A method, system, medium and product for processing tally data in a smart port

Abstract

A method, system, medium, and product for processing tally data for a smart port, relating to the field of electronic digital data processing, include: obtaining ship loading and unloading plans, tally operation records, and cost accounting data according to a preset cycle to generate standard tally data; extracting feature data within a lead time window from the standard tally data; inputting the feature data into a prediction calculation model to generate multiple prediction scenarios for changes in loading and unloading plans based on historical operation patterns; performing parallel calculations on multiple sets of prediction scenarios to obtain scenario prediction data; comparing real-time tally data collected at the port site with the scenario prediction data to calculate the data fit; selecting the most matching prediction scenario as the current execution scenario based on the data fit, and storing other prediction scenarios in a backup scenario library; and generating tally operation instructions and cost settlement data based on the current execution scenario. Implementing this application can improve the efficiency of multi-link data processing in ports.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing, and in particular to a method, system, medium and product for processing tally data of a smart port. Background Art

[0002] With the rapid development of port logistics and the continued growth in container and bulk cargo volumes, tallying operations are playing an increasingly important role in port operations. Tallying operations involve multiple processes, including cargo delivery, inspection, counting, and recording, requiring the accurate recording and management of a large amount of operational information. Furthermore, tallying operations require data exchange with multiple systems, including terminal operating systems and financial systems, and the provision of corresponding business services to customers.

[0003] In related technologies, port tally management systems utilize information technology for operational management. The system receives ship arrival information and loading and unloading plans via an electronic data interchange interface, and tally clerks use handheld terminals to collect on-site operational data. The scheduling system automatically generates operational plans and personnel schedules based on pre-set rules. Regarding document management, the system supports the generation of electronic documents in standard formats and exchanges data with relevant parties via EDI (Electronic Data Interchange). The expense management module automatically calculates operational expenses based on contractually agreed rates, generates electronic invoices, and facilitates payment through the bank-enterprise direct connection system.

[0004] However, the relevant technology adopts a linear data processing mode, and the data updates of each link need to be processed and verified in a fixed order. When the loading and unloading plan changes, the data updates of subsequent tallying operations, cost accounting and other links are slow, which will affect the timeliness of on-site scheduling decisions. Summary of the Invention

[0005] This application provides a method, system, medium and product for processing tally data in a smart port, which are used to improve the efficiency of multi-link data processing in the port.

[0006] In the first aspect, the present application provides a tally data processing method for a smart port, which is applied to a tally management system. The method includes: obtaining ship loading and unloading plans, tallying operation records and cost accounting data from the terminal operating system and the financial system according to a preset cycle, and generating standard tallying data containing cargo attributes, operation volume attributes and time attributes based on a preset mapping relationship; extracting time series attributes, cargo loading and unloading attributes and personnel configuration attributes within the lead time window from the standard tallying data to generate feature data representing the state of the tallying operation; inputting the feature data into a prediction calculation model to generate multiple sets of prediction scenarios for changes in unloading plans based on historical operation patterns; each set of prediction scenarios includes an operation scheduling sequence and a cost change sequence; performing parallel calculations on multiple sets of prediction scenarios to obtain scenario prediction data including tallying operation timing and cost accounting values; comparing the real-time tallying data collected at the port site with the scenario prediction data to calculate the data consistency of each prediction scenario; selecting the most matching prediction scenario as the current execution scenario based on the data consistency, and storing other prediction scenarios in a backup scenario library; generating tallying operation instructions and cost settlement data according to the current execution scenario.

[0007] In the above embodiment, the tally management system acquires tally data according to a preset cycle and performs standardized processing, extracts feature data and inputs it into a prediction model to generate multiple sets of prediction scenarios, calculates the prediction scenarios in parallel to obtain prediction data, compares it with real-time data, and selects the most matching scenario for execution; thus, the efficiency of port tally data processing is improved, and multi-scenario prediction enables the system to quickly respond to plan changes, adjust operation instructions and fee settlement in a timely manner, and ensure that port operations are carried out efficiently and orderly.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after comparing the real-time tally data collected at the port site with the scenario prediction data and calculating the data consistency of each prediction scenario, the method also includes: triggering a scenario reconstruction instruction when all data consistency is less than a preset consistency threshold; in response to the scenario reconstruction instruction, transmitting the real-time tally data back to the prediction calculation model to regenerate a new prediction scenario for the change in loading and unloading plan.

[0009] In the above embodiment, the tallying management system triggers scenario reconstruction when the data consistency is lower than the threshold, and transmits real-time data back to the prediction model to regenerate the scenario. The prediction model can be adjusted in time according to the actual operation situation to avoid serious deviation between the prediction scenario and the actual situation, thereby ensuring the accuracy and timeliness of the tallying operation scheduling decision and improving the system's ability to handle abnormal situations.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of triggering the scene reconstruction instruction when the degree of consistency of all data is less than a preset consistency threshold, the method also includes: in response to the scene reconstruction instruction, obtaining historical scene data with the same operation process and cargo category from the backup scene library; based on the operation time nodes in the historical scene data, calibrating and compensating the operation time nodes in the real-time tallying data to generate scene deviation data containing the operation volume difference and the cost difference; based on the scene deviation data, optimizing the prediction calculation model.

[0011] In the above embodiment, the tally management system obtains historical similar scenario data to calibrate and compensate the real-time data, and generates deviation data for optimizing the prediction model, so that the scenario prediction is more in line with the actual operation characteristics.

[0012] In combination with some embodiments of the first aspect, in some embodiments, before the step of extracting time series attributes, cargo loading and unloading attributes, and personnel configuration attributes within a lead time window from standard tallying data to generate characteristic data representing the status of the tallying operation, the method further includes: receiving a change application for a ship loading and unloading plan; the change application includes cargo quantity adjustment information and operation time adjustment information; based on real-time personnel configuration and the change application, determining the number of tallying personnel and the number of operating tools in the changed operation plan; and generating a personnel grouping plan and a tool configuration plan based on the number of tallying personnel and the number of operating tools.

[0013] In the above embodiment, the tally management system dynamically adjusts the personnel and tool configuration plan according to the change application, which can quickly respond to the plan change requirements, reasonably allocate operating resources, avoid waste of manpower and material resources, and improve the efficiency of port resource utilization.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after selecting the most matching prediction scenario as the current execution scenario based on data consistency and storing other prediction scenarios in the backup scenario library, the method also includes: based on a preset scenario display template, converting the job scheduling sequence in the current execution scenario into a task flow chart; the task flow chart includes job link nodes and data flow between job link nodes; extracting the tally personnel grouping information and job tool configuration information corresponding to each job link node, and generating a link execution card containing the start and end time of the job, the job volume and the cost accounting value; real-time monitoring of the job volume changes in the link execution card, and when it is detected that the job volume changes exceed the preset fluctuation range, triggering a job warning signal, and retrieving alternative execution scenarios from the backup scenario library.

[0015] In the above embodiment, the tally management system will perform scene visualization, monitor changes in workload in real time, and issue intelligent warnings, making it easier for managers to understand the progress of operations, detect abnormal situations in a timely manner, and take countermeasures, thereby improving the controllability and safety of port operations.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating tallying operation instructions and fee settlement data according to the current execution scenario, the method also includes: determining the operation completion degree of the current execution scenario based on preset settlement conditions, and when the operation completion degree reaches a preset progress threshold, marking the current execution scenario as the final settlement scenario; extracting the cargo category, operation volume and operation duration information from the final settlement scenario, calculating according to the preset rate rules, and generating a target bill containing cost items, billing rules and preferential policies; electronically signing and encrypting the target bill, and pushing it to the business terminal through the preset data interface.

