Logistics network income evaluation method, apparatus and device, and storage medium

Abstract

The invention discloses a logistics network income evaluation method and device, equipment and a storage medium. The method comprises the following steps: acquiring stage historical income and stage historical expenditure of a target logistics network in a historical time period; performing data processing on the stage historical income and the stage historical expenditure to obtain stage historical target income and stage historical target expenditure; determining an income evaluation index based on the stage historical target income and the stage historical target expenditure; determining a target income influence factor of the target logistics network; analyzing the target income influence degree of the target income influence factor on the target logistics network; establishing an income prediction model based on the income evaluation index and the target income influence degree; and based on the income prediction model, predicting and evaluating the income condition of the target logistics network in the future time period. According to the scheme, income prediction model training can be performed in combination with multi-dimensional data, the comprehensiveness of income evaluation is improved, and the prediction effect is improved.

Description

Technical Field

[0001] The present invention belongs to the field of logistics and transportation technology, and specifically relates to a logistics network point revenue evaluation method, device, equipment and storage medium. Background Art

[0002] Logistics outlets refer to facilities that undertake the functions of cargo storage, transshipment, sorting, etc. in the logistics supply chain, including warehouses, distribution centers, and transshipment stations. With the rapid development of the logistics industry, logistics outlets, as an important part of the logistics network, have a direct impact on the overall competitiveness of enterprises through their operational efficiency and profitability. Traditional profitability evaluation methods usually rely on simple financial statements or empirical judgments, and often only consider some cost and revenue factors, and are unable to deeply explore the various complex factors that affect outlet profitability and their interrelationships, making it difficult to accurately judge the operating conditions of outlets and provide effective support for decision-making. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method, device, equipment and storage medium for evaluating the revenue of a logistics network, so as to solve the problem that the revenue evaluation data in the prior art is single and the evaluation effect is poor.

[0004] According to one aspect of the present application, a logistics network point revenue evaluation method is disclosed, comprising: Obtain the historical income and expenditure of the target logistics outlets during the historical period; Process the data of the historical income and expenditure of the stage respectively to obtain the historical target income and expenditure of the stage; Determine the benefit evaluation index based on the historical target income and historical target expenditure of the said stage; Determine the factors affecting the target revenue of the target logistics network; Analyze the impact of the target revenue influencing factors on the target revenue of the target logistics network; Based on the profit evaluation index and the impact degree of the target profit, a profit prediction model is established; Based on the revenue prediction model, a forecast and evaluation is performed on the revenue of the target logistics network in the future time period.

[0005] In some embodiments, the data of the stage historical income and the stage historical expenditure are processed separately to obtain the stage historical target income and the stage historical target expenditure, including: The historical income of the stage and the historical expenditure of the stage are cleaned respectively, so as to process the abnormal data into a target format to obtain the historical target income of the stage and the historical target expenditure of the stage.

[0006] In some embodiments, determining the revenue evaluation index based on the historical target income of the stage and the historical target expenditure of the stage includes: The profit evaluation index includes a first profit, a second profit and a return on investment. The first profit is used to represent the remaining profit of the target logistics network after deducting the historical target expenditure of the stage. The second profit is used to represent the remaining profit of the target logistics network after deducting the target tax from the first profit. The return on investment is used to represent the expected investment return of the target logistics network. The first income profit is determined based on the following formula: First income profit = stage historical target income - stage historical target expenditure; The second income profit is determined based on the following formula; Second income profit = first income profit - target tax; The return on investment is determined based on the following formula: Return on investment = (second income profit / total investment) × 100%.

[0007] In some embodiments, the factors affecting the target revenue of the target logistics network point include: Acquire multiple revenue-related factors of the target logistics network; Determine the degree of influence of each revenue-related factor on the target revenue of the target logistics network point; Get the target impact threshold; The target revenue influencing factor is determined based on the target impact threshold and the degree of impact of each revenue-related factor on the target revenue of the target logistics network point.

