CN108288106B - Big data-based tourist flow prediction method - Google Patents
Big data-based tourist flow prediction method Download PDFInfo
- Publication number
- CN108288106B CN108288106B CN201711033423.3A CN201711033423A CN108288106B CN 108288106 B CN108288106 B CN 108288106B CN 201711033423 A CN201711033423 A CN 201711033423A CN 108288106 B CN108288106 B CN 108288106B
- Authority
- CN
- China
- Prior art keywords
- data
- passenger flow
- flow
- establishing
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007619 statistical method Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 238000012937 correction Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000007418 data mining Methods 0.000 claims abstract description 4
- 230000011664 signaling Effects 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 15
- 230000000737 periodic effect Effects 0.000 claims description 3
- CSRZQMIRAZTJOY-UHFFFAOYSA-N trimethylsilyl iodide Substances C[Si](C)(C)I CSRZQMIRAZTJOY-UHFFFAOYSA-N 0.000 claims description 3
- 210000001503 joint Anatomy 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 17
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000005484 gravity Effects 0.000 description 4
- 238000010835 comparative analysis Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005206 flow analysis Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a big data-based tourist flow prediction method, which comprises the following steps: data acquisition, wherein user position information is acquired; data association, namely associating the user position information with the user position state; data processing, namely eliminating interference data on the passenger flow of a specific area through a specific model and calibrating statistical data; counting and predicting passenger data passenger flow by adopting a Match algorithm; establishing a reverse-thrust model based on a statistical analysis and data mining method, and further calculating the total user flow of the designated area; step six: the method comprises the steps of counting historical data passenger flow data based on data statistical analysis of passenger flow, establishing a passenger flow prediction model, establishing a calculation model with week as a unit according to characteristics of scenic spot visitors, and assisting data correction with year. The invention realizes the real-time dynamic monitoring of the tourist flow of the tourist unit and the analysis of the tourist source by constructing the tourist flow dynamic monitoring system.
Description
Technical Field
The invention relates to a passenger flow prediction method, in particular to a tourist passenger flow prediction method based on big data.
Background
The traditional passenger flow statistics methods include the following several methods: artificial passenger flow statistics, infrared sensing passenger flow statistics, triple-roller gate passenger flow statistics, gravity sensing passenger flow statistics, and the like.
And (3) manual statistics mode: the passenger flow volume is counted manually, and the method has great defects.
The disadvantages are as follows: first, the concentration of the statistical staff is unlikely to be highly concentrated for a long time, and it is very easy to miss the number of customers when tired. Secondly, in the aspect of time, the statistician cannot work continuously for a long time, and for the business hours of a market which are generally more than 12 hours, comprehensive statistics is difficult to achieve. Thirdly, in the aspect of cost, the cost of manpower salary generated by passenger flow statistics in a manual mode is higher than that of equipment statistics without doubt, equipment is disposable, and the cost of manpower is continuous. Therefore, the artificial passenger flow statistics method can only be used as an approximate number statistics in a certain time period, and the comprehensiveness and the effectiveness are poor.
The infrared induction statistical method comprises the following steps: the infrared induction passenger flow statistical equipment can be divided into: the main realization mode of the infrared correlation mode, the infrared reflection mode and other devices is to cut off or block infrared rays to enable the infrared rays to generate resistance change for a human body passing through an infrared sensing area, or to judge the number of the human body by detecting specific infrared rays of about 10um emitted by the human body. The method has moderate cost, can automatically acquire passenger flow data when people freely enter and exit the doorway, and has small equipment and attractive installation.
The disadvantages are as follows: firstly, the infrared light is easily interfered by external factors, so that the statistical data of the infrared light has larger errors; for a wider doorway, the phenomenon of missing data is easy to occur when a plurality of people pass through the doorway simultaneously; secondly, due to the technical reasons, the infrared mode cannot well judge whether the customer enters or exits, and only the fact that the person passes through the infrared mode can be counted, so that the unicity of data acquisition influences the result of passenger flow analysis.
