Disclosure of Invention
The invention aims to provide a scenic spot people number prediction system and a scenic spot people number prediction method based on big data, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a scenic spot people number prediction system based on big data comprises a tourist accommodation area analysis module, a playing time period analysis module, a hotel room reservation type statistic module, a hotel accommodation people number statistic module, a scenic spot people number prediction module, a current day actual people flow statistic module and a people flow prediction correction module,
the system comprises a current day actual people flow counting module, a current day actual people flow counting module and a time node recording module, wherein the current day actual people flow counting module is used for counting the number of actual playing people and the time node of the tourists entering a scenic area, the current day actual people flow counting module comprises a people flow counting submodule and a time node recording submodule, the people flow counting submodule is used for recording the number of the tourists entering the scenic area on the current day, and the time node recording submodule is used for recording the time node of the tourists entering the scenic area;
the playing time period analysis module analyzes the optimal playing time period of the scenic spot according to historical visitor data, the playing time period analysis module comprises a time period people flow rate density analysis submodule and an optimal playing time period analysis submodule, the time period people flow rate density analysis submodule is used for acquiring historical visitor data and analyzing the people flow rate density of any time period of the scenic spot according to the historical visitor data, and the optimal playing time period analysis submodule is used for selecting the optimal playing time period according to the people flow rate density;
the tourist stay area analysis module comprises a tourist stay area selection submodule and a tourist stay hotel selection submodule, the tourist stay area selection submodule is used for analyzing the stay area of the tourist according to the optimal playing time period obtained by analysis of the playing time period analysis module, and the tourist stay selection submodule is used for selecting the tourist stay according to the tourist stay area obtained by analysis of the tourist stay area selection submodule and establishing a hotel information set;
the hotel reservation room type counting module is used for counting various room type reservation total numbers of the hotels selected by the visitor check-in hotel selecting sub-module, the hotel check-in number counting module is used for counting the number of persons in the hotels according to the various room type reservation total numbers of the hotels to be reserved, the scenic spot number prediction module is used for predicting the number of persons playing in scenic spots, and the people flow prediction correction module corrects the prediction coefficient of the scenic spot number prediction module according to the number of persons playing in the scenic spots and the actual number of persons playing in the current day of the scenic spots, which are obtained through prediction.
Further, the time node recording submodule presets a plurality of time periods
The people flow counting submodule records the number of visitors entering the scenic spot at each time period on the day and the total number of visitors entering the scenic spot on the day according to the time periods
The people flow recording submodule records the number of visitors entering the scenic spot once every other time interval
Wherein, in the step (A),
is a period of time
The number of visitors entering the scenic spot, and the people flow counting submodule acquires the starting time of each time intervalThe system comprises nodes and a deadline node, the number of visitors entering a scenic spot in each time period is recorded according to the start time node and the deadline node, and the number of visitors entering the scenic spot in each time period is counted by setting the time periods, so that the optimal playing time period of the scenic spot in some time period can be obtained, and the optimal playing time period is the time period in which the number of visitors playing in the scenic spot is large.