[0008] In some embodiments, analyzing the degree of influence of the target revenue influencing factors on the target revenue of the target logistics network point includes: Analyze the influence degree of each of the target revenue influencing factors on the single revenue of the target logistics network point; Taking the single benefit impact degree as the target benefit impact degree; Draw a single benefit impact chart and send it to the target interface for display.

[0009] In some embodiments, analyzing the degree of influence of the target revenue influencing factors on the target revenue of the target logistics network point includes: Randomly combining a plurality of the target profit influencing factors to obtain a plurality of groups of combined profit influencing factors; Determine the distribution type and distribution parameters of each group of factors affecting the portfolio return; Based on the distribution type, distribution parameters and Monte Carlo simulation function, determine the probability distribution and variation range of each group of factors affecting the portfolio return; The target benefit impact degree is determined based on the probability distribution and the variation range.

[0010] In some embodiments, the establishing of a revenue prediction model based on the revenue evaluation index and the target revenue impact degree includes: Get the linear regression model; Based on the revenue evaluation index and the target revenue impact degree, the linear regression model is trained and optimized to obtain the revenue prediction model.

[0011] According to another aspect of the present application, a logistics network point revenue evaluation device is also disclosed, the device comprising: The stage historical data acquisition module is used to obtain the stage historical income and stage historical expenditure of the target logistics network in the historical time period; A data processing module is used to process the historical income and historical expenditure of a stage respectively to obtain the historical target income and historical target expenditure of the stage; A revenue evaluation index determination module, used to determine the revenue evaluation index based on the historical target income of the stage and the historical target expenditure of the stage; A target revenue influencing factor determination module, used to determine the target revenue influencing factors of the target logistics network point; A target revenue impact degree analysis module is used to analyze the impact degree of the target revenue impact factors on the target revenue of the target logistics network point; A revenue prediction model building module, used to build a revenue prediction model based on the revenue evaluation index and the target revenue impact degree; The forecasting and evaluation module is used to forecast and evaluate the revenue situation of the target logistics network in the future time period based on the revenue forecasting model.

[0012] According to another aspect of the present application, an electronic device is also disclosed, which includes a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the electronic device executes each step of the logistics network revenue evaluation method as described in any one of the above items.

[0013] According to another aspect of the present application, a computer-readable storage medium is also disclosed, on which instructions are stored, characterized in that when the instructions are executed by a processor, each step of the logistics network point revenue evaluation method as described in any of the above items is implemented.