Three-roller gate mode: the three-roller gate mode mainly adopts a mechanical mode, and a customer enters a relevant place and needs to pass through a rolling gate opening, and the rolling gate rolls once, so that the entering and exiting of one person is recorded.
The disadvantages are as follows: the triple-roller gate mode is more accurate for data statistics, but as a triple-roller gate machine needs to be installed at an entrance, the triple-roller gate is lack of attractiveness and insufficient convenience for a market, and cannot be rapidly entered and exited, so that the triple-roller gate is not suitable for being applied to places such as the market.
The gravity sensing mode is as follows: the gravity sensing is mainly that a gravity sensing device is installed on a floor, and the number of passengers is calculated when a human body tramples. But are rarely used by commercial users due to the relatively high installation requirements, high cost, and stability issues.
By combining the traditional passenger flow statistics modes, the requirements of commercial users are difficult to be well met.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a tourist flow prediction method based on big data, and the functions of tourist distribution, passenger source analysis, behavior analysis and early warning monitoring are realized by means of mobile phone big data.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a big data-based tourist flow prediction method is characterized by comprising the following steps:
the method comprises the following steps: data acquisition, wherein user position information is acquired;
step two: data association, namely associating the user position information with the user position state;
step three: data processing, namely eliminating interference data on the passenger flow of a specific area through a specific model and calibrating statistical data;
step four: counting and predicting passenger data passenger flow by adopting a Match algorithm;
step five: establishing a reverse-thrust model based on a statistical analysis and data mining method, and further calculating the total user flow of the designated area;
step six: the method comprises the steps of counting historical data passenger flow data based on data statistical analysis of passenger flow, establishing a passenger flow prediction model, establishing a calculation model with week as a unit according to characteristics of scenic spot visitors, and assisting data correction with year.
Further, the first step is specifically that,
acquiring user position updating information in real time, and butting the user position updating information with a signaling sharing platform in a socket interface mode to acquire position updating data;
collecting operator call signaling data in real time, and butting the operator call signaling data with a signaling sharing platform in a socket interface mode to obtain the operator call signaling data;
establishing a corresponding relation among the IMSI, the TMSI and the MSISDN by using numbers, generation time and logic relations in different signaling interface signaling, and recording the updating time of the corresponding relation;
and according to the corresponding relation and the updating time thereof, carrying out number backfill on the IMSI or MSISDN of the received signaling message, and storing the signaling message after the number backfill.
Further, the second step is specifically that,
establishing a user position state table through the data acquired in real time, updating the latest state of the user position in real time, marking a label on the source of the user, and counting the passenger flow condition of a certain area and the source distribution condition of the user in other places in real time;
through statistical analysis of historical data of the position updating data, the change condition of periodic passenger flow of the city dimension or the specific region dimension is counted according to the mode of day, week and month.
Furthermore, in the third step, the network quality condition of the key base station is counted in real time by collecting and processing the real-time call of the operator call, and meanwhile, the network quality condition is butted with an alarm system, so that when the network quality of the key base station has a problem, the network problem is immediately warned and immediately processed.
Further, the Match algorithm of the fourth step is specifically,
defining r to represent the number of tourists and t to represent the prediction time, calculating the weighted average of the contemporaneous data according to the historical data, namely:
taking multi-dimensional statistical prediction of week data, month data, year data and holiday data as correction. Accordingly, the data of different dimensions have different weights. Data defining week, month, year and holiday are rw rm ry rh. And adjusting the size of the weight parameter by comparing the deviation amount of the historical actual data and the historical predicted data.
Δr=|rr-rpL wherein rrRepresenting true data, rpRepresenting predictive data
Defining the adjusted corresponding weight parameter as abcd, and selecting the number of week, month and year data as the prediction as j kl. The final prediction equation is obtained as:
further, in the sixth step, according to the historical data, the overlapping statistics is carried out with the period of weeks, the holiday data are excluded, if the data on monday are predicted, the data trends of all monday in the history are counted, the overlapping is carried out, the middle value is weighted according to the time sequence to obtain the trend of the change curve, and then the increase and decrease degree is calculated according to the current numerical value and the trend of the change curve to predict the passenger flow change of hours in the future.
