Low-altitude passenger flow prediction method, system and equipment

Abstract

The invention discloses a low-altitude passenger flow prediction method, system and equipment. The method comprises the following steps: firstly, collecting original data of each low-altitude passenger flow type; wherein the low-altitude passenger flow type comprises low-altitude rescue, low-altitude travel, low-altitude business and low-altitude commuting; the method comprises the following steps: firstly, acquiring original data of each low-altitude passenger flow type, then analyzing the original data of each low-altitude passenger flow type, determining a low-altitude selection proportion of each low-altitude passenger flow type, generating a passenger flow prediction value of each low-altitude passenger flow type based on the low-altitude selection proportion, and finally summarizing the passenger flow prediction values of each low-altitude passenger flow type to obtain a low-altitude passenger flow total prediction value. According to the invention, the flexibility, accuracy and efficiency of low-altitude passenger flow prediction can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, system and device for predicting low-altitude passenger flow. Background Art

[0002] With the rapid development of the low-altitude economy, low-altitude transportation has become a crucial solution for alleviating ground traffic congestion and improving emergency response efficiency. Applications for low-altitude transportation encompass a wide range of sectors, including medical rescue, cultural tourism, high-end business travel, and urban commuting. However, the rational allocation of low-altitude transportation resources relies on accurate passenger flow forecasting, and existing technologies still have significant shortcomings in this regard.

[0003] Patent publication number CN114066062A proposes a method for forecasting urban takeout and express delivery services, which are high-value, small-volume, and time-sensitive, using a four-stage traffic method. This forecast divides advanced urban air passenger flow into three parts: induced air traffic demand, regional air traffic demand, and urban air traffic demand. However, in reality, different travel purposes lead to different preferences. For example, business travelers are more concerned about timeliness, while leisure travelers are more concerned about experience. Therefore, it cannot be measured using a fixed parameter model. In addition, the four-stage method assumes that traffic distribution is based on a fixed attraction model. However, the generation and attraction of urban air traffic passenger flow are related to multiple factors such as travel distance, the price of low-altitude use, the social attributes of residents, and the economic conditions of residents. This may break the traditional distance-impedance relationship and cause the distribution prediction to fail. In summary, the existing technical methods mainly have problems such as insufficient practical significance, insufficient scientific method, and lack of scenario analysis, resulting in low reliability and accuracy of passenger flow forecasts. Summary of the Invention

[0004] The purpose of the present invention is to provide a low-altitude passenger flow prediction method, system and device, which can make the prediction results of low-altitude passenger flow more consistent with reality and improve the accuracy of low-altitude passenger flow prediction.

[0005] To achieve the above objectives, an embodiment of the present invention provides a low-altitude passenger flow prediction method, comprising:

[0006] Collecting raw data of various low-altitude passenger flow types; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting;

[0007] Analyzing the raw data of each low-altitude passenger flow type, determining a low-altitude selection ratio for each low-altitude passenger flow type, and generating a passenger flow prediction value for each low-altitude passenger flow type based on the low-altitude selection ratio;

[0008] The passenger flow forecast values of each low-altitude passenger flow type are summarized to obtain the total low-altitude passenger flow forecast value.

[0009] The analyzing the original data of each low-altitude passenger flow type to determine the low-altitude selection ratio of each low-altitude passenger flow type, and generating the passenger flow prediction value of each low-altitude passenger flow type based on the low-altitude selection ratio, includes:

[0010] Performing a timeliness analysis based on emergency data and emergency hospital locations to determine a low-altitude rescue ratio, and generating a low-altitude rescue passenger flow forecast based on the low-altitude rescue ratio;

[0011] Conducting timeliness analysis and price analysis based on cultural tourism data and transportation hub locations to determine the proportion of low-altitude cultural passenger traffic, and generating a low-altitude cultural passenger traffic forecast based on the proportion of low-altitude cultural passenger traffic;

[0012] Determining the low-altitude proportion of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generating a low-altitude business passenger flow forecast value based on the low-altitude proportion of each type of business trip;

[0013] Based on the distribution of high-net-worth individuals and the low-altitude commuting utility function, the low-altitude commuting selection probability is determined, and a low-altitude commuting passenger flow prediction value is generated based on the low-altitude commuting selection probability.

[0014] Optionally, performing a timeliness analysis based on emergency data and emergency hospital locations to determine a low-altitude rescue ratio, and generating a low-altitude rescue passenger flow prediction value based on the low-altitude rescue ratio, includes:

[0015] Based on the number of first aids and the proportion of various illnesses, potential groups for low-altitude rescue are screened, and various high-incidence occasions for first aid are screened based on the potential groups for low-altitude rescue;

[0016] Divide the emergency hospital into multiple time zones according to its location, conduct time zone analysis on various emergency high-incidence areas based on the divided time zones and the distribution of emergency population, and obtain the coverage of emergency hospitals on various emergency high-incidence areas;

[0017] Conduct price elasticity analysis on the potential low-altitude rescue groups, and predict the proportion of low-altitude rescue under different time limits and different prices;

[0018] A low-altitude rescue passenger flow prediction value is generated according to the coverage degree and the low-altitude rescue ratio.

[0019] Optionally, performing timeliness analysis and price analysis based on cultural tourism data and transportation hub locations to determine the proportion of low-altitude cultural passenger traffic, and generating a low-altitude cultural passenger traffic forecast based on the proportion of low-altitude cultural passenger traffic, includes:

[0020] Analyze multiple travel routes of cultural and tourism tourists based on cultural and tourism data;

[0021] Calculate the potential passenger flow of low-altitude cultural tourism along each travel route based on cultural tourism data and the psychological characteristics of cultural tourism tourists;

[0022] Divide multiple time zones based on the location of transportation hubs, conduct timeliness and price analysis on each travel route, and obtain the proportion of low-altitude cultural passenger traffic under different prices, different travel routes, and different time zones;

[0023] A low-altitude cultural tourism passenger flow forecast value is generated based on the potential low-altitude cultural tourism passenger flow of each travel route and the proportion of low-altitude cultural tourism passenger flow under different prices, different travel routes and different time zones.

[0024] Optionally, the calculation of the potential low-altitude cultural tourism passenger flow for each travel route based on cultural tourism data and psychological characteristics of cultural tourism tourists includes:

[0025] According to the number of scenic spots and the psychological characteristics of cultural tourists, the proportion of cultural tourists on each travel route is calculated;

[0026] Calculate the cultural tourism flow of each travel route based on the total amount of urban cultural tourism and the proportion of cultural tourism flow;

[0027] Based on cultural and tourism data, extract the proportion of low-altitude cultural and tourism potential passenger flow for each travel route;

[0028] According to the cultural and tourism passenger flow of each travel route and the ratio of the low-altitude cultural and tourism potential passenger flow, the low-altitude cultural and tourism potential passenger flow of each travel route is calculated.

[0029] Optionally, determining the low-altitude proportion of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generating a low-altitude business passenger flow prediction value based on the low-altitude proportion of each type of business trip, includes:

[0030] Extract the proportion of business trips based on the daily passenger volume at the transportation hub;

[0031] Divide passenger flow attributes according to travel location, travel time and arrival time, and predict the proportion of travel flow under different attributes;

[0032] Calculate the passenger flow of each type of business trip under different attributes based on the roadside passenger flow of the transportation hub, the proportion of business trips, and the proportion of passenger flows under different attributes;

[0033] Predict the proportion of low-altitude business trips for each type of business trip under different attributes;

[0034] A low-altitude business passenger flow prediction value is generated based on the travel passenger flow of each type of business trip under the different attributes and the low-altitude business proportion of each type of business trip under the different attributes.