[0014] The present invention includes but is not limited to the following beneficial effects: (1) This solution can combine multi-dimensional data to train the revenue prediction model, improve the comprehensiveness of the revenue evaluation, and improve the prediction effect; (2) This solution can process the historical income and historical expenditure data and remove outliers, thereby ensuring the accuracy and completeness of the data, avoiding evaluation bias caused by data quality problems, improving the training accuracy of the prediction model, and thus improving the accuracy of the subsequent revenue effect evaluation; (3) This solution forms a complete revenue evaluation process through the steps of obtaining historical data, data processing, revenue indicator calculation, influencing factor analysis and prediction model establishment. This systematic method can cover a relatively comprehensive range of aspects from From data collection to forecasting and evaluation, the problem of misjudgment caused by one-sided analysis or lack of systematicity in traditional revenue evaluation is solved; (4) This solution analyzes the factors affecting target revenue and their impact on revenue, and quantifies the impact, which can provide specific guidance for network operation optimization, such as giving priority to optimizing highly sensitive factors to increase revenue; (5) This solution is based on historical data and revenue evaluation indicators, combined with the factors affecting target revenue, to establish a revenue forecasting model, which can scientifically predict future revenue. This forecasting capability can help logistics companies understand the revenue changes of target outlets in different business scenarios in advance, and provide support for resource allocation and strategic decision-making; (6) Traditional Revenue evaluation often relies on experience and judgment, which may be subjective and uncertain. However, this solution uses a data-driven approach, combines revenue evaluation indicators and prediction models, reduces the interference of human factors, and the data-based and quantitative analysis results are more objective and scientific, which can provide companies with more reliable decision-making basis; (7) This solution can effectively eliminate abnormal data (such as incorrect entry, duplicate records or extreme values) by cleaning the historical income and expenditure of each stage, thereby ensuring the accuracy and completeness of the data. This processing method can avoid the deviation of the evaluation results due to data quality problems, provide a reliable data basis for subsequent analysis, improve the training accuracy of the model prediction, and further Improved the accuracy of network revenue evaluation; (8) This scheme established a relatively comprehensive revenue evaluation indicator system. These indicators quantitatively analyzed the revenue of the target logistics network from different dimensions, which can more comprehensively and meticulously reflect the actual operating benefits of the network; (9) This scheme can effectively screen out the key factors that have a greater impact on the target revenue, avoid being disturbed by minor or irrelevant factors in the analysis, and improve optimization efficiency; (10) This scheme can accurately quantify the specific impact of a single factor on the target revenue by analyzing the impact of each target revenue influencing factor on the single revenue of the logistics network, and then help enterprises understand the role of each factor in the revenue structure and provide data support for optimization decisions;(11) This scheme can fully consider the interaction between factors (such as synergy or conflict effect) by randomly combining multiple target profit influencing factors and analyzing their combined profit impact, which can more comprehensively reflect the actual situation and improve the evaluation accuracy. In addition, the Monte Carlo simulation function is further used to analyze the probability distribution and variation range of the combined profit influencing factors, which can effectively deal with the uncertainty problems in complex systems. Through a large number of random simulations, more reliable profit forecasting results can be provided to help enterprises make better decisions in an uncertain environment; (12) This scheme trains and optimizes the linear regression model based on profit evaluation indicators and target profit impact, which can effectively capture the law of profit changes, thereby establishing a more accurate profit forecasting model and improving the accuracy of the forecast. ; BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0016] Figure 1 This is a flow chart of the logistics network revenue evaluation method of the embodiment of the present application; Figure 2 It is another flow chart of the logistics network point revenue evaluation method of the embodiment of the present application; Figure 3 It is another flow chart of the logistics network point revenue evaluation method of the embodiment of the present application; Figure 4 It is another flow chart of the logistics network point revenue evaluation method of the embodiment of the present application; Figure 5 It is a structural block diagram of a logistics network point revenue evaluation device according to an embodiment of the present application; Figure 6 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The embodiment of the present invention provides a method for evaluating the revenue of a logistics network point, the method comprising: obtaining the stage historical revenue and stage historical expenditure of a target logistics network point in a historical time period; performing data processing on the stage historical revenue and stage historical expenditure respectively to obtain the stage historical target revenue and stage historical target expenditure; determining a revenue evaluation index based on the stage historical target revenue and stage historical target expenditure; determining the target revenue influencing factors of the target logistics network point; analyzing the degree of influence of the target revenue influencing factors on the target revenue of the target logistics network point; establishing a revenue prediction model based on the revenue evaluation index and the degree of influence of the target revenue; and predicting and evaluating the revenue of the target logistics network point in the future time period based on the revenue prediction model. This solution can be combined with multi-dimensional data to train the revenue prediction model, improve the comprehensiveness of the revenue evaluation, and improve the prediction effect.

[0018] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiment of the present invention is described below. Specifically, Figure 1 A flow chart of the logistics network revenue evaluation method of this application, see Figure 1 , which may include the following steps: S100. Obtain the stage historical income and stage historical expenditure of the target logistics network point within the historical time period.

[0020] Specifically, the historical time period may be a time period before the current time period, and the time period may be one day, one week, or one month. The specific time period may be set based on actual needs and is not specifically limited here.