Compared with the prior art, the invention has the following advantages and effects:
1. by constructing a tourist flow dynamic monitoring system, the real-time dynamic monitoring of the tourist flow of a tourist unit and the analysis of tourist sources are realized;
2. the early warning monitoring management function of tourists in each scenic spot is realized;
3. providing multi-dimensional analysis of tourists in each scenic spot, and realizing transverse and ring ratio analysis of each scenic spot;
4. the system helps tourism units to carry out targeted marketing and management, and provides accurate decision data support for analysis and decision of tourism management departments.
Drawings
FIG. 1 is a system block diagram of a big data based tourist flow prediction method of the present invention.
Fig. 2 is a number geographic location association diagram of the present invention.
Fig. 3 is a schematic diagram of a cloud computing sharing platform of the present invention.
FIG. 4 is a diagram of an operator data analysis model of the present invention.
FIG. 5 is a graph of sample size versus accuracy for an embodiment of the present invention.
FIG. 6 is a graph of prediction accuracy for an embodiment of the present invention.
Fig. 7 is a final passenger flow prediction effect diagram of an embodiment of the invention.
Detailed Description
The present invention will be described in further detail below by way of examples with reference to the accompanying drawings, which are illustrative of the present invention and are not to be construed as limiting the present invention.
As shown in fig. 1, in the prediction method for tourist flow based on big data, the position update data of the signaling sharing platform is used as a data source, and through a data preprocessing stage, tag information such as the ID and the position of a full amount of users is stored in a unified data warehouse; and performing statistical analysis such as population flow distribution based on multiple dimensions based on a data warehouse. And counting the network quality conditions of corresponding positions according to indexes such as call times, disconnection rate and the like, and visually monitoring the network quality operation conditions of regional dimensions. Comprises the following steps:
the method comprises the following steps: data acquisition, wherein user position information is acquired;
collecting user position updating information in real time, butting with a signaling sharing platform in a socket interface mode to obtain position updating data, and completing data reception within a second level;
collecting operator call signaling data in real time, and butting with a signaling sharing platform in a socket interface mode to obtain the operator call signaling data, wherein the data reception is completed within a second level;
establishing a corresponding relation among the IMSI, the TMSI and the MSISDN by using numbers, generation time and logic relations in different signaling interface signaling, and recording the updating time of the corresponding relation;
and according to the corresponding relation and the updating time thereof, carrying out number backfill on the IMSI or MSISDN of the received signaling message, and storing the signaling message after the number backfill.
Step two: data association, namely associating the user position information with the user position state;
establishing a user position state table through the data acquired in real time, updating the latest state of the user position in real time, marking a label on the source of the user, and counting the passenger flow condition of a certain area and the source distribution condition of the user in other places in real time;
through statistical analysis of historical data of the position updating data, the change condition of periodic passenger flow of the city dimension or the specific region dimension is counted according to the mode of day, week and month. The number geographical location association is shown in figure 2.
Step three: and (3) data processing, namely eliminating interference data for the passenger flow of a specific area through a specific model, and calibrating statistical data, such as: removing standing population, passerby, foreign people standing still, etc.;
by collecting and processing real-time calls called by operators, the network quality condition of key base stations is counted in real time and is simultaneously butted with an alarm system, and when the network quality of the key base stations is in a problem, the network problem can be immediately warned and immediately processed. The cloud computing sharing platform is shown in figure 3.
Step four: counting and predicting passenger data passenger flow by adopting a Match algorithm;
the Match algorithm is embodied in the form of,
defining r to represent the number of tourists and t to represent the prediction time, calculating the weighted average of the contemporaneous data according to the historical data, namely:
taking multi-dimensional statistical prediction of week data, month data, year data and holiday data as correction. Accordingly, the data of different dimensions have different weights. Data defining week, month, year and holiday are rw rm ry rh. And adjusting the size of the weight parameter by comparing the deviation amount of the historical actual data and the historical predicted data.
