Method and device for predicting number of passenger cars out of island based on comprehensive data analysis

Abstract

The invention belongs to the technical field of data processing, and particularly discloses a method and device for predicting the number of passenger cars going out of an island based on comprehensive data analysis, and the method comprises the steps: obtaining the license plate number information of target passenger cars going into the island and not going out of the island in a historical time period; based on the license plate number information, obtaining the license plate number attribution, the number of passengers and the on-island duration of the target passenger car entering the island for the last time in the historical time period; on the basis of the license plate number attribution and the number of passengers on the bus, searching a cross statistical table of the time dimension of the prediction date and time period, and obtaining the on-island prediction duration of the target sea-crossing bus; based on the on-island prediction duration and the on-island duration of the target sea passing passenger car, determining a prediction value of the number of the passenger cars going out of the island every day in the prediction date and time period; wherein the cross statistical table is a statistical result obtained by analyzing the historical passenger car on-island duration by taking the license plate number attribution and the number of passengers as cross dimensions, and the cross statistical tables corresponding to different time dimensions are different.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and more specifically, relates to a method and device for predicting the number of passenger buses leaving the island based on comprehensive data analysis. Background Art

[0002] As an important channel connecting Hainan and inland areas, the passenger and vehicle ferry transportation in the Qiongzhou Strait plays a vital role in promoting economic exchanges and personnel exchanges between the two places, and undertakes a large number of passenger and vehicle transportation tasks. During holidays and peak tourist seasons, the vehicle throughput of the passenger and vehicle ferry in the Qiongzhou Strait can reach twice or even three times the daily throughput, resulting in heavy traffic pressure in and out of the island, prone to congestion and delays, and seriously affecting transportation efficiency.

[0003] During the peak transportation period, the number of vehicles crossing the sea from the island is predicted, so as to formulate reasonable transportation plans and scheduling schemes, which can effectively alleviate traffic pressure. The vehicles crossing the sea can be divided into passenger cars and trucks. Among them, the crossing of trucks has a certain regularity, which is related to the crop growth cycle on the island and the operation of some industries; however, the crossing of passenger cars is more due to tourism, business, etc., which has a strong randomness, so the focus is on predicting the number of passenger cars leaving the island.

[0004] At present, some technical solutions attempt to predict the number of buses leaving the island based on historical data. However, due to the randomness of buses entering and leaving the island, historical data often cannot accurately reflect the current and future actual conditions, and the prediction results have large errors. Summary of the invention

[0005] In view of the defects existing in the related technologies, the embodiments of the present application provide a method and device for predicting the number of passenger buses leaving the island based on comprehensive data analysis, aiming to solve the problem of difficulty in accurately predicting the number of passenger buses leaving the island.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting the number of passenger buses leaving the island based on comprehensive data analysis, comprising: Obtain the license plate information of target sea-crossing buses that entered the island but did not leave the island during the historical period; Based on the license plate information, obtain the license plate location, number of passengers and duration of the target sea-crossing passenger bus that last entered the island during the historical period; Based on the place of ownership of the license plate number and the number of passengers, find the cross-statistical table of the time dimension of the predicted date time period to obtain the predicted time of the target cross-sea passenger bus on the island; Based on the predicted time on the island and the time on the island of the target buses crossing the sea, determine the predicted value of the number of buses leaving the island every day during the predicted date period; Among them, the cross-statistical table is the statistical result of analyzing the historical length of time buses have been on the island based on the cross-dimensions of the license plate number's place of origin and the number of passengers on board. The cross-statistical tables corresponding to different time dimensions are different.

[0007] In a second aspect, the embodiment of the present application further provides a device for predicting the number of passenger buses leaving the island based on comprehensive data analysis, comprising: The first acquisition module is used to obtain the license plate information of the target sea-crossing passenger buses that entered the island but did not leave the island within the historical period; The second acquisition module is used to obtain the license plate number location, number of passengers and duration of the target sea-crossing passenger bus entering the island for the last time in the historical period based on the license plate number information; The first prediction module is used to find the cross-statistical table of the time dimension of the predicted date time period based on the place of ownership of the license plate number and the number of passengers on the vehicle, and obtain the predicted time of the target cross-sea passenger bus on the island; The second prediction module is used to determine the predicted value of the number of buses leaving the island every day within the predicted date period based on the predicted time on the island and the time on the island of the target buses crossing the sea; Among them, the cross-statistical table is the statistical result of analyzing the historical length of time buses have been on the island based on the cross-dimensions of the license plate number's place of origin and the number of passengers on board. The cross-statistical tables corresponding to different time dimensions are different.

