Method and device for predicting earnings of high-altitude leasing equipment

Abstract

The invention discloses a high-altitude leasing equipment income prediction method and device, and relates to the field of big data processing, and the method comprises the steps: determining the equipment information of to-be-tested equipment; based on a lease unit price prediction model corresponding to the target equipment type, obtaining an equipment lease unit price prediction value corresponding to the service life of the target equipment; based on a lease rate prediction model corresponding to the target equipment type, obtaining a lease rate prediction value of the to-be-tested equipment at a specified time node; and based on the equipment lease unit price prediction value and the lease rate prediction value, determining the predicted future income of the to-be-tested equipment at the specified time node. According to the method, the equipment lease unit price prediction value is determined by using the lease unit price prediction model, the lease rate prediction value is determined by referring to the adaptability of the equipment lease unit price to the market fluctuation and the differentiated influence of different industry demands on the equipment lease unit price, the lease rate prediction accuracy in the complex market environment is ensured, and the lease rate prediction efficiency is improved. Therefore, the high-altitude leasing equipment income prediction accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of big data processing, and in particular to a method and device for predicting the revenue of high-altitude rental equipment. Background Art

[0002] Based on the sale and leaseback model, aerial work platform leasing service providers transfer the ownership of equipment assets to financial institutions and simultaneously sign a structured financial lease agreement to complete the leaseback of the target assets. Under this infrastructure, aerial work platform leasing service providers rely on professional leasing management capabilities to carry out equipment operating leases for terminal application scenarios, effectively obtain equipment operating income, and pay rent to financial institutions regularly based on the equipment operating income obtained. For financial institutions, it is necessary to effectively evaluate the coverage of the future income of equipment assets to the repayment ability of aerial work platform leasing service providers, and to accurately predict whether the income of aerial work platforms (which can be understood as aerial leasing equipment) is sufficient to match the factoring rent receivables provided by financial institutions.

[0003] When it comes to revenue forecasting for high-altitude rental equipment, traditional forecasting methods mostly rely on static parameters or single-dimensional analysis, which results in significant deviations between the forecast results and actual conditions. Summary of the invention

[0004] The present application provides a method and device for predicting the revenue of high-altitude rental equipment, with the aim of improving the prediction accuracy of the revenue of high-altitude rental equipment.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] A method for predicting the income of high-altitude rental equipment, comprising:

[0007] Determine the device information of the device to be tested; the device information includes the service life of the target device and the target device type;

[0008] Based on the rental price prediction model corresponding to the target equipment type, the equipment rental price prediction value corresponding to the service life of the target equipment is obtained; the rental price prediction model is used to output the maximum value of the target value and the equipment daily consumption cost; the target value is the product of the output value of the objective function and the target parameter; the objective function is a function with the equipment service life of the target equipment as the independent variable and the equipment rental price of the target equipment as the dependent variable; the target parameter is determined based on the market factor and the industry index trend factor;

[0009] Based on the rental rate prediction model corresponding to the target device type, the rental rate prediction value of the device under test at a specified time node is obtained; the rental rate prediction model is used to characterize the rental rate of the target device at multiple time nodes; the target device is a sample device belonging to the target device type;

[0010] Based on the predicted value of the equipment rental unit price and the predicted value of the rental rate, the predicted future income of the equipment under test at the specified time node is determined.

[0011] Optionally, the objective function is obtained based on logarithmic regression fitting of target equipment rental data, where the target equipment rental data includes daily equipment rental price samples of the target equipment in the past and historical equipment service life samples.

[0012] Optionally, the equipment information also includes the original value of the target equipment and the depreciation period of the target equipment, and the daily cost of the equipment is determined based on the original value of the target equipment, the depreciation period of the target equipment and the service life of the target equipment.

[0013] Optionally, the market factor is determined based on an aerial work platform rental price index, which is an indicator used to quantitatively describe the degree of change in the rental level of aerial rental equipment over time.

[0014] Optionally, the industry index trend factor is determined based on a client industry development trend index, and the client industry development trend index is an indicator used to quantitatively describe the degree of change in the level of added value of a client industry over time, and the client industry is an industry related to aerial work platforms.

[0015] Optionally, obtaining a predicted value of the equipment rental price corresponding to the service life of the target equipment based on a rental price prediction model corresponding to the target equipment type includes:

[0016] Acquire a rental unit price prediction model corresponding to the target equipment type;

[0017] The target equipment service life is used as the input of the rental price prediction model to obtain the equipment rental price prediction value output by the rental price prediction model; the rental price prediction model is P(UY,MKT,B,RV)=max(P(UY)*(1+MKT+B),RV), where P represents the equipment rental price prediction value, P(UY) represents the objective function, UY represents the equipment service life, MKT represents the market factor, B represents the industry index trend factor, and RV represents the equipment daily consumption cost.

