Device residual value calculation method, apparatus, and device

Abstract

This invention provides a method, apparatus, and device for calculating equipment residual value, comprising: acquiring equipment information, wherein the equipment information is information corresponding to the equipment whose residual value is to be calculated; selecting a residual value calculation method for the equipment whose residual value is to be calculated based on the equipment information; when the selected residual value calculation method is a machine learning method, constructing a feature set through the equipment information, processing the feature set through a machine learning model to obtain a first equipment residual value; when the selected residual value calculation method is a replacement cost method, obtaining a baseline residual value based on the equipment information, calculating a depreciation rate based on the equipment information, and calculating a second equipment residual value based on the baseline residual value and the depreciation rate. This achieves automated calculation of equipment residual value, reduces manual intervention, and improves the efficiency and accuracy of calculating equipment residual value.

Description

Technical Field

[0001] This invention relates to the field of equipment evaluation, and more specifically to a method, apparatus, and equipment for calculating equipment residual value. Background Technology

[0002] With the development of equipment, the number of construction machinery and equipment is increasing day by day, but the used market for construction machinery and equipment is still in its infancy. The residual value assessment of construction machinery and equipment usually adopts a traditional manual assessment method.

[0003] However, traditional manual assessment methods rely on experience-based judgment, which often leads to differences in assessments due to varying levels of experience among assessors, resulting in low assessment efficiency and accuracy. Summary of the Invention

[0004] In view of this, embodiments of the present invention aim to provide a method, apparatus, and equipment for calculating the residual value of equipment, in order to solve the problems in the prior art where the residual value assessment of construction machinery equipment relies on experience-based judgment, data samples are scarce and scattered, some business units lack system support for equipment accounting, and valuation data is only stored in offline document form, resulting in low assessment efficiency. Alternatively, the valuation method may have incomplete elements, making it impossible to achieve dynamic and accurate valuation.

[0005] This invention provides a method for calculating the residual value of equipment, the method comprising: Obtain equipment information, which is the information corresponding to the equipment whose residual value is to be calculated; Based on the equipment information, select the residual value calculation method for the equipment whose residual value needs to be calculated; When the selected residual value calculation method is machine learning, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain the first equipment residual value. When the selected residual value calculation method is the replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate.

[0006] In one possible embodiment, when the selected residual value calculation method is a machine learning method, constructing a feature set using the device information, and processing the feature set using a machine learning model to obtain the first device residual value includes: Filter key information from the device information and construct a feature set based on the key information; The machine learning model is used to assign corresponding weights to each feature in the feature set. The first equipment residual value is calculated based on the feature set and the corresponding weights.

[0007] In one possible embodiment, when the selected residual value calculation method is the replacement cost method, obtaining a baseline residual value based on the equipment information, calculating the depreciation rate based on the equipment information, and calculating a second equipment residual value based on the baseline residual value and the depreciation rate include: Based on the equipment type and cargo space volume in the equipment information, obtain the baseline residual value; Based on the equipment brand in the equipment information, obtain the brand coefficient; Based on the equipment age in the equipment information, obtain the corresponding age-related depreciation rate and depreciation rate, as well as the corresponding age-related depreciation rate coefficient and technical condition depreciation rate coefficient; Based on the equipment information, obtain the equipment technical condition assessment score and the amount of impairment; The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and the corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient.

[0008] In one possible embodiment, the calculation of the second equipment residual value based on the baseline residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient includes: Multiply the stated age-based depreciation rate by the age-based depreciation rate coefficient to obtain the first product; The second product is obtained based on the technical condition depreciation rate coefficient and the equipment technical condition assessment score; The third product is obtained based on the second product and the depreciation rate; Multiply the brand coefficient and the impairment amount to obtain the fourth product; Add the first product to the third product to obtain a sum, and multiply the sum by the benchmark residual to obtain a fifth product; Subtracting the fifth product from the fourth product yields the second equipment residual value.

