Ship operation data processing method and device, and storage medium

Abstract

This invention relates to the field of ship operation management technology, specifically providing a ship operation data processing method, device, and storage medium, comprising: calling a list based on information entry behavior through an interactive interface; saving the data generated by the information entry behavior to the list, the data including ship information and operation information; performing information standardization preprocessing on the list; calculating operation efficiency based on the preprocessed list, writing the operation efficiency into an operation report, and uploading the operation report to a management terminal. This invention directly performs information standardization preprocessing on the list, enabling on-site verification and feedback of data quality, and then uploads the standardized preprocessed operation data to the management terminal, allowing the management terminal to obtain a large amount of valid data.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of ship operation management, and particularly relates to a ship operation data processing method, device and storage medium. BACKGROUND

[0002] The existing ship operation management relies on manual recording of operation data on an Excel template. Although the Excel template limits the data range of operation recording, it cannot correct errors in time. When data analysis and statistics are performed, the error data cannot be modified any more. Therefore, there are many invalid data, which is not conducive to the analysis of operation data and the scientific management of ship operation. SUMMARY

[0003] In view of the above problems of the prior art, the present application provides a ship operation data processing method, device and storage medium to solve the above technical problems.

[0004] In a first aspect, the present application provides a ship operation data processing method, comprising: calling a list according to information input behavior of an interactive interface; saving data generated by the information input behavior to the list, the data comprising ship information and operation information; performing information normalization preprocessing on the list; calculating operation efficiency according to the preprocessed list, and writing the operation efficiency into an operation report, and uploading the operation report to a management terminal.

[0005] In an optional embodiment, the calling of the list according to the information input behavior of the interactive interface comprises: obtaining first information input behavior of a first interactive interface; obtaining first information generated by the first information input behavior, the first information comprising ship identity information and operation identity information; querying a matching list from the created list according to the first information; confirming that the matching list is queried, and calling the matching list; confirming that the matching list is not queried, creating a new list and calling the new list.

[0006] In an optional embodiment, the saving of the data generated by the information input behavior to the list, the data comprising ship information and operation information, comprises: obtaining second information input behavior of a second interactive interface, the second interactive interface being a sub-interface of the first interactive interface; extracting an array generated by the second information input behavior in the second interactive interface; updating the array to the called list.

[0007] In an optional implementation, the list undergoes information normalization preprocessing, including: Remove spaces from parameter values ​​in the list; Validate whether required fields are empty; if they are empty, mark the list as incomplete. Validate invalid data in the list and mark the invalid data. Verify the abnormal fields in the list, where the abnormal fields do not meet the threshold range of the corresponding parameter items; If an abnormal field is found in the list, a correction pop-up is generated for the abnormal field, and the abnormal field is updated according to the field entered in the correction pop-up.

[0008] In an optional implementation, calculating the job efficiency based on the preprocessed list and uploading the job efficiency to the management terminal includes: Extract the number of work boxes, number of single hooks, work time, waiting time for AGV, mechanical failure time and abnormal downtime from the work information in the list; Calculate the gross efficiency of the operation: Gross efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ (2 × Working time); Calculate the net efficiency of the operation: Net efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ [2 × (Total operation time - Waiting time for AGV - Mechanical failure time - Abnormal downtime)]; The net efficiency is compared with a preset efficiency threshold. If the net efficiency exceeds the efficiency threshold, an error reporting task is generated. Execute the error reporting task to enter the modification interaction interface. The modification interaction interface includes a correction information input box, which is an input box corresponding to the quantity of work boxes, the number of single hooks, the operation time, the waiting time for AGV, the mechanical failure time, and the abnormal downtime. Update the list with the information re-entered in the modified interactive interface, and recalculate the job efficiency based on the updated list; The net efficiency and the corresponding gross efficiency, which do not exceed the efficiency threshold, are uploaded to the management terminal.

[0009] In an optional implementation, the method further includes managing the terminal to analyze job reports, wherein the method for analyzing job reports includes: The management terminal will summarize the work reports received within the set time period and extract the gross efficiency, net efficiency, worker information, and work type information from the work reports. The information on job type and the information on the workers are converted into quantitative classification features as classification variables; Obtain multiple net efficiencies corresponding to each quantified classification feature, and calculate the average net efficiency of the multiple net efficiencies; Multiple quantitative classification features and their corresponding average net efficiency are arranged into a feature matrix; The XGBoost regression model is used to predict the highest net efficiency and the combination of quantized classification features corresponding to the highest net efficiency based on the feature matrix. The XGBoost regression model calculates the reduction in loss function caused by feature splitting in each decision tree, sums the gain values ​​of the quantized classification features in all trees, and obtains the importance score of the quantized classification features after normalization.

[0010] Where T is the total number of trees, Let the split gain of feature i in the t-th tree be , Let feature j be the split gain in the t-th tree; For the tree model of XGBoost, the TreeExplainer algorithm calculates the contribution of quantified categorical features to all possible subset combinations by recursively traversing the tree path: ‌

[0011] Where N is the feature set, S is a subset excluding feature i, and f(S) is the model output based on subset S; Calculate the weighted sum of importance score and contribution of quantitative classification features, select the multiple quantitative classification features with the highest weighted sum, and solidify the multiple quantitative classification features into the optimal job allocation combination.

[0012] In an optional implementation, before calling the behavior list based on information entered from the interactive interface, the method further includes a management terminal pre-allocating a list, the method of pre-allocating the list including: Obtain task allocation information, which includes a correspondence between one or more sets of basic information of operators and basic information of ships; One or more lists are created based on the task allocation information, and the lists store a set of basic information about the personnel and the vessels. Obtain the location information of the handheld terminal, and determine the working location of the handheld terminal based on the location information; Based on the ship's berthing position in the ship's basic information and the working position of the handheld terminal, the correspondence between the handheld terminal and the ship's basic information is determined; Based on the aforementioned correspondence, a list containing the ship's basic information will be sent to the corresponding handheld terminal.

[0013] In an optional implementation, the method further includes: The list of received data is cached on the handheld terminal; The handheld terminal retrieves a matching list from a cached list based on the partial information of the operators entered through the interactive interface. The handheld terminal imports the basic information of the ship and the basic information of the operators from the matching list into the interactive interface.

[0014] Thirdly, a device is provided, comprising: Memory, used to store ship operation data processing programs; A processor is configured to implement the steps of the ship operation data processing method as provided in the first aspect when executing the ship operation data processing program.