[0018] Optionally, the training process of the occupancy rate prediction model includes:

[0019] Acquire the rental rate data of the target device in advance; the rental rate data of the target device includes the rental rate samples of the target device in each month in the past;

[0020] The target equipment rental rate data is fitted using a time series prediction algorithm to obtain a corresponding time series prediction model; the time series prediction model includes a Holt-Winters model, which is an R t (k)=L(t)+k*B(t)+S(t+ks), where R t (k) represents the occupancy rate forecast value for the period t+k after the period t, L(t) represents the time smoothing value, B(t) represents the time trend value, S(t) represents the seasonal smoothing value, s represents the preset cycle length, and t and k are both positive integers;

[0021] Based on the time series prediction model and combined with the industry index trend factor, the occupancy rate prediction model is determined; the occupancy rate prediction model is R t (k)=(L(t)+k*B(t)+S(t+ks))*(1+B / 12), where B represents the industry index trend factor.

[0022] A prediction device for high-altitude rental equipment revenue, comprising:

[0023] A device information determination unit, used to determine device information of the device to be tested; the device information includes the service life of the target device and the target device type;

[0024] A rental price prediction unit, for obtaining a predicted value of the equipment rental price corresponding to the service life of the target equipment based on a rental price prediction model corresponding to the target equipment type; the rental price prediction model is used to output a maximum value between a target value and a daily equipment consumption cost; the target value is the product of an output value of an objective function and a target parameter; the objective function is a function with the equipment service life of the target equipment as an independent variable and the equipment rental price of the target equipment as a dependent variable; the target parameter is determined based on market factors and industry index trend factors;

[0025] An occupancy rate prediction unit, configured to obtain an occupancy rate prediction value of the device under test at a specified time node based on an occupancy rate prediction model corresponding to the target device type; the occupancy rate prediction model is used to characterize the occupancy rate of the target device at multiple time nodes; the target device is a sample device belonging to the target device type;

[0026] A future revenue prediction unit is used to determine the predicted future revenue of the device under test at the specified time node based on the predicted value of the device rental unit price and the predicted value of the rental rate.

[0027] A storage medium includes a stored program, wherein the program executes the method for predicting the income of high-altitude rental equipment when executed by a processor.

[0028] An electronic device, comprising: a processor, a memory and a bus; the processor and the memory are connected via the bus;

[0029] The memory is used to store programs, and the processor is used to run programs, wherein the program executes the method for predicting the income of high-altitude rental equipment when the processor runs it.

[0030] The technical solution provided in the present application determines the target equipment type and target equipment service life of the equipment to be tested. Based on the rental unit price prediction model corresponding to the target equipment type, the predicted value of the equipment rental unit price corresponding to the service life of the target equipment is obtained. Based on the rental rate prediction model corresponding to the target equipment type, the rental rate prediction value of the equipment to be tested at a specified time node is obtained. Based on the equipment rental unit price prediction value and the rental rate prediction value, the predicted future income of the equipment to be tested at the specified time node is determined. The present application uses a rental unit price prediction model to determine the equipment rental unit price prediction value, refers to the adaptability of the equipment rental unit price to market fluctuations, and the differentiated impact of different industry demands on the equipment rental unit price, and uses the rental rate prediction model to determine the rental rate prediction value to ensure the accuracy of the rental rate prediction in a complex market environment. Combining the equipment rental unit price prediction value and the rental rate prediction value can improve the prediction accuracy of the income of high-altitude rental equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A flowchart of a method for predicting the income of high-altitude rental equipment provided in an embodiment of the present application;

[0033] Figure 2 A flow chart of another method for predicting the income of high-altitude rental equipment provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of the architecture of a device for predicting the revenue of high-altitude rental equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] In this application, relational terms such as first and second, etc. are used only 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. 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 more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0037] like Figure 1 As shown, it is a flow chart of a method for predicting the income of high-altitude rental equipment provided in an embodiment of the present application, including the following steps.

[0038] S101: Determine device information of a device to be tested.

[0039] The device information includes the target device's service life and the target device's type.

[0040] It should be noted that the equipment to be tested belongs to an aerial work platform. For the aerial work platform, the equipment service life of the aerial work platform specifically refers to the number of years the equipment has been in use. For example, if XX equipment has been in use for 3 years, the equipment service life of XX equipment can be set to 3 years.

[0041] In some examples, the service life of the aerial work platform can be determined based on the factory date of the aerial work platform. Assuming that the current system time is April 10, 2025, and the factory date of the aerial work platform is April 10, 2021, the service life of the aerial work platform can be determined to be 4 years.

[0042] In some examples, the equipment types of the aerial work platform include articulated boom equipment, straight boom equipment, scissor lift equipment, and other types of equipment.

[0043] Optionally, the device information of the device under test also includes the original value of the target device and the depreciation period of the target device.

[0044] In some examples, the original equipment value of the aerial work platform refers to the total cost spent by the company when purchasing (or making) the aerial work platform.

[0045] In some examples, the depreciation period of the aerial work platform is the period determined in accordance with specified policy rules.

[0046] In a possible implementation manner, the device information of the device under test may be obtained from a specified database.