[0008] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0009] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0010] In a fifth aspect, an embodiment of the present application further provides a computer program product, which, when executed on a processor, enables the processor to execute the method described in the first aspect or any possible implementation of the first aspect.

[0011] The method and device for predicting the number of buses leaving the island based on comprehensive data analysis provided in the embodiment of the present application, through statistical annual historical data, conducts big data analysis on the length of stay on the island at different dates, different license plate numbers and different numbers of accompanying personnel, and establishes a cross-statistical table of multiple time dimensions. By querying the table, the length of stay on the island of each vehicle entering the island can be finely predicted; combined with the predicted length of stay on the island of each vehicle, the predicted number of buses leaving the island every day within the predicted date time period is statistically analyzed, and the number of buses leaving the island every day within the predicted date time period is predicted, which effectively solves the problems of the lack of prediction rules for vehicles leaving the island and the large fluctuations based on experience values. Furthermore, considering the situation where demand surges after suspension due to bad weather, a sea crossing demand intensity coefficient curve is designed based on the intensity type of sea crossing demand after resumption of flights in different time dimensions, and the situation where the intensity of sea crossing demand decreases over time after resumption of flights is characterized. With the help of this curve, the demand changes caused by backlog can be superimposed on the original island departure prediction value queue, providing method support for emergency dispatch under special circumstances. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 It is a flow chart of a method for predicting the number of passenger buses leaving the island based on comprehensive data analysis provided in an embodiment of the present application; Figure 2 is a cross-sea crossing demand intensity coefficient curve of different cross-sea crossing demand intensity types after resumption of navigation provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of a device for predicting the number of passenger buses leaving the island based on comprehensive data analysis provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] Figure 1 is a flow chart of a method for predicting the number of passenger buses leaving the island based on comprehensive data analysis provided in an embodiment of the present application, such as Figure 1As shown, the method includes at least the following steps: S101. Obtain license plate information of target sea-crossing passenger buses that entered the island but did not leave the island within a historical period of time.

[0016] Specifically, the current buses that have not left the island are the basis for predicting the number of buses that will leave the island every day in the next few days. However, in actual implementation, considering the aborigines and permanent residents on the island, although these people who stay on the island for a long time also belong to the category of passengers on the buses that have not left the island, the probability of these people leaving the island in a concentrated manner during the peak transportation period is very low. Therefore, only the buses that entered the island but did not leave the island in a relatively short historical period are used as the target buses, and the historical time period is selected, such as the past 30 days, the past 15 days, etc.

[0017] At the same time, since buses need to undergo strict vehicle and personnel identity verification when entering and leaving the island via the passenger and vehicle ferry, the identification information of the target crossing sea buses that have not yet left the island can be obtained from the database. The identification information can specifically be the license plate number information.

[0018] For example, the number of buses leaving the island in the next 7 days is predicted by default. The system automatically captures the settlement data of all buses entering and leaving the island in the past 30 days, and obtains the license plate information of the target buses that have not left the island in the past 30 days through the following method: Step 1-a: Capture all the data of buses entering the island within 30 days in chronological order, and establish the bus queue QI{(CDC1, count), (CDC2, count), ..., (CDC n , count)}, CDC represents the bus license plate number, count represents the number of times the bus enters the island. During the capture process, if the bus license plate number has not been included in the queue QI, it will be written into the island-entering bus queue QI in order, and its count value will be changed to 1 to generate a new (CDC, count) value; if the license plate number is already in the island-entering bus queue QI, the count value after the license plate number will be added by 1 (indicating that the bus has entered the island multiple times in the past 30 days), and the island-entering bus queue QI will be updated. All the data of the buses entering the island are processed to generate the island-entering bus queue QI within the past 30 days.

