A production cost accounting method based on port big data

Through the evaluation and tuning of the process classification of port operation data and the cost analysis algorithm model, the problem of inaccurate port production cost accounting is solved, and the accurate accounting of port production cost and operation efficiency is achieved.

CN118569685BInactive Publication Date: 2024-12-03YANTAI PORT GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411044492.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the existing production cost accounting methods for port big data, the name, format and content of documents between terminal companies are not unified, resulting in low standardization ratio of business management data and inaccurate production cost accounting.

Method used

By collecting port operation data, conducting process classification, building cost analysis algorithm models, conducting model evaluation and tuning, combining data processing and shaping, obtaining production cost accounting indicators, judging the compliance of port production costs, and improving accounting accuracy.

Benefits of technology

It realizes accurate accounting of port production costs, improves accounting accuracy, ensures that the performance of the cost analysis model and unit test indicators meet standards, and improves port operation efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118569685B_ABST
    Figure CN118569685B_ABST
Patent Text Reader

Abstract

The present invention discloses a production cost accounting method based on port big data, and relates to the field of data processing technology. The production cost accounting method based on port big data includes the following steps: data collection; process classification; data model construction; data model evaluation; production cost accounting. The present invention classifies the initial port operation data obtained by the process to obtain a process classification number set, and then constructs a cost analysis algorithm data model according to the obtained process classification number set, and then evaluates and optimizes the cost analysis algorithm data model, and finally calculates the production cost of the port to be accounted for according to the production cost accounting data obtained by data processing and shaping and combines the cost analysis algorithm data model to obtain the production cost accounting index to judge whether the production cost of the port to be accounted meets the standard, thereby achieving the effect of improving the accuracy of port production cost accounting, and solving the problem of inaccurate port production cost accounting in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a production cost accounting method based on port big data. Background Art

[0002] The existing production cost accounting method of port big data refers to the calculation and accounting of production costs using the large amount of data generated in port operations. This method can help port managers understand the cost structure of port operations more accurately, thereby optimizing resource allocation, improving efficiency, reducing costs, and achieving sustainable development of port operations. Through the production cost accounting method based on port big data, port managers can have a more comprehensive understanding of the cost situation of port operations, thereby optimizing resource allocation, improving operational efficiency, and achieving a win-win situation of economic and social benefits.

[0003] For example, the invention patent with announcement number: CN115563389B announces a port logistics information push method and system based on big data, including: upon receiving port logistics query request information initiated by a target user based on a corresponding target user terminal device, determining the target user's attention level information for port logistics information based on the target user's historical logistics-related behavior information stored in a target big data database; determining the amount of logistics information data corresponding to the target user based on the attention level information; extracting the corresponding target port logistics information from the initial port logistics information corresponding to the target port logistics object corresponding to the target user based on the logistics information data volume, and pushing the target port logistics information to the target user terminal device corresponding to the target user.

[0004] For example, a patent application with publication number: CN117874677A discloses a carbon emission accounting management method and system based on big data, including: obtaining the carbon dioxide concentration of carbon emission sources under a period as data constituting a time series matrix; obtaining the correlation coefficient between the data; constructing an undirected graph based on the correlation coefficients between all rows of data and obtaining a strongly correlated carbon emission source combination; clustering the data to obtain data point clusters; obtaining the trend sensitivity index of the data point based on the position characteristics, numerical characteristics and difference characteristics between the data points in the data clustering cluster and the neighborhood range; taking the data as input, using the least squares linear fitting method to obtain the straight line equation of each row of data; obtaining the frequency spectrum of each row of data, and obtaining the main periodic components of the data based on the frequency spectrum of the data; obtaining the degree of carbon emission source combination synergy between the strongly correlated carbon emission source combination data and the data based on the slope of the straight line equation of the data, the main periodic components and the average of the correlation coefficients between the data and other data in the corresponding strongly correlated carbon emission source combination; obtaining an adaptive shrinkage factor based on the trend sensitivity index of the data point and the degree of synergy of the carbon emission source combination; taking each row of data as a data set, and performing abnormal point detection on the data set based on the adaptive shrinkage factor.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] In the existing technology, the traditional method of calculating the production cost of port big data has inconsistent document names, formats and contents among terminal companies, and there are differences in the types of documents; the requirements for documents in management among terminal companies are inconsistent, and there are no clear specifications; the standardization ratio of business management data is also low, resulting in inaccurate port production cost accounting. Summary of the invention

[0007] The embodiment of the present application solves the problem of inaccurate port production cost accounting in the prior art by providing a production cost accounting method based on port big data, thereby improving the accuracy of port production cost accounting.