[0047] S102: Based on the rental unit price prediction model corresponding to the target equipment type, obtain a predicted value of the equipment rental unit price corresponding to the service life of the target equipment.

[0048] Among them, the rental unit price prediction model is used to output the maximum value of the target value and the daily consumption cost of the equipment; the target value is the product of the output value of the objective function and the target parameter; the objective function is a function with the equipment service life of the target equipment as the independent variable and the equipment rental price of the target equipment as the dependent variable; the target parameter is determined based on market factors and industry index trend factors.

[0049] It should be noted that the target device is a sample device belonging to the target device type.

[0050] In some examples, target parameter=1+market factor+industry index trend factor.

[0051] Optionally, the implementation process of obtaining the equipment rental unit price prediction value corresponding to the target equipment service life based on the rental unit price prediction model corresponding to the target equipment type can be: obtaining the rental unit price prediction model corresponding to the target equipment type; taking the target equipment service life as the input of the rental unit price prediction model to obtain the equipment rental unit price prediction value output by the rental unit price prediction model; the rental unit price prediction model is P(UY,MKT,B,RV)=max(P(UY)*(1+MKT+B),RV), where P represents the equipment rental unit price prediction value, P(UY) represents the objective function, UY represents the equipment service life, MKT represents the market factor, B represents the industry index trend factor, and RV represents the equipment daily consumption cost.

[0052] In some examples, using the target equipment life as an input to the rental unit price prediction model can be understood as using the target equipment life as an input value of the objective function.

[0053] Optionally, the objective function is based on logarithmic regression fitting of target equipment rental data, where the target equipment rental data includes daily equipment rental price samples of the target equipment in the past and historical equipment service life samples.

[0054] In some examples, after obtaining the target equipment rental data from the specified data source, the target equipment rental data needs to be preprocessed, and the preprocessing process includes but is not limited to the following: If the fields contained in the target equipment rental data are equipment type, rental price, rental date, and equipment factory date, it is necessary to calculate the equipment service life of the equipment as of the rental date based on the two fields of equipment factory date and rental date, and round up the calculated value (that is, the equipment service life must be an integer); eliminate the data in the target equipment rental data where the equipment service life field is empty or less than or equal to 0.

[0055] In a possible implementation, by performing data analysis on equipment rental data of different equipment types, it is found that the equipment rental prices of different equipment types have obvious differences, indicating that the equipment rental price is related to the equipment type, and it is found that the equipment rental prices of different equipment years of use have obvious differences, indicating that the equipment life is related to the equipment type.

[0056] In a possible implementation, data analysis is performed on equipment rental data samples of type XX to obtain the corresponding relationship between the average rental price of the corresponding equipment of type XX (which can be regarded as the equipment rental price) and the equipment service life. Through this correspondence, it can be found that there is a decay trend between the equipment rental price and the equipment service life, and as the equipment service life increases, the decay trend of the equipment rental price gradually slows down. For this reason, regression fitting can be performed on the target equipment rental data to obtain the objective function P(UY).

[0057] In some examples, the types of regression fitting include, but are not limited to, linear regression and logarithmic regression. Optionally, the objective function may also be based on linear regression fitting of the target equipment rental data.

[0058] It is understandable that the objective function obtained by performing regression fitting on the target equipment rental data can essentially be understood as a decreasing function, which can theoretically decay without a lower limit. However, in the actual business process, if the equipment rental price cannot cover the daily cost of the equipment when the equipment is rented, the aerial work platform rental service provider will not rent the equipment. For this reason, a judgment formula is added to P(UY). If the output value of P(UY) (i.e. the equipment rental price) is lower than the daily cost of the equipment when the equipment is rented, the daily cost of the equipment should be selected as the equipment rental unit price.

[0059] Optionally, the daily equipment consumption cost is determined based on the original value of the target equipment, the depreciation period of the target equipment, and the service life of the target equipment.

[0060] In some examples, the equipment daily consumption cost is the sum of the equipment daily depreciation amount, the daily equipment management fee and the daily equipment maintenance fee. Specifically, the equipment daily consumption cost = the equipment daily depreciation amount + the daily equipment management fee + the daily equipment maintenance fee.

[0061] In a possible implementation, the daily depreciation amount of the equipment = the original value of the target equipment * (1-5%) * ((target equipment depreciation period - target equipment service life) / (target equipment depreciation period * (1 + target equipment depreciation period) / 2)) / 365.

[0062] In a possible implementation, the daily equipment management fee = original value of target equipment * 1‰ / 30.

[0063] In a possible implementation, single-day equipment maintenance fee = original value of target equipment * 5% / 365.

[0064] For aerial work platforms, the equipment rental price is not only related to the attributes of the equipment itself (i.e., equipment type and equipment service life), but also related to the overall rental environment of the aerial work platform. Therefore, market factors that can reflect the impact of the overall rental environment of the aerial work platform on the equipment rental price will be used as parameters of the rental unit price prediction model to improve the reliability of the rental unit price prediction model.