[0009] In one possible embodiment, before assigning corresponding weights to each feature in the feature set using a machine learning model, the method further includes: Obtain historical device feature data; According to the time parameters of the historical equipment feature data, the historical equipment feature data is divided to obtain the first historical equipment feature data and the second historical equipment feature data. The first historical equipment feature data is used for model training, and the second historical equipment feature data is used for model verification. The first historical device feature data is searched by grid search to obtain N sets of parameter combinations; The N parameter combinations are validated through cross-validation to obtain the parameter combination with the highest score; The initial machine learning model is trained using the parameter combination with the highest score to obtain the trained machine learning model. The trained machine learning model is tested using the second historical device feature data to obtain the machine learning model.

[0010] In one possible embodiment, after obtaining the first device residual value, the method further includes: Obtain the historical transaction prices corresponding to the equipment whose residual value is to be calculated; The residual value of the first equipment is compared with the historical transaction price to obtain the first valuation deviation; If the first valuation deviation is less than a preset deviation threshold, the first equipment residual value is determined to be a first equipment residual value that conforms to the preset rules, and then output.

[0011] In one possible embodiment, after calculating the second device residual value, the method further includes: Obtain the industry-specific threshold for the equipment; The residual value of the third equipment is calculated based on the industry rule threshold. The residual value of the second equipment is compared with the residual value of the third equipment to obtain the second valuation deviation; If the second valuation deviation is less than the preset deviation threshold, the second equipment residual value is determined to be the second equipment residual value that conforms to the preset rules, and then output.

[0012] In one possible embodiment, the method for selecting the residual value calculation method for the device to be calculated based on the device information includes: Based on the equipment information, determine the equipment type; When the equipment type is an excavator, machine learning is selected as the residual value calculation method for the equipment whose residual value is to be calculated. If the equipment type is not an excavator, the replacement cost method is selected as the method for calculating the residual value of the equipment to be calculated.

[0013] In a second aspect, the present invention provides a device for calculating the residual value of equipment, the device comprising: The acquisition module is used to acquire device information, which is the information corresponding to the device whose residual value is to be calculated; The selection module is used to select the residual value calculation method for the equipment whose residual value is to be calculated based on the equipment information. The construction module is used to construct a feature set based on the equipment information when the selected residual value calculation method is machine learning, and to process the feature set through a machine learning model to obtain the first equipment residual value. The calculation module is used to obtain a baseline residual value based on the equipment information when the selected residual value calculation method is the replacement cost method, calculate the depreciation rate based on the equipment information, and calculate a second equipment residual value based on the baseline residual value and the depreciation rate.

[0014] Thirdly, this application provides an electronic device, the device comprising: a memory and a processor; the memory being used to store related program code; the processor being used to call the program code to execute the device residual value calculation method described in any of the implementations of the first aspect.

[0015] Fourthly, this application provides a computer-readable storage medium for storing a computer program for executing the device residual value calculation method described in any implementation of the first aspect above.

[0016] Fifthly, this application provides a computer program product, which includes a computer program / instruction, and when the computer program / instruction is executed by a processor, it implements the device residual value calculation method described in any of the implementations of the first aspect above.

[0017] In the above implementation of the present invention, by acquiring equipment information, which is information corresponding to the equipment whose residual value is to be calculated; and selecting a residual value calculation method for the equipment based on the equipment information, thereby equipping different equipment with suitable calculation methods and improving the accuracy of residual value calculation; when the selected residual value calculation method is a machine learning method, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain a first equipment residual value; when the selected residual value calculation method is a replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate. This achieves automated calculation of equipment residual values, reduces manual intervention, and improves the efficiency and accuracy of calculating equipment residual values. Attached Figure Description

[0018] Figure 1 This is a flowchart of a method for calculating the residual value of equipment provided in an embodiment of the present invention.

[0019] Figure 2 The flowchart of step S104 provided in the embodiment of the present invention.

[0020] Figure 3A schematic diagram of a device for calculating the residual value of equipment provided in an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] One embodiment of the present invention provides a method for calculating the residual value of equipment. The method involves acquiring equipment information, specifically information corresponding to the equipment whose residual value is to be calculated; selecting a residual value calculation method based on the equipment information, thereby equipping different equipment with suitable calculation methods and improving the accuracy of residual value calculation; when the selected residual value calculation method is a machine learning method, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain a first equipment residual value; when the selected residual value calculation method is a replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate. This method automates the calculation of equipment residual value, reduces manual intervention, and improves the efficiency and accuracy of equipment residual value calculation.