Furthermore, the actual people flow statistical module on the same day is connected with the playing time period analysis module, and the historical visitor data acquired by the time period people flow density analysis submodule comprises time period information
And the number of visitors entering the scenic spot at each time interval
The time interval people flow density analysis submodule calculates the people flow density of the corresponding time interval, and the people flow density
Through the time interval and the number of people entering the scenic spot corresponding to the time interval, the people flow density in the time interval can be calculated, the people flow density also shows the number of people playing in the scenic spot in the time interval, in fact, the optimal playing time of each scenic spot is different due to different types and weather, but the optimal playing time interval of different scenic spots can be obtained by calculating the people flow density of each scenic spot in each time interval in a targeted manner, wherein,
is composed of
The people flow density in the time interval, and the optimal play time interval analysis submodule acquires the people flow density
When said optimum time of playSegment analysis submodule according to people flow density
Computing
People flow density difference ratio in time interval
Wherein, in the step (A),
is a human flow density difference threshold value when
People flow density difference ratio in time interval
When the value is more than or equal to the first preset value, the
The time period is stored into the optimal play time period set, which is described in
The people flow density value in the time interval is larger, namely, the number of people who play in the scenic spot in the time interval is larger, therefore, the people can be regarded as the scenic spot
The time interval is the optimal playing time interval, and further the time interval is obtained
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Also greater than or equal to the first preset value, will
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Less than the first predetermined value, because the threshold represents a critical value, but if only a comparison of critical values is passed, the comparison result may have an error, and therefore, the people flow density of two periods of time must be compared, because
The people flow density of the time interval may be a value which just meets the judgment condition
The people flow density of the time interval may be a value just not in accordance with the judgment condition, i.e. the time interval is a time interval
Time interval specific pedestrian volume density
People flow density of time intervalThe degree is a little smaller, therefore, the people flow density of the two time periods needs to be compared again to ensure the accuracy of the data, and simultaneously,
then further obtain
Time period and
the density of the flow of people in the time interval is calculated
A value of (A) when
When the value of (A) is less than or equal to a second preset value, the value of (B) will be
The time period is stored into the set of optimal play time periods,
the optimal play period analysis submodule acquires period information stored in an optimal play period set, the optimal play period analysis submodule determines a start time node and an end time node of each period according to the period information, and further determines continuous periods and discontinuous periods in the optimal play period set, the continuous periods include a plurality of periods, namely the end time node of a previous period corresponds to the start time node of a next period in the plurality of periods, the discontinuous periods are individual periods, namely the start time node of the individual period corresponds to the end time node of the previous period and the end time node of the individual period does not correspond to the start time node of the next period, the optimal play period analysis submodule marks the continuous periods and the discontinuous periods in the optimal play period set as optimal play periods, previously, small time periods are set, and when time nodes of consecutive time periods, i.e. at least two small time periods, exist in the optimal play time period set are connected together, the time nodes can be combined into one time period for analysis.
Further, the tourist entry area analysis module is connected with the playing time period analysis module, the tourist entry area selection submodule acquires an optimal playing time period through the playing time period analysis module, the tourist entry area selection submodule stores a departure time node in advance, the tourist entry area selection submodule further acquires an end time node of the optimal playing time period and calculates a time difference between the end time node and the departure time node, and the tourist entry area selection submodule estimates the maximum mileage which can be traveled by the vehicle in the time difference according to the time difference,
the method comprises the steps that a scenic spot central point and an area outline of a scenic spot are further obtained, the minimum distance between any point on the area outline and the scenic spot central point is used as a compensation radius, a visitor entry area submodule takes the sum of the maximum mileage and the compensation radius as the area radius of a visitor entry area, and establishes a visitor entry area according to the area radius and the circle center, when a common visitor goes to the scenic spot for playing, the hotel cannot be fixed at a place far away from the scenic spot, most visitors can choose to go to the scenic spot for playing in the optimal playing time period, therefore, according to analysis of the optimal playing time period, the deadline of the optimal playing time period can be obtained, and then the entering range of the hotel can be predicted according to the departure time and the maximum driving speed allowed by a vehicle in a designated area.
Further, the visitor check-in hotel selection submodule firstly acquires the visitor check-in area, then selects first hotel information located in the visitor check-in area according to address information of the hotel,
the visitor check-in hotel selection submodule further acquires the edge position of the visitor check-in area, second hotel information which is a certain distance away from the edge position is selected, the visitor check-in hotel selection submodule stores the first hotel information and the second hotel information into a hotel information set, the departure time is based on the travel habits of most of people, but some people are used to the same time and are earlier than the travel time of most of people, and therefore hotels near the check-in area can be selected.
Further, hotel reservation room type statistics module connects visitor check-in hotel selects the submodule, hotel reservation room type statistics module further acquires the hotel information of storage among the hotel information set, hotel reservation room type statistics module is provided with room type A, room type B, room type C in advance, the type of room type is divided according to the maximum number of check-in people of all kinds of room types, hotel reservation room type statistics module basis hotel information statistics each hotel is in the predetermined quantity of all kinds of room types of certain period of time, certain period of time is visitor check-in time, can learn the total number of check-in people of all hotels according to the predetermined quantity and the maximum number of check-in people of room type.