[0008] The embodiment of the present application provides a production cost accounting method based on port big data, comprising the following steps: S1, collecting initial port operation data of the port to be accounted for, wherein the initial port operation data is obtained through a production business system; S2, classifying the obtained initial port operation data according to the production operation process to obtain a process classification number set, wherein the process classification number set includes a cargo type number set, a ship type number set and an operation type number set; S3, constructing a corresponding sub-cost algorithm model according to the obtained process classification number set, and integrating the constructed sub-cost algorithm model into a cost analysis algorithm data model; S4, performing model evaluation on the integrated cost analysis algorithm data model to obtain a data model evaluation result, and performing model optimization on the cost analysis algorithm data model according to the data model evaluation result, wherein the data model evaluation result is used to describe the production cost accuracy of the cost analysis algorithm data model; S5, performing data processing and shaping on the initial production cost accounting data extracted from the power consumption data of the port to be accounted for to obtain production cost accounting data, and at the same time, calculating the production cost of the port to be accounted for in combination with the cost analysis algorithm data model to obtain a production cost accounting index, and judging whether the production cost of the port to be accounted meets the standard according to the production cost accounting index.

[0009] Furthermore, the specific method for obtaining the unit test index is as follows: obtain unit coverage from the actual application process of the cost analysis algorithm data model, and the unit coverage includes code line coverage, function coverage, condition coverage and path coverage; obtain the unit test index of the cost analysis algorithm data model according to the obtained unit coverage, and the unit test index is calculated using the following formula:

[0010] ;

[0011] In the formula, e is a natural constant, n represents the number of the sub-cost algorithm model, , is the total number of sub-cost algorithm models, For unit test indicators, is the code line coverage of the nth sub-cost algorithm model, is the function coverage of the nth sub-cost algorithm model, is the condition coverage of the nth sub-cost algorithm model, is the path coverage of the nth sub-cost algorithm model.

[0012] Furthermore, the specific method for obtaining the performance test index is as follows: obtaining corresponding performance test data from the actual application process of the cost analysis algorithm data model, the performance test data including response time, processing speed and pressure assessment rate; obtaining a performance test coefficient according to the obtained performance test data, the performance test coefficient including a response time coefficient and a processing speed coefficient; obtaining a performance test index of the cost analysis algorithm data model according to the obtained performance test coefficient and pressure assessment rate, the performance test index is calculated using the following formula:

[0013] ;

[0014] In the formula, e is a natural constant, m represents the number of the cost analysis algorithm data model, , M is the total number of cost analysis algorithm data models, is the performance test index of the mth cost analysis algorithm data model, is the response time coefficient of the mth cost analysis algorithm data model, is the processing speed coefficient of the mth cost analysis algorithm data model, is the stress assessment rate of the mth cost analysis algorithm data model.

[0015] Furthermore, the specific steps for obtaining the production cost accounting indicators include: classifying the obtained production cost accounting data according to the cost relationship standard to obtain direct production cost accounting data and indirect production cost accounting data; directly classifying the direct cost accounting data, and indirectly allocating the indirect production cost accounting data, and at the same time combining the cost analysis algorithm data model to obtain the production cost accounting data of the production operation process of the port to be accounted for; and obtaining the production cost accounting indicators of the port to be accounted for based on the obtained production cost accounting data.

[0016] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0017] 1. The process classification data set is obtained by classifying the initial port operation data obtained, and then a cost analysis algorithm data model is constructed according to the obtained process classification data set. Then, the cost analysis algorithm data model is evaluated and optimized. Finally, the production cost accounting data obtained by data processing and shaping is combined with the cost analysis algorithm data model to calculate the production cost of the port to be accounted for and obtain the production cost accounting index to judge whether the production cost of the port to be accounted meets the standard, so as to accurately calculate the production cost of the port to be accounted, thereby realizing the improvement of the accuracy of port production cost accounting, and effectively solving the problem of inaccurate port production cost accounting in the prior art.

[0018] 2. By obtaining unit coverage from the actual application process of the cost analysis algorithm data model, and then obtaining the unit test indicators of the cost analysis algorithm data model based on the obtained unit coverage, and finally evaluating the actual working situation of the sub-cost algorithm model in the cost analysis algorithm data model through the obtained unit test indicators, the actual working situation of the sub-cost algorithm model in the cost analysis algorithm data model is quantified, thereby achieving a more accurate evaluation of the actual working situation of the sub-cost algorithm model in the cost analysis algorithm data model.

[0019] 3. By obtaining the corresponding performance test data from the actual application process of the cost analysis algorithm data model, and then obtaining the performance test coefficient based on the obtained performance test data, and then obtaining the performance test index of the cost analysis algorithm data model based on the obtained performance test coefficient and the pressure assessment rate, and finally evaluating the performance of the cost analysis algorithm data model through the calculated performance test index, the performance of the cost analysis algorithm data model is quantified, thereby achieving a more accurate evaluation of the performance of the cost analysis algorithm data model. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a production cost accounting method based on port big data provided in an embodiment of the present application;

[0021] Figure 2 A flowchart for constructing a sub-cost algorithm model provided in an embodiment of the present application;

[0022] Figure 3 A diagram of a method for obtaining data model evaluation results provided in an embodiment of the present application;

[0023] Figure 4 A statistical chart of changes in production cost accounting indicators provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiment of the present application solves the problem of inaccurate port production cost accounting in the prior art by providing a production cost accounting method based on port big data. The initial port operation data obtained is classified by process through the production operation process to obtain a process classification number set, and then a corresponding sub-cost algorithm model is constructed according to the obtained process classification number set, and the constructed sub-cost algorithm model is integrated into a cost analysis algorithm data model. Then, a model evaluation is performed on the integrated cost analysis algorithm data model to obtain a data model evaluation result, and the cost analysis algorithm data model is model-tuned according to the data model evaluation result. Finally, the initial production cost accounting data extracted from the power consumption data of the port to be accounted for is processed and shaped to obtain production cost accounting data. At the same time, the production cost of the port to be accounted is calculated in combination with the cost analysis algorithm data model to obtain a production cost accounting index. The compliance of the production cost of the port to be accounted for is judged according to the production cost accounting index, thereby improving the accuracy of port production cost accounting.

[0025] The technical solution in the embodiment of the present application is to solve the problem of inaccurate calculation of port production costs. The overall idea is as follows:

[0026] By classifying the initial port operation data obtained through process classification, a process classification data set is obtained, and a cost analysis algorithm data model is constructed based on this. Then, the cost analysis algorithm data model is evaluated and optimized. Finally, the production cost accounting data obtained through data processing and shaping is combined with the cost analysis algorithm data model to calculate the production cost of the port to be accounted for, and the production cost accounting index is obtained to determine whether the production cost of the port to be accounted meets the standard, thereby achieving the effect of improving the accuracy of port production cost accounting.

[0027] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0028] like Figure 1As shown, it is a flow chart of a production cost accounting method based on port big data provided by an embodiment of the present application, the method comprising the following steps: S1, collecting initial port operation data of the port to be accounted for, the initial port operation data being obtained through a production business system, the production business system comprising a port management system, automation equipment and sensors, the initial port operation data comprising production plan data, production allocation data and operation ticket data; S2, classifying the obtained initial port operation data according to the production operation process to obtain a process classification number set, the process classification number set representing a collection of port operation data of a single process in the production operation process, the process classification number set comprising a cargo type number set, a ship type number set and an operation type number set; S3, constructing a corresponding sub-cost algorithm model according to the obtained process classification number set, and integrating the constructed sub-cost algorithm model into a cost analysis algorithm data model, the sub-cost algorithm model This algorithm model is used to describe the production cost situation of a single process. The sub-cost algorithm models include cargo classification algorithm models, ship classification algorithm models and operation classification algorithm models. The cost analysis algorithm data model is used to describe the production cost situation of a unified process. S4. The integrated cost analysis algorithm data model is evaluated to obtain a data model evaluation result, and the cost analysis algorithm data model is optimized according to the data model evaluation result. The data model evaluation result is used to describe the production cost accuracy of the cost analysis algorithm data model. S5. The initial production cost accounting data extracted from the power consumption data of the port to be accounted for is processed and shaped to obtain production cost accounting data. At the same time, the production cost of the port to be accounted for is calculated in combination with the cost analysis algorithm data model to obtain the production cost accounting index. The production cost compliance of the port to be accounted for is judged according to the production cost accounting index.