[0024] Please see Figure 1 In one exemplary embodiment, a method for calculating the residual value of equipment is provided, which is applied to the residual value assessment scenario of used equipment. The method may include the following steps: S101: Obtain device information, wherein the device information is the information corresponding to the device whose residual value is to be calculated.

[0025] Specifically, the process involves acquiring equipment information corresponding to the device whose residual value is to be calculated. This equipment information can include comprehensive data on the device, encompassing static attribute data, dynamic attribute data, and market parameters. Static attribute data includes inherent equipment attributes such as brand, model, tonnage / cubic meter / meter range, manufacturing date, chassis type, power type, and battery brand. Dynamic attribute data includes usage status data such as service life, operating hours, cumulative idle time, recent idle status, condition level, and lock status. Maintenance data includes core component replacement records, number of major overhauls, total number of maintenance visits, and inspection scores. Market parameters can include market environment data, such as regional market dynamics, brand influence, seasonal factors, and provincial factors, as well as transaction and procedural data, such as the purchase price, historical transaction prices, procedural completeness, and transfer status. By acquiring comprehensive data on the equipment whose residual value is to be calculated, inaccurate residual value calculations can be avoided due to incomplete data, such as missing key indicators like condition level. For details on the specific fields, data types, and functions of the equipment information, please refer to Table 1.

[0026] Table 1 The parameters included in the above equipment information are for illustrative purposes only and do not constitute a limitation on the equipment information.

[0027] S102: Based on the equipment information, select the residual value calculation method for the equipment whose residual value is to be calculated.

[0028] In this embodiment, the residual value calculation method of the device to be calculated can be selected according to the type of device, thereby improving the compatibility between the device and the algorithm and improving the accuracy of calculating the residual value of the device.

[0029] Specifically, the step of selecting a residual value calculation method for the equipment to be calculated based on the equipment information may include: Based on the equipment information, determine the equipment type; When the equipment type is an excavator, machine learning is selected as the residual value calculation method for the equipment whose residual value is to be calculated. If the equipment type is not an excavator, the replacement cost method is selected as the method for calculating the residual value of the equipment to be calculated.

[0030] In the specific implementation process, the equipment type is determined based on the equipment information. For example, the model number in the equipment information value determines whether the equipment is an excavator. If the equipment type is an excavator, machine learning is selected as the method for calculating the residual value of the equipment to be calculated. If the equipment type is not an excavator, such as a diesel mixer truck or a pump truck, the replacement cost method is selected as the method for calculating the residual value of the equipment to be calculated. A machine learning model is specifically configured for excavators to deeply mine the dynamic data correlations of equipment use and maintenance, thereby achieving accurate calculation of the equipment's residual value. For other types of equipment, a replacement cost method model is specifically configured to calculate the equipment's residual value based on standardized industry rules, improving the accuracy of the calculated equipment residual value.

[0031] S103: When the selected residual value calculation method is machine learning, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain the first equipment residual value.

[0032] In this embodiment, when the selected residual value calculation method is machine learning, a feature set is constructed using the device information. The constructed feature set is then input into a machine learning model, which processes the feature set to obtain the first device residual value.

[0033] Specifically, when the selected residual value calculation method is machine learning, the step of constructing a feature set using the equipment information and processing the feature set using a machine learning model to obtain the first equipment residual value may include: Filter key information from the device information and construct a feature set based on the key information; The machine learning model is used to assign corresponding weights to each feature in the feature set. The first equipment residual value is calculated based on the feature set and the corresponding weights.

