Bulk and general cargo contract performance prediction method and system based on tallying data and prediction model

Abstract

The invention discloses a bulk and general cargo contract performance prediction method and system based on tallying data and a prediction model, and relates to the technical field of bulk and general cargo port management, and the method comprises the steps: collecting the tallying data of bulk and general cargos in the port arriving and unloading process in real time, and forming the accumulation of the cargo number in a contract period; constructing a prediction model based on the historical transportation volume, the tallying data, the shipping fluctuation and the predicted port arrival data, and predicting the final cargo volume in the same period according to the prediction model to obtain a predicted cumulative tallying volume; establishing different contract models according to different protocol contract types and contract modeling rules, wherein the protocol contract types comprise guaranteed contracts and ladder contracts; calculating the settlement amount of the contract based on the predicted cumulative tallying amount and a contract modeling rule; adopting a Monte Carlo method to calculate the standard reaching probability of the contract based on the predicted cumulative tallying quantity and the contract model; according to the invention, dynamic monitoring, quantitative analysis and prediction evaluation of the contract execution condition are realized.

Description

Technical Field

[0001] This invention relates to the field of bulk cargo port management technology, and in particular to a method and system for predicting the performance of bulk cargo contracts based on tallying data and a predictive model. Background Technology

[0002] In bulk cargo transportation and port loading / unloading operations, contract settlement is typically based primarily on the quantity of goods transported and the corresponding rates. A common model is to apply a fixed rate within an agreed-upon quantity range, with more favorable rates available as the cumulative transport volume reaches higher ranges. Currently, the most widely used contract types in the industry include volume-guaranteed contracts and tiered contracts. A volume-guaranteed contract means that both parties pre-agree on the volume of goods transported within a certain period (i.e., the contract amount), and settlement is based on a preferential rate applied to that agreed-upon volume; if the actual transport volume does not reach the agreed-upon amount, the customer must make up the difference at the standard rate. A tiered contract, on the other hand, divides the actual completed business volume into multiple billing tiers; the larger the business volume, the more favorable the applicable rate, aiming to incentivize customers to increase their transport volume and achieve a win-win situation for both supply and demand parties.

[0003] However, existing contract performance management suffers from the following major problems: First, actual performance data is typically only aggregated and confirmed upon contract completion or phase settlement, lacking a real-time feedback mechanism. Second, the correlation between contract quantity and rate is not dynamically quantified during execution, making it difficult to assess in real time whether preferential conditions have been met. Third, statistics are based solely on completed cargo handling data, failing to incorporate anticipated arrival information to predict future performance trends. Furthermore, the lack of real-time monitoring and automatic early warning functions for contract performance progress prevents timely risk identification in the early stages of deviations and fails to provide data-driven decision support for management, resulting in delayed response measures and impacting overall contract execution efficiency and economic benefits. Summary of the Invention

[0004] In view of the above-mentioned prior art, the present invention provides a method and system for predicting the performance of bulk cargo contracts based on tallying data and prediction models, which mainly solves the technical problems existing in the background art.

[0005] To achieve the above objectives, the technical solution of this invention is implemented as follows: Firstly, a method for predicting the performance of bulk cargo contracts based on tallying data and a predictive model, the method comprising the following steps: real-time collection of tallying data during the arrival and unloading process of bulk cargo, and formation of a cumulative quantity of goods within the contract period; Based on historical transport volume, cargo handling data, shipping fluctuations and expected arrival data, a prediction model is constructed. The final cargo volume during the contract period is predicted based on the prediction model, and the predicted cumulative cargo handling volume is obtained. Different contract models are established based on different agreement contract types and contract modeling rules. The agreement contract types include volume guarantee contracts and tiered contracts. The settlement amount of the contract is calculated based on the predicted cumulative cargo volume and contract modeling rules. The Monte Carlo method is used to calculate the contract fulfillment probability based on the predicted cumulative cargo volume and contract model; and the contract performance difference risk warning is given based on the fulfillment probability.