[0021] Furthermore, historical income and expenditure of a certain period can be obtained from internal business systems such as financial systems, order systems, transportation management systems, warehouse management systems, etc. The historical income of a certain period may include but is not limited to the income of outlets obtained from the financial system, the amount of customer payments obtained from the order system, and other income, and the historical expenditure of a certain period may include but is not limited to the expenditure of outlets obtained from the financial system, the transportation costs (fuel costs, tolls, etc.) obtained from the transportation management system, and the storage costs (such as rental costs, equipment depreciation, labor costs, etc.) obtained from the warehouse management system.

[0022] Further, in an example, the historical income and historical expenditure of a stage can be pre-displayed on the interface, and the details interface can be entered by clicking the [Quick Entry] or [Indicator Entry] on the interface. The details interface can display the historical income and / or historical expenditure of the stage. For example, in the embodiment of the present application, the details interface is used to display the discount rate total value trend chart shown in Figure XX, the allocation pricing table and the customer pricing table. Further, the historical income and historical expenditure of the stage can also include kilogram segment pricing fees, freight, delivery fees and other fees. For the description of these fees, please refer to the contents in Table 1: Table 1 S102. Process the historical income and historical expenditure of a certain period respectively to obtain the historical target income and historical target expenditure of that period.

[0023] The data processing of the historical income and historical expenditure of a stage can be respectively processing the abnormal data in the historical income of the stage in a target format to obtain the historical target income of the stage, and processing the abnormal data in the historical expenditure of the stage in a target format to obtain the historical target expenditure of the stage. Specifically, when the abnormal data is missing data, the target format processing is to fill the abnormal data, for example, it can be supplemented according to the trend of historical data or the average data of the same type of outlets. When the abnormal data is repeated, the target format processing can be to remove the repeated data.

[0024] It is understandable that this example can process historical revenue and historical expenditure data and remove outliers, thereby ensuring the accuracy and completeness of the data, avoiding evaluation bias caused by data quality issues, improving the training accuracy of the prediction model, and thus improving the accuracy of subsequent profit effect evaluation.

[0025] Furthermore, after determining the historical target income and the historical target expenditure of the stage, the historical target income and the historical target expenditure of the stage can be organized into a table, for example, as shown in Table 2 below.

[0026] Table 2 Through the above steps, enterprises can systematically obtain the historical income and expenditure data of the target logistics outlets in the historical time period. These data not only provide a basis for revenue evaluation, but also provide an important reference for subsequent operational management and strategic decision-making. In addition, this solution can effectively eliminate abnormal data (such as incorrect entry, duplicate records or extreme values) by cleaning the historical income and expenditure of the stage, thereby ensuring the accuracy and completeness of the data. This processing method can avoid the deviation of the evaluation results due to data quality problems, provide a reliable data basis for subsequent analysis, improve the training accuracy of the model prediction, and further improve the accuracy of the outlet revenue evaluation.

[0027] S104. Determine the benefit evaluation indicators based on the historical target income and historical target expenditure of the stage.

[0028] In one example, the revenue evaluation index includes a first revenue profit, a second revenue profit, and a return on investment. The first revenue profit is used to represent the remaining revenue of the target logistics network after deducting the historical target expenditure of the stage, the second revenue profit is used to represent the remaining revenue of the target logistics network after deducting the target tax from the first revenue profit, and the return on investment is used to represent the expected investment revenue of the target logistics network; The first income profit is determined based on the following formula: First income profit = stage historical target income - stage historical target expenditure; Second income profit is determined based on the following formula; Second income profit = first income profit - target tax; The return on investment is determined based on the following formula: Return on investment = (second income profit / total investment) × 100%.

[0029] It is understandable that in this example, a relatively comprehensive income evaluation indicator system is established, including the first income profit, the second income and the return on investment. These indicators quantitatively analyze the income of the target logistics network from different dimensions, and can more comprehensively and meticulously reflect the actual operating benefits of the network; S106. Determine the factors influencing the target revenue of the target logistics outlets.