[0034] In this embodiment, given that the equipment type is an excavator and the residual value calculation method is machine learning, the equipment information can first be cleaned. This includes handling missing values, outliers, and integrating the data to remove outliers and supplement missing values, thereby reducing noise and improving the completeness of the equipment information. The outlier-handled equipment information is then integrated to obtain integrated equipment information. Key information in the integrated equipment information is further filtered. This key information may include equipment brand, tonnage, year of manufacture, service life, working hours, condition rating, new machine sales price, number of repairs, core component replacement status, province, and operating condition. Specifically, the feature importance ranking function of the XGBoost algorithm can be used to filter key features from the integrated equipment information. After obtaining the key information, a feature set is constructed. The specific process of constructing the feature set includes: determining sample units and assigning labels to the samples. For example, if the value to be calculated is the residual value of a piece of equipment, the sample unit can be the equipment information of a piece of equipment, and the assigned label can be residual value. Features are extracted from key information of a device, including numerical, categorical, temporal, and textual features. A feature set is obtained by combining the extracted features with assigned labels. This feature set is then input into a machine learning model, which assigns weights to each feature in the set; for example, a weight of 0.25 is assigned to working hours, 0.22 to years of use, and 0.18 to inspection score. Based on the feature set and its corresponding weights, the machine learning model calculates the first residual value of the device.

[0035] Furthermore, in order to improve the accuracy of the machine learning model in calculating the residual value of the first device, the machine learning model can be trained before assigning corresponding weights to each feature in the feature set through the machine learning model.

[0036] Specifically, in this embodiment, before assigning corresponding weights to each feature in the feature set using a machine learning model, the following steps are also included: Obtain historical device feature data; According to the time parameters of the historical equipment feature data, the historical equipment feature data is divided to obtain the first historical equipment feature data and the second historical equipment feature data. The first historical equipment feature data is used for model training, and the second historical equipment feature data is used for model verification. The first historical device feature data is searched by grid search to obtain N sets of parameter combinations; The N parameter combinations are validated through cross-validation to obtain the parameter combination with the highest score; The initial machine learning model is trained using the parameter combination with the highest score to obtain the trained machine learning model. The trained machine learning model is tested using the second historical device feature data to obtain the machine learning model.

[0037] In practice, historical equipment feature data can be used to train untrained machine learning models. First, historical equipment feature data is acquired, which can include comprehensive historical data about the equipment, such as inherent attributes, usage records, price references, maintenance habits, and images of key components. The historical equipment feature data is then divided according to its time parameters to obtain first and second historical equipment feature data. The first historical equipment feature data is used for model training, and the second historical equipment feature data is used for model validation. This allows for the evaluation of the machine learning model's generalization ability, detection of overfitting, and prevention of data leakage.

[0038] A grid search is used to search the first historical device feature data according to a preset parameter range, obtaining N sets of parameter combinations. Here, N is a positive integer greater than 1. Cross-validation is used to validate the N sets of parameter combinations, obtaining the score for each validation iteration. The average score for each set of parameters is calculated based on these scores. The combination with the highest average score is selected as the optimal parameter combination, i.e., the parameter combination with the highest score. The initial machine learning model is trained using this highest-scoring parameter combination to obtain the trained machine learning model. The trained machine learning model is then tested using the second historical device feature data. If the error between the predicted value output by the trained machine learning model and the preset value is less than a preset error, the machine learning model is considered complete. The preset error can be 15% or 10%, etc., and can be set according to the user's accuracy requirements.

[0039] After calculating the residual value of the first device, the residual value of the first device can be verified using the verification rules corresponding to the first device.

[0040] Specifically, after obtaining the first equipment residual value, the following steps are also included: Obtain the historical transaction prices corresponding to the equipment whose residual value is to be calculated; The residual value of the first equipment is compared with the historical transaction price to obtain the first valuation deviation; If the first valuation deviation is less than a preset deviation threshold, the first equipment residual value is determined to be a first equipment residual value that conforms to the preset rules, and then output.

[0041] In the specific implementation process, the historical transaction price corresponding to the equipment whose residual value is to be calculated is obtained, such as the historical transaction price of other excavator equipment. The residual value of the first equipment is compared with the historical transaction price to obtain a first valuation deviation; if the first valuation deviation is less than a preset deviation threshold, the residual value of the first equipment is determined to be a first equipment residual value that conforms to a preset rule, and is output.

[0042] S104: When the selected residual value calculation method is the replacement cost method, a baseline residual value is obtained based on the equipment information, the depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate.