Further, hotel reservation room type statistics module is connected hotel number of registering statistics module, hotel number of registering statistics module further obtains the predetermined total number of all kinds of room types of hotel in certain period of time, wherein, the predetermined total number of room type A, room type B, room type C is marked as
、
、
The hotel attendance number counting module calculates the attendance total number of the hotel in the certain time period according to the preset total number of various house types and the maximum attendance number corresponding to each house type
Wherein, in the step (A),
the maximum number of people who live in the house type A,
is a house type BThe maximum number of people who live in the house,
the maximum number of dwells for house type C.
Furthermore, the hotel check-in number counting module is connected with the scenic spot number predicting module, and the scenic spot number predicting module further acquires the total check-in number of the hotel in a certain time period
The scenic spot people number prediction module is used for predicting the total number of people living in the scenic spot according to the total number of people living in the scenic spot
Predicting the number of tourists in the scenic spot
Wherein, in the step (A),
because persons who can not check in the hotel can go to the hotel for playing, and some visitors can not check in the hotel and directly drive to the scenic spot, of course, most of the persons who directly drive to the scenic spot are local persons, the prediction coefficient is set according to the number of checked-in persons of the hotel obtained by prediction, and the difference between the data can be reflected according to the comparison between the number of the visitors in the scenic spot obtained by prediction and the number of the persons who actually go to the scenic spot, so that the prediction coefficient can be further corrected to make up the prediction difference of the number of the persons who do not necessarily check in the hotel and do not necessarily check in the hotel mentioned before,
the scenic spot number prediction module is also connected with an actual people flow statistical module on the same day, and further obtains the total number of visitors entering the scenic spot on the same day
,
The scenic spot people number prediction module is also connected with a people flow prediction correction module, and people areThe flow prediction correction module further obtains the number of the tourists in the scenic spot obtained by prediction
And the total number of visitors entering the scenic spot on the same day
The people flow prediction correction module is based on
And
correcting the prediction coefficient, the prediction coefficient after the 1 st correction
Wherein, in the step (A),
the initial prediction coefficient is the prediction coefficient after the i-th correction
According to the prediction coefficient after the 1 st correction, the scenic spot number prediction module predicts the number of scenic spot visitors in the next day
Wherein, in the step (A),
the prediction coefficient after the 2 nd correction is known from the above contents for the total number of the hotel's check-in on the next day
Wherein, in the step (A),
the total number of visitors entering the scenic spot for the next day and so on can be calculated after the ith correctionThe prediction coefficient is obtained by obtaining the relation between the number of the hotel guests and the flow of the guests in the scenic spot according to the historical data of the current period, and an initial prediction coefficient can be preset, namely the initial prediction coefficient is
However, the heat degree of a scenic spot is changed along with the change of time, on the basis of the lack of later-period data, the initial prediction coefficient can be corrected once according to daily actual data, the correction interval is short every other day, and the flow of people does not change greatly, so that the accuracy of the data can be ensured, even in the case of holidays or weather influence, the duration of the influence of common holidays or severe weather on the scenic spots can be more than one day, the prediction coefficient is continuously corrected according to the proportion of the number of people actually going to the scenic spot and the flow of people obtained through prediction, and the influence of external reasons such as weather and holidays can be reduced.
Further, a scenic spot people number prediction method based on big data comprises the following steps:
s1: recording time nodes when the tourists enter the scenic area and the number of the tourists entering the scenic area in each time period, and counting the total number of the tourists on the day according to the number of the tourists in each time period;
s2: calculating the people flow density of each time interval according to the time interval information and the number of the visitors entering the scenic spot of each time interval, and analyzing the optimal playing time interval according to the people flow density;
s3: selecting a tourist check-in area and a tourist check-in hotel according to the optimal playing time period, the scenic spot central point and the scenic spot area outline;
s4: counting the preset total number of all types of rooms of each hotel in a certain time period according to the selected hotel information of the visitors entering the hotel, and further counting the total number of people entering the hotel according to the preset total number of all types of rooms and the maximum number of people entering the hotel corresponding to the types of the rooms;
s5: and predicting the number of tourists in the scenic region by the total number of the tourists living in the scenic region, correcting the prediction coefficient according to the predicted number of the tourists in the scenic region and the total number of the tourists on the day, and calculating the number of the tourists in the scenic region predicted on the next day according to the corrected prediction coefficient.