[0065] Optionally, the market factor is determined based on an aerial work platform rental price index, which is an indicator used to quantitatively describe the degree of change in the rental level of aerial rental equipment over time.

[0066] In some examples, the aerial work platform rental price index can be obtained from the Internet, for example, the lifting work platform rental price index from June 2023 to January 2025 released by the Construction Machinery Leasing Branch of the China Construction Machinery Industry Association can be obtained from the Internet as the aerial work platform rental price index.

[0067] In a possible implementation, a linear regression algorithm is used to perform a linear regression fit on the aerial work platform rental price index, and the corresponding equation Y=k*X+t can be obtained, where Y represents the rental price, k represents the slope, X represents the time (such as a certain month), and t represents the intercept. Given that aerial work platforms have a variety of equipment types, the rental price levels of each equipment type vary, and the k shown in the equation Y=k*X+t represents the average absolute rate of change, so the average absolute rate of change needs to be converted into the average relative rate of change, so that the expression of the market factor can be MKT=k / t*12.

[0068] For aerial work platforms, the equipment rental price will also be affected by the market supply and demand relationship. Therefore, the customer industry related to the aerial work platform will have an impact on the equipment rental price. Therefore, the industry index trend factor that can reflect the impact of the customer industry on the equipment rental price will be used as a parameter of the rental unit price prediction model to improve the reliability of the rental unit price prediction model.

[0069] Generally speaking, equipment rental prices are usually affected by the relationship between market supply and demand. When the market development trend of the customer industry is positive, the supply and demand relationship of the rental equipment will gradually tend to be in short supply, which will lead to an increase in equipment rental prices. On the contrary, if the market trend is not good, the price may fall. Therefore, when evaluating the trend of equipment rental prices, it is particularly necessary to take into account the customer industry with which the business is closely related, which can effectively improve the reliability of the rental unit price prediction model.

[0070] Optionally, the industry index trend factor is determined based on the client industry development trend index, which is an indicator used to quantitatively describe the degree of change in the level of added value of the client industry over time, and the client industry is an industry related to aerial work platforms.

[0071] In some examples, by analyzing the business database of an aerial work platform rental service provider, it can be determined that the customer industries include construction, wholesale and retail, and manufacturing.

[0072] In some examples, the client industry development trend index can be obtained from data sources provided by the Internet. Specifically, the development trend index that can represent the construction industry, wholesale and retail industry, and manufacturing industry is collected from the database of the National Bureau of Statistics website. For example, the annual construction industry value-added index from 2004 to 2024 is collected from the database of the National Bureau of Statistics website as the construction industry development trend index, the annual wholesale and retail industry value-added index from 2004 to 2024 is used as the wholesale and retail industry development trend index, and the manufacturing PMI index from September 2022 to February 2025 is used as the manufacturing industry development trend index.

[0073] In a possible implementation, polynomial fitting is used for the construction industry value-added index of each year to obtain the first equation for calculating the future annual growth rate of the construction industry value-added. Specifically, C=ax 3 -bx 2 +0.0245x+c and R 2 = d, where C represents the growth rate of added value of the construction industry, x represents the time node (specifically, the year), R 2represents the square correlation coefficient, and a, b, c, and d are all constants. After determining the first equation, the growth rate of the added value of the construction industry in the specified future year can be determined based on the specified future year as input (for example, if the future income of the equipment under test in a certain month in 2025 is predicted, 2025 can be used as the specified future year, and x=n is entered in the first equation, where n is the index of the specified future year).

[0074] In a possible implementation, polynomial fitting is used for the wholesale and retail industry value-added index of each year to obtain a second equation for calculating the future annual growth rate of the wholesale and retail industry value-added. Specifically, W=ax 3 -bx 2 +cx+d and R 2 =e, where W represents the growth rate of added value of wholesale and retail industry, x represents the time node (specifically, the year), R 2 represents the square correlation coefficient, and a, b, c, d, and e are all constants. After determining the second equation, the growth rate of wholesale and retail value-added in the specified future year can be determined based on the specified future year as input (for example, if the future income of the device under test in a certain month in 2025 is predicted, 2025 can be used as the specified future year, and x=n is entered in the second equation, where n is the index of the specified future year).

[0075] In a possible implementation, the manufacturing PMI index of each year is fitted using a moving average algorithm to obtain an equation for calculating the future monthly growth rate of the manufacturing PMI index, and the equation for the future monthly growth rate of the manufacturing PMI index is multiplied by 12 to obtain a third-party formula for calculating the future annual growth rate of the manufacturing PMI index. Specifically, M t =1 / 2*(M t +M t-1 ) and R 2 =a, where M represents the growth rate of the manufacturing PMI index, t represents the time node (specifically, the year), R 2 Represents the square correlation coefficient, and a is a constant. After determining the third-party program, the manufacturing PMI index growth rate for the specified future year can be determined based on the specified future year as input (for example, if the future revenue of the equipment under test in a certain month in 2025 is predicted, 2025 can be used as the specified future year, and t=n is entered in the third-party program, where n is the index of the specified future year).