[0017] In the above embodiment, the tally management system automatically executes the fee settlement and bill generation process, which improves settlement efficiency and accuracy. At the same time, electronic signature encryption ensures the security of settlement data and provides customers with a better service experience.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of electronically signing and encrypting the target bill and pushing it to the business terminal through a preset data interface, the method also includes: receiving bill confirmation information returned by the business terminal, extracting the receivables and payables in the bill confirmation information, and generating an electronic statement containing payment details and payment time limits; signing and confirming the electronic statement based on the electronic signature rules, and generating an electronic contract containing workload terms and settlement terms according to the preset contract template; storing the electronic statement and electronic contract in the blockchain system to generate bill transaction records and invoices to be confirmed.

[0019] In the above embodiment, the tally management system implements blockchain-based electronic reconciliation and contract management, ensuring the immutability and traceability of transaction records, improving the standardization and transparency of port operations, and effectively preventing commercial risks.

[0020] In a second aspect, an embodiment of the present application provides a tally management system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code comprising computer instructions, the one or more processors calling the computer instructions to cause the tally management system to execute the method as described in the first aspect and any possible implementation manner of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a tally management system, the tally management system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a tally management system, the tally management system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It is understandable that the tally management system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects that can be achieved can be referenced to the beneficial effects of the corresponding methods and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. Due to the adoption of a parallel data processing method based on multi-scenario prediction, including technical features such as periodic acquisition of standardized tally data, extraction of feature data, generation of multiple sets of forecast scenarios for parallel calculation, real-time data comparison and scenario selection, the system can process multiple forecast scenarios simultaneously, quickly respond to plan changes, and adjust operation instructions in a timely manner. This effectively solves the problems of slow data updates and delayed scheduling decisions caused by the linear processing mode used in existing technologies, thereby achieving efficient processing of port tally data and significantly improving operational efficiency and resource utilization.

[0026] 2. Due to the adoption of a dynamic scene reconstruction mechanism, including technical features such as matching threshold judgment, scene reconstruction triggering, real-time data feedback and new scene generation, the system has adaptive capabilities and can adjust the prediction model in time according to actual operating conditions, effectively solving the problem of fixed prediction scenes and difficulty in dealing with abnormal situations in existing technologies, thereby realizing dynamic optimization of the prediction model and improving the accuracy of scene prediction.

[0027] 3. Due to the adoption of an intelligent fee settlement mechanism, including technical features such as job completion judgment, application of fee calculation rules, electronic signature encryption and data interface push, the system can automatically complete the entire process from job confirmation to bill generation, effectively solving the problems of low efficiency and error-prone manual settlement in existing technologies, thereby realizing the automation and standardization of tally fee settlement, improving settlement efficiency and accuracy, and at the same time ensuring data security through electronic signatures and optimizing customer service experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of a method for processing tally data in a smart port according to an embodiment of the present application;

[0029] Figure 2 This is another flowchart of the method for processing tally data in a smart port according to an embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of the structure of a physical device of the tally management system in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "above", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations of one or more of the listed items.

[0032] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0033] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0034] A large port container terminal handles hundreds of container loading and unloading operations daily. Traditional tallying operations rely heavily on manual planning and adjustments. Changes in ship schedules or cargo quantities require tallying managers to replan operations. For example, a vessel scheduled to carry 500 TEUs suddenly requires 100 more containers, with the loading requirement completed two hours early. In this situation, managers must reassess manpower allocation, adjust work sequences, and recalculate costs. This entire process is time-consuming and prone to oversights, impacting operational efficiency and customer satisfaction.

[0035] In related technologies, tally operation management and fee settlement can be achieved by using fixed-rule operation plan generation methods and simple manual accounting methods. The following describes a scenario using the related art smart port tally data processing method.

[0036] A port used a simple automated system for tallying management, generating work plans based on pre-set, fixed rules. When a cargo ship carrying 300 refrigerated containers was delayed due to weather, and some containers needed to be temporarily relocated, the system could only regenerate the plan based on the pre-set rules, unable to dynamically adjust work priorities and resource allocation based on actual conditions. Furthermore, the system's recalculation of expenses was rather mechanical, making it impossible to flexibly apply various preferential policies. This led to an increase in customer complaints and impacted the port's market competitiveness.

[0037] The smart port tally data processing method in the embodiments of this application, by establishing a predictive calculation model and a scenario parallel processing mechanism, achieves intelligent generation and rapid adjustment of operation plans, which not only improves the efficiency and accuracy of plan formulation, but also effectively responds to various sudden changes. The following describes scenarios using the smart port tally data processing method in this application.

[0038] A port tally management system using this solution, when handling a mixed cargo ship carrying 400 standard containers and 100 hazardous goods containers, received a request from the shipowner to temporarily add 50 standard containers. The system quickly retrieved similar scenarios from its historical scenario library and automatically generated multiple forecast scenarios. By comparing the feasibility of each scenario through parallel calculation, the system selected the optimal solution: adjusting the loading order of the hazardous goods containers, optimizing personnel grouping, and rationalizing equipment usage. The system also automatically calculated cost changes and generated a new settlement plan. The entire process took only minutes, significantly improving operational efficiency and customer satisfaction.

[0039] It can be seen that the tallying data processing method of the smart port in the embodiment of the present application can not only realize the intelligent management of tallying operations, but also effectively solve the problems of slow plan adjustment, unreasonable resource allocation, inaccurate cost accounting in traditional solutions, thereby realizing efficient management and accurate settlement of tallying operations.

[0040] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the tally data processing method of the smart port in an embodiment of the present application.

[0041] S101. Obtain ship loading and unloading plans, tallying operation records, and cost accounting data from the terminal operating system and financial system according to a preset cycle, and generate standard tallying data containing cargo attributes, operation volume attributes, and time attributes based on a preset mapping relationship.

[0042] Among them, the preset cycle refers to the time interval for the tally management system to obtain data regularly, such as every 30 minutes, every hour, etc.; the terminal operating system refers to the information system used to manage port loading and unloading operations, and the financial system refers to the system used to process financial data related to port operations; the ship loading and unloading plan refers to the timing arrangement of cargo loading and unloading after the ship berths; the tally operation record refers to the detailed record of the quantity, quality and other information during the cargo loading and unloading process; the cost accounting data is used to represent the details of various expenses related to the tally operation; the preset mapping relationship represents the corresponding rules for converting data from different sources into a standard format; cargo attributes include cargo type, weight, packaging and other characteristics; the workload attribute represents the workload indicator of the loading and unloading operation; the time attribute is used to represent the time node information of the operation.

[0043] The tally management system executes this step at the beginning of each preset cycle to acquire and integrate operational data. Specifically, the tally management system first obtains the latest ship loading and unloading plan from the terminal operating system through the system interface, including ship schedules, berths, cargo information, etc.; it also obtains operation records from the tally operation site collection system, covering cargo handover, inspection, counting, and other aspects; and obtains cost accounting data from the financial system, including operation rates, preferential policies, etc. The tally management system standardizes the acquired raw data according to pre-defined mapping rules, extracting basic cargo characteristics, operation volume indicators, and time node information, and generating standard format data for subsequent processing.

[0044] In some embodiments, data standardization can be achieved in a variety of ways: Optionally, the tally management system can adopt data cleaning, field mapping and format conversion methods, first perform outlier detection and missing value processing on the original data, then uniformly map the field names of different systems to standard fields, and finally uniformly convert the data format to a standard format such as JSON or XML; Optionally, the tally management system can also adopt semantic analysis methods, by establishing an ontology model to identify the conceptual relationships in different data sources, extract key information and integrate it into standard data according to predefined semantic rules. It is understandable that other data standardization methods can also be used, which are not limited here. In addition, the preset mapping relationship can be dynamically adjusted and optimized according to actual business needs.