[0015] Fourthly, a computer-readable storage medium is provided, on which a ship operation data processing program is stored, wherein when the ship operation data processing program is executed by a processor, the ship operation data processing method as provided in the first aspect is implemented.

[0016] The beneficial effects of this invention are that the ship operation data processing method, equipment and storage medium provided by this invention improve the convenience of users entering operation data by establishing an interactive interface and call list. After the entered data is placed into the list, the list is directly preprocessed for information standardization, realizing on-site verification and feedback of data quality. Then, the standardized preprocessed operation data is uploaded to the management terminal, enabling the management terminal to obtain a large amount of effective data, thereby providing a stable data foundation for the data analysis of the management terminal.

[0017] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0020] Figure 2 This is another illustrative flowchart of a method according to an embodiment of the present invention.

[0021] Figure 3 This is a schematic diagram of the architecture of a method according to an embodiment of the present invention.

[0022] Figure 4This is a first effect diagram of the interactive interface of a method according to an embodiment of the present invention.

[0023] Figure 5 This is a second effect diagram of the interactive interface of a method according to an embodiment of the present invention.

[0024] Figure 6 This is a third effect diagram of the interactive interface of a method according to an embodiment of the present invention.

[0025] Figure 7 This is a fourth effect diagram of the interactive interface of a method according to an embodiment of the present invention.

[0026] Figure 8 This is the fifth effect diagram of the interactive interface of a method according to an embodiment of the present invention.

[0027] Figure 9 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0030] The key terms used in this invention will be explained below.

[0031] XGBoost (eXtreme Gradient Boosting) is an ensemble learning algorithm based on the gradient boosting framework. It optimizes model performance by iteratively building decision trees (CART regression trees) and accumulating prediction results. Its core mechanisms include: **Objective Function:** Consists of a loss function (e.g., mean squared error) and regularization terms (L1 / L2), controlling model complexity and preventing overfitting. **Second-Order Taylor Expansion:** When building a new tree, a second-order approximation of the loss function is performed to quickly locate the optimal split point and weight allocation. **Residual Fitting:** Each new tree focuses on correcting the prediction error of the previous tree; the final prediction is a weighted sum of the outputs of all trees.

[0032] TreeExplainer is a tool within the SHAP (SHapley Additive exPlanations) framework specifically designed for interpreting tree models. Based on Shapley value theory in cooperative game theory, it quantifies the contribution of features to single-sample predictions.

[0033] The ship operation data processing method provided in this embodiment of the invention is executed by computer equipment, and correspondingly, the ship operation data processing system runs on the computer equipment.

[0034] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 1 The implementing entity can be a ship operation data processing system. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0035] like Figure 1 As shown, the method includes: S1. Enter the action call list based on the information from the interactive interface; S2. Save the data generated by the information entry behavior to the list, the data including ship information and operation information; S3. Perform information normalization preprocessing on the list; S4. Calculate the work efficiency based on the preprocessed list, write the work efficiency into the work report, and upload the work report to the management terminal.

[0036] In one embodiment of the present invention, based on step S1, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0037] S101. Obtain the first information entry behavior of the first interactive interface.

[0038] Determine the specific characteristics of the first interactive interface. For web applications, this can be identified by the page's URL or specific HTML element identifiers (such as unique IDs or class names). For mobile applications, it can be identified by the name of the Activity (Android) or ViewController (iOS) corresponding to the interface.

[0039] After identifying the first interactive interface, it is necessary to monitor the user's information entry behavior on that interface. For text input boxes, the system should be able to detect the input action when the user enters characters. For controls such as drop-down selection boxes, radio buttons, and checkboxes, the system should be able to capture the change in their selected state when the user changes it, thereby determining that the user has entered information.

[0040] S102. Obtain the first information generated by the first information entry behavior, the first information including ship identity information and operation identity information.

[0041] Upon detecting a user's information entry activity on the primary interactive interface, the system needs to extract specific information from the corresponding input controls. For text boxes containing vessel identification information, such as vessel name or vessel number, the system reads the specific content entered by the user. For controls containing job identification information, such as the job type selected in a drop-down menu, the system obtains the specific option value selected by the user.

[0042] After obtaining this information, it needs to be validated. For example, the vessel number may require a specific format for numbers or strings, and the system will check whether the vessel number entered by the user conforms to the specified format requirements. If it does not conform, the system will prompt the user to re-enter the information in the correct format.

[0043] After successful verification, the system encapsulates and integrates vessel identity information and operation identity information. Vessel name, vessel number, and other vessel identity-related information are grouped into one category, while operation identity-related information, such as operation type, is grouped into another category, forming a unified data structure that includes both types of information for easier subsequent processing.

[0044] S103. Query the matching list from the created list based on the first information.

[0045] Based on the initial information obtained and encapsulated from user input, corresponding query conditions are constructed. For example, in a relational database, an SQL query statement is generated to filter data that meets the conditions from a stored list table based on the ship name, ship number, and operation type. In a non-relational database, query conditions are constructed according to the corresponding syntax rules to retrieve document records that meet the requirements.

[0046] In this embodiment, the matching list is retrieved directly from local storage.

[0047] S104. If the matching list is found, then the matching list is invoked.

[0048] After executing the query, determine whether a matching list was successfully retrieved. In relational databases, this can be determined by checking the number of rows returned in the query results; if the number of rows is greater than zero, it means that matching data was found. In non-relational databases, you can check the number of query results; if the number is greater than zero, it means that matching document records were found.

[0049] Once a matching list is found, it is retrieved according to specific business needs. This means the list is cached so that data entered in subsequent interactive interfaces can be written to it.

[0050] S105. If it is confirmed that no matching list is found, a new list is created and the new list is called.

[0051] When it is determined that no matching list is found (i.e., the number of rows in the query result is zero in the relational database, or the number of rows in the query result is zero in the non-relational database), the system will start the process of creating a new list.

[0052] Based on the previously obtained vessel and operational identity information, create a new record in the corresponding database.

[0053] In one embodiment of the present invention, based on step S2, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0054] S201. Obtain the second information input behavior of the second interactive interface, wherein the second interactive interface is a subordinate interface of the first interactive interface.

[0055] The second interactive interface is determined by pre-defined interface hierarchy navigation logic within the application. For example, in the main menu structure, the first interactive interface may be at a specific level. When the user performs a specific action (such as clicking a button or selecting a specific option), the program enters the second interactive interface according to internally defined navigation rules. When writing the interface code, parent-child container relationships, specific interface identifiers, or page paths are typically used to associate these two interfaces, thereby clarifying their hierarchical relationship. For various input controls on the second interactive interface, the system continuously monitors user actions. For text input boxes, the system tracks user keystrokes, deletions, and modifications in real time; for dropdown boxes, the system immediately captures the change when options switch; for radio buttons and checkboxes, the system responds quickly when the user changes their selected state, ensuring that all information input behavior of the user on this interface can be obtained in a timely manner.