Further, the scenic spot people number prediction method further comprises the following steps:
s1-1, the daily actual pedestrian volume counting module comprises a pedestrian volume counting submodule and a time node recording submodule, wherein the time node recording submodule records time nodes when tourists enter a scene area, and the time node recording submodule is preset with a plurality of time periods
The people flow counting submodule records the number of visitors entering the scenic spot at each time period on the day and the total number of visitors entering the scenic spot on the day according to the time periods
And the number of visitors entering the scenic spot is recorded every other time interval
Wherein, in the step (A),
is a period of time
The number of visitors entering the scenic spot;
s2-1, the playing time period analysis module comprises a time period people flow rate density analysis submodule and an optimal playing time period analysis submodule, the time period people flow rate density analysis submodule obtains historical visitor data, and the historical visitor data comprises time period information
And the number of visitors entering the scenic spot at each time interval
The time interval people flow density analysis submodule calculates the people flow density of the corresponding time interval,the density of the flow of people
Wherein, in the step (A),
is composed of
The people flow density in the time interval, and the optimal play time interval analysis submodule acquires the people flow density
The optimal play time period analysis submodule analyzes the optimal play time period according to the density of the flow of people
Computing
People flow density difference ratio in time interval
Wherein, in the step (A),
is a human flow density difference threshold value when
People flow density difference ratio in time interval
When the value is more than or equal to the first preset value, the
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Also greater than or equal to the first preset value, will
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Less than a first preset value, and, at the same time,
then further obtain
Time period and
the density of the flow of people in the time interval is calculated
A value of (A) when
When the value of (A) is less than or equal to a second preset value, the value of (B) will be
The time period is stored into an optimal play time period set;
s3-1: the tourist accommodation area analysis module comprises a tourist accommodation area selection submodule and a tourist accommodation hotel selection submodule, the tourist accommodation area selection submodule acquires an optimal play time period through the play time period analysis module, the tourist accommodation area selection submodule stores a departure time node in advance, the tourist accommodation area selection submodule further acquires a stop time node of the optimal play time period and calculates a time difference between the stop time node and the departure time node, the tourist accommodation area selection submodule estimates a maximum mileage which can be traveled by a vehicle in the time difference according to the time difference and further acquires a central point of a scenic area and an area outline of the scenic area, a minimum distance between any point on the area outline and the central point of the scenic area is taken as a compensation radius, and the tourist accommodation area submodule takes the sum of the maximum mileage and the compensation radius as an area radius of the tourist accommodation area, establishing a tourist check-in area according to the area radius and the circle center by taking a scenic spot center point as the circle center, wherein a tourist check-in hotel selection submodule firstly acquires the tourist check-in area, and then selects first hotel information located in the tourist check-in area according to address information of a hotel, the tourist check-in hotel selection submodule further acquires the edge position of the tourist check-in area, selects second hotel information at a certain distance from the edge position, and the tourist check-in hotel selection submodule stores the first hotel information and the second hotel information into a hotel information set;
s4-1: hotel reservation room type statistical module is connected visitor selection submodule of living in the hotel, hotel reservation room type statistical module further acquires the hotel information of storage in the hotel information set, hotel reservation room type statistical module is provided with room type A, room type B, room type C in advance, the type of room type is according to the room type of all kindsThe maximum number of people who check in is divided, hotel reservation room type statistical module is according to each hotel in the predetermined quantity of all kinds of room types of certain period of time of hotel information statistics, certain period of time is visitor's time of checking in, hotel reservation room type statistical module connects hotel number of people statistical module of checking in, hotel number of people statistical module of checking in further obtains the predetermined total number of hotel in all kinds of room types of certain period of time, and wherein, the predetermined total number of room type A, room type B, room type C marks as the predetermined total number of room type A, room type B, room type C
、
、
The hotel attendance number counting module calculates the attendance total number of the hotel in the certain time period according to the preset total number of various house types and the maximum attendance number corresponding to each house type
Wherein, in the step (A),
the maximum number of people who live in the house type A,
the maximum number of people who live in house type B,