[0045] In practice, data formats and update cycles may differ across systems, leading to data asynchrony. To address this, the tally management system employs a data version control mechanism, assigning a timestamp and version number to each piece of data. During data integration, the latest version is prioritized, and out-of-sync historical data is supplemented and updated. Data consistency checks are also implemented to ensure the integrity and accuracy of data across systems. Any data inconsistencies are detected, triggering an alarm and initiating data synchronization.

[0046] S102: extracting time series attributes, cargo loading and unloading attributes, and personnel configuration attributes within a lead time window from standard tallying data to generate feature data representing a tallying operation status.

[0047] Among them, the leading time window represents the time range for analyzing historical data, such as the previous 4 hours, the previous 24 hours, etc.; time series attributes include time series characteristics such as operation start time, completion time, and interval duration; cargo loading and unloading attributes refer to loading and unloading operation-related characteristics such as cargo type, quantity, and operation method; personnel configuration attributes represent human resource characteristics such as the number of tallying personnel, division of labor, and working hours; feature data is used to represent the overall status and trend characteristics of tallying operations, including key indicators such as operation efficiency and resource utilization.

[0048] The tally management system performs this step after completing data standardization to extract key features reflecting the status of operations. Specifically, the tally management system first determines the scope of the lead time window and dynamically adjusts the window size based on the operation cycle and data update frequency. It then extracts operation records for each time node from the standard tally data in a time series, including operation type, duration, completion status, etc.; it also extracts characteristics such as operation methods, equipment utilization, and operation efficiency during the cargo loading and unloading process; and it also obtains the configuration of tally personnel, including information such as the number of personnel, professional division of labor, and working hours. The tally management system combines and correlates these extracted features to construct a multidimensional feature vector to represent the overall status of the current tally operation.

[0049] In some embodiments, feature extraction and state representation can be achieved through a variety of methods: Optionally, the tally management system can employ a sliding time window mechanism, setting a fixed-size time window and gradually sliding it to calculate the statistical values, changing trends, and correlations of various features within the window, thereby capturing the dynamic characteristics of the operation status. Optionally, the tally management system can also employ deep learning methods to automatically learn implicit features in the data by constructing a feature extraction network, thereby achieving a high-dimensional representation of the operation status. It is understood that other feature engineering methods can also be employed to achieve feature representation of the operation status, which is not limited here.

[0050] During feature extraction, excessive feature dimensionality can lead to increased computational complexity. To address this, the tally management system employs feature selection and dimensionality reduction techniques. First, the importance of each feature is assessed based on metrics like information gain, identifying key features that contribute significantly to the characterization of operational status. Dimensionality reduction methods such as principal component analysis (PCA) are then used to map high-dimensional features into a low-dimensional space, preserving essential information while reducing computational complexity. This feature selection and dimensionality reduction ensures accurate characterization and improves subsequent processing efficiency.

[0051] S103: Input the characteristic data into the prediction calculation model, and generate prediction scenarios of changes in the assembly and unloading plans of multiple units based on historical operation patterns.

[0052] Among them, historical operation patterns refer to typical operation rules and patterns summarized from historical data; prediction scenarios are used to represent possible changes in loading and unloading plans; changes in loading and unloading plans include adjustments to operation timing, personnel and equipment configuration, etc.; operation scheduling sequence represents the execution order of operation links; cost change sequence refers to the cost adjustments caused by changes in operation plans.

[0053] After acquiring feature data, the tally management system performs this step to predict possible plan change scenarios. Specifically, the tally management system first inputs the extracted feature data into a pre-trained prediction calculation model. This model learns operational patterns and change patterns by analyzing historical data. Then, based on the current feature state, the model predicts possible plan changes that may occur in the future, including adjustments to the operational sequence, changes in staffing, and changes in equipment usage. It also considers the influence of external factors such as weather and shipping schedules, generating multiple sets of prediction scenarios with different change characteristics. For each prediction scenario, the model also generates a corresponding operation scheduling sequence and cost change sequence to evaluate the feasibility and economic efficiency of the scenario implementation.

[0054] It should be noted that the predictive calculation model utilizes a deep learning architecture. During the model training phase, the model is based on historical tallying operation data. Inputs include operation time series characteristics (such as loading and unloading rates and operation duration), cargo characteristics (such as category, weight, and volume), resource allocation characteristics (such as number of personnel and equipment type), and environmental characteristics (such as weather conditions and changes in ship schedules). Actual operation plan changes and corresponding execution results are used as training labels. The model is optimized by minimizing the mean square error between the prediction error and the actual results, while an L2 regularization term is introduced to prevent overfitting. The model itself is constructed with a multi-layer neural network, including a time series feature extraction layer (using a bidirectional LSTM structure to capture long-term and short-term temporal dependencies), a multi-head attention layer (with eight attention heads, each focusing on feature correlations at different time scales), and a prediction output layer (mapped to the prediction space using a fully connected layer). Positional encoding is specifically incorporated into the attention layer design to maintain the integrity of temporal information. During the model's usage phase, the model inputs a feature vector of the current operation status (including the last four hours' operation records and the known plan for the next two hours). The model then outputs multiple sets of possible plan change scenarios. Each scenario includes a job scheduling sequence (predicting the specific operation schedule for the next four hours, accurate to 15-minute granularity) and a corresponding cost change sequence (predicting the adjusted values ​​for various costs). For example, if a cargo ship carrying 500 standard containers temporarily adds 100 containers, the model can predict multiple feasible operation plans based on historical data and current status, including specific implementation suggestions such as adjusting the operation sequence, optimizing staffing, and rearranging equipment use. It also predicts the potential increase in operation time and cost changes that each plan may bring.

[0055] Furthermore, the tally management system can address the impact of external factors such as weather and vessel schedules by establishing a multi-source data fusion mechanism. The system accesses weather forecast APIs to obtain weather forecast data and obtains vessel schedule change information from the vessel management system. It then aligns and integrates these external factor data with operational characteristic data. The system assigns influence weights and rule templates to external factors, dynamically adjusting operational parameters during scenario generation. For example, it can extend the estimated operating time in the event of a severe weather warning and optimize staffing when a vessel schedule is advanced.

[0056] In some embodiments, predictive scenario generation can be achieved through a variety of methods: Alternatively, the tally management system can employ a rule-based scenario generation method, enumerating all possible change combinations based on pre-set business rules and constraints, screening out valid scenarios that meet the criteria, and calculating the probability and impact of each scenario. Alternatively, the tally management system can employ deep reinforcement learning methods, building a decision model to explore different change strategies in a virtual environment and learn the optimal scenario generation strategy. It is understood that other intelligent algorithms can also be employed to automatically generate predictive scenarios, which are not limited here.

[0057] During scenario generation, there may be an excessive number of scenarios or low-quality scenarios. To address this, the tally management system employs a scenario evaluation and screening mechanism. This mechanism first defines scenario evaluation metrics, including feasibility, affordability, and stability. It then conducts a multi-dimensional evaluation and scoring of the generated scenarios, selecting high-scoring, high-quality scenarios. Furthermore, a maximum number of scenarios is set to ensure that system resource usage remains within a reasonable range. This scenario evaluation and screening ensures both the quality of the predicted scenarios and the consumption of computing resources.

[0058] S104: Perform parallel calculations on multiple sets of prediction scenarios to obtain scenario prediction data including tallying operation time series and cost accounting values.

[0059] Among them, parallel computing refers to the calculation method of processing multiple sets of prediction scenarios simultaneously; the timing of tallying operations refers to the execution time points and sequence arrangements of each operation link; the cost accounting value includes the calculation results of various expenses such as loading and unloading costs, tallying costs, and warehousing costs; scenario prediction data is used to represent the specific execution plan and expected results of each prediction scenario; the time accuracy of the prediction data refers to the time interval granularity of the prediction results, such as minutes, hours, etc.

