Dynamic price adjustment method and device based on online car-hailing supply-demand relationship, medium and equipment

Abstract

The invention provides a dynamic price adjustment method and device based on an online car-hailing supply-demand relationship, a medium and equipment, and the method comprises the steps: determining a current honeycomb region located in a target city, and obtaining historical order data and quasi-real-time order data in the current honeycomb region; based on the historical order data and the quasi-real-time order data, analyzing supply and demand related indexes of the current honeycomb area; the supply and demand related indexes comprise historical supply and demand related indexes and quasi-real-time supply and demand related indexes; calculating a historical price adjustment rate and a quasi-real-time adjustment rate based on the historical supply and demand related indexes and the quasi-real-time supply and demand related indexes respectively; calculating a final price adjustment multiplying power based on the calculated historical price adjustment multiplying power and the quasi-real-time adjustment multiplying power; and performing price adjustment on the online car-hailing order of the current honeycomb area by using the final price adjustment multiplying power. According to the invention, historical and real-time data are comprehensively considered, multiple indexes are integrated, the weight is set to judge the supply and demand relationship of the online car-hailing platform, the price adjustment rate is dynamically adjusted, and the operation effect of the online car-hailing platform is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a dynamic pricing method and device, medium, and equipment based on the supply and demand relationship of online car-hailing. Background Art

[0002] At present, it is difficult for online ride-hailing platforms to accurately predict the demand and time distribution of users. If the platform overestimates demand and the actual demand is lower, it will lead to a situation where supply exceeds demand. On the contrary, if the platform underestimates demand and the actual demand is higher, it will lead to a situation where supply exceeds demand. Common reasons for the imbalance between supply and demand are as follows: (1) Time factors: During rush hour, holidays, and traffic congestion, travel demand surges. This periodic peak demand often leads to a shortage of online ride-hailing services because the number of available drivers cannot effectively match the sudden increase in demand; (2) Geographic factors: Specific popular areas, such as commercial centers, large-scale event venues, tourist attractions, etc., often have local supply and demand imbalances due to their characteristics of attracting people. In these areas, the demand of passengers far exceeds the number of drivers available to provide services; (3) Weather factors: Severe weather conditions, such as rain, snow, and storms, not only increase the difficulty of travel, but also significantly increase the demand for taxis, while affecting drivers' willingness to drive.

[0003] The following problems may arise in the case of the above-mentioned supply-demand imbalance: (1) Passenger waiting time is prolonged: In the case of supply-demand imbalance, passengers may have to wait for a long time to get service, which directly leads to a decline in user experience; (2) Driver pressure increases: Drivers working during peak hours or in bad weather face greater work pressure and also face safety risks; (3) Service quality fluctuations: When demand exceeds supply, in order to respond quickly to demand, service quality may decline; and when supply exceeds demand, drivers may provide excessive service in order to compete for orders. Summary of the invention

[0004] To this end, the present invention provides a dynamic pricing method and device, medium, and equipment based on the supply and demand relationship of online ride-hailing, aiming to solve the technical problems of prolonged passenger waiting time, increased driver pressure, and fluctuating service quality caused by the imbalance of supply and demand of online ride-hailing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions:

[0006] According to a first aspect of the present invention, the present invention provides a dynamic pricing method based on the supply and demand relationship of online car-hailing, the method comprising:

[0007] Determine a current honeycomb area in a target city, and obtain historical order data and quasi-real-time order data in the current honeycomb area;

[0008] Based on the historical order data and the quasi-real-time order data, analyzing supply and demand related indicators of the current honeycomb area; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators;

[0009] Calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively;

[0010] Calculate the final price adjustment ratio based on the calculated historical price adjustment ratio and the quasi-real-time adjustment ratio by using the preset price adjustment rule;

[0011] The final price adjustment ratio is used to adjust the price of online car-hailing orders in the current honeycomb area.

[0012] Optionally, the supply and demand related indicators include the first-round winning rate, the first-round vehicle dispatch rate, the average dispatch times per order, the order quantity and the average dispatch time per order;

[0013] The first-round winning rate is the proportion of user orders successfully matched to drivers in the first round of dispatch;

[0014] The first round of available car dispatch rate is the ratio of available drivers successfully selected in the first round of dispatch for user orders;

[0015] The average dispatch number is the ratio of the number of drivers with available vehicles to the number of available vehicles in the first round of dispatch;

[0016] The order quantity is the number of orders placed starting from the current honeycomb area;

[0017] The average scheduling time for each order is the average scheduling time for all orders placed.

