A ship fire-fighting and life-saving detection and quotation automation system

By combining data acquisition, AI review and analysis, and quotation optimization modules, the problem of quotation deviation in the ship fire-fighting and life-saving inspection quotation system has been solved, realizing an intelligent and standardized quotation process and improving the work efficiency and accuracy of inspection agencies.

CN122509985APending Publication Date: 2026-08-04SMART CHAIN TECHNOLOGY (ZHENJIANG) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610510155.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-17
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

The existing ship fire-fighting and life-saving inspection pricing system lacks in-depth mining and analysis capabilities, resulting in frequent pricing deviations. It cannot meet the needs of inspection agencies for pricing review and optimization and risk control, nor can it adapt to the needs of scenarios with complex inspection items and frequent price fluctuations.

Method used

It employs a data acquisition module, an AI review and analysis module, a deviation warning module, and a pricing optimization module. Through AI algorithms, it analyzes historical pricing data, identifies the causes of deviations and generates analysis results, sets multi-dimensional deviation warning thresholds, and compares new pricing with historical pricing, real-time costs, and regulatory requirements to generate the optimal pricing recommendation.

Benefits of technology

It has achieved intelligent and standardized pricing across the entire process, reducing manual labor, improving pricing accuracy and work efficiency, minimizing deviations, and enhancing the business competitiveness and compliance of testing institutions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122509985A_ABST
    Figure CN122509985A_ABST
Patent Text Reader

Abstract

The application discloses a kind of ship fire fighting lifesaving detection quotation automation system, it is related to automatic quotation technical field, comprising: data acquisition module, for collecting various data of ship fire fighting lifesaving detection, various data include historical quotation data, transaction result data, actual cost data, regulatory requirement data and real-time cost data, are integrated into data set after preprocessing;AI review analysis module, obtain data in data set, analyze historical quotation data based on AI review algorithm, judge deviation reason and classify, generate analysis result.The application analyzes historical quotation by AI algorithm, identifies and generates analysis result by classifying deviation reason;Replace the cumbersome process of traditional manual review, not only greatly reduce the work intensity of detection personnel, but also accurately locate the short board of quotation, provide scientific basis for detection organization to continuously optimize quotation strategy, reduce repeated deviation, improve work efficiency, promote the standardized development of industry.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of automated pricing technology, specifically to an automated pricing system for ship fire-fighting and life-saving detection. Background Technology

[0002] Ship fire and lifesaving inspections are a crucial aspect of ensuring safe navigation. The inspection items are complex, covering multiple categories such as fire extinguishers, fire hydrants, lifeboats, life rafts, and alarm systems. Furthermore, the inspection standards and items vary significantly between different types of vessels (small yachts, coastal cargo ships, and ocean-going cruise ships), leading to frequent price fluctuations due to various factors. Simultaneously, ship inspection quotes must strictly adhere to relevant regulatory requirements and the pricing rules of electronic bidding and procurement platforms; the accuracy of the quote directly impacts the business competitiveness and compliance of the inspection agency.

[0003] Currently, most existing ship inspection quotation systems focus on "recording historical quotations," offering only basic storage and retrieval of quotation data, lacking the ability to deeply mine and analyze this data. In practical applications, inspection agencies often rely on manual experience to estimate labor costs, material costs, and equipment depreciation when submitting quotations, which easily leads to quotation deviations, and the reasons for these deviations cannot be identified in a timely manner. Furthermore, there is a lack of effective early warning mechanisms regarding the rationality and compliance of new quotations. This often results in new quotations deviating significantly from similar historical quotations, failing to meet real-time cost levels, or violating the quotation rules of electronic bidding and procurement platforms (such as unit price control prices and quotation discount rate requirements). This leads to invalid quotations, missed business opportunities, or losses due to excessively high quotations that make the company uncompetitive, or excessively low quotations that result in losses.