[0076] In some examples, the expression of the industry index trend factor can be B=(C*C 占比 +W*W 占比 +M*M 占比 ) / (C 占比 +W 占比 +M 占比), where C represents the growth rate of added value of construction industry in the specified future year, W represents the growth rate of added value of wholesale and retail industry in the specified future year, M represents the growth rate of manufacturing PMI index in the specified future year, C 占比 Represents the proportion of the construction industry's business volume in the total business volume of aerial work platform rental service providers, W 占比 Represents the proportion of wholesale and retail business in the total business of aerial work platform rental service providers, M 占比 Represents the proportion of manufacturing business volume in the total business volume of aerial work platform rental service providers. Generally speaking, C 占比 , W 占比 and M 占比 It can be obtained when analyzing the business database of aerial work platform rental service providers.

[0077] In a possible implementation, the rental unit price prediction model corresponding to the crank arm equipment may be: P(UY,MKT,B,RV) 曲臂 =max(P(UY) 曲臂 *(1+MKT+B),RV).

[0078] In a possible implementation, the rental unit price prediction model corresponding to the straight arm equipment can be: P(UY,MKT,B,RV) 直臂 =max(P(UY) 直臂 *(1+MKT+B),RV).

[0079] In a possible implementation, the rental unit price prediction model corresponding to the straight arm equipment can be: P(UY,MKT,B,RV) 剪叉 =max(P(UY) 剪叉 *(1+MKT+B),RV).

[0080] S103: Based on the occupancy rate prediction model corresponding to the target device type, obtain an occupancy rate prediction value of the device to be tested at a specified time node.

[0081] The occupancy rate prediction model is used to characterize the occupancy rate of the target device at multiple time nodes, and the target device is a sample device belonging to the target device type.

[0082] In some examples, the type of time node includes but is not limited to month, quarter, cycle, etc. If the type of time node is considered as month, the rental rate prediction model can be used to characterize the rental rate of the target device in 12 months. If the type of time node is considered as quarter, the rental rate prediction model can be used to characterize the rental rate of the target device in 4 quarters.

[0083] It should be noted that the designated time node can be understood as a certain month or quarter in the future year. Specifically, the designated time node can be set by technical personnel according to actual business needs.

[0084] Optional, the occupancy rate prediction model training process can be found in Figure 2 The steps are shown and the corresponding explanations.

[0085] S104: Determine the predicted future revenue of the equipment under test at a specified time point based on the predicted value of the equipment rental unit price and the predicted value of the rental rate.

[0086] Among them, after obtaining the predicted value of the equipment rental unit price and the predicted value of the rental rate, combined with the number of days included in the specified time node, the predicted future income of the equipment to be tested at the specified time node can be calculated.

[0087] In some examples, predicted future revenue = predicted equipment rental unit price * predicted rental rate * number of days at a specified time node.

[0088] In a possible implementation, if the designated time node is January, the number of days in the designated time node may be set to 31; if the designated time node is January to March, the number of days in the designated time node may be set to 90 days.

[0089] It should be noted that by fitting the equipment price attenuation curve through historical data (i.e., target equipment rental data), a logarithmic regression model is introduced to characterize the marginal decreasing characteristics of the equipment rental unit price as the equipment service life increases, and market factors and industry index trend factors are constructed. The macro index of the construction machinery rental market and the economic development indicators of the customer industry are dynamically embedded in the rental unit price forecast model to ensure that the price forecast results synchronously reflect changes in the market environment and industrial trends, thereby enhancing the adaptability of the equipment rental unit price forecast to market fluctuations.

[0090] It is understandable that the equipment daily consumption cost is embedded in the rental price forecast model as a threshold judgment condition to ensure that the forecast price meets the bottom line of the enterprise's operating costs, avoid decision-making risks caused by theoretical model deviations, and ensure that the equipment rental price forecast value meets the actual business profit logic, avoiding the risk of losses caused by rental price forecast model deviations. Adding industry index trend factors to the rental price forecast model allows the equipment rental price forecast value to reflect the differentiated impact of different industry demands on the equipment rental price.

[0091] It can be understood that the embodiment of the present application constructs a composite prediction model that integrates the equipment attribute attenuation law, market dynamic index, and industry economic cycle (i.e., the combined use of the rental unit price prediction model and the occupancy rate prediction model), which significantly improves the accuracy, explainability and adaptability of the aerial work platform revenue forecast to a complex economic environment, and provides reliable quantitative decision-making support for equipment asset management, rental pricing strategy optimization and enterprise resource planning.

[0092] The process shown in S101-S104 above uses the rental price prediction model to determine the equipment rental price prediction value, refers to the adaptability of the equipment rental price prediction value to market fluctuations, and the differentiated impact of different industry demands on the equipment rental price prediction value, and uses the rental rate prediction model to determine the rental rate prediction value to ensure the accuracy of the rental rate prediction in a complex market environment. Combining the equipment rental price prediction value and the rental rate prediction value can improve the prediction accuracy of the high-altitude rental equipment revenue.