[0035] Optionally, determining the low-altitude commuting selection probability based on the distribution of high-net-worth individuals and the low-altitude commuting utility function, and generating a low-altitude commuting passenger flow prediction value based on the low-altitude commuting selection probability, includes:

[0036] Screening residential areas of high-net-worth individuals, and calculating the total passenger flow of the high-net-worth individuals during the morning peak hours based on traffic data;

[0037] Compare the time utility, cost utility, and comfort utility of the first mode of transportation and low-altitude commuting, and construct a probability function for choosing low-altitude commuting;

[0038] Calculate the commuting volume of high-net-worth individuals based on the proportion of regular commuting passenger flow and the total passenger flow of the high-net-worth individuals during the morning peak;

[0039] According to the commuting volume of the high-net-worth population and the low-altitude commuting selection probability function, low-altitude commuting passenger flow at different commuting distances is generated.

[0040] Optionally, the low-altitude commuting selection probability function is P UAM :

[0041] P UAM =1 / [1+exp[V car -V UAM );

[0042] V UAM =b1T UAM +b2F UAM +b3C UAM ;

[0043] Among them, V car is the commuting utility function of the first means of transportation, V UAM is the utility function of low-altitude commuting, T UAM 、F UAM 、C UAM are the low-altitude commuting time utility function, low-altitude commuting cost utility function and low-altitude commuting comfort utility function respectively, b1, b2 and b3 are the importance coefficients of the low-altitude commuting time utility function, low-altitude commuting cost utility function and low-altitude commuting comfort utility function respectively;

[0044] The utility function of low-altitude commuting cost is:

[0045] F UAM =(α*D / v car -β*D / v UAM )*F per +F car ;

[0046] D is the travel distance, α, β are the time value coefficients, v car 、v UAMThe speed of the first mode of transportation commuting and low-altitude commuting, F per is the unit time value of high net worth individuals, F car is the cost utility function of commuting using the first means of transportation.

[0047] To achieve the above objectives, an embodiment of the present invention further provides a low-altitude passenger flow prediction system, comprising:

[0048] A low-altitude passenger flow type determination module is used to obtain the low-altitude passenger flow type; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting;

[0049] The low-altitude rescue passenger flow prediction module is used to perform timeliness analysis based on emergency data and emergency hospital locations to generate low-altitude rescue passenger flow prediction values;

[0050] The low-altitude cultural passenger flow prediction module is used to perform timeliness analysis and price analysis based on cultural tourism data and transportation hub locations, and generate low-altitude cultural passenger flow prediction values;

[0051] Low-altitude business passenger flow prediction module, used to generate low-altitude business passenger flow prediction values based on the number of passengers and passenger flow attributes at the transportation hub;

[0052] Low-altitude commuter passenger flow prediction module, used to generate low-altitude commuter passenger flow prediction values based on the distribution of high-net-worth individuals and the low-altitude commuter utility function;

[0053] The low-altitude rescue passenger flow forecast value, the low-altitude literary passenger flow forecast value, the low-altitude business passenger flow forecast value and the low-altitude business passenger flow forecast are summarized to obtain a total low-altitude passenger flow forecast value.

[0054] To achieve the above objectives, an embodiment of the present invention also provides a low-altitude passenger flow prediction device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the low-altitude passenger flow prediction method described in any one of the above items.

[0055] To achieve the above objectives, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the low-altitude passenger flow prediction methods described above.

[0056] Compared with the prior art, the embodiments of the present invention provide a method, system and device for predicting low-altitude passenger flow. First, based on the differences in users' travel purposes, the present invention divides low-altitude passenger flow into four categories: low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting. Classification prediction is carried out for the four types of low-altitude scenarios. For example, in the low-altitude rescue scenario, the probability of choosing low-altitude is analyzed from the aspects of illness, rescue distance, price elasticity, etc.; in the low-altitude cultural tourism, the probability of choosing low-altitude is analyzed from the aspects of travel path, travel time, and timeliness requirements of the destination; in the low-altitude business, the probability of choosing low-altitude is analyzed from the aspects of whether it is first class, travel area, travel time, and travel duration; in low-altitude commuting, a utility function is constructed from the three aspects of travel time, travel cost and comfort to analyze the probability of choosing low-altitude. Therefore, the embodiments of the present invention establish the correlation between the proportion of low-altitude selection of each type and each factor, so that the prediction results are more in line with reality and the accuracy of low-altitude passenger flow prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings used in the implementation methods. Obviously, the drawings described below are only some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 1 is a flow chart of a method for predicting low-altitude passenger flow provided by an embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram of the main travel routes of urban cultural and tourist flows provided by an embodiment of the present invention;

[0060] Figure 3 This is a time utility function comparison diagram of car commuting and low-altitude commuting provided by an embodiment of the present invention;

[0061] Figure 4 This is a cost-effectiveness comparison chart of car commuting and low-altitude commuting provided by an embodiment of the present invention;

[0062] Figure 5 This is a diagram comparing the comfort and utility of car commuting and low-altitude commuting, provided by an embodiment of the present invention;

[0063] Figure 6 This is a comparison chart of the selection probabilities of car commuting and low-altitude commuting provided by an embodiment of the present invention;

[0064] Figure 7 This is another flow chart of a low-altitude passenger flow prediction method provided by an embodiment of the present invention;

[0065] Figure 8This is a structural block diagram of a low-altitude passenger flow prediction system provided by an embodiment of the present invention;

[0066] Figure 9 This is a structural block diagram of a low-altitude passenger flow prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0068] See also Figure 1 , Figure 1 1 is a flow chart of a low-altitude passenger flow prediction method provided by an embodiment of the present invention, wherein the low-altitude passenger flow prediction method comprises steps S1 to S3:

[0069] Step S1: collecting raw data of various low-altitude passenger flow types; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting;

[0070] Step S2: Analyze the original data of each low-altitude passenger flow type, determine the low-altitude selection ratio of each low-altitude passenger flow type, and generate a passenger flow prediction value for each low-altitude passenger flow type based on the low-altitude selection ratio;

[0071] Step S3: Summarize the passenger flow prediction values of each low-altitude passenger flow type to obtain a total low-altitude passenger flow prediction value.

[0072] In an embodiment of the present invention, the main components of future low-altitude passenger flow are first determined based on the city's low-altitude development trends. Specifically, with the development of low-altitude airspace in cities, the air traffic environment continues to improve, and aircraft performance and related technologies continue to improve, providing better conditions for medical emergencies. Medical emergencies are characterized by time urgency and extremely high requirements for transportation convenience. Low-altitude flight can overcome the limitations of ground transportation, achieve faster access to the patient's location, and transport the patient to a medical institution. It can also expand the coverage of medical rescue and achieve wider application. Therefore, low-altitude rescue will become an important component of future low-altitude passenger flow. Low-altitude cultural tourism meets people's pursuit of diversified and high-end tourism experiences. Under the development trend of low-altitude airspace in cities, related infrastructure and services will continue to improve, and policies may also provide support, making it the first to become a scene that is focused on cultivation. Low-altitude flight allows tourists to appreciate urban landscapes and natural scenery from a unique perspective. This novel way of travel has great market potential and will attract a large number of tourists, thus becoming one of the main types of low-altitude passenger flow. High-end urban business people have high demands for travel efficiency and convenience. Against the backdrop of urban low-altitude development, low-altitude flight can provide them with customized, flexible travel services, avoiding the many cumbersome steps and ground traffic congestion of conventional air travel, and meeting their needs for quick arrival at their destinations. This is the primary commercial scenario, and therefore, low-altitude business is bound to be a major component of low-altitude passenger traffic. Intra-city commuting faces the challenge of ground traffic congestion, while low-altitude commuting offers the advantages of speed and efficiency. With the development of the urban low-altitude sector, as related technologies mature, costs decrease, and infrastructure improves, more and more people will choose low-altitude commuting. Furthermore, considering that the development of low-altitude cultural tourism requires a certain level of spending power and time, intra-city commuters have the potential to become consumers of low-altitude cultural tourism, making them the primary reserve force for low-altitude cultural tourism. This also illustrates the importance and development potential of low-altitude intra-city commuting as a type of low-altitude passenger traffic.