[0004] Furthermore, existing pricing systems are not customized for the specific needs of ship fire-fighting and life-saving inspections, failing to meet the demands of scenarios with complex inspection items and frequent price fluctuations. This makes it difficult to satisfy the actual needs of inspection agencies for price review and optimization, and risk control. To address this, we propose an automated pricing system for ship fire-fighting and life-saving inspections. Summary of the Invention

[0005] To address the aforementioned technical issues, an automated pricing system for ship fire-fighting and life-saving inspections is provided. This technical solution resolves the problem of failing to meet the requirements of inspection agencies for pricing review and optimization, as well as risk control.

[0006] To achieve the above objectives, the technical solution adopted by this invention is: an automated system for quoting and monitoring ship firefighting and lifesaving operations, comprising: The data acquisition module is used to collect various types of data from ship fire-fighting and life-saving inspections. These data include historical price data, transaction result data, actual cost data, regulatory requirement data, and real-time cost data. After preprocessing, the data is integrated into a dataset. The AI ​​retrospective analysis module acquires data from the dataset, analyzes historical pricing data based on AI retrospective algorithms, identifies and categorizes the causes of deviations, and generates analysis results. The deviation warning module, based on the analysis results combined with real-time cost data and regulatory requirement data, presets multi-dimensional deviation warning thresholds. The warning thresholds include the deviation threshold for similar historical quotations, the real-time cost deviation threshold, and the regulatory compliance threshold. When the testing personnel enter a new quotation, the new quotation is compared with similar historical quotations, real-time costs, and regulatory requirements in real time. If the deviation between the new quotation and similar historical quotations exceeds the preset deviation threshold, or if there is an unreasonable deviation from the real-time cost, or if it violates regulatory requirements, an warning signal will be automatically issued. The pricing optimization module, based on early warning signals, performs multi-scenario analysis on the current deviation pricing to generate the optimal pricing suggestion; The interactive module visually displays the current best price suggestion for testing personnel to view.

[0007] Preferably, the steps for analyzing historical pricing data based on the AI ​​retrospective analysis algorithm within the AI ​​retrospective analysis module are as follows: The data in the dataset is retrieved and normalized to obtain a standardized feature dataset; Based on a standardized dataset, the deviation value corresponding to historical price data is calculated. The deviation value calculation adopts a dual accounting method, and the dual accounting formula is as follows: Absolute deviation = |Historical quoted amount - Actual transaction price|; Relative deviation = (Absolute deviation / Actual transaction price) × 100%; By combining actual cost data, the deviation between historical quotations and actual total costs is calculated to help determine the reasonableness of the deviation and form a deviation dataset, which includes three indicators: absolute deviation, relative deviation, and cost deviation.

[0008] Preferably, the steps for determining and classifying the causes of deviations and generating analysis results are as follows: Based on the deviation dataset, the causes of deviations are identified and classified using a random forest classification model. The classification dimensions of deviation causes are set, including deviations in labor cost estimation, cost deviations caused by material price fluctuations, quotation deviations caused by insufficient adaptation between ship type and inspection scenario, and deviations caused by unreasonable allocation of equipment loss. After training the model, feature matching is performed to match the deviation data of each historical quote with the preset deviation category and perform classification and labeling. The results of the deviation cause classification and labeling are compared and verified with the actual detection scenario data to calculate the accuracy of deviation cause identification; if the accuracy is lower than 90%, the model is retrained and the feature weights are redistributed. Integrate the deviation dataset with the deviation cause classification and annotation results to generate standardized analysis results; The analysis results are output to the deviation warning module in a structured format.

[0009] Preferably, the deviation threshold for historical quotations of the same type is determined by statistically analyzing historical quotation data of the same type of ships and the same type of inspection items, calculating the mean and standard deviation of the quotation distribution, and taking the mean ± k times the standard deviation, where k is selected based on the risk level and is chosen to be 1.5-2.0, as the deviation threshold for historical quotations of the same type. The real-time cost deviation threshold is based on actual cost data. The real-time cost deviation threshold is set, the deviation range between historical quotations and real-time total cost is calculated, and the upper and lower limits of cost deviation are determined. When the quotation is lower than the lower limit of real-time total cost or higher than the upper limit of real-time total cost, it is determined that there is an unreasonable deviation in real-time cost. The upper and lower limit values ​​are the real-time cost deviation thresholds. The regulatory compliance threshold is based on regulatory requirements to extract compliance constraints, including unit price control requirements, price discount rate range and minimum price for testing items. These compliance constraints are then converted into quantitative thresholds. The acquired thresholds are integrated to construct a multi-dimensional deviation early warning threshold.