[0029] In this embodiment, the automatic power consumption collection system for operating equipment is used to collect power consumption data of the operating equipment at preset time intervals through the automatic power collection system. The power consumption data represents the power consumption of the operating equipment under normal operation during the preset time interval. The cost accounting system is used to extract initial production cost accounting data from the power consumption data. The initial production cost accounting data represents data used for the accounting of port production costs. The production cost accounting indicators are used to describe the production cost situation of the port to be accounted for; thereby improving the accuracy of port production cost accounting.

[0030] Furthermore, the specific steps of process classification are as follows: formulate process classification standards according to the production operation process, the process classification standards include cargo classification standards, ship classification standards and operation classification standards, and pre-process the collected initial port operation data to obtain port operation data; automatically classify the pre-processed port operation data according to the formulated process classification standards and mark the types of the classified port operation data, organize the classified port operation data according to the production operation process to construct a process classification data set, and manage the constructed process classification data set; at the same time, output the constructed process classification data set as a visual chart.

[0031] In this embodiment, preprocessing includes data cleaning and data processing. Data cleaning includes removing noise, supplementing missing values ​​and eliminating outliers. Data processing means converting the format of initial port operation data to obtain a unified format and type. Category marking is used to distinguish the classification of port operation data. Data set management includes data set data storage, data set data backup, data set data archiving, data set data retrieval and data set data sharing. Visual charts are used to enable preset personnel to intuitively understand and use process classification data sets. This achieves an improvement in the accuracy of initial port operation data classification.

[0032] Further, such as Figure 2 As shown, it is a flow chart for constructing a sub-cost algorithm model provided in an embodiment of the present application, and the specific construction steps of the sub-cost algorithm model are as follows: step one, extracting a classification cost feature set from the acquired process classification data set; step two, feature encoding the extracted classification cost feature set to obtain a classification cost feature encoding set; step three, dividing the acquired classification cost feature encoding set into corresponding training set, validation set and test set, using the training set to perform model training on the data model to obtain a data training model, using the validation set to perform model validation on the data training model to obtain a data validation model, using the test set to perform model testing on the data validation model to obtain a test result, if the corresponding threshold condition is met, the sub-cost algorithm model is obtained, otherwise execute step one.

[0033] In this embodiment, the classified cost feature set represents the feature data related to the cost in a single process, and the classified cost feature set includes a cargo-based cost feature set, a ship-based cost feature set, and an operation-based cost feature set; the classified cost feature coding set is used to encode the classified cost feature set into a numerical type, and the classified cost feature coding set includes a cargo-based cost feature coding set, a ship-based cost feature coding set, and an operation-based cost feature coding set; the data model has the function of production cost accounting; the applicability of the construction of the sub-cost algorithm model is improved, and the accuracy of port production cost accounting is further improved.

[0034] Furthermore, the integration step of the cost analysis algorithm data model is as follows: constructing a data interface between the sub-cost algorithm model and the cost analysis algorithm data model according to the flow direction of the data in the process classification data set, and integrating the cost analysis algorithm data model by calling the data interface of the sub-cost algorithm model.

[0035] In this embodiment, the flow direction includes flow from the sub-cost algorithm model to the cost analysis algorithm data model and bidirectional flow; the data interface is used to ensure seamless connection and transmission of port operation data between models, and the data interface includes the format and calling method of the data; the reliability of the integration of the cost analysis algorithm data model is improved, and the accuracy of port production cost accounting is further improved.