Δr=|rr-rpL wherein rrRepresenting true data, rpRepresenting predictive data
Defining the adjusted corresponding weight parameter as abcd, and selecting the number of week, month and year data as the prediction as j kl. The final prediction equation is obtained as:
the accuracy of the sample estimation value is closely related to the absolute size of the sample size, the proportional relation of the sample size in the total is not large, and in the actual sampling process, the sampling accuracy of the sampled sample size is 25% of the total (the market occupation of telecommunication), and reaches 99.9%. Therefore, theoretically, the method has the feasibility of reverse thrust. The operator data analysis model is shown in figure 4.
Step five: establishing a reverse-thrust model based on a statistical analysis and data mining method, and further calculating the total user flow of the designated area; the relationship between sample size and accuracy is shown in FIG. 5.
Step six: the method comprises the steps of counting historical data passenger flow data based on data statistical analysis of passenger flow, establishing a passenger flow prediction model, establishing a calculation model with week as a unit according to characteristics of scenic spot visitors, and assisting data correction with year.
According to historical data, carrying out superposition statistics by taking a week as a period, excluding holiday data, counting the data trends of all Mondays in the history if the Monday data is predicted, superposing, weighting according to the time sequence, taking the middle value to obtain a change curve trend, and calculating the increase and decrease degree according to the current value and the change curve trend so as to predict the passenger flow change of hours in the future. The prediction accuracy is shown in fig. 6.
The recent passenger flow change rules have similarity, the more recent time has higher reference value, so the weight is set according to the time sequence, and the weight is decreased from near to far by taking a month as a unit. And the coefficients of the decreasing rate are compared by up-down floating 10 percent, the accuracy rates under three conditions are calculated, and the most accurate coefficient is selected. The average accuracy of data for passenger flow prediction is about 85% according to a passenger flow change model obtained by historical data statistics.
The following description will be made in detail.
Case 1: long island intelligent tour
The chart format displays important tourism statistical data and can call historical data for comparative analysis. Through the passenger flow and the passenger source information acquired by the operator, the real-time passenger flow statistics of the scenic spot, the reception and arrangement statistics of the tourists in the scenic spot, the geometric proportion analysis of the number of the receptions in the scenic spot, the preferred scenic spot arrangement statistics, the age level analysis of the tourists, the residence time analysis of the tourists in the scenic spot and the arrangement statistics of the tourists on the tour routes can be carried out. Various statistical data are stored and inquired in a list mode, and effect demonstration is carried out in modes of a histogram, a broken line graph, a pie chart and the like. The final passenger flow prediction effect graph is shown in fig. 7.
Real-time passenger flow analysis: the module provides the number of tourists in real time for long island and all scenic spots, and the data updating frequency is as follows: and updated once in 15 minutes.
And (3) tourist source analysis: the module provides the province ranking of the visitors to the city and the scenic spot and the proportion of the visitors in each province according to the day, and shows the distribution condition of the visitors in each country in a week in a heat map mode. The method is characterized in that the popularity of scenic spots of a city is used for assisting a travel marketing department to make a corresponding market allocation policy, and data is updated once in 15 minutes.
And (3) guest attribute analysis: the module analyzes the sex and the distribution of the age layers of the tourists in the scenic spots of the long island and all scenic spots according to the statistics of the day, and divides the age layers of the tourists into 0-20 years old, 20-30 years old, 30-40 years old, 40-50 years old, 50-60 years old, 60 years old and above. The data show the proportion of tourists in each age group by a pie chart, support personalized service and accurate marketing of the tourism industry, and count up with new data every day.
And (4) counting the average staying time of the tourists in the scenic spots under the city according to the day by the module, and displaying the ranking of the average staying time of the tourists in the scenic spots in the next week.
Passenger flow comparison and analysis: the module provides comparative analysis of holidays (the highest number of people) and normal passenger flow in cities and scenic spots, and realizes the comparative analysis of the number of tourists on the basis of data accumulation.