[0030] In one example, Figure 2 Another flow chart of the logistics network point profit evaluation method is an exemplary description of the factors affecting the target profit of the target logistics network point in step S106. For details, refer to Figure 2 , including the following steps: S200. Obtain multiple revenue correlation factors of the target logistics network.

[0031] Exemplarily, the profit-related factors are factors that affect the profit of the target logistics network, and the profit-related factors may include but are not limited to business volume, transportation price, labor cost and other factors.

[0032] S202. Determine the degree of influence of each revenue-related factor on the target revenue of the target logistics network.

[0033] In one example, the random forest algorithm can be used to evaluate the importance score of each factor and identify the impact of each revenue-related factor on the target revenue of the target logistics outlet. It can be understood that the random forest algorithm is a conventional algorithm for evaluating the importance of the target object, which will not be repeated here. In this example, the degree of influence on the target revenue is characterized based on the importance score. When the importance score of a certain revenue-related factor is high, it means that the revenue-related factor has a greater impact on the target revenue of the target logistics outlet. When the importance score of a certain revenue-related factor is low, it means that the revenue-related factor has a smaller impact on the target revenue of the target logistics outlet. Preferably, the importance score can be any score between 0 and 10 points.

[0034] S204: Obtain a target impact threshold.

[0035] Specifically, the target impact threshold may be preset. For example, the target impact threshold may be set to 5 points, 6 points, or 7 points. Specifically, it may be set based on actual needs and is not specifically limited here.

[0036] S206: Determine the target revenue influencing factors based on the target impact threshold and the degree of impact of each revenue-related factor on the target revenue of the target logistics network.

[0037] In one example, a revenue-related factor having an importance score greater than a target impact threshold may be determined as a target revenue impact factor.

[0038] It can be understood that this solution can effectively screen out the key factors that have a greater impact on the target return, avoid being disturbed by minor or irrelevant factors in the analysis, and improve the optimization efficiency.

[0039] S108. Analyze the degree to which the factors influencing the target revenue affect the target revenue of the target logistics outlets.

[0040] like Figure 3 As shown, it is another flow chart of the logistics network point revenue evaluation method. The method is a rational explanation of step S108. Figure 3 , which may include the following steps: S300. Analyze the influence of each target revenue influencing factor on the single revenue of the target logistics network.

[0041] In this step, only one sensitivity factor is changed each time, and other factors remain unchanged. The influence of the factor on the revenue evaluation index (such as gross profit, net profit, ROI, etc.) when it changes within a certain range (such as ±10%, ±20%) is calculated. In one example, the random forest algorithm can be used to evaluate the importance score of each target revenue influencing factor, and then based on the score of each target revenue influencing factor, the influence of each target revenue influencing factor on the single revenue of the target logistics network is determined.

[0042] Furthermore, in another example, the Pearson correlation coefficient or the Spearman rank correlation coefficient can also be used to analyze the linear relationship between the target revenue influencing factors such as business volume, transportation price, etc. and the revenue index. For example, the value range of the correlation coefficient is between -1 and 1, close to 1 or -1 indicates a strong correlation, and close to 0 indicates a weak correlation. Furthermore, a multivariate linear regression model is established based on multivariate linearity to analyze the specific impact of each variable (such as business volume, transportation price, etc.) on revenue, that is, the relative importance of each factor is judged by the regression coefficient. The larger the coefficient, the more significant the impact of the factor on revenue.

[0043] S302. Taking the single benefit impact degree as the target benefit impact degree.

[0044] Furthermore, after determining the impact degree of the target revenue, step S304 may be performed.

[0045] S304: Draw a single revenue impact chart and send it to the target interface for display.

[0046] It can be understood that by analyzing the degree of influence of each target revenue influencing factor on the single revenue of the logistics network, the solution can accurately quantify the specific impact of a single factor on the target revenue, which can then help enterprises understand the role of each factor in the revenue structure and provide data support for optimizing decisions.

