Building material logistics transportation management method

Abstract

The invention discloses a building material logistics transportation management method, and relates to the technical field of logistics transportation management, and the management method comprises the specific steps: S100, multi-source data collection: through cooperation with a meteorological and traffic management department and a map platform, deploying a plurality of data collection devices through cooperation with the meteorological and traffic management department and the map platform; multi-source data of meteorology, road conditions, vehicle states and cargo states are collected in real time, and a transportation knowledge graph is constructed by using named entity recognition and semantic analysis technologies, so that data dimensions and information amount are enriched, association relationships and potential risks among entities are visually displayed in the form of the graph, and the risk of the transportation knowledge graph is reduced. According to the invention, a solid foundation is provided for subsequent real-time data integration and risk analysis and prediction, and the comprehensive and intelligent management mode effectively improves the efficiency and safety of logistics transportation, reduces the transportation cost, and improves the competitiveness of enterprises.

Description

Technical Field

[0001] The invention relates to the technical field of logistics and transportation management, and in particular to a method for managing logistics and transportation of building materials. Background Art

[0002] With the acceleration of urbanization and the vigorous development of infrastructure construction, the construction materials logistics and transportation industry has ushered in unprecedented development opportunities. However, the complexity of this industry has also become increasingly prominent, especially in terms of risk management and emergency response during transportation. In order to ensure the safe and efficient transportation of construction materials, major logistics companies have sought innovative management methods. At present, with the rapid development of the Internet of Things, big data, and artificial intelligence technologies, it has provided new technical support for the logistics and transportation management of construction materials. By integrating these advanced technologies, companies can achieve real-time monitoring of the transportation process, risk prediction, and emergency response, thereby greatly improving transportation efficiency and safety.

[0003] Although traditional construction material logistics and transportation management methods have met the basic needs of the industry to a certain extent, their shortcomings are becoming increasingly apparent. First, traditional methods mainly rely on manual experience and simple data analysis, and it is difficult to achieve comprehensive and real-time monitoring of the transportation process, which makes it difficult to promptly discover and deal with problems that arise during transportation, increasing potential risks. Secondly, traditional methods lack scientific basis and accuracy in risk prediction, and can often only be judged based on experience, which greatly reduces the effectiveness of risk management. In addition, traditional methods also have a lag in emergency response, making it difficult to make correct decisions and actions in the first place, thus affecting transportation efficiency and safety.

[0004] Therefore, developing a construction material logistics and transportation management method not only improves transportation efficiency and safety, but also provides a strong guarantee for the sustainable development of the construction material logistics and transportation industry. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a method for building material logistics and transportation management. The method integrates multiple advanced links such as multi-source data collection, knowledge graph construction, real-time data integration, risk analysis and prediction, and emergency response. Through in-depth cooperation and deployment of data collection equipment, comprehensive monitoring of weather, road conditions, vehicles and cargo status is achieved. With the help of knowledge graph technology, various types of correlation relationships in the transportation process are mined and constructed, realizing accurate prediction and efficient response to potential risks.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a construction material logistics transportation management method, the specific steps of the management method are: S100, multi-source data collection: Through cooperation with meteorological, traffic management departments and map platforms, and deployment of data collection equipment on vehicles and cargo packaging, multi-source data on weather, road conditions, vehicle status and cargo status in the transportation of construction materials are collected; S200, knowledge graph construction: pre-process the collected multi-source data, use named entity recognition technology to identify relevant entities from text data, use semantic analysis technology to mine the relationship between weather and material risks, road conditions and transportation impacts, vehicle failures and related factors, use graph database technology, use the identified entities as nodes of the graph, and the relationship between entities as edges. The weight of the edge is determined according to the calculated relationship strength. The transportation knowledge graph is constructed and indexes are created for the nodes and edges. Information is regularly extracted from newly collected multi-source data and newly occurring transportation event-related data, and new entities and new relationships between entities are re-identified and analyzed to update the knowledge graph. S300, real-time data integration: Receive collected data in real time, remove duplicates, errors and incomplete parts through cleaning, classify and annotate new data according to the entity and relationship standards of the knowledge graph, and extract transportation risk characteristics from multi-source real-time data; S400, risk analysis and prediction: the extracted features are connected to the constructed knowledge graph system, and the potential transportation risks are mined by combining rules and probabilistic reasoning with the knowledge graph. The risk assessment model is constructed using the risk quantitative assessment formula. The potential risks mined are quantitatively assessed using the risk assessment model, and the risks are divided into different levels according to the risk quantification value. S500 emergency response: Once a risk warning occurs, the transportation route is automatically adjusted according to the knowledge graph and real-time road conditions, spare vehicles are dispatched according to the vehicle condition and the urgency of the task, and drivers, consignees and managers are notified via SMS and APP push to inform them of the risk details and response measures.

[0007] Further, in said S100, the data collection devices used in the multi-source data collection are a speed sensor, an engine status sensor, a tire pressure sensor, a temperature and humidity sensor, a temperature and humidity sensor, a vibration sensor and a tilt sensor.

[0008] Furthermore, in S200, the named entity recognition technology is used to identify relevant entities from text data in the knowledge graph construction. Suppose the collected text data set is , the identified entity set is , the calculation formula is: ,in, Representing Entities The weight of Is text data The weight of Indicates the total amount of text data collected. is a matching function, when the entity In text The value is 1 when it appears in the , otherwise it is 0. Exceeding the set threshold , include it in the final entity set .

[0009] Furthermore, the quantification of the relationship between weather and material risks in the knowledge graph construction in S200 is used to describe weather phenomena. and building materials risks , defining the strength of the relationship between them The calculation formula is: ,in is the total number of historical transport events, It is The weight of a historical event, is the impact assessment function, according to Weather phenomena in historical events Risks to building materials The actual impact is scored in the range of [0, 1].

[0010] Furthermore, the quantification of the relationship between road conditions and transportation impact in the knowledge graph construction in S200 is used for road condition events. and transportation factors , the strength of its relationship The calculation formula is: ,in, Is related to road events The number of relevant historical records, It is The weight of the historical records, is the impact evaluation function, according to Traffic events in history Factors affecting transportation The influence degree is scored, and the value range is [0, 1].

[0011] Furthermore, in S200, the relationship between vehicle failure and related factors in the knowledge graph construction is quantified, and for vehicle failure types and related factors , the strength of the relationship between them The calculation formula is: ,in is the number of historical cases related to vehicle failures, It is The weight of historical cases, is the correlation evaluation function, according to Vehicle failure types in historical cases Related factors The correlation degree is scored, and the value range is [0, 1].

[0012] Furthermore, in said S300, extraction of transportation risk features in real-time data integration, the knowledge graph is assumed to be ,in is a collection of nodes, is the edge set, and the identified entity set is , guided by the knowledge graph, define the feature extraction function , the real-time data vector Mapping to feature vector The calculation formula is: ,in, is the weight coefficient, Is a node in the knowledge graph and The strength of the relationship between represents the total number of entities identified, is the set of identified entities The entity.

[0013] Furthermore, in S400, mining of potential transportation risks in risk analysis and prediction, the inference function is assumed to be , with the feature vector and knowledge graph As input, output potential risk set , the calculation formula is: ,in is the weight coefficient determined according to the risk association rules in the knowledge graph. is the value of the risk characteristic vector, It is a feature-related node in the knowledge graph and risk nodes The strength of the relationship between Represents the total number of risk characteristics.

[0014] Furthermore, in the risk analysis and prediction, the risk quantification evaluation formula is used to construct a risk evaluation model, and the potential risk set mined is assumed to be , introducing quantitative values ​​for risk assessment , the calculation formula is: ,in is a natural constant, is the potential risk value mined, is the intercept term, The original potential risk value The weight coefficient of represents the number of other influencing factors introduced, Representative An additional influencing factor, Corresponding to additional influencing factors The weight coefficient of .

[0015] Furthermore, in the above S400, the risk level classification in the risk analysis prediction is set as , low risk: when When the risk level is low, it is medium risk. , which is a medium risk level; high risk: when , which is a high risk level.

[0016] Compared with the prior art, this construction material logistics and transportation management method has the following beneficial effects: 1. The present invention cooperates with meteorological, traffic management departments and map platforms to deploy a variety of data collection equipment, collects multi-source data on weather, road conditions, vehicle status and cargo status in real time, and uses named entity recognition and semantic analysis technology to build a transportation knowledge graph, which not only enriches the data dimension and information volume, but also intuitively displays the relationship and potential risks between entities in the form of a graph, providing a solid foundation for subsequent real-time data integration and risk analysis and prediction. This comprehensive and intelligent management method effectively improves the efficiency and safety of logistics and transportation, reduces transportation costs, and enhances the competitiveness of enterprises.

[0017] 2. The present invention deeply explores potential transportation risks by combining rules with probabilistic reasoning, and uses risk quantification assessment formulas to build a risk assessment model to accurately quantify risks. At the same time, different levels are divided according to the risk quantification values. Once the threshold is reached, an early warning is immediately issued. The transportation route can be automatically adjusted according to the knowledge graph and real-time road conditions, spare vehicles can be dispatched, and relevant personnel can be notified in a timely manner through various means. This fast and accurate emergency response mechanism can take quick measures when risks occur, effectively avoid or reduce losses, which not only enhances the flexibility and response capabilities of logistics transportation, but also improves customer satisfaction and corporate social responsibility.

[0018] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a system architecture and flow chart of a construction material logistics and transportation management method; Figure 2 Schematic diagram of entity relationships and risk associations in the transportation knowledge graph. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0022] Embodiment 1 Urban construction materials transportation project Project background: In a commercial center construction project in a large city, a large amount of steel bars, cement, and glass building materials need to be transported from the building materials warehouse in the suburbs to the construction site. The transportation route covers the city's main roads, viaducts, and some construction sections. The distance is long and the road conditions are complicated. The city's weather changes frequently, posing a great challenge to transportation safety and efficiency.

[0023] Implementation process Multi-source data acquisition (S100): Speed ​​sensors, engine status sensors, tire pressure sensors, temperature and humidity sensors, vibration sensors, and tilt sensors are carefully installed on transport vehicles. At the same time, close data sharing cooperation is reached with local meteorological departments and traffic management departments, and access is made to a high-precision map platform. In a critical transportation mission, the meteorological department issued a rainfall warning before departure, and the traffic management department prompted traffic control on some sections of the road due to road maintenance. After the vehicle was started, each sensor quickly entered the working state and monitored the key data of vehicle speed, engine temperature, and tire pressure in real time. For example, the speed sensor continuously records the vehicle's driving speed, and the engine status sensor accurately monitors the various operating parameters of the engine, providing a detailed data basis for subsequent analysis.

[0024] Knowledge graph construction (S200): The collected text data containing rich information about weather, road conditions, and vehicle status is first strictly preprocessed. Advanced named entity recognition technology is used to accurately identify key entities such as "rainfall", "road maintenance", and "engine overheating" from a large amount of text data. Suppose the collected text data set is , the identified entity set is , the calculation formula is: , when the entity In text The value is 1 when it appears in the , otherwise it is 0. Exceeding the set threshold , include it in the final entity set , for weather phenomena and building materials risks , defining the strength of the relationship between them The calculation formula is: , determine the relationship between weather phenomena and building material risks, and for road events and transportation factors , the strength of its relationship The calculation formula is: , determine the relationship between road events and transportation influencing factors, and for vehicle failure types and related factors , the strength of the relationship between them The calculation formula is: , determine the relationship between vehicle failure types and related factors, and finally use graph database technology to take the identified entities as nodes of the graph, the relationship between entities as edges, and the weight of the edge is determined according to the calculated relationship strength. A transportation knowledge graph is constructed, and an efficient index is created for the nodes and edges. In the constructed graph, the "rainfall" node and the "cement moisture risk" node are closely connected through an edge with a higher weight, which intuitively shows the strong correlation between the two.

[0025] Real-time data integration (S300): Receive data continuously from vehicle sensors in real time, remove duplicate, erroneous and incomplete data through data cleaning algorithms, and accurately classify and label new data based on the entity and relationship standards established in the knowledge graph. For example, when it is recognized that the vehicle speed suddenly drops and the engine temperature rises sharply, the feature vector that may have the risk of vehicle failure is extracted by combining the knowledge system of the knowledge graph. Suppose the knowledge graph is ,in is a collection of nodes, is the edge set, and the identified entity set is , guided by the knowledge graph, define the feature extraction function , the real-time data vector Mapping to feature vector The calculation formula is: , providing accurate data support for subsequent risk analysis.

[0026] Risk analysis and prediction (S400): The extracted feature vectors are connected to a complete knowledge graph system. With the help of the powerful reasoning ability of the knowledge graph, the potential transportation risks are deeply mined through an innovative method combining rules and probabilistic reasoning. The reasoning function is set as , with the feature vector and knowledge graph As input, output potential risk set , the calculation formula is: In this process, the risk quantitative assessment formula is used to build a risk assessment model. Let the potential risk set mined be , introducing quantitative values ​​for risk assessment , the calculation formula is: , quantitatively evaluate the potential risks discovered. After calculation, the risk assessment value of the vehicle breaking down due to engine overheating in this transportation mission is 0.6. According to the risk level classification rules, when When the risk is medium, the system immediately issues an early warning to remind relevant personnel to take timely response measures.

[0027] Emergency response (S500): Once a risk warning is issued, the system quickly activates the emergency response mechanism. According to the road condition information stored in the knowledge graph and the real-time road condition monitoring data, the system automatically re-plans the transportation route, cleverly avoiding traffic control and flooded sections to ensure smooth transportation. At the same time, it quickly dispatches nearby spare vehicles to the scene to transfer goods to minimize the risk of cargo delays. Through SMS and APP push, drivers, consignees and managers are notified in a timely manner, and detailed risk details such as engine overheating that may cause the vehicle to break down, as well as corresponding response measures, such as changing the transportation route and preparing for cargo transfer. With the close cooperation of various departments, cargo delays and losses were successfully avoided, the timely supply of construction materials was effectively guaranteed, and the smooth progress of the commercial center construction project was ensured.

[0028] To sum up, in the urban construction material transportation project, the present invention comprehensively obtains various types of information in transportation through multi-source data collection, laying the foundation for subsequent links. The knowledge graph construction uses advanced technology to sort out the entity relationship, so that the risk factors are clearly presented, and the real-time data integration is closely coordinated with the risk analysis and prediction. The formula is used to accurately quