Urban rail transit passenger volume prediction method, device and equipment

Abstract

The invention provides an urban rail transit passenger volume prediction method, device and equipment, and the method comprises the steps: obtaining the historical daily passenger volume, the maximum temperature, the minimum temperature, the wind level and the weather condition of the rail transit of a target city, and the maximum temperature, the minimum temperature, the wind level and the weather condition of the future date; converting the historical daily wind level into numerical data to obtain first data; converting the historical daily weather condition into numerical data to obtain second data; obtaining a historical daily weather comfort index based on the historical daily highest temperature, the minimum temperature, the first data and the second data; obtaining a historical daily unhooking evaluation index based on the historical daily weather comfort index and the passenger volume; and based on the historical daily unhooking evaluation index, the highest temperature, the lowest temperature, the wind level and the weather condition of the future date, predicting the passenger volume of the future date. According to the invention, the passenger volume of the urban rail transit can be predicted more accurately.

Description

Technical Field

[0001] The present application belongs to the technical field of rail transit prediction, and in particular to a method, device and equipment for predicting passenger volume of urban rail transit. Background Art

[0002] Weather changes have a close impact on traffic volume. When the weather changes, people will adopt different modes of transportation to meet their transportation needs. For example, on rainy and snowy days, some people who originally traveled by bicycle or electric vehicle will choose to drive or take urban public transportation. Because cars are exposed to the natural environment on the road, they are subject to the influence of the natural environment. In rainy and snowy weather, the roads will become more congested than usual. During the rush hour on weekdays, if the city has rail transit, people will choose rail transit. This is because most rail transit is built underground, and rainy and snowy weather has little impact on rail transit travel. However, rainy and snowy weather will lead to an increase in rail transit travel, which often puts pressure on rail transit operations.

[0003] In the current research on the impact of weather on urban rail transit travel, the focus is mainly on statistical analysis based on historical weather conditions and urban rail transit passenger volume, and with the development of big data technology, continuous data mining and the introduction of new models to predict future urban rail transit passenger volume, but the current passenger volume prediction methods have obvious problems. For example: when predicting rail transit passenger volume, regional factors are not considered; when analyzing weather historical data to predict passenger volume, only a certain meteorological analysis is relied on. For example, on rainy days, the impact of rain itself on passenger volume prediction is considered, but the impact of meteorological level (how much rainfall) on passenger volume is not considered, which causes deviations in the prediction results, thereby affecting the reasonable scheduling and allocation of public resources by rail transit operating departments. Summary of the invention

[0004] The embodiments of the present application provide a method, device and apparatus for predicting the passenger volume of urban rail transit, so as to more accurately predict the passenger volume of urban rail transit.

[0005] This application is implemented through the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for predicting passenger volume of urban rail transit, comprising:

[0007] Obtain the target city's rail transit daily passenger volume, daily maximum temperature, daily minimum temperature, daily wind level, daily weather conditions, as well as the maximum temperature of a future date, the minimum temperature of a future date, the wind level of a future date, and the weather conditions of a future date.

[0008] The historical daily wind level is converted into numerical data to obtain the first data; the historical daily weather conditions are converted into numerical data to obtain the second data.

[0009] Based on the historical daily maximum temperature, the historical daily minimum temperature, the first data and the second data, the historical daily weather comfort index is obtained.

[0010] Based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, the historical daily decoupling evaluation index is obtained.

[0011] Based on the historical daily decoupling evaluation index, the maximum temperature of the future date, the minimum temperature of the future date, the wind level of the future date and the weather conditions of the future date, the passenger volume of the target city's rail transit on the future date is predicted.

[0012] In a second aspect, an embodiment of the present application provides a device for predicting passenger volume of urban rail transit, comprising:

[0013] The data acquisition module is used to obtain the target city's rail transit historical daily passenger volume, historical daily maximum temperature, historical daily minimum temperature, historical daily wind level, historical daily weather conditions, as well as the maximum temperature of a future date, the minimum temperature of a future date, the wind level of a future date, and the weather conditions of a future date.

[0014] The data conversion module is used to convert the historical daily wind level into numerical data to obtain the first data; and convert the historical daily weather conditions into numerical data to obtain the second data.

[0015] The first operation module is used to obtain a historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data and the second data.

[0016] The second operation module is used to obtain a historical daily decoupling evaluation index based on the historical daily weather comfort index and the historical daily passenger volume of rail transit.

[0017] The result output module is used to predict the passenger volume of the target city rail transit on a future date based on the historical daily decoupling evaluation index, the maximum temperature on a future date, the minimum temperature on a future date, the wind level on a future date, and the weather conditions on a future date.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, the memory being used to store a computer program, and when the processor executes the computer program, the method for predicting the passenger volume of urban rail transit as described in any one of the first aspects is implemented.

[0019] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0020] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0021] The present application establishes a weather comfort index through the historical daily maximum temperature, the historical daily minimum temperature, the historical daily wind level and the historical daily weather conditions, and links the weather comfort index with the passenger volume to obtain a decoupling evaluation index. The application uses the local historical daily decoupling evaluation index, the maximum temperature, the minimum temperature, the wind level and the weather conditions of future dates to predict the passenger volume of future dates. It comprehensively considers factors such as temperature, wind level and weather conditions, avoids the traditional method of only considering weather conditions, and can more accurately predict the passenger volume. In addition, it abandons the traditional method of using time series models, artificial neural network models and machine learning models to predict passenger volume, and instead considers the decoupling relationship between the local historical daily weather comfort index and passenger volume. Using the decoupling relationship for prediction can better adapt to local conditions and obtain passenger volume prediction results with more local characteristics.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0024] Figure 1 It is a flow chart of a method for predicting the passenger volume of urban rail transit provided in one embodiment of the present application;

[0025] Figure 2 It is a structural schematic diagram of a device for predicting passenger volume of urban rail transit provided in one embodiment of the present application;

[0026] Figure 3 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] At present, regional factors are not taken into account when considering the prediction of rail transit travel volume; when analyzing historical weather data for prediction, only a certain meteorological analysis is relied upon. For example, when considering rainy days, the impact of rain itself on passenger volume is considered, but the impact of meteorological level on passenger volume is not considered. At that time, the predicted results will be biased, which will affect the rail transit operation department's reasonable scheduling and allocation of public resources.

[0034] Based on the above problems, the embodiment of the present application provides a method for predicting urban rail transit passenger volume. In addition to considering the influence of temperature, wind level and weather conditions, it also takes into account the impact of the latitude of the target city (climate changes in different regions) on passenger volume, thereby improving the accuracy of passenger volume prediction and obtaining more accurate passenger volume prediction results, thereby providing a certain data basis for local rail transit departments, facilitating staff to make real-time adjustments to rail transit operations based on different predicted passenger volumes, thereby reducing waste of resources and saving resources.

[0035] Figure 1 is a schematic diagram of the process of predicting the passenger volume of urban rail transit provided by an embodiment of the present application, with reference to Figure 1 , the detailed description of the urban rail transit passenger volume prediction method is as follows:

[0036] Step 101, obtaining the target city's rail transit daily passenger volume, daily maximum temperature, daily minimum temperature, daily wind level, daily weather conditions, as well as the maximum temperature of a future date, the minimum temperature of a future date, the wind level of a future date, and the weather conditions of a future date.

[0037] Specifically, weather conditions refer to sunny days, light rain, showers, light snow, heavy snow, etc. Wind level means no wind, soft wind, light wind, breeze, etc.

[0038] Step 102, converting the historical daily wind level into numerical data to obtain first data; converting the historical daily weather conditions into numerical data to obtain second data.

[0039] Specifically, the wind level can be converted into numerical data through Table 1. The specific process includes: determining the corresponding wind speed range through the wind level, and randomly selecting a number in the wind speed range as the first data.

[0040] The historical daily wind level corresponds to a wind speed range, so there is a corresponding first data for each day in history.

[0041] Table 1

[0042]

[0043] Specifically, the weather conditions can be converted into numerical data through Table 2 and Table 3. The specific process includes: determining the corresponding precipitation level through the weather conditions; and randomly selecting a number in the precipitation range in the precipitation level as the second data.

[0044] The historical daily weather conditions all correspond to a precipitation range, so there is a corresponding second data for the historical daily weather conditions.

[0045] Table 2

[0046]

[0047]

[0048] Table 3

[0049]

[0050] Specifically, for example, when the wind level on A day in A month in A year is a breeze and the weather condition is a blizzard, the corresponding first data is any one between 3.4 and 5.4, and the corresponding second data is any one between 10.0 and 19.9.

[0051] Step 103, obtaining a historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data and the second data.

[0052] Exemplarily, step 103 may include:

[0053] Based on the historical daily maximum temperature, the historical daily minimum temperature and the first data, combined with the second formula, the historical daily clothing index is obtained.

[0054] The historical daily maximum temperature, historical daily minimum temperature, first data, second data and historical daily clothing index are standardized by the range standardization method.

[0055] The entropy method is used to calculate the proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the historical daily clothing index.

[0056] Based on the standardized proportion and weight of the historical daily maximum temperature, the standardized proportion and weight of the historical daily minimum temperature, the standardized proportion and weight of the first data, the standardized proportion and weight of the second data, and the standardized proportion and weight of the historical daily clothing index, combined with the third formula, the historical daily weather comfort index is obtained.

[0057] The second formula can be:

[0058]

[0059] Among them, P i5 represents the clothing index of the i-th day, T max Indicates the maximum value of the historical daily maximum temperature, T i ave represents the average temperature of the i-th day, which is equal to the average of the highest and lowest temperatures of the i-th day. H represents 75% of the human metabolic rate, R represents the solar constant, and α i represents the solar altitude angle on the i-th day, v i represents the first data of the i-th day;

[0060] Specifically, the calculation of the clothing index incorporates the latitude of the target city and comprehensively considers climate change in different regions, which can ensure the accuracy of the subsequent calculation of the weather comfort index, and then ensure the accuracy of the decoupling relationship between the weather comfort index and passenger volume, and finally ensure the accuracy of the predicted passenger volume.

[0061] Specifically, the value of H can be 87W / m 2 , the value of R can be 1357W / m 2 , assuming that the latitude of the research area is β, the solar altitude angle α in spring and autumn is 90°-β, the solar altitude angle α in summer is 90°-β+23°26′, and the solar altitude angle α in winter is 90°-β-23°26′.

[0062] The third formula can be:

[0063] C i =W1P i1 +W2P i2 +W3P i3 +W4P i4 +W5P i5

[0064] Among them, C i represents the weather comfort index of the i-th day, P i1 represents the weight of the highest temperature on the ith day after standardization, W1 represents the weight of the highest daily temperature after standardization, P i2 represents the weight of the lowest temperature on the ith day after standardization, W2 represents the weight of the lowest daily temperature after standardization, and P i3 represents the proportion of the first data of the i-th day after the standardization process, W3 represents the weight of the first data after the standardization process, and P i4 represents the proportion of the second data of the i-th day after the standardization process, W4 represents the weight of the second data after the standardization process, and P i5W5 represents the weight of the clothing index of the i-th day after standardization, and W6 represents the weight of the historical daily clothing index after standardization.

[0065] Specifically, the weather comfort index calculation formula of this solution also incorporates the clothing index, so that the calculated weather comfort index is more accurate and can more accurately reflect the decoupling state between weather comfort and passenger volume.

[0066] Specifically, standardizing the historical daily maximum temperature, the historical daily minimum temperature, the first data, and the second data by using the range standardization method may include:

[0067] The historical daily maximum temperature, historical daily minimum temperature, first data, second data and historical clothing index are all used as an indicator, and the historical date is used as the sample number to establish a matrix There are a total of m samples in the matrix X, and each sample contains 5 indicators.

[0068]

[0069] Among them, X i1 represents the maximum temperature on the i-th day after standardization, x m1 Represents the maximum temperature on the mth day.

[0070]

[0071] Among them, X i2 represents the minimum temperature of the i-th day after standardization, x m2 Indicates the minimum temperature on the mth day.

[0072]

[0073] Among them, X i3 represents the first data of the i-th day after standardization, x m3 Indicates the first data of the mth day.

[0074]

[0075] Among them, X i4 represents the second data of the i-th day after standardization, x m4 Indicates the second data of the mth day.

[0076]

[0077] Among them, X i5 represents the clothing index of the i-th day after standardization, x m5 Represents the clothing index on the mth day.

[0078] Specifically, in order to make the weights and proportions of subsequent calculations more accurate in calculating the weather comfort index, it is necessary to eliminate the dimensional differences of the acquired data to avoid the influence of the value of the data itself on its proportion in the calculation process of the weather comfort index, resulting in inaccurate calculation of the final data and failure to achieve the purpose of accurately predicting passenger volume.

[0079] Exemplarily, calculating the proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the standardized historical daily clothing index respectively by the entropy method may include:

[0080] The entropy method is used to calculate the proportion of the standardized historical daily maximum temperature and the weight of the standardized historical daily maximum temperature.

[0081] The entropy method is used to calculate the proportion of the standardized historical daily minimum temperature and the weight of the standardized historical daily minimum temperature.

[0082] The proportion of the first data after the standardization process is calculated by the entropy method, and the weight of the first data after the standardization process is calculated.

[0083] The proportion of the second data after the standardization process is calculated by the entropy method, and the weight of the second data after the standardization process is calculated.

[0084] By using the entropy method, the proportion of the standardized historical daily clothing index is calculated, and the weight of the standardized historical daily clothing index is calculated.

[0085] Exemplarily, calculating the proportion of the standardized historical daily maximum temperature by the entropy method may include:

[0086] The entropy method is used in combination with the seventh formula to calculate the proportion of the standardized historical daily maximum temperature.

[0087] The seventh formula can be:

[0088]

[0089] Among them, P i1 represents the proportion of the highest temperature on the i-th day after standardization, X i1 It represents the maximum temperature of the i-th day after standardization, and m is the number of historical days.

[0090] The weight of the standardized historical daily maximum temperature is calculated by the entropy method, which can include:

[0091] The entropy method is combined with the eighth formula to calculate the weight of the standardized historical daily maximum temperature.

[0092] The eighth formula can be:

[0093]

[0094] Among them, W1 represents the weight of the historical daily maximum temperature after standardization.

[0095] By using the entropy method, the proportion of the standardized historical daily minimum temperature can be calculated, which can include:

[0096] By using the entropy method and combining the ninth formula, the proportion of the standardized historical daily minimum temperature is calculated;

[0097] The ninth formula can be:

[0098]

[0099] Among them, P i2 represents the proportion of the lowest temperature on the ith day after standardization, X i2 represents the minimum temperature on the i-th day after normalization.

[0100] The weight of the historical daily minimum temperature after standardization is calculated by the entropy method, which can include:

[0101] The entropy method is combined with the tenth formula to calculate the weight of the standardized historical daily minimum temperature.

[0102] The tenth formula can be:

[0103]

[0104] Among them, W2 represents the weight of the historical daily minimum temperature after standardization.

[0105] Calculating the proportion of the first data after the standardization process by the entropy method may include:

[0106] The entropy method is combined with the eleventh formula to calculate the proportion of the first data after the standardized processing.

[0107] The eleventh formula can be:

[0108]

[0109] Among them, P i3 represents the proportion of the first data of the i-th day after standardization, X i3 Represents the first data of the i-th day after normalization.

[0110] Calculating the weight of the first data after the standardization process by the entropy method may include:

[0111] The weight of the first data after the standardization process is calculated by the entropy method in combination with the twelfth formula.

[0112] The twelfth formula can be:

[0113]

[0114] Wherein, W3 represents the weight of the first data after the normalization process.

[0115] Calculating the proportion of the second data after the standardization process by the entropy method may include:

[0116] The entropy method is combined with the thirteenth formula to calculate the proportion of the second data after the standardization process.

[0117] The thirteenth formula can be:

[0118]

[0119] Among them, P i4 represents the proportion of the second data of the i-th day after standardization, X i4 Represents the second data of the i-th day after normalization.

[0120] Calculating the weight of the second data after the standardization process by the entropy method may include:

[0121] The entropy method is combined with the fourteenth formula to calculate the weight of the second data after the standardization process.

[0122] The fourteenth formula can be:

[0123]

[0124] Wherein, W4 represents the weight of the first data after the normalization process.

[0125] By using the entropy method, the proportion of the standardized historical daily clothing index can be calculated, which can include:

[0126] By using the entropy method and combining it with the fifteenth formula, the weight of the standardized historical daily clothing index is calculated.

[0127] The fifteenth formula can be:

[0128]

[0129] Among them, P i5 represents the weight of the clothing index on the i-th day after standardization, X i5Represents the clothing index of the i-th day after standardized processing.

[0130] By using the entropy method, the weight of the standardized historical daily clothing index can be calculated, which can include:

[0131] The entropy method is combined with the sixteenth formula to calculate the weight of the standardized historical daily clothing index.

[0132] The sixteenth formula can be:

[0133]

[0134] Among them, W5 represents the weight of the historical daily clothing index after standardization.

[0135] Step 104, based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, obtain the historical daily decoupling evaluation index.

[0136] Exemplarily, step 104 may include:

[0137] Based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, combined with the first formula, the historical daily decoupling evaluation index is obtained.

[0138] The first formula can be:

[0139]

[0140] Among them, DI i represents the decoupling evaluation index on the ith day, C i represents the weather comfort index of the i-th day, Q i represents the passenger volume on the i-th day, C i-1 represents the weather comfort index of the i-1th day, Q i-1 represents the passenger volume on the i-1th day.

[0141] Step 105 , predicting the passenger volume of the target city rail transit on a future date based on the historical daily decoupling evaluation index, the maximum temperature on a future date, the minimum temperature on a future date, the wind level on a future date, and the weather conditions on a future date.

[0142] Exemplarily, step 105 may include:

[0143] The weather comfort index for the future date is calculated based on the maximum temperature for the future date, the minimum temperature for the future date, the wind level for the future date, and the weather conditions for the future date.

[0144] Based on the historical daily decoupling evaluation index, the decoupling status of future dates is determined.

[0145] Based on the decoupling status of the future date, the average of the historical daily decoupling evaluation indexes corresponding to the decoupling status that is the same as the decoupling status of the future date in the historical daily decoupling status is calculated to obtain the decoupling evaluation index of the future date.

[0146] Based on the decoupling evaluation index of the future date, the weather comfort index of the future date, the weather comfort index of the preset standard day and the passenger volume of the preset standard day, combined with the fourth formula, the passenger volume of the future date is calculated.

[0147] The fourth formula is:

[0148]

[0149] Among them, Q' represents the passenger volume on the future date, DI' represents the decoupling evaluation index on the future date, C' represents the weather comfort index on the future date, and C X represents the weather comfort index of the preset standard day X, Q X represents the passenger volume of the preset standard day X, and i represents any day in the historical daily period.

[0150] Exemplarily, based on the maximum temperature of the future date, the minimum temperature of the future date, the wind level of the future date, and the weather conditions of the future date, the weather comfort index of the future date is calculated, including:

[0151] The wind level of the future date is converted into numerical data to obtain the third data; the weather conditions of the future date are converted into numerical data to obtain the fourth data.

[0152] Based on the maximum temperature of the future date, the minimum temperature of the future date and the third data, combined with the fifth formula, the clothing index of the future date is calculated.

[0153] The maximum temperature of the future date, the minimum temperature of the future date, the third data, the fourth data and the clothing index of the future date are standardized by the range standardization method.

[0154] Based on the standardized historical daily maximum temperature and the standardized maximum temperature of the future date, a maximum temperature set is obtained; based on the standardized historical daily minimum temperature and the standardized minimum temperature of the future date, a minimum temperature set is obtained; based on the standardized first data and the standardized third data, a first numerical data set is obtained; based on the standardized second data and the standardized fourth data, a second numerical data set is obtained; based on the standardized historical daily clothing index and the standardized clothing index of the future date, a clothing index set is obtained.

[0155] The entropy method is used to calculate the proportion and weight of the standardized maximum temperature of future dates in the maximum temperature set, the proportion and weight of the standardized minimum temperature of future dates in the minimum temperature set, the proportion and weight of the third data of future dates in the first numerical data set, the proportion and weight of the standardized fourth data of future dates in the second numerical data set, and the proportion and weight of the standardized clothing index of future dates in the clothing index set.

[0156] Among them, the principle of calculating the proportion and weight of the standardized maximum temperature of the future date in the above-mentioned maximum temperature set by the entropy method is the same as the principle of calculating the proportion and weight of the standardized historical daily maximum temperature by the entropy method; the principle of calculating the proportion and weight of the standardized minimum temperature of the future date in the above-mentioned minimum temperature set by the entropy method is the same as the principle of calculating the proportion and weight of the standardized historical daily minimum temperature by the entropy method; the principle of calculating the proportion and weight of the third data of the standardized future date in the above-mentioned first numerical data set by the entropy method is the same as the principle of calculating the proportion and weight of the standardized first data by the entropy method; the principle of calculating the proportion and weight of the fourth data of the standardized future date in the above-mentioned second numerical data set by the entropy method is the same as the principle of calculating the proportion and weight of the standardized second data by the entropy method; the principle of calculating the proportion and weight of the standardized future date clothing index in the above-mentioned clothing index set by the entropy method is the same as the principle of calculating the proportion and weight of the standardized historical daily clothing index by the entropy method. The above-mentioned specific process will not be described in detail.

[0157] Based on the standardized proportion and weight of the maximum temperature of the future date, the standardized proportion and weight of the minimum temperature of the future date, the standardized proportion and weight of the third data of the future date, the standardized proportion and weight of the fourth data of the future date, and the standardized proportion and weight of the clothing index of the future date, combined with the sixth formula, the weather comfort index of the future date is calculated.

[0158] The fifth formula is:

[0159]

[0160] Among them, P' i5 represents the clothing index for the future date, T' max Indicates the maximum value of the maximum temperature of the future date and the historical daily maximum temperature, T' averepresents the average temperature of a future date, the average temperature of the future date is equal to the average of the maximum temperature and the minimum temperature of the future date, H represents 75% of the human metabolic rate, R represents the solar constant, α' represents the solar altitude angle of the future date, and v' represents the third data of the future date.

[0161] The sixth formula is:

[0162] C'=W'1P' i1 +W'2P' i2 +W'3P' i3 +W'4P' i4 +W5P' i5

[0163] Among them, C' represents the weather comfort index of the future date, P' i1 represents the proportion of the maximum temperature of the future date after standardization, W'1 represents the weight of the maximum temperature set after standardization, P' i2 represents the weight of the minimum temperature of the future date after standardization, W'2 represents the weight of the minimum temperature set after standardization, P' i3 represents the weight of the third data of the future date after standardization, W'3 represents the weight of the first numerical data set after standardization, P' i4 represents the weight of the fourth data of the future date after standardization, W'4 represents the weight of the second numerical data set after standardization, P' i5 W5 represents the weight of the clothing index of the future date after standardization, and W6 represents the weight of the clothing index set after standardization.

[0164] Exemplarily, based on the historical daily decoupling evaluation index, determining the decoupling status of a future date includes:

[0165] Based on the historical daily decoupling evaluation index, the historical daily decoupling status is determined.

[0166] Statistics are collected on the historical daily decoupling status to determine the probabilities of different decoupling states on each working day and the probabilities of different decoupling states on each holiday.

[0167] According to the future date, determine which working day the future date is; and determine the decoupling state of the future date according to the maximum value of the probabilities of different decoupling states on the working day.

[0168] Alternatively, determine which holiday the future date is; and determine the decoupling state of the future date based on the maximum value of the probabilities of different decoupling states of the holiday.

[0169] Specifically, in order to facilitate understanding of the step of determining the decoupling status of a future date, the following embodiment is shown. In combination with Table 4, the decoupling status of the i-th day can be obtained according to the decoupling evaluation index of the i-th day; Table 4

[0170]

[0171]

[0172] Assuming that the future date is a Monday among working days, then it is necessary to obtain the decoupling status of Mondays on each working day in history. Assuming that there are a total of 20 Mondays on working days, the number of occurrences of the decoupling states of expansion negative decoupling, expansion connection, weak decoupling, strong decoupling, recession decoupling, recession connection, weak negative decoupling and strong negative decoupling are 1, 1, 4, 1, 3, 1, 2 and 7 respectively. Then, after statistics, the decoupling state that is most likely to occur (with a probability of 7 / 20) on Mondays among working days in history is strong negative decoupling, so it can be determined that the decoupling state of the future date is strong negative decoupling.

[0173] In addition, another embodiment provides the decoupling status of a certain place for one year, as shown in Table 5:

[0174] Table 5

[0175]

[0176]

[0177]

[0178]

[0179] After statistics, the probability of decoupling status on each working day and non-working day is shown in Table 6. In Table 6, It represents the average value of all data with the highest probability of occurrence. In short, the calculation process of the DI value on Monday is: first find the most likely decoupling state on Monday, and according to this decoupling state, collect the corresponding set of decoupling evaluation indexes in the history of working days on Mondays with strong negative decoupling. The average value of all elements in this set is -1.3568. Other working days or non-working days in the table The calculation method of is the same as above.

[0180] Table 6

[0181]

[0182] Specifically, after obtaining the passenger volume in the future, it can provide a reference for the transportation management department to deploy plans in advance or adaptively adjust the train schedule to cope with the passenger volume in the future, reduce unnecessary waste of resources, and save energy.

[0183] The above-mentioned urban rail transit passenger volume prediction method establishes a weather comfort index through the historical daily maximum temperature, the historical daily minimum temperature, the historical daily wind level and the historical daily weather conditions, and links the weather comfort index with the passenger volume to obtain a decoupling evaluation index. The historical daily decoupling evaluation index of the local area, the maximum temperature, the minimum temperature, the wind level and the weather conditions of future dates are used to predict the passenger volume of future dates. It comprehensively considers factors such as temperature, wind level and weather conditions, avoids the traditional method of considering weather conditions alone, and can predict the passenger volume more accurately. In addition, it abandons the traditional method of using time series models, artificial neural network models and machine learning models to predict passenger volume, but considers the decoupling relationship between the local historical daily weather comfort index and passenger volume. The use of the decoupling relationship for prediction can better adapt to local conditions and obtain passenger volume prediction results with more local characteristics.

[0184] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0185] Corresponding to the urban rail transit passenger volume prediction method described in the above embodiment, Figure 2 A structural block diagram of an urban rail transit passenger volume prediction device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0186] See also Figure 2 , the urban rail transit passenger volume prediction device in the embodiment of the present application may include:

[0187] The data acquisition module 201 is used to obtain the historical daily passenger volume, historical daily maximum temperature, historical daily minimum temperature, historical daily wind level, historical daily weather conditions of the rail transit in the target city, as well as the maximum temperature of a future date, the minimum temperature of a future date, the wind level of a future date and the weather conditions of a future date.