[0043] In this embodiment, when the equipment type is determined to be a non-excavator and the selected residual value calculation method is the replacement cost method, the baseline residual value can be directly found based on the equipment information, and the depreciation rate can be calculated based on the equipment information. Thus, the second equipment residual value can be calculated based on the baseline residual value and the depreciation rate.

[0044] Among them, reference Figure 2 When the selected residual value calculation method is the replacement cost method, the steps of obtaining a baseline residual value based on the equipment information, calculating the depreciation rate based on the equipment information, and calculating the second equipment residual value based on the baseline residual value and the depreciation rate may specifically include: S1041, Obtain the baseline residual value based on the equipment type and cargo space volume in the equipment information; S1042, Obtain the brand coefficient based on the equipment brand in the equipment information; S1043, Based on the equipment age in the equipment information, obtain the corresponding age depreciation rate and depreciation rate, as well as the corresponding age depreciation rate coefficient and technical condition depreciation rate coefficient; S1044, Obtain the equipment technical condition assessment score and impairment amount based on the equipment information; S1045. The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and the corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient.

[0045] In the specific implementation process, the baseline residual value can be obtained based on the equipment type and cargo space volume in the equipment information. The baseline residual value can be obtained by searching the equipment database based on the equipment type and cargo space volume in the equipment information. The brand coefficient can be obtained based on the equipment brand in the equipment information. Based on the equipment age in the equipment information, the corresponding age-related depreciation rate and depreciation rate, as well as the corresponding age-related depreciation rate coefficient and technical condition depreciation rate coefficient, along with the equipment technical condition assessment score and impairment amount, can be obtained from a preset correspondence table.

[0046] Preset correspondence table The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and the corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient.

[0047] The specific steps for calculating the second equipment residual value based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient include: Multiply the stated age-based depreciation rate by the age-based depreciation rate coefficient to obtain the first product; The second product is obtained based on the technical condition depreciation rate coefficient and the equipment technical condition assessment score; The third product is obtained based on the second product and the depreciation rate; Multiply the brand coefficient and the impairment amount to obtain the fourth product; Add the first product to the third product to obtain a sum, and multiply the sum by the benchmark residual to obtain a fifth product; Subtracting the fifth product from the fourth product yields the second equipment residual value.

[0048] In the specific implementation process, the first product is obtained by multiplying the current age depreciation rate by the current age depreciation rate coefficient; the second product is obtained based on the technical condition depreciation rate coefficient and the equipment technical condition assessment score. Specifically, the equipment technical condition assessment score is divided by 100 to obtain the equipment technical condition assessment percentage, and the equipment technical condition assessment percentage is multiplied by the technical condition depreciation rate coefficient to obtain the second product. The third product is obtained based on the second product and the depreciation rate. Specifically, the difference between 1 and the depreciation rate is calculated, and the difference is multiplied by the second product to obtain the third product. The fourth product is obtained by multiplying the brand coefficient and the impairment amount; the first and third products are added together to obtain a sum, and the sum is multiplied by the baseline residual value to obtain a fifth product; the second equipment residual value is obtained by subtracting the fifth product from the fourth product. The specific formula for calculating the second equipment residual value is as follows: W = R×(α×c + β×(X / 100))×(1 - D) - F × γ Where W is the residual value of the second equipment, R is the baseline residual value, α is the age-related depreciation rate coefficient, β is the technical condition depreciation rate coefficient, and α + β = 1. C is the age-related depreciation rate, which is determined by querying the corresponding residual value rate based on the equipment's service life.

[0049] X represents the equipment's technical condition assessment score, ranging from [0, 100]. D represents the depreciation rate. F represents the impairment amount, including material and labor costs required to replace parts or restore functionality. γ represents the brand coefficient.

[0050] Assuming the equipment has a service life of 4 years, the depreciation rate is c = 45%, α = 0.6, β = 0.4, and the technical condition score is X = 82 points; the depreciation rate is D = 35%; and the brand coefficient is γ = 0.96. Substituting these values ​​into the formula W = R × (α × c + β × (X / 100)) × (1 - D) - F × γ, we get W = 62 × (0.6 × 0.45 + 0.4 × 0.82) × (1 - 0.35) - 3 × 0.96 ≈ 62 × (0.27 + 0.328) × 0.65 - 2.88 ≈ 62 × 0.598 × 0.65 - 2.88 ≈ 241,000.

[0051] After calculating the residual value of the second device, the residual value of the second device can be verified using the verification rules for the second device.

[0052] Specifically, after calculating the residual value of the second equipment, the following steps are also included: Obtain the industry-specific threshold for the equipment; The residual value of the third equipment is calculated based on the industry rule threshold. The residual value of the second equipment is compared with the residual value of the third equipment to obtain the second valuation deviation; If the second valuation deviation is less than the preset deviation threshold, the second equipment residual value is determined to be the second equipment residual value that conforms to the preset rules, and then output.

[0053] In the specific implementation process, by obtaining the equipment industry rule threshold, it is confirmed whether the second equipment residual value conforms to the preset rules, that is, whether the second equipment residual value is accurate. The equipment industry rule threshold can be the upper limit of the depreciation rate or the fluctuation range of the benchmark price. When the depreciation rate and benchmark price are at their upper limits, they are substituted into the calculation formula for the second equipment residual value to calculate the third equipment residual value. The second equipment residual value is compared with the third equipment residual value to obtain the second valuation deviation. If the second valuation deviation is less than the preset deviation threshold, the second equipment residual value is determined to conform to the preset rules, that is, the calculated accurate second equipment residual value, and is output. The preset deviation threshold can be set according to actual conditions, such as according to the user's deviation requirements.

[0054] Based on the method provided in the above embodiments, by acquiring equipment information, which is information corresponding to the equipment whose residual value is to be calculated; selecting a residual value calculation method for the equipment based on the equipment information, thereby equipping different equipment with suitable calculation methods and improving the accuracy of residual value calculation; when the selected residual value calculation method is a machine learning method, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain a first equipment residual value; when the selected residual value calculation method is the replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate. This achieves automated calculation of equipment residual values, reduces manual intervention, and improves the efficiency and accuracy of calculating equipment residual values.

[0055] Based on the above method embodiments, this invention also provides a device for calculating equipment residual value. See also... Figure 3 The diagram shown is a schematic diagram of a device for calculating the residual value of equipment provided in an embodiment of the present invention.

[0056] The device 300 includes: The acquisition module 301 is used to acquire device information, wherein the device information is the information corresponding to the device whose residual value is to be calculated; Selection module 302 is used to select the residual value calculation method for the equipment to be calculated based on the equipment information; The construction module 303 is used to construct a feature set based on the equipment information when the selected residual value calculation method is machine learning, and to process the feature set through a machine learning model to obtain the first equipment residual value. The calculation module 304 is used to obtain a baseline residual value based on the equipment information when the selected residual value calculation method is the replacement cost method, calculate the depreciation rate based on the equipment information, and calculate a second equipment residual value based on the baseline residual value and the depreciation rate.

[0057] In one possible implementation, when the selected residual value calculation method is a machine learning method, constructing a feature set using the device information, and processing the feature set using a machine learning model to obtain the first device residual value includes: Filter key information from the device information and construct a feature set based on the key information; The machine learning model is used to assign corresponding weights to each feature in the feature set. The first equipment residual value is calculated based on the feature set and the corresponding weights.

[0058] In one possible implementation, when the selected residual value calculation method is the replacement cost method, the process of obtaining a baseline residual value based on the equipment information, calculating a depreciation rate based on the equipment information, and calculating a second equipment residual value based on the baseline residual value and the depreciation rate includes: Based on the equipment type and cargo space volume in the equipment information, obtain the baseline residual value; Based on the equipment brand in the equipment information, obtain the brand coefficient; Based on the equipment age in the equipment information, obtain the corresponding age-related depreciation rate and depreciation rate, as well as the corresponding age-related depreciation rate coefficient and technical condition depreciation rate coefficient; Based on the equipment information, obtain the equipment technical condition assessment score and the amount of impairment; The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and the corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient.

[0059] In one possible implementation, the calculation of the second equipment residual value based on the baseline residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient includes: Multiply the stated age-based depreciation rate by the age-based depreciation rate coefficient to obtain the first product; The second product is obtained based on the technical condition depreciation rate coefficient and the equipment technical condition assessment score; The third product is obtained based on the second product and the depreciation rate; Multiply the brand coefficient and the impairment amount to obtain the fourth product; Add the first product to the third product to obtain a sum, and multiply the sum by the benchmark residual to obtain a fifth product; Subtracting the fifth product from the fourth product yields the second equipment residual value.

[0060] In one possible implementation, before assigning corresponding weights to each feature in the feature set using a machine learning model, the method further includes: Obtain historical device feature data; According to the time parameters of the historical equipment feature data, the historical equipment feature data is divided to obtain the first historical equipment feature data and the second historical equipment feature data. The first historical equipment feature data is used for model training, and the second historical equipment feature data is used for model verification. The first historical device feature data is searched by grid search to obtain N sets of parameter combinations; The N parameter combinations are validated through cross-validation to obtain the parameter combination with the highest score; The initial machine learning model is trained using the parameter combination with the highest score to obtain the trained machine learning model. The trained machine learning model is tested using the second historical device feature data to obtain the machine learning model.

[0061] In one possible implementation, after obtaining the first device residual value, the method further includes: Obtain the historical transaction prices corresponding to the equipment whose residual value is to be calculated; The residual value of the first equipment is compared with the historical transaction price to obtain the first valuation deviation; If the first valuation deviation is less than a preset deviation threshold, the first equipment residual value is determined to be a first equipment residual value that conforms to the preset rules, and then output.

[0062] In one possible implementation, after calculating the second device residual value, the method further includes: Obtain the industry-specific threshold for the equipment; The residual value of the third equipment is calculated based on the industry rule threshold. The residual value of the second equipment is compared with the residual value of the third equipment to obtain the second valuation deviation; If the second valuation deviation is less than the preset deviation threshold, the second equipment residual value is determined to be the second equipment residual value that conforms to the preset rules, and then output.

[0063] In one possible implementation, the method for selecting the residual value calculation method for the device to be calculated based on the device information includes: Based on the equipment information, determine the equipment type; When the equipment type is an excavator, machine learning is selected as the residual value calculation method for the equipment whose residual value is to be calculated. If the equipment type is not an excavator, the replacement cost method is selected as the method for calculating the residual value of the equipment to be calculated.

[0064] See Figure 4 , Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this application.

[0065] The device 400 includes a memory 401 and a processor 402; the memory 401 is used to store relevant program code; the processor 402 is used to call the program code and execute the device residual value calculation method described in the above method embodiment.

[0066] Furthermore, embodiments of the present invention also provide a computer-readable storage medium for storing a computer program for executing the equipment residual value calculation method described in the above method embodiments.

[0067] This invention also provides a computer program product, which includes a computer program / instruction. When the computer program / instruction is executed by a processor, it implements the equipment residual value calculation method described in the above method embodiments.

[0068] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0069] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0070] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. The units or modules described as separate components may or may not be physically separate. The components shown as units or modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units or modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions, and operations that may be implemented according to various embodiments of the invention, including methods, apparatus, and devices. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0072] It should be understood that in this invention, "at least one (item)" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0073] It should also be noted that, in this invention, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0074] The steps of the methods or algorithms described in conjunction with the embodiments disclosed in this invention can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for calculating the residual value of equipment, characterized in that, The method includes: Obtain equipment information, which is the information corresponding to the equipment whose residual value is to be calculated; Based on the equipment information, select the residual value calculation method for the equipment whose residual value needs to be calculated; When the selected residual value calculation method is machine learning, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain the first equipment residual value. When the selected residual value calculation method is the replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate.

2. The method according to claim 1, characterized in that, When the selected residual value calculation method is machine learning, a feature set is constructed using the equipment information, and the feature set is processed by a machine learning model to obtain the first equipment residual value, including: Filter key information from the device information and construct a feature set based on the key information; The machine learning model is used to assign corresponding weights to each feature in the feature set. The first equipment residual value is calculated based on the feature set and the corresponding weights.