[0036] Further, such as Figure 3 As shown, a diagram of a method for obtaining data model evaluation results provided in an embodiment of the present application, and a specific method for obtaining data model evaluation results is as follows: performing unit testing on a sub-cost algorithm model in a cost analysis algorithm data model to obtain unit test indicators, and comparing the unit test indicators with preset threshold conditions to obtain unit test results, and the unit test indicators are used to describe the actual working conditions of the sub-cost algorithm model in the cost analysis algorithm data model; performing performance testing on the sub-cost algorithm model in the cost analysis algorithm data model to obtain performance test indicators, and comparing the performance test indicators with preset threshold conditions to obtain performance test results, and the performance test indicators are used to describe the performance of the cost analysis algorithm data model; the data model evaluation results include unit test results and performance test results.

[0037] In this embodiment, unit testing is a process for verifying whether the smallest testable unit in the code works as expected; unit testing results include unit testing passing the standard and unit testing failing the standard; performance testing results include performance testing passing the standard and performance testing failing the standard; the evaluation efficiency of the cost analysis algorithm data model is improved, and the accuracy of port production cost accounting is further improved.

[0038] Furthermore, the specific method for obtaining the unit test indicators is as follows: obtain the unit coverage rate from the actual application process of the cost analysis algorithm data model, the unit coverage rate includes code line coverage rate, function coverage rate, condition coverage rate and path coverage rate, the code line coverage rate indicates the proportion of executed code in the actual application process of the cost analysis algorithm data model, the function coverage rate indicates the proportion of tested functions in the actual application process of the cost analysis algorithm data model, the condition coverage rate indicates the proportion of tested conditional branches in the actual application process of the cost analysis algorithm data model, and the path coverage rate indicates the proportion of tested execution paths in the actual application process of the cost analysis algorithm data model; obtain the unit test indicators of the cost analysis algorithm data model according to the obtained unit coverage rate, and the unit test indicators are calculated using the following formula:

[0039] ;

[0040] In the formula, e is a natural constant, n represents the number of the sub-cost algorithm model, , is the total number of sub-cost algorithm models, For unit test indicators, is the code line coverage of the nth sub-cost algorithm model, is the function coverage of the nth sub-cost algorithm model, is the condition coverage of the nth sub-cost algorithm model, is the path coverage of the nth sub-cost algorithm model.

[0041] In this embodiment, the statistical table of changes in unit test indicators is shown in Table 1:

[0042] Table 1 Statistics of changes in unit test indicators

[0043]

[0044] It can be seen from the above table that unit test indicators cannot be directly obtained through single data, but need to be obtained through comprehensive analysis of code line coverage, function coverage, condition coverage and path coverage. For example, the path coverage of the second group of data is greater than the path coverage in the third group of data, but the final unit test indicators of the second group are smaller than those of the third group, because code line coverage, function coverage and condition coverage also have an impact, so a comprehensive analysis is required; the actual working conditions of the sub-cost algorithm model in the cost analysis algorithm data model are digitized, which further improves the accuracy of port production cost accounting.

[0045] It is important to understand that ideally, we want to achieve a high line coverage of code, but not all uncovered lines are problems; some may be unused code or exception handling paths; function coverage ensures that all important functions or methods are tested; condition coverage is used to ensure that the code behaves correctly under different conditions; path coverage is used to measure whether all possible execution paths are tested.

[0046] Furthermore, the specific method for obtaining the performance test index is as follows: obtain the corresponding performance test data from the actual application process of the cost analysis algorithm data model, the performance test data includes response time, processing speed and pressure assessment rate, the pressure assessment rate indicates the cost analysis capability of the cost analysis algorithm data model for a unified process when the actual production operation of the port is saturated; obtain the performance test coefficient according to the obtained performance test data, the performance test coefficient includes the response time coefficient and the processing speed coefficient; the response time coefficient is the ratio of the response time to the corresponding reference deviation and the absolute value of the corresponding reference value difference, and the processing speed coefficient is the ratio of the processing speed to the corresponding reference deviation and the absolute value of the corresponding reference value difference; obtain the performance test index of the cost analysis algorithm data model according to the obtained performance test coefficient and pressure assessment rate, and the performance test index is calculated using the following formula:

[0047] ;

[0048] In the formula, e is a natural constant, m represents the number of the cost analysis algorithm data model, , M is the total number of cost analysis algorithm data models, is the performance test index of the mth cost analysis algorithm data model, is the response time coefficient of the mth cost analysis algorithm data model, is the processing speed coefficient of the mth cost analysis algorithm data model, is the stress assessment rate of the mth cost analysis algorithm data model.