[0188] The data conversion module 202 is used to convert the historical daily wind level into numerical data to obtain first data; and convert the historical daily weather conditions into numerical data to obtain second data.

[0189] The first operation module 203 is used to obtain a historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data and the second data.

[0190] The second operation module 204 is used to obtain a historical daily decoupling evaluation index based on the historical daily weather comfort index and the historical daily passenger volume of rail transit.

[0191] The result output module 205 is used to predict the passenger volume of the target city rail transit on a future date based on the historical daily decoupling evaluation index, the maximum temperature on a future date, the minimum temperature on a future date, the wind level on a future date, and the weather conditions on a future date.

[0192] Exemplarily, the second operation module 204 is specifically used for:

[0193] Based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, combined with the first formula, the historical daily decoupling evaluation index is obtained.

[0194] The first formula can be:

[0195]

[0196] Among them, DI i represents the decoupling evaluation index on the ith day, C i represents the weather comfort index of the i-th day, Q i represents the passenger volume on the i-th day, C i-1 represents the weather comfort index of the i-1th day, Q i-1 represents the passenger volume on the i-1th day.

[0197] Exemplarily, the first operation module 203 is specifically configured to:

[0198] Based on the historical daily maximum temperature, the historical daily minimum temperature and the first data, combined with the second formula, the historical daily clothing index is obtained.

[0199] The historical daily maximum temperature, historical daily minimum temperature, first data, second data and historical daily clothing index are standardized by the range standardization method.

[0200] The entropy method is used to calculate the proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the historical daily clothing index.

[0201] Based on the standardized proportion and weight of the historical daily maximum temperature, the standardized proportion and weight of the historical daily minimum temperature, the standardized proportion and weight of the first data, the standardized proportion and weight of the second data, and the standardized proportion and weight of the historical daily clothing index, combined with the third formula, the historical daily weather comfort index is obtained.

[0202] The second formula is:

[0203]

[0204] Among them, P i5 represents the clothing index of the i-th day, T max Indicates the maximum value of the historical daily maximum temperature, T i ave represents the average temperature of the i-th day, which is equal to the average of the highest and lowest temperatures of the i-th day. H represents 75% of the human metabolic rate, R represents the solar constant, and α i represents the solar altitude angle on the i-th day, v i Represents the first data of the i-th day.

[0205] The third formula is:

[0206] C i =W1P i1 +W2P i2 +W3P i3 +W4P i4 +W5P i5

[0207] Among them, C i represents the weather comfort index of the i-th day, P i1 represents the weight of the highest temperature on the ith day after standardization, W1 represents the weight of the highest daily temperature after standardization, P i2 represents the weight of the lowest temperature on the ith day after standardization, W2 represents the weight of the lowest daily temperature after standardization, and P i3 represents the proportion of the first data of the i-th day after the standardization process, W3 represents the weight of the first data after the standardization process, and P i4 represents the proportion of the second data of the i-th day after the standardization process, W4 represents the weight of the second data after the standardization process, and P i5 W5 represents the weight of the clothing index of the i-th day after standardization, and W6 represents the weight of the historical daily clothing index after standardization.

[0208] Exemplarily, the result output module 205 is specifically used for:

[0209] The weather comfort index for the future date is calculated based on the maximum temperature for the future date, the minimum temperature for the future date, the wind level for the future date, and the weather conditions for the future date.

[0210] Based on the historical daily decoupling evaluation index, the decoupling status of future dates is determined.

[0211] Based on the decoupling status of the future date, the average of the historical daily decoupling evaluation indexes corresponding to the decoupling status that is the same as the decoupling status of the future date in the historical daily decoupling status is calculated to obtain the decoupling evaluation index of the future date.

[0212] Based on the decoupling evaluation index of the future date, the weather comfort index of the future date, the weather comfort index of the preset standard day and the passenger volume of the preset standard day, combined with the fourth formula, the passenger volume of the future date is calculated.

[0213] The fourth formula can be:

[0214]

[0215] Among them, Q' represents the passenger volume on the future date, DI' represents the decoupling evaluation index on the future date, C' represents the weather comfort index on the future date, and C X represents the weather comfort index of the preset standard day X, Q X represents the passenger volume of the preset standard day X, and i represents any day in the historical daily period.

[0216] Exemplarily, the result output module 205 may also be used to:

[0217] The wind level of the future date is converted into numerical data to obtain the third data; the weather conditions of the future date are converted into numerical data to obtain the fourth data.

[0218] Based on the maximum temperature of the future date, the minimum temperature of the future date and the third data, combined with the fifth formula, the clothing index of the future date is calculated.

[0219] The maximum temperature of the future date, the minimum temperature of the future date, the third data, the fourth data and the clothing index of the future date are standardized by the range standardization method.

[0220] Based on the standardized historical daily maximum temperature and the standardized maximum temperature of the future date, a maximum temperature set is obtained; based on the standardized historical daily minimum temperature and the standardized minimum temperature of the future date, a minimum temperature set is obtained; based on the standardized first data and the standardized third data, a first numerical data set is obtained; based on the standardized second data and the standardized fourth data, a second numerical data set is obtained; based on the standardized historical daily clothing index and the standardized clothing index of the future date, a clothing index set is obtained.

[0221] The entropy method is used to calculate the proportion and weight of the standardized maximum temperature of future dates in the maximum temperature set, the proportion and weight of the standardized minimum temperature of future dates in the minimum temperature set, the proportion and weight of the third data of future dates in the first numerical data set, the proportion and weight of the standardized fourth data of future dates in the second numerical data set, and the proportion and weight of the standardized clothing index of future dates in the clothing index set.

[0222] Based on the standardized proportion and weight of the maximum temperature of the future date, the standardized proportion and weight of the minimum temperature of the future date, the standardized proportion and weight of the third data of the future date, the standardized proportion and weight of the fourth data of the future date, and the standardized proportion and weight of the clothing index of the future date, combined with the sixth formula, the weather comfort index of the future date is calculated.

[0223] The fifth formula is:

[0224]

[0225] Among them, P' i5 represents the clothing index for the future date, T' max Indicates the maximum value of the maximum temperature of the future date and the historical daily maximum temperature, T' ave represents the average temperature of a future date, the average temperature of the future date is equal to the average of the maximum temperature and the minimum temperature of the future date, H represents 75% of the human metabolic rate, R represents the solar constant, α' represents the solar altitude angle of the future date, and v' represents the third data of the future date.