3. The method according to claim 1, characterized in that, When the selected residual value calculation method is the replacement cost method, a baseline residual value is obtained based on the equipment information, a depreciation rate is calculated based on the equipment information, and a second equipment residual value is calculated based on the baseline residual value and the depreciation rate, including: Based on the equipment type and cargo space volume in the equipment information, obtain the baseline residual value; Based on the equipment brand in the equipment information, obtain the brand coefficient; Based on the equipment age in the equipment information, obtain the corresponding age-related depreciation rate and depreciation rate, as well as the corresponding age-related depreciation rate coefficient and technical condition depreciation rate coefficient; Based on the equipment information, obtain the equipment technical condition assessment score and the amount of impairment; The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and the corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient.

4. The method according to claim 3, characterized in that, The second equipment residual value is calculated based on the benchmark residual value, brand coefficient, age-depreciation rate, depreciation rate, equipment technical condition assessment score, impairment amount, and corresponding age-depreciation rate coefficient and technical condition depreciation rate coefficient, including: Multiply the stated age-based depreciation rate by the age-based depreciation rate coefficient to obtain the first product; The second product is obtained based on the technical condition depreciation rate coefficient and the equipment technical condition assessment score; The third product is obtained based on the second product and the depreciation rate; Multiply the brand coefficient and the impairment amount to obtain the fourth product; Add the first product to the third product to obtain a sum, and multiply the sum by the benchmark residual to obtain a fifth product; Subtracting the fifth product from the fourth product yields the second equipment residual value.

5. The method according to claim 2, characterized in that, Before assigning corresponding weights to each feature in the feature set using a machine learning model, the method further includes: Obtain historical device feature data; According to the time parameters of the historical equipment feature data, the historical equipment feature data is divided to obtain the first historical equipment feature data and the second historical equipment feature data. The first historical equipment feature data is used for model training, and the second historical equipment feature data is used for model verification. The first historical device feature data is searched by grid search to obtain N sets of parameter combinations; The N parameter combinations are validated through cross-validation to obtain the parameter combination with the highest score; The initial machine learning model is trained using the parameter combination with the highest score to obtain the trained machine learning model. The trained machine learning model is tested using the second historical device feature data to obtain the machine learning model.

6. The method according to claim 1, characterized in that, After obtaining the first equipment residual value, the process further includes: Obtain the historical transaction prices corresponding to the equipment whose residual value is to be calculated; The residual value of the first equipment is compared with the historical transaction price to obtain the first valuation deviation; If the first valuation deviation is less than a preset deviation threshold, the first equipment residual value is determined to be a first equipment residual value that conforms to the preset rules, and then output.

7. The method according to claim 1, characterized in that, After calculating the residual value of the second equipment, the process also includes: Obtain the industry-specific threshold for the equipment; The residual value of the third equipment is calculated based on the industry rule threshold. The residual value of the second equipment is compared with the residual value of the third equipment to obtain the second valuation deviation; If the second valuation deviation is less than the preset deviation threshold, the second equipment residual value is determined to be the second equipment residual value that conforms to the preset rules, and then output.

8. The method according to claim 1, characterized in that, The method for calculating the residual value of the equipment to be calculated based on the equipment information includes: Based on the equipment information, determine the equipment type; When the equipment type is an excavator, machine learning is selected as the residual value calculation method for the equipment whose residual value is to be calculated. If the equipment type is not an excavator, the replacement cost method is selected as the method for calculating the residual value of the equipment to be calculated.

9. A device for calculating the residual value of equipment, characterized in that, The device includes: The acquisition module is used to acquire device information, which is the information corresponding to the device whose residual value is to be calculated; The selection module is used to select the residual value calculation method for the equipment whose residual value is to be calculated based on the equipment information. The construction module is used to construct a feature set based on the equipment information when the selected residual value calculation method is machine learning, and to process the feature set through a machine learning model to obtain the first equipment residual value. The calculation module is used to obtain a baseline residual value based on the equipment information when the selected residual value calculation method is the replacement cost method, calculate the depreciation rate based on the equipment information, and calculate a second equipment residual value based on the baseline residual value and the depreciation rate.

10. An electronic device, characterized in that, The device includes: a memory and a processor; the memory is used to store relevant program code; the processor is used to call the program code to execute the device residual value calculation method according to any one of claims 1 to 8.

Images