[0010] Preferably, real-time comparison involves comparing the current new quote with similar historical quotes and calculating the relative deviation between them. The calculation formula is as follows: Relative deviation = |New quote amount - Average historical quote of similar products| / Average historical quote of similar products × 100%; The calculated relative deviation value is compared with a preset historical price deviation threshold for the same type to determine whether it exceeds the threshold range; Retrieve the real-time cost data corresponding to the new quote, calculate the real-time total cost of the current quote item, calculate the cost deviation between the new quote amount and the real-time total cost, compare the cost deviation with the preset real-time cost deviation threshold, and determine whether there is an unreasonable deviation between the new quote and the real-time cost. Obtain current regulatory requirements data, compare new pricing information with regulatory compliance thresholds, and determine whether there is a violation of regulatory requirements.

[0011] Preferably, the real-time comparison results are summarized and a warning is determined. If any comparison result meets the warning triggering condition, it is determined that a warning needs to be triggered; if all three comparison results meet the compliance requirements, it is determined that no warning needs to be triggered; a corresponding warning signal is generated and transmitted to the quotation optimization module.

[0012] The preferred multi-scheme derivation steps are as follows: Upon receiving an early warning signal, the pricing optimization module constructs a pricing optimization simulation model, sets simulation parameters, and takes compliance, rationality, and economy as core objectives. Input parameters include real-time cost details, historical pricing distribution of similar bids, and regulatory compliance thresholds. Several differentiated optimization schemes are preset, each with a different optimization focus, specifically including: Based on historical quotes of similar types, and using the best historical quotes and deviation distribution of similar types as the core, the current quote amount is adjusted to keep the quote amount within a preset threshold. With matching real-time costs as the core, optimize the allocation ratio of labor, material, and equipment losses, and calculate the quotation range; To meet regulatory compliance requirements and adapt to bidding rules, the unit price of the quotation was adjusted accordingly. Each of the pre-set optimization schemes is verified, including compliance verification, rationality verification, and economic verification. After verification, the data is output to the interactive module in a structured format.

[0013] Preferably, the compliance verification involves: determining whether the proposed price meets regulatory compliance thresholds and bidding rules; Reasonableness verification involves determining whether the deviation between the proposed price and similar historical prices and real-time costs is within the allowable range. The economic verification process involves: determining whether the quoted price of the proposed solution can cover the real-time cost and ensure a reasonable profit margin for the testing organization; eliminating solutions that do not meet the verification requirements; scoring the remaining feasible solutions on their feasibility; and selecting the top 2-3 candidate solutions based on their scores.

[0014] Preferably, the data acquisition module obtains various types of data by connecting to the ship fire-fighting and life-saving inspection and management system through interfaces to acquire historical quotation data, transaction result data, and actual cost data; it also captures regulatory requirement data and real-time cost data in real time by connecting to the industry supervision platform; the preprocessing includes data cleaning, data correction, and data integration.

[0015] Preferably, the interactive module adopts a structured display method to present the best quotation suggestion information and displays the details of the quotation in the form of charts.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention analyzes historical quotations using AI algorithms, identifies the causes of classification deviations, and generates analysis results. Replacing the tedious process of traditional manual review, it significantly reduces the workload of testing personnel and accurately identifies quotation shortcomings. This provides a scientific basis for testing institutions to continuously optimize their quotation strategies and reduce recurring deviations. It presets multi-dimensional thresholds for real-time comparison of new quotations, and the quotation optimization module generates optimal quotation suggestions based on early warning signals. This achieves intelligent and standardized quoting throughout the entire process, improving data quality and quotation accuracy, reducing manual labor and quotation error rates, increasing work efficiency, and promoting the standardized development of the industry. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system framework of the present invention. Detailed Implementation