[0073] Exemplarily, the embodiment of the present invention collects the original passenger flow data for the four main low-altitude types, namely low-altitude rescue, low-altitude cultural tourism, low-altitude business, and urban commuting, and identifies the spatiotemporal distribution characteristics of each type of low-altitude passenger flow by performing a timeliness analysis on the collected original data, predicts the low-altitude passenger flow of each type of low-altitude passenger flow at different price levels, and finally summarizes the low-altitude passenger flow predicted for each type of passenger flow at different price levels, and comprehensively calculates the total predicted value of low-altitude passenger flow. The embodiment of the present invention can take into account the differences in users' travel purposes and divide low-altitude passenger flow into four categories, namely low-altitude emergency, low-altitude cultural tourism, low-altitude business, and low-altitude commuting. It improves the fixed attraction model of the traditional four-stage method and can more accurately reflect the actual situation of passenger flow in the low-altitude field compared to the general passenger flow prediction method, thereby improving the pertinence and accuracy of the prediction.

[0074] In an optional implementation manner, the step S2 specifically includes:

[0075] Step S21: Perform timeliness analysis based on emergency data and emergency hospital locations to determine a low-altitude rescue ratio, and generate a low-altitude rescue passenger flow forecast based on the low-altitude rescue ratio;

[0076] Step S22: Perform timeliness analysis and price analysis based on cultural tourism data and transportation hub locations to determine the proportion of low-altitude cultural passenger flow, and generate a low-altitude cultural passenger flow forecast based on the proportion of low-altitude cultural passenger flow;

[0077] Step S23: determining the low-altitude ratio of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generating a low-altitude business passenger flow forecast value based on the low-altitude ratio of each type of business trip;

[0078] Step S24: Based on the distribution of high-net-worth individuals and the low-altitude commuting utility function, determine the low-altitude commuting selection probability, and generate a low-altitude commuting passenger flow prediction value based on the low-altitude commuting selection probability.

[0079] In an optional implementation manner, the step S21 specifically includes:

[0080] Step S211: Screening potential low-altitude rescue groups based on the number of first aid requests and the proportion of various illnesses, and screening various high-incidence first aid occasions based on the potential low-altitude rescue groups;

[0081] Step S212: Divide the emergency hospital into multiple time zones according to their locations, and perform time zone analysis on various emergency high-incidence areas based on the divided time zones and the distribution of emergency populations to determine the coverage of the emergency hospitals on the various emergency high-incidence areas.

[0082] Step S213: performing price elasticity analysis on the potential low-altitude rescue groups to predict the low-altitude rescue ratios under different time limits and different prices;

[0083] Step S214: Generate a low-altitude rescue passenger flow prediction value based on the coverage degree and the low-altitude rescue ratio.

[0084] Specifically, in step S211, the current number of emergency patients and the proportion of each disease condition P are calculated using the following formula: i , thus making it clear that low-altitude rescue is mainly aimed at groups with highly time-sensitive illnesses, that is, potential groups for low-altitude rescue.

[0085]

[0086] Among them, X represents the distribution of 120 emergency population, P i Represents the proportion of the i-th disease, and the number of disease categories is less than or equal to N.

[0087] For example, referring to Table 1, Table 1 is the disease categories of 120 emergency rescue provided by an embodiment of the present invention. As shown in Table 1, by counting the proportions of various diseases, it can be found that except for endocrine, urinary system, others, and death, which are non-emergency situations, other types of diseases are judged to be highly time-sensitive conditions, that is, potential passenger flow for low-altitude rescue.

[0088] Table 1. Disease categories of 120 emergency medical services

[0089]

[0090] Furthermore, in step S211, high-incidence locations for emergency medical services are determined by statistically analyzing the high-incidence areas for various time-sensitive diseases. For example, as shown in Table 2, high-incidence locations for emergency medical services are primarily concentrated in homes, offices / public service facilities, highways, and other areas. Based on historical data analysis, it can be pre-determined that the high-incidence locations for emergency medical services account for 58%, 12%, 20%, and 10%, respectively.

[0091] Table 2 Various emergency high-incidence areas

[0092]

[0093] Specifically, in step S212, the distribution of emergency personnel may be calculated based on the urban population density distribution relationship.

[0094] In an optional implementation, the distribution of emergency personnel is calculated based on the urban population density distribution relationship, specifically including:

[0095] The target research area is divided into 100*100m grids. Based on the current population distribution, the population density of each grid is calculated using the following formula:

[0096]

[0097] X j =X*P j ;

[0098]

[0099] Among them, Y is the current total population of the city, m is the number of grid points within the research area, P j is the current population density of the j-th grid point, X j is the distribution of 120 emergency population at the j-th grid point.

[0100] Specifically, in step S212, the location of the city's 120 emergency hospitals or medical institutions can be obtained through current POI crawling or official websites, and then multiple time-sensitive circles are divided with the obtained emergency hospital location as the center. For example, except for some diseases such as cardiac arrest and airway foreign bodies, the rescue time should be within 4 minutes. For most other diseases, the optimal time from onset to treatment is within 30 minutes. Therefore, the embodiment of the present invention divides the time-sensitive circles with the emergency hospital location as the center and the rescue time as 15 minutes, 30 minutes, and more than 1 hour drive as the radius.

[0101] Furthermore, in step S212, the timeliness analysis is carried out on the divided timeliness circles mainly for various emergency high-incidence areas, namely, homes, offices / public service facilities, and highways. See Table 3, which shows the coverage of emergency hospitals for various emergency high-incidence areas. As shown in Table 3, for example, The ratio of the total coverage of residential POIs within the hospital's 15-minute time zone to the total number of residential POIs within the study area; It is the ratio of the total population covered by the hospital's 15-minute time zone to the population of residential areas within the study area.

[0102] Table 3 Coverage of emergency hospitals in various high-incidence areas of emergency care

[0103]

[0104] Specifically, in step S213, considering that the medical emergency group has a low price elasticity, when the distance to the hospital is greater than 30 minutes, the demand for use does not significantly decrease with increasing prices. However, within 30 minutes, ground transportation is more time-efficient than ground travel. Therefore, see Table 4, which shows the predicted low-altitude rescue ratios for different time zones and prices according to an embodiment of the present invention.

[0105] Table 4 The proportion of low-altitude rescue under different time limits and prices

[0106]

[0107] Specifically, in step S214, the predicted low-altitude rescue passenger flow is calculated based on the coverage of the emergency hospital for each type of accident site and the low-altitude rescue ratio under different time zones and prices. See Table 5, which shows the predicted low-altitude passenger flow for various high-incidence emergency situations under different time zones and prices, according to an embodiment of the present invention.

[0108] Table 5 Predicted values of low-altitude rescue passenger flow in various emergency high-incidence areas under different time zones and different prices

[0109]

[0110]

[0111] For example,

[0112] Scenario 1: The single-trip price is 300-500 yuan, and the daily low-altitude rescue passenger flow is:

[0113]

[0114] Scenario 2: The single-trip price is between 500-1000 yuan. The daily low-altitude rescue passenger volume is:

[0115]

[0116] Scenario 3: The single-trip price is between 1,000 and 2,000 yuan. The daily low-altitude rescue passenger volume is:

[0117]

[0118] In an optional embodiment, step S22 specifically includes:

[0119] Step S221: Analyze multiple travel routes of cultural and tourism travelers based on cultural and tourism data;

[0120] Step S222: Calculate the potential low-altitude cultural tourism passenger flow for each travel route based on cultural tourism data and the psychological characteristics of cultural tourism tourists;

[0121] Step S223: Divide the transportation hub into multiple time zones according to their location, perform time efficiency analysis and price analysis on each travel route, and obtain the proportion of low-altitude cultural passenger traffic under different prices, different travel routes, and different time zones;

[0122] Step S224: Generate a low-altitude cultural tourism passenger flow prediction value based on the potential low-altitude cultural tourism passenger flow of each travel route and the proportion of low-altitude cultural tourism passenger flow under the different prices, different travel routes, and different time zones.