[0018] Optionally, the calculating of the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively includes:

[0019] Calculating the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively;

[0020] Calculate the historical relative tension and the quasi-real-time relative tension of the current honeycomb area in the target city by using the historical supply-demand tension and the real-time supply-demand correlation tension respectively;

[0021] The historical relative tension and the quasi-real-time relative tension are respectively used to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio.

[0022] Optionally, the calculating the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively includes:

[0023] Based on the historical supply and demand related indicators, the historical supply and demand tension of the current honeycomb area is calculated using the following formula:

[0024]

[0025] a1+b1+c1+d1+e1=1

[0026] Among them, S1 is the historical supply-demand tension; A1 is the historical first-round winning rate; a1 is the historical first-round winning rate weight; B1 is the historical first-round vehicle dispatch rate; b1 is the historical first-round vehicle dispatch weight; C1 is the historical average dispatch times; c1 is the historical average dispatch times weight; D1 is the historical order volume; d1 is the historical order volume weight; E1 is the historical average dispatch time; e1 is the historical average dispatch time weight;

[0027] as well as,

[0028] Based on the quasi-real-time supply and demand related indicators, the quasi-real-time supply and demand tension of the current honeycomb area is calculated using the following formula:

[0029]

[0030] a2+b2+c2+d2+e2=1

[0031] Among them, S2 is the tension of quasi-real-time supply and demand relationship; A2 is the quasi-real-time first-round winning rate; a2 is the weight of the quasi-real-time first-round winning rate; B2 is the quasi-real-time first-round vehicle dispatch rate; b2 is the weight of the quasi-real-time first-round vehicle dispatch rate; C2 is the average number of dispatches for quasi-real-time orders; c2 is the weight of the average number of dispatches for quasi-real-time orders; D2 is the quasi-real-time order volume; d2 is the weight of the quasi-real-time order volume; e2 is the average dispatch time for quasi-real-time orders; e2 is the weight of the average dispatch time for quasi-real-time orders.

[0032] Optionally, the calculating the historical relative tension and the quasi-real-time relative tension of the current honeycomb area in the target city by respectively using the historical supply-demand tension and the real-time supply-demand correlation tension, comprises:

[0033] Obtaining a historical supply-demand tension dataset and a real-time supply-demand related tension dataset of all honeycomb areas in the target city, and determining the median of the historical supply-demand tension dataset and the median of the real-time supply-demand related tension dataset;

[0034] Based on the historical supply-demand tension of the current honeycomb area, the historical relative tension is calculated using the following formula:

[0035]

[0036] Among them, Q1 is the historical relative tension; S1 is the historical supply and demand tension; M1 is the median of the historical supply and demand tension data set;

[0037] as well as,

[0038] Based on the quasi-real-time supply-demand tension of the current honeycomb area, the quasi-real-time relative tension is calculated using the following formula:

[0039]

[0040] Among them, Q2 is the quasi-real-time relative tension; S2 is the quasi-real-time supply and demand tension; M2 is the median of the quasi-real-time supply and demand tension data set.

[0041] Optionally, the calculating of a historical price adjustment ratio and a quasi-real-time adjustment ratio by respectively using the historical relative tension and the quasi-real-time relative tension includes:

[0042] Based on the historical relative tension, the historical price adjustment ratio is calculated using the following formula:

[0043] Rate1=x1*arctan(Q1*x2+x3)+x4

[0044] Among them, Rate1 is the historical price adjustment ratio; Q1 is the historical relative tension; x1, x2, x3, x4 are constants;

[0045] as well as,

[0046] Based on the quasi-real-time relative tension, the quasi-real-time price adjustment ratio is calculated using the following formula:

[0047] Rate2=x1*arctan(Q2*x2+x3)+x4

[0048] Among them, Rate2 is the quasi-real-time price adjustment ratio; Q2 is the quasi-real-time relative tension; x1, x2, x3, and x4 are constants.

[0049] Optionally, the using of a preset price adjustment rule to calculate a final price adjustment ratio based on the calculated historical price adjustment ratio and the quasi-real-time adjustment ratio includes:

[0050] The final price adjustment ratio is calculated based on the preset historical price adjustment ratio weight and the quasi-real-time adjustment ratio weight. The formula is as follows:

[0051] Rate=weight1*Rate1+weight2*Rate2

[0052] Among them, Rate is the final price adjustment ratio; weight1 is the weight of the historical price adjustment ratio; Rate1 is the historical price adjustment ratio; weight2 is the weight of the quasi-real-time price adjustment ratio; Rate2 is the quasi-real-time price adjustment ratio.