[0047] Furthermore, Figure 4 This is another flow chart of the method for evaluating the revenue of logistics outlets. This method is another rational explanation of step S108. Figure 4 , which may include the following steps: S400, randomly combining multiple target return influencing factors to obtain multiple groups of combined return influencing factors.

[0048] Specifically, after determining the factors affecting the target return, multiple groups of combined return influencing factors can be generated based on a random number generation algorithm.

[0049] S402. Determine the distribution type and distribution parameters of the factors affecting the return of each group of portfolios.

[0050] Specifically, the distribution type may include but is not limited to normal distribution, exponential distribution, uniform distribution, etc. The specific distribution type may be selected based on actual needs. After the distribution type is determined, the corresponding distribution parameters (such as mean, standard deviation, etc.) are further estimated.

[0051] S404. Based on the distribution type, distribution parameters and Monte Carlo simulation function, determine the probability distribution and variation range of the factors affecting the return of each group of portfolios.

[0052] Specifically, the Monte Carlo simulation method can be used to perform multiple random sampling of the factors affecting the return of each group of portfolios. This process will generate a large number of return results, so that the probability distribution and range of variation of each combination can be determined based on the selected distribution type and parameters. Monte Carlo simulation can effectively capture uncertainty and risk and provide data support for subsequent analysis.

[0053] S406. Determine the impact degree of the target return based on the probability distribution and the variation range.

[0054] Furthermore, based on the probability distribution and variation range obtained in step S404, the influence of each combination on the target return is evaluated. Specifically, this can be achieved by calculating statistical indicators such as expected value and variance, thereby identifying which factors have the greatest impact on the return.

[0055] It can be understood that this example can more fully consider the interaction between factors (such as synergy or conflict effect) by randomly combining multiple target return influencing factors and analyzing the degree of their combined return impact, which can more comprehensively reflect the actual situation and improve the evaluation accuracy. Further use of the Monte Carlo simulation function to analyze the probability distribution and range of variation of the combined return influencing factors can effectively deal with the uncertainty problems in complex systems. Through a large number of random simulations, it can provide more reliable return forecast results and help companies make better decisions in uncertain environments.

[0056] S110. Establish a revenue prediction model based on the revenue evaluation indicators and the impact degree of the target revenue.

[0057] Specifically, a linear regression model can be used to fit the target income impact factors corresponding to the target income impact degree that meets the income evaluation index to determine the income. The form of the model is: Y=β0+ β 1×X+ β 2XXX+...... β 2XXX+ ϵ; Among them, Y is the return, β0 is the intercept, β1, β2, β n are regression coefficients, ϵ is the error term; X1, X2, Xn is the independent variable (e.g., transportation cost, storage cost, order quantity, etc.); In one example, when the independent variables are transportation cost, storage cost, order quantity, etc., the benefits satisfy the following relationship: Revenue == β 0+ β 1× Shipping cost+ β 2× Storage Cost+ β 3×Order Quantity+ ϵ; Specifically, the regression coefficient uses historical data to train a linear regression model to obtain the regression coefficient.

[0058] The target income impact factor corresponding to the target income impact degree that meets the income evaluation index may be a target income impact factor in which any one or more of the first income profit, the second income profit, or the return on investment meets the target requirements. The target requirements may be, for example, the first income profit or the first income profit meets the target amount, and the return on investment meets the target ratio.

[0059] Specifically, the target revenue influencing factors corresponding to the target revenue influencing degree can be divided into data of training set and test set, and the linear regression model can be trained based on the training set, for example, using the scikit-learn library in Python to implement the linear regression model training, and calling the fit method after obtaining the linear regression model. The model will calculate the regression coefficient and intercept based on the training data.

[0060] S112. Based on the revenue forecasting model, forecast and evaluate the revenue of the target logistics network in the future time period.