[0019] Step 1-b, capture all the data of buses leaving the island within 30 days in chronological order, read the license plate numbers of the buses leaving the island in chronological order, and search them in the QI of the buses entering the island. When the license plate number appears in the QI of the buses entering the island, reduce the count value of the corresponding CDC by 1, and update the QI of the buses entering the island.

[0020] Step 1-c: remove all license plate numbers CDC with count values ​​less than 1 in the QI queue updated in step 1-b, and form a new island-entering bus queue QID {CDC1, CDC2, ..., CDC n}, the queue QID contains the license plate information of the target sea-crossing passenger buses that have entered the island but have not left the island in the past 30 days.

[0021] S102, based on the license plate information, obtaining the location of the license plate number, the number of passengers on the vehicle, and the length of time the target sea-crossing passenger vehicle has been on the island for the last time it entered the island during a historical period of time.

[0022] Specifically, after locating the license plate information of the target sea-crossing passenger bus that has not left the island within the historical time period, based on the license plate information, the relevant data of the last entry into the island that matches the license plate information can be captured from the database, including the license plate number's place of origin, the number of passengers on the bus, and the length of time on the island, in preparation for subsequent data analysis.

[0023] For example, the island-entering bus queue QID {CDC1, CDC2, ..., CDC n}, associate the data of passenger vehicles entering the island, and obtain the relevant data of the last entry of all license plate numbers in the queue QID, including the license plate number's location CDCP, the number of passengers CDP, and the time on the island CDTA. Among them, the time on the island CDTA is determined by the entry time CDT and today's date.

[0024] S103. Based on the place of ownership of the license plate number and the number of passengers on board, a cross-statistical table of the time dimension of the predicted date time period is searched to obtain the predicted duration of the target cross-sea bus on the island.

[0025] Specifically, the cross-statistical table is a statistical result of analyzing the length of time the bus has been on the island with the license plate number and the number of passengers as the cross-dimensions. Different cross-statistical tables correspond to different time dimensions.

[0026] Through the license plate number location and the number of passengers on board of the target bus crossing the sea, the cross-statistical table of the time dimension of the predicted date time period is searched, so as to obtain the average time on the island corresponding to the current license plate number location and the number of passengers on board counted in the table, which is used as the predicted time on the island of the target bus crossing the sea.

[0027] On the one hand, considering the convenience of tourists from various provinces driving to Hainan Island, Hainan Island's restrictions on vehicles with out-of-province license plates, Hainan Island's regulations on exemption of certain fees in specific provinces, etc., there is a certain correlation between the place of origin of the bus license plate number and the length of time the bus stays on the island.

[0028] On the other hand, there is a certain correlation between the number of passengers on the bus and the length of time the bus stays on the island. The passenger capacity of buses entering and leaving the island is generally 5-7 seats. Different numbers of passengers on the bus often mean different needs for entering and leaving the island. For example, a passenger number of 1 is generally a short-term business need, and a passenger number of 7 is generally a longer-term stay with the elderly and children. Strictly speaking, the number and age distribution of passengers on the bus are more strongly correlated with the length of time the bus stays on the island, but as a supplement to the prediction of the length of time on the island based on the license plate number, relying on the number of passengers on the bus can greatly improve the prediction accuracy while maintaining a low computational complexity.

[0029] Therefore, in the embodiment of the present application, the license plate number of the bus and the number of passengers on the bus are selected as cross-dimensions, the historical length of time the bus has been on the island is analyzed and counted, a cross-statistical table is constructed, and the time for the bus to leave the island is predicted based on the pre-constructed cross-statistical table, thereby realizing the prediction of the number of buses leaving the island.

[0030] At the same time, considering that the number of buses leaving the island will fluctuate over time, the fluctuation is obvious during holidays, and the degree of fluctuation will be different for different types of holidays. Therefore, different cross-statistical tables are counted in different time dimensions. Table 1 is an example of a cross-statistical table for a certain time dimension provided in an embodiment of the present application.