[0056] S202. Extract the array generated by the second information entry behavior in the second interactive interface.

[0057] Based on the layout and functions of the input controls in the second interactive interface, user input information is collected. The contents of multiple text input boxes are retrieved sequentially, reading the user input content in each box one by one. The selected values ​​of drop-down lists, radio buttons, and checkboxes are also identified and collected by the system; if multiple such controls exist, the selected value of each control will not be missed. The collected information is organized into an array. This order can be based on the arrangement of input controls on the interface or a specific order specified by the business logic. For example, the contents of text input boxes can be placed into the array first, followed by the selection values ​​of dropdown lists, radio buttons, and checkboxes. During the array construction process, ensure that each array element precisely corresponds to the user input item on the interface, and that the data type and format of the elements meet the requirements for subsequent processing. S203. Update the array to the called list.

[0058] The system locates the corresponding list file or data structure based on local storage rules. Common local storage methods include files in specific formats within the file system (such as JSON or CSV files) or predefined data structures (such as arrays or objects) in the application's local memory. The system identifies the list by file path, filename, or memory variable name.

[0059] Based on the array content and the structural characteristics of the local list, formulate an appropriate data update strategy. If there is a one-to-one correspondence between array elements and fields in the list, the array element values ​​can be directly updated to the corresponding fields in the list. If the array data requires preprocessing or format conversion to match list fields, such as if the date format in the array is different from the date format stored in the list, the date format in the array should be converted first before performing the update operation. After determining the update strategy, the specific update operation is executed. If the list is stored in the file system, the system reads the file content, modifies the corresponding data according to the update strategy, and then writes the modified content back to the file. If the list is stored in a local memory data structure, the corresponding element values ​​in the memory list data structure are directly modified to complete the data update. After the update operation is complete, the system reads the local list data again, compares the data status before and after the update, and confirms whether the array data has been correctly updated in the list. If the update result does not meet expectations, the system promptly activates the error handling mechanism, such as canceling the update operation, providing error information to the user, and prompting them to re-enter the information.

[0060] In one embodiment of the present invention, based on step S3, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0061] S301. Remove spaces from parameter values ​​in the list.

[0062] Iterate through the entire list. For each item in the list, determine which are parameter values. This requires considering the list's structure and predefined rules. For example, if the list is a structure recording job information. Once parameter values ​​are identified, check them for whitespace. Remove any leading, middle, or trailing whitespace from the parameter values.

[0063] S302. Validate whether the required fields are empty. If they are empty, mark the list as incomplete.

[0064] Before processing the list, the system needs to determine which fields are required. This is usually determined during the system design phase or when defining the business logic. For example, in an employee information list, employee name and employee ID might be set as required fields. This information about required fields is stored in the system's configuration file or related data dictionary. Iterate through each item in the local list again. For each item, check if the value of each required field is empty, according to the defined list of required fields. If a required field in any item is found to be empty, the entire list is marked as incomplete. This can be achieved by adding a specific identifier field to the list, such as a field named "Completion Status" with the value set to "Incomplete". This allows for quick identification of incomplete lists during subsequent business processing.

[0065] S303. Validate invalid data in the list and mark the invalid data.

[0066] The system iterates through each item in the local list, validating each parameter value according to predefined valid data rules. If a parameter value is found to be invalid, the system marks it. This marking can be done by adding a comment next to the data item, or by adding a dedicated field to the list for marking invalid data and setting its value to "invalid," allowing for quick identification and processing of invalid data later.

[0067] S304. Verify the abnormal fields in the list, where the abnormal fields do not conform to the threshold range of the corresponding parameter items.

[0068] A reasonable threshold range needs to be set for each parameter. This is determined based on business experience and actual needs. Iterate through each item in the local list, and for each parameter, check whether its value falls within the set threshold range. If the value of a parameter exceeds the set threshold range, the system will identify the field as an abnormal field.

[0069] S305. Confirm that there are abnormal fields in the list, generate a correction pop-up for the abnormal fields, and update the abnormal fields according to the fields entered in the correction pop-up.

[0070] After identifying the abnormal fields, check if there are any fields marked as abnormal in the list. This can be done by iterating through the list of identifiers used to mark abnormal fields. Once an abnormal field is detected, a dedicated correction pop-up is generated for each abnormal field. The pop-up will include the name of the abnormal field, the current abnormal value, and an input box for the user to enter a correction value. After the user enters the correct value in the correction pop-up, the system will retrieve this input value. Then, based on the list structure and storage method, the system will find the corresponding abnormal field and update its value to the user-entered correction value.

[0071] In one embodiment of the present invention, based on step S4, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0072] S401. Extract the number of work boxes, number of single hooks, work time, waiting time for AGV, mechanical failure time and abnormal downtime from the work information in the list.

[0073] The system first determines the storage location of the job information in the local list. This information may be stored in a local file in a structured form (such as a JSON object or a CSV table), or in the application's memory as a data structure such as an array or a dictionary.

[0074] Based on the system's preset field definitions, the target data fields are identified. For example: number of work boxes, number of single hooks, work time, waiting time for AGV, mechanical failure time, and abnormal downtime.

[0075] S402. Calculate the gross efficiency of the operation: Gross efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ (2 × Working time); S403. Calculate the net efficiency of the operation: Net efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ [2 × (Total operation time - Waiting time for AGV - Mechanical failure time - Abnormal downtime)]; S404. Compare the net efficiency with a preset efficiency threshold. If the net efficiency exceeds the efficiency threshold, generate an error reporting task.

[0076] The system reads preset efficiency thresholds from local configuration files (such as XML / JSON configurations) or built-in constants.

[0077] The calculated net efficiency value is compared with the threshold. If the net efficiency value is greater than the first threshold (indicating abnormally high efficiency), an error reporting mechanism is triggered. If the net efficiency value is less than the second threshold (indicating abnormally low efficiency), an error reporting mechanism is triggered. The first threshold is greater than the second threshold.

[0078] Create an error reporting task containing information such as job record ID, current net efficiency value, and threshold, and add the error reporting task to the system task queue to await processing.

[0079] S405. Execute the error reporting task and enter the modification interaction interface. The modification interaction interface includes a correction information input box, which is an input box corresponding to the quantity of work boxes, the number of single hooks, the operation time, the waiting time for AGV, the mechanical failure time, and the abnormal downtime.

[0080] Interface redirection: The system locates the corresponding job data based on the job record ID in the error task; it then redirects to a specially designed correction interface, which displays the original data of the current job record.

[0081] Control binding: Each input box is bound to a corresponding job parameter (e.g., the job time input box is bound to the job time field); the interface displays the current value and allows the user to modify it.

[0082] Validation mechanism: Perform real-time format validation on user-input values ​​(e.g., must be positive, conform to time format, etc.); provide error messages (e.g., "time cannot be negative").

[0083] S406. Update the list with the information re-entered in the modified interactive interface, and recalculate the job efficiency based on the updated list.

[0084] Data synchronization: After the user confirms the modification, the system will synchronize the new value in the input box to the job data object in memory.

[0085] Perform the update operation based on the storage type (file or memory): File storage: Read the original file, replace the corresponding records, and then rewrite it; In-memory storage: Directly modifying field values ​​within the data structure; Efficiency recalculation: Automatically triggers the calculation processes of S402 and S403, and the newly calculated gross efficiency and net efficiency values ​​are displayed on the interface in real time.

[0086] S407. Upload the net efficiency and corresponding gross efficiency, which do not exceed the efficiency threshold, to the management terminal.

[0087] Data filtering: Traverse all job records and filter out records with net efficiency ≤ threshold; Data encapsulation: Package the selected gross efficiency, net efficiency, and associated job ID into a data message; add metadata such as timestamps and device identifiers.

[0088] Data transmission: Data packets are sent to the management terminal server via HTTP / HTTPS protocol; breakpoint resumption and retransmission mechanisms are supported to ensure data integrity.

[0089] Feedback processing: Receive confirmation information from the server, record the job ID of a successfully uploaded job, and avoid duplicate uploads.

[0090] Based on the above embodiments, step S5 is added to provide a method for analyzing job reports: S501. The management terminal summarizes the work reports received within the set time period and extracts the gross efficiency, net efficiency, worker information, and work type information from the work reports.

[0091] First, the time frame must be clearly defined. This time frame can be pre-configured in the system, such as one week or one month. The management terminal will then read the start and end times of this time range from its own configuration file or database.

[0092] The management terminal filters all job reports received within a set time period from the location where it stores job reports. It iterates through the stored report records, checks whether the report's receipt time falls within the specified time range, and collects the reports that meet the criteria together.

[0093] For each summarized work report, the management terminal extracts gross efficiency, net efficiency, worker information (such as worker name and number), and work type information (such as goods category and specifications) from the report based on the report format (such as JSON, CSV, etc.) and predefined field mapping relationships. The extracted information is temporarily stored in a data structure for subsequent processing.

[0094] S502. Convert the job type information and the job personnel information into quantitative classification features as classification variables.

[0095] It is clear that the information on job type and the information on the workers are categorical variables, meaning that this information is composed of different categories rather than continuous values.

[0096] Define encoding rules for each categorical variable. Common methods include one-hot encoding and label encoding. For one-hot encoding, each category is converted into a binary vector with a length equal to the number of categories, where only the position corresponding to the category is 1 and the rest are 0.

[0097] According to the established coding rules, the job type information and worker information in the job report are converted into quantified classification features. The converted features are then stored in a new data structure and associated with the corresponding gross efficiency and net efficiency data.

[0098] S503. Obtain multiple net efficiencies corresponding to each quantified classification feature, and calculate the average net efficiency of the multiple net efficiencies.

[0099] The work report data is grouped according to quantitative classification characteristics. Work reports with the same combination of quantitative classification characteristics are grouped together. For example, all work reports with worker number 1 and work type "electronic products" are grouped together.

[0100] For each group, extract all net efficiency values ​​corresponding to that group from the associated data. Collect these net efficiency values ​​into a list or array.

[0101] The net efficiency values ​​collected for each group are summed, and then divided by the number of net efficiency values ​​to obtain the average net efficiency for that group. Each quantified categorical feature combination and its corresponding average net efficiency are stored in a new data structure.

[0102] S504. Arrange multiple quantitative classification features and their corresponding average net efficiency into a feature matrix.

[0103] Determine the structure of the feature matrix, where each row represents a combination of quantified categorical features, and each column represents a feature or average net efficiency. For example, columns 1 to n are quantified categorical features, and column (n+1) is the average net efficiency.

[0104] Arrange the previously obtained quantitative classification feature combinations and their corresponding average net efficiencies according to a matrix structure. Fill the corresponding row and column of the matrix with the feature values ​​of each quantitative classification feature combination, and fill the last column of that row with the average net efficiency. This results in a two-dimensional feature matrix.

[0105] S505. Using the XGBoost regression model, predict the highest net efficiency and the combination of quantitative classification features corresponding to the highest net efficiency based on the feature matrix.

[0106] Specifically, the management terminal loads the pre-trained XGBoost regression model from a pre-stored location. If the model does not exist, it needs to be trained using historical data first. After loading the model, initialization settings are performed, such as setting the prediction parameters and specifying the input format of the feature matrix.

[0107] During training, the model calculates the reduction in loss function resulting from feature splitting in each decision tree. For each quantified categorical feature, its split gain is calculated in each decision tree. The gain values ​​for that quantified categorical feature across all trees are then summed. The summed gain values ​​for all quantified categorical features are then normalized to obtain the importance score for each quantified categorical feature. The purpose of normalization is to ensure that the importance scores of all features are on a uniform scale for easier comparison.

[0108] The XGBoost regression model calculates the reduction in loss function due to feature splitting in each decision tree, sums the gain values ​​of the quantified classification features across all trees, and then normalizes the results to obtain the importance score of the quantified classification features.

[0109] Where T is the total number of trees, Let the split gain of feature i in the t-th tree be , Let feature j be the split gain in the t-th tree; For the tree model of XGBoost, the TreeExplainer algorithm calculates the contribution of quantified categorical features to all possible subset combinations by recursively traversing the tree path: ‌

[0110] Where N is the feature set, S is a subset excluding feature i, and f(S) is the model output based on subset S.

[0111] The entire model prediction process is as follows: The feature matrix is ​​input into the XGBoost regression model for prediction. Based on the input feature matrix, the model predicts the net efficiency corresponding to each quantized categorical feature combination. The highest net efficiency is identified from the prediction results, and the quantized categorical feature combination corresponding to this highest net efficiency is determined.