[0123] Specifically, in step S221, see Figure 2 , Figure 2 This is a schematic diagram of the main travel routes of urban cultural and tourist flows provided by an embodiment of the present invention. Figure 2As shown, the main travel purposes of foreign tourists for cultural tourism are arrival, sightseeing and rest, so the main starting and ending points are transportation hubs, scenic spots and hotels. Going from the hub to the hotel or restaurant corresponds to route ① in the figure; going directly from the hub to the scenic spot corresponds to route ② in the figure; going from the scenic spot to the hotel or restaurant corresponds to route ③ in the figure; moving between different scenic spots corresponds to route ④ in the figure (circular arrows at the scenic spot); going from the hotel or restaurant to the scenic spot corresponds to route ⑤ in the figure; returning from the scenic spot to the hub corresponds to route ⑥ in the figure; going from the hotel or restaurant to the hub corresponds to route ⑦ in the figure, forming a total of ⑧ travel paths. It should be noted that since catering activities are mainly solved behind the scenic area / around the hotel, the embodiment of the present invention does not conduct special research on this path.

[0124] Furthermore, the duration of the tour is analyzed, and the corresponding key nodes in the tour duration are combined to clarify the complete travel chain. See Table 6, which shows the analysis of the low-altitude cultural tourism day travel chain in an embodiment of the present invention. For example, the tour can be divided into one-day tours and multi-day tours based on the duration of the tour, where a one-day tour does not involve the path of arriving and leaving the hotel. In addition, based on the differences in the travel paths of multi-day tours, it is divided into the day of arrival, the day of departure, and other days (non-arrival and departure).

[0125] Table 6 Analysis of the cultural tourism day trip chain

[0126]

[0127] In an optional embodiment, the step S222 specifically includes:

[0128] A1. Calculate the proportion of cultural tourism traffic along each route based on the number of scenic spots and the psychological characteristics of cultural tourism tourists.

[0129] A2. Calculate the cultural tourism flow for each route based on the total number of cultural tourism activities in the city and the proportion of cultural tourism flow.

[0130] A3. Based on cultural tourism data, extract the potential proportion of low-altitude cultural tourism passenger flow for each travel route;

[0131] A4. Calculate the potential low-altitude cultural and tourism passenger flow for each travel route based on the cultural and tourism passenger flow for each travel route and the ratio of the potential low-altitude cultural and tourism passenger flow.

[0132] Specifically, in step A1, based on the general city size and scenic spot data, it is predicted how many days tourists may visit, so as to clarify the proportion of cultural tourists who choose each travel route. For example, the passenger flow of one-day tours, arrival days, and departure days in City A is accumulated to 100%, and the passenger flow on other days is 25% (that is, the passenger flow with a tour duration of more than 2 days accounts for 25%, mainly because the passenger flow on other days intersects with the passenger flow on arrival days and departure days) to predict the passenger flow proportion of each travel route selected in one-day or multi-day tours. As shown in Figure 7, the cultural tourist flow proportion prediction of each travel route in City A provided by an embodiment of the present invention is provided.

[0133] Table 7A Forecast of cultural and tourist traffic proportions by travel route in each city

[0134]

[0135] Specifically, in step A2, the total amount of cultural tourism within the target research scope is predicted based on the city's major external transportation hubs. It should be noted that external transportation hubs mainly refer to railway stations, high-speed rail stations, and airports, and do not include highways, because passengers arriving via highways will mainly drive as a mode of transportation, and the rate of choosing low-altitude travel is relatively low. Then, according to the determined proportion of cultural tourism traffic for each travel route, the predicted total amount of cultural tourism is allocated to each travel route to obtain the cultural tourism traffic for each travel route. For example, for travel route ①, the cultural tourism traffic from the hub to the hotel is P1.

[0136] Specifically, in step A3, by analyzing the characteristics of cultural and tourist tourists, 4A-level and above scenic spots and 5-star hotels are extracted as the potential group of low-altitude cultural and tourist tourists. By counting the number and number of rooms of 5-star and above hotels and the daily passenger flow of 5A-level scenic spots, the proportion of high-end cultural and tourist traffic is extracted, that is, the potential group of low-altitude cultural and tourist tourists. For example, the proportion of low-altitude cultural and tourist potential passenger flow in path ① is r1.

[0137] Furthermore, in step A4, the cultural tourism passenger flow P1 of each travel route is multiplied by the low-altitude cultural tourism potential passenger flow ratio r1 of each travel route to obtain the low-altitude cultural tourism potential passenger flow on each travel route. For example, the low-altitude cultural tourism potential passenger flow of route ① from the hub to the five-star hotel is

[0138] Specifically, in step S223, a timeliness analysis is performed for multiple travel start and end points of a single travel route. For example, for travel route ① external transportation hub-five-star hotel, where the number of external transportation hubs is N S , the number of five-star hotels is N h , if N S <N h, then the timeliness of each transportation hub A, B…i to the hotel is analyzed in turn, and the coverage rate of transportation hub A to the hotel with timeliness of 30 minutes, 60 minutes, and more than 60 minutes is obtained respectively.

[0139] See Table 8, which shows the coverage relationship between travel route ① external transportation hubs and five-star hotels.

[0140] Table 8 Travel Path① Coverage Relationship between External Transportation Hubs and Five-Star Hotels

[0141]

[0142] Furthermore, the timeliness analysis results of multiple travel origins and destinations are aggregated, that is, the weights of each transportation hub A, B…i in the travel path ① are combined. It can be concluded that the coverage rate of hotels that can be reached by driving for 30 minutes, 60 minutes, and more than 60 minutes from the transportation hub is

[0143]

[0144] in, It can be set based on the total number of arriving and departing passengers, such as the size of attractions and the number of rooms for hotels; it can also be set based on historical experience data.

[0145] Following the same method, the timeliness analysis of travel paths ② to ⑦ was conducted to obtain a summary table of timeliness circles, which is the proportion of low-altitude cultural passenger flow in different timeliness circles under different travel paths, as shown in Table 9.

[0146] Table 9 Passenger flow ratios in different travel time zones under different travel routes

[0147]

[0148] Furthermore, as shown in Table 10, it is predicted that under different prices, the proportion of cultural and tourism groups in different travel routes and time zones who choose low-altitude flights, that is, the proportion of low-altitude cultural and tourism traffic, will be the same.

[0149] Table 10 Forecast of the proportion of low-altitude cultural passenger flow under different prices, different travel routes and different time zones

[0150]

[0151] Specifically, in step S224, a low-altitude cultural passenger flow prediction value is generated based on the potential low-altitude cultural tourism passenger flow of each travel route and the proportion of low-altitude cultural passenger flow under different prices, different travel routes, and different time zones. Then, each low-altitude cultural passenger flow prediction value is summarized to obtain a total passenger flow prediction value for low-altitude cultural tourism.

[0152] In an optional embodiment, step S23 specifically includes:

[0153] Step S231: Extract the proportion of business trips based on the daily passenger arrival and departure volume of the transportation hub;

[0154] Step S232: classify passenger flow attributes according to travel location, travel time, and arrival time, and predict the proportion of passenger flow under different attributes;

[0155] Step S233: Calculate the passenger flow of each type of business trip under different attributes based on the roadside passenger flow of the transportation hub, the proportion of business trips, and the proportion of passenger flows under different attributes;

[0156] Step S234: predicting the low-altitude ratio of each type of business trip under different attributes;

[0157] Step S235: Generate a low-altitude business passenger flow prediction value based on the travel passenger flow of each type of business trip under the different attributes and the low-altitude proportion of each type of business trip under the different attributes.