[0031] Table 1

[0032] In some embodiments, the cross-statistic table in S103 is obtained based on the following steps: Obtain annual historical data including the license plate number of the buses crossing the sea, the number of passengers on board, and the length of time on the island; Divide annual historical data into multiple time dimensions based on statutory holidays; Taking the license plate number's location and the number of passengers on board as cross-dimensions, the length of time the buses spend on the island is analyzed to obtain cross-statistical tables of multiple time dimensions.

[0033] Specifically, different time dimensions correspond to different cross-statistical tables. There is a strong correlation between the number of buses entering and leaving the island and tourism demand, and tourists' tourism demand is directly related to statutory holidays. Therefore, based on statutory holidays, the annual historical data including the license plate number of buses crossing the sea, the number of passengers and the length of time on the island are divided into multiple time dimensions, such as Spring Festival travel (20 days before and after the first day of the first lunar month), summer / winter vacation, National Day / May Day (3 days before the holiday to the end of the holiday), three-day holiday, regular weekend (Friday to Saturday) and weekdays (Monday to Thursday).

[0034] According to the multiple time dimensions divided, with the license plate number's location and the number of passengers on board as cross dimensions, the length of time the buses spend on the island is analyzed and counted, and cross-statistical tables of the multiple time dimensions are obtained.

[0035] S104. Determine a predicted value of the number of buses leaving the island every day within the predicted date period based on the predicted time on the island and the time already on the island of the target buses crossing the sea.

[0036] Specifically, the predicted time on the island and the time on the island of the target bus can be used to predict the future time on the island of the target bus, that is, to predict the departure date of the target bus. Optionally, the future time on the island CDTL' is obtained by subtracting the time on the island CDTA from the predicted time on the island CDTL. If the obtained CDTL' is less than 0, it is assigned a value of 1 (with days as the statistical unit).

[0037] Based on the predicted departure date of the target cross-sea buses, the predicted departure buses for each day within the predicted date period are counted to obtain the predicted value of the number of departure buses for each day within the predicted date period, so as to formulate reasonable transportation plans and scheduling plans, so as to effectively alleviate the traffic pressure during the peak transportation period.

[0038] Furthermore, considering that the passenger and vehicle ferry is very sensitive to weather changes, once extreme weather such as heavy fog, strong winds, and high waves occur or are predicted, the ship will stop sailing, which will in turn delay the original departure plan of tourists on the island. Therefore, in the embodiment of the present application, different methods are used to predict the number of passenger buses leaving the island for the non-stop and stop states.

[0039] Case 1: Forecast of the number of buses leaving the island without stopping flights.

[0040] In some embodiments, in the non-stop flight state, S104 specifically includes: Based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus, the target predicted date of departure from the island of the target sea-crossing passenger bus is determined; Based on the target departure forecast date, the forecast departure buses for each day within the forecast date time period are counted to determine the forecast value of the number of departure buses for each day within the forecast date time period.

[0041] Specifically, without stopping the flight, the predicted time on the island of the target bus minus the time it has been on the island is used to predict the future time on the island of the target bus, thereby obtaining the predicted date of departure from the island of the target bus.

[0042] The target departure date is used as the departure date of the target bus, and the predicted departure date of the bus is counted every day within the prediction date period to obtain the predicted number of buses leaving the island every day within the prediction date period. The queue CDPre{CD1, CD2, ..., CD n}, where CD n It indicates the predicted value of the number of buses leaving the island on the nth day within the prediction date time period.

[0043] It can be imagined that, in the non-stop flight state, the historical time period is generally selected as the time period closest to the current prediction time, such as the past 30 days, the past 10 days, etc.; the prediction date time period is the time period closest to the current prediction time, such as the next week, the next 15 days, etc.

[0044] Case 2: Forecast of the number of buses leaving the island when flights are suspended.