[0053] According to a second aspect of the present invention, the present invention provides a dynamic pricing device based on the supply and demand relationship of online car-hailing, the device comprising:

[0054] A data acquisition module, used to determine a current honeycomb area in a target city, and acquire historical order data and quasi-real-time order data in the current honeycomb area;

[0055] An indicator analysis module, used to analyze supply and demand related indicators of the current honeycomb area based on the historical order data and the quasi-real-time order data; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators;

[0056] A data processing module, used to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively;

[0057] A multiplier calculation module, used to calculate a final price adjustment multiplier based on the calculated historical price adjustment multiplier and the quasi-real-time adjustment multiplier by using a preset price adjustment rule;

[0058] The price adjustment application module is used to adjust the price of the online car-hailing orders in the current honeycomb area using the final price adjustment ratio.

[0059] According to the third aspect of the present invention, the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor executes a dynamic pricing method based on the supply and demand relationship of online car-hailing as described in any one of the first aspect of the present invention.

[0060] According to the fourth aspect of the present invention, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a dynamic pricing method based on the supply and demand relationship of online car-hailing is implemented as described in any one of the first aspect of the present invention.

[0061] The present invention adopts the above technical solution and has at least the following beneficial effects:

[0062] Through the scheme of the present invention, the current honeycomb area located in the target city is determined, and the historical order data and quasi-real-time order data in the current honeycomb area are obtained; based on the historical order data and quasi-real-time order data, the supply and demand related indicators of the current honeycomb area are analyzed; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators; based on the historical supply and demand related indicators and the quasi-real-time supply and demand related indicators, the historical price adjustment ratio and the quasi-real-time adjustment ratio are calculated respectively; using the preset price adjustment rules, the final price adjustment ratio is calculated based on the calculated historical price adjustment ratio and the quasi-real-time adjustment ratio; and the online car-hailing orders in the current honeycomb area are adjusted using the final price adjustment ratio. Through the present invention, the historical and real-time data of the current honeycomb area are comprehensively considered, multiple indicators are integrated and weights are set to judge the supply and demand relationship of online car-hailing, and the price adjustment ratio is dynamically adjusted, which greatly improves the operation effect of the online car-hailing platform.

[0063] 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 invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of a process of a dynamic pricing method based on the supply and demand relationship of online car-hailing provided by an embodiment of the present invention is shown;

[0066] Figure 2 A schematic diagram of a process for calculating an adjustment ratio using supply-demand related indicators provided by an embodiment of the present invention is shown;

[0067] Figure 3 A schematic diagram of the structure of a dynamic pricing device based on the supply and demand relationship of online car-hailing provided by one embodiment of the present invention is shown;

[0068] Figure 4 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0069] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0070] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0071] The embodiment of the present invention provides a dynamic pricing method based on the supply and demand relationship of online car-hailing. Figure 1 As shown, at least the following steps S101 to S105 may be included:

[0072] Step S101, determine the current honeycomb area in the target city, and obtain historical order data and quasi-real-time order data in the current honeycomb area.

[0073] Dynamic pricing is a strategy that addresses the imbalance between supply and demand by adjusting prices. When passenger demand is high and vehicle supply is insufficient, the platform can increase prices to attract more drivers to join the service, thereby increasing supply. Conversely, when passenger demand is low and vehicle supply is excessive, the platform can lower prices to encourage more passengers to use the service, thereby balancing the supply and demand relationship.

[0074] The embodiment of the present invention first divides the target city that needs to be dynamically priced into multiple honeycomb areas, considers the supply and demand relationship of the current honeycomb area, and obtains the historical order data and quasi-real-time order data of the current honeycomb area as necessary. It should be noted that the collection period range of the quasi-real-time order data and the historical order data can be set according to actual needs, and the present invention does not limit this.

[0075] Step S102, analyzing supply and demand related indicators of the current honeycomb area based on historical order data and quasi-real-time order data.

[0076] The supply and demand related indicators in the embodiment of the present invention include the first-round winning rate A, the first-round vehicle dispatch rate B, the average dispatch time C, the order quantity D and the average dispatch time E.

[0077] Among them, the first-round winning rate A is the winning rate of user orders in the first round of dispatching. This indicator reflects the proportion of orders successfully matched to drivers in the first round of dispatching. A higher first-round winning rate usually means a better balance between supply (available drivers) and demand (order volume), that is, there are enough driver resources to meet order demand.

[0078] The first-round car dispatch rate B is the number of orders that have available drivers selected within the first-round selection range of user orders / the number of orders that enter the dispatch. This indicator indicates the proportion of orders that can successfully select available drivers within the first-round selection range. A higher first-round car dispatch rate means that more orders can find available drivers, indicating a higher degree of match between supply and demand.