[0158] Specifically, in step S231, the daily passenger arrival and departure volumes at hubs such as high-speed rail stations and airports can be counted separately, business class and non-business class passengers can be distinguished, and then the proportion of business class seats on high-speed rail and airplanes, as well as the proportion of business trips, can be calculated.

[0159] For example, for high-speed rail stations, we analyze the main types of vehicles that pass through high-speed rail stations within the target research range, calculate the proportion of business class, and combine the survey data to predict the proportion of high-end business travelers in business class. The proportion of business class travelers with business travel as their purpose is R t The proportion of non-business class passengers whose travel purpose is business travel is R t,n .

[0160] For example, for airports, we analyze the main aircraft types at the airports within the research scope, combine the proportion of first-class cabins of each aircraft type, and use the survey data to predict the proportion of high-end business travelers in first-class cabins. The proportion of first-class cabins with business travel as the purpose is R a The proportion of non-business class passengers whose travel purpose is business travel is R a,n .

[0161] Specifically, in step S232, first, based on whether or not the passengers leave the station, they are divided into in-station transfer passenger flow and roadside passenger flow. Since in-station transfer passenger flow has no direct correlation with the city, it is not considered. Subsequently, it is divided into the city and surrounding cities according to the destination location, and the time of arrival at the hub is divided into night (18:00-8:00 the next day) and day (8:00-18:0). Among them, the city is further divided into the time from the hub to the destination <30min, 30-60min, >60min. The passenger flow attributes are divided by the above distinction of travel location, travel time and arrival time. For example, the passenger characteristics analysis of transportation hub A is shown in Table 11.

[0162] Table 11 Passenger characteristics analysis of transportation hub A

[0163]

[0164] Furthermore, the proportion of travel passenger flows in different areas, different arrival time periods, and different travel duration attributes is calculated. For example, the proportion of passenger flows within the city and outside the city is mainly determined by the construction level, economy, and geographical location of the railway station and airport of the studied city. The arrival time is daytime / nighttime and is determined by the arrival schedule and frequency of the railway station and airport. The time from the hub to the destination mainly depends on the size of the city and the location distribution of the destination. In order to calculate the passenger flow distribution under different travel time periods, the total number of business land POIs within the study scope can be obtained, and the number of business land POIs covered by 30 minutes and 60 minutes from the high-speed rail station and airport can be counted respectively, and the proportion of this type of POI in the city can be obtained to obtain the proportion of travel passenger flows covered under different attributes of each hub, as shown in Table 12.

[0165] Table 12 Calculation of passenger flow ratio under different attributes

[0166]

[0167] Specifically, in step S233, for the four types of business travel passenger flows, namely, high-speed rail business class, high-speed rail non-business class, airplane first class, and airplane non-first class, the roadside passenger flow of high-speed rail and airport is set as C t ,C a The passenger flow under different attributes is obtained by dividing the roadside passenger flow at the transportation hub among arriving passengers by the proportion of business trips and the proportion of travel passenger flow under different attributes. The passenger flow statistics of each type of business trip under different attributes are shown in Table 13:

[0168] Table 13 Passenger flow statistics of various types of business trips under different attributes

[0169]

[0170] Specifically, in step S234, the proportion of low-altitude travel is predicted for each of the four types of business travel: high-speed rail business class, high-speed rail non-business class, first class, and non-first class. For example, as shown in Table 14, the predicted low-altitude proportion for each type of business travel under different attributes is provided for this embodiment of the present invention.

[0171] Table 14 Predicted values of low-altitude ratios for various types of business trips under different attributes

[0172]

[0173] Specifically, in step S235, the total passenger flow forecast value of low-altitude business travel can be obtained by multiplying the passenger flow of each type of business travel under different attributes by the low-altitude proportion of each type of business travel under different attributes.

[0174] In a specific embodiment, step S24 specifically includes:

[0175] Step S241: Filter residential areas of high-net-worth individuals and calculate the total passenger flow of the high-net-worth individuals during the morning peak hours based on traffic data;

[0176] Step S242: Compare the time utility, cost utility, and comfort utility of the first means of transportation and low-altitude commuting, and construct a low-altitude commuting selection probability function;

[0177] Step S243: Calculate the commuting volume of the high-net-worth population based on the regular commuting passenger flow ratio and the total passenger flow of the high-net-worth population during the morning peak;

[0178] Step S244: Generate low-altitude commuting passenger flow at different commuting distances based on the commuting volume of the high-net-worth population and the low-altitude commuting selection probability function.

[0179] Specifically, in step S241, based on the prediction of the single cost of low-altitude travel, it can be concluded that the cost of low-altitude travel is 3-5 times that of a regular taxi. Therefore, the embodiment of the present invention determines that the main target of the potential passenger flow for low-altitude commuting is mainly high-net-worth individuals.

[0180] Secondly, we can use web crawlers to obtain POI data for high-net-worth individuals' residential areas. For example, we can filter for "unit price > 80,000 yuan" and "community name" containing "villa" or "property type" to identify high-net-worth individuals' residential areas. If the obtained data contains "total number of houses," we count the number of households; otherwise, we calculate the actual number of high-net-worth individuals living in these areas by calculating the total number of houses = building area * volume ratio / housing area.

[0181] Then, based on the actual number of residents of the high-net-worth group, according to the "Traffic Travel Rate", it can be calculated that the morning peak travel rate of residential (large-sized) is 0.96 / household, and the evening peak travel rate is 0.88 / household. In the embodiment of the present invention, taking the morning peak as an example, the total passenger flow of the high-net-worth group during the morning peak is determined to be S.

[0182] Specifically, in step S242, through analysis and research, it is found that the commuting distance of more than 90% of the groups is mainly concentrated within 40 km. Therefore, the embodiment of the present invention uses 40 km as the upper limit as the research range of travel distance.

[0183] Specifically, in step S242, first, taking a car as the first means of transportation as an example, the car commuting utility function V is constructed from the three aspects of travel time, travel cost, and comfort. car , the specific formula is as follows:

[0184] V car =a1T car +a2F car +a3C car ;

[0185] Where, T car is the utility of car commuting time; F car is the cost utility of car commuting; C car is the comfort utility of car commuting; a1, a2, and a3 are the importance coefficients of the corresponding utility functions.

[0186] Furthermore, the time utility of car commuting and low-altitude commuting is quantified, and the time utility function of low-altitude commuting is clarified. For example, the travel time of cars and airplanes is compared. Here, the driving speed of cars in cities is 35km / h, and the flying speed of low-altitude is 180km / h. In addition, cars can achieve point-to-point travel, while the location of low-altitude take-off and landing facilities needs to consider factors such as topography, airspace clearance, etc. Therefore, it is assumed that the walking time between the starting point and the destination is 10 minutes. Therefore, a comparison chart of the travel utility function of car commuting and low-altitude commuting can be obtained. See Figure 3 , is a time utility function comparison diagram of car commuting and low-altitude commuting provided by an embodiment of the present invention. Figure 3As shown, the line graph of "Time Functions" shows the changes in travel time for cars (Car) and low-altitude commuting (UAM, Urban Air Mobility) at different travel distances. Among them, the horizontal axis represents the travel distance (distance), the unit is km, ranging from 0 to 40, and the vertical axis represents the travel time (Time). The time data is normalized, so the range is from 0 to 1.0. It can be seen that as the distance increases, the travel time of cars increases relatively quickly, especially after the distance exceeds 20km, the downward trend of time is more obvious, indicating that distance has a greater impact on car travel time. Low-altitude travel is relatively less affected by distance. When the travel distance is 15km, the travel time of cars and low-altitude commuting is basically the same. Therefore, according to the comparative analysis of the specific implementation situation, it is assumed that the travel time utility function of low-altitude commuting is T UAM .