[0045] In some embodiments, S104 specifically includes: Determine the intensity type of sea crossing demand after resumption of flights in the time dimension of the forecast date time period, and find the sea crossing demand intensity coefficient curve corresponding to the intensity type of sea crossing demand after resumption of flights. The sea crossing demand intensity coefficient curve is a curve that the intensity of sea crossing demand after resumption of flights decreases with the resumption of flights time; Based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus, the target predicted date of departure from the island of the target sea-crossing passenger bus is determined; Based on the target island departure forecast date, determine the first forecast value of the number of buses leaving the island every day within the forecast date period; based on the target island departure forecast date, the set suspension time and the found sea crossing demand intensity coefficient curve, determine the second forecast value of the number of buses leaving the island every day within the forecast date period; Based on the first prediction value and the second prediction value, determine the predicted value of the number of passenger vehicles leaving the island every day within the predicted date time period.

[0046] Specifically, once a flight suspension occurs, the number of buses leaving the island after the resumption of flights will surge, and will drop significantly over time. However, in different time dimensions, the degree of surge in the number of buses leaving the island after the resumption of flights is different. Therefore, the intensity type of sea crossing demand after the resumption of flights is set for different time dimensions, and the sea crossing demand intensity coefficient curve is set for different sea crossing demand intensity types after the resumption of flights. The sea crossing demand intensity coefficient curve is a curve in which the sea crossing demand intensity decreases with the resumption of flights time after the resumption of flights. By looking up this curve, the daily surge in the number of people in the continuous period after the resumption of flights can be predicted. Optionally, the sea crossing demand intensity coefficient curve can be obtained through statistical analysis of historical data, or it can be established by technical personnel through historical experience.

[0047] Figure 2is a cross-sea demand intensity coefficient curve of different cross-sea demand intensity types after resumption of navigation provided in an embodiment of the present application, such as Figure 2 As shown, the intensity types of sea crossing demand after the resumption of flights in different time dimensions are divided into three categories: strong demand, general demand and weak demand. For strong demand, such as Spring Festival (20 days before and after the first day of the new year), National Day / May Day (3 days before the holiday to the end of the holiday), three-day holidays, etc., the demand for sea crossing is the highest after the resumption of flights, and it will drop significantly in the next 3-7 days. For general demand, such as winter and summer vacations and weekends, the demand for sea crossing after the resumption of flights is relatively flat, and there will be a certain degree of surge after the resumption of flights, and then gradually flatten out as the demand is released. For weak demand, such as general working days, the demand for sea crossing after the resumption of flights is even flatter, and generally you can choose to postpone the sea crossing to a later date.

[0048] The prediction of the number of passenger buses leaving the island every day within a certain period of time after the resumption of flights can be divided into two parts: one part is the passenger buses that originally need to leave the island, and the other part is the passenger buses that are stranded due to the suspension of flights.

[0049] In the actual prediction process, the predicted time the target bus will stay on the island minus the time it has been on the island is used to predict the future time the target bus will stay on the island without stopping, thereby obtaining the predicted date for the target bus to leave the island without stopping.

[0050] On the one hand, the target predicted departure date is used to solve the first predicted value of the daily number of buses that are required to leave the island within the predicted date period.

[0051] In some embodiments, determining a first predicted value of the number of passenger vehicles leaving the island per day within a predicted date time period specifically includes: Based on the target predicted departure date, the predicted departure buses for each day within the predicted date time period are counted to determine a first predicted value of the number of departure buses for each day within the predicted date time period.

[0052] Specifically, regardless of whether the flight is suspended, the target island departure forecast date is used as the target sea crossing bus departure forecast date, and the predicted island departure buses are counted every day within the forecast date time period based on the target island departure forecast date to obtain a first forecast value of the number of island departure buses every day within the forecast date time period. The first forecast value only considers the sea crossing buses that may have originally needed to leave the island.

[0053] On the other hand, the second predicted value of the number of new buses leaving the island every day during the predicted date period is solved by using the target predicted date of leaving the island, the set suspension duration and the found intensity coefficient of sea crossing demand.

[0054] In some embodiments, determining a second predicted value of the number of passenger vehicles leaving the island per day within the predicted date time period specifically includes: Based on the target departure date, the total number of buses that are expected to depart from the island between the suspension start date and the set resumption date are counted; Based on the statistically predicted total number of buses leaving the island and the found sea crossing demand intensity coefficient curve, a second predicted value of the number of buses leaving the island every day within the predicted date time period is determined.