[0093] like Figure 2 As shown, it is a flow chart of another method for predicting the income of high-altitude rental equipment provided in an embodiment of the present application, including the following steps.

[0094] S201: Pre-acquire rental rate data of target equipment.

[0095] The target equipment rental rate data includes rental rate samples of the target equipment in each month in the past.

[0096] In some examples, the rental year and month, equipment type, rental days, total days, rental rate and other field data of the target equipment can be obtained from the specified database, where the rental days represent the number of equipment rented out every day, the total days represent the total number of equipment that can be rented out every day, and the daily rental rate of the target equipment can be regarded as rental days / total days. Specifically, when the missing rate of the rental days, total days, rental rate and other fields does not meet the requirements, the interpolation method can be used to supplement the missing data. In addition, when the outliers of the rental days, total days, rental rate and other fields do not meet the requirements, the corresponding outliers can be replaced by moving averages, or the outliers can be deleted and supplemented by interpolation.

[0097] S202: Using a time series prediction algorithm, fit the target equipment rental rate data to obtain a corresponding time series prediction model.

[0098] Among them, the time series prediction model includes the Holt-Winters model, which is an R t (k)=L(t)+k*B(t)+S(t+ks), where R t(k) represents the occupancy rate forecast value for the t+k period after the t period, L(t) represents the time smoothing value, B(t) represents the time trend value, S(t) represents the seasonal smoothing value, s represents the preset cycle length, and t and k are both positive integers.

[0099] In some examples, given that the rental rate of the target equipment shows periodic fluctuations over time and has a certain correlation with factors such as time and season, a time series prediction algorithm is used to fit the rental rate.

[0100] In a possible implementation, the trend and seasonality in the Holt-Winters model can be set as additive, and the number of cycles can be regarded as a periodic parameter.

[0101] In a possible implementation, using the rental rate data of the crank arm equipment, the determined time series prediction model can be: L(t) 曲臂 =a*(R(t) 曲臂 -S(ts) 曲臂 )+(1-a)*L(t-1) 曲臂 ; B(t) 曲 Arm = a*(L(t) 曲臂 -L(t-1) 曲臂 )+(1-a)*B(t-1) 曲臂 ; S(t) 曲臂 =S(ts) 曲臂 ; Rt(k) 曲臂 =(L(t) 曲臂 +k*B(t) 曲臂 +S(t+ks) 曲臂 ).

[0102] In a possible implementation, using the rental rate data of the straight arm equipment, the determined time series prediction model can be: L(t) 直臂 =a*(R(t) 直臂 -S(ts) 直臂 )+(1-a)*L(t-1) 直臂 ; B(t) 直臂 =a*(L(t) 直臂 -L(t-1) 直臂 )+(1-a)*B(t-1) 直臂 ; S(t) 直臂 =b*(R(t) 直臂 -L(t) 直臂 )+(1-b)*S(ts) 直臂 ; Rt(k) 直臂 =(L(t) 直臂 +k*B(t) 直臂 +S(t+ks)直臂 ).

[0103] In a possible implementation, using the rental rate data of the scissor lift equipment, the determined time series prediction model can be: L(t) 剪叉 =a*(R(t) 剪叉 -S(ts) 剪叉 )+(1-a)*L(t-1) 剪叉 ; B(t) 剪叉 =c*(L(t) 剪叉 -L(t-1) 剪叉 )+(1-c)*B(t-1) 剪叉 ; S(t) 剪叉 =d*(R(t) 剪叉 -L(t) 剪叉 )+(1-d)*S(ts) 剪叉 ; Rt(k) 剪叉 =(L(t) 剪叉 +k*B(t) 剪叉 +S(t+ks) 剪叉 ).

[0104] It should be noted that a, b, c and d shown in the above embodiment are all constants determined by corresponding occupancy rate data.

[0105] S203: Determine an occupancy rate prediction model based on the time series prediction model and in combination with the industry index trend factor.

[0106] Among them, the occupancy rate prediction model is R t (k)=(L(t)+k*B(t)+S(t+ks))*(1+B / 12), where B represents the industry index trend factor.

[0107] It should be noted that since the customer industry will not only affect the changes in equipment rental prices, but also the equipment rental rate, the industry index trend factor is added to the time series prediction model to form the final rental rate prediction model.

[0108] Generally speaking, the development of the customer industry will not only affect the change of rental prices, but also the equipment rental rate. If the customer industry is more prosperous, more aerial work platforms will be required, resulting in a higher equipment rental rate. Conversely, when the customer industry is in a downturn, the equipment rental rate will also decrease.