the maximum number of dwells for house type C;
s5-1: the hotel check-in number counting module is connected with the scenic spot number prediction module, and the scenic spot number prediction module further acquires the total check-in number of the hotel in a certain time period
The scenic spot people number prediction module is used for predicting the total number of people living in the scenic spot according to the total number of people living in the scenic spot
Predicting the number of tourists in the scenic spot
Wherein, in the step (A),
in order to predict the coefficients of the coefficients,
the scenic spot number prediction module is also connected with an actual people flow statistical module on the same day, and further obtains the total number of visitors entering the scenic spot on the same day
,
The scenic spot number prediction module is also connected with a people flow prediction correction module, and the people flow prediction correction module further obtains the number of scenic spot tourists obtained through prediction
And the total number of visitors entering the scenic spot on the same day
The people flow prediction correction module is based on
And
correcting the prediction coefficient, the prediction coefficient after the 1 st correction
Wherein, in the step (A),
the initial prediction coefficient is the prediction coefficient after the i-th correction
According to the prediction coefficient after the 1 st correction, the scenic spot number prediction module predicts the number of scenic spot visitors in the next day
Wherein, in the step (A),
the total number of the hotel in the next day.
Compared with the prior art, the invention has the following beneficial effects: the invention records time nodes when tourists enter a scenic area and the number of the tourists entering the scenic area in each time period, calculates the actual total number of the tourists and the people flow density in each time period on the same day, analyzes the optimal playing time period according to the people flow density, selects a tourists entering area and a tourists entering the hotel according to the optimal playing time period, counts the preset total number of all types of rooms in a certain time period of each hotel according to the selected information of the hotel entering the hotel, further counts the total number of the tourists entering the scenic area according to the preset total number of all types of the rooms, predicts the number of the tourists in the scenic area through the total number of the tourists entering the scenic area, corrects the prediction coefficient according to the actual total number of the tourists in the current day, and predicts the number of the tourists in the scenic area on the next day.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution:
a scenic spot people number prediction system based on big data comprises a tourist accommodation area analysis module, a playing time period analysis module, a hotel room reservation type statistic module, a hotel accommodation people number statistic module, a scenic spot people number prediction module, a current day actual people flow statistic module and a people flow prediction correction module,
the daily actual people flow counting module is used for counting the number of actual playing people and time nodes of visitors entering the scenic area, the daily actual people flow counting module comprises a people flow counting submodule and a time node recording submodule, the people flow counting submodule is used for recording the number of visitors entering the scenic area on the same day, and the time node recording submodule is used for recording the time nodes of the visitors entering the scenic area;
the system comprises a playing time period analysis module, a time period people flow density analysis module and an optimal playing time period analysis module, wherein the playing time period analysis module analyzes the optimal playing time period of a scenic spot according to historical visitor data, the time period people flow density analysis module is used for acquiring historical visitor data and analyzing the people flow density of any time period of the scenic spot according to the historical visitor data, and the optimal playing time period analysis module is used for selecting the optimal playing time period according to the people flow density;
the tourist admission area analysis module comprises a tourist admission area selection submodule and a tourist admission hotel selection submodule, the tourist admission area selection submodule is used for analyzing the admission area of the tourist according to the optimal playing time period obtained by analysis of the playing time period analysis module, and the tourist admission hotel selection submodule is used for selecting the tourist to enter the hotel according to the tourist admission area obtained by analysis of the tourist admission area selection submodule and establishing a hotel information set;
the hotel reservation room type counting module is used for counting the reservation total number of all types of rooms of the hotel selected by the visitor check-in hotel selection sub-module, the hotel check-in number counting module is used for counting the number of the guests in the hotel according to the reservation total number of all types of rooms of the hotel, the scenic spot number prediction module is used for predicting the number of the visitors in the scenic spot, and the people flow prediction correction module corrects the prediction coefficient of the scenic spot number prediction module according to the number of the visitors in the scenic spot and the actual number of the visitors in the current day of the scenic spot, which are obtained through prediction.