[0055] Specifically, in order to further consider the surge in demand for buses leaving the island after the resumption of flights, the target departure forecast date is used to count the total number of buses leaving the island between the suspension start date and the set resumption date without stopping flights. These buses may leave the island at any time after the resumption of flights, so the total number of buses leaving the island is weighted using the cross-sea demand intensity coefficient curve found to obtain the second forecast value of the number of buses leaving the island every day during the forecast date period. The second forecast value takes into account the increase in the number of buses leaving the island after the resumption of flights.

[0056] Furthermore, the first prediction value and the second prediction value calculated daily within the prediction date time period are accumulated to obtain a prediction value for the number of buses leaving the island every day.

[0057] For example, due to heavy rain, the flight is suspended and is expected to resume in 2 days. The first prediction value sequence CDPre{CD1, CD2, ..., CD n}, the total number of buses leaving the island for the two-day suspension is predicted to be CD1+CD2. Determine that the intensity type of the demand for crossing the sea after the resumption of flights corresponding to the current time dimension is strong demand, find the corresponding demand intensity coefficient curve, and the second predicted value sequence of the number of buses leaving the island every day after the resumption of flights is Qe{Qe1, Qe2, ..., Qe m}, Qe m = Cross-sea demand intensity coefficient on the mth day after the resumption of flights × (CD1+CD2). Thus, we can get the forecast sequence CDPre'{CD3+Qe1, CD4+Qe2,..., CD m-2 +Q m}.

[0058] It should be noted that since the duration of suspension or resumption of flights is often difficult to predict, the embodiment of the present application predicts the number of buses leaving the island within the predicted date time period by setting the resumption date, in order to cope with the surge in demand for leaving the island after the resumption of flights caused by the suspension of flights.

[0059] It can be imagined that, in the suspension state, the historical time period generally selects the time period closest to the suspension start date, such as 30 days before the suspension, 10 days before the suspension, etc.; the predicted date time period generally selects the time period closest to the resumption date, such as the next week after the resumption, the next 15 days after the resumption, etc.

[0060] The method for predicting the number of buses leaving the island based on comprehensive data analysis provided in the embodiment of the present application, through statistical annual historical data, conducts big data analysis on the length of stay on the island at different dates, different license plate numbers and different numbers of accompanying personnel, and establishes a cross-statistical table of multiple time dimensions. By querying the table, the length of stay on the island of each vehicle entering the island can be finely predicted; combined with the predicted length of stay on the island of each vehicle, the predicted number of buses leaving the island every day within the predicted date time period is statistically analyzed, and the number of buses leaving the island every day within the predicted date time period is predicted, which effectively solves the problems of the lack of prediction rules for vehicles leaving the island and the large fluctuations based on experience values. Furthermore, considering the situation in which demand surges after suspension due to bad weather, a sea crossing demand intensity coefficient curve is designed based on the intensity type of sea crossing demand after resumption of flights in different time dimensions, and the situation in which the intensity of sea crossing demand decreases over time after resumption of flights is characterized. With the help of this curve, the demand changes caused by backlog can be superimposed on the original island departure prediction value queue, providing method support for emergency dispatch under special circumstances.

[0061] Figure 3 is a schematic diagram of the structure of a device for predicting the number of passenger buses leaving the island based on comprehensive data analysis provided in an embodiment of the present application, such as Figure 3 As shown, the device at least includes: The first acquisition module 301 is used to obtain the license plate information of the target sea-crossing passenger bus that entered the island but did not leave the island within the historical time period; The second acquisition module 302 is used to acquire the license plate number location, the number of passengers and the length of time on the island of the target sea-crossing passenger bus that last entered the island within a historical period based on the license plate number information; The first prediction module 303 is used to find the cross-statistical table of the time dimension of the predicted date time period based on the place of ownership of the license plate number and the number of passengers on the vehicle, and obtain the predicted time of the target cross-sea passenger bus on the island; The second prediction module 304 is used to determine the predicted value of the number of buses leaving the island every day within the predicted date period based on the predicted time on the island and the time on the island of the target buses crossing the sea; Among them, the cross-statistical table is the statistical result of analyzing the historical length of time buses have been on the island based on the cross-dimensions of the license plate number's place of origin and the number of passengers on board. The cross-statistical tables corresponding to different time dimensions are different.