[0109] The process shown in S201-S203 above can utilize the rental rate data of the target equipment and combine it with the industry index trend factor to train a rental rate prediction model. The rental rate prediction model uses the Holt-Winters model to capture the linearity, trend and seasonal fluctuation of the rental rate, and uses the industry index trend factor for secondary correction, breaking through the limitations of traditional methods for short-term periodicity and long-term trend correlation analysis, improving the accuracy of rental rate prediction in a complex market environment, and providing a favorable basis for predicting the rental rate of the equipment under test.

[0110] like Figure 3 As shown, it is a schematic diagram of the architecture of a device for predicting the income of high-altitude rental equipment provided in an embodiment of the present application, including the steps shown below.

[0111] The device information determination unit 100 is used to determine the device information of the device to be tested; the device information includes the service life of the target device and the target device type.

[0112] The rental price prediction unit 200 is used to obtain the equipment rental price prediction value corresponding to the service life of the target equipment based on the rental price prediction model corresponding to the target equipment type; the rental price prediction model is used to output the maximum value of the target value and the equipment daily consumption cost; the target value is the product of the output value of the objective function and the target parameter; the objective function is a function with the equipment service life of the target equipment as the independent variable and the equipment rental price of the target equipment as the dependent variable; the target parameter is determined based on market factors and industry index trend factors.

[0113] Optionally, the objective function is based on logarithmic regression fitting of target equipment rental data, where the target equipment rental data includes daily equipment rental price samples of the target equipment in the past and historical equipment service life samples.

[0114] Optionally, the equipment information also includes the original value of the target equipment and the depreciation period of the target equipment. The daily cost of the equipment is determined based on the original value of the target equipment, the depreciation period of the target equipment and the service life of the target equipment.

[0115] Optionally, the market factor is determined based on an aerial work platform rental price index, which is an indicator used to quantitatively describe the degree of change in the rental level of aerial rental equipment over time.

[0116] Optionally, the industry index trend factor is determined based on the client industry development trend index, which is an indicator used to quantitatively describe the degree of change in the level of added value of the client industry over time, and the client industry is an industry related to aerial work platforms.

[0117] Optionally, the rental unit price prediction unit 200 is specifically used to: obtain a rental unit price prediction model corresponding to the target equipment type; use the service life of the target equipment as the input of the rental unit price prediction model to obtain the equipment rental unit price prediction value output by the rental unit price prediction model; the rental unit price prediction model is P(UY,MKT,B,RV)=max(P(UY)*(1+MKT+B),RV), where P represents the equipment rental unit price prediction value, P(UY) represents the objective function, UY represents the equipment service life, MKT represents the market factor, B represents the industry index trend factor, and RV represents the daily consumption cost of the equipment.

[0118] The occupancy rate prediction unit 300 is used to obtain the occupancy rate prediction value of the device under test at a specified time node based on the occupancy rate prediction model corresponding to the target device type; the occupancy rate prediction model is used to characterize the occupancy rate of the target device at multiple time nodes; the target device is a sample device belonging to the target device type.

[0119] Optionally, the training process of the rental rate prediction model includes: obtaining the rental rate data of the target equipment in advance; the rental rate data of the target equipment includes the rental rate samples of the target equipment in each month in the past; using the time series prediction algorithm to fit the rental rate data of the target equipment to obtain the corresponding time series prediction model; the time series prediction model includes the Holt-Winters model, and the Holt-Winters model is R t (k)=L(t)+k*B(t)+S(t+ks), where R t (k) represents the occupancy rate forecast value of the t+k period after the t period, L(t) represents the time smoothing value, B(t) represents the time trend value, S(t) represents the seasonal smoothing value, s represents the preset cycle length, and t and k are both positive integers; based on the time series prediction model, combined with the industry index trend factor, the occupancy rate prediction model is determined; the occupancy rate prediction model is R t (k)=(L(t)+k*B(t)+S(t+ks))*(1+B / 12), where B represents the industry index trend factor.

[0120] The future revenue prediction unit 400 is used to determine the predicted future revenue of the device under test at a specified time node based on the predicted value of the device rental unit price and the predicted value of the rental rate.

[0121] For each unit shown above, the rental price prediction model is used to determine the equipment rental price prediction value, and the adaptability of the equipment rental price prediction value to market fluctuations and the differentiated impact of different industry demands on the equipment rental price prediction value are referred to. The rental rate prediction model is used to determine the rental rate prediction value to ensure the accuracy of the rental rate prediction in a complex market environment. Combining the equipment rental price prediction value and the rental rate prediction value can improve the prediction accuracy of the high-altitude rental equipment revenue.

[0122] The present application also provides a computer-readable storage medium, which includes a stored program, wherein the program executes the method for predicting the income of high-altitude rental equipment provided by the present application.

[0123] The present application also provides an electronic device, including: a processor, a memory and a bus. The processor and the memory are connected via a bus, the memory is used to store programs, and the processor is used to run the programs, wherein the method for predicting the income of high-altitude rental equipment provided by the present application is executed when the programs are run.