[0226] The sixth formula is:

[0227] C'=W'1P' i1 +W'2P' i2 +W'3P' i3 +W'4P' i4 +W5P'i5

[0228] Among them, C' represents the weather comfort index of the future date, P' i1 represents the proportion of the maximum temperature of the future date after standardization, W'1 represents the weight of the maximum temperature set after standardization, P' i2 represents the weight of the minimum temperature of the future date after standardization, W'2 represents the weight of the minimum temperature set after standardization, P' i3 represents the weight of the third data of the future date after standardization, W'3 represents the weight of the first numerical data set after standardization, P' i4 represents the weight of the fourth data of the future date after standardization, W'4 represents the weight of the second numerical data set after standardization, P' i5 W5 represents the weight of the clothing index of the future date after standardization, and W6 represents the weight of the clothing index set after standardization.

[0229] Exemplarily, the result output module 205 may also be used to:

[0230] Based on the historical daily decoupling evaluation index, the historical daily decoupling status is determined.

[0231] Statistics are collected on the historical daily decoupling status to determine the probabilities of different decoupling states on each working day and the probabilities of different decoupling states on each holiday.

[0232] According to the future date, determine which working day the future date is; and determine the decoupling state of the future date according to the maximum value of the probabilities of different decoupling states on the working day.

[0233] Alternatively, determine which holiday the future date is; and determine the decoupling state of the future date based on the maximum value of the probabilities of different decoupling states of the holiday.

[0234] Exemplarily, the first operation module 203 may also be used for:

[0235] The entropy method is used to calculate the proportion of the standardized historical daily maximum temperature and the weight of the standardized historical daily maximum temperature.

[0236] The entropy method is used to calculate the proportion of the standardized historical daily minimum temperature and the weight of the standardized historical daily minimum temperature.

[0237] The proportion of the first data after the standardization process is calculated by the entropy method, and the weight of the first data after the standardization process is calculated.

[0238] The proportion of the second data after the standardization process is calculated by the entropy method, and the weight of the second data after the standardization process is calculated.

[0239] By using the entropy method, the proportion of the standardized historical daily clothing index is calculated, and the weight of the standardized historical daily clothing index is calculated.

[0240] Exemplarily, the proportion of the standardized historical daily maximum temperature is calculated by the entropy method, including:

[0241] The entropy method is used in combination with the seventh formula to calculate the proportion of the standardized historical daily maximum temperature.

[0242] The seventh formula is:

[0243]

[0244] Among them, P i1 represents the proportion of the highest temperature on the i-th day after standardization, X i1 It represents the maximum temperature of the i-th day after standardization, and m is the number of historical days.

[0245] The weight of the standardized historical daily maximum temperature is calculated by the entropy method, including:

[0246] The entropy method is combined with the eighth formula to calculate the weight of the standardized historical daily maximum temperature.

[0247] The eighth formula is:

[0248]

[0249] Among them, W1 represents the weight of the historical daily maximum temperature after standardization.

[0250] The entropy method is used to calculate the proportion of the standardized historical daily minimum temperature, including:

[0251] The entropy method is combined with the ninth formula to calculate the proportion of the standardized historical daily minimum temperature.

[0252] The ninth formula is:

[0253]

[0254] Among them, P i2 represents the proportion of the lowest temperature on the ith day after standardization, X i2 represents the minimum temperature on the i-th day after normalization.

[0255] The entropy method is used to calculate the weight of the standardized historical daily minimum temperature, including:

[0256] The entropy method is combined with the tenth formula to calculate the weight of the standardized historical daily minimum temperature.

[0257] The tenth formula is:

[0258]

[0259] Among them, W2 represents the weight of the historical daily minimum temperature after standardization.

[0260] The proportion of the first data after the standardization process is calculated by the entropy method, including:

[0261] The entropy method is combined with the eleventh formula to calculate the proportion of the first data after the standardized processing.

[0262] The eleventh formula is:

[0263]

[0264] Among them, P i3 represents the proportion of the first data of the i-th day after standardization, X i3 Represents the first data of the i-th day after normalization.

[0265] The weight of the first data after the normalization process is calculated by the entropy method, including:

[0266] The weight of the first data after the standardization process is calculated by the entropy method in combination with the twelfth formula.

[0267] The twelfth formula is:

[0268]

[0269] Wherein, W3 represents the weight of the first data after the normalization process.

[0270] The proportion of the second data after the standardization process is calculated by the entropy method, including:

[0271] The entropy method is combined with the thirteenth formula to calculate the proportion of the second data after the standardization process.

[0272] The thirteenth formula is:

[0273]

[0274] Among them, P i4 represents the proportion of the second data of the i-th day after standardization, X i4 Represents the second data of the i-th day after normalization.

[0275] The weight of the second data after the standardization process is calculated by the entropy method, including:

[0276] The entropy method is combined with the fourteenth formula to calculate the weight of the second data after the standardization process.

[0277] The fourteenth formula is:

[0278]

[0279] Wherein, W4 represents the weight of the first data after the normalization process.

[0280] The entropy method is used to calculate the proportion of the standardized historical daily clothing index, including:

[0281] By using the entropy method and combining it with the fifteenth formula, the weight of the standardized historical daily clothing index is calculated.

[0282] The fifteenth formula is:

[0283]

[0284] Among them, P i5 represents the weight of the clothing index on the i-th day after standardization, X i5 Represents the clothing index of the i-th day after standardized processing.

[0285] The entropy method is used to calculate the weight of the standardized historical daily clothing index, including:

[0286] The entropy method is combined with the sixteenth formula to calculate the weight of the standardized historical daily clothing index.

[0287] The sixteenth formula is:

[0288]

[0289] Among them, W5 represents the weight of the historical daily clothing index after standardization.

[0290] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0291] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0292] The present application also provides an electronic device, see Figure 3 The electronic device 300 may include: at least one processor 310 and a memory 320, wherein the memory 320 is used to store a computer program 321, and the processor 310 is used to call and run the computer program 321 stored in the memory 320 to implement the steps in any of the above-mentioned method embodiments, for example Figure 1 Steps 101 to 105 in the illustrated embodiment. Alternatively, when the processor 310 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 2 The functions of each module are shown.

[0293] Exemplarily, the computer program 321 may be divided into one or more modules / units, one or more modules / units are stored in the memory 320, and are executed by the processor 310 to complete the present application. The one or more modules / units may be a series of computer program segments that can complete specific functions, and the program segments are used to describe the execution process of the computer program in the electronic device 300.

[0294] Those skilled in the art will understand that Figure 3 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0295] The processor 310 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. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0296] The memory 320 may be an internal storage unit of the electronic device, or an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory 320 is used to store the computer program and other programs and data required by the electronic device. The memory 320 may also be used to temporarily store data that has been output or is to be output.