[0062] In some embodiments, in the suspended state, the second prediction module 304 includes: A search unit is used to determine the intensity type of sea crossing demand after resumption of navigation in the time dimension of the forecast date time period, and to search for the sea crossing demand intensity coefficient curve corresponding to the intensity type of sea crossing demand after resumption of navigation, wherein the sea crossing demand intensity coefficient curve is a curve that the intensity of sea crossing demand after resumption of navigation decreases with the resumption of navigation time; The first determination unit is used to determine the target predicted departure date of the target sea-crossing passenger bus based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus; The first prediction unit is used to determine a first prediction value of the number of passenger vehicles leaving the island every day within a prediction date time period based on a target prediction date for leaving the island; The second prediction unit is used to determine a second prediction value of the number of passenger buses leaving the island every day within the prediction date time period based on the target island departure prediction date, the set suspension time and the found sea crossing demand intensity coefficient curve; The second determination unit is used to determine the predicted value of the number of passenger buses leaving the island every day within the predicted date time period based on the first predicted value and the second predicted value.

[0063] In some embodiments, the first prediction unit is specifically configured to: Based on the target predicted departure date, statistics are collected on the number of passenger buses predicted to depart from the island every day within the predicted date time period to determine a first predicted value of the number of passenger buses predicted to depart from the island every day within the predicted date time period.

[0064] In some embodiments, the second prediction unit is specifically configured to: Based on the target departure date, the total number of buses that are expected to depart from the island between the suspension start date and the set resumption date are counted; Based on the statistically predicted total number of buses leaving the island and the found sea crossing demand intensity coefficient curve, a second predicted value of the number of buses leaving the island every day within the predicted date time period is determined.

[0065] In some embodiments, in the non-stop flight state, the second prediction module 304 includes: The first determination unit is used to determine the target predicted departure date of the target sea-crossing passenger bus based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus; The third determination unit is used to count the predicted number of passenger buses leaving the island every day within the predicted date time period based on the target island departure prediction date, and determine the predicted value of the number of passenger buses leaving the island every day within the predicted date time period.

[0066] In some embodiments, the cross-statistic table is obtained based on the following steps: Obtain annual historical data including the license plate number of the buses crossing the sea, the number of passengers on board, and the length of time on the island; Divide annual historical data into multiple time dimensions based on statutory holidays; Taking the license plate number's location and the number of passengers on board as cross-dimensions, the length of time the buses spend on the island is analyzed to obtain cross-statistical tables of multiple time dimensions.

[0067] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0068] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0069] Based on the method in the above embodiment, an embodiment of the present application provides an electronic device. The device may include: at least one memory for storing programs and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the above embodiment.

[0070] Figure 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 4 As shown, the electronic device may include: a processor 401, a communications interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communications interface 402 and the memory 403 communicate with each other via the communication bus 404. The processor 401 may call the software instructions in the memory 403 to execute the method described in the above embodiment.

[0071] In addition, the logic instructions in the above-mentioned memory 403 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application.

[0072] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0073] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0074] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0075] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0076] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0077] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0078] It is easy for those skilled in the art to understand that the above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for predicting the number of passenger buses leaving the island based on comprehensive data analysis, characterized in that: include: Obtain the license plate information of target sea-crossing buses that entered the island but did not leave the island during the historical period; Based on the license plate information, obtain the license plate location, number of passengers and duration of the target sea-crossing passenger bus entering the island for the last time during the historical period; Based on the place of ownership of the license plate number and the number of passengers on board, a cross-statistical table of the time dimension of the predicted date time period is searched to obtain the predicted duration of the target sea-crossing passenger bus on the island; Determine the predicted value of the number of buses leaving the island every day within the predicted date time period based on the predicted time on the island and the time on the island of the target buses crossing the sea; Among them, the cross-statistical table is a statistical result of analyzing the historical length of time buses have been on the island based on the cross-dimensions of the license plate number's location and the number of passengers on board. Different cross-statistical tables correspond to different time dimensions.