[0112] S506. Calculate the weighted sum of the importance score and contribution of the quantitative classification features, select the multiple quantitative classification features with the highest weighted sum, and solidify the multiple quantitative classification features into the optimal job allocation combination.

[0113] First, the weights for importance and contribution scores must be determined. These weights can be set based on business needs and experience; for example, the weight for importance can be set to 0.6, and the weight for contribution to 0.4. The total weight is 1.

[0114] For each quantitative classification feature, its importance score is multiplied by its corresponding weight, its contribution score is multiplied by its corresponding weight, and then the two results are added together to obtain the weighted sum of the quantitative classification feature.

[0115] Sort the quantitative categorical features according to their weighted sum from highest to lowest. Based on business needs, select the top 5 quantitative categorical features with the highest weighted sums. For example, you can select the top 5 quantitative categorical features with the highest weighted sums.

[0116] The selected combinations of quantitative classification features are used as the optimal job allocation combination and stored in the database or configuration file of the management terminal. This allows subsequent job allocation to directly reference this optimal combination, improving job efficiency.

[0117] Based on the above embodiments, in order to reduce the amount of data entry by on-site workers and improve the efficiency of work data recording, a method for adding a pre-assigned list is provided, including: Management terminal pre-assignment list method: 1. Obtain job assignment information.

[0118] The management terminal first obtains task allocation information from a reliable data source. This data source can be a database, such as the company's internal task management database, which stores various task-related data. It can also be other business systems, with data transmission occurring through inter-system data interfaces. The task allocation information contains one or more sets of correspondences between basic personnel information and basic vessel information. Basic personnel information may include personnel name, employee number, department, skill level, etc.; basic vessel information may include vessel name, vessel number, vessel type, vessel berthing location, etc. The management terminal accurately extracts this correspondence data from the data source according to pre-set rules and formats.

[0119] 2. Create one or more lists based on the job assignment information.

[0120] Based on the acquired task allocation information, the management terminal begins creating lists. For each pair of personnel and vessel basic information, a separate list is created. These lists are stored using specific data structures, such as arrays or objects in memory, or in temporary files. Each list clearly stores a set of personnel and vessel basic information, ensuring information integrity and relevance. The list structure is optimized based on future usage needs, facilitating further processing and querying by the management terminal.

[0121] 3. Obtain the location information of the handheld terminal, and determine the working location of the handheld terminal based on the location information.

[0122] The management terminal needs to establish a communication connection with the handheld terminal to obtain its location information using specific positioning technologies. Common positioning technologies include GPS positioning and cell tower triangulation. The handheld terminal periodically sends its location information to the management terminal. After receiving the location information, the management terminal matches it with a pre-defined work area map. The work area map marks various specific work locations, and the management terminal determines the handheld terminal's specific work location based on the latitude, longitude, or other coordinate information. For example, if the work area is divided into multiple dock areas, the management terminal can determine which dock and specific location the handheld terminal is in.

[0123] 4. Based on the ship's berthing position and the working position of the handheld terminal in the ship's basic information, determine the correspondence between the handheld terminal and the ship's basic information.

[0124] The management terminal compares and analyzes the ship berthing locations in the previously created list of basic ship information with the handheld terminal's working location. By calculating the distance or positional relationship between the two, it determines the correspondence between the handheld terminal and the ship's basic information. If the handheld terminal's working location and a ship's berthing location are within a reasonable range (this range can be set according to actual business needs), then a correspondence is considered to exist between the handheld terminal and that ship. For example, if the handheld terminal is located in a specific area of ​​a dock, and a ship happens to be berthed near that area, then their correspondence can be determined.

[0125] This is because in ship operation scenarios, the correspondence between the operator's handheld terminal and the ship may be dynamic. For example, the operator may be assigned to two ship operation tasks. After completing the operation task of one ship, the operator will go to perform the operation task of the next ship. Therefore, in the past, the operator needed to repeatedly enter his own information and the ship's information from the handheld terminal.

[0126] 5. Based on the aforementioned correspondence, a list containing the ship's basic information is sent to the corresponding handheld terminal.

[0127] Based on the established correspondence between handheld terminals and ship basic information, the management terminal sends a list containing the corresponding ship basic information to the relevant handheld terminal. Before sending, the management terminal formats and encrypts the list data to ensure accuracy and security during transmission. The management terminal sends the list data to the handheld terminal via a network communication protocol. During transmission, a reliable transmission mechanism is employed to ensure that the data arrives at the handheld terminal completely and accurately. If errors or data loss occur during transmission, the management terminal will resend the data.

[0128] Handheld terminal operation process: 1. The list of data received in the handheld terminal's cache.

[0129] After receiving the list from the management terminal, the handheld terminal stores it in a local cache. This cache can be part of the handheld terminal's memory or storage device. This is done to facilitate quick subsequent retrieval and use, avoiding the need to retrieve data from the management terminal each time. The handheld terminal verifies the received list to ensure data integrity and accuracy. If a problem is found, it sends feedback to the management terminal requesting a resend of the data.

[0130] 2. The handheld terminal retrieves the matching list from the cached list based on the partial information of the operators entered through the interactive interface.

[0131] The handheld terminal provides an interactive interface where operators can enter partial personal information, such as employee ID and name. The terminal then searches a locally cached list based on the entered information. The search process matches the entered information with the operator's basic information in the list. Fuzzy matching or exact matching can be used, depending on the specific business needs. For example, if only part of a name is entered, the terminal can use fuzzy matching to find a list of all names containing that part.

[0132] 3. The handheld terminal imports the basic information of the ship and the basic information of the operators from the matching list into the interactive interface.

[0133] Once the handheld terminal retrieves the matching list, it imports the basic information of the vessel and personnel from the list into the interactive interface for display. This eliminates the need for personnel to repeatedly import this information and allows for the correction of any errors, reducing the amount of data entry required. During the import process, the handheld terminal formats the information for a clear and easy-to-read presentation on the interface. It also provides interactive functions such as editing information and viewing detailed information to meet the practical needs of the personnel.

[0134] The invention will now be described using a VBA user interface as an example.

[0135] Please refer to Figure 2 The ship operation data processing flow includes: 1. Improve operational convenience through an interactive user interface to achieve standardized entry, dynamic verification, and automated aggregation of ship operation data.

[0136] 2. By combining dock production and operation data, it automatically generates personal efficiency reports and supports one-click export. It supports both local and network modes to ensure the security of data storage.

[0137] 3. Use VBA to dynamically validate data to ensure the accuracy of recorded data.