[0018] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0019] Reference Figure 1 As shown, an automated system for quoting ship fire-fighting and life-saving detection includes: The data acquisition module is used to collect various types of data from ship fire-fighting and life-saving inspections. These data include historical price data, transaction result data, actual cost data, regulatory requirement data, and real-time cost data. After preprocessing, the data is integrated into a dataset. A multi-interface collaborative data acquisition mode is adopted. It connects to the ship fire-fighting and life-saving inspection management system via Ethernet interface to selectively acquire historical quotation data, transaction result data, and actual cost data stored in the system. The historical quotation data covers detailed quotations for different ship types and inspection items over the past three years. It connects to the industry regulatory platform via API interface to capture real-time regulatory requirements and cost data related to ship fire-fighting and life-saving inspections. Real-time cost data includes current labor costs, unit prices of inspection materials, and depreciation costs of inspection equipment. Simultaneously, a manual data entry interface is reserved for sporadic data from special scenarios such as inspections of older ships, allowing inspection personnel to manually supplement and enter data to ensure data integrity. Data preprocessing implementation: Standardize and preprocess the collected raw data. Specific steps include: Data cleaning: The 3σ principle is used to remove data containing missing key information, logical contradictions, and outliers; Data correction: Standardize and correct data with inconsistent formats, unify the data format to YYYY-MM-DD and the monetary unit to "yuan", and eliminate differences in units; Data integration: The preprocessed data is classified and organized according to ship type and inspection items to build a structured and standardized dataset, which is then stored in the system's built-in MySQL database for subsequent modules to access.

[0020] The AI ​​retrospective analysis module acquires data from the dataset, analyzes historical pricing data based on AI retrospective algorithms, identifies and categorizes the causes of deviations, and generates analysis results. Specifically, the process involves calling historical price data, transaction result data, and actual cost data from a standardized dataset, performing correlation matching on the three types of data, extracting key feature parameters such as historical price amount, actual transaction price, and actual total cost, and using the Min-Max normalization method to map the feature parameters to the [0, 1] interval to obtain a standardized feature dataset, thereby eliminating the impact of dimensional differences on the accuracy of algorithm analysis. Deviation value calculation, based on a standardized feature dataset, employs a dual-calculation method to calculate the deviation value corresponding to each historical price data point. The specific formula is as follows: Absolute deviation = |Historical quoted amount - Actual transaction price|; Relative deviation = (Absolute deviation / Actual transaction price) × 100%; At the same time, by combining actual cost data, the cost deviation between historical quotations and actual total costs is calculated, forming a deviation dataset containing three core indicators: absolute deviation, relative deviation, and cost deviation. Deviation cause identification and classification: Based on the deviation dataset, a random forest classification model is used to identify and classify the causes of deviations. Four categories of deviation causes are preset: deviations in labor cost estimation, cost deviations due to material price fluctuations, pricing deviations due to insufficient adaptation between ship type and testing scenario, and deviations due to unreasonable allocation of equipment wear and tear. The random forest classification model is trained using historical data from the past three years. After training, the deviation data of each historical quotation is matched with the preset deviation categories through feature matching to complete the classification and labeling of deviation causes. Model validation and optimization involves comparing the classification and labeling results of deviation causes with the actual detection scenario data to verify the accuracy of deviation cause identification. If the accuracy is lower than 90%, the random forest classification model is automatically retrained using newly added historical data to optimize feature weight allocation until the accuracy reaches 90% or higher. The analysis results are generated and output by integrating the deviation dataset and the deviation cause classification and labeling results to generate standardized analysis results. The analysis results include historical price deviation statistics, the proportion of various deviation causes, and deviation characteristics of different ship types / inspection items. The analysis results are output to the deviation early warning module in JSON structured format and stored in a MySQL database for subsequent review and traceability.