2. The method for predicting the number of passenger cars leaving the island according to claim 1, characterized in that: In the suspended state, the determination of the predicted value of the number of buses leaving the island every day during the predicted date time period includes: Determine the intensity type of sea crossing demand after resumption of navigation in the time dimension of the predicted date time period, and find the sea crossing demand intensity coefficient curve corresponding to the intensity type of sea crossing demand after resumption of navigation, wherein the sea crossing demand intensity coefficient curve is a curve in which the intensity of sea crossing demand after resumption of navigation decreases with the resumption of navigation time; Determining a target predicted departure date of the target sea-crossing passenger bus based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus; Based on the target predicted date of departure from the island, a first predicted value of the number of passenger buses departing from the island per day within the predicted date period is determined; based on the target predicted date of departure from the island, the set suspension time and the found sea crossing demand intensity coefficient curve, a second predicted value of the number of passenger buses departing from the island per day within the predicted date period is determined; Based on the first prediction value and the second prediction value, a prediction value of the number of passenger buses leaving the island per day within the prediction date time period is determined.

3. The method for predicting the number of passenger cars leaving the island according to claim 2, characterized in that: The step of determining a second predicted value of the number of passenger vehicles leaving the island every day within the predicted date time period includes: Based on the target predicted departure date, the total number of passenger buses predicted to depart from the island between the suspension start date and the set resumption date without stopping the flights is counted; Based on the statistically predicted total number of passenger buses leaving the island and the found sea crossing demand intensity coefficient curve, a second predicted value of the number of passenger buses leaving the island per day within the predicted date time period is determined.

4. The method for predicting the number of passenger cars leaving the island according to claim 2, characterized in that: The step of determining a first predicted value of the number of passenger vehicles leaving the island every day within the predicted date time period includes: Based on the target predicted departure date, statistics are collected on the number of passenger buses predicted to depart from the island every day within the predicted date time period to determine a first predicted value of the number of passenger buses predicted to depart from the island every day within the predicted date time period.

5. The method for predicting the number of passenger cars leaving the island according to claim 1, characterized in that: In the case of non-stop flights, the predicted value of the number of buses leaving the island every day within the predicted date and time period includes: Determining a target predicted departure date of the target sea-crossing passenger bus based on the predicted time on the island and the time on the island of the target sea-crossing passenger bus; Based on the target predicted departure date, the predicted departure buses for each day within the predicted date time period are counted to determine the predicted number of departure buses for each day within the predicted date time period.

6. The method for predicting the number of passenger cars leaving the island according to any one of claims 1 to 5, characterized in that: The cross-statistical table is obtained based on the following steps: Obtain annual historical data including the license plate number of the buses crossing the sea, the number of passengers on board, and the length of time on the island; Dividing the annual historical data into multiple time dimensions based on statutory holidays; The length of time the bus spends on the island is analyzed with the license plate number's location and the number of passengers on board as cross-dimensions to obtain a cross-statistical table of the multiple time dimensions.

7. A device for predicting the number of passenger cars leaving the island based on comprehensive data analysis, characterized in that: include: The first acquisition module is used to obtain the license plate information of the target sea-crossing passenger buses that entered the island but did not leave the island within the historical period; The second acquisition module is used to obtain the license plate number location, the number of passengers and the length of time on the island of the target sea-crossing passenger bus that entered the island for the last time during the historical time period based on the license plate number information; The first prediction module is used to find the cross-statistical table of the time dimension of the predicted date time period based on the place of ownership of the license plate number and the number of passengers on the vehicle, and obtain the predicted time of the target cross-sea passenger bus on the island; The second prediction module determines the predicted value of the number of buses leaving the island every day within the predicted date time period based on the predicted time on the island and the time on the island of the target bus crossing the sea; Among them, the cross-statistical table is a statistical result of analyzing the historical length of time buses have been on the island based on the cross-dimensions of the license plate number's location and the number of passengers on board. Different cross-statistical tables correspond to different time dimensions.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

Images