[0060] The tally management system executes this step after generating multiple forecast scenarios to efficiently calculate the execution effects of each scenario. Specifically, the tally management system first assigns the forecast scenarios to multiple computing nodes and initiates parallel computing tasks. For each scenario, the system simulates the execution of the job scheduling sequence, calculating the start time, completion time, and duration of each link to form a complete job schedule. Simultaneously, based on changes in workload and rate policies, it calculates adjustments for various fees, including basic fees, additional fees, and discount amounts. Furthermore, the system evaluates the resource requirements and constraints of scenario execution to ensure the feasibility of the forecast results. Finally, the schedule and cost accounting results are integrated into the scenario forecast data.

[0061] In some embodiments, parallel computing can be implemented in a variety of ways: Optionally, the tally management system can employ a distributed computing framework, dividing the prediction scenario into multiple subtasks and assigning them to a computing cluster. Each node independently computes and aggregates the results, achieving a balanced distribution of the computing load. Optionally, the tally management system can also employ GPU-accelerated computing, leveraging the parallel computing capabilities of graphics processors to simultaneously process multiple scenarios, significantly improving computing efficiency. It is understood that other high-performance computing methods can also be employed to improve scenario computing efficiency, which are not limited here.

[0062] During parallel computing, there may be problems with computing node failure or load imbalance. To address this, the tally management system uses task scheduling and fault-tolerance mechanisms. First, it dynamically load balances computing tasks, adjusting task allocation based on node performance and load. When a node failure is detected, the system automatically migrates the task to a backup node for continued computing. A checkpoint mechanism is also established for computing results, regularly saving intermediate computing states to facilitate fault recovery. Furthermore, the system monitors computing progress, prioritizing or splitting slower-performing tasks to ensure timely computation in all scenarios.

[0063] S105: Compare the real-time tally data collected at the port site with the scenario prediction data, and calculate the data consistency of each prediction scenario.

[0064] Among them, real-time tallying data refers to real-time operational information collected from on-site equipment and personnel at the port; data consistency indicates the degree of match between the predicted scenario and the actual situation; data comparison dimensions include operation progress, resource utilization, cost calculation and other aspects; error tolerance indicates the acceptable range of prediction deviation; weight coefficient is used to indicate the importance of different comparison dimensions; and calculation cycle indicates the time interval for data comparison.

[0065] The tally management system performs this step after completing the scenario prediction data calculation to evaluate the accuracy of the prediction results. Specifically, the tally management system first collects real-time tally data from the port site, including operation progress, personnel and equipment status, cargo information, etc.; then compares the real-time data with the data of each prediction scenario in multiple dimensions, including deviations in operation timing, differences in resource allocation, and errors in cost calculation; the system sets a weight coefficient for each comparison dimension to reflect its importance in the overall evaluation; a comprehensive fit index is obtained through weighted calculation to measure the degree of match between the prediction scenario and the actual situation; and the system also records the key differences in the comparison process to provide a basis for subsequent scenario optimization.

[0066] In some embodiments, data comparison and fit calculation can be achieved through a variety of methods: Optionally, the tally management system can use a distance-based similarity calculation method to convert real-time data and predicted data into feature vectors, calculate the Euclidean distance or cosine similarity between the vectors, and obtain a numerical fit degree. Optionally, the tally management system can also use a fuzzy logic evaluation method to comprehensively evaluate the matching of multiple dimensions by setting a set of fuzzy rules, thereby obtaining a more realistic fit judgment. It is understood that other data matching measurement methods can also be used to achieve prediction effect evaluation, which is not limited here.

[0067] During the data comparison process, real-time data may be delayed or have unstable data quality. To address this, the tally management system employs data preprocessing and exception handling mechanisms. First, real-time data is time-aligned and cleaned to eliminate the effects of acquisition delays and noise interference. When data anomalies are detected, the system initiates a data repair process, addressing outliers through methods such as interpolation or nearest neighbor data replacement. Simultaneously, the system dynamically adjusts the error tolerance to ensure assessment accuracy while adapting to the fluctuating nature of real-time data. For persistently anomalous data sources, the system issues an alert and temporarily reduces their weight in the comprehensive assessment to ensure the reliability of the fit calculation.

[0068] S106: Based on the data consistency, the most matching prediction scenario is selected as the current execution scenario, and the other prediction scenarios are stored in the backup scenario library.

[0069] Among them, the most matching prediction scenario represents the scenario plan with the highest data consistency; the current execution scenario refers to the job plan selected for actual execution; the backup scenario library is used to store other prediction scenarios with reference value; the scenario screening threshold represents the minimum consistency requirement for scenario selection; the scenario priority refers to the execution importance ranking of different scenarios; the scenario storage structure includes information such as scenario characteristics, execution conditions and association relationships.

[0070] The tally management system performs this step after obtaining the data consistency of each forecast scenario to determine the optimal execution plan. Specifically, the tally management system first sorts all forecast scenarios in descending order of consistency and selects the scenario with the highest consistency that exceeds the screening threshold as the current execution scenario. At the same time, it evaluates the reference value of other scenarios, including the similarity of the scenario characteristics and the convertibility of the execution conditions. For scenarios with reference value, the system stores their complete information in the backup scenario library, including scenario characteristics, execution conditions, and related scenarios. The system also establishes an associated index between scenarios to facilitate the rapid identification of alternative solutions when the execution scenario changes. The backup scenario library is regularly maintained to clean up expired or low-value scenario data.

[0071] In some embodiments, scenario selection and storage management can be implemented in a variety of ways: Optionally, the tally management system can employ a multi-objective optimization approach, simultaneously considering multiple objectives such as degree of fit, execution cost, and resource usage, selecting the optimal execution scenario through Pareto optimality, with other non-dominated solutions serving as backup scenarios. Optionally, the tally management system can also employ a knowledge graph approach, constructing scenario information into a semantic network and storing the hierarchical relationships and transformation rules between scenarios through a graph structure, enabling intelligent scenario management and rapid retrieval. It is understood that other decision optimization methods can also be employed to implement scenario selection and management, and these are not limited here.

[0072] During the scene management process, the backup scene library may experience capacity expansion or inefficient scene retrieval. To address this issue, the tally management system uses a scene compression and index optimization mechanism. It first extracts features and performs dimensionality reduction on scene data to reduce storage space usage. It then establishes a multi-level index structure, including time indexes, feature indexes, and association indexes, to improve scene retrieval efficiency. The system also regularly evaluates scene usage frequency and conversion success rates, archiving or cleaning low-value scenes. Furthermore, the system caches frequently used scenes to increase access speed to hotspot scenes. These optimization measures ensure the availability of backup scenes while improving the efficiency of scene management.

[0073] S107: Generate tallying operation instructions and fee settlement data according to the current execution scenario.

[0074] Among them, tallying operation instructions represent specific operation task arrangements and execution requirements; cost settlement data include operation cost calculation results and settlement basis; operation task elements include operation objects, operation content, execution personnel, equipment and tools and other information; cost calculation rules include basic rates, preferential policies, additional fees and other pricing elements; data push interface is used to transmit instructions and settlement information to relevant systems; data version identifier indicates the timeliness of instructions and settlement data.

[0075] The tally management system executes this step after determining the current execution scenario to generate practical operational instructions. Specifically, the tally management system first analyzes the job scheduling sequence in the current execution scenario and extracts the specific task elements of each link, including information such as operation time, location, personnel, and equipment. It then converts the task elements into standard operation instructions, clarifying the work content and quality requirements of each execution personnel. At the same time, it calculates various expenses based on the operation volume and rate policy, and generates cost data with cost details, calculation basis, and settlement rules. The system pushes the operation instructions to the on-site execution terminal through a preset data interface and pushes the cost data to the financial system. All pushed data is accompanied by version identification to ensure the timeliness and consistency of the data.