[0079] Average dispatch times C is the number of drivers with available cars in the first round / the number of available cars in the first round. This indicator indicates the average number of orders dispatched by each available driver. A higher average dispatch times in the first round means that each driver can receive more orders, indicating that the supply (driver resources) is relatively sufficient and can meet more order demands.

[0080] The order volume D is the number of orders placed with the starting point within the current honeycomb area. This indicator indicates the number of orders placed with the starting point within the honeycomb. A higher order volume means that there are more order demands and more driver resources may be needed to meet these orders.

[0081] The average dispatch time E is the sum of (order receiving time - order placing time) or (cancellation time - order placing time) of all orders / the number of orders received + cancellations in the corresponding period. This indicator represents the average dispatch time of all orders. A lower average dispatch time means that the order is dispatched faster and the matching efficiency between supply and demand is higher.

[0082] It is understandable that when the first-round winning rate A, the first-round vehicle dispatch rate B, and the first-round average dispatch times C are high, the order volume D is moderate, and the average dispatch time E is low, it can be considered that the balance between supply and demand is good and the supply and demand relationship is relatively stable. On the contrary, if these indicators are low or unbalanced, there may be an imbalance between supply and demand, and corresponding measures need to be taken to adjust the relationship between supply and demand.

[0083] The embodiments of the present invention analyze historical supply and demand related indicators based on the historical order data of the current honeycomb area, and obtain the historical first-round winning rate A1; the historical first-round vehicle dispatch rate B1; the historical average dispatch times C1; the historical order quantity D1; and the historical average scheduling time E1; and analyze the quasi-real-time supply and demand related indicators based on the quasi-real-time order data of the current honeycomb area, and obtain the quasi-real-time first-round winning rate A2; the quasi-real-time first-round vehicle dispatch rate B2; the quasi-real-time average dispatch times C2; the quasi-real-time order quantity D2; and the quasi-real-time average scheduling time E2.

[0084] Step S103, calculating the historical price adjustment ratio and the quasi-real-time price adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively.

[0085] like Figure 2 As shown, the calculation of the adjustment ratio using supply and demand related indicators specifically includes the following steps S1031 to S1033:

[0086] Step S1031: Calculate the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively.

[0087] Specifically, based on historical supply and demand related indicators, the historical supply and demand tension of the current honeycomb area can be calculated using the following formula:

[0088]

[0089] a1+b1+c1+d1+e1=1

[0090] Among them, S1 is the historical supply-demand tension; A1 is the historical first-round winning rate; a1 is the historical first-round winning rate weight; B1 is the historical first-round car dispatch rate; b1 is the historical first-round car dispatch weight; C1 is the historical average number of dispatches; c1 is the historical average number of dispatches; D1 is the historical order volume; d1 is the historical order volume weight; E1 is the historical average dispatch time; e1 is the historical average dispatch time weight.

[0091] Furthermore, based on the quasi-real-time supply and demand related indicators, the following formula can be used to calculate the quasi-real-time supply and demand tension of the current honeycomb area:

[0092]

[0093] a2+b2+c2+d2+e2=1

[0094] Among them, S2 is the tension of quasi-real-time supply and demand relationship; A2 is the quasi-real-time first-round winning rate; a2 is the weight of the quasi-real-time first-round winning rate; B2 is the quasi-real-time first-round vehicle dispatch rate; b2 is the weight of the quasi-real-time first-round vehicle dispatch rate; C2 is the average number of dispatches per quasi-real-time order; c2 is the weight of the average number of dispatches per quasi-real-time order; D2 is the quasi-real-time order volume; d2 is the weight of the quasi-real-time order volume; E2 is the average dispatch time per quasi-real-time order; e2 is the weight of the average dispatch time per quasi-real-time order.

[0095] The embodiment of the present invention sets weights for different supply-demand related indicators and performs weighted processing on each indicator to obtain the tension of the supply-demand relationship. It can be understood that when the tension of the supply-demand relationship is between (0, 1), when the tension of the supply-demand relationship is infinitely close to 0, it means that the supply is insufficient to meet the demand, and when the tension of the supply-demand relationship is infinitely close to 1, it means that the supply exceeds the demand. It should also be noted that in actual applications, the weights of various supply-demand related indicators, that is, the degree of influence on the tension of the supply-demand relationship, can be adjusted according to actual conditions, so that the tension of the supply-demand relationship can be more accurately reflected.

[0096] Step S1032: Calculate the historical relative tension and quasi-real-time relative tension of the current honeycomb area in the target city by using the historical supply-demand tension and the real-time supply-demand tension respectively.