[0006] As a preferred embodiment of the present invention, the predicted cumulative cargo volume is obtained by predicting the final cargo volume during the contract period based on a prediction model, as detailed below: Let the cumulative amount of goods handled at the current moment be... The remaining contract period is The prediction increment of the prediction model for the k-th time period in the future is Then the projected cumulative cargo handling volume at the end of the contract period for: .

[0007] As a preferred embodiment of the present invention, the modeling rules for volume guarantee contracts include: Using the contract target volume as an indicator, the settlement unit price is determined by comparing the predicted cumulative cargo handling volume at the end of the contract period with the contract target volume; and the final settlement is based on whether the predicted cumulative cargo handling volume at the end of the contract period reaches the indicator, to determine whether to apply the preferential rate or the standard rate.

[0008] As a preferred embodiment of the present invention, for guaranteed volume contracts, a mechanism combining advance settlement and end-of-period adjustment is adopted for monetary settlement, as follows: When the predicted cumulative inventory volume is greater than or equal to the contract target volume, it is determined that the target has been met, and the final total amount payable is directly obtained by multiplying the predicted cumulative inventory volume by the preferential rate. When the predicted cumulative cargo handling volume is less than the contract target volume, it is determined as a failure to meet the target, and the final total amount payable is obtained by multiplying the predicted cumulative cargo handling volume by the standard rate.

[0009] As a preferred embodiment of the present invention, the modeling rules for tiered contracts are as follows: The contract forecast cumulative cargo handling volume range is divided into multiple continuous and non-overlapping quantity intervals. Each interval is configured with a corresponding lower limit, upper limit, and specific segmented fee rate. Based on the different quantity intervals in which the cumulative cargo handling volume is located throughout the entire contract period, the settlement amount of the completed segment and the remaining difference of the uncompleted segment are calculated.

[0010] As a preferred embodiment of the present invention, for tiered contracts, a real-time segmented pricing mechanism is adopted for amount settlement, as follows: When the predicted cumulative cargo handling volume crosses the upper limit of a preset interval and enters the next interval, the currently applicable rate is switched to the segmented rate of the next interval, and the amounts of each completed quantity interval are accumulated. The settlement amount of each interval is the product of the actual quantity passed in that interval and its corresponding segmented rate.

[0011] As a preferred embodiment of the present invention, for tiered contracts, a mechanism is also adopted for settlement of amounts, which is first settled based on the execution price and then uniformly traced back at the end of the period, as follows: Based on the predicted cumulative inventory volume, first determine which complete quantity ranges it crosses, and calculate the payable amount in each range. Sum the payable amounts to obtain the theoretical final payable amount. Then calculate the difference between the final payable amount and the total amount temporarily settled at the agreed execution price during the entire execution period, and generate an adjustment amount.

[0012] As a preferred embodiment of the present invention, the Monte Carlo method is used to predict the probability of contract fulfillment based on the predicted cumulative cargo volume and the contract model, as follows: In the forecasting phase, M future forecast paths are generated through Monte Carlo simulation, resulting in a set of cumulative forecast values ​​at the end of the period. ; For tiered contracts, let the target threshold be L. The probability of achieving the target threshold L can be approximately calculated using the following formula. :

[0013] For volume-guaranteed contracts, let the volume-guaranteed index be... The probability of contract compliance is calculated using the following formula. :

[0014] Where m is the number of samples. ， Let L be the cumulative cargo handling volume at the end of the period under the Mth prediction path, and L be the contract target threshold. This is the lower bound of the next interval for the ladder contract. This is an indicator function used to determine whether the condition is met. If the condition is true, the value is 1; otherwise, the value is 0.

[0015] As a preferred embodiment of the present invention, a risk warning for contract performance discrepancies is provided based on the probability of compliance, specifically including: For tiered contracts, the probability of meeting the requirements is divided into "high probability," >80%", "Medium probability, 50% < <80%)", "Low probability", <50%; For volume guarantee contracts, the probability of meeting the target is categorized as "worry-free target meeting". >90%", "Needs attention, 60% < <90%", "High risk", <60%; When the probability of meeting the target falls below a preset threshold, a performance warning is automatically triggered, and execution suggestions are output.