[0076] In some embodiments, instruction generation and fee calculation can be implemented in a variety of ways: Alternatively, the tally management system can employ a templated instruction generation method, presetting standard instruction templates for different types of operations, automatically populating the template content based on specific task elements, and generating standardized operation instructions. Alternatively, the tally management system can employ an intelligent decision tree approach, constructing multi-level decision rules to automatically derive the optimal instruction combination and fee calculation scheme based on operation conditions and constraints. It is understood that other intelligent processing methods can also be employed to achieve the automatic generation of instructions and fee data, which are not limited here.

[0077] During the execution of instructions, conflicts or cost calculation errors may occur. To address this issue, the tally management system adopts an instruction verification and cost audit mechanism. First, it performs conflict detection on the generated work instructions to ensure that there are no conflicts in the time and resource arrangements between different instructions. When a potential conflict is detected, the system automatically adjusts the instruction sequence or provides alternative solutions. At the same time, multiple verifications are performed on the cost calculation results, including rate applicability checks, preferential policy verification, and total amount rationality judgment. If anomalies are found, the system will trigger a manual review process and retain detailed records of the calculation process to facilitate problem tracing and resolution. These safeguards ensure the executable nature of work instructions and the accuracy of cost settlement.

[0078] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , which is another flow chart of the tally data processing method of the smart port in the embodiment of the present application.

[0079] S201. Obtain ship loading and unloading plans, tallying operation records, and cost accounting data from the terminal operating system and financial system according to a preset cycle, and generate standard tallying data containing cargo attributes, operation volume attributes, and time attributes based on a preset mapping relationship.

[0080] Referring to step S101 , the tally management system will acquire and standardize data.

[0081] S202: extracting time series attributes, cargo loading and unloading attributes, and personnel configuration attributes within a lead time window from standard tallying data to generate feature data representing the tallying operation status.

[0082] Referring to step S102 , the tally management system performs data feature extraction.

[0083] In some embodiments, the tally management system will enable an intelligent resource scheduling mechanism, that is, the tally management system will receive a change application for the ship loading and unloading plan; the change application includes cargo quantity adjustment information and operation time adjustment information; based on real-time personnel configuration and change application, the number of tally personnel and the number of operating tools in the changed operation plan are determined; based on the number of tally personnel and the number of operating tools, a personnel grouping plan and a tool configuration plan are generated.

[0084] Among them, the change application represents a request to modify the original loading and unloading plan; the cargo quantity adjustment information refers to the cargo quantity that needs to be changed; the operation time adjustment information represents the operation time arrangement after the plan is changed; the real-time personnel configuration is used to represent the current available tally personnel status; the number of tally personnel refers to the number of manpower required to perform the changed operation; the number of operating tools represents the required equipment and tool configuration; the personnel grouping plan is used to represent the work allocation plan of the tally personnel; and the tool configuration plan refers to the use arrangement of the operating tools.

[0085] The tally management system executes this step upon receiving a request for a change in the ship's loading and unloading plan to adjust the allocation of operational resources. Specifically, the tally management system first parses the change request to obtain the increase or decrease in cargo quantity and the adjustment range for operating time. It then queries the current tally staff's on-the-job status, professional qualifications, and workload, and calculates the required number of tally staff based on the changed workload. It also evaluates the availability and efficiency of operational tools to determine the number of tools required for the changed operation. Based on personnel and tool requirements, the tally management system comprehensively considers factors such as personnel expertise, operational experience, and working hours to generate an optimized personnel grouping plan. For operational tools, the system develops a detailed tool configuration and rotation plan based on tool performance characteristics and operational requirements.

[0086] In some embodiments, resource allocation optimization can be achieved in a variety of ways: Optionally, the tally management system can use integer programming methods to allocate resources, constructing factors such as personnel professional level, working hours, and tool usage efficiency as constraints, taking maximizing work efficiency as the objective function, solving the optimal resource allocation plan, and processing integer constraints through a branch and bound algorithm; Optionally, the tally management system can also use heuristic algorithms to explore the resource allocation space through simulated annealing or genetic algorithms, balancing the workload of each group of personnel while ensuring work quality, and achieving reasonable resource allocation. It is understandable that other optimization algorithms can also be used to achieve optimal resource allocation, which is not limited here.

[0087] During the resource allocation process, personnel or tools may become temporarily unavailable, preventing the execution of the plan. To address this issue, the tally management system employs a dynamic adjustment mechanism. First, a resource status monitoring mechanism is established to track personnel attendance and tool usage in real time. When resource anomalies are detected, the system initiates an emergency adjustment process, which includes calculating alternatives for available resources and adjusting job groupings and tool configurations. The system also assesses the impact of the adjustment on operational efficiency and, if necessary, ensures operational progress by extending working hours or temporarily redeploying resources. Furthermore, the system maintains a backup resource pool to provide resource support for emergencies. These measures ensure the reliability and adaptability of resource allocation plans.

[0088] S203: Input the characteristic data into the prediction calculation model, and generate prediction scenarios of changes in the assembly and unloading plans of multiple units based on historical operation patterns.

[0089] Referring to step S103 , the tally management system performs scenario prediction.

[0090] S204: Perform parallel calculations on multiple sets of prediction scenarios to obtain scenario prediction data including tallying operation time series and cost accounting values.

[0091] Referring to step S104 , the tally management system implements parallel computing of scenario simulation.

[0092] S205: Compare the real-time tally data collected at the port site with the scenario prediction data, and calculate the data consistency of each prediction scenario.

[0093] Referring to step S105 , the tally management system will perform data comparison.

[0094] S206: When the degree of consistency of all data is less than a preset consistency threshold, trigger a scene reconstruction instruction.

[0095] Among them, the preset matching threshold represents the minimum standard for judging whether the scenario is available; the scenario reconstruction instruction is used to trigger the prediction model to regenerate the scenario; the data matching evaluation period represents the time interval for checking the data matching situation; the system alarm level is used to indicate the severity of the scenario mismatch.

[0096] After calculating the degree of fit for each scenario, the tally management system executes this step to address forecast failures. Specifically, the tally management system first checks whether the data fit for all forecast scenarios is below a preset threshold, indicating that the current forecast model may no longer be applicable. If all scenarios are confirmed to be mismatched, the system generates a scenario reconstruction instruction containing information such as the current operation status and the reason for the mismatch. The system also issues an early warning signal, notifying relevant personnel to pay attention to any operational anomalies. The system also temporarily freezes the execution of the current forecast scenario, pending the generation of a new one.

[0097] In some embodiments, scenario reconstruction triggering can be achieved through various methods: Optionally, the tally management system can employ a multi-level threshold judgment mechanism, setting matching thresholds of varying severity and implementing corresponding processing strategies based on the severity level. Optionally, the tally management system can also employ trend analysis methods to monitor matching trends, predict potential scenario failures in advance, and implement preventative scenario reconstruction. It is understood that other intelligent judgment methods can also be employed to achieve timely triggering of scenario reconstruction, which are not limited here.

[0098] During the scene reconstruction process, frequent reconstruction triggering can lead to system instability. To address this issue, the tally management system employs a reconstruction control mechanism. First, it sets a minimum reconstruction interval to avoid overly frequent reconstruction operations. It also records reconstruction history, analyzes the causes of reconstruction, and conducts root cause analysis and optimization for frequently occurring issues. Furthermore, the system assesses the impact on operations before reconstruction and, when necessary, adopts a gradual reconstruction strategy to ensure smooth system operation.

[0099] In some embodiments, the tallying management system will establish a dynamic scenario indexing mechanism, that is, the tallying management system will respond to the scenario reconstruction instruction and obtain historical scenario data with the same operation process and cargo category from the backup scenario library; based on the operation time nodes in the historical scenario data, the operation time nodes in the real-time tallying data are calibrated and compensated to generate scenario deviation data containing the operation volume difference and the cost difference; based on the scenario deviation data, the prediction calculation model is optimized.