[0021] The deviation warning module, based on the analysis results combined with real-time cost data and regulatory requirement data, presets multi-dimensional deviation warning thresholds. The warning thresholds include the deviation threshold for similar historical quotations, the real-time cost deviation threshold, and the regulatory compliance threshold. When the testing personnel enter a new quotation, the new quotation is compared with similar historical quotations, real-time costs, and regulatory requirements in real time. If the deviation between the new quotation and similar historical quotations exceeds the preset deviation threshold, or if there is an unreasonable deviation from the real-time cost, or if it violates regulatory requirements, an warning signal will be automatically issued. The historical price deviation threshold for similar items is determined by statistically analyzing historical price data for similar types of vessels and similar testing items, calculating the mean and standard deviation of the price distribution, selecting a k value of 1.8, and using the mean ± 1.8 times the standard deviation as the historical price deviation threshold for similar items. The historical price mean for testing fire extinguishers on small yachts is 1200 yuan, and the standard deviation is 100 yuan. Therefore, the historical price deviation threshold for similar items is 1200 ± 180 yuan, which is 1020 yuan - 1380 yuan. The real-time cost deviation threshold is determined by statistically analyzing the deviation range between historical quotations and the real-time total cost based on actual cost data. Quotations below 5% or above 20% of the real-time total cost are considered unreasonable deviations, and the corresponding upper and lower limits are the real-time cost deviation thresholds. For example, if the real-time total cost of a certain testing project is 1000 yuan, then the lower limit of the real-time cost deviation threshold is 950 yuan, and the upper limit is 1200 yuan. Regulatory compliance thresholds are derived from industry regulatory requirements and electronic bidding and procurement platform rules. Compliance constraints are extracted, including unit price control requirements, price discount rate range, and minimum price limit for testing items. These constraints are then converted into quantifiable regulatory compliance thresholds. Threshold integration integrates the above three types of thresholds to construct a multi-dimensional deviation early warning threshold system, which is stored in the system database to support testing personnel in adjusting threshold parameters according to market environment and regulatory policies; The steps for real-time comparison and early warning determination of new quotes are as follows: Inspectors input new quotation information through the interactive module, including vessel type, inspection items, and quotation amount; the system simultaneously calls up corresponding historical quotation data, real-time cost data, and regulatory requirement data in the standardized dataset; Comparison with historical quotes of similar types: Calculate the relative deviation between the new quote and the average of historical quotes of similar types. The calculation formula is: Relative deviation = |New quote amount - Average of historical quotes of similar types| / Average of historical quotes of similar types × 100%; Compare the calculation result with the deviation threshold of historical quotes of similar types to determine whether it exceeds the threshold range. Real-time cost comparison: retrieve the real-time cost data corresponding to the new quote, calculate the real-time total cost of the testing project, calculate the cost deviation between the new quote and the real-time total cost, compare it with the preset real-time cost deviation threshold, and determine whether there is any unreasonable deviation. Regulatory requirement comparison: The new quotation information is compared with the regulatory compliance thresholds item by item to determine whether the new quotation meets the constraints such as unit price control, quotation discount rate, and minimum quotation. Warning determination: Summarize the results of the above three comparisons. If any one of them meets the warning triggering conditions, it is determined that a warning needs to be triggered; if all three are compliant, it is determined that no warning needs to be triggered; a corresponding graded warning signal is generated and transmitted to the quotation optimization module.