[0049] In this embodiment, the expression of the response time coefficient is: ,in, is the response time of the mth cost analysis algorithm data model, is the reference response time of the mth cost analysis algorithm data model, is the response time reference deviation; the expression of the processing speed coefficient is ,in, is the processing speed of the mth cost analysis algorithm data model, is the reference processing speed of the mth cost analysis algorithm data model, To handle speed reference deviation; the performance of the cost analysis algorithm data model is digitized, further improving the accuracy of port production cost accounting.

[0050] It should be understood that the reference response time is obtained by analyzing and counting the response time of the cost analysis algorithm data model and taking the average value, and the reference processing speed is obtained by analyzing and counting the processing speed of the cost analysis algorithm data model and taking the average value; the response time reference deviation is obtained by analyzing and counting the response time of the cost analysis algorithm data model through the reference deviation calculation formula, and the processing speed reference deviation is obtained by analyzing and counting the processing speed of the cost analysis algorithm data model through the reference deviation calculation formula.

[0051] Furthermore, the optimization method of model tuning is: using correlation analysis to remove the sub-classification cost characteristics of the port to be accounted for; obtaining the model parameters to be optimized based on the data model evaluation results of the cost analysis algorithm data model, and initializing the Bayesian optimizer, and using the initialized Bayesian optimizer to search for the optimal parameter combination in the parameter space; using the iterative tuning method to evaluate the searched optimal parameter combination to obtain the target model performance, the target model performance is used to measure the degree of adaptation between the optimal parameter combination and the preset performance production cost accuracy evaluation index, the target model performance is input into the cost analysis algorithm data model to re-evaluate the production cost accuracy, and optimize according to the results of the production cost accuracy evaluation until the model production cost accuracy meets the preset requirements.

[0052] In this embodiment, sub-classification cost features are used to reduce the complexity of accounting and the risk of overfitting. The sub-classification cost features include low correlation and redundancy. Low correlation means that the correlation of the classification cost features is lower than the average correlation. Initialization means updating the probability model of the Bayesian optimizer according to historical evaluation results. The parameter space is used to identify and determine the area where the optimal parameter combination is located. This realizes the precise tuning of the cost analysis algorithm data model, further improving the accuracy of port production cost accounting.

[0053] Furthermore, the specific process of obtaining production cost accounting data is as follows: obtaining the power consumption data of the port to be accounted for from the established automatic power consumption collection system for operating equipment, and using the production cost accounting system to extract initial production cost accounting data from the power consumption data; according to the preset requirements for production cost accounting by preset personnel, the fields in the initial production cost accounting data are split into different time intervals and data conversion is performed to obtain production cost accounting data.

[0054] In this embodiment, data conversion includes structural conversion and row-column conversion. Structural conversion means converting the split fields into a cost accounting format. The cost accounting format is a pattern recognized by the cost analysis algorithm data model. Row-column conversion means transforming the rows and columns of the split fields. This improves the data quality of the acquired production cost accounting data and further improves the accuracy of port production cost accounting.

[0055] Furthermore, the specific steps for obtaining the production cost accounting indicators include: classifying the obtained production cost accounting data according to the cost relationship standard to obtain direct production cost accounting data and indirect production cost accounting data, and the cost relationship standard includes direct cost and indirect cost; directly classifying the direct cost accounting data, and indirectly allocating the indirect production cost accounting data, and at the same time combining the cost analysis algorithm data model to obtain the production cost accounting data of the production operation sub-process of the port to be accounted for, direct classification means classifying the direct production cost accounting data into the production operation sub-process of the port production operation of the port to be accounted for, and indirect allocation means allocating the indirect production cost accounting data into the production operation sub-process according to a preset ratio, and the production operation sub-process includes cargo classification process, ship classification process and operation classification process, and the production cost accounting data includes production electricity consumption and production fuel consumption; obtaining the production cost accounting indicators of the port to be accounted for according to the obtained production cost accounting data.