[0100] Among them, the scenario reconstruction instruction indicates the system command that needs to regenerate the prediction scenario; the backup scenario library refers to the database that stores historical prediction scenarios; the operation process indicates the sequence of execution steps of the tallying operation; the cargo category refers to the classification type of cargo; the historical scenario data indicates the operation records under similar circumstances in the past; the operation time node is used to indicate the time point of each operation link; the calibration compensation refers to the correction and adjustment of the time data; the operation volume difference indicates the deviation between the actual operation volume and the predicted value; the cost difference is used to indicate the difference between the actual cost and the predicted cost; the scenario deviation data refers to the statistical information reflecting the prediction error; the prediction calculation model indicates the algorithm model used to generate the prediction scenario.

[0101] The tally management system executes this step upon receiving a scenario reconstruction instruction to optimize the forecasting model. Specifically, the tally management system first retrieves historical scenarios from the backup scenario library that match the current operation process and cargo category, including complete information such as operation scheduling, resource allocation, and cost calculation. It then compares the time nodes in the historical scenarios with the time nodes in the real-time tally data, calculates the time deviation, and makes compensation adjustments. It also analyzes the difference between the actual and predicted values ​​of the workload and costs, generating scenario deviation data that represents the forecast error. Finally, the tally management system uses this scenario deviation data to adjust and optimize the parameters of the forecasting calculation model to improve the accuracy of subsequent forecasts.

[0102] In some embodiments, model optimization can be achieved in a variety of ways: Optionally, the tally management system can use the gradient descent method to optimize the model, first calculating the gradient of the prediction error with respect to the model parameters, and then iteratively updating the parameter values ​​along the gradient direction until the error converges to an acceptable range. During this period, the learning rate needs to be dynamically adjusted to balance the optimization efficiency and stability. Optionally, the tally management system can also use the Bayesian optimization method, by constructing a Gaussian process model to describe the parameter space, using the acquisition function to guide the parameter search direction, achieving a balance between exploration and utilization, and gradually finding the optimal parameter configuration. It is understandable that other optimization algorithms can also be used to improve the performance of the prediction model, which is not limited here.

[0103] During model optimization, over-optimization can lead to a decrease in model generalization. To address this, the tally management system employs a regularization control mechanism. First, a regularization term is introduced into the optimization objective to limit the complexity of model parameters. Cross-validation is then used to evaluate model performance, dividing the dataset into a training set and a validation set. The optimization process is monitored based on the validation set's performance. If validation set performance degrades, the system promptly adjusts the regularization strength or prematurely terminates the optimization process. Furthermore, the system saves snapshots of the model during optimization, allowing rollback to the best-performing version when necessary. These measures ensure the effectiveness and reliability of model optimization.

[0104] S207: In response to the scenario reconstruction instruction, the real-time tally data is transmitted back to the prediction calculation model to regenerate a new prediction scenario for the loading and unloading plan change.

[0105] Among them, the new prediction scenario represents the new scenario plan generated after reconstruction; the real-time tally data feedback interface is used to input the current operation data into the prediction model; the data feedback content includes information such as operation status, resource allocation, and execution effect; the prediction model reload means using new data to update the model status; the scenario generation parameters include configuration items such as prediction duration, number of scenarios, and constraints.

[0106] The tally management system executes this step after receiving a scenario reconstruction instruction to generate a new forecasting solution. Specifically, the tally management system first inputs real-time tally data into the forecasting calculation model through a feedback interface. This data includes the current operation status and recent change trends. The model then re-forecasts the scenario based on the latest data, generating a new set of scenarios that match the current situation. The system performs a preliminary assessment of the newly generated scenarios to ensure their relevance to the current operation status. The triggering conditions and processing steps of the scenario reconstruction are also saved for subsequent model optimization.

[0107] In some embodiments, new scenarios can be generated through a variety of methods: Alternatively, the tally management system can employ incremental learning methods to locally update the prediction model using newly added real-time data, allowing it to quickly adapt to operational changes. Alternatively, the tally management system can employ combinatorial optimization methods to construct hybrid scenarios that meet new conditions by recombining high-quality components of existing scenarios. It is understood that other scenario generation methods can also be employed to achieve dynamic adjustment of the prediction model, and these are not limited here.

[0108] The generation of new scenarios can be slow or have inconsistent quality. To address this, the tally management system employs a rapid response mechanism. It first rapidly generates a base scenario using cached scenario templates. Simultaneously, it initiates parallel computing tasks to optimize and improve the base scenario. The system also dynamically adjusts generation parameters to find a balance between scenario quality and generation speed. These optimization measures ensure the timeliness and effectiveness of scenario reconstruction.

[0109] S208: Based on the data consistency, the most matching prediction scenario is selected as the current execution scenario, and the other prediction scenarios are stored in the backup scenario library.

[0110] Referring to step S106 , the tally management system will perform scenario determination and backup storage.

[0111] In some embodiments, the tallying management system will adopt a visual monitoring engine, that is, the tallying management system will convert the job scheduling sequence in the current execution scenario into a task flow chart based on a preset scenario display template; the task flow chart includes the operation link nodes and the data flow between the operation link nodes; extract the tallying personnel grouping information and operation tool configuration information corresponding to each operation link node, and generate a link execution card containing the operation start and end time, operation volume and cost accounting value; monitor the operation volume changes in the link execution card in real time, and when it is detected that the operation volume changes exceed the preset fluctuation range, trigger the operation warning signal, and call the alternative execution scenario from the backup scenario library.

[0112] Among them, the scene display template represents the preset visual display format; the job scheduling sequence refers to the execution order of the tallying operation; the task flow chart is used to represent the logical relationship of the job links; the job link node represents the specific job task point; the data flow refers to the information transmission relationship between nodes; the link execution card is used to represent the execution information of the specific job task; the job start and end time represents the start and end time points of the task; the workload represents the specific workload data; the cost accounting value refers to the corresponding cost calculation result; the preset fluctuation range represents the acceptable workload change range; the job warning signal is used to indicate the prompt information of abnormal situations; the alternative execution scenario refers to the alternative plan that can be switched.

[0113] The tally management system executes this step after determining the current execution scenario, which is used to visually monitor the execution status of the job. Specifically, the tally management system first converts the job scheduling sequence into an intuitive task flow chart based on the preset display template, clearly showing the sequence and dependency relationships between each operation link; then, the system associates the corresponding execution information for each operation link node, including the grouping of responsible tally personnel and the required operation tool configuration; the system generates detailed link execution cards, which display the operation start time, expected completion time, current operation volume and cost accounting in real time; the tally management system continuously monitors the changes in the operation volume of each link. When it detects that the change range exceeds the preset range, it immediately triggers an early warning and automatically retrieves suitable alternative solutions from the backup scenario library to provide decision support for operation adjustments.

[0114] In some embodiments, visual monitoring can be achieved through a variety of methods: Optionally, the tally management system can use dynamic flowchart technology, using node coloring to indicate operation status, using line thickness to indicate data flow, combining animation effects to display operation progress, and supporting node expansion to view detailed information, achieving multi-level visual display; Optionally, the tally management system can also use a data dashboard to display key indicators such as operation volume, progress, and costs through multi-dimensional charts, using early warning threshold lines to reflect abnormal situations in real time, and supporting data drill-down analysis of specific causes. It is understandable that other visualization methods can also be used to achieve operation monitoring, which are not limited here.

[0115] During visual monitoring, data update delays can lead to untimely display. To address this, the tally management system employs a real-time push mechanism. This mechanism first establishes an efficient data channel, using technologies like WebSocket to achieve real-time data transmission. It also implements an incremental update strategy, transmitting only changed data to reduce transmission latency. The system also prioritizes displayed content to ensure that important information is updated first. When a network anomaly is detected, the system activates a local cache mechanism and automatically synchronizes updates after the network is restored, ensuring display continuity. These measures ensure the real-time and reliable nature of monitoring displays.