[0097] Specifically, the historical supply-demand tension dataset and the real-time supply-demand related tension dataset of all honeycomb areas in the target city can be obtained, and the median of the historical supply-demand tension dataset and the median of the real-time supply-demand related tension dataset can be determined. That is, the quasi-real-time supply-demand tension and the historical supply-demand tension of all honeycomb areas in the target city are calculated according to the formula for calculating the supply-demand tension in step S1 above, and they are sorted respectively, and the medians are obtained as M1 and M2 respectively.

[0098] Furthermore, based on the historical supply-demand tension of the current honeycomb area, the historical relative tension is calculated using the following formula:

[0099]

[0100] Among them, Q1 is the historical relative tension; S1 is the historical supply and demand tension; M1 is the median of the historical supply and demand tension data set.

[0101] Based on the quasi-real-time supply-demand tension in the current honeycomb area, the quasi-real-time relative tension is calculated using the following formula:

[0102]

[0103] Among them, Q2 is the quasi-real-time relative tension; S2 is the quasi-real-time supply and demand tension; M2 is the median of the quasi-real-time supply and demand tension data set.

[0104] The embodiment of the present invention calculates the supply-demand tension of all honeycomb areas and sorts them, and takes the median as a reference value, which can avoid the influence of extreme values ​​on the results and more accurately evaluate the tension of the supply-demand relationship.

[0105] Step S1033: Calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio by using the historical relative tension and the quasi-real-time relative tension respectively.

[0106] Specifically, the historical price adjustment ratio can be calculated based on the historical relative tension using the following formula:

[0107] Rate1=x1*arctan(Q1*x2+x3)+x4

[0108] Among them, Rate1 is the historical price adjustment ratio; Q1 is the historical relative tension; x1, x2, x3, and x4 are constants.

[0109] Furthermore, based on the quasi-real-time relative tension, the quasi-real-time price adjustment ratio can be calculated using the following formula:

[0110] Rate2=x1*arctan(Q2*x2+x3)+x4

[0111] Among them, Rate2 is the quasi-real-time price adjustment ratio; Q2 is the quasi-real-time relative tension; x1, x2, x3, and x4 are constants.

[0112] The embodiment of the present invention sets a constant and uses the arctan function to calculate the rate, so that the tension of the supply and demand relationship can be mapped to a suitable range. This can better reflect the tension of the supply and demand relationship and serve as a basis for subsequent price adjustment strategies. It should be noted that the constant can be data obtained based on expert experience or experiments, and in actual applications, it can also be adjusted according to demand.

[0113] Step S104, using the preset price adjustment rules, based on the calculation of historical price adjustment ratios and quasi-real-time adjustment ratios, calculate the final price adjustment ratio.

[0114] The final price adjustment ratio is calculated based on the preset historical price adjustment ratio weight and the quasi-real-time adjustment ratio weight. The formula is as follows:

[0115] Rate=weight1*Rate1+weight2*Rate2

[0116] Among them, Rate is the final price adjustment ratio; weight1 is the weight of the historical price adjustment ratio; Rate1 is the historical price adjustment ratio; weight2 is the weight of the quasi-real-time price adjustment ratio; Rate2 is the quasi-real-time price adjustment ratio.

[0117] The final price adjustment coefficient of the embodiment of the present invention is obtained by weight calculation, which comprehensively considers the tension of the supply and demand relationship and the importance of each indicator. In this way, dynamic price adjustment can be carried out according to actual conditions to balance the supply and demand relationship and improve the operation effect of the platform.

[0118] Step S105, using the final price adjustment ratio to adjust the price of online taxi orders in the current honeycomb area.

[0119] The embodiment of the present invention provides a dynamic price adjustment method based on the supply and demand relationship of online car-hailing, which determines the current honeycomb area located in the target city, obtains historical order data and quasi-real-time order data in the current honeycomb area; analyzes the supply and demand related indicators of the current honeycomb area based on the historical order data and the quasi-real-time order data; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators; calculates the historical price adjustment multiplier and the quasi-real-time adjustment multiplier based on the historical supply and demand related indicators and the quasi-real-time supply and demand related indicators respectively; calculates the final price adjustment multiplier based on the calculation of the historical price adjustment multiplier and the quasi-real-time adjustment multiplier; and adjusts the price of the online car-hailing order in the current honeycomb area using the final price adjustment multiplier. The present invention combines quasi-real-time with historical data, and comprehensively considers multiple indicators such as the first round winning rate, the first round car dispatch rate, the average dispatch number, the order quantity and the average dispatch time, so as to comprehensively evaluate the tension of the supply and demand relationship, comprehensively consider the supply and demand situation in the area where the current order is located, and better predict future supply and demand changes.

