation human number value of the day to be predicted.
3. The ARMA algorithm based crowd gathering tendency prediction method as claimed in claim 2, wherein the activity level is an integer of 0-4, and the activity level N of the day to be predicted is determined according to a preset grading rule based on the activity information of the daytThe method comprises the following steps:
searching the activity participation number of the same activity in a preset database based on the activity information of the current day, and if the activity participation number cannot be searched, judging the activity level N of the day to be predictedtIs 0;
if the data is found, reading the value of the activity participant nearest to the day to be predicted, and confirming the activity level N based on a preset grading ruletWherein the preset grading rule is as follows:
when the number of the people participating in the activity is less than 500 people, the activity level N of the day to be predictedtIs 1;
when the value of the activity participants is not less than 500 and less than 2000, the activity level N of the day to be predictedtIs 2;
when the value of the activity participants is not less than 2000 and less than 5000, the activity level N of the day to be predictedtIs 3;
when the value of the activity participants is not less than 5000 persons, the activity level N of the day to be predictedtIs 4.
4. The method for predicting people group aggregation tendency based on ARMA algorithm as claimed in claim 2, wherein the values of the aggregation weight and the error weight are integers in the range of 0-10, and the method is based on the activity level NtTraining the daily aggregated human value and the daily activity information in the p days to obtain a prediction function YtThe method comprises the following steps:
converting the daily aggregated human number value and the daily activity information in p days into a matrix, respectively assigning initial RANDOM weights of the aggregated weight and the error weight to integers of 0-10 by using a RANDOM function, calculating a Loss value Loss function between the estimated value and a real value by using a least square method after calculating the estimated value by forward propagation:
iterating according to a preset termination rule and a gradient descent method to obtain the final weight parameter theta of the aggregation weight or the error weight1:
5. The method for predicting crowd gathering tendency based on ARMA algorithm as claimed in claim 4, wherein the preset termination rule comprises one of the following conditions:
the average Loss value of the Loss function is not more than 1;
the number of iterations reaches fifty thousand and the average loss value decreases less than 0.001 in the last ten.
7. The method of claim 1, wherein said determining if said predicted aggregated human figure is an outlier based on said daily aggregated human figure and said predicted aggregated human figure for said r-day comprises the steps of:
randomly selecting an aggregated people value from the daily aggregated people values and the predicted aggregated people values over the r-day;
performing data segmentation of isolated forests according to the daily aggregation person numerical value and the predicted aggregation person numerical value in the r day of the selected aggregation person numerical value, placing records of which the aggregation person numerical values are smaller than the selected aggregation person numerical value on a left daughter, and placing records of which the aggregation person numerical values are larger than or equal to the selected aggregation person numerical value on a right child;
recursively constructing the left and right daughter until one of the following conditions is met: the input aggregated human number value has only one record or a plurality of same records; the height of the tree reaches the preset height;
and judging whether only one predicted aggregation person numerical value is returned and whether the predicted aggregation person numerical value is larger than a preset early warning value, if so, confirming that the predicted aggregation person numerical value is an abnormal point.
8. The method for predicting people group aggregation tendency based on ARMA algorithm of claim 7, wherein the preset height is one-fourth of the total data volume of the daily people group number value and the predicted people group number value within the r-day.
9. The method for predicting people group aggregation tendency based on ARMA algorithm of claim 7, wherein the preset pre-warning value is the sum of the average value of the daily aggregated people number in the r-day and three times the standard deviation of the daily aggregated people number in the r-day.
10. The method for predicting population aggregation tendency based on ARMA algorithm of claim 1, wherein r is 30 and p is 365.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010588491.1A CN111768031B (en) | 2020-06-24 | 2020-06-24 | Method for predicting crowd gathering trend based on ARMA algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010588491.1A CN111768031B (en) | 2020-06-24 | 2020-06-24 | Method for predicting crowd gathering trend based on ARMA algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111768031A true CN111768031A (en) | 2020-10-13 |
CN111768031B CN111768031B (en) | 2023-09-19 |
Family
ID=72722390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010588491.1A Active CN111768031B (en) | 2020-06-24 | 2020-06-24 | Method for predicting crowd gathering trend based on ARMA algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111768031B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113993153A (en) * | 2021-10-27 | 2022-01-28 | 中国联合网络通信集团有限公司 | Crowd gathering prediction method, device, equipment and computer readable storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000056762A (en) * | 1999-02-25 | 2000-09-15 | 이종수 | Prediction method for city water request of water service system |
JP2004280731A (en) * | 2003-03-19 | 2004-10-07 | Nri & Ncc Co Ltd | Traffic congestion prediction system, traffic congestion prediction method, and compensation data system |