Carrying out statistics on a first visit scenic spot: the module respectively counts the ranking and the proportion of tourists of the first scenic spot of the tourist in the city of the other province and the tourist in the city by the dimensions of the scenic spots.
And (3) analyzing a tour route: and analyzing the Top10 ranking of the popular tour routes in each city according to the tourist position track, and displaying the ranking of each tour route and the occupation ratio of the tourists.
Case 2: xuzhou intelligent tour
The method comprises the following steps of scenic spot real-time passenger flow statistics, scenic spot visitor reception scheduling statistics, scenic spot visitor reception number homonymy-proportion ring ratio analysis, preferred scenic spot scheduling statistics, visitor age level analysis, visitor scenic spot residence time analysis and visitor visiting line scheduling statistics. Various statistical data are stored and inquired in a list mode, and effect demonstration is carried out in modes of a histogram, a broken line graph, a pie chart and the like.
The system needs to process more than 1600 general user signaling data (including Jiangsu local clients and roaming clients), and the busy hour signaling flow exceeds 800 Mbps.
Experiments have shown that 85% of human trajectories can be correctly predicted using this algorithm. On the basis, a historical data back-stepping method is provided, so that the accuracy of prediction is further improved, the functions of tourist distribution, passenger source analysis, behavior analysis and early warning monitoring are realized, and a scientific and accurate decision basis is provided for management and marketing of tourism resources.
The above description of the present invention is intended to be illustrative. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (4)
1. A big data-based tourist flow prediction method is characterized by comprising the following steps:
the method comprises the following steps: data acquisition, wherein user position information is acquired;
step two: data association, namely associating the user position information with the user position state;
the second step is specifically that the first step is,
establishing a user position state table through the data acquired in real time, updating the latest state of the user position in real time, marking a label on the source of the user, and counting the passenger flow condition of a certain area and the source distribution condition of the user in other places in real time;
through statistical analysis of historical data of the position updating data, the change conditions of the periodic passenger flow with specific region dimensionality are counted in a day, week and month mode;
step three: data processing, namely eliminating interference data on the passenger flow of a specific area through a specific model and calibrating statistical data;
step four: counting and predicting passenger data passenger flow by adopting a Match algorithm;
the Match algorithm of the fourth step is specifically that,
defining r to represent the number of tourists and t to represent the prediction time, calculating the weighted average of the contemporaneous data according to the historical data, namely:
taking multi-dimensional statistical prediction of week data, month data, year data and holiday data as correction, wherein the corresponding weights of the data with different dimensions are different; data defining week, month, year and holiday are rw、rm、ry、rhAdjusting the size of the weight parameter by comparing the offset of the historical actual data and the historical predicted data;
Δr=|rr-rpl wherein rrRepresenting true data, rpRepresenting prediction data, defining the adjusted corresponding weight parameters as a, b, c and d, and selecting the number of week, month and year data as prediction as j, k and l respectively; the final prediction equation is obtained as:
step five: establishing a reverse-thrust model based on a statistical analysis and data mining method, and further calculating the total user flow of the designated area;
step six: the method comprises the steps of counting historical data passenger flow data based on data statistical analysis of passenger flow, establishing a passenger flow prediction model, establishing a calculation model with week as a unit according to characteristics of scenic spot visitors, and assisting data correction with year.
2. A big data based tourist flow prediction method according to claim 1, characterized in that: the step one is specifically that the step one is that,
acquiring user position updating information in real time, and butting the user position updating information with a signaling sharing platform in a socket interface mode to acquire position updating data;
collecting operator call signaling data in real time, and butting the operator call signaling data with a signaling sharing platform in a socket interface mode to obtain the operator call signaling data;
establishing a corresponding relation among the IMSI, the TMSI and the MSISDN by using numbers, generation time and logic relations in different signaling interface signaling, and recording the updating time of the corresponding relation;
and according to the corresponding relation and the updating time thereof, carrying out number backfill on the IMSI or MSISDN of the received signaling message, and storing the signaling message after the number backfill.