[0120] Further, as Figure 1 The specific implementation of the present invention provides a dynamic price adjustment device based on the supply and demand relationship of online car-hailing, such as Figure 3 As shown, the device may include: a data acquisition module 310, an indicator analysis module 320, a data processing module 330, a multiplier calculation module 340 and a price adjustment application module 350.

[0121] The data acquisition module 310 may be used to determine the current honeycomb area in the target city and acquire historical order data and quasi-real-time order data in the current honeycomb area;

[0122] The indicator analysis module 320 can be used to analyze the supply and demand related indicators of the current honeycomb area based on the historical order data and the quasi-real-time order data; the supply and demand related indicators include the historical supply and demand related indicators and the quasi-real-time supply and demand related indicators;

[0123] The data processing module 330 may be used to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively;

[0124] The multiplier calculation module 340 may be used to calculate the final price adjustment multiplier based on the historical price adjustment multiplier and the quasi-real-time adjustment multiplier using the preset price adjustment rules;

[0125] The price adjustment application module 350 can be used to adjust the price of online car-hailing orders in the current honeycomb area using the final price adjustment ratio.

[0126] Optionally, the data processing module 330 may also be used to calculate the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively;

[0127] The historical supply-demand tension and the real-time supply-demand tension are used to calculate the historical relative tension and the quasi-real-time relative tension of the current honeycomb area in the target city.

[0128] The historical relative tension and the quasi-real-time relative tension are used respectively to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio.

[0129] Optionally, the data processing module 330 may also be used to calculate the historical supply-demand tension of the current honeycomb region based on historical supply-demand related indicators using the following formula:

[0130]

[0131] a1+b1+c1+d1+e1=1

[0132] Among them, S1 is the historical supply-demand tension; A1 is the historical first-round winning rate; a1 is the historical first-round winning rate weight; B1 is the historical first-round vehicle dispatch rate; b1 is the historical first-round vehicle dispatch weight; C1 is the historical average dispatch times; c1 is the historical average dispatch times weight; D1 is the historical order volume; d1 is the historical order volume weight; E1 is the historical average dispatch time; e1 is the historical average dispatch time weight;

[0133] as well as,

[0134] Based on the quasi-real-time supply and demand related indicators, the following formula is used to calculate the quasi-real-time supply and demand tension in the current honeycomb area:

[0135]

[0136] a2+b2+c2+d2+e2=1

[0137] Among them, S2 is the tension of quasi-real-time supply and demand relationship; A2 is the quasi-real-time first-round winning rate; a2 is the weight of the quasi-real-time first-round winning rate; B2 is the quasi-real-time first-round vehicle dispatch rate; b2 is the weight of the quasi-real-time first-round vehicle dispatch rate; C2 is the average number of dispatches per quasi-real-time order; c2 is the weight of the average number of dispatches per quasi-real-time order; D2 is the quasi-real-time order volume; d2 is the weight of the quasi-real-time order volume; E2 is the average dispatch time per quasi-real-time order; e2 is the weight of the average dispatch time per quasi-real-time order.

[0138] Optionally, the data processing module 330 may also be used to obtain a historical supply-demand tension dataset and a real-time supply-demand related tension dataset of all honeycomb areas in the target city, and determine the median of the historical supply-demand tension dataset and the median of the real-time supply-demand related tension dataset;

[0139] Based on the historical supply and demand tension of the current honeycomb area, the historical relative tension is calculated using the following formula:

[0140]

[0141] Among them, Q1 is the historical relative tension; S1 is the historical supply and demand tension; M1 is the median of the historical supply and demand tension data set;

[0142] as well as,

[0143] Based on the quasi-real-time supply-demand tension in the current honeycomb area, the quasi-real-time relative tension is calculated using the following formula:

[0144]

[0145] Among them, Q2 is the quasi-real-time relative tension; S2 is the quasi-real-time supply and demand tension; M2 is the median of the quasi-real-time supply and demand tension data set.

[0146] Optionally, the data processing module 330 may also be used to calculate the historical price adjustment ratio based on the historical relative tension using the following formula:

[0147] Rate1=x1*arctan(Q1*x2+x3)+x4

[0148] Among them, Rate1 is the historical price adjustment ratio; Q1 is the historical relative tension; x1, x2, x3, x4 are constants;

[0149] as well as,

[0150] Based on the relative tension of quasi-real-time, the quasi-real-time price adjustment ratio is calculated using the following formula:

[0151] Rate2=x1*arctan(Q2*x2+x3)+x4

[0152] Among them, Rate2 is the quasi-real-time price adjustment ratio; Q2 is the quasi-real-time relative tension; x1, x2, x3, and x4 are constants.