[0056] In this embodiment, the production cost accounting index is calculated using the following formula:

[0057] ;

[0058] In the formula, e is a natural constant, f represents the number of the port to be calculated, , F is the total number of ports to be calculated, is the production cost accounting index of the fth port to be accounted for, is the production power consumption of the cargo sorting process of the fth port to be calculated, is the production power consumption of the ship sorting process of the fth port to be calculated, is the production power consumption of the sub-operation process of the fth port to be calculated, is the production fuel consumption of the cargo classification process of the fth port to be calculated, is the production fuel consumption of the ship dispatching process of the fth port to be calculated, is the production fuel consumption of the sub-operation process of the f-th port to be accounted for.

[0059] Specifically, the total production power consumption is defined as , total production fuel consumption , then the production cost accounting index can be simplified as: ,like Figure 4 As shown, it is a statistical chart of the changes in the production cost accounting indicators provided in the embodiment of the present application. It can be seen from the figure that the total production power consumption and the total production oil consumption are positively correlated with the production cost accounting indicators; when the total production power consumption increases, the larger the production cost accounting indicator, the higher the production cost of the port to be accounted for; when the total production oil consumption increases, the larger the production cost accounting indicator, the higher the production cost of the port to be accounted for; the digitization of the production cost situation of the port to be accounted for is realized, and the accuracy of the port production cost accounting is further improved.

[0060] It should be understood that the total production electricity consumption is the proportion of production electricity consumption in the process of port production operations in all production costs, and the total production oil consumption is the proportion of production oil consumption in the process of port production operations in all production costs; both production electricity consumption and production oil consumption are measured uniformly through prices.

[0061] To summarize, the embodiment of the present application obtains a process classification number set by performing process classification on the acquired initial port operation data, then constructs a cost analysis algorithm data model based on the obtained process classification number set, then performs model evaluation and optimization on the cost analysis algorithm data model, and finally calculates the production cost of the port to be accounted for based on the production cost accounting data obtained by data processing and shaping and combines it with the cost analysis algorithm data model to obtain production cost accounting indicators to determine whether the production cost of the port to be accounted meets the standards, thereby accurately calculating the production cost of the port to be accounted, thereby achieving an improvement in the accuracy of port production cost accounting, and effectively solving the problem of inaccurate port production cost accounting in the prior art.

[0062] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A production cost accounting method based on port big data, characterized in that: The following steps are involved: S1, collecting the initial port operation data of the port to be calculated, wherein the initial port operation data is obtained through the production business system; S2, classifying the initial port operation data according to the production operation process to obtain a process classification number set, wherein the process classification number set includes a cargo type number set, a ship type number set and an operation type number set; S3, constructing a corresponding sub-cost algorithm model according to the obtained process classification data set, and integrating the constructed sub-cost algorithm model into a cost analysis algorithm data model; S4, performing a model evaluation on the integrated cost analysis algorithm data model to obtain a data model evaluation result, and performing model tuning on the cost analysis algorithm data model according to the data model evaluation result, wherein the data model evaluation result is used to describe the production cost accuracy of the cost analysis algorithm data model; S5, processing and shaping the initial production cost accounting data extracted from the power consumption data of the port to be accounted for to obtain production cost accounting data, and at the same time, combining the cost analysis algorithm data model to calculate the production cost of the port to be accounted for to obtain a production cost accounting index, and judging whether the production cost of the port to be accounted for meets the standard according to the production cost accounting index; The specific method for obtaining the data model evaluation result is as follows: Performing unit testing on the sub-cost algorithm model in the cost analysis algorithm data model to obtain unit test indicators, and comparing the unit test indicators with preset threshold conditions to obtain unit test results, wherein the unit test indicators are used to describe the actual working conditions of the sub-cost algorithm model in the cost analysis algorithm data model; Performing a performance test on a sub-cost algorithm model in the cost analysis algorithm data model to obtain a performance test index, and comparing the performance test index with a preset threshold condition to obtain a performance test result, wherein the performance test index is used to describe the performance of the cost analysis algorithm data model; The data model evaluation results include unit test results and performance test results; The specific method for obtaining the unit test indicators is as follows: Obtain unit coverage from the actual application process of the cost analysis algorithm data model, wherein the unit coverage includes code line coverage, function coverage, condition coverage, and path coverage; The unit test index of the cost analysis algorithm data model is obtained according to the obtained unit coverage, and the unit test index is calculated using the following formula: ; In the formula, e is a natural constant, n represents the number of the sub-cost algorithm model, , is the total number of sub-cost algorithm models, For unit test indicators, is the code line coverage of the nth sub-cost algorithm model, is the function coverage of the nth sub-cost algorithm model, is the condition coverage of the nth sub-cost algorithm model, is the path coverage of the nth sub-cost algorithm model; The specific method for obtaining the performance test indicators is as follows: Acquire corresponding performance test data from the actual application process of the cost analysis algorithm data model, wherein the performance test data includes response time, processing speed and stress assessment rate; Acquire a performance test coefficient according to the acquired performance test data, wherein the performance test coefficient includes a response time coefficient and a processing speed coefficient; The performance test index of the cost analysis algorithm data model is obtained according to the obtained performance test coefficient and pressure assessment rate. The performance test index is calculated using the following formula: ; In the formula, e is a natural constant, m represents the number of the cost analysis algorithm data model, , M is the total number of cost analysis algorithm data models, is the performance test index of the mth cost analysis algorithm data model, is the response time coefficient of the mth cost analysis algorithm data model, is the processing speed coefficient of the mth cost analysis algorithm data model, is the stress assessment rate of the mth cost analysis algorithm data model.

2. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The specific steps of the process classification are as follows: Formulate process classification standards according to the production operation process, wherein the process classification standards include cargo classification standards, ship classification standards and operation classification standards, and pre-process the collected initial port operation data to obtain port operation data; According to the established process classification standards, the pre-processed port operation data is automatically classified and the classified port operation data is marked. The classified port operation data is organized according to the production operation process to construct a process classification data set, and the constructed process classification data set is managed; At the same time, the constructed process classification data set is output as a visual chart.

3. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The specific construction steps of the sub-cost algorithm model are as follows: Step 1, extracting a classification cost feature set from the acquired process classification data set; Step 2, feature encoding the extracted classification cost feature set to obtain a classification cost feature encoding set; Step three, divide the obtained classification cost feature coding set into corresponding training set, validation set and test set, use the training set to train the data model to obtain the data training model, use the validation set to validate the data training model to obtain the data validation model, use the test set to test the data validation model to obtain the test result, if the corresponding threshold condition is met, the sub-cost algorithm model is obtained, otherwise execute step one.

4. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The integration steps of the cost analysis algorithm data model are: The data interface between the sub-cost algorithm model and the cost analysis algorithm data model is constructed according to the flow direction of the data in the process classification data set, and the cost analysis algorithm data model is integrated by calling the data interface of the sub-cost algorithm model.

5. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The optimization method of the model tuning is: Use correlation analysis to remove sub-classified cost features of ports to be accounted for; The model parameters to be optimized are obtained according to the data model evaluation results of the cost analysis algorithm data model, and the Bayesian optimizer is initialized. At the same time, the initialized Bayesian optimizer is used to search for the optimal parameter combination in the parameter space; The searched optimal parameter combination is evaluated using an iterative tuning method to obtain the target model performance, which is used to measure the degree of fit between the optimal parameter combination and the preset performance production cost accuracy evaluation index. The target model performance is input into the cost analysis algorithm data model to re-evaluate the production cost accuracy, and optimized according to the results of the production cost accuracy evaluation until the model production cost accuracy meets the preset requirements.

6. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The specific process of obtaining the production cost accounting data is as follows: Obtain the power consumption data of the port to be calculated from the established automatic power consumption collection system for operating equipment, and use the production cost accounting system to extract initial production cost accounting data from the power consumption data; According to the preset requirements of the preset personnel for production cost accounting, the fields in the initial production cost accounting data are split into different time intervals and data conversion is performed to obtain the production cost accounting data.

7. A production cost accounting method based on port big data as claimed in claim 1, characterized in that: The specific steps for obtaining the production cost accounting index include: The acquired production cost accounting data is classified according to the cost relationship standard to obtain direct production cost accounting data and indirect production cost accounting data; Directly classify the direct cost accounting data and indirectly allocate the indirect production cost accounting data, and at the same time, combine the cost analysis algorithm data model to obtain the production cost accounting data of the production operation sub-process of the port to be accounted; The production cost accounting indicators of the port to be accounted are obtained based on the obtained production cost accounting data.