3. A big data based tourist flow prediction method according to claim 1, characterized in that: in the third step, the network quality condition of the key base station is counted in real time by collecting and processing the real-time call called by the operator, and meanwhile, the network quality condition is in butt joint with the alarm system, and when the network quality of the key base station has a problem, the network problem is immediately warned and immediately processed.
4. A big data based tourist flow prediction method according to claim 1, characterized in that: and sixthly, performing superposition statistics by taking a week as a period according to historical data, excluding holiday data, predicting Monday data, counting data trends of all Mondays in the history, superposing, weighting according to time sequence, taking a middle value to obtain a change curve trend, and calculating an increase and decrease degree according to the current value and the change curve trend so as to predict passenger flow change of hours in the future.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711033423.3A CN108288106B (en) | 2017-10-30 | 2017-10-30 | Big data-based tourist flow prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711033423.3A CN108288106B (en) | 2017-10-30 | 2017-10-30 | Big data-based tourist flow prediction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108288106A CN108288106A (en) | 2018-07-17 |
CN108288106B true CN108288106B (en) | 2022-03-15 |
Family
ID=62831512
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711033423.3A Active CN108288106B (en) | 2017-10-30 | 2017-10-30 | Big data-based tourist flow prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108288106B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126736B (en) * | 2018-11-01 | 2023-09-01 | 百度在线网络技术(北京)有限公司 | Enterprise passenger flow volume determining method and device, server and storage medium |
CN109345042B (en) * | 2018-11-19 | 2021-10-01 | 中国联合网络通信集团有限公司 | Method and device for predicting passenger flow heat intensity change |
CN110674210A (en) * | 2019-09-23 | 2020-01-10 | 钟栎娜 | Method for comprehensively evaluating tourist destinations based on big data |
CN113132891B (en) * | 2019-12-30 | 2022-06-28 | 中国移动通信集团浙江有限公司 | Passenger flow statistical method and system based on mobile signaling |
CN111258252B (en) * | 2020-01-21 | 2020-12-01 | 三江学院 | Tourist attraction heat real-time monitoring system and method |
CN111507546A (en) * | 2020-07-02 | 2020-08-07 | 江西鹭鹭行科技有限公司 | Subway transfer route generation method and device, storage medium and computer equipment |
CN111784414B (en) * | 2020-07-21 | 2022-04-29 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and medium |
CN112365638A (en) * | 2020-11-16 | 2021-02-12 | 成都中科大旗软件股份有限公司 | Scenic spot passenger flow early warning system |
CN112465566B (en) * | 2020-12-14 | 2023-08-04 | 树蛙信息科技(南京)有限公司 | Market passenger flow prediction method based on historical data auxiliary scene analysis |
CN112738729B (en) * | 2020-12-31 | 2023-06-16 | 桂林旅游学院 | Method and system for discriminating visiting and returning tourists through mobile phone signaling data |
CN113177073A (en) * | 2021-01-14 | 2021-07-27 | 北京亚洲卫星通信技术有限公司 | Intelligent venue operation management data analysis method |
CN113517038A (en) * | 2021-03-02 | 2021-10-19 | 阿里巴巴新加坡控股有限公司 | Method, device and equipment for predicting affinity between drug and target |
CN113536891B (en) * | 2021-05-10 | 2023-01-03 | 新疆爱华盈通信息技术有限公司 | Pedestrian traffic statistical method, storage medium and electronic equipment |
CN114219114B (en) * | 2021-12-24 | 2022-08-26 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
CN116227760B (en) * | 2023-05-11 | 2023-08-18 | 广西大也智能数据有限公司 | Method, device, storage medium and equipment for predicting influence of travel activities |
CN117056730A (en) * | 2023-09-08 | 2023-11-14 | 广西大也智能数据有限公司 | Method, device, equipment and storage medium for data prediction |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105101087A (en) * | 2015-07-29 | 2015-11-25 | 郭今戈 | Method and system for pedestrian flow estimation and trend prediction based on location area and real-time communication |