[0187] Furthermore, the cost functions of car commuting and low-altitude commuting are quantified. Generally, the cost utility is an exponential function of the travel distance. As the distance increases, the utility of the travel cost gradually decreases. Compare the travel functions of low-altitude and car commuting. Figure 4 , Figure 4 This is a cost-effectiveness comparison chart of car commuting and low-altitude commuting provided by an embodiment of the present invention. Figure 4 This figure shows how travel costs vary with distance for car commuting and low-altitude commuting. The horizontal axis represents distance (distance), ranging from 0 km to 40 lm, and the vertical axis represents money (money). Travel costs are normalized so that they range from 0 to 1.0. The broken line (Money Function (Base 0.9)) represents the car travel cost function. As travel distance increases, costs gradually decrease, and the curve declines relatively gently. The broken line (Money Function (Base 0.8)) represents the low-altitude travel cost function. Costs also decrease with distance, but the rate of decrease is greater than that of car travel, meaning that costs decrease more rapidly with distance. This indicates that for both modes of transportation, the longer the distance, the lower the travel cost per unit distance. Furthermore, for the same travel distance, the cost of low-altitude travel is consistently higher than that of car travel.

[0188] By comparing the benefits of car and airplane travel costs, where the car travel cost is calculated based on the price of a private car, the utility function F of the low-altitude travel cost in this embodiment of the present invention is: UAM as follows:

[0189] F UAM =(α*D / v car -β*D / v UAM )*Fper +F car ;

[0190] Where D is the travel distance, α and β are the time value coefficients, and v car 、v UAM is the speed of car commuting / travel and low-altitude commuting / travel, F per is the unit time value of high net worth individuals, F car is the cost-utility function of car commuting. In the embodiment of the present invention, it is assumed that the low-altitude commuting cost is twice the car commuting cost.

[0191] It should be noted that F per =C / T;

[0192] Wherein, C is the annual salary. Studies have shown that the annual income of high-net-worth individuals is more than 1 million yuan. Therefore, the embodiment of the present invention assumes that the annual income of high-net-worth individuals is more than 1 million yuan, and the unit time cost is 520 yuan; T is the average working time per person, T = (365-104-20) × 8 = 1928h, that is, a year has 365 days, 52 weeks, 2 days off per week, and other holidays totaling 20 days, and each working day lasts 8 hours.

[0193] Furthermore, the travel comfort function is quantified. Figure 5 , Figure 5 This is a comparison chart of the comfort and utility of car commuting and low-altitude commuting provided by an embodiment of the present invention. Figure 5 As shown in the figure, the comfort level of traveling by car and airplane is compared. The comfort level of traveling by car is gamma distributed. It increases or decreases with the travel distance. For example, within 3 km, non-motorized vehicles are more restricted. When the travel distance is 12 km, the travel comfort level reaches the highest. When the travel distance exceeds 15 km, the travel comfort level drops sharply. The comfort level function of low-altitude travel is C. UAM According to the logistic model, when the total travel distance is less than 40 km, the comfort level always increases gradually with the increase of travel distance, mainly because it is more suitable for long-distance passenger transport.

[0194] In an optional embodiment, in step S242, the constructed low-altitude commuting selection probability function is P UAM :

[0195] P UAM =1 / [1+exp[V car -V UAM );

[0196] P car =1 / [1+exp[-V car +V UAM );

[0197] Where, P car is the probability of choosing car commuting, P UAM is the probability of choosing low-altitude commuting, V car is the utility function of car commuting, V UAM is the utility function of low-altitude commuting.

[0198] Among them, V UAM =b1T UAM +b2F UAM +b3C UAM ;

[0199] b1, b2, and b3 are the importance coefficients of the low-altitude commuting time utility function, the low-altitude commuting cost utility function, and the low-altitude commuting comfort utility function, respectively, which can be set to 3, 1, and 2, because travel time is most important to high-net-worth individuals, followed by comfort, and they are relatively less sensitive to costs.

[0200] See also Figure 6 , Figure 6 A comparison chart of the selection probabilities of car commuting and low-altitude commuting provided in an embodiment of the present invention. Figure 6 This figure shows the changing probability of people choosing a car and Urban Air Mobility (UAM) for different travel distances. The horizontal axis (distance) ranges from 0km to 40km, while the vertical axis represents the probability of choosing a travel mode (probability), ranging from 0 to 1.0. The figure shows how the probability of choosing a car varies with distance. As distance increases, the probability of choosing a car initially increases, peaking at around 10km, and then gradually decreases. The probability of choosing UAM gradually increases with distance, exceeding the probability of choosing a car after a distance of around 15km.

[0201] Specifically, in step S243, based on the urban work-residence relationship, the proportion of commuting passenger flow at different commuting distances can be calculated, so that the commuting volume of high-net-worth individuals is equal to the total passenger flow S of high-net-worth individuals during the morning peak period * the proportion of regular commuting passenger flow, as shown in Table 15:

[0202] Table 15: Regular commuting passenger flow ratio and high net worth individual commuting volume at different commuting distances

[0203] distance Regular commuting passenger flow ratio Commuting volume of high net worth individuals 0-5 <![CDATA[P5]]> <![CDATA[S*P5]]> 5-10 <![CDATA[P 10 ]]> <![CDATA[S*P 10 ]]> 10-15 <![CDATA[P 15 ]]> <![CDATA[S*P 15 ]]> …… 35-40 <![CDATA[P 40 ]]> <![CDATA[S*P 40 ]]>

[0204] Specifically, in step S244, the low-altitude commuter passenger flow S is calculated based on the selected utility function using the following formula: UAM :

[0205]

[0206] Where S is the total passenger flow of high-net-worth individuals during the morning peak; P i is the proportion of regular commuting passengers with commuting distance i; is the proportion of passenger flow that chooses low-altitude commuting when the commuting distance is i.

[0207] In summary, see Figure 7 , Figure 7 This is another flow chart of a low-altitude passenger flow prediction method provided by an embodiment of the present invention. Figure 7 As shown, a low-altitude passenger flow prediction method provided by an embodiment of the present invention is mainly used to predict four types of low-altitude passenger flows, namely, low-altitude rescue, low-altitude cultural tourism, low-altitude business, and low-altitude commuting. Among them, with respect to the prediction of low-altitude rescue passenger flow, first determine which illnesses are time-sensitive illnesses that require low-altitude emergency rescue, then grasp the location of the hospital and the high-incidence areas of emergency treatment, conduct a timeliness analysis on the hospital, and predict the proportion of those who choose low-altitude rescue according to different circles and prices, and finally calculate the total predicted value of low-altitude rescue passenger flow. With respect to the prediction of low-altitude cultural passenger flow, first clarify the starting and ending points of the trip (such as hubs, scenic spots, hotels, etc.), then determine the travel chain (such as different itinerary modes such as one-day tours and multi-day tours) and the total passenger flow and proportion of each chain, conduct a timeliness analysis on the starting and ending points, divide them into different timeliness circles, and combine different circles and prices to predict the proportion of those who choose low-altitude travel, and calculate the total predicted value of low-altitude cultural passenger flow. For forecasting low-altitude business passenger traffic, we first need to determine the daily passenger volume arriving and departing from external hubs, understand the proportion of first-class seats at airports and the proportion of business seats on high-speed trains, and then analyze the passenger flow ratios in different regions, time periods, and durations. It is best to predict the proportion of low-altitude travel by scenario, and calculate the total forecast value of low-altitude business passenger traffic. For forecasting low-altitude commuter passenger traffic, we first determine the location of high-net-worth individuals and measure their total travel volume during the morning peak. We then construct a utility function based on travel time, cost, and comfort. We then construct a probability function for low-altitude commuting. Based on different commuting distances, we predict the proportion of low-altitude commuting choices and calculate the total forecast value of low-altitude commuter passenger traffic.

