Transport capacity purchasing abnormity monitoring and early warning method

Abstract

The invention discloses a transport capacity purchase abnormity monitoring and early warning method, and relates to the technical field of logistics transportation, and the method comprises the following steps: collecting original data needed by logistics purchase through a multi-source data collection system, and carrying out the preprocessing of the collected original data, including data cleaning, integration, standardization and feature extraction; according to the method, historical transportation records of predetermined transportation capacity are called and verified through the Internet of Things technology, risk prediction and early warning are carried out in combination with an AI algorithm, deep mining and analysis are carried out on data in the purchasing process, potential problems are identified, improvement measures are given, and data support is provided for purchasing decision making in combination with the big data warehouse. According to the method, support is provided for data analysis in the transport capacity purchasing process through a big data warehouse, a provider transfers and provides historical transport records and real-time state data of predetermined transport capacity to a buyer from two stages, and an AI algorithm can comprehensively carry out risk prediction and early warning on a transport capacity purchasing decision.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and in particular to a method for monitoring and warning abnormalities in transport procurement. Background Art

[0002] With the rapid development of the logistics industry, the demand for real-time tracking and management of logistics freight is increasing. Digital freight refers to a new freight model that uses digital technology to optimize and improve the freight process in order to improve freight efficiency, reduce freight costs, and enhance freight safety and service quality. In a complex supply chain system, capacity procurement is a key link connecting goods and end users. Its stability and efficiency directly affect the company's operational efficiency and customer satisfaction.

[0003] However, traditional capacity procurement monitoring and early warning methods often rely on manual experience and limited data analysis, making it difficult to fully and real-time grasp the various dynamic changes in the transportation process, resulting in frequent problems such as delayed procurement decisions and untimely risk warnings. Summary of the invention

[0004] The purpose of the present invention is to provide a method for monitoring and warning abnormalities in transport procurement to address the deficiencies in the above-mentioned prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A capacity procurement abnormal monitoring and early warning method comprises the following steps: using a multi-source data acquisition system to collect raw data required for logistics procurement, and pre-processing the collected raw data, including data cleaning, integration, standardization and feature extraction, so as to build a big data warehouse, using the Internet of Things technology to retrieve and verify the historical transportation records of scheduled capacity, combining with the Al algorithm for risk prediction and early warning, deeply mining and analyzing the data required in the procurement process, identifying potential problems and providing improvement measures, combining with the big data warehouse to provide data support for procurement decisions, the provider transfers the real-time status data of the scheduled capacity to the buyer, and provides the estimated completion time of the previous order for comparison with the buyer's prediction system, based on the analysis results, uses the artificial intelligence algorithm to identify potential problems such as insufficient capacity, transportation delays, vehicle failures, etc., and generates early warning information including problem type, impact range, and recommended measures, so as to support the buyer to adjust the capacity procurement plan to improve the procurement decision.

[0007] Preferably, a multi-dimensional evaluation is conducted on the identified suppliers based on AI algorithms, including historical performance, price competitiveness, service quality, etc., to form a supplier evaluation report. Based on the supplier evaluation report and logistics needs, a dynamic pricing strategy is used to generate intelligent quotations, and key data support is provided when negotiating with suppliers.

[0008] Preferably, the warning information is displayed in a priority-ordered manner, and the display order of the warning information is automatically adjusted according to the urgency and impact scope of the problem.

[0009] Preferably, the early warning information has a tracking feedback function to record how the buyer and seller handle each issue in the early warning information, providing a basis for subsequent procurement optimization and improvement.

[0010] Preferably, the improvement measures in the warning information are customized according to the type of problem, severity and specific procurement needs, including but not limited to adjusting the transportation plan, activating spare transportation capacity and communicating solutions with suppliers.

[0011] Preferably, the Internet of Things technology is also used for remote diagnosis and repair of transportation vehicle failures. When the transportation capacity is abnormal, the supplier provides an access channel, allowing the buyer to access the supplier's platform through remote data transmission, to achieve instant diagnosis and repair guidance of vehicle failures, and to verify the abnormal transportation capacity.

[0012] Preferably, it also includes an algorithm model feedback mechanism, in which the buyer provides feedback on the accuracy of forecast and warning information and the effectiveness of suggested measures based on actual conditions, and the system continuously optimizes the performance of the artificial intelligence algorithm and warning model based on the feedback results.

[0013] Preferably, the data cleaning step includes identifying and removing duplicate data, abnormal data, and incomplete data, and using a machine learning algorithm to intelligently fill in missing values.

[0014] Preferably, the dynamic pricing strategy further includes performing a price elasticity analysis on transportation demand in a specific time period or under special conditions based on historical transaction data and market trend forecasts, and taking into account seasonal factors and competitor pricing strategies.

[0015] Preferably, the risk prediction and early warning system combines natural language processing technology to analyze the feedback text information generated during the transportation process.

[0016] In the above technical solution, a big data warehouse is used to support data analysis in the capacity procurement process, and the provider transfers the historical transportation records and real-time status data of the scheduled capacity to the buyer in two stages, so that the Al algorithm can comprehensively predict and warn of risks in the capacity procurement decision, and use artificial intelligence algorithms to identify potential problems before the purchased capacity is put into use, supporting the buyer to adjust the capacity procurement plan in a timely manner, improving the problem identification and early warning mechanism, and adding more bargaining chips to the capacity procurement negotiations.

[0017] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0018] This application document provides an overview of various implementations or examples of the technology described in the present disclosure, and is not a comprehensive disclosure of the entire scope or all features of the disclosed technology.

[0019] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is an overall schematic diagram of a method for monitoring and early warning of abnormal transport procurement according to the present invention;

[0022] Figure 2 A schematic diagram of the process of supplier evaluation and dynamic pricing in a method for abnormal monitoring and early warning of transport procurement of the present invention;

[0023] Figure 3 The present invention is a flowchart of remote diagnosis and repair of the Internet of Things in a method for monitoring and early warning of abnormal transportation procurement. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0025] See also Figure 1-3 , an abnormal capacity procurement monitoring and early warning method provided by an embodiment of the present invention comprises the following steps:

[0026] Use a multi-source data collection system to collect the raw data required for logistics procurement, and pre-process the collected raw data, including data cleaning, integration, standardization and feature extraction, to build a big data warehouse;

[0027] Through the Internet of Things technology, the historical transportation records of the scheduled capacity are retrieved and verified, and the risk prediction and early warning are carried out in combination with AI algorithms. The data required in the procurement process are deeply mined and analyzed, potential problems are identified and improvement measures are given, and the big data warehouse is combined to provide data support for procurement decisions;

[0028] The provider transfers the real-time status data of the scheduled capacity to the buyer, and provides the estimated completion time of the previous order for comparison with the buyer's forecasting system. Based on the analysis results, it uses artificial intelligence algorithms to identify potential problems such as insufficient capacity, transportation delays, and vehicle failures, and generates early warning information including problem type, impact scope, and recommended measures to support the buyer in adjusting the capacity procurement plan to improve procurement decisions.

[0029] Specifically, we first deploy a multi-source data acquisition system to collect and pre-process the data. The system integrates data interfaces from logistics management systems, transport vehicle GPS tracking systems, warehouse management systems, and third-party logistics service providers. These systems transmit real-time original data in multiple dimensions, including order information, vehicle location, transportation status, historical transportation efficiency, driver evaluation, etc. The collected original data first undergoes a data cleaning process to remove duplicate, erroneous, and invalid data items. Subsequently, data integration technology is used to integrate data from different systems to form a unified data format. Next, the data is standardized to ensure that all indicators are comparable under the same dimension. Finally, feature extraction technology is used to extract features that have a key impact on capacity procurement decisions, such as transportation time, cost, efficiency, vehicle type, etc., to build a big data warehouse. In the early stages of capacity procurement, the system first extracts and transfers the carrier's historical transportation records from the data warehouse to the buyer. These data not only help The buyer evaluates the credibility and capabilities of the carrier, and can also use the Al algorithm to analyze the carrier's performance under different routes, seasons, and weather conditions to provide a basis for purchasing decisions. As the procurement process progresses, the system dynamically updates and transmits the carrier's real-time status data. These data include vehicle location, estimated arrival time, current load conditions, driver behavior patterns, etc., to ensure that the buyer can grasp the dynamic changes of scheduled transportation resources in real time, and provide instant information for emergency adjustment or optimization of procurement plans. Combined with real-time status data, it can monitor abnormal situations in the transportation process in real time, such as vehicle failure warnings, deviations from scheduled routes, delay risks, etc., and immediately issue early warning notifications to the buyer. The buyer can take timely response measures based on the early warning information, such as adjusting the transportation plan, changing the carrier, or increasing insurance coverage. The system can identify potential problems that may exist before the purchased transportation capacity is put into use in advance, such as insufficient vehicle maintenance and insufficient driver experience. Once these problems are discovered, they will be immediately fed back to the buyer.

[0030] Compared with the prior art, the embodiment of the present invention provides support for data analysis in the capacity procurement process through a big data warehouse, and allows the provider to transfer the historical transportation records and real-time status data of the scheduled capacity to the buyer in two stages, so that the Al algorithm can comprehensively predict and warn of risks in the capacity procurement decision, and use artificial intelligence algorithms to identify potential problems before the purchased capacity is put into use, supporting the buyer to adjust the capacity procurement plan in a timely manner, improving the problem identification and early warning mechanism, and also adding more bargaining chips to the negotiation of capacity procurement.

[0031] In a further technical solution of the present invention, a multi-dimensional evaluation is performed on the identified suppliers based on the Al algorithm, including historical performance, price competitiveness, service quality, etc., to form a supplier evaluation report. According to the supplier evaluation report and logistics needs, a dynamic pricing strategy is used to generate intelligent quotations, and key data support is provided when negotiating with suppliers. Specifically, the key dimensions required for evaluating suppliers are clearly defined, including but not limited to historical performance, price competitiveness, service quality, reliability, technological innovation capabilities, compliance with environmental protection standards, etc. Each dimension can be further subdivided into multiple sub-indicators. For example, historical performance can be refined into punctuality rate, breakage rate, customer complaint rate, etc. Machine learning or deep learning algorithms are used to analyze the pre-processed data to identify suppliers. To distinguish the performance of each supplier in different dimensions, the algorithm can automatically learn and optimize the evaluation model based on historical data, and gradually improve the accuracy and efficiency of the evaluation. While evaluating suppliers, the system also needs to conduct an in-depth analysis of the buyer's logistics needs, including transportation volume, transportation distance, transportation time requirements, special needs (such as temperature control, dangerous goods transportation), etc. Combining logistics needs and supplier evaluation results, the system conducts a cost-benefit analysis, considering factors such as price, service quality, reliability, etc. of different suppliers, and evaluates the total cost and potential benefits of each plan. After the negotiation, the system collects the buyer's actual use feedback on the supplier and compares and analyzes it with the previous evaluation results, which helps to discover the shortcomings of the evaluation model and make continuous optimization.

[0032] In a further technical solution of the present invention, the warning information is displayed in a priority-sorted manner, and the display order of the warning information is automatically adjusted according to the urgency and impact scope of the problem. In order to further improve the practicality and response efficiency of the system, it is an important supplementary measure to display the warning information in a priority-sorted manner. Specifically, the priority evaluation standard is evaluated according to the urgency of the problem. For example, a vehicle failure that causes a transportation interruption is a high urgency, while an expected minor delay is a lower urgency. Minor problems have a lower impact on procurement decisions. When the priority of the problem is too high, it will not only greatly affect the procurement decision, but will also be displayed to the capacity purchaser in advance, so that the purchaser can evaluate the economic losses and brand reputation losses that may be caused by the problem. Problems with potential large losses can receive higher attention and be fully analyzed and prevented before procurement. High-priority warning information should also be displayed in a highlighted or bold font to support quick response operations, one-click notification of relevant personnel, activation of emergency plans, adjustment of procurement plans, etc., so that buyers can respond to problems quickly.

[0033] In a further technical solution of the present invention, the early warning information has its own tracking and feedback function, which records the handling of each issue in the early warning information between the buyer and each capacity supplier, and provides a basis for subsequent optimization and improvement of other capacity procurement. Specifically, a set of standard feedback processing record processes are formulated to clarify the responsibilities, steps and time limits of buyers and suppliers in handling problems. The process should include initial response, detailed investigation, solution formulation, execution and verification, and other stages, with clear division of responsibilities. The system regularly summarizes the handling of all early warning information, including key indicators such as processing time, success rate, and common problem types. When the buyer purchases capacity, these previous handling situations are first considered, and then the current procurement strategy is adjusted.

[0034] In a further technical solution of the present invention, improvement measures in the early warning information are customized according to the type of problem, severity and specific procurement needs, including but not limited to adjusting the transportation plan, activating spare transportation capacity and communicating solutions with suppliers. Specifically, the recommended measures generation module can customize the improvement measures in the early warning information according to the specific needs or preferences of the buyer, and share the obtained improvement measures with the supplier. If the problem affects the established transportation time or route, the system automatically calculates and recommends a new transportation plan, including re-planning the route, adjusting the transportation time, optimizing the loading sequence, etc., to ensure that the goods are delivered on time. When there is insufficient capacity or problems with the main means of transportation, are there spare capacity resources, such as spare vehicles, transportation capabilities of partners, etc., to quickly fill the capacity gap? For problems that require the cooperation of suppliers to solve (such as cargo delays, quality problems, etc.), the system automatically generates a communication template, including problem description, expected solution, time requirements, etc., and sends it to relevant suppliers in advance to ensure that both parties respond in time and make reasonable decisions based on the communication between buyers and suppliers.

[0035] In a further technical solution of the present invention, the Internet of Things technology is also used for remote diagnosis and repair of transportation vehicle failures. When the transportation capacity is abnormal, the supplier provides an access channel, allowing the buyer to access the supplier's platform through remote data transmission, to achieve immediate diagnosis and repair guidance of vehicle failures, and to verify the abnormal transportation capacity. Specifically, the Internet of Things technology is deeply integrated to achieve remote diagnosis and repair of transportation vehicle failures. When the supplier's system detects that the transportation vehicle is abnormal, it immediately triggers the fault mechanism, and the supplier then provides a secure remote access channel to the buyer. Through this channel, the buyer can use the remote data transmission function of the Internet of Things device to seamlessly access the supplier's fault diagnosis platform. On the platform, the buyer can view the vehicle's operating data, fault code and sensor status in real time, communicate with the supplier's technical support team in real time, and jointly diagnose the vehicle failure. The buyer tracks the completion of the fault throughout the process, shortening the fault handling time. In addition, through the real-time nature of remote data transmission, both parties can quickly verify the abnormal transportation capacity to ensure the accuracy and timeliness of information, thereby further improving transportation efficiency and customer satisfaction.

[0036] A further technical solution of the present invention also includes an algorithm model feedback mechanism, whereby the buyer provides feedback on the accuracy of the forecast and warning information and the effectiveness of the suggested measures based on the actual situation. The system continuously optimizes the performance of the artificial intelligence algorithm and the warning model based on the feedback results. Specifically, an algorithm model feedback mechanism is introduced to form a closed-loop optimization path. After the warning information and improvement measures are integrated into the capacity procurement link, the system provides buyers with a convenient feedback channel, encouraging buyers to evaluate and provide feedback on the accuracy of the forecast and warning information and the effectiveness of the suggested measures based on the actual situation. The feedback covers multiple dimensions such as information accuracy, timeliness, effectiveness of measures, and difficulties in actual implementation. After receiving the feedback, the system will analyze which types of forecast information frequently have errors and which types of warning information are frequently received. If the feedback from recipients is not timely enough, or which suggested measures are not effective in actual operations, the automated or manually assisted optimization process will be initiated to make targeted adjustments and optimizations to the artificial intelligence algorithms and early warning models. These adjustments and optimizations include adjusting algorithm parameters, optimizing model structure, introducing new data features, updating training data sets, etc. The optimized algorithms and models will be redeployed to the system to improve the accuracy and effectiveness of predictions and warnings, and at the same time make the suggested measures more in line with actual operational needs. Through this continuous feedback and optimization cycle, not only the accuracy and timeliness of prediction and warning information are ensured, but also the effectiveness and operability of the suggested measures are continuously improved, thereby providing buyers with more intelligent, efficient and reliable capacity procurement management services, and reducing some abnormal situations that may occur later.

[0037] In a further technical solution of the present invention, the data cleaning step includes identifying and removing duplicate data, abnormal data and incomplete data, and using a machine learning algorithm to intelligently fill in missing values. Specifically, a hash table or database query technology is used to quickly identify and delete duplicate records in the data set to ensure the uniqueness of the data. Some abnormal values ​​may be caused by data entry errors or extreme events, and can also be further manually reviewed or eliminated. For missing values, first analyze the cause and pattern of the missing (such as random missing, completely random missing, non-random missing), and then use appropriate strategies to process according to the characteristics of the missing data and business logic. For missing values ​​that can be inferred from other fields, a machine learning algorithm (such as decision tree, random forest regression, etc.) is used for intelligent filling. For missing values ​​that cannot be inferred, it is necessary to fill in default values ​​according to business rules or retain the missing state for manual filling. After manual filling, the algorithm is used to detect whether the data range meets the normal standard. The valid data after data cleaning can occupy less space in the big data warehouse and accurately provide data support for subsequent procurement decisions.

[0038] In a further technical solution of the present invention, the dynamic pricing strategy further includes conducting a price elasticity analysis on the transportation demand in a specific time period or under special conditions based on historical transaction data and market trend forecasts, and taking into account seasonal factors and the pricing strategies of competitors. Specifically, based on historical transaction data, an elasticity theory model is used to analyze the demand response at different price levels, determine the price sensitive range, and monitor the price changes of competitors in combination with market demand and changes in peak and off-season seasons. The game theory is used to predict the pricing strategies that competitors may adopt, and the company adjusts its own quotation accordingly to maintain its competitive advantage. On the premise of maximizing cost benefits, different intelligent quotation schemes are generated for different suppliers.

[0039] In a further technical solution of the present invention, the risk prediction and early warning system combines natural language processing technology to analyze the feedback text information generated during the transportation process. Specifically, the text classification technology in NLP is used to automatically classify the preprocessed text information into preset risk categories, such as "delay risk", "cargo damage risk", "safety risk", etc. As the transportation activities continue, the system will continuously accumulate new feedback text data, and automatically update and optimize its NLP model and risk prediction algorithm. In addition, by collecting user feedback and evaluating the early warning effect, the system can continuously improve its prediction accuracy and practicality to better serve the risk management needs of the transportation procurement industry.

[0040] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that, for those skilled in the art, the described embodiments can be modified in various ways without departing from the spirit and scope of the present invention. Therefore, the above description is illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring and early warning of abnormal transport procurement, characterized in that: The steps include: Use a multi-source data collection system to collect the raw data required for logistics procurement, and pre-process the collected raw data, including data cleaning, integration, standardization and feature extraction, to build a big data warehouse; Through the Internet of Things technology, the historical transportation records of the scheduled capacity are retrieved and verified, and the risk prediction and early warning are carried out in combination with the AII algorithm. The data required in the procurement process is deeply mined and analyzed, potential problems are identified and improvement measures are given, and the big data warehouse is combined to provide data support for procurement decisions; The provider transfers the real-time status data of the scheduled capacity to the buyer, and provides the estimated completion time of the previous order for comparison with the buyer's forecasting system. Based on the analysis results, the provider uses artificial intelligence algorithms to identify potential problems such as insufficient capacity, transportation delays, and vehicle failures, and generates early warning information including problem type, impact scope, and recommended measures to support the buyer in adjusting the capacity procurement plan to improve procurement decisions.

2. A method for monitoring and warning abnormal transport procurement according to claim 1, characterized in that: Based on AI algorithms, we conduct multi-dimensional evaluations on identified suppliers, including historical performance, price competitiveness, service quality, etc., to form a supplier evaluation report. Based on the supplier evaluation report and logistics needs, we use dynamic pricing strategies to generate intelligent quotations and provide key data support when negotiating with suppliers.

3. The method for monitoring and warning abnormality of transport procurement according to claim 1 is characterized in that: The warning information is displayed in a priority order, and the display order of the warning information is automatically adjusted according to the urgency and impact scope of the problem.

4. The method for monitoring and warning abnormality of transport procurement according to claim 1 is characterized in that: The early warning information has its own tracking and feedback function, which records how the buyer and seller handle each issue in the early warning information, providing a basis for subsequent procurement optimization and improvement.

5. The method for monitoring and warning abnormality of transport procurement according to claim 1 is characterized in that: The corrective measures in the warning information are customized according to the type and severity of the problem and specific procurement needs, including but not limited to adjusting transportation plans, activating backup transportation capacity and communicating solutions with suppliers.

6. The method for monitoring and warning abnormality of transport procurement according to claim 1, characterized in that: The Internet of Things technology is also used for remote diagnosis and repair of transport vehicle failures. When the transport capacity is abnormal, the supplier provides an access channel, allowing buyers to access the supplier's platform through remote data transmission, to achieve instant diagnosis and repair guidance of vehicle failures, and to verify the abnormal transport capacity.

7. The method for monitoring and warning abnormality of transport procurement according to claim 1, characterized in that: It also includes an algorithm model feedback mechanism, in which buyers provide feedback on the accuracy of forecast and warning information and the effectiveness of recommended measures based on actual conditions. The system continuously optimizes the performance of artificial intelligence algorithms and warning models based on the feedback results.

8. The method for monitoring and warning abnormality of transport procurement according to claim 1, characterized in that: The data cleaning step includes identifying and removing duplicate data, abnormal data, and incomplete data, and using a machine learning algorithm to intelligently fill in missing values.

9. The method for monitoring and warning abnormality of transport procurement according to claim 2, characterized in that: The dynamic pricing strategy further includes conducting a price elasticity analysis on transportation demand during a specific time period or under special conditions based on historical transaction data and market trend forecasts, and taking into account seasonal factors and competitor pricing strategies.

10. The method for monitoring and warning abnormality of transport procurement according to claim 1, characterized in that: The risk prediction and early warning system combines natural language processing technology to analyze the feedback text information generated during the transportation process.

Images