CN106355289A (en) * | 2016-09-20 | 2017-01-25 | 杭州东信北邮信息技术有限公司 | Method for predicting passenger flow of scenic regions on basis of location service |
CN106970976A (en) * | 2017-03-27 | 2017-07-21 | 重庆邮电大学 | A kind of real-time dynamic passenger flow volume statistical method in scenic spot based on visitor's mobile signaling protocol data |
CN107180270A (en) * | 2016-03-12 | 2017-09-19 | 上海宏理信息科技有限公司 | Passenger flow forecasting and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090319172A1 (en) * | 2007-04-26 | 2009-12-24 | Timebi, Lda | Travel time prediction system |
-
2017
- 2017-10-30 CN CN201711033423.3A patent/CN108288106B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105101087A (en) * | 2015-07-29 | 2015-11-25 | 郭今戈 | Method and system for pedestrian flow estimation and trend prediction based on location area and real-time communication |
CN107180270A (en) * | 2016-03-12 | 2017-09-19 | 上海宏理信息科技有限公司 | Passenger flow forecasting and system |
CN106355289A (en) * | 2016-09-20 | 2017-01-25 | 杭州东信北邮信息技术有限公司 | Method for predicting passenger flow of scenic regions on basis of location service |
CN106970976A (en) * | 2017-03-27 | 2017-07-21 | 重庆邮电大学 | A kind of real-time dynamic passenger flow volume statistical method in scenic spot based on visitor's mobile signaling protocol data |
Also Published As
Publication number | Publication date |
---|---|
CN108288106A (en) | 2018-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108288106B (en) | Big data-based tourist flow prediction method | |
CN110545558B (en) | High-speed service area crowd density estimation system based on Wi-Fi data | |
Kaltenbrunner et al. | Urban cycles and mobility patterns: Exploring and predicting trends in a bicycle-based public transport system | |
CN110598154B (en) | Tourism comprehensive statistics big data system based on fusion multi-channel data | |
CN104508507B (en) | The self-adaption cluster of position | |
Qin et al. | Applying big data analytics to monitor tourist flow for the scenic area operation management | |
US20210140777A1 (en) | Routing With Environmental Awareness | |
CN105246033B (en) | A kind of crowd state monitoring method and monitoring device based on terminal positioning | |
CN107704586A (en) | A kind of methods, devices and systems of user's portrait based on User Activity address | |
CN109902930B (en) | Auxiliary system for planning matched facilities based on real population indexes | |
CN108027940A (en) | Analysis system and analysis method | |
AU2013205716A1 (en) | Location-based cognitive and predictive communication system | |
CN106576383A (en) | Deployment criteria for unmanned aerial vehicles to improve cellular phone communications | |
CN107533734A (en) | It is used to help the automatic method and apparatus for arranging user's stroke | |
EP3567531A1 (en) | Forecast demand for mobility units | |
WO2022217685A1 (en) | Method and system for intelligent path planning of tourist attractions | |
JP4411417B2 (en) | Integrated information service system | |
Randriamanamihaga et al. | Clustering the Vélib׳ dynamic Origin/Destination flows using a family of Poisson mixture models | |
Demissie et al. | Modeling location choice of taxi drivers for passenger pickup using GPS data | |
CN104657457B (en) | A kind of user evaluates data processing method, video recommendation method and the device of video | |
CN111951037A (en) | Big data-based passenger flow prediction and travel marketing method | |
CN108733692A (en) | A kind of social information recommendation method and apparatus | |
Tan et al. | Tidal phenomenon of the dockless bike-sharing system and its causes: the case of Beijing | |
CN115866547A (en) | Fixed area tourist counting method, system and storage medium based on signaling data | |
CN107205220A (en) | A kind of method and device of determination region stream of people's quantity |
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 | ||
CB02 | Change of applicant information |
Address after: 210029 No. 268, Hanzhoung Road, Nanjing, Jiangsu Applicant after: CLP Hongxin Information Technology Co., Ltd Address before: 210029 No. 268, Hanzhoung Road, Nanjing, Jiangsu Applicant before: Jiangsu Hongxin System Integration Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |