CN117610731A

CN117610731A - Method, device and storage medium for predicting transport capacity purchasing cost

Info

Publication number: CN117610731A
Application number: CN202311609247.9A
Authority: CN
Inventors: 胡晓菁; 冯媛; 高岩; 刘潇; 叶春力; 朱雯; 李秀春; 郑莹; 杨露露
Original assignee: China Post Information Technology Beijing Co ltd
Current assignee: China Post Information Technology Beijing Co ltd
Priority date: 2023-11-28
Filing date: 2023-11-28
Publication date: 2024-02-27

Abstract

The invention discloses a method, a device and a storage medium for predicting the purchasing cost of transport capacity. The method comprises the following steps: for each transport route, acquiring own capacity data of a target transport company, outsourcing capacity data of a cooperative transport company and market capacity data of other transport companies, and determining own capacity cost corresponding to each own transport vehicle according to own associated data; determining predicted outsourcing profit data and predicted market profit data based on the owned cost of operation, the outsourcing capacity data, and the market capacity data; and carrying out capacity purchasing cost prediction on the predicted outsourcing profit data, the predicted market profit data, the own capacity data and the outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model to obtain a prediction result, wherein the capacity purchasing cost prediction result is the highest cost for paying. The problem of lower accuracy of prediction of the purchasing cost of the transportation capacity is solved, and the accuracy of prediction of the purchasing cost of the transportation capacity is improved.

Description

Method, device and storage medium for predicting transport capacity purchasing cost

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method and apparatus for predicting purchasing cost of capacity, and a storage medium.

Background

Capacity purchasing is an important issue that needs to be considered by logistics companies each year, and in ideal cases, the marketer should be enough, the market competition is enough and sufficient, and the final capacity purchasing cost can be in a reasonable interval. However, since competition in the real market is insufficient, profits of winning suppliers may be too high, resulting in cost waste, purchase limit is required to avoid the excessively high suppliers from disturbing bidding environment.

In the related technical scheme for predicting the purchasing cost of the transportation capacity, the purchasing cost of the transportation capacity is predicted according to the purchasing cost of the transportation capacity in the past and the market research. However, the accuracy of capacity procurement cost prediction is low because the annual situation is different, resulting in that the capacity procurement cost in the past is already not matched with the current market, and the scope of market research is limited.

Disclosure of Invention

The invention provides a method, a device and a storage medium for predicting the purchasing cost of a transport capacity, so as to improve the accuracy of predicting the purchasing cost of the transport capacity.

According to an aspect of the present invention, there is provided a capacity procurement cost prediction method, the method comprising:

for each transport route, acquiring the self-capacity data of the target transport company, the outsourcing capacity data of the cooperative transport company and the market capacity data of the other transport company, wherein the self-capacity data comprises self-associated data of at least one self-transport vehicle, the outsourcing capacity data comprises outsourcing service data and outsourcing cost data, and the market capacity data comprises historical transport data and historical vehicle attribute data of the other transport vehicle of the other transport company in a historical time period;

Determining, based on the own associated data, an own capacity cost including a corresponding one of each of the own transportation vehicles;

determining predicted outsourcing profit data based on the own capacity cost and the outsourcing capacity data, and determining predicted market profit data based on the own capacity cost and the market capacity data;

and carrying out capacity purchasing cost prediction on the predicted outsourcing profit data, the predicted market profit data, the own capacity data and the outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model to obtain a capacity purchasing cost prediction result, wherein the capacity purchasing cost prediction result is the highest cost for paying.

According to another aspect of the present invention, there is provided an apparatus for predicting a purchasing cost of shipping capacity, the apparatus comprising:

the system comprises an operation capacity data acquisition module, an operation capacity data acquisition module and a control module, wherein the operation capacity data acquisition module is used for acquiring operation capacity data of a target transport company, outsourcing operation capacity data of a cooperative transport company and market operation capacity data of other transport companies for each transport route, the operation capacity data comprise associated data of at least one own transport vehicle, the outsourcing operation capacity data comprise outsourcing service data and outsourcing cost data, and the market operation capacity data comprise historical transport data and historical vehicle attribute data of other transport vehicles of other transport companies in historical time periods;

The capacity cost determining module is used for determining the corresponding capacity cost of each own transport vehicle according to the own associated data;

a profit prediction module for determining predicted outsourcing profit data based on the owned cost of fortune and the outsourcing capacity data, and determining predicted market profit data based on the owned cost of fortune and the market capacity data;

and the purchasing cost prediction module is used for predicting the capacity purchasing cost of the predicted outsourcing profit data, the predicted market profit data, the own capacity data and the outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model to obtain a capacity purchasing cost prediction result, wherein the capacity purchasing cost prediction result is the highest cost for paying.

According to another aspect of the present invention, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the capacity procurement costs prediction method of any of the embodiments of the invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute an operational procurement costs prediction method according to any of the embodiments of the invention.

According to the technical scheme, for each transport route, the self-capacity data of a target transport company, the outsourcing capacity data of a cooperative transport company and the market capacity data of other transport companies are obtained, wherein the self-capacity data comprises self-associated data of at least one self-transport vehicle, the outsourcing capacity data comprises outsourcing service data and outsourcing cost data, and the market capacity data comprises historical transport data and historical vehicle attribute data of other transport vehicles of other transport companies within historical time; determining, based on the own associated data, an own capacity cost including a corresponding one of each of the own transportation vehicles; determining forecasted outsourcing profit data based on the owned cost of operation and the outsourcing capacity data, and determining forecasted market profit data based on the owned cost of operation and the market capacity data; and carrying out capacity purchasing cost prediction on the predicted outsourcing profit data, the predicted market profit data, the own capacity data and the outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model to obtain a capacity purchasing cost prediction result, wherein the capacity purchasing cost prediction result is the highest cost for paying. The problem of lower accuracy of prediction of the purchasing cost of the transportation capacity is solved, and the accuracy of prediction of the purchasing cost of the transportation capacity is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for predicting shipping costs provided in accordance with an embodiment of the present invention;

FIG. 2 is a flow chart of another capacity procurement cost prediction method provided according to an embodiment of the invention;

FIG. 3 is a flow chart of a specific capacity procurement cost prediction method according to an embodiment of the invention;

FIG. 4 is a block diagram of a capacity procurement cost prediction apparatus according to an embodiment of the invention;

fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "target" and "initial" and the like in the description of the present invention and the claims and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a flowchart of a method for predicting an availability procurement cost according to an embodiment of the invention, which is applicable to a scenario of performing an availability procurement cost prediction based on historical availability data, and may be executed by an availability procurement cost prediction device, which may be implemented in the form of hardware and/or software and configured in a processor of an electronic device.

As shown in fig. 1, the capacity procurement cost prediction method includes the steps of:

s110, acquiring own capacity data of the target transport company, outsourcing capacity data of the cooperative transport company and market capacity data of other transport companies for each transport route, wherein the own capacity data comprises self-associated data of at least one own transport vehicle.

The outsourcing capacity data comprises outsourcing service data and outsourcing cost data, and the market capacity data comprises historical transportation data and historical vehicle attribute data of other transportation vehicles of other transportation companies in the historical time duration.

The target carrier is a company needing to predict the purchasing cost of the transport capacity. The partner carrier is a carrier that provides a carrier service to the target carrier, that is, the partner carrier provides a carrier strength to the target carrier based on the carrier service, and the other carrier is a carrier that can provide a carrier service in addition to the partner carrier and the target carrier.

It will be appreciated that, on the one hand, vehicles are traveling on different terrains and the costs of time and transportation that need to be expended are different, and therefore, there is a need for capacity procurement cost prediction for a transportation route. On the other hand, in order to improve accuracy of the capacity purchasing cost prediction, it is necessary to combine the original purchasing capacity cost with market conditions to perform the capacity purchasing cost prediction. In addition, considering that the capacity costs of other carriers on the market reflect the market quotation of capacity procurement costs to some extent, it is necessary to acquire capacity data of other carriers over a period of time to provide more accurate market quotation data.

In this embodiment, the own associated data includes historical transportation data and capacity attribute data, the historical transportation data including at least one of historical transportation mileage data, historical loading rate data, historical transportation efficiency data, and historical labor cost data of the own vehicle; the capacity attribute data includes at least one of tonnage data, volume data, insurance data, and maintenance data of the own vehicle.

For each transport route, the historical transport mileage data, the historical loading rate data, the historical transport efficiency data and the historical labor cost data, the tonnage data, the volume data, the insurance data and the maintenance data of the own vehicles in one year are obtained, and the service evaluation index and the service cost data of the transport vehicles of the cooperative transport company are obtained, and the historical transport mileage data, the historical loading rate data, the historical transport efficiency data and the historical labor cost data, the tonnage data, the volume data, the insurance data and the maintenance data of other transport vehicles of other transport companies in the market are obtained; and dividing each data into four groups according to quarters to obtain the own capacity data, outsourcing capacity data and market capacity data of each quarter.

Optionally, the outsourcing capacity data of the partner carrier and the market capacity data of the other carrier are preprocessed to update the outsourcing capacity data of the partner carrier and the market capacity data of the other carrier. Specifically, preprocessing outsourcing capacity data of a acting carrier and market capacity data of other carriers includes: respectively carrying out statistical analysis on the outsourcing capacity data and the market capacity data to obtain a statistical analysis result corresponding to the outsourcing capacity data and a statistical analysis result corresponding to the market capacity data; the outsourcing capacity data is updated based on the statistical analysis results corresponding to the outsourcing capacity data, and the market capacity data is updated based on the statistical analysis results corresponding to the market capacity data. This has the advantage that the accuracy of the capacity data can be improved to improve the accuracy of the capacity procurement cost forecast.

Illustratively, considering the diversity of market capacity data of other transport companies, for the same transport route, performing statistical analysis on the market capacity data to obtain the median of all the market capacity data so as to update the market capacity data; meanwhile, for the same transportation route, carrying out statistical analysis on the outsourcing capacity data, screening out the outsourcing capacity data corresponding to transportation services such as transportation period, temporary emergency and the like, and determining the average value of the outsourcing cost data in the screened outsourcing capacity data so as to update the outsourcing capacity data.

Optionally, the self-capacity data, the outsourcing capacity data of the cooperative carrier, and the market capacity data of the other party carrier are respectively divided into at least one subset of data according to a preset data division rule to update the self-capacity data, the outsourcing capacity data of the cooperative carrier, and the market capacity data of the other party carrier. Specifically, the self-capacity data, the outsourcing capacity data of the cooperative carrier, and the market capacity data of the other party carrier are divided into at least one subset of data according to the time period, respectively, so as to update the self-capacity data, the outsourcing capacity data of the cooperative carrier, and the market capacity data of the other party carrier.

Exemplary, historical transportation mileage data, historical loading rate data, historical transportation efficiency data and historical labor cost data, tonnage data, volume data, insurance data and maintenance data of own vehicles in one year are obtained, service evaluation indexes and service cost data of transportation vehicles of cooperative transportation companies, and historical transportation mileage data, historical loading rate data, historical transportation efficiency data and historical labor cost data, tonnage data, volume data, insurance data and maintenance data of other transportation vehicles of other transportation companies in the market; and dividing each data into four groups according to quarters to obtain the own capacity data, outsourcing capacity data and market capacity data of each quarter.

S120, determining the own transportation cost corresponding to each own transportation vehicle according to the own associated data.

It will be appreciated that the original purchasing capacity costs of the target carrier include: costs corresponding to own transport vehicles, and costs corresponding to the transport services of the co-operating transport company. Wherein costs corresponding to the transportation services of the co-operating transportation company are directly available, it is therefore necessary to determine the own transportation costs corresponding to each own transportation vehicle.

Considering that the factors influencing the cost are many, and the influence degree of each influencing factor on the cost is different, the influencing factors of the own operational cost and the importance degree thereof can be determined first; determining the cost corresponding to each influencing factor; and determining the corresponding own transport cost of each own transport vehicle based on the corresponding cost of each influencing factor and the importance degree thereof.

Specifically, according to the self-association data, determining influence factors of the self-transportation costs corresponding to each self-transportation vehicle, and setting weight values corresponding to the influence factors based on the influence degree of each influence factor on the costs; based on the weight values, a determination is made that includes a corresponding owned cost of transportation for each owned transportation vehicle.

In this embodiment, determining, based on the own associated data, an own operational cost including a corresponding one of each of the own transportation vehicles includes: determining at least one capacity cost data corresponding to the self-associated data according to the self-associated data; and summing all the capacity cost data to obtain the corresponding own capacity cost of each own transport vehicle.

Specifically, according to the historical transportation mileage data, the historical loading rate data, the historical transportation efficiency data, the historical labor cost data, the tonnage data, the volume data, the insurance data and the maintenance data of the own transportation vehicles, for each own transportation vehicle, determining the current transportation cost corresponding to the current data, and summing all the current transportation costs to obtain the own transportation cost corresponding to each own transportation vehicle.

In this embodiment, determining at least one capacity cost data corresponding to the own associated data according to the own associated data includes: determining a transport productivity, a fixed cost, and a dynamic cost corresponding to the self-associated data; and determining the own capacity cost corresponding to the own capacity data based on the transportation productivity, the fixed cost, the dynamic cost and the preset corresponding relation, wherein the preset corresponding relation comprises the corresponding relation among the fixed cost, the dynamic cost, the transportation productivity and the own capacity cost.

The fixed cost refers to the cost which is kept unchanged in a certain period and a certain transportation volume range and is not influenced by the transportation volume variation, and the fixed cost can comprise the total cost corresponding to labor, depreciation, insurance and the like in the transportation process; dynamic costs refer to costs that are affected by traffic fluctuations, and related to the use of the transport vehicle, dynamic costs may include the total costs associated with fuel consumption, road and bridge, insurance and maintenance, mileage, etc. during transport.

Specifically, a correspondence relationship between fixed costs, dynamic costs, transportation productivity, and own capacity costs is created in advance; determining a transport productivity, a fixed cost, and a dynamic cost based on the self-associated data; the own capacity cost corresponding to the own capacity data is determined based on the transportation productivity, the fixed cost, the dynamic cost, and the preset correspondence.

In the present embodiment, since the dynamic cost is affected by the traffic variation, determining the final dynamic cost based on the transportation productivity and the dynamic cost, specifically, determining the final dynamic cost based on the transportation productivity and the dynamic cost includes: the final dynamic cost is determined based on the ratio of the dynamic cost and the transport productivity. Further, the final dynamic cost and the sum of the costs are determined, resulting in a cost of capability.

By way of example, considering that purchasing occurs before transportation occurs, the traditional relation model is improved, the corresponding relation between the fixed cost, the dynamic cost, the transportation productivity and the self-capacity cost in the formula (1) is determined, the self-capacity cost can be directly obtained based on the corresponding relation, the accuracy and the calculation speed of the self-capacity cost are improved, and the accuracy and the efficiency of estimating the self-capacity purchasing cost are further improved.

Wherein C is the cost of operation, C _f For dynamic cost, C _c For a fixed cost, W is the transport productivity. The dynamic cost is the total cost corresponding to fuel, road and bridge, maintenance fee, mileage and the like, and the fixed cost comprises the total cost corresponding to manpower, depreciation, insurance and the like.

W is determined based on equation (2):

wherein P is rated load, Q is tonnage utilization rate, S is load mileage, and T is driving time.

S130, determining predicted outsourcing profit data based on the own capacity cost and the outsourcing capacity data, and determining predicted market profit data based on the own capacity cost and the market capacity data.

Wherein the forecasted outsourcing profit data is profit of the partner carrier determined from the own operational cost for the same transportation route, and the forecasted market profit data is profit of the other partner carrier determined from the own operational cost for the same transportation route.

It is understood that in order to determine the profit of the partner carrier and the profit of the other party carrier, the profit of the partner carrier may be determined based on the capacity cost of the partner carrier, and the profit of the other party carrier may be determined based on the capacity cost of the other party carrier. However, since the capacity cost of the partner carrier and the capacity cost of the other carrier cannot be directly obtained, the own capacity cost is used as the capacity cost of the partner carrier and the capacity cost of the other carrier, respectively, to predict the profit of the partner carrier and the profit of the other carrier.

Specifically, based on the difference value between the outsourcing cost data and the own capacity cost in the outsourcing capacity data, the predicted outsourcing profit data is determined; historical cost data for the carrier of the other party is determined based on historical transportation data and historical vehicle attribute data in the market capacity data, and forecasted market profit data is determined based on the difference between the historical cost data and the own capacity cost. This has the advantage that the reasonable profit of the co-carrier and the other carrier can be determined to increase the rationality of the capacity procurement cost forecast results.

And S140, carrying out capacity purchasing cost prediction on predicted outsourcing profit data, predicted market profit data, own capacity data and outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model to obtain a capacity purchasing cost prediction result.

Wherein, the capacity purchase cost prediction result is the highest cost for paying.

The capacity purchasing cost prediction model is used for predicting the capacity purchasing cost of the target carrier based on predicted outsourcing profit data, predicted market profit data, own capacity data and outsourcing capacity data.

It will be appreciated that prior to training the capacity procurement cost prediction model, a sample tab set and a training sample set need to be constructed to train the capacity procurement cost prediction model based on the sample tab set and the training sample set.

In this embodiment, constructing a training sample set includes: for each haul route, a set of sample forecasted outsourcing profit data, sample forecasted market profit data, sample owned capacity data, and sample outsourcing capacity data within a set historical time period is taken as a training sample set.

Specifically, for each transportation route, acquiring historical transportation mileage data, historical loading rate data, historical transportation efficiency data, historical labor cost data, tonnage data, volume data, insurance data and maintenance data of the own vehicle in a set historical time period, and taking the data as sample own transportation capacity data; meanwhile, acquiring historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data of an outsourcing vehicle of a transport vehicle of a cooperative transport company in a set historical time period, taking the data as sample outsourcing service data, and taking the data as sample market capacity data, namely historical transport mileage data, historical loading rate data, historical transport efficiency data, historical labor cost data, tonnage data, volume data, insurance data and maintenance data of other transport vehicles of other transport companies in a market in the set historical time period; determining a sample self-capacity cost corresponding to the sample self-capacity data; determining sample forecasted consist profit data based on the sample inherent cost and sample outsourcing capacity data, and determining sample forecasted market profit data based on the sample inherent cost and sample market capacity data; and taking a data set consisting of the sample forecast outsourcing profit data, the sample forecast market profit data, the sample self-carrying capacity data and the sample outsourcing carrying capacity data as a training sample to obtain a training sample set.

Optionally, according to the set proportion, the training samples in the training sample set are divided into a test sample and a training sample, so as to update the training sample set. Illustratively, training samples in the training sample set are divided into a test sample and a training sample according to a ratio of 1:4, and a test sample set and a training sample set are obtained.

In this embodiment, constructing a sample tag set includes: determining optimal outsourcing service data corresponding to the outsourcing service data; and determining a sample tag set based on contract cost data corresponding to the optimal outsourcing service data. The outsourcing service data comprises at least one of historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data of the outsourcing vehicle, and the outsourcing cost data comprises contract cost data.

The contract cost data is the transport cost data originally agreed by the target transport company and the cooperative transport company. The optimal outsourcing service data is the best data for the transportation service in the cooperated transportation company.

It will be appreciated that considering that the outsourcing service quality of the co-carrier and the contract cost data may in some scenarios exhibit a positive correlation, it is desirable to determine the highest cost based on the optimal outsourcing service data.

In this embodiment, determining the optimal outsourcing service data corresponding to the outsourcing service data may include: for each transportation route, determining at least one of historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data of the outsourcing vehicle, and taking the data as outsourcing service data; the method comprises the steps that evaluation indexes aiming at outsourcing service data are established in advance and are used for determining service evaluation results corresponding to the outsourcing service data so as to obtain service sequencing results of all transportation routes; and taking the outsourcing service data corresponding to the optimal service evaluation result as optimal outsourcing service data, and taking contract cost data corresponding to the optimal outsourcing service data as a sample label corresponding to the transportation route.

For each transportation route, determining historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data of the outsourcing vehicles, and taking the data as outsourcing service data; an evaluation index for the outsourcing service data is pre-established and used for determining the service level corresponding to the outsourcing service data so as to obtain service level sequencing results corresponding to all the outsourcing service data; and taking the outsourcing service data corresponding to the highest service level as optimal outsourcing service data based on the service level sequencing result. Further, the contract cost data corresponding to the optimal outsourcing service data is used as a sample label corresponding to the transportation route, so that a sample label set is obtained.

In this embodiment, training the capacity purchasing cost prediction model based on the sample tag set and the training sample set includes: for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model to obtain capacity purchasing cost prediction data; wherein the input samples include self-capacity data, outsourcing capacity data, predicted outsourcing profit data, and predicted market profit data; determining a loss value based on the capacity purchasing cost prediction data and the sample tag set, so as to correct model parameters in the capacity purchasing cost prediction model based on the loss value; and converging a loss function in the capacity purchasing cost prediction model to be used as a training target, so as to obtain the capacity purchasing cost prediction model.

The capacity purchasing cost prediction data is capacity purchasing cost obtained based on the capacity purchasing cost prediction model.

Wherein the loss value is determined based on the capacity procurement cost prediction data, the sample label corresponding to the current training sample, and a preset loss function, wherein the preset loss function may include a cross entropy loss function (cross-entropy loss function), an average absolute error (Mean Absolute Error, MAE), or a residual standard deviation (Root mean squared error, RMSE).

Specifically, for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model, and outputting capacity purchasing cost prediction data corresponding to the current input sample; determining a loss value corresponding to a current input sample based on the capacity purchasing cost prediction data, the sample tags in the sample tag set corresponding to the current training sample, and a preset loss function; correcting model parameters of the capacity purchasing cost prediction model so as to reduce a loss value; and stopping training when the loss function converges to obtain the capacity purchasing cost prediction model. This has the advantage that overfitting can be prevented.

Illustratively, constructing a support vector machine (Support Vector Machine, SVM) regression model as an operational purchasing cost prediction model; for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model, and outputting capacity purchasing cost prediction data corresponding to the current input sample; determining an RMSE loss value corresponding to the current input sample based on the capacity procurement cost prediction data, the contract cost data corresponding to the current training sample in the sample tag set, and the remaining standard deviation, as shown in equation (3):

Wherein L represents the total number of training samples, y _i The cost of contract data is represented by the data,and representing capacity purchasing cost prediction data.

Correcting training parameters of model parameters of the capacity purchasing cost prediction model so as to reduce loss values; and stopping training when the loss function converges to obtain the capacity purchasing cost prediction model.

Optionally, the capacity procurement cost prediction model is determined based on a Grid Search method (Grid Search). Specifically, determining the capacity procurement cost prediction model based on the Grid Search method (Grid Search) includes: and presetting a candidate value list of the super parameters of the capacity purchasing cost prediction model, carrying out exhaustive search on all possible parameter combinations, training and evaluating the capacity purchasing cost prediction model based on each group of parameters, and finally selecting the parameter combination with the best performance as the super parameters of the capacity purchasing cost prediction model to obtain the capacity purchasing cost prediction model.

According to the technical scheme, based on the fact that the profit of the cooperative carrier and the profit of the other carrier are predicted based on the own capacity cost, reasonable profit of the cooperative carrier and the other carrier can be determined, and therefore the rationality of the capacity purchasing cost prediction result is improved; and the capacity purchasing cost is determined based on the historical capacity data and the capacity purchasing cost prediction model, so that the association relation between the capacity purchasing cost and specific transportation conditions can be explored from the deep time dimension and the wider data dimension, the capacity purchasing cost prediction degree is improved, and the capacity purchasing cost and purchasing flow standard rate are further reduced.

Fig. 2 is a flowchart of another method for predicting the purchasing cost of capacity according to an embodiment of the present invention, where the present embodiment is applicable to a scenario of predicting purchasing cost of capacity based on historical capacity data, and the method for predicting purchasing cost of capacity according to the present embodiment belongs to the same inventive concept as the method for predicting purchasing cost of capacity in the above embodiment, and further describes a process of acquiring own capacity data of a target carrier and outsourcing capacity data of a cooperated carrier based on the above embodiment.

As shown in fig. 2, the capacity procurement cost prediction method includes:

s210, for each transportation route, market capacity data of other transportation companies in the historical time period, historical own capacity data of target transportation companies in the initial time period and historical outsourcing capacity data of cooperative transportation companies are obtained.

Wherein the initial time period is a history time of a set duration including the current time, and the initial time period may be a period of time corresponding to the history time, for example, the initial time period may be a period of time of the past year including the current time.

Specifically, for each transportation route, historical own capacity data of the target transportation company, historical outsourcing service data and historical outsourcing cost data of the cooperative transportation company, and market capacity data of other transportation companies corresponding to the historical duration including the current moment are acquired.

S220, performing outlier removal and minimum maximum normalization processing on the historical self-capacity data and the historical outsourcing capacity data so as to update the historical self-capacity data and the historical outsourcing capacity data.

In this embodiment, performing outlier removal and minimum maximum normalization processing on the historical self-owned capacity data and the historical outsourcing capacity data to update the historical self-owned capacity data and the historical outsourcing capacity data includes: based on a 3sigma principle, respectively detecting abnormal values of historical self-capacity data of a target transport company and historical outsourcing capacity data of a cooperative transport company in an initial time period to remove the abnormal data, and carrying out minimum maximum normalization (Min-Max Normalization) processing on the historical self-capacity data and the historical outsourcing capacity data to carry out linear transformation on the historical self-capacity data and the historical outsourcing capacity data so as to map the historical self-capacity data and the historical outsourcing capacity data to between 0 and 1. The method has the advantages that the influence of the dimension of the data can be eliminated, the gap between the data is reduced, and further, the speed of data processing is improved; meanwhile, the influence of abnormal values can be eliminated, and the accuracy of the prediction of the capacity purchasing cost is further improved.

For the historical outsourcing capacity data, the outsourcing cost data with larger differences caused by the reasons of transportation period, temporary emergency and the like are deleted, and for the same transportation route, the historical outsourcing capacity data is averaged to update the outsourcing cost data; for the same transportation route, determining a median of the market capacity data to update the market capacity data; and for the same transportation route, based on a 3sigma principle, respectively detecting abnormal values of the historical self-capacity data of the target transportation company and the historical outsourcing capacity data of the cooperative transportation company in an initial time period to remove the abnormal data, and carrying out minimum and maximum normalization processing on the historical self-capacity data and the historical outsourcing capacity data to update the historical self-capacity data and the historical outsourcing capacity data.

And S230, screening the historical self-capacity data and the historical outsourcing capacity data to obtain the self-capacity data and the outsourcing capacity data in the target time period.

It will be appreciated that the capacity procurement cost prediction is based on historical data, and that considering the variation of capacity data, the longer data may have a weaker correlation with the current capacity procurement cost prediction, and thus, it is necessary to determine the historical data of the optimal time period (i.e., the target time period) to improve the accuracy of the capacity procurement cost prediction.

The target time period is determined based on a vector autoregressive model, and corresponds to the time period with the highest predicted relevance of the current capacity purchasing cost.

In this embodiment, in order to more accurately predict the purchasing cost of the capacity, the change condition of the capacity data needs to be considered, so that the historical capacity data is regressed based on the current capacity data of the vector autoregressive model, so as to estimate the dynamic relationship between the historical capacity data and the current capacity data, so as to determine the target time period corresponding to the historical capacity data.

The vector auto-regression (VAR) model is a model for regression of a plurality of hysteresis variables of all variables based on the variables in the model in the same time period, and is used for estimating the dynamic relationship of each variable without any prior constraint condition.

In this embodiment, the screening of the historical intrinsic and extrinsic operational data based on the vector autoregressive model includes: constructing a vector autoregressive model on historical self-capacity data and historical outsourcing capacity data; and determining an optimal hysteresis order based on a preset hysteresis order checking rule, and determining a target time period based on the optimal hysteresis order to obtain historical self-capacity data and historical outsourcing capacity data corresponding to the target time period.

Wherein the preset hysteresis order checking rule includes at least one of bayesian information criterion (Bayesian information criterion, BIC), red pool information criterion (Akaike information criterion, AIC), schwaltz criterion (Schwarz Criterion, SC), hannan-Quinn (HQ) information criterion, final prediction error (Final Prediction Error, FPE), and analytical Likelihood Ratio (LR).

In this embodiment, determining the target time period includes: constructing a vector autoregressive model based on the historical outsourcing capacity data in the initial time period; and iterating the model parameters of the vector autoregressive model until the associated information of the vector autoregressive model meets the iteration conditions, and obtaining a target time period.

Wherein the correlation information may be determined based on a model evaluation index, and the iteration condition may be determined based on a model evaluation method, which may be at least one of model stability check, impulse response analysis, and variance decomposition.

Specifically, all parameter combinations of model parameters of the vector autoregressive model are determined; for each parameter combination, determining a vector autoregressive model corresponding to the current parameter combination; evaluating each vector autoregressive model based on a model evaluation method to obtain an optimal vector autoregressive model; and determining a target time period based on the parameter combination corresponding to the optimal vector autoregressive model. This has the advantage that the reliability and accuracy of the model is ensured.

Illustratively, all parameter combinations of model parameters of the vector autoregressive model are determined; for each parameter combination, determining a vector autoregressive model corresponding to the current parameter combination; evaluating each vector autoregressive model based on model stability test to obtain a model evaluation result; further, based on the model evaluation result, impulse response analysis and variance decomposition are carried out on each vector autoregressive model so as to determine an optimal vector autoregressive model; and determining a target time period based on the parameter combination corresponding to the optimal vector autoregressive model.

Optionally, iterating the model parameters of the vector autoregressive model until the associated information of the vector autoregressive model meets the iteration condition, to obtain a target time period, including: determining an optimal hysteresis order of the vector autoregressive model based on a Bayesian information criterion; and taking the time period corresponding to the optimal hysteresis order as a target time period.

Specifically, all parameter combinations of model parameters of the vector autoregressive model are determined; for each parameter combination, determining a BIC value corresponding to the current parameter combination to obtain a minimum BIC value; taking the parameter combination corresponding to the minimum BIC value as an optimal parameter combination, taking the hysteresis time order corresponding to the optimal parameter combination as an optimal hysteresis order, obtaining a time period corresponding to the optimal hysteresis order, and taking the time period as a target time period.

In this embodiment, the vector autoregressive model corresponding to the optimal hysteresis order is shown in formula (4):

wherein Y is _t,m The method is current outsourcing actual cost data, and n is the optimal hysteresis order, namely historical self-carrying capacity data and historical outsourcing capacity data of the first n quarters; m represents the total number of samples, m=1,..m, X _t,p,m The p-th variable is used for representing the mth sample at the t moment, and the variable comprises at least one of historical transportation mileage data, historical loading rate data and historical transportation efficiency data of a partner transportation vehicle in the historical outsourcing capacity data, and at least one of historical labor cost data, tonnage data, volume data, insurance data, maintenance data, historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data.

S240, determining the own transportation cost corresponding to each own transportation vehicle according to the own associated data.

S250, determining predicted outsourcing profit data based on the own capacity cost and the outsourcing capacity data, and determining predicted market profit data based on the own capacity cost and the market capacity data.

And S260, carrying out capacity purchasing cost prediction on predicted outsourcing profit data, predicted market profit data, own capacity data and outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model, and obtaining a capacity purchasing cost prediction result.

According to the technical scheme, the outer cost data and the own capacity data which are obviously different are deleted by comparing the capacity data of similar transportation conditions, so that cost fluctuation caused by possible human factors or special conditions such as temporary urgent purchase is avoided. And predicting the dynamic influence of the outsourcing capacity data and the own capacity data on the capacity purchasing cost based on the vector autoregressive model, and predicting the capacity purchasing cost based on the function of the outsourcing actual cost and all hysteresis values, so that the accuracy of the capacity purchasing cost prediction is improved.

Fig. 3 is a flowchart of a specific method for predicting an purchasing cost of an operation according to an embodiment of the present invention, where the embodiment is applicable to a scenario of predicting purchasing cost of an operation based on historical purchasing cost data, as shown in fig. 3, the method for predicting purchasing cost of an operation includes:

s310, acquiring the own capacity data of the target carrier, the outsourcing capacity data of the cooperative carrier and the market capacity data of other carriers for each transport route.

For each transport route, acquiring the own capacity data of the target transport company, the outsourcing capacity data of the cooperative transport company and the market capacity data of other transport companies; determining a median of historical transportation data in the market capacity data to update the long-duration capacity data; and respectively grouping the self-capacity data of the target carrier and the outsourcing capacity data of the cooperative carrier according to the quarters to obtain the self-capacity data and the outsourcing capacity data corresponding to each quarter. Further, for the self-capacity data and the outsourcing capacity data corresponding to each quarter, respectively determining variances of the self-capacity data and the outsourcing capacity data corresponding to the current quarter; for the self-capacity data and the outsourcing capacity data with the variance exceeding the preset variance value, respectively detecting abnormal values of the self-capacity data and the outsourcing capacity data based on a 3sigma principle, and removing the abnormal values to update the self-capacity data and the outsourcing capacity data; and respectively carrying out average value processing on the self-owned cost data in the self-owned capacity data and the outsourcing cost data in the outsourcing capacity data for the self-owned capacity data and the outsourcing capacity data with the variance not exceeding the preset variance value so as to update the self-owned capacity data and the outsourcing capacity data. Minimum and maximum normalization is performed on the available capacity data, the outsourcing capacity data and the market capacity data to update the available capacity data and the outsourcing capacity data.

S320, determining transportation productivity, fixed cost and dynamic cost corresponding to the self-associated data; the own capacity cost corresponding to the own capacity data is determined based on the transportation productivity, the fixed cost, the dynamic cost, and the preset correspondence.

S330, determining predicted outsourcing profit data based on the own operational cost and the outsourcing operational data, and determining predicted market profit data based on the own operational cost and the market operational data.

S340, constructing a vector autoregressive model about the outsourcing actual cost data and the outsourcing capacity data, determining the optimal hysteresis order of the vector autoregressive model based on a Bayesian information criterion, and obtaining a target time period to update the outsourcing capacity data.

Specifically, the outsourcing actual cost data is taken as a dependent variable, and outsourcing historical cost data, historical transportation mileage data, historical loading rate data, historical transportation efficiency data and historical labor cost data of outsourcing vehicles in outsourcing capacity data are taken as explanatory variables to construct a vector autoregressive model; determining an optimal hysteresis order of the vector autoregressive model based on a Bayesian information criterion; and taking the time period corresponding to the optimal hysteresis order as a target time period to obtain outsourcing capacity data corresponding to the target time period.

S350, determining optimal outsourcing service data corresponding to outsourcing service data in outsourcing capacity data, and determining a sample tag set based on contract cost data corresponding to the optimal outsourcing service data.

Specifically, for each transportation route, determining historical performance rate data, historical time rate data, historical tonnage matching data and historical labor cost data of the outsourcing vehicle, and taking the data as outsourcing service data; the method comprises the steps that evaluation indexes aiming at outsourcing service data are established in advance and are used for determining service evaluation results corresponding to the outsourcing service data so as to obtain service sequencing results of all transportation routes; and taking the outsourcing service data corresponding to the optimal service evaluation result as optimal outsourcing service data, and taking contract cost data corresponding to the optimal outsourcing service data as a sample label corresponding to the transportation route.

S360, for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model to obtain capacity purchasing cost prediction data.

Specifically, constructing a support vector machine regression model as an operational purchasing cost prediction model; and for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model, and outputting capacity purchasing cost prediction data corresponding to the current input sample.

And S370, determining a loss value between the capacity purchasing cost prediction data and the sample label set based on the residual standard deviation so as to correct model parameters in the capacity purchasing cost prediction model based on the loss value.

Specifically, based on the capacity purchasing cost prediction data, contract cost data corresponding to the current training sample in the sample label set and the residual standard deviation, an RMSE loss value corresponding to the current input sample is determined, and model parameters in the capacity purchasing cost prediction model are corrected with the minimum loss value as a target.

And S380, determining optimal model parameters based on a grid search method and the loss value, and taking the capacity purchasing cost prediction model corresponding to the optimal model parameters as a target capacity purchasing cost prediction model.

S390, carrying out the prediction of the capacity purchasing cost on the predicted outsourcing profit data, the predicted market profit data, the own capacity data and the outsourcing capacity data based on the target capacity purchasing cost prediction model to obtain a prediction result.

Fig. 4 is a block diagram of a capacity procurement cost prediction apparatus according to an embodiment of the invention, which is applicable to a scenario of capacity procurement cost prediction based on historical capacity data, and the apparatus may be implemented in hardware and/or software, and integrated into a processor of an electronic device having an application development function.

As shown in fig. 4, the capacity procurement cost prediction apparatus includes: an capacity data obtaining module 401, configured to obtain, for each transport route, capacity data of a target transport company, outsourcing capacity data of a cooperative transport company, and market capacity data of a other transport company, where the capacity data includes associated data of at least one own transport vehicle, the outsourcing capacity data includes outsourcing service data and outsourcing cost data, and the market capacity data includes historical transport data and historical vehicle attribute data of the other transport vehicle of the other transport company in a historical duration; an operational cost determination module 402, configured to determine, based on the own associated data, an own operational cost including a corresponding own operational cost for each own transportation vehicle; a profit prediction module 403 for determining predicted outsource profit data based on the own capacity cost and the outsource capacity data, and determining predicted market profit data based on the own capacity cost and the market capacity data; the purchasing cost prediction module 404 is configured to predict the capacity purchasing cost of the predicted outsourcing profit data, the predicted market profit data, the own capacity data, and the outsourcing capacity data based on a pre-trained capacity purchasing cost prediction model, and obtain a capacity purchasing cost prediction result, where the capacity purchasing cost prediction result is the highest cost for paying. The problem of lower accuracy of prediction of the purchasing cost of the transportation capacity is solved, and the accuracy of prediction of the purchasing cost of the transportation capacity is improved.

Optionally, the capacity data acquisition module 401 is specifically configured to:

acquiring historical self-capacity data of the target carrier and historical outsourcing capacity data of the cooperative carrier in an initial time period;

performing outlier removal and minimum maximum normalization processing on the historical self-capacity data and the historical outsourcing capacity data to update the historical self-capacity data and the historical outsourcing capacity data;

and screening the historical self-capacity data and the historical outsourcing capacity data to obtain the self-capacity data and the outsourcing capacity data in a target time period, wherein the target time period is determined based on a vector autoregressive model.

Optionally, the capacity cost determination module 402 is specifically configured to:

determining at least one capacity cost data corresponding to the self-associated data according to the self-associated data;

and summing all the capacity cost data to obtain the corresponding own capacity cost of each own transport vehicle.

Optionally, the capacity cost determination module 402 includes a capacity cost determination unit, specifically configured to:

determining a transport productivity, a fixed cost, and a dynamic cost corresponding to the self-associated data;

And determining a self-capacity cost corresponding to the self-capacity data based on the transportation productivity, the fixed cost, the dynamic cost and a preset correspondence, wherein the preset correspondence comprises a correspondence among the fixed cost, the dynamic cost, the transportation productivity and the self-capacity cost.

Optionally, the capacity data acquisition module 401 further comprises a time period determining unit, which is specifically configured to:

determining the target time period;

the determining the target time period includes:

constructing the vector autoregressive model based on the historical self-capacity data and the historical outsourcing capacity data in the initial time period;

and iterating the model parameters of the vector autoregressive model until the association information of the vector autoregressive model meets the iteration condition, so as to obtain the target time period.

Optionally, the time period determining unit is further configured to:

determining an optimal hysteresis order of the vector autoregressive model based on a Bayesian information criterion;

and taking the time period corresponding to the optimal hysteresis order as the target time period.

Optionally, the device further comprises a model training module, and the model training module is specifically configured to:

constructing a sample tag set and a training sample set, and training the capacity purchasing cost prediction model based on the sample tag set and the training sample set;

the building of the sample tag set includes:

determining optimal outsourcing service data corresponding to the outsourcing service data;

and determining the sample tag set based on contract cost data corresponding to the optimal outsourcing service data.

Optionally, the model training module further comprises a model training unit, and the model training unit is specifically configured to:

for each training sample, inputting an input sample in the current training sample into the capacity purchasing cost prediction model to obtain capacity purchasing cost prediction data;

wherein the input samples include the owned capacity data, the outsourcing capacity data, the predicted outsourcing profit data, and the predicted market profit data;

determining a loss value based on the capacity purchase cost prediction data and the sample tag set to correct model parameters in the capacity purchase cost prediction model based on the loss value;

And converging a loss function in the capacity purchasing cost prediction model to serve as a training target, so as to obtain the capacity purchasing cost prediction model.

The capacity purchasing cost prediction device provided by the embodiment of the invention can execute the capacity purchasing cost prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the capacity procurement cost prediction method.

In some embodiments, the capacity procurement cost prediction method may be implemented as a computer program that is tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more of the steps of the capacity procurement cost prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the capacity procurement cost prediction method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable capacity procurement cost prediction apparatus, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method for predicting capacity procurement costs, comprising:

for each transport route, acquiring self-capacity data of a target transport company, outsourcing capacity data of a cooperative transport company and market capacity data of other transport companies, wherein the self-capacity data comprises self-associated data of at least one self-transport vehicle, the outsourcing capacity data comprises outsourcing service data and outsourcing cost data, and the market capacity data comprises historical transport data and historical vehicle attribute data of other transport vehicles of other transport companies in a historical time period;

Determining a self-capacity cost corresponding to each self-contained transport vehicle according to the self-associated data;

determining predicted outsourcing profit data based on the owned cost of fortune and the outsourcing capacity data, and determining predicted market profit data based on the owned cost of fortune and the market capacity data;

2. The method of claim 1, wherein the obtaining the own capacity data of the target carrier, the outsourcing capacity data of the cooperating carrier, comprises:

3. The method of claim 1, wherein said determining, based on said own associated data, an own operational cost including a corresponding own transportation vehicle for each own transportation vehicle comprises:

4. A method according to claim 3, wherein said determining at least one capacity cost data corresponding to said self-associated data from said self-associated data comprises:

5. The method as recited in claim 2, further comprising:

determining the target time period;

the determining the target time period includes:

constructing the vector autoregressive model based on the historical outsourcing capacity data in the initial time period;

6. The method of claim 5, wherein iterating the model parameters of the vector autoregressive model until the associated information of the vector autoregressive model satisfies an iteration condition, to obtain the target time period, comprises:

7. The method of claim 1, wherein the outsourcing service data comprises at least one of historical performance rate data, historical time-lapse rate data, historical tonnage matching data, and historical labor cost data of an outsourced vehicle, the outsourcing cost data comprising contract cost data;

The method further comprises the steps of:

the building of the sample tag set includes:

8. The method of claim 7, wherein the training the capacity procurement cost prediction model based on the sample tag set and the training sample set comprises:

9. An apparatus for predicting a purchasing cost of transportation, comprising:

10. A computer readable storage medium storing computer instructions for causing a processor to implement the capacity procurement cost prediction method of any of claims 1-8 when executed.