[0016] Secondly, the aforementioned bulk cargo contract performance prediction system includes: The data acquisition module collects real-time cargo handling data during the arrival and unloading process of bulk cargo, and generates a cumulative cargo quantity for the contract period. The forecasting module constructs a forecasting model based on historical transport volume, cargo handling data, shipping fluctuations, and expected arrival data. The forecasting model predicts the final cargo volume within the contract period, thus obtaining the predicted cumulative cargo handling volume. The contract modeling module establishes different contract models based on different contract types and contract modeling rules. The contract types include volume guarantee contracts and tiered contracts. The cost calculation module calculates the settlement amount of the contract based on the predicted cumulative cargo volume and contract modeling rules. The risk warning module uses the Monte Carlo method to calculate the contract fulfillment probability based on the predicted cumulative cargo volume and contract model; and provides a risk warning for contract performance discrepancies based on the fulfillment probability.

[0017] Thirdly, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores multiple instructions; the processor loads instructions from the memory to execute steps in any of the bulk cargo contract performance prediction methods based on tally data and prediction models provided in embodiments of this application.

[0018] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in embodiments of this application.

[0019] Fifthly, embodiments of this application also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in embodiments of this application.

[0020] The beneficial effects of this invention are as follows: This invention provides a method and system for predicting the performance of bulk cargo contracts based on tallying data and prediction models. This invention combines current tallying data, expected arrival data, and prediction models to achieve dynamic monitoring, quantitative analysis, and predictive evaluation of contract performance, helping port enterprises and cargo owners to determine in advance whether they can achieve higher preferential tiers, thereby guiding decision-making. At the same time, this invention also assists both parties to the contract to adjust transportation and settlement strategies in a timely manner through risk warning, comprehensively improving the level of intelligence and real-time response capability of contract performance. Attached Figure Description

[0021] Figure 1 A schematic diagram illustrating the steps of a bulk cargo contract performance prediction method based on tallying data and a prediction model provided in this application; Figure 2 This is a schematic diagram of the structure of a bulk cargo contract performance prediction system provided in this application. Detailed Implementation

[0022] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. In the following description, the expression "some embodiments" refers to a subset of all possible embodiments; however, it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0023] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0024] It should be understood that the present invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Furthermore, the terminology used herein is intended only to describe particular embodiments and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “compose” and / or “comprising,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0025] It should also be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "inner," "outer," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0026] To fully understand this invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.

[0027] Firstly, please refer to the attached document. Figure 1 A method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model, the method comprising the following steps: Step S1, collecting tallying data in real time during the arrival and unloading process of bulk cargo, and forming a cumulative quantity of goods within the contract period; In this embodiment, during the arrival and unloading process of each ship carrying iron ore for Party A, cargo handling data is collected in real time through the integration of Terminal Operating System (TOS), weighbridge system, and handheld terminals for cargo handlers. This step realizes the automated and real-time collection of cargo handling data and aggregates discrete operation data into cumulative completion volume under the contract dimension, solving the problem of lack of real-time feedback mechanism in the prior art and providing a dynamic and real data source for the prediction model.

[0028] Step S2: Based on historical transport volume, cargo handling data, shipping fluctuations and expected arrival data, construct a prediction model, predict the final cargo volume during the contract period according to the prediction model, and obtain the predicted cumulative cargo handling volume; In this embodiment, the historical transport volume includes the quarterly and monthly arrival patterns of Party A over the past few years. The cargo handling data refers to the cumulative volume and its arrival time series obtained in S1. The shipping fluctuation data includes global dry bulk freight rate indices, weather conditions on major routes, berth congestion indices, etc. The expected arrival data includes the expected arrival schedule for the fourth quarter, which is already en route or booked, obtained from Party A or the shipping company, along with their predicted cargo volumes.

[0029] The predicted cumulative cargo volume obtained by the predictive model is used as common input data for both volume guarantee contracts and tiered contracts to conduct quantitative performance analysis.