[0116] S209: Generate tallying operation instructions and fee settlement data according to the current execution scenario.

[0117] Referring to step S107 , the tally management system performs data prediction based on the scenario.

[0118] S210: Determine the job completion of the current execution scenario based on preset settlement conditions, and when the job completion reaches a preset progress threshold, mark the current execution scenario as a final settlement scenario.

[0119] Among them, the preset settlement conditions represent the combination of conditions that trigger fee settlement; the job completion degree refers to the completion ratio of the current job progress relative to the plan; the preset progress threshold represents the minimum completion progress for fee settlement; the final settlement scenario is used to determine the basis for fee calculation; the completion degree calculation rules include the progress calculation methods for different job types.

[0120] The tally management system continuously executes this step during the current scenario to determine the timing of fee settlement. Specifically, the tally management system first checks the current operation status based on preset settlement conditions, including cargo loading and unloading progress, document integrity, and equipment return status. It then comprehensively evaluates the overall operation progress based on completion calculation rules for different cargo categories. When the system confirms that the operation completion rate has reached the preset threshold, it locks the current execution scenario as the final settlement scenario. The system also records the time and basis for determining the settlement scenario to ensure traceability of the settlement process.

[0121] In some embodiments, completion assessment can be achieved through a variety of methods: Alternatively, the tally management system can employ a weighted calculation method, assigning weight coefficients to different operational links and calculating the overall completion degree through weighted summation. Alternatively, the tally management system can employ critical path analysis to identify key nodes in the operational process and use the completion status of these key nodes to determine the overall progress. It is understood that other progress assessment methods can also be employed to accurately calculate the completion degree of an operation, and these are not limited here.

[0122] During the completion assessment process, operations may be interrupted or progress may be regressed. To address this, the tally management system employs a status check mechanism. This first establishes a checkpoint system for operation progress, regularly recording and verifying progress status. When an abnormal change is detected, the system initiates an exception handling process, analyzes the cause, and adjusts the completion calculation. Simultaneously, the system dynamically updates the final settlement scenario until the operation is truly complete. These measures ensure the accuracy and reliability of settlement scenario determination.

[0123] S211. Extract the cargo category, operation volume, and operation duration information from the final settlement scenario, calculate according to the preset rate rules, and generate a target bill that includes cost items, billing rules, and preferential policies.

[0124] Among them, the cargo category indicates the classification identification of different types of cargo; the operation volume includes billing basis such as loading and unloading quantity, storage time, etc.; the operation time indicates the actual operation duration; the preset rate rules include pricing schemes such as basic rate and tiered rate; the cost sub-items indicate the detailed composition of various types of costs; the billing rules include calculation formulas and applicable conditions; the preferential policies include discount schemes and preferential conditions.

[0125] The tally management system executes this step after determining the final settlement scenario to generate the formal invoice. Specifically, the tally management system first extracts the basic data required for fee calculation from the settlement scenario, including cargo specifications, operation type, and operation time. It then calculates each fee according to preset rate rules, taking into account factors such as basic fees, additional fees, and discounts. The system records the calculation process of each fee in detail, including billing standards, calculation formulas, and applicable policies. Finally, all fee items are consolidated into a standardized target invoice to ensure the completeness and accuracy of the invoice content.

[0126] In some embodiments, fee calculation can be implemented in a variety of ways: Optionally, the tally management system can employ a multi-tiered pricing model, applying different billing rules based on different business scenarios and customer types to achieve flexible fee accounting. Optionally, the tally management system can also employ an intelligent pricing algorithm that dynamically adjusts fee parameters to optimize revenue by analyzing historical transaction data and market conditions. It is understood that other billing methods can also be used to achieve reasonable fee calculation, and this is not limited here.

[0127] During the bill generation process, errors in fee calculations or improper application of preferential policies may occur. To address this, the tally management system employs a multi-verification mechanism. First, the extracted basic data is verified for accuracy. Then, the calculation results for each fee item are checked for rationality, including fee range checks and historical comparative analysis. The system also verifies the logic behind preferential policies to avoid duplicate or conflicting offers. For any anomalies, the system generates an audit prompt requiring manual review and confirmation. These verification measures ensure the accuracy and compliance of target bills.

[0128] S212: The target bill is electronically signed and encrypted, and pushed to the business terminal through the preset data interface.

[0129] Among them, electronic signature encryption means digitally signing and encrypting bill data; the preset data interface includes push targets and communication protocols; business terminals include client systems, financial systems, management terminals, etc.; data encryption algorithms include symmetric encryption and asymmetric encryption schemes; signature verification mechanism is used to ensure data integrity and non-repudiation; data push status indicates the processing results of bill transmission and reception.

[0130] The tally management system performs this step after generating the target bill, ensuring secure data transmission. Specifically, the tally management system first digitally signs the target bill, calculating the signature on the bill content using a pre-set key. It then encrypts the signed bill data to ensure data security during transmission. The system pushes the encrypted bill to the relevant business terminal via a pre-set data interface, simultaneously transmitting the necessary decryption and verification information. The system monitors the push process, recording the bill delivery status and receipt confirmation to ensure reliable data transmission.

[0131] In some embodiments, secure transmission can be achieved through a variety of methods: Optionally, the tally management system can employ a hierarchical encryption strategy, applying different encryption strengths to bill information of varying importance, balancing security and efficiency. Alternatively, the tally management system can employ blockchain technology, recording the bill transmission process via a distributed ledger to ensure data immutability. It is understood that other secure transmission solutions can also be employed to achieve reliable push of bill data, and these are not intended to be limiting here.

[0132] During the data push process, network interruptions or terminal offline issues may occur. To address this, the tally management system employs a reliable transmission mechanism. First, a data push retry mechanism is established, automatically retransmitting when a transmission failure is detected. The system also maintains a push queue to cache and manage undelivered bills. Furthermore, the system offers multi-channel push options, enabling alternate channels to continue transmission if the primary channel becomes unavailable. The system regularly clears expired push records to maintain the efficient operation of the push queue. These safeguards ensure the reliable delivery and timely processing of bill data.

[0133] In some embodiments, the tally management system will build an intelligent settlement chain, that is, the tally management system will receive the bill confirmation information returned by the business terminal, extract the receivables and payables in the bill confirmation information, and generate an electronic statement containing payment details and payment time limits; sign and confirm the electronic statement based on the electronic signature rules, and generate an electronic contract containing workload terms and settlement terms according to the preset contract template; store the electronic statement and electronic contract in the blockchain system, and generate bill transaction records and invoices to be confirmed.

[0134] Among them, the bill confirmation information indicates the confirmation result of the business terminal reconciliation statement; the amount receivable and payable refers to the amount of fees that need to be collected or paid; the electronic statement is used to represent the digital reconciliation voucher; the payment details represent the detailed information of fee income and expenditure; the payment time limit refers to the time limit requirement for fee settlement; the electronic signature rules are used to represent the authentication standards of digital signatures; the preset contract template represents the standardized contract document format; the workload clause refers to the agreed content on workload in the contract; the settlement clause represents the agreed content of fee calculation and payment; the blockchain system is used to represent the distributed ledger storage system; the bill transaction record refers to the full process information of bill processing; the invoice to be confirmed represents the electronic invoice to be issued.

[0135] The tally management system executes this step after receiving the bill confirmation information to complete the fee settlement and contract signing. Specifically, the tally management system first parses the bill confirmation information returned by the business terminal and extracts the confirmed receivable and payable amounts; then it generates a standardized electronic statement, detailing the collection and payment details, settlement basis, and payment period of each fee; at the same time, according to the preset contract template, it fills the confirmed workload information and fee settlement information into the corresponding clause positions to generate a complete electronic contract document; the tally management system digitally signs the document according to the electronic signature rules to ensure the legal validity of the document; finally, the signed electronic statement and electronic contract are stored in the blockchain system, generating an unalterable transaction record and initiating the invoice issuance process.