[0138] 4. Based on Excel, it can be deployed locally or connected to a server for synchronization, lowering the barrier to entry and making it accessible to all operators. It allows for quick configuration and use with zero upfront cost.

[0139] 5. Integrate functions such as recording abnormal ship issues, evaluating loading and unloading personnel, and handing over ships and machinery to strengthen the supervision of the operation process.

[0140] Please refer to Figure 3 This system consists of the following core modules: 1. Data entry module: Provide an interactive input interface (UserForm) through a VBA user interface (such as "Quick Input"), including fields such as vessel name, berth number, and work crew. Please refer to [reference needed]. Figure 4 .

[0141] Standardized option selection is achieved using the `ComboBox` dropdown selection control. Based on long-term summarization, 30 frequently occurring problems in ship operations have been categorized as follows: Dangerous Goods (Operations), Dangerous Goods (Waiting Time), Hatch Covers (Operations), Hatch Covers (Waiting Time), Oversized Cargo (Operations), Oversized Cargo (Waiting Time), Cage Locking, Cage Handling Abnormalities, Single Hook Operations, Shell Changing, Waiting for AGVs, Locking Pad Abnormalities, Loading / Unloading Personnel Stoppage, Single-Machine Automation Operation Abnormalities, Command Level Abnormalities, Mechanical Failures, Disconnecting / Connecting Double Spreaders, Bridge Position Adjustment, Platform Operations, Flat Rack Operations, Handling Abnormal Containers, Overly High Container Relocation, Technical Department Inspection / Repair, Foreign Affairs / Strong Wind Stoppage, Stoppages Caused by Operational Intersections, Other Abnormal Stoppages, Overturned Containers / Collecting Containers, Number of Inserted Gears, Other Manual Operations, Shell Changing Due to Dangerous Goods Operations. Operators should select from the dropdown menu to ensure data consistency. Please refer to the following: Figure 5 .

[0142] Based on the `CommandButton` control, it provides timestamps for records and gives operators a quick way to enter data.

[0143] Based on the `OptionButton` selection button and the `ToggleButton` toggle button, operators can switch and select the working condition to enter.

[0144] 2. Data Processing Module: This system performs real-time data validation based on Excel data validation. It uses VBA (the `Validation` function) to verify the validation results, employs the `Trim` function to remove spaces, and combines this with `IF` statements to check if required fields are empty. For example: “Sub Example() Dim rng As Range Dim cell As Range Dim res As Range Dim lastRow As Long Get the last line lastRow = Cells(Rows.Count, "C").End(xlUp).Row 'Set range Set rng = Range("C2:R"&lastRow) 'Initialize res Set res = Nothing 'Traverse each cell within the range For each cell In rng Remove spaces if the cell value is not an error value. If Not IsError(cell.Value) Then cell.Value = Trim(cell.Value) End If Check if the cell's validation rules have failed. If Not cell.Validation.Value Then Cells(cell.Row, 19) = "NULL" ' Marks column S as "NULL" If res is nothing, then Set res = cell ' If it is the first invalid cell, assign the value to res Else Set res = Union(res, cell) ' Otherwise, merge the current cell into res. End If Else cell.Interior.Pattern = xlNone ' Clear background fill if validation passes End If Next cell If there is invalid data If not res is nothing then MsgBox "Invalid data, located at: "&res.Address(0, 0) ' A pop-up window displays the address of the invalid data. res.Select 'Select invalid data' res.Interior.Color = vbYellow 'Mark invalid data as yellow' Else If there is no invalid data, clear the background fill of the entire worksheet. ActiveSheet.UsedRange.Interior.Pattern = xlNone End If End Sub Abnormal data triggers a pop-up alert (`MsgBox`). Using the address hint and location feature, the error field is highlighted with `Interior.Color=vbYellow`. This entry is marked in the "Multi-Function Column" for easy validation before summary statistics. If the data is corrected and validated again using the program, the mark and highlight will be automatically cleared.

[0145] The VBA algorithm calculates the time consumed for various operations, such as single hook, hatch cover, and hazardous materials handling, based on the input time period and quantity. If the duration of these special operations exceeds 5 minutes, a pop-up message will appear stating, "The quantity and time entered in the previous entry may be incorrect. Please check and confirm immediately." For example: "dc = Format(Cells(r, 11) / Cells(r, 15), "hh:mm:ss") If TimeValue(dc)>TimeValue("00:05:00") Or TimeValue(dc) <TimeValue("00:01:00") Then MsgBox: "The quantity and time entered in the previous message may be incorrect. Please check and confirm." This code checks if the unit time of the previous line ("r") is between 1 minute and 5 minutes.

[0146] The statistical efficiency system automatically categorizes and calculates the time consumption of each item in the record. Combining the operator's working time and the number of work boxes, the system calculates the operator's gross efficiency (hooks / hour) according to the formula: Gross efficiency = (number of work boxes (TEU) - number of single hooks) ÷ (2 × working time (hours)).

[0147] Based on the formula: Net efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ [2 × (Total working time - Waiting time for AGV - Mechanical failure time - Other abnormal downtime)], the net efficiency of the operator (hook / hour) can be calculated.

[0148] The system will verify the calculated net efficiency of the operation. When the net efficiency is less than 40 (hooks / hour), the system will mark the efficiency in red, indicating that the calculated net efficiency is too high, and remind the operator to check the input value or record the problem.

[0149] After verification, the operator can generate an efficiency report with one click and upload it to the server.

[0150] 3. Data storage module: Local mode: Data is stored in an Excel workbook and backed up to a specified path periodically using the `FileCopy` function to protect data security.

[0151] Network mode: Access the shared server (such as `\\10.158.16.200\Operation\`) via `Workbooks.Open` to achieve data synchronization across multiple terminals.

[0152] The system checks network connectivity using the `ping` function during startup, for example: “Sub ping() Dim objWSShell, strEcho, oExec As Object Dim IP As String On Error Resume Next Set objWSShell = CreateObject("Wscript.shell") Replace "**.**.**.**"' with the server that needs to be checked. cmdping = "ping "&IP&" -n 3" Set oExec = objWSShell.exec(cmdping) Do Until oExec.stdout.AtEndOfstream strEcho = strEcho&oExec.stdout.readline()&Chr(13) Loop Debug.Print strEcho If `InStr(strEcho, "Lost = 0 (0% loss)")` or `InStr(strEcho, "Lost = 0 (0% loss)")` then... MsgBox "Connected to public drive" ThisWorkbook.Sheets("Shift Job Information").Range("o1") = 1 Else If MsgBox("Not connected to the public drive, please contact the associated public drive immediately to confirm whether local mode should be temporarily enabled", vbYesNo) Then ThisWorkbook.Sheets("Shift Job Information").Range("o1") = 0 End If End If Set objWSShell = Nothing Set oExec = Nothing Set strEcho = Nothing End Sub Automatically selects local or server storage mode. In case of network interruption, local data is temporarily stored and the user is notified.