[0022] The pricing optimization module, based on early warning signals, performs multi-scenario analysis on the current deviation pricing to generate the optimal pricing suggestion; Multi-scheme simulation and implementation steps: Data loading: Receives warning signals from the deviation warning module, extracts the warning cause and deviation value, and simultaneously calls up real-time cost details, historical price distribution of similar products, and regulatory compliance threshold parameters from the standardized dataset; Model Construction and Parameter Setting: Construct a pricing optimization simulation model with compliance, rationality, and economy as core objectives. Input parameters include real-time cost details, distribution of similar historical pricing, and regulatory compliance thresholds. Three sets of differentiated optimization schemes are preset. Option 1 takes historical quotations for contract-related products as the core, refers to the best historical quotations and deviation distribution of similar products, adjusts the current quotation amount, and ensures that the deviation from historical quotations of similar products is controlled within a preset threshold. Option 2 focuses on matching real-time costs, optimizing the allocation ratio of labor, materials, and equipment losses (e.g., adjusting the equipment loss allocation ratio from 10% to 8%), and calculating a reasonable price range. Option 3 focuses on meeting regulatory compliance, adapting to regulatory requirements and bidding rules, adjusting the unit price and discount rate of the quotation, and ensuring that the quotation is compliant. Solution Validation: Perform three validations on each of the three optimization solutions: Compliance verification: Determine whether the proposed price meets regulatory compliance thresholds and bidding rules; Reasonableness verification: Determine whether the deviation between the proposed price and similar historical prices and real-time costs is within the allowable range; Economic feasibility verification: Determine whether the quoted price of the proposed solution can cover the real-time cost and ensure a reasonable profit margin for the testing agency; eliminate solutions that do not meet the verification requirements, and score the remaining feasible solutions on a feasibility basis with a weight of 40% for compliance, 30% for rationality, and 30% for economy, and select the top two groups of optimal candidate solutions. The formula for calculating the feasibility score is as follows: Feasibility score = Compliance score 40%+ Reasonableness Score 30%+ economic score 30%; We conduct three checks: compliance, rationality, and economy. If any one of them fails, the product is immediately rejected. Suggestion generation and output: Optimize the best candidate solutions in detail, determine one set of optimal pricing suggestions, and clarify the optimal pricing amount, pricing details, cost allocation method and compliance basis; output the optimal pricing suggestions to the interaction module in a structured format.

[0023] The interactive module visually displays the current best price suggestion for testing personnel to view; The interactive module adopts a web-based interface design, supports login and use on a computer, and presents the best quotation suggestions in a structured display manner. It uses a pie chart to show the distribution of labor costs, material costs, and equipment depreciation costs in the quotation details, and uses a table to clearly list the quotation amount, cost details, optimization basis, and compliance verification results. The best quotation amount and compliance verification results are highlighted to facilitate testing personnel to quickly grasp key information. Meanwhile, the interactive module allows testing personnel to click and view the detailed calculation process of the quotation details, similar historical quotation data, and specific clauses of regulatory requirements, enabling traceability of quotation suggestions; it also supports exporting the best quotation suggestion as a standardized PDF document for easy archiving and reporting; based on the displayed information, testing personnel can directly modify the quotation parameters in the interactive module, and after modification, the system will automatically re-trigger the comparison, warning, and optimization process to achieve a closed-loop operation of quotation adjustment.

[0024] Specific Implementation Cases Taking the pricing of fire hydrant inspection on a coastal cargo ship as an example, the complete operation process of the system is explained: The data acquisition module connects to the testing and management system via an interface to obtain historical price data (mean 1500 yuan, standard deviation 100 yuan), transaction result data, and actual cost data for this type of cargo ship fire hydrant testing; it also connects to the industry regulatory platform to obtain real-time cost data (real-time total cost 1400 yuan) and regulatory requirements (unit price not exceeding 1800 yuan, discount rate not less than 85%), and integrates them into a standardized dataset after preprocessing. The AI ​​retrospective analysis module calls the dataset, performs normalization and deviation calculation to obtain a historical price deviation dataset; it then uses a random forest classification model to identify the causes of deviations, generates analysis results (the main deviation is material price fluctuations), and outputs them to the deviation warning module. The deviation warning module has preset thresholds: the historical price deviation threshold is 1500±180 yuan (1320-1680 yuan), the real-time cost deviation threshold is 1330-1680 yuan, and the regulatory compliance threshold is 1530-1800 yuan; the testing personnel can enter a new price of 1700 yuan. The deviation warning module performs real-time comparison: the new quote deviates from the historical quote of the same type by 3.33% (not exceeding the threshold) and from the real-time total cost by 7.14% (not exceeding the threshold), but exceeds the regulatory compliance threshold of 1680 yuan, triggering a warning warning and transmitting it to the quote optimization module; The pricing optimization module simulated three sets of solutions, and after verification and screening, generated the optimal pricing suggestion of 1680 yuan (which meets regulatory requirements and takes into account both cost and reasonableness), and output it to the interaction module. The interactive module uses pie charts and tables to visually display the details and optimization basis of the 1680 yuan quote. After the testing personnel review and confirm the quote, the quoting process is completed.