[0061] Specifically, the transportation cost, warehousing cost, order quantity, etc. in the future time period can be input into the revenue prediction model, and the revenue of the target logistics network can be determined based on the output results of the revenue prediction model.

[0062] It can be understood that this technical solution can combine multi-dimensional data to train the revenue prediction model, improve the comprehensiveness of the revenue evaluation, and improve the prediction effect. Moreover, through the steps of obtaining historical data, data processing, calculating revenue indicators, analyzing influencing factors, and establishing a prediction model, a complete revenue evaluation process is formed. This systematic method can cover all aspects from data collection to prediction and evaluation in a relatively comprehensive manner, and solve the problem of misjudgment caused by one-sided analysis or lack of systematicity in traditional revenue evaluation. Furthermore, by analyzing the factors affecting the target revenue and their influence on the revenue, and by quantifying the influence, specific guidance can be provided for the optimization of branch operations, such as giving priority to Optimize highly sensitive factors to increase revenue; further, based on historical data and revenue evaluation indicators, combined with factors affecting target revenue, establish a revenue forecasting model that can scientifically predict future revenue situations. This forecasting capability can help logistics companies understand in advance the revenue changes of target outlets under different business scenarios, and provide support for resource allocation and strategic decision-making; further, traditional revenue evaluation often relies on experience and judgment, which may be subjective and uncertain. This solution uses a data-driven approach, combined with revenue evaluation indicators and forecasting models, to reduce the interference of human factors. The digitized and quantitative analysis results are more objective and scientific, and can provide companies with more reliable decision-making basis.

[0063] Further, such as Figure 5 As shown, a logistics network point revenue evaluation device is also disclosed, the device comprising: The stage historical data acquisition module is used to obtain the stage historical income and stage historical expenditure of the target logistics network in the historical time period; A data processing module is used to process the historical income and historical expenditure of a stage respectively to obtain the historical target income and historical target expenditure of the stage; A revenue evaluation index determination module is used to determine the revenue evaluation index based on the historical target income and historical target expenditure of the stage; The module for determining the factors affecting the target revenue is used to determine the factors affecting the target revenue of the target logistics network. The module for analyzing the impact degree of target revenue is used to analyze the impact degree of the factors affecting the target revenue on the target logistics network points. The revenue forecasting model building module is used to build a revenue forecasting model based on the revenue evaluation index and the impact degree of the target revenue; The forecasting and evaluation module is used to forecast and evaluate the revenue of the target logistics network in the future time period based on the revenue forecasting model.

[0064] The application introduction of the relevant modules of the device in this example can refer to the relevant introduction of the principle of the above method, which will not be repeated here.

[0065] According to another aspect of the present application, the present application also discloses an electronic device, which includes a memory and at least one processor, wherein instructions are stored in the memory; at least one processor calls the instructions in the memory so that the electronic device executes each step of the above-mentioned logistics outlet receipt rate analysis method.

[0066] above Figure 5 The logistics network point receipt rate analysis device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0067] Figure 6 6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 633 or data 632. Among them, the memory 620 and the storage medium 630 can be short-term storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 600. Furthermore, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the electronic device 600.

[0068] The electronic device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 6 The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0069] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the logistics network revenue evaluation method.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0071] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0072] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logistics network revenue evaluation method, characterized in that: The method comprises: Obtain the historical income and expenditure of the target logistics outlets during the historical period; Process the data of the historical income and expenditure of the stage respectively to obtain the historical target income and expenditure of the stage; Determine the benefit evaluation index based on the historical target income and historical target expenditure of the said stage; Determine the factors affecting the target revenue of the target logistics network; Analyze the impact of the target revenue influencing factors on the target revenue of the target logistics network; Based on the profit evaluation index and the impact degree of the target profit, a profit prediction model is established; Based on the revenue prediction model, a forecast and evaluation is performed on the revenue of the target logistics network in the future time period.