[0030] Step S3: Establish different contract models according to different agreement contract types and contract modeling rules. The agreement contract types include volume guarantee contracts and tiered contracts. Step S4: Calculate the settlement amount of the contract based on the predicted cumulative cargo handling volume and contract modeling rules; In some embodiments, the type of contract is identified before calculating the settlement amount of the contract.

[0031] For example, the modeling data of the contract is read. If the identification logic detects that the contract model simultaneously defines three key parameters: contract target quantity, preferential rate, and standard rate, the contract is identified as a "quantity guarantee contract." Upon successful identification, the modeling rules specifically for quantity guarantee contracts are invoked to calculate the settlement amount of the contract. If the identification logic detects that the contract model defines a list containing multiple quantity ranges and their corresponding segmented rates, but does not define a single "quantity guarantee target quantity," it is identified as a tiered contract. Upon successful identification, the modeling rules for tiered contracts are invoked to calculate the settlement amount of the contract.

[0032] Step S5: The Monte Carlo method is used to calculate the contract compliance probability based on the predicted cumulative cargo volume and the contract model; and a risk warning for contract performance discrepancies is issued based on the compliance probability.

[0033] As a preferred embodiment of the present invention, the predicted cumulative cargo volume is obtained by predicting the final cargo volume during the contract period based on a prediction model, as detailed below: Let the cumulative amount of goods handled at the current moment be... The remaining contract period is The prediction increment of the prediction model for the k-th time period in the future is Then the projected cumulative cargo handling volume at the end of the contract period for: .

[0034] As a preferred embodiment of the present invention, the modeling rules for volume guarantee contracts include: Using the contract target volume as an indicator, the settlement unit price is determined by comparing the predicted cumulative cargo handling volume at the end of the contract period with the contract target volume; and the final settlement is based on whether the predicted cumulative cargo handling volume at the end of the contract period reaches the indicator, to determine whether to apply the preferential rate or the standard rate.

[0035] As a preferred embodiment of the present invention, for volume guarantee contracts, a mechanism combining advance settlement and end-of-period adjustment is adopted for monetary settlement, and the calculation process is as follows: First, predefine the key parameters of the contract. Key parameters include, but are not limited to: the target contract volume, the preferential rate applicable to the achievement of the target, and the standard rate applicable to the non-achievement of the target, wherein the preferential rate is lower than the standard rate.

[0036] During the contract execution period, cargo handling data is collected in real time, and the cumulative cargo handling volume is dynamically calculated. At the end of the contract period, the final cumulative cargo handling volume is compared with the preset contract target volume, and different settlement logics are executed based on the comparison results, as follows: When the predicted cumulative inventory volume is greater than or equal to the contract target volume, it is determined that the target has been met, and the final total amount payable is directly obtained by multiplying the predicted cumulative inventory volume by the preferential rate. When the predicted cumulative cargo handling volume is less than the contract target volume, it is determined as a failure to meet the target, and the final total amount payable is obtained by multiplying the predicted cumulative cargo handling volume by the standard rate.

[0037] In this embodiment, the predicted cumulative inventory volume is... Substituting this into the modeling rules of the volume guarantee contract, among which, the preferential rate... (Yuan / ton), the settlement price used when standards are met, with a standard rate of [missing information]. (RMB / ton), used to represent the settlement price when the standard is not met, and requires... The cumulative amount required to be calculated based on the preferential rate during the contract period is:

[0038] Assume the quantity assurance and quantity achievement indicator function is as follows: ,when ≥ hour, =1; Conversely, =0. When the contract target quantity is not met, the actual total amount payable is:

[0039] Because settlement is made first at a discounted rate during the execution period, if the contract target quantity is not met, a one-time price difference needs to be paid. The price difference is calculated as follows: .

[0040] In some embodiments, a mechanism combining advance settlement and end-of-term adjustment is employed for volume guarantee contracts. That is, during contract execution, settlement is temporarily made at a preferential rate. At the end of the contract period, after the aforementioned compliance determination is completed, if the result is non-compliance, a price difference compensation operation is automatically triggered. Specifically, a compensation amount is first calculated and generated, which is equal to the product of the cumulative cargo volume and the difference between the standard rate and the preferential rate. Through this compensation operation, the temporary total amount previously settled at the preferential rate is corrected to the final total amount payable calculated at the standard rate.