[0153] Optionally, the multiplier calculation module 340 may be used to calculate the final price adjustment multiplier according to the preset historical price adjustment multiplier ratio weight and the quasi-real-time adjustment multiplier ratio weight, and the formula is as follows:

[0154] Rate=weight1*Rate1+weight2*Rate2

[0155] Among them, Rate is the final price adjustment ratio; weight1 is the weight of the historical price adjustment ratio; Rate1 is the historical price adjustment ratio; weight2 is the weight of the quasi-real-time price adjustment ratio; Rate2 is the quasi-real-time price adjustment ratio.

[0156] It should be noted that for other corresponding descriptions of the functional modules involved in the dynamic pricing device based on the supply and demand relationship of online car-hailing provided in the embodiment of the present invention, please refer to Figure 1 The corresponding description of the method shown will not be repeated here.

[0157] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of dynamic price adjustment based on the supply and demand relationship of online car-hailing as described in any of the above embodiments are implemented.

[0158] Based on the above Figure 1 The method shown and Figure 3 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 4 As shown, the computer device may include a communication bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device, wherein each functional unit can communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the steps of the dynamic pricing method based on the supply and demand relationship of online car-hailing described in the above embodiment.

[0159] Those skilled in the art can clearly understand that the specific working processes of the systems, devices, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they are not further described here.

[0160] In addition, the functional units in various embodiments of the present invention may be physically independent of each other, or two or more functional units may be integrated together, or all functional units may be integrated into one processing unit. The above integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

[0161] Those skilled in the art can understand that if the integrated functional unit is implemented in the form of software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can essentially or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, which includes a number of instructions to enable a computing device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention when running the instructions. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes.

[0162] Alternatively, all or part of the steps of implementing the aforementioned method embodiments may be accomplished by hardware associated with program instructions (such as a computing device such as a personal computer, a server, or a network device), and the program instructions may be stored in a computer-readable storage medium. When the program instructions are executed by a processor of a computing device, the computing device executes all or part of the steps of the methods described in the embodiments of the present invention.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that within the spirit and principles of the present invention, the technical solutions described in the aforementioned embodiments can still be modified, or some or all of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate from the protection scope of the present invention.

Claims

1. A dynamic pricing method based on the supply and demand relationship of online car-hailing, characterized in that: The method comprises: Determine a current honeycomb area in a target city, and obtain historical order data and quasi-real-time order data in the current honeycomb area; Based on the historical order data and the quasi-real-time order data, analyzing supply and demand related indicators of the current honeycomb area; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators; Calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively; Calculate the final price adjustment ratio based on the calculated historical price adjustment ratio and the quasi-real-time adjustment ratio by using the preset price adjustment rule; The final price adjustment ratio is used to adjust the price of online car-hailing orders in the current honeycomb area.

2. The method according to claim 1, characterized in that The supply and demand related indicators include the first-round winning rate, the first-round vehicle dispatch rate, the average dispatch times per order, the order quantity and the average dispatch time per order; The first-round winning rate is the ratio of user orders to drivers successfully matched in the first round of dispatch; The first round of available car dispatch rate is the ratio of available drivers successfully selected for user orders in the first round of dispatch; The average dispatch number is the ratio of the number of drivers with available vehicles to the number of available vehicles in the first round of dispatch; The order quantity is the number of orders placed starting from the current honeycomb area; The average scheduling time for each order is the average scheduling time for all orders placed.

3. The method according to claim 1, characterized in that The calculating of the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively includes: Calculating the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively; Calculate the historical relative tension and the quasi-real-time relative tension of the current honeycomb area in the target city by using the historical supply-demand tension and the real-time supply-demand correlation tension respectively; The historical relative tension and the quasi-real-time relative tension are respectively used to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio.