The time node recording submodule presets a plurality of time periods
The people flow counting submodule records the number of the visitors entering the scenic spot in each time period on the day and the total number of the visitors entering the scenic spot on the day according to the time periods
The flow recording submodule records the number of visitors entering the scenic spot once every other time interval
Wherein, in the step (A),
is a period of time
The number of visitors entering the scenic spot is obtained by the people flow counting submodule, the starting time node and the ending time node of each time interval are obtained, and the number of visitors entering the scenic spot in each time interval is recorded according to the starting time node and the ending time node.
The actual flow statistics module on the same day is connected with the playing time period analysis module, the time period flow density analysis submodule acquires historical visitor data, and the historical visitor data comprises time period information
And the number of visitors entering the scenic spot at each time interval
The time interval people flow density analysis submodule calculates the people flow density of the corresponding time interval, and the people flow density
Wherein, in the step (A),
is composed of
People flow density in time interval, and the best play time interval analysis submodule acquires the people flow density
The optimal playing time period analysis submodule analyzes the optimal playing time period according to the people flow density
Computing
People flow density difference ratio in time interval
Wherein, in the step (A),
is a human flow density difference threshold value when
People flow density difference ratio in time interval
When the value is more than or equal to the first preset value, the
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Also greater than or equal to the first preset value, will
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Less than a first preset value, and, at the same time,
then further obtain
Time period and
the density of the flow of people in the time interval is calculated
A value of (A) when
When the value of (A) is less than or equal to a second preset value, the value of (B) will be
The time period is stored into the set of optimal play time periods,
the optimal play time period analysis submodule acquires time period information stored in the optimal play time period set, the optimal play time period analysis submodule determines a start time node and an end time node of each time period according to the time period information, and further determines continuous time periods and discontinuous time periods in the optimal play time period set, the continuous time periods comprise a plurality of time periods, namely the end time node of a previous time period in the time periods corresponds to the start time node of a next time period, the discontinuous time periods are independent time periods, namely the start time node of the independent time period corresponds to the end time node of the previous time period, and the end time node of the independent time period does not correspond to the start time node of the next time period, and the optimal play time period analysis submodule marks the continuous time periods and the discontinuous time periods in the optimal play time period set as optimal play time periods.
The tourist accommodation area analysis module is connected with the playing time period analysis module, the tourist accommodation area selection submodule acquires the optimal playing time period through the playing time period analysis module, the tourist accommodation area selection submodule stores a starting time node in advance, the tourist accommodation area selection submodule further acquires a stop time node of the optimal playing time period and calculates the time difference between the stop time node and the starting time node, the tourist accommodation area selection submodule estimates the maximum mileage which can be driven by the vehicle in the time difference according to the time difference,
and further acquiring a scenic spot central point and an area outline of the scenic spot, taking the minimum distance between any point on the area outline and the scenic spot central point as a compensation radius, taking the sum of the maximum mileage and the compensation radius as the area radius of the tourist entrance area, taking the scenic spot central point as a circle center, and establishing the tourist entrance area according to the area radius and the circle center.
The visitor check-in hotel selection submodule firstly acquires a visitor check-in area, selects first hotel information positioned in the visitor check-in area according to the address information of the hotel,
the visitor stay hotel selection submodule further acquires an edge position of the visitor stay area, selects second hotel information at a certain distance from the edge position, and stores the first hotel information and the second hotel information into a hotel information set.
Hotel reservation room type statistical module connects visitor and checks in the hotel and chooses the submodule, hotel reservation room type statistical module further acquires the hotel information of storage in the middle of the hotel information set, hotel reservation room type statistical module is provided with room type A in advance, room type B, room type C, the maximum number of checking in of the type of room type according to all kinds of room types is divided, hotel reservation room type statistical module counts the reservation quantity of each hotel in all kinds of room types of certain period of time according to hotel information, certain period of time is visitor check-in time.