[0041] As a preferred embodiment of the present invention, the modeling rules for tiered contracts are as follows: The contract forecast cumulative cargo handling volume range is divided into multiple continuous and non-overlapping quantity intervals. Each interval is configured with a corresponding lower limit, upper limit, and specific segmented fee rate. Based on the different quantity intervals in which the cumulative cargo handling volume is located throughout the entire contract period, the settlement amount of the completed segment and the remaining difference of the uncompleted segment are calculated.

[0042] As a preferred embodiment of the present invention, for tiered contracts, a real-time segmented pricing mechanism is adopted for amount settlement, as follows: When the predicted cumulative cargo handling volume crosses the upper limit of a preset interval and enters the next interval, the currently applicable rate is switched to the segmented rate of the next interval, and the amounts of each completed quantity interval are accumulated. The settlement amount of each interval is the product of the actual quantity passed in that interval and its corresponding segmented rate.

[0043] In this embodiment, a tiered contract refers to applying different rates to different segments based on the cumulative transportation volume within the contract period. The quantity range is divided into several segments. The unit price for each segment is ,Will Substitute the components into the tiered pricing formula for the tiered contract to determine its final position within the tier. The unit price for each segment is: The amount payable at the end of the period can be expressed as:

[0044] in, The number of interval segments, The first The lower and upper bounds of the segment, This refers to the rate for that range.

[0045] Real-time accumulation of transportation volume during contract execution. Continuously growing, depending on the current situation Determine the current timeframe and calculate the difference between the completed segment's amount and the remaining amount for the incomplete segment. For example, when the cumulative transport volume reaches the lower bound of the next tier. At that time, the unit price will be from Automatically switch to This enables dynamic discounts.

[0046] As a preferred embodiment of the present invention, for tiered contracts, a mechanism is adopted for settlement of amounts based on the execution price upfront, with a unified retrospective settlement at the end of the period. In this model, to simplify operations during contract execution, a provisional settlement is made in advance throughout the execution period based on a unified agreed execution price, for example, according to the initial fee rate or a benchmark fee rate agreed upon by both parties. At the end of the contract period, a one-time settlement is then conducted according to the complete tiered rules.

[0047] Specifically, based on the predicted cumulative cargo volume, it is first determined which complete quantity ranges it has crossed, and the payable amount in each range is calculated. The payable amounts are summed to obtain the theoretical final payable amount. Then, the difference between the final payable amount and the total amount temporarily settled at the agreed execution price during the entire execution period is calculated, and an adjustment amount is generated.

[0048] In this embodiment, based on segmented intervals After determining the current cost level, calculate the cost amount of the intervals already crossed, and further output the incremental cargo volume required to reach the next level. The calculation method is as follows:

[0049] This clarifies the marginal demand for the next tier of preferential conditions.

[0050] To ensure commercial convenience, this invention supports both "real-time segmented pricing" and "settlement based on the executed price first, with unified retrospective pricing at the end of the period": Under the real-time segmented pricing method, billing is accumulated based on the actual intervals crossed during execution; under the end-of-period retrospective method, settlement is first made at the agreed executed price during the execution period, and then the final billing is calculated according to the formula at the end of the period. Make a difference adjustment.

[0051] As a preferred embodiment of the present invention, the Monte Carlo method is used to predict the probability of contract fulfillment based on the predicted cumulative cargo volume and the contract model, as follows: In the forecasting phase, M future forecast paths are generated through Monte Carlo simulation, resulting in a set of cumulative forecast values ​​at the end of the period. ; For tiered contracts, let the target threshold be L. The probability of achieving the target threshold L can be approximately calculated using the following formula. :

[0052] For volume-guaranteed contracts, let the volume-guaranteed index be... The probability of contract compliance is calculated using the following formula. :

[0053] Where m is the number of samples. ， Let L be the cumulative cargo handling volume at the end of the period under the Mth prediction path, and L be the contract target threshold. This is the lower bound of the next interval for the ladder contract. This is an indicator function used to determine whether the condition is met. If the condition is true, the value is 1; otherwise, the value is 0.