[0124] In addition, the functions described above in the embodiments of the present application may be at least partially performed by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0125] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0126] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for predicting the income of high-altitude rental equipment, characterized in that: include: Determine the device information of the device under test; The device information includes the age of the target device and the type of the target device; Based on the rental price prediction model corresponding to the target equipment type, the equipment rental price prediction value corresponding to the service life of the target equipment is obtained; the rental price prediction model is used to output the maximum value of the target value and the equipment daily consumption cost; the target value is the product of the output value of the objective function and the target parameter; the objective function is a function with the equipment service life of the target equipment as the independent variable and the equipment rental price of the target equipment as the dependent variable; the target parameter is determined based on the market factor and the industry index trend factor; Based on the rental rate prediction model corresponding to the target device type, the rental rate prediction value of the device under test at a specified time node is obtained; the rental rate prediction model is used to characterize the rental rate of the target device at multiple time nodes; the target device is a sample device belonging to the target device type; Based on the predicted value of the equipment rental unit price and the predicted value of the rental rate, the predicted future income of the equipment under test at the specified time node is determined.

2. The method according to claim 1, characterized in that The objective function is obtained based on logarithmic regression fitting of target equipment rental data, where the target equipment rental data includes daily equipment rental price samples of the target equipment in the past and historical equipment service life samples.

3. The method according to claim 1, characterized in that The equipment information also includes the original value of the target equipment and the depreciation period of the target equipment. The daily cost of the equipment is determined based on the original value of the target equipment, the depreciation period of the target equipment and the service life of the target equipment.

4. The method according to claim 1, characterized in that: The market factor is determined based on the aerial work platform rental price index, which is an indicator used to quantitatively describe the degree of change in the rental level of aerial rental equipment in the past period of time.

5. The method according to claim 1, characterized in that The industry index trend factor is determined based on the customer industry development trend index. The customer industry development trend index is an indicator used to quantitatively describe the degree of change in the level of added value of the customer industry in the past period of time. The customer industry is an industry related to aerial work platforms.

6. The method according to claim 1, characterized in that Based on the rental unit price prediction model corresponding to the target equipment type, obtaining the equipment rental unit price prediction value corresponding to the service life of the target equipment, including: Acquire a rental unit price prediction model corresponding to the target equipment type; The target equipment service life is used as the input of the rental price prediction model to obtain the equipment rental price prediction value output by the rental price prediction model; the rental price prediction model is P(UY,MKT,B,RV)=max(P(UY)*(1+MKT+B),RV), where P represents the equipment rental price prediction value, P(UY) represents the objective function, UY represents the equipment service life, MKT represents the market factor, B represents the industry index trend factor, and RV represents the equipment daily consumption cost.

7. The method according to claim 1, characterized in that The training process of the occupancy rate prediction model includes: Acquire the rental rate data of the target device in advance; the rental rate data of the target device includes the rental rate samples of the target device in each month in the past; The target equipment rental rate data is fitted using a time series prediction algorithm to obtain a corresponding time series prediction model; the time series prediction model includes a Holt-Winters model, which is an R t (k)=L(t)+k*B(t)+S(t+ks), where R t (k) represents the occupancy rate forecast value for the period t+k after the period t, L(t) represents the time smoothing value, B(t) represents the time trend value, S(t) represents the seasonal smoothing value, s represents the preset cycle length, and t and k are both positive integers; Based on the time series prediction model and combined with the industry index trend factor, the occupancy rate prediction model is determined; the occupancy rate prediction model is R t (k)=(L(t)+k*B(t)+S(t+ks))*(1+B / 12), where B represents the industry index trend factor.

8. A prediction device for high-altitude rental equipment revenue, characterized in that: include: A device information determination unit, used to determine device information of the device under test; The device information includes the age of the target device and the type of the target device; A rental price prediction unit, for obtaining a predicted value of the equipment rental price corresponding to the service life of the target equipment based on a rental price prediction model corresponding to the target equipment type; the rental price prediction model is used to output a maximum value between a target value and a daily equipment consumption cost; the target value is the product of an output value of an objective function and a target parameter; the objective function is a function with the equipment service life of the target equipment as an independent variable and the equipment rental price of the target equipment as a dependent variable; the target parameter is determined based on market factors and industry index trend factors; An occupancy rate prediction unit, configured to obtain an occupancy rate prediction value of the device under test at a specified time node based on an occupancy rate prediction model corresponding to the target device type; the occupancy rate prediction model is used to characterize the occupancy rate of the target device at multiple time nodes; the target device is a sample device belonging to the target device type; A future revenue prediction unit is used to determine the predicted future revenue of the device under test at the specified time node based on the predicted value of the device rental unit price and the predicted value of the rental rate.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein the program, when executed by a processor, executes the method for predicting the income of high-altitude rental equipment as described in any one of claims 1-7.

10. An electronic device, characterized in that: include: processor, memory, and bus; The processor is connected to the memory via the bus; The memory is used to store programs, and the processor is used to run programs, wherein the program, when run by the processor, executes the method for predicting the income of high-altitude rental equipment as described in any one of claims 1-7.

Images