[0153] 4. Functional Expansion Module: Please refer to the information entry and function documentation. Figure 6 : The "Information Entry and Function" extension module meets the daily data entry and query needs of operators.

[0154] Evaluation of loading and unloading personnel's work: through a dedicated user interface (such as...) Figure 7 (As shown) Records problems encountered by loading and unloading personnel, supports marking the reasons for deductions and automatic calculation of total scores, and uploads to the server with one click.

[0155] Other data entry: Use the `ComboBox` dropdown selection control to perform temporary statistics by category, such as... Figure 8 As shown, the list is updated by connecting to the server via `Workbooks.Open`, for example: "Application.Workbooks.Open Path"\****.xlsx", , ReadOnly = True r = Workbooks("****.xlsx").Sheets("sheet1").Range("b"&Rows.Count).End(xlUp).Row Set rng = Workbooks("****.xlsx").Sheets("sheet1").Range("b2:b"&r) For each cel In rng ListBox1.AddItem cel Next This code can display the contents of a server file in a list format for operators to select from.

[0156] Quickly summarize operator information by selecting items from the list, and support one-click upload to the server.

[0157] Emergency mode: In case of an emergency, the system will automatically switch to the backup spreadsheet. Data will be stored in the backup spreadsheet via `Copy` and `PasteSpecialPaste` to ensure the continuity of data entry.

[0158] Issue feedback: Issue feedback is encrypted and stored on the server via messages to facilitate communication between administrators and users.

[0159] Vessel Planning: Open the berth operation planning page using the default browser via the address configured in `FollowHyperlink`.

[0160] Ship information and gantry crane information: Establishes a system for searching and modifying data files corresponding to the server, enabling quick understanding of ship length, locking pad condition, abnormal locations, gantry crane mechanism status, and issues.

[0161] Ship report generation: By calling `Application.FileDialog(msoFileDialogFilePicker)`, statisticians select and merge relevant records, access server templates, and generate a visual statistical report locally.

[0162] Dynamic report generation: The recorded data is formed into a pivot table, with rows representing operators and project numbers, and values ​​representing summation items (quantity and time). The `Private Sub Worksheet_Activate` method is called to execute the `RefreshAll` method to update the pivot table and generate statistical reports such as the number of anomalies and special time consumption.

[0163] Based on the above system, the ship operation data entry process includes: 1. Environment configuration: Install Microsoft Excel 2013 or later and enable macro functionality (path: File → Options → Trust Center → Enable all macros).

[0164] 2. System startup: After opening the workbook, the main interface will automatically pop up. Enter the ship name, operator, select machinery, work team, loading and unloading conditions, work deck or hold, and work bay position, and then click the "Start Work" button to generate the work record.

[0165] 3. Data entry: Clicking the "Start Time" button will automatically record the current time. Abnormal events can be selected through the drop-down menu (such as Hazardous Materials (Operation) or Hazardous Materials (Waiting Time)).

[0166] You can also quickly select common exception events, and the buttons can be customized and set according to frequency.

[0167] The quick fill button represents the content corresponding to frequently used serial numbers, allowing for quick selection and entry. It supports custom notes to be quickly filled in with abnormal events, and the input can be reset by clicking the "Clear" button.

[0168] Note: The `ComboBox` dropdown selection control automatically generates dropdown options based on the selected item number.

[0169] Clicking the end time will automatically record the current time, complete the verification of the current record, and provide prompts to the operator based on the verification results.

[0170] A continuous stop button is provided, which provides a convenient continuous recording capability based on the recording status (such as ending the current time and starting the next record at the same time, or starting a record with the same end time as the current time, which the system will automatically determine based on the end time). The recording process may involve shift changes among team members. Clicking on the shift handover in the user interface will automatically save the current table to the local machine and automatically calculate and fill in the next work team and shift system. The person taking over the shift only needs to fill in their own name.

[0171] To end a vessel operation record, click "Completed Ship." The system will automatically perform data verification. If the data verification fails, the system will display the error data, highlight it, and stop the completion summary process. If the data verification is successful, the system will automatically fill in the completion information and then place it in the corresponding shared directory on the server according to the shift system and work group.

[0172] Loading and unloading personnel evaluation process: 1. Function call: Click the "Information Entry and Function Button" in the user interface, and then click the "Loading and Unloading Entry" button in the pop-up interface to automatically enter the bridge crane number and fill in the loading and unloading team information.

[0173] 2. Evaluation process: Selecting the evaluation target (commander, bridge leader) will automatically generate a list of evaluation criteria. Double-clicking an item in the list will generate a deduction record, and the system will automatically calculate the total score and grade.

[0174] Click the "Generate Evaluation Form" button to save the data to the server's shared directory.

[0175] Example 3: Statistics 1. Function call: Click the "Information Entry and Function Button" in the user interface, and then click the "Statistics" button in the pop-up window. The system will automatically verify all records, and after verification, a statistics interface will pop up, categorizing and calculating the time consumption of all records for the current operator.

[0176] Input the quantity of boxes and time for the matching record period, and the system will automatically calculate the gross efficiency and net efficiency of the total number of hooks, and verify the calculated net efficiency.

[0177] The statistics interface only requires you to enter the amount of work and the duration of work.

[0178] After clicking "Generate Report", the system will automatically generate an efficiency report and upload it to the server. The report will be sorted by ship name and machinery number in the server file for easy viewing.

[0179] Ship report generation process: Click the "Information Entry and Function Button" in the user interface, and then click the "Generate Ship Report" button in the pop-up window.

[0180] In the pop-up interface, select the records that need to be merged. After confirming, the system executes the merge command and generates a ship operation problem statistics report locally.

[0181] Emergency Mode: If a table has a formatting error, click the "Information Entry and Function Buttons" in the user interface, and then click the "Emergency Mode" button in the pop-up window. The system will automatically access the server to use a backup table, and the data will be temporarily stored via Copy / PasteSpecial for emergency use. Reactivate the workbook and perform a version number comparison verification using Private Sub Workbook_Open. The system will automatically prompt the operator to upgrade or replace the table with the official version, and the data will be completely copied at the same time.