[0054] In some embodiments, to ensure the objectivity and reliability of the prediction results, the present invention strictly limits the sampling source when using the Monte Carlo method: A. Model-based sampling. In the process of neural network prediction, different prediction paths are generated by maintaining Dropout activation or using model ensemble. Each path corresponds to the natural output of the model under different stochastic conditions, reflecting the inherent uncertainty of the model; B. Sampling based on historical residuals. Utilizing the distribution of historical prediction residuals for bootstrapping or perturbation, the residuals are added to the point prediction results to generate reasonable future paths, ensuring that the results conform to actual transportation patterns.

[0055] C. Human manipulation is prohibited. It is not permitted to manually set sampling ranges or forcibly modify predicted values ​​to guarantee compliance. All sampling must be automatically generated based on historical data or model output to ensure that the probability of compliance truly reflects the performance risk.

[0056] Therefore, by using the aforementioned neural network prediction method and sampling constraint mechanism, this invention can not only more accurately predict the cumulative volume of goods at the end of the contract period, but also quantify the predicted settlement amount and difference risk by combining the modeling rules of guaranteed volume contracts and tiered contracts.

[0057] As a preferred embodiment of the present invention, a risk warning for contract performance discrepancies is provided based on the probability of compliance, specifically including: For tiered contracts, the probability of meeting the requirements is divided into "high probability," >80%", "Medium probability, 50% < <80%)", "Low probability", <50%; For volume guarantee contracts, the probability of meeting the target is categorized as "worry-free target meeting". >90%", "Needs attention, 60% < <90%", "High risk", <60%; When the probability of meeting the target falls below a preset threshold, a performance warning is automatically triggered, and execution suggestions are output.

[0058] In this embodiment, if the probability of achieving the target shows that it is likely to reach the next level, it prompts the parties to continue to maintain or accelerate the transportation plan; if the probability of achieving the target shows that it is difficult to achieve, it prompts the relevant parties to adjust their strategies in advance to avoid overly high expectations.

[0059] For example, during risk warning, the confidence level of the predicted path generated by the Monte Carlo method is simultaneously linked to the estimated amount of supplementary payment for non-compliance with volume guarantee contracts to enhance risk awareness. Monthly cargo handling volume recommendations need to align with historical patterns. First, the remaining time period is extracted from the historical cargo handling data in step 5, such as the proportion of November and December in the same period. For instance, if the cargo handling volume in November and December has consistently accounted for 1:2 of the total volume in that period over the past three years, this proportion is determined as the allocation benchmark. Then, combined with the remaining difference from step 3 and the external variables from step 5, such as fluctuations in port operation efficiency, the remaining target total cargo volume is calculated. For example, if the basic remaining volume is 400 tons, an additional 20 tons buffer may be needed due to potential declines in operation efficiency, resulting in a total target of 420 tons. Finally, the monthly target is allocated according to historical proportions, such as 140 tons in November and 280 tons in December, avoiding unrealistic deviations caused by average allocation. At the end of each month, the deviation rate between the actual cargo handling volume and the monthly target is compared, and the proportion of the remaining months and the total target are updated to ensure dynamic adaptation of the recommendations.

[0060] Specifically, the decision-making strategy is tailored to the specific content delivered by both parties to the contract. Taking a tiered contract as an example, in high-probability compliance scenarios, shippers are advised to maintain historical schedules and ports to reserve corresponding equipment. In medium-probability scenarios, shippers are advised to prioritize ensuring previous shipment volumes and ports to extend operating hours. In low-probability scenarios, shippers are offered options such as "increasing capacity" or "negotiating adjustments to contract volumes," and ports are provided with support for equipment maintenance and contract modification processes. Furthermore, information can be visualized through compliance probability trend charts, monthly target comparison charts, and priority decision lists, helping both parties intuitively grasp key information and improving the efficiency of decision implementation.