[0025] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. An automated system for quoting and detecting firefighting and lifesaving operations on ships, characterized in that, include: The data acquisition module is used to collect various types of data from ship fire-fighting and life-saving inspections. These data include historical price data, transaction result data, actual cost data, regulatory requirement data, and real-time cost data. After preprocessing, the data is integrated into a dataset. The AI ​​retrospective analysis module acquires data from the dataset, analyzes historical pricing data based on AI retrospective algorithms, identifies and categorizes the causes of deviations, and generates analysis results. The deviation warning module, based on the analysis results combined with real-time cost data and regulatory requirement data, presets multi-dimensional deviation warning thresholds. The warning thresholds include the deviation threshold for similar historical quotations, the real-time cost deviation threshold, and the regulatory compliance threshold. When the testing personnel enter a new quotation, the new quotation is compared with similar historical quotations, real-time costs, and regulatory requirements in real time. If the deviation between the new quotation and similar historical quotations exceeds the preset deviation threshold, or if there is an unreasonable deviation from the real-time cost, or if it violates regulatory requirements, an warning signal will be automatically issued. The pricing optimization module, based on early warning signals, performs multi-scenario analysis on the current deviation pricing to generate the optimal pricing suggestion; The interactive module visually displays the current best price suggestion for testing personnel to view.

2. The automated system for quoting and testing ship firefighting and lifesaving operations according to claim 1, characterized in that, The AI ​​retrospective analysis module analyzes historical pricing data using AI retrospective algorithms as follows: The data in the dataset is retrieved and normalized to obtain a standardized feature dataset; Based on a standardized dataset, the deviation value corresponding to historical price data is calculated. The deviation value calculation adopts a dual accounting method, and the dual accounting formula is as follows: Absolute deviation = |Historical quoted amount - Actual transaction price|; Relative deviation = (Absolute deviation / Actual transaction price) × 100%; By combining actual cost data, the deviation between historical quotations and actual total costs is calculated to help determine the reasonableness of the deviation and form a deviation dataset, which includes three indicators: absolute deviation, relative deviation, and cost deviation.

3. The automated system for ship firefighting, lifesaving detection, and quotation according to claim 1, characterized in that, The steps for determining and classifying the causes of deviations and generating analysis results are as follows: Based on the deviation dataset, the causes of deviations are identified and classified using a random forest classification model. The classification dimensions of deviation causes are set, including deviations in labor cost estimation, cost deviations caused by material price fluctuations, quotation deviations caused by insufficient adaptation between ship type and inspection scenario, and deviations caused by unreasonable allocation of equipment loss. After training the model, feature matching is performed to match the deviation data of each historical quote with the preset deviation category and perform classification and labeling. The results of the deviation cause classification and labeling are compared and verified with the actual detection scenario data to calculate the accuracy of deviation cause identification; if the accuracy is lower than 90%, the model is retrained and the feature weights are redistributed. Integrate the deviation dataset with the deviation cause classification and annotation results to generate standardized analysis results; The analysis results are output to the deviation warning module in a structured format.

4. The automated system for ship firefighting, lifesaving detection, and quotation according to claim 1, characterized in that, The threshold for deviation of historical quotations for the same type of vessel is determined by statistically analyzing historical quotation data for the same type of vessel and the same type of inspection items, calculating the mean and standard deviation of the quotation distribution, and taking the mean ± k times the standard deviation, where k is selected based on the risk level and is set to 1.5-2.0, as the threshold for deviation of historical quotations for the same type of vessel. The real-time cost deviation threshold is based on actual cost data. The real-time cost deviation threshold is set, the deviation range between historical quotations and real-time total cost is calculated, and the upper and lower limits of cost deviation are determined. When the quotation is lower than the lower limit of real-time total cost or higher than the upper limit of real-time total cost, it is determined that there is an unreasonable deviation in real-time cost. The upper and lower limit values ​​are the real-time cost deviation thresholds. The regulatory compliance threshold is based on regulatory requirements to extract compliance constraints, including unit price control requirements, price discount rate range and minimum price for testing items. These compliance constraints are then converted into quantitative thresholds. The acquired thresholds are integrated to construct a multi-dimensional deviation early warning threshold.