US20080033991A1 (en) * | 2006-08-03 | 2008-02-07 | Jayanta Basak | Prediction of future performance of a dbms |
CN107038492A (en) * | 2016-02-04 | 2017-08-11 | 滴滴(中国)科技有限公司 | Daily Order volume Forecasting Methodology and device based on Arma models |
CN107798409A (en) * | 2016-08-30 | 2018-03-13 | 中兴智能交通股份有限公司 | A kind of crowd massing Forecasting Methodology based on time series models |
CN108427989A (en) * | 2018-06-12 | 2018-08-21 | 中国人民解放军国防科技大学 | Deep space-time prediction neural network training method for radar echo extrapolation |
CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
CN109002904A (en) * | 2018-06-21 | 2018-12-14 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Prophet-ARMA |
CN109492788A (en) * | 2017-09-13 | 2019-03-19 | 中移(杭州)信息技术有限公司 | Prediction flow of the people and the method and relevant device for establishing flow of the people prediction model |
CN109697207A (en) * | 2018-12-25 | 2019-04-30 | 苏州思必驰信息科技有限公司 | The abnormality monitoring method and system of time series data |
-
2020
- 2020-06-24 CN CN202010588491.1A patent/CN111768031B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000056762A (en) * | 1999-02-25 | 2000-09-15 | 이종수 | Prediction method for city water request of water service system |
JP2004280731A (en) * | 2003-03-19 | 2004-10-07 | Nri & Ncc Co Ltd | Traffic congestion prediction system, traffic congestion prediction method, and compensation data system |
US20080033991A1 (en) * | 2006-08-03 | 2008-02-07 | Jayanta Basak | Prediction of future performance of a dbms |
CN107038492A (en) * | 2016-02-04 | 2017-08-11 | 滴滴(中国)科技有限公司 | Daily Order volume Forecasting Methodology and device based on Arma models |
CN107798409A (en) * | 2016-08-30 | 2018-03-13 | 中兴智能交通股份有限公司 | A kind of crowd massing Forecasting Methodology based on time series models |
CN109492788A (en) * | 2017-09-13 | 2019-03-19 | 中移(杭州)信息技术有限公司 | Prediction flow of the people and the method and relevant device for establishing flow of the people prediction model |
CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
CN108427989A (en) * | 2018-06-12 | 2018-08-21 | 中国人民解放军国防科技大学 | Deep space-time prediction neural network training method for radar echo extrapolation |
CN109002904A (en) * | 2018-06-21 | 2018-12-14 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Prophet-ARMA |
CN109697207A (en) * | 2018-12-25 | 2019-04-30 | 苏州思必驰信息科技有限公司 | The abnormality monitoring method and system of time series data |
Non-Patent Citations (5)
Title |
---|
DORINE C. DUIVES 等: "Enhancing Crowd Monitoring System Functionality through Data Fusion: Estimating Flow Rate from Wi-Fi Traces and Automated Counting System Data", SENSORS, vol. 20, no. 21, pages 1 - 25 * |
冯玉香: "ARMA模型在景区客流量预测中的应用", 浙江统计, no. 10, pages 8 - 10 * |
曾大军 等: "开源信息在突发事件应急管理中的应用", 科技导报, vol. 26, no. 16, pages 27 - 33 * |
梁捷;梁广明;: "基于ARMA和K-means聚类的用电量数据异常识别", 湖北电力, no. 04, pages 65 - 70 * |
罗甘;: "基于航空大数据的机场客流量时空分布预测", 电子技术与软件工程, no. 18, pages 155 - 156 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113993153A (en) * | 2021-10-27 | 2022-01-28 | 中国联合网络通信集团有限公司 | Crowd gathering prediction method, device, equipment and computer readable storage medium |
CN113993153B (en) * | 2021-10-27 | 2023-07-04 | 中国联合网络通信集团有限公司 | Crowd gathering prediction method, device, equipment and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111768031B (en) | 2023-09-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ali et al. | A data-driven approach for multi-scale GIS-based building energy modeling for analysis, planning and support decision making | |
CN111612206B (en) | Neighborhood people stream prediction method and system based on space-time diagram convolution neural network | |
Lin et al. | Using machine learning to assist crime prevention | |
CN108172301B (en) | Mosquito-borne infectious disease epidemic situation prediction method and system based on gradient lifting tree | |
WO2018188543A1 (en) | Real-time credit score adjustment processing method and device and processing server | |
Imai et al. | Employment, deterrence, and crime in a dynamic model | |
Park et al. | Investigating clustering and violence interruption in gang-related violent crime data using spatial–temporal point processes with covariates | |
WO2018145586A1 (en) | Credit scoring method and server | |
CN109002492B (en) | Performance point prediction method based on LightGBM | |
CN111221991B (en) | Method and device for determining personnel identity attribute and electronic equipment | |
CN111159763A (en) | System and method for analyzing portrait of law-related personnel group | |
CN110598129A (en) | Cross-social network user identity recognition method based on two-stage information entropy | |
CN115577152A (en) | Online book borrowing management system based on data analysis | |
CN114387103A (en) | Transaction risk identification method and device | |
CN111768031A (en) | Method for predicting crowd gathering tendency based on ARMA algorithm | |
CN113609424A (en) | Computing and early warning system and method for network public sentiment popularity | |
Yabe et al. | Predicting irregular individual movement following frequent mid-level disasters using location data from smartphones | |
KR102342192B1 (en) | Apparatus and Method for Predicting Disaster risk based on bigdata | |
US12013908B2 (en) | Evaluation updating device, method, and program | |
Vrochidou et al. | Assessment and localization of structural damage in r/c structures through intelligent seismic signal processing | |
CN110399399B (en) | User analysis method, device, electronic equipment and storage medium | |
CN105787075A (en) | Event prediction method and device based on data mining | |
Verasakulvong et al. | Online emerging topic detection on Twitter using random forest with stock indicator features | |
CN110807251A (en) | Network public opinion polarization method and system integrating individual heterogeneity and dynamic dependency | |
CN110297977A (en) | A kind of personalized recommendation single goal evolvement method for raising platform towards crowd |
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 |