[0061] Therefore, this invention achieves a mapping from "predicted cargo volume" to "estimated settlement amount and difference risk," enabling the prediction model results to be closely integrated with contract rule modeling. This allows for clear cost assessments and risk warnings before the contract is fully executed. When the probability of achieving the target falls below a preset threshold, the system automatically triggers a performance warning and outputs execution suggestions, such as "a minimum cargo volume of X tons needs to be completed each month" or "the transportation plan should be optimized to ensure entry into the next tier of discounts."

[0062] Secondly, please refer to the attached document. Figure 2 The aforementioned bulk cargo contract performance prediction system includes: The data acquisition module collects real-time cargo handling data during the arrival and unloading process of bulk cargo, and generates a cumulative cargo quantity for the contract period. The forecasting module constructs a forecasting model based on historical transport volume, cargo handling data, shipping fluctuations, and expected arrival data. The forecasting model predicts the final cargo volume within the contract period, thus obtaining the predicted cumulative cargo handling volume. The contract modeling module establishes different contract models based on different contract types and contract modeling rules. The contract types include volume guarantee contracts and tiered contracts. The cost calculation module calculates the settlement amount of the contract based on the predicted cumulative cargo volume and contract modeling rules. The risk warning module uses the Monte Carlo method to calculate the contract fulfillment probability based on the predicted cumulative cargo volume and contract model; and provides a risk warning for contract performance discrepancies based on the fulfillment probability.

[0063] Thirdly, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores multiple instructions; the processor loads instructions from the memory to execute steps in any of the bulk cargo contract performance prediction methods based on tally data and prediction models provided in embodiments of this application.

[0064] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in embodiments of this application.

[0065] Fifthly, embodiments of this application also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in embodiments of this application.

[0066] In this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0067] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in embodiments of this application.

[0068] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0069] According to one aspect of this application, a computer program product or computer program is provided, comprising a computer program / instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer program / instructions from the computer-readable storage medium and executes the computer program / instructions, causing the electronic device to perform the method provided in various optional implementations of the bulk cargo contract performance prediction method based on tallying data and a prediction model provided in the above embodiments.

[0070] Since the instructions stored in the storage medium can execute the steps in any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in the embodiments of this application, the beneficial effects that any of the bulk cargo contract performance prediction methods based on tallying data and prediction models provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0071] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model, characterized in that, The method includes the following steps: real-time collection of cargo handling data during the arrival and unloading of bulk cargo at the port, and accumulation of cargo quantity within the contract period; Based on historical transport volume, cargo handling data, shipping fluctuations and expected arrival data, a prediction model is constructed. The final cargo volume during the contract period is predicted based on the prediction model, and the predicted cumulative cargo handling volume is obtained. Different contract models are established based on different agreement contract types and contract modeling rules. The agreement contract types include volume guarantee contracts and tiered contracts. The settlement amount of the contract is calculated based on the predicted cumulative cargo volume and contract modeling rules. The Monte Carlo method is used to calculate the contract fulfillment probability based on the predicted cumulative cargo volume and contract model; and the contract performance difference risk warning is given based on the fulfillment probability.

2. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 1, characterized in that, Based on the prediction model, the final cargo volume during the contract period is predicted, and the predicted cumulative cargo volume is obtained as follows: Let the cumulative amount of goods handled at the current moment be... The remaining contract period is The prediction increment of the prediction model for the k-th time period in the future is Then the projected cumulative cargo handling volume at the end of the contract period for: .

3. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 2, characterized in that, The modeling rules for volume guarantee contracts include: Using the contract target volume as an indicator, the settlement unit price is determined by comparing the predicted cumulative cargo handling volume at the end of the contract period with the contract target volume; and the final settlement is based on whether the predicted cumulative cargo handling volume at the end of the contract period reaches the indicator, to determine whether to apply the preferential rate or the standard rate.

4. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 3, characterized in that, For volume guarantee contracts, a mechanism combining advance settlement and end-of-period adjustment is adopted for monetary settlement, as detailed below: When the predicted cumulative inventory volume is greater than or equal to the contract target volume, it is determined that the target has been met, and the final total amount payable is directly obtained by multiplying the predicted cumulative inventory volume by the preferential rate. When the predicted cumulative cargo handling volume is less than the contract target volume, it is determined as a failure to meet the target, and the final total amount payable is obtained by multiplying the predicted cumulative cargo handling volume by the standard rate.

5. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 2, characterized in that, The modeling rules for tiered contracts are as follows: The contract forecast cumulative cargo handling volume range is divided into multiple continuous and non-overlapping quantity intervals. Each interval is configured with a corresponding lower limit, upper limit, and specific segmented fee rate. Based on the different quantity intervals in which the cumulative cargo handling volume is located throughout the entire contract period, the settlement amount of the completed segment and the remaining difference of the uncompleted segment are calculated.

6. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 5, characterized in that, For tiered contracts, a real-time segmented pricing mechanism is used for settlement, as detailed below: When the predicted cumulative cargo handling volume crosses the upper limit of a preset interval and enters the next interval, the currently applicable rate is switched to the segmented rate of the next interval, and the amounts of each completed quantity interval are accumulated. The settlement amount of each interval is the product of the actual quantity passed in that interval and its corresponding segmented rate.

7. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 6, characterized in that, For tiered contracts, a mechanism is adopted for settlement based on the execution price first, followed by unified retrospective settlement at the end of the period, as detailed below: Based on the predicted cumulative inventory volume, first determine which complete quantity ranges it crosses, and calculate the payable amount in each range. Sum the payable amounts to obtain the theoretical final payable amount. Then calculate the difference between the final payable amount and the total amount temporarily settled at the agreed execution price during the entire execution period, and generate an adjustment amount.

8. The method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model according to claim 7, characterized in that, The Monte Carlo method is used to predict the probability of contract fulfillment based on the predicted cumulative cargo volume and the contract model, as follows: In the forecasting phase, M future forecast paths are generated through Monte Carlo simulation, resulting in a set of cumulative forecast values ​​at the end of the period. ; For tiered contracts, let the target threshold be L. The probability of achieving the target threshold L can be approximately calculated using the following formula. : For volume-guaranteed contracts, let the volume-guaranteed index be... The probability of contract compliance is calculated using the following formula. : Where m is the number of samples. ， Let L be the cumulative cargo handling volume at the end of the period under the Mth prediction path, and L be the contract target threshold. This is the lower bound of the next interval for the ladder contract. This is an indicator function used to determine whether the condition is met. If the condition is met, the value is 1; otherwise, the value is 0.

9. A method for predicting the performance of bulk cargo contracts based on tallying data and a prediction model, as described in claim 8, is characterized in that... Based on the probability of meeting the target, a risk warning for contract performance discrepancies is issued, specifically including: For tiered contracts, the probability of meeting the requirements is divided into "high probability," ">80%", "Medium probability, 50% <" "<80%)", "Low probability", <50%; For volume guarantee contracts, the probability of meeting the target is categorized as "worry-free target meeting". ">90%", "Needs attention, 60% <" "<90%", "High risk" <60%; When the probability of meeting the target falls below a preset threshold, a performance warning is automatically triggered, and execution suggestions are output.

10. A bulk cargo contract performance prediction system, characterized in that, The system includes: The data acquisition module collects real-time cargo handling data during the arrival and unloading process of bulk cargo, and generates a cumulative cargo quantity for the contract period. The forecasting module constructs a forecasting model based on historical transport volume, cargo handling data, shipping fluctuations, and expected arrival data. The forecasting model predicts the final cargo volume within the contract period, thus obtaining the predicted cumulative cargo handling volume. The contract modeling module establishes different contract models based on different contract types and contract modeling rules. The contract types include volume guarantee contracts and tiered contracts. The cost calculation module calculates the settlement amount of the contract based on the predicted cumulative cargo volume and contract modeling rules. The risk warning module uses the Monte Carlo method to calculate the contract fulfillment probability based on the predicted cumulative cargo volume and contract model; and provides a risk warning for contract performance discrepancies based on the fulfillment probability.

Images