[0136] In some embodiments, electronic document processing can be achieved through a variety of methods: Optionally, the tally management system can use a PKI system for electronic signatures, verify the identity of the signing entity through digital certificates, use an asymmetric encryption algorithm to generate the signature value, and add timestamp information when signing to ensure the validity and non-repudiation of the signature; Optionally, the tally management system can also use consortium chain technology to automatically execute reconciliation and settlement processes through smart contracts, use a consensus mechanism to ensure the consistency of transaction records, and ensure data security and traceability through distributed storage. It is understood that other cryptographic evidence storage methods can also be used to achieve secure processing of electronic documents, which are not limited here.

[0137] During electronic document processing, signature verification failures or blockchain write timeouts may occur. To address this, the tally management system employs multiple safeguards. First, a pre-verification step is added to the signature process to ensure the integrity and formatting of the signature data. If a signature anomaly is detected, the system automatically retries the signing process while preserving the original data for verification. For blockchain writes, the system employs a hierarchical storage strategy, first storing data in local secure storage and ensuring successful blockchain writes before clearing the local copy. The system also monitors the blockchain network status and automatically adjusts submission strategies in the event of congestion to ensure successful data writes. These measures ensure the reliability and integrity of electronic document processing.

[0138] In the embodiment of the present application, due to the use of intelligent prediction technology based on historical scenarios and parallel computing optimization methods, it is possible to quickly generate and evaluate multiple sets of prediction scenarios, and continuously improve the prediction accuracy through real-time data comparison and dynamic optimization mechanisms; at the same time, by introducing blockchain technology and electronic signature mechanisms, the security and reliability of fee settlement are achieved; in addition, through visual monitoring and early warning mechanisms, real-time supervision of the operation process is guaranteed, effectively solving the problems of low plan adjustment efficiency, unreasonable resource allocation, inaccurate cost accounting, and poor data security in traditional tallying operation management, thereby realizing intelligent management, precise settlement and full-process control of tallying operations, significantly improving port operation efficiency and service quality.

[0139] The following describes the tally management system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the structure of a physical device of the tally management system in an embodiment of the present application.

[0140] It should be noted that Figure 3 The structure of the tally management system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0141] like Figure 3 As shown, the tally management system includes a CPU 301, which can perform various appropriate actions and processes based on programs stored in a ROM 302 or programs loaded from a storage unit 308 into a RAM 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0142] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the removable media can be installed in the storage section 308 as needed.

[0143] In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from the removable medium 311. When the computer program is executed by the CPU 301, the various functions defined in the present invention are performed.

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0145] Specifically, the tally management system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the tally data processing method of the smart port provided by the above embodiment is implemented.

[0146] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the tally management system described in the above embodiments, or may exist independently and not be incorporated into the tally management system. The storage medium carries one or more computer programs, which, when executed by a processor of the tally management system, enable the tally management system to implement the smart port tally data processing method provided in the above embodiments.

[0147] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0148] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

Claims

1. A method for processing tally data in a smart port, characterized in that: Applied to a tally management system, the method includes: Obtain ship loading and unloading plans, tally operation records, and cost accounting data from the terminal operating system and financial system according to the preset cycle, and generate standard tally data containing cargo attributes, operation volume attributes, and time attributes based on the preset mapping relationship; Extracting time series attributes, cargo loading and unloading attributes, and personnel configuration attributes within a lead time window from the standard tallying data to generate feature data representing the tallying operation status; Inputting the characteristic data into a prediction calculation model to generate multiple prediction scenarios of changes in assembly and unloading plans based on historical operation patterns; each set of the prediction scenarios includes an operation scheduling sequence and a cost change sequence; Performing parallel calculations on multiple sets of prediction scenarios to obtain scenario prediction data including tallying operation timing and cost accounting values; Comparing the real-time tally data collected at the port site with the scenario prediction data, and calculating the degree of data consistency for each prediction scenario; Based on the data consistency, the most matching prediction scenario is selected as the current execution scenario, and the other prediction scenarios are stored in the backup scenario library; Generate tally operation instructions and fee settlement data according to the current execution scenario.

2. The method according to claim 1, characterized in that After the step of comparing the real-time tally data collected at the port site with the scenario prediction data and calculating the degree of data consistency of each prediction scenario, the method further includes: When the degree of consistency of all the data is less than a preset consistency threshold, triggering a scene reconstruction instruction; In response to the scenario reconstruction instruction, the real-time tally data is transmitted back to the prediction calculation model to regenerate a new prediction scenario for the loading and unloading plan change.

3. The method according to claim 2, characterized in that When all the data consistency is less than a preset consistency threshold, after the step of triggering a scene reconstruction instruction, the method further includes: In response to the scene reconstruction instruction, acquiring historical scene data with the same operation process and cargo category from the backup scene library; Based on the operation time nodes in the historical scenario data, the operation time nodes in the real-time tally data are calibrated and compensated to generate scenario deviation data including the operation volume difference and the cost difference; Based on the scenario deviation data, the prediction calculation model is optimized.

4. The method according to claim 1, wherein Before the step of extracting time series attributes, cargo handling attributes, and personnel configuration attributes within the lead time window from the standard tallying data to generate feature data representing the tallying operation status, the method further includes: Receive a change application for a vessel loading and unloading plan; the change application includes cargo quantity adjustment information and operation time adjustment information; Determine the number of tally personnel and operating tools required for the changed operation plan based on the real-time personnel allocation and the change application; Based on the number of tally personnel and the number of operating tools, a personnel grouping plan and a tool configuration plan are generated.

5. The method according to claim 1, wherein After the step of selecting the most matching prediction scenario as the current execution scenario based on the data consistency and storing other prediction scenarios in a backup scenario library, the method further includes: Based on a preset scenario display template, the job scheduling sequence in the current execution scenario is converted into a task flow chart; the task flow chart includes job link nodes and data flows between job link nodes; Extracting tally personnel grouping information and operation tool configuration information corresponding to each operation link node, and generating a link execution card containing the operation start and end time, operation volume and cost accounting value; The workload changes in the link execution card are monitored in real time. When it is detected that the workload changes exceed a preset fluctuation range, a job warning signal is triggered, and an alternative execution scenario is retrieved from the backup scenario library.

6. The method according to claim 1, characterized in that After the step of generating tallying operation instructions and fee settlement data according to the current execution scenario, the method further includes: Determining the job completion of the current execution scenario based on a preset settlement condition, and marking the current execution scenario as a final settlement scenario when the job completion reaches a preset progress threshold; Extracting the cargo category, operation volume, and operation duration information from the final settlement scenario, calculating according to the preset rate rules, and generating a target bill that includes cost itemization, billing rules, and preferential policies; The target bill is electronically signed and encrypted, and pushed to the business terminal through a preset data interface.

7. The method according to claim 6, characterized in that After the step of electronically signing and encrypting the target bill and pushing it to the service terminal through a preset data interface, the method further includes: Receiving the bill confirmation information returned by the business terminal, extracting the receivable and payable amounts in the bill confirmation information, and generating an electronic statement containing payment details and payment deadlines; Sign and confirm the electronic statement based on the electronic signature rules, and generate an electronic contract containing workload terms and settlement terms according to the preset contract template; The electronic statement and the electronic contract are stored in the blockchain system to generate a bill transaction record and an invoice to be confirmed.

8. A tally management system, characterized in that: The tally management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the tally management system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the tally management system, the tally management system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a tally management system, the tally management system is enabled to execute the method according to any one of claims 1 to 7.

Images