[0297] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0298] The urban rail transit passenger volume prediction method provided in the embodiment of the present application can be applied to electronic devices such as computers, wearable devices, vehicle-mounted devices, tablet computers, laptops, netbooks, etc. The embodiment of the present application does not impose any restrictions on the specific type of electronic devices.

[0299] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0300] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0301] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0302] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0303] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for predicting passenger volume of urban rail transit, characterized in that: include: Obtain the target city's rail transit daily passenger volume, daily maximum temperature, daily minimum temperature, daily wind level, daily weather conditions, as well as the maximum temperature, minimum temperature, wind level, and weather conditions for future dates; Convert the historical daily wind scale into numerical data to obtain first data; Convert the historical daily weather conditions into numerical data to obtain second data; Obtaining a historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data, and the second data; Based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, a historical daily decoupling evaluation index is obtained; Based on the historical daily decoupling evaluation index, the maximum temperature on the future date, the minimum temperature on the future date, the wind level on the future date and the weather conditions on the future date, the passenger volume of the target city rail transit on the future date is predicted.

2. The method for predicting passenger volume of urban rail transit according to claim 1, characterized in that: The historical daily decoupling evaluation index is obtained based on the historical daily weather comfort index and the historical daily passenger volume of rail transit, including: Based on the historical daily weather comfort index and the historical daily rail transit passenger volume, combined with the first formula, the historical daily decoupling evaluation index is obtained; The first formula is: Among them, DI i represents the decoupling evaluation index on the ith day, C i represents the weather comfort index of the i-th day, Q i represents the passenger volume on the i-th day, C i-1 represents the weather comfort index of the i-1th day, Q i-1 represents the passenger volume on the i-1th day.

3. The method for predicting passenger volume of urban rail transit according to claim 1, characterized in that: The obtaining of the historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data and the second data comprises: Based on the historical daily maximum temperature, the historical daily minimum temperature and the first data, a historical daily clothing index is obtained in combination with a second formula; Standardizing the historical daily maximum temperature, the historical daily minimum temperature, the first data, the second data, and the historical daily clothing index by using a range standardization method; The proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the standardized historical daily clothing index are calculated respectively by the entropy method; Based on the proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the standardized historical daily clothing index, combined with a third formula, the historical daily weather comfort index is obtained; The second formula is: Among them, P i5 represents the clothing index of the i-th day, T max Indicates the maximum value of the historical daily maximum temperature, T i ave represents the average temperature of the i-th day, which is equal to the average of the highest and lowest temperatures of the i-th day. H represents 75% of the human metabolic rate, R represents the solar constant, and α i represents the solar altitude angle on the i-th day, v i represents the first data of the i-th day; The third formula is: C i =W1P i1 +W2P i2 +W3P i3 +W4P i4 +W5P i5 Among them, C i represents the weather comfort index of the i-th day, P i1 represents the weight of the highest temperature of the ith day after standardization, W1 represents the weight of the historical daily highest temperature after standardization, P i2 represents the weight of the lowest temperature on the ith day after standardization, W2 represents the weight of the lowest daily temperature after standardization, and P i3 represents the proportion of the first data of the i-th day after the standardization process, W3 represents the weight of the first data after the standardization process, and P i4 represents the proportion of the second data of the i-th day after the standardization process, W4 represents the weight of the second data after the standardization process, and P i5 W5 represents the weight of the clothing index of the i-th day after the standardized processing, and W6 represents the weight of the historical daily clothing index after the standardized processing.

4. The method for predicting passenger volume of urban rail transit according to claim 3, characterized in that: The predicting of the passenger volume of the target city rail transit on the future date based on the historical daily decoupling evaluation index, the maximum temperature on the future date, the minimum temperature on the future date, the wind level on the future date and the weather conditions on the future date includes: Calculate the weather comfort index of the future date based on the maximum temperature of the future date, the minimum temperature of the future date, the wind level of the future date and the weather conditions of the future date; Determining the decoupling status of the future date based on the historical daily decoupling evaluation index; Based on the decoupling state of the future date, calculating the average of the historical daily decoupling evaluation indexes corresponding to the decoupling state that is the same as the decoupling state of the future date in the historical daily decoupling states, to obtain the decoupling evaluation index of the future date; Based on the decoupling evaluation index of the future date, the weather comfort index of the future date, the weather comfort index of the preset standard day and the passenger volume of the preset standard day, the passenger volume of the future date is calculated in combination with the fourth formula; The fourth formula is: Wherein, Q' represents the passenger volume on the future date, DI' represents the decoupling evaluation index on the future date, C' represents the weather comfort index on the future date, and C X represents the weather comfort index of the preset standard day X, Q X represents the passenger volume of the preset standard day X, and i represents any day in the historical daily period.

5. The method for predicting passenger volume of urban rail transit according to claim 4, characterized in that: The calculating the weather comfort index of the future date based on the maximum temperature of the future date, the minimum temperature of the future date, the wind level of the future date and the weather conditions of the future date comprises: Convert the wind level of the future date into numerical data to obtain third data; convert the weather conditions of the future date into numerical data to obtain fourth data; Calculate the clothing index for the future date based on the maximum temperature for the future date, the minimum temperature for the future date and the third data in combination with a fifth formula; Standardizing the maximum temperature of the future date, the minimum temperature of the future date, the third data, the fourth data, and the clothing index of the future date by using a range standardization method; Based on the standardized historical daily maximum temperature and the standardized maximum temperature of the future date, a maximum temperature set is obtained; based on the standardized historical daily minimum temperature and the standardized minimum temperature of the future date, a minimum temperature set is obtained; based on the standardized first data and the standardized third data, a first numerical data set is obtained; based on the standardized second data and the standardized fourth data, a second numerical data set is obtained; based on the standardized historical daily clothing index and the standardized clothing index of the future date, a clothing index set is obtained; Calculate respectively by entropy method the proportion and weight of the highest temperature of the standardized future date in the highest temperature set, the proportion and weight of the lowest temperature of the standardized future date in the lowest temperature set, the proportion and weight of the third data of the standardized future date in the first numerical data set, the proportion and weight of the fourth data of the standardized future date in the second numerical data set, and the proportion and weight of the clothing index of the standardized future date in the clothing index set; Based on the proportion and weight of the highest temperature of the future date after the standardization, the proportion and weight of the lowest temperature of the future date after the standardization, the proportion and weight of the third data of the future date after the standardization, the proportion and weight of the fourth data of the future date after the standardization, and the proportion and weight of the clothing index of the future date after the standardization, in combination with the sixth formula, the weather comfort index of the future date is calculated; The fifth formula is: Among them, P' i5 represents the clothing index for the future date, T' max Indicates the maximum value of the maximum temperature of the future date and the historical daily maximum temperature, T' ave represents the average temperature of a future date, the average temperature of the future date is equal to the average of the maximum temperature and the minimum temperature of the future date, H represents 75% of the human body metabolic rate, R represents the solar constant, α' represents the solar altitude angle of the future date, and v' represents the third data of the future date; The sixth formula is: C'=W'1P' i1 +W'2P' i2 +W'3P' i3 +W'4P' i4 +W5P' i5 Where C' represents the weather comfort index for the future date, P' i1 represents the weight of the maximum temperature of the future date after the standardization, W'1 represents the weight of the maximum temperature set after the standardization, P' i2 represents the weight of the minimum temperature of the future date after the standardization, W'2 represents the weight of the minimum temperature set after the standardization, P' i3 represents the weight of the third data of the future date after the standardization process, W'3 represents the weight of the first numerical data set after the standardization process, P' i4 represents the weight of the fourth data of the future date after the standardization process, W'4 represents the weight of the second numerical data set after the standardization process, P' i5 W5 represents the weight of the clothing index of the future date after the standardization process, and W6 represents the weight of the clothing index set after the standardization process.