[0182] Figure 9The ship operation data processing method provided in the embodiments of this application can be applied to equipment. Those skilled in the art will understand that the equipment structure involved in the embodiments of this invention does not constitute a limitation on the equipment. The equipment may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the equipment includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0183] The device 900 may include a processor 910, a memory 920, and a communication unit 930. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0184] The memory 920 can be used to store execution instructions of the processor 910. The memory 920 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 920 are executed by the processor 910, the device 900 is able to perform some or all of the steps in the above method embodiments.

[0185] The processor 910 serves as the control center of the storage device, connecting various parts of the electronic device via various interfaces and lines. It executes software programs and / or modules stored in the memory 920, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 910 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0186] The communication unit 930 is used to establish a communication channel, enabling the storage device to communicate with other devices. It can receive user data sent by other devices or send user data to other devices.

[0187] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0188] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other medium capable of storing program code. It includes several instructions to cause a computer device (which may be a personal computer, a server, or a second device, network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0189] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0190] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0191] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0193] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A method for processing ship operation data, characterized in that, include: The action list is invoked based on the information entered from the interactive interface; The data generated by the information entry behavior is saved to the list, and the data includes ship information and operation information; The list is preprocessed for information normalization. The work efficiency is calculated based on the preprocessed list, and the work efficiency is written into the work report, which is then uploaded to the management terminal.

2. The method according to claim 1, characterized in that, The action call list is entered based on the information entered through the interactive interface, including: Obtain the first information entry behavior of the first interactive interface; Acquire the first information generated by the first information entry behavior, the first information including ship identity information and operation identity information; Based on the first information, query the matching list from the already created list; If the matching list is found, then the matching list is retrieved. If no matching list is found, a new list is created and the new list is invoked.

3. The method according to claim 2, characterized in that, The data generated by the information entry behavior is saved to the list, and the data includes vessel information and operation information, including: The second information input behavior of the second interactive interface is obtained, and the second interactive interface is a subordinate interface of the first interactive interface; Extract the array generated by the second information input behavior in the second interactive interface; Update the array to the list that was called.

4. The method according to claim 1, characterized in that, The list undergoes information normalization preprocessing, including: Remove spaces from parameter values ​​in the list; Validate whether required fields are empty; if they are empty, mark the list as incomplete. Validate invalid data in the list and mark the invalid data. Verify the abnormal fields in the list, where the abnormal fields do not meet the threshold range of the corresponding parameter items; If an abnormal field is found in the list, a correction pop-up is generated for the abnormal field, and the abnormal field is updated according to the field entered in the correction pop-up.

5. The method according to claim 1, characterized in that, Calculate the job efficiency based on the preprocessed list, and upload the job efficiency to the management terminal, including: Extract the number of work boxes, number of single hooks, work time, waiting time for AGV, mechanical failure time and abnormal downtime from the work information in the list; Calculate the gross efficiency of the operation: Gross efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ (2 × Working time); Calculate the net efficiency of the operation: Net efficiency = (Working box quantity (TEU) - Number of single hooks) ÷ [2 × (Total operation time - Waiting time for AGV - Mechanical failure time - Abnormal downtime)]; The net efficiency is compared with a preset efficiency threshold. If the net efficiency exceeds the efficiency threshold, an error reporting task is generated. Execute the error reporting task to enter the modification interaction interface. The modification interaction interface includes a correction information input box, which is an input box corresponding to the quantity of work boxes, the number of single hooks, the operation time, the waiting time for AGV, the mechanical failure time, and the abnormal downtime. Update the list with the information re-entered in the modified interactive interface, and recalculate the job efficiency based on the updated list; The net efficiency and the corresponding gross efficiency, which do not exceed the efficiency threshold, are uploaded to the management terminal.

6. The method according to claim 5, characterized in that, The method also includes analyzing job reports using a management terminal, and the methods for analyzing job reports include: The management terminal will summarize the work reports received within the set time period and extract the gross efficiency, net efficiency, worker information, and work type information from the work reports. The information on job type and the information on the workers are converted into quantitative classification features as classification variables; Obtain multiple net efficiencies corresponding to each quantified classification feature, and calculate the average net efficiency of the multiple net efficiencies; Multiple quantitative classification features and their corresponding average net efficiency are arranged into a feature matrix; The XGBoost regression model is used to predict the highest net efficiency and the combination of quantized classification features corresponding to the highest net efficiency based on the feature matrix. The XGBoost regression model calculates the reduction in loss function caused by feature splitting in each decision tree, sums the gain values ​​of the quantized classification features in all trees, and obtains the importance score of the quantized classification features after normalization. Where T is the total number of trees, Let the split gain of feature i in the t-th tree be , Let feature j be the split gain in the t-th tree; For the tree model of XGBoost, the TreeExplainer algorithm calculates the contribution of quantified categorical features to all possible subset combinations by recursively traversing the tree path: ‌ Where N is the feature set, S is a subset excluding feature i, and f(S) is the model output based on subset S; Calculate the weighted sum of importance score and contribution of quantitative classification features, select the multiple quantitative classification features with the highest weighted sum, and solidify the multiple quantitative classification features into the optimal job allocation combination.

7. The method according to claim 1, characterized in that, Before calling the behavior list based on the information entered through the interactive interface, the method also includes a pre-allocated list for the management terminal. The method for pre-allocating the list includes: Obtain task allocation information, which includes a correspondence between one or more sets of basic information of operators and basic information of ships; One or more lists are created based on the task allocation information, and the lists store a set of basic information about the personnel and the vessels. Obtain the location information of the handheld terminal, and determine the working location of the handheld terminal based on the location information; Based on the ship's berthing position in the ship's basic information and the working position of the handheld terminal, the correspondence between the handheld terminal and the ship's basic information is determined; Based on the aforementioned correspondence, a list containing the ship's basic information will be sent to the corresponding handheld terminal.

8. The method according to claim 7, characterized in that, The method further includes: The list of received data is cached on the handheld terminal; The handheld terminal retrieves a matching list from a cached list based on the partial information of the operators entered through the interactive interface. The handheld terminal imports the basic information of the ship and the basic information of the operators from the matching list into the interactive interface.

9. A device, characterized in that, include: Memory, used to store ship operation data processing programs; A processor is configured to implement the steps of the ship operation data processing method as described in any one of claims 1-8 when executing the ship operation data processing program.

10. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a ship operation data processing program, which, when executed by a processor, implements the steps of the ship operation data processing method as described in any one of claims 1-7.

Images