5. The automated system for ship firefighting, lifesaving, detection, and quotation according to claim 1, characterized in that: Real-time comparison compares the current new quote with similar historical quotes and calculates the relative deviation between them. The calculation formula is as follows: Relative deviation = |New quote amount - Average historical quote of similar products| / Average historical quote of similar products × 100%; The calculated relative deviation value is compared with a preset historical price deviation threshold for the same type to determine whether it exceeds the threshold range; Retrieve the real-time cost data corresponding to the new quote, calculate the real-time total cost of the current quote item, calculate the cost deviation between the new quote amount and the real-time total cost, compare the cost deviation with the preset real-time cost deviation threshold, and determine whether there is an unreasonable deviation between the new quote and the real-time cost. Obtain current regulatory requirements data, compare new pricing information with regulatory compliance thresholds, and determine whether there is a violation of regulatory requirements.

6. The automated system for ship firefighting, lifesaving, detection, and quotation according to claim 5, characterized in that: The real-time comparison results are summarized and an early warning is determined. If any comparison result meets the early warning triggering condition, it is determined that an early warning needs to be triggered. If all three comparison results meet the compliance requirements, it is determined that no warning needs to be triggered; The corresponding early warning signal is generated and transmitted to the quotation optimization module.

7. The automated system for quoting and testing ship firefighting and lifesaving operations according to claim 1, characterized in that, The steps for multi-scheme deduction are as follows: After receiving the warning signal, the pricing optimization module constructs a pricing optimization simulation model, sets simulation parameters, and takes compliance, rationality, and economy as the core objectives, and inputs real-time cost details, distribution of similar historical pricing, and regulatory compliance threshold parameters. Several sets of differentiated optimization schemes are preset, each with a different optimization focus, specifically including: Based on historical quotes of similar types, and using the best historical quotes and deviation distribution of similar types as the core, the current quote amount is adjusted to keep the quote amount within a preset threshold. With matching real-time costs as the core, optimize the allocation ratio of labor, material, and equipment losses, and calculate the quotation range; To meet regulatory compliance requirements and adapt to bidding rules, the unit price of the quotation was adjusted accordingly. Each of the pre-set optimization schemes is verified, including compliance verification, rationality verification, and economic verification. After verification, the data is output to the interactive module in a structured format.

8. The automated system for ship firefighting, lifesaving detection, and quotation according to claim 7, characterized in that, The compliance verification involves determining whether the proposed price meets regulatory compliance thresholds and bidding rules. Reasonableness verification involves determining whether the deviation between the proposed price and similar historical prices and real-time costs is within the allowable range. The economic verification process involves: determining whether the quoted price of the proposed solution can cover the real-time cost and ensure a reasonable profit margin for the testing organization; eliminating solutions that do not meet the verification requirements; scoring the remaining feasible solutions on their feasibility; and selecting the top 2-3 candidate solutions based on their scores.

9. The automated system for quoting and testing of ship firefighting and lifesaving operations according to claim 1, characterized in that: The data acquisition module obtains various types of data by connecting to the ship fire-fighting and life-saving monitoring management system through interfaces to acquire historical quotation data, transaction result data, and actual cost data; By connecting to industry regulatory platforms, we can capture regulatory requirements data and real-time cost data in real time; preprocessing includes data cleaning, data correction, and data integration.

10. The automated system for quoting and testing of ship firefighting and lifesaving operations according to claim 1, characterized in that: The interactive module uses a structured display method to present the best quotation suggestions and displays the details of the quotation in chart form.