The hotel reservation room type counting module is connected with the hotel check-in number counting module, the hotel check-in number counting module further obtains the reservation total number of all types of rooms of the hotel in a certain time period, wherein the reservation total number of the room type A, the room type B and the room type C is recorded as
、
、
The hotel total number of check-in people counting module calculates the total number of check-in people of the hotel in a certain time period according to the preset total number of various house types and the maximum number of check-in people corresponding to each house type
Wherein, in the step (A),
the maximum number of people who live in the house type A,
the maximum number of people who live in house type B,
the maximum number of dwells for house type C.
The hotel check-in number counting module is connected with the scenic spot number prediction module, and the scenic spot number prediction module further acquires the total check-in number of the hotel in a certain time period
The scenic spot number predicting module predicts the total number of people
Predicting the number of tourists in the scenic spot
Wherein, in the step (A),
in order to predict the coefficients of the coefficients,
the scenic spot number prediction module is also connected with the current actual people flow statistics module, and further acquires the total number of visitors entering the scenic spot on the current day
,
The scenic spot number prediction module is also connected with a people flow prediction correction module, and the people flow prediction correction module further obtains the number of scenic spot tourists obtained through prediction
And the total number of visitors entering the scenic spot on the same day
The people flow prediction correction module is based on
And
correcting the prediction coefficient, the prediction coefficient after the 1 st correction
Wherein, in the step (A),
the initial prediction coefficient is the prediction coefficient after the i-th correction
According to the prediction coefficient after the 1 st correction, the scenic spot number prediction module predicts the number of scenic spot visitors in the next day
Wherein, in the step (A),
the total number of the hotel in the next day.
A scenic spot number prediction method based on big data comprises the following steps:
s1: recording time nodes when the tourists enter the scenic area and the number of the tourists entering the scenic area in each time period, and counting the total number of the tourists on the day according to the number of the tourists in each time period;
s2: calculating the people flow density of each time interval according to the time interval information and the number of the visitors entering the scenic spot of each time interval, and analyzing the optimal playing time interval according to the people flow density;
s3: selecting a tourist check-in area and a tourist check-in hotel according to the optimal playing time period, the scenic spot central point and the scenic spot area outline;
s4: counting the preset total number of all types of rooms of each hotel in a certain time period according to the selected hotel information of the visitors entering the hotel, and further counting the total number of people entering the hotel according to the preset total number of all types of rooms and the maximum number of people entering the hotel corresponding to the types of the rooms;
s5: and predicting the number of tourists in the scenic region by the total number of the tourists living in the scenic region, correcting the prediction coefficient according to the predicted number of the tourists in the scenic region and the total number of the tourists on the day, and calculating the number of the tourists in the scenic region predicted on the next day according to the corrected prediction coefficient.