4. The method according to claim 3, characterized in that The calculating the historical supply-demand relationship tension and the quasi-real-time supply-demand relationship tension of the current honeycomb area based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively includes: Based on the historical supply and demand related indicators, the historical supply and demand tension of the current honeycomb area is calculated using the following formula: a1+b1+c1+d1+e1=1 Among them, S1 is the historical supply-demand tension; A1 is the historical first-round winning rate; a1 is the historical first-round winning rate weight; B1 is the historical first-round vehicle dispatch rate; b1 is the historical first-round vehicle dispatch weight; C1 is the historical average dispatch times; c1 is the historical average dispatch times weight; D1 is the historical order volume; d1 is the historical order volume weight; E1 is the historical average dispatch time; e1 is the historical average dispatch time weight; as well as, Based on the quasi-real-time supply and demand related indicators, the quasi-real-time supply and demand tension of the current honeycomb area is calculated using the following formula: a2+b2+c2+d2+e2=1 Among them, S2 is the tension of quasi-real-time supply and demand relationship; A2 is the quasi-real-time first-round winning rate; a2 is the weight of the quasi-real-time first-round winning rate; B2 is the quasi-real-time first-round vehicle dispatch rate; b2 is the weight of the quasi-real-time first-round vehicle dispatch rate; C2 is the average number of dispatches per quasi-real-time order; c2 is the weight of the average number of dispatches per quasi-real-time order; D2 is the quasi-real-time order volume; d2 is the weight of the quasi-real-time order volume; E2 is the average dispatch time per quasi-real-time order; e2 is the weight of the average dispatch time per quasi-real-time order.

5. The method according to claim 3, characterized in that: The calculating the historical relative tension and the quasi-real-time relative tension of the current honeycomb area in the target city by respectively using the historical supply-demand tension and the real-time supply-demand correlation tension, comprises: Obtaining a historical supply-demand tension dataset and a real-time supply-demand related tension dataset of all honeycomb areas in the target city, and determining the median of the historical supply-demand tension dataset and the median of the real-time supply-demand related tension dataset; Based on the historical supply-demand tension of the current honeycomb area, the historical relative tension is calculated using the following formula: Among them, Q1 is the historical relative tension; S1 is the historical supply and demand tension; M1 is the median of the historical supply and demand tension data set; as well as, Based on the quasi-real-time supply-demand tension of the current honeycomb area, the quasi-real-time relative tension is calculated using the following formula: Among them, Q2 is the quasi-real-time relative tension; S2 is the quasi-real-time supply and demand tension; M2 is the median of the quasi-real-time supply and demand tension data set.

6. The method according to claim 3, characterized in that The calculating of the historical price adjustment ratio and the quasi-real-time price adjustment ratio by respectively using the historical relative tension and the quasi-real-time relative tension includes: Based on the historical relative tension, the historical price adjustment ratio is calculated using the following formula: Rate1=x1*arctan(Q1*x2+x3)+x4 Among them, Rate1 is the historical price adjustment ratio; Q1 is the historical relative tension; x1, x2, x3, x4 are constants; as well as, Based on the quasi-real-time relative tension, the quasi-real-time price adjustment ratio is calculated using the following formula: Rate2=x1*arctan(Q2*x2+x3)+x4 Among them, Rate2 is the quasi-real-time price adjustment ratio; Q2 is the quasi-real-time relative tension; x1, x2, x3, and x4 are constants.

7. The method according to any one of claims 1 to 6, characterized in that: The method of calculating the final price adjustment ratio by using the preset price adjustment rule based on the calculated historical price adjustment ratio and the quasi-real-time adjustment ratio includes: The final price adjustment ratio is calculated based on the preset historical price adjustment ratio weight and the quasi-real-time adjustment ratio weight. The formula is as follows: Rate=weight1*Rate1+weight2*Rate2 Among them, Rate is the final price adjustment ratio; weight1 is the weight of the historical price adjustment ratio; Rate1 is the historical price adjustment ratio; weight2 is the weight of the quasi-real-time price adjustment ratio; Rate2 is the quasi-real-time price adjustment ratio.

8. A dynamic pricing device based on the supply and demand relationship of online car-hailing, characterized in that: The device comprises: A data acquisition module, used to determine a current honeycomb area in a target city, and acquire historical order data and quasi-real-time order data in the current honeycomb area; An indicator analysis module, used to analyze supply and demand related indicators of the current honeycomb area based on the historical order data and the quasi-real-time order data; the supply and demand related indicators include historical supply and demand related indicators and quasi-real-time supply and demand related indicators; A data processing module, used to calculate the historical price adjustment ratio and the quasi-real-time adjustment ratio based on the historical supply-demand related indicators and the quasi-real-time supply-demand related indicators respectively; A multiplier calculation module, used to calculate a final price adjustment multiplier based on the calculated historical price adjustment multiplier and the quasi-real-time adjustment multiplier by using a preset price adjustment rule; The price adjustment application module is used to adjust the price of the online car-hailing orders in the current honeycomb area using the final price adjustment ratio.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the dynamic pricing method based on the supply and demand relationship of online car-hailing as described in any one of claims 1 to 7.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the dynamic pricing method based on the supply and demand relationship of online car-hailing as described in any one of claims 1 to 7.

Images