2. The logistics network revenue evaluation method according to claim 1 is characterized in that: The data of the historical income and historical expenditure of the stage are processed respectively to obtain the historical target income and historical target expenditure of the stage, including: The historical income of the stage and the historical expenditure of the stage are cleaned respectively, so as to process the abnormal data into a target format to obtain the historical target income of the stage and the historical target expenditure of the stage.

3. The logistics network revenue evaluation method according to claim 1 is characterized in that: The income evaluation index determined based on the historical target income of the stage and the historical target expenditure of the stage includes: The profit evaluation index includes a first profit, a second profit and a return on investment. The first profit is used to represent the remaining profit of the target logistics network after deducting the historical target expenditure of the stage. The second profit is used to represent the remaining profit of the target logistics network after deducting the target tax from the first profit. The return on investment is used to represent the expected investment return of the target logistics network. The first income profit is determined based on the following formula: First income profit = stage historical target income - stage historical target expenditure; The second income profit is determined based on the following formula; Second income profit = first income profit - target tax; The return on investment is determined based on the following formula: Return on investment = (second income profit / total investment) × 100%.

4. The logistics network revenue evaluation method according to claim 1, characterized in that: The factors affecting the target revenue of the target logistics network point include: Acquire multiple revenue-related factors of the target logistics network; Determine the degree of influence of each revenue-related factor on the target revenue of the target logistics network point; Get the target impact threshold; The target revenue influencing factor is determined based on the target impact threshold and the degree of impact of each revenue-related factor on the target revenue of the target logistics network point.

5. The method for evaluating the profitability of a logistics network according to claim 1, characterized in that: The analyzing the influence degree of the target revenue influencing factors on the target revenue of the target logistics network point includes: Analyze the influence degree of each of the target revenue influencing factors on the single revenue of the target logistics network point; Taking the single benefit impact degree as the target benefit impact degree; Draw a single benefit impact chart and send it to the target interface for display.

6. The method for evaluating the revenue of a logistics network according to claim 1, characterized in that: The analyzing the influence degree of the target revenue influencing factors on the target revenue of the target logistics network point includes: Randomly combining a plurality of the target profit influencing factors to obtain a plurality of groups of combined profit influencing factors; Determine the distribution type and distribution parameters of each group of factors affecting the portfolio return; Based on the distribution type, distribution parameters and Monte Carlo simulation function, determine the probability distribution and variation range of each group of factors affecting the portfolio return; The target benefit impact degree is determined based on the probability distribution and the variation range.

7. The method for evaluating the revenue of a logistics network according to claim 1, characterized in that: The establishing of a revenue prediction model based on the revenue evaluation index and the target revenue impact degree includes: Get the linear regression model; Based on the revenue evaluation index and the target revenue impact degree, the linear regression model is trained and optimized to obtain the revenue prediction model.

8. A logistics network point revenue evaluation device, characterized in that: The device comprises: The stage historical data acquisition module is used to obtain the stage historical income and stage historical expenditure of the target logistics network in the historical time period; A data processing module is used to process the historical income and historical expenditure of a stage respectively to obtain the historical target income and historical target expenditure of the stage; A revenue evaluation index determination module, used to determine the revenue evaluation index based on the historical target income of the stage and the historical target expenditure of the stage; A target revenue influencing factor determination module, used to determine the target revenue influencing factors of the target logistics network point; A target revenue impact degree analysis module is used to analyze the impact degree of the target revenue impact factors on the target revenue of the target logistics network point; A revenue prediction model building module, used to build a revenue prediction model based on the revenue evaluation index and the target revenue impact degree; The forecasting and evaluation module is used to forecast and evaluate the revenue situation of the target logistics network in the future time period based on the revenue forecasting model.

9. An electronic device, characterized in that: The electronic device includes a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the electronic device executes each step of the logistics network revenue evaluation method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the logistics network point revenue evaluation method as described in any one of claims 1-7 are implemented.

Images