The scenic spot people number prediction method further comprises the following steps:
s1-1, the daily actual pedestrian volume counting module comprises a pedestrian volume counting submodule and a time node recording submodule, wherein the time node recording submodule records time nodes when tourists enter a scenic area, and the time node recording submodule is preset with a plurality of time periods
The people flow counting submodule records the number of the visitors entering the scenic spot in each time period on the day and the total number of the visitors entering the scenic spot on the day according to the time periods
And the number of visitors entering the scenic spot is recorded every other time interval
Wherein, in the step (A),
is a period of time
The number of visitors entering the scenic spot;
s2-1, the playing time period analysis module comprises a time period people flow rate density analysis submodule and an optimal playing time period analysis submodule, the time period people flow rate density analysis submodule acquires historical visitor data, and the historical visitor data comprises time period information
And the number of visitors entering the scenic spot at each time interval
The time interval people flow density analysis submodule calculates the people flow density of the corresponding time interval, and the people flow density
Wherein, in the step (A),
is composed of
People flow density in time interval, and the best play time interval analysis submodule acquires the people flow density
The optimal playing time period analysis submodule analyzes the optimal playing time period according to the people flow density
Computing
People flow density difference ratio in time interval
Wherein, in the step (A),
is a human flow density difference threshold value when
People flow density difference ratio in time interval
When the value is more than or equal to the first preset value, the
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Also greater than or equal to the first preset value, will
Time interval storage enters an optimal play time interval set and further obtains
Proportion of difference in pedestrian density over time
,
If it is
Proportion of difference in pedestrian density over time
Less than a first preset value, and, at the same time,
then further obtain
Time period and
the density of the flow of people in the time interval is calculated
A value of (A) when
When the value of (A) is less than or equal to a second preset value, the value of (B) will be
The time period is stored into an optimal play time period set;
s3-1: the tourist accommodation area analysis module comprises a tourist accommodation area selection submodule and a tourist accommodation hotel selection submodule, the tourist accommodation area selection submodule acquires an optimal play time period through the play time period analysis module, the tourist accommodation area selection submodule stores a departure time node in advance, the tourist accommodation area selection submodule further acquires a stop time node of the optimal play time period and calculates a time difference between the stop time node and the departure time node, the tourist accommodation area selection submodule estimates the maximum mileage which can be driven by a vehicle in the time difference according to the time difference and further acquires a scenic area central point and an area outline of the scenic area, the minimum distance between any point on the area outline and the scenic area central point is used as a compensation radius, and the tourist accommodation area submodule uses the sum of the maximum mileage and the compensation radius as an area radius of the tourist accommodation area, the method comprises the steps that a scenic spot central point is used as a circle center, a tourist check-in area is established according to an area radius and the circle center, a tourist check-in hotel selection submodule firstly obtains the tourist check-in area, then first hotel information located in the tourist check-in area is selected according to address information of a hotel, the tourist check-in hotel selection submodule further obtains the edge position of the tourist check-in area, second hotel information at a certain distance from the edge position is selected, and the tourist check-in hotel selection submodule stores the first hotel information and the second hotel information into a hotel information set;
s4-1: the hotel reservation room type statistic module is connected with the visitor check-in hotel selection submodule and further acquires hotel letters stored in the hotel information setThe hotel reservation room type counting module is provided with a room type A, a room type B and a room type C in advance, the types of the room types are divided according to the maximum number of the guests entering the room, the hotel reservation room type counting module counts the reservation number of various room types of each hotel in a certain time period according to hotel information, the certain time period is guest entering time, the hotel reservation room type counting module is connected with the hotel entering number counting module, the hotel entering number counting module further acquires the reservation total number of various room types of the hotel in the certain time period, wherein the reservation total number of the room types A, the room type B and the room type C is recorded as the reservation total number
、
、
The hotel total number of check-in people counting module calculates the total number of check-in people of the hotel in a certain time period according to the preset total number of various house types and the maximum number of check-in people corresponding to each house type
Wherein, in the step (A),
the maximum number of people who live in the house type A,
the maximum number of people who live in house type B,
the maximum number of dwells for house type C;
s5-1: the hotel check-in number counting module is connected with the scenic spot number prediction module, and the scenic spot number prediction module further acquires the total check-in number of the hotel in a certain time period
The scenic spot number predicting module predicts the total number of people
Predicting the number of tourists in the scenic spot
Wherein, in the step (A),
in order to predict the coefficients of the coefficients,
the scenic spot number prediction module is also connected with the current actual people flow statistics module, and further acquires the total number of visitors entering the scenic spot on the current day
,
The scenic spot number prediction module is also connected with a people flow prediction correction module, and the people flow prediction correction module further obtains the number of scenic spot tourists obtained through prediction
And the total number of visitors entering the scenic spot on the same day
The people flow prediction correction module is based on
And
correcting the prediction coefficient, the prediction coefficient after the 1 st correction
Wherein, in the step (A),
the initial prediction coefficient is the prediction coefficient after the i-th correction
According to the prediction coefficient after the 1 st correction, the scenic spot number prediction module predicts the number of scenic spot visitors in the next day
Wherein, in the step (A),
the total number of the hotel in the next day.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.