[0208] The embodiment of the present invention focuses on the main core elements and the differences in users' travel purposes, and divides low-altitude passenger flow into four categories: low-altitude rescue, low-altitude cultural tourism, low-altitude business, and low-altitude commuting. It improves the fixed attraction model of the traditional four-stage method, establishes the correlation between the selection ratio of each type of low-altitude and each factor, makes the prediction result more in line with reality, and improves the accuracy of low-altitude passenger flow prediction. At the same time, the present invention has both flexibility and universality, takes into account four travel purposes, and is oriented towards discrete single departure and arrival points. Therefore, this method is not only suitable for low-altitude passenger transport prediction in the entire city, but also can be used for a type of travel scenario, and can also be used for passenger flow demand prediction of single plots such as hospitals, high-speed rail stations, airports, and tourist attractions, with a wider prediction range. The embodiment of the present invention constructs a full-process system from scenario analysis, parameter calibration to result measurement, which can realize the prediction work without calibrating parameters, and only requires simple collection of basic data, and has faster prediction efficiency. In addition, the present invention takes into account that with the development of the low-altitude economy, the maturity of technology gradually improves, the frequency of use increases, and the cost of a single trip gradually decreases. Therefore, the impact of travel cost differences on the probability of low-altitude selection is studied, which can accurately meet the research needs of future dynamic development.

[0209] See also Figure 8 , Figure 8 1 is a structural block diagram of a low-altitude passenger flow prediction system 200 provided in an embodiment of the present invention, wherein the low-altitude passenger flow prediction system 200 includes:

[0210] The data collection module 201 is used to collect raw data of various low-altitude passenger flow types; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting;

[0211] The low-altitude passenger flow prediction module 202 is used to analyze the original data of each low-altitude passenger flow type, determine the low-altitude passenger flow ratio of each low-altitude passenger flow type, and generate a passenger flow prediction value for each low-altitude passenger flow type based on the low-altitude selection ratio;

[0212] The prediction result generating module 203 is used to aggregate the passenger flow prediction values of each low-altitude passenger flow type to obtain a total low-altitude passenger flow prediction value.

[0213] In an optional implementation, the low-altitude passenger flow prediction module 202 includes:

[0214] A low-altitude rescue passenger flow prediction unit 221 is configured to perform a timeliness analysis based on emergency data and emergency hospital locations, determine a low-altitude rescue ratio, and generate a low-altitude rescue passenger flow prediction value based on the low-altitude rescue ratio;

[0215] The low-altitude cultural passenger flow prediction unit 222 is configured to perform timeliness analysis and price analysis based on cultural tourism data and transportation hub locations, determine the proportion of low-altitude cultural passenger flow, and generate a low-altitude cultural passenger flow prediction value based on the proportion of low-altitude cultural passenger flow;

[0216] The low-altitude business passenger flow prediction unit 223 is used to determine the low-altitude proportion of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generate a low-altitude business passenger flow prediction value based on the low-altitude proportion of each type of business trip;

[0217] The low-altitude commuting passenger flow prediction unit 2024 is used to determine the low-altitude commuting selection probability based on the distribution of high-net-worth people and the low-altitude commuting utility function, and generate a low-altitude commuting passenger flow prediction value based on the low-altitude commuting selection probability.

[0218] In an optional implementation manner, the low-altitude rescue passenger flow prediction unit 221 is specifically configured to:

[0219] Based on the number of first aids and the proportion of various illnesses, potential groups for low-altitude rescue are screened, and various high-incidence occasions for first aid are screened based on the potential groups for low-altitude rescue;

[0220] Divide the emergency hospital into multiple time zones according to its location, conduct time zone analysis on various emergency high-incidence areas based on the divided time zones and the distribution of emergency population, and obtain the coverage of emergency hospitals on various emergency high-incidence areas;

[0221] Conduct price elasticity analysis on the potential low-altitude rescue groups, and predict the proportion of low-altitude rescue under different time limits and different prices;

[0222] A low-altitude rescue passenger flow prediction value is generated according to the coverage degree and the low-altitude rescue ratio.

[0223] In an optional implementation manner, the low-altitude passenger flow prediction unit 2022 is specifically configured to:

[0224] Analyze multiple travel routes of cultural and tourism tourists based on cultural and tourism data;

[0225] Calculate the potential passenger flow of low-altitude cultural tourism along each travel route based on cultural tourism data and the psychological characteristics of cultural tourism tourists;

[0226] Divide multiple time zones based on the location of transportation hubs, conduct timeliness and price analysis on each travel route, and obtain the proportion of low-altitude cultural passenger traffic under different prices, different travel routes, and different time zones;

[0227] A low-altitude cultural tourism passenger flow forecast value is generated based on the potential low-altitude cultural tourism passenger flow of each travel route and the proportion of low-altitude cultural tourism passenger flow under different prices, different travel routes and different time zones.

[0228] In an optional implementation, the low-altitude business passenger flow prediction unit 2023 is specifically configured to:

[0229] Extract the proportion of business trips based on the daily passenger volume at the transportation hub;

[0230] Divide passenger flow attributes according to travel location, travel time and arrival time, and predict the proportion of travel flow under different attributes;

[0231] Calculate the passenger flow of each type of business trip under different attributes based on the roadside passenger flow of the transportation hub, the proportion of business trips, and the proportion of passenger flows under different attributes;

[0232] Predict the proportion of low-altitude business trips for each type of business trip under different attributes;

[0233] A low-altitude business passenger flow prediction value is generated based on the travel passenger flow of each type of business trip under the different attributes and the low-altitude business proportion of each type of business trip under the different attributes.

[0234] In an optional implementation manner, the low-altitude commuter passenger flow prediction unit 2024 is specifically configured to:

[0235] Screening residential areas of high-net-worth individuals, and calculating the total passenger flow of the high-net-worth individuals during the morning peak hours based on traffic data;

[0236] Compare the time utility, cost utility, and comfort utility of the first mode of transportation and low-altitude commuting, and construct a probability function for choosing low-altitude commuting;

[0237] Calculate the commuting volume of high-net-worth individuals based on the proportion of regular commuting passenger flow and the total passenger flow of the high-net-worth individuals during the morning peak;

[0238] According to the commuting volume of the high-net-worth population and the low-altitude commuting selection probability function, low-altitude commuting passenger flow at different commuting distances is generated.

[0239] It should be noted that the low-altitude passenger flow prediction system provided in an embodiment of the present invention is used to execute all the process steps of a low-altitude passenger flow prediction method in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0240] See also Figure 9 , Figure 9 is a block diagram of a low-altitude passenger flow prediction device 300 provided in an embodiment of the present invention. The low-altitude passenger flow prediction device 300 includes a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program, the steps of each of the above-mentioned low-altitude passenger flow prediction method embodiments, such as steps S1 to S3, are implemented.

[0241] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the low-altitude passenger flow prediction device 300.

[0242] The low-altitude passenger flow prediction device 300 may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will appreciate that the schematic diagram is merely an example of the low-altitude passenger flow prediction device 300 and does not limit the low-altitude passenger flow prediction device 300. The low-altitude passenger flow prediction device 300 may include more or fewer components than shown in the diagram, or may combine certain components or different components. For example, the low-altitude passenger flow prediction device 300 may also include input and output devices, network access devices, buses, and the like.

[0243] The processor 31 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, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 31 is the control center of the low-altitude passenger flow prediction device 300, and utilizes various interfaces and lines to connect various parts of the entire low-altitude passenger flow prediction device 300.

[0244] The memory 32 can be used to store the computer programs and / or modules. The processor 31 implements the various functions of the low-altitude passenger flow prediction device 300 by running or executing the computer programs and / or modules stored in the memory 32 and accessing the data stored in the memory 32. The memory 32 can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 32 can include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0245] Wherein, if the module / unit integrated in the low-altitude passenger flow prediction device 300 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 31, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0246] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A low-altitude passenger flow prediction method, characterized in that: include: Collecting raw data of various low-altitude passenger flow types; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting; Analyzing the raw data of each low-altitude passenger flow type, determining a low-altitude selection ratio for each low-altitude passenger flow type, and generating a passenger flow prediction value for each low-altitude passenger flow type based on the low-altitude selection ratio; The passenger flow forecast values of each low-altitude passenger flow type are summarized to obtain the total low-altitude passenger flow forecast value.

2. The low-altitude passenger flow prediction method according to claim 1, characterized in that: The analyzing the original data of each low-altitude passenger flow type to determine the low-altitude selection ratio of each low-altitude passenger flow type, and generating the passenger flow prediction value of each low-altitude passenger flow type based on the low-altitude selection ratio, includes: Performing a timeliness analysis based on emergency data and emergency hospital locations to determine a low-altitude rescue ratio, and generating a low-altitude rescue passenger flow forecast based on the low-altitude rescue ratio; Conducting timeliness analysis and price analysis based on cultural tourism data and transportation hub locations to determine the proportion of low-altitude cultural passenger traffic, and generating a low-altitude cultural passenger traffic forecast based on the proportion of low-altitude cultural passenger traffic; Determining the low-altitude proportion of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generating a low-altitude business passenger flow forecast value based on the low-altitude proportion of each type of business trip; Based on the distribution of high-net-worth individuals and the low-altitude commuting utility function, the low-altitude commuting selection probability is determined, and a low-altitude commuting passenger flow prediction value is generated based on the low-altitude commuting selection probability.

3. The low-altitude passenger flow prediction method according to claim 1, wherein: The timeliness analysis based on the emergency data and the location of the emergency hospital is performed to determine the low-altitude rescue ratio, and a low-altitude rescue passenger flow prediction value is generated based on the low-altitude rescue ratio, including: Based on the number of first aids and the proportion of various illnesses, potential groups for low-altitude rescue are screened, and various high-incidence occasions for first aid are screened based on the potential groups for low-altitude rescue; Divide the emergency hospital into multiple time zones according to its location, conduct time zone analysis on various emergency high-incidence areas based on the divided time zones and the distribution of emergency population, and obtain the coverage of emergency hospitals on various emergency high-incidence areas; Conduct price elasticity analysis on the potential low-altitude rescue groups, and predict the proportion of low-altitude rescue under different time limits and different prices; A low-altitude rescue passenger flow prediction value is generated according to the coverage degree and the low-altitude rescue ratio.

4. The low-altitude passenger flow prediction method according to claim 1, wherein: The timeliness analysis and price analysis based on the cultural tourism data and the location of the transportation hub are performed to determine the proportion of low-altitude cultural passenger flow, and a low-altitude cultural passenger flow forecast value is generated based on the proportion of low-altitude cultural passenger flow, including: Analyze multiple travel routes of cultural and tourism tourists based on cultural and tourism data; Calculate the potential low-altitude cultural tourism passenger flow along each travel route based on cultural tourism data and the psychological characteristics of cultural tourism tourists; Divide the transportation hub into multiple time zones, conduct timeliness and price analysis on each travel route, and obtain the proportion of low-altitude cultural passenger traffic under different prices, different travel routes, and different time zones; A low-altitude cultural tourism passenger flow forecast value is generated based on the potential low-altitude cultural tourism passenger flow of each travel route and the proportion of low-altitude cultural tourism passenger flow under different prices, different travel routes and different time zones.

5. The low-altitude passenger flow prediction method according to claim 4, characterized in that: The above method calculates the potential passenger flow of low-altitude cultural tourism along each travel route based on cultural tourism data and the psychological characteristics of cultural tourism tourists, including: According to the number of scenic spots and the psychological characteristics of cultural tourists, the proportion of cultural tourists on each travel route is calculated; Calculate the cultural tourism flow of each travel route based on the total amount of urban cultural tourism and the proportion of cultural tourism flow; Based on cultural and tourism data, extract the proportion of low-altitude cultural and tourism potential passenger flow for each travel route; According to the cultural and tourism passenger flow of each travel route and the ratio of the low-altitude cultural and tourism potential passenger flow, the low-altitude cultural and tourism potential passenger flow of each travel route is calculated.

6. The low-altitude passenger flow prediction method according to claim 1, characterized in that: The method of determining the low-altitude proportion of each type of business trip based on the passenger volume and passenger flow attributes of the transportation hub, and generating a low-altitude business passenger flow prediction value based on the low-altitude proportion of each type of business trip, includes: Extract the proportion of business trips based on the daily passenger volume at the transportation hub; Divide passenger flow attributes according to travel location, travel time and arrival time, and predict the proportion of travel flow under different attributes; Calculate the passenger flow of each type of business trip under different attributes based on the roadside passenger flow of the transportation hub, the proportion of business trips, and the proportion of passenger flows under different attributes; Predict the proportion of low-altitude business trips for each type of business trip under different attributes; A low-altitude business passenger flow prediction value is generated based on the travel passenger flow of each type of business trip under the different attributes and the low-altitude business proportion of each type of business trip under the different attributes.

7. The low-altitude passenger flow prediction method according to claim 1, wherein: The method of determining the low-altitude commuting selection probability based on the distribution of high-net-worth individuals and the low-altitude commuting utility function, and generating a low-altitude commuting passenger flow prediction value based on the low-altitude commuting selection probability, includes: Screening residential areas of high-net-worth individuals, and calculating the total passenger flow of the high-net-worth individuals during the morning peak hours based on traffic data; Compare the time utility, cost utility, and comfort utility of the first mode of transportation and low-altitude commuting, and construct a probability function for choosing low-altitude commuting; Calculate the commuting volume of high-net-worth individuals based on the proportion of regular commuting passenger flow and the total passenger flow of the high-net-worth individuals during the morning peak; According to the commuting volume of the high-net-worth population and the low-altitude commuting selection probability function, low-altitude commuting passenger flow at different commuting distances is generated.

8. The low-altitude passenger flow prediction method according to claim 7, characterized in that: The low-altitude commuting selection probability function is P UAM : P UAM =1 / [1+exp[V car -V UAM ); In UAM =b1T UAM +b2F UAM +b3C UAM ; Among them, V car is the commuting utility function of the first means of transportation, V UAM is the utility function of low-altitude commuting, T UAM 、F UAM 、C UAM are the low-altitude commuting time utility function, low-altitude commuting cost utility function and low-altitude commuting comfort utility function respectively, b1, b2 and b3 are the importance coefficients of the low-altitude commuting time utility function, low-altitude commuting cost utility function and low-altitude commuting comfort utility function respectively; The utility function of low-altitude commuting cost is: F UAM =(α*D / v car -β*D / v UAM )*F per +F car ; D is the travel distance, α, β are the time value coefficients, v car 、v UAM The speed of the first mode of transport commuting and low-altitude commuting, F per is the unit time value of high net worth individuals, F car is the cost utility function of commuting using the first means of transportation.

9. A low-altitude passenger flow prediction system, characterized in that: include: A data collection module is used to collect raw data of various low-altitude passenger flow types; wherein the low-altitude passenger flow types include low-altitude rescue, low-altitude cultural tourism, low-altitude business and low-altitude commuting; A low-altitude passenger flow prediction module is used to analyze the original data of each low-altitude passenger flow type, determine the low-altitude passenger flow ratio of each low-altitude passenger flow type, and generate a passenger flow prediction value for each low-altitude passenger flow type based on the low-altitude selection ratio; The prediction result generation module is used to summarize the passenger flow prediction values of each low-altitude passenger flow type to obtain the total low-altitude passenger flow prediction value.

10. A low-altitude passenger flow prediction device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the low-altitude passenger flow prediction method according to any one of claims 1 to 8 is implemented.

Images