6. The method for predicting passenger volume of urban rail transit according to claim 4, characterized in that: Determining the decoupling status of the future date based on the historical daily decoupling evaluation index includes: Determining a historical daily decoupling status based on the historical daily decoupling evaluation index; Counting the historical daily decoupling states, determining the probabilities of different decoupling states on each working day and the probabilities of different decoupling states on each holiday; According to the future date, determine which working day the future date is; determine the decoupling state of the future date according to the maximum value of the probabilities of different decoupling states on the working day; Alternatively, determine which holiday the future date is; and determine the decoupling state of the future date according to the maximum value of the probabilities of different decoupling states of the holiday.

7. The method for predicting passenger volume of urban rail transit according to claim 3, characterized in that: The entropy method is used to calculate the proportion and weight of the standardized historical daily maximum temperature, the proportion and weight of the standardized historical daily minimum temperature, the proportion and weight of the standardized first data, the proportion and weight of the standardized second data, and the proportion and weight of the standardized historical daily clothing index, including: Calculate the proportion of the standardized historical daily maximum temperature and the weight of the standardized historical daily maximum temperature by entropy method; Calculate the proportion of the standardized historical daily minimum temperature and the weight of the standardized historical daily minimum temperature by entropy method; Calculating the proportion of the first data after the standardization process and calculating the weight of the first data after the standardization process by using an entropy method; Calculating the proportion of the second data after the standardization process and calculating the weight of the second data after the standardization process by an entropy method; The proportion of the standardized historical daily clothing index is calculated by the entropy method, and the weight of the standardized historical daily clothing index is calculated.

8. The method for predicting passenger volume of urban rail transit according to claim 7, characterized in that: The step of calculating the proportion of the standardized historical daily maximum temperature by the entropy method includes: By using the entropy method and combining the seventh formula, the proportion of the historical daily maximum temperature after the standardization process is calculated; The seventh formula is: Among them, P i1 represents the proportion of the highest temperature on the i-th day after standardization, X i1 represents the maximum temperature of the i-th day after standardization, and m is the number of historical days; The step of calculating the weight of the standardized historical daily maximum temperature by the entropy method includes: Calculate the weight of the standardized historical daily maximum temperature by using the entropy method in combination with the eighth formula; The eighth formula is: Wherein, W1 represents the weight of the historical daily maximum temperature after the standardization process; The calculating the proportion of the standardized historical daily minimum temperature by the entropy method includes: By using the entropy method and the ninth formula, the proportion of the historical daily minimum temperature after the standardization process is calculated; The ninth formula is: Among them, P i2 represents the proportion of the lowest temperature on the ith day after standardization, X i2 represents the minimum temperature of the i-th day after standardization; The step of calculating the weight of the standardized historical daily minimum temperature by the entropy method includes: The weight of the historical daily minimum temperature after the standardization process is calculated by the entropy method in combination with the tenth formula; The tenth formula is: Wherein, W2 represents the weight of the historical daily minimum temperature after the standardization process; The calculating the proportion of the first data after the standardization process by the entropy method includes: Calculate the proportion of the first data after the standardization process by using the entropy method in combination with the eleventh formula; The eleventh formula is: Among them, P i3 represents the proportion of the first data of the i-th day after standardization, X i3 represents the first data of the i-th day after standardization; The step of calculating the weight of the first data after the standardization process by using an entropy method includes: Calculate the weight of the first data after the standardization process by using the entropy method in combination with the twelfth formula; The twelfth formula is: Wherein, W3 represents the weight of the first data after the standardization process; Calculating the proportion of the second data after the standardization process by the entropy method includes: Calculate the proportion of the second data after the standardization process by using the entropy method in combination with the thirteenth formula; The thirteenth formula is: Among them, P i4 represents the proportion of the second data of the i-th day after standardization, X i4 represents the second data of the i-th day after standardization; The step of calculating the weight of the standardized second data by an entropy method includes: Calculate the weight of the second data after the standardization process by using the entropy method in combination with the fourteenth formula; The fourteenth formula is: Wherein, W4 represents the weight of the first data after the standardization process; The calculating the proportion of the standardized historical daily clothing index by the entropy method includes: By using the entropy method and the fifteenth formula, the weight of the standardized historical daily clothing index is calculated; The fifteenth formula is: Among them, P i5 represents the weight of the clothing index on the i-th day after standardization, X i5 represents the clothing index of the i-th day after standardized processing; The step of calculating the weight of the standardized historical daily clothing index by the entropy method includes: Calculate the weight of the standardized historical daily clothing index by using the entropy method in combination with the sixteenth formula; The sixteenth formula is: Wherein, W5 represents the weight of the historical daily clothing index after the standardization process.

9. A device for predicting passenger volume of urban rail transit, characterized in that: include: A data acquisition module is used to obtain the target city's rail transit daily passenger volume, daily maximum temperature, daily minimum temperature, daily wind level, daily weather conditions, as well as the maximum temperature of a future date, the minimum temperature of a future date, the wind level of a future date, and the weather conditions of a future date; A data conversion module, used to convert the historical daily wind level into numerical data to obtain first data; convert the historical daily weather conditions into numerical data to obtain second data; A first calculation module, configured to obtain a historical daily weather comfort index based on the historical daily maximum temperature, the historical daily minimum temperature, the first data, and the second data; A second operation module is used to obtain a historical daily decoupling evaluation index based on the historical daily weather comfort index and the historical daily passenger volume of rail transit; A result output module is used to predict the passenger volume of the target city rail transit on the future date based on the historical daily decoupling evaluation index, the maximum temperature on the future date, the minimum temperature on the future date, the wind level on the future date and the weather conditions on the future date.

10. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be run on the processor, and wherein the processor implements the urban rail transit passenger volume prediction method as described in any one of claims 1 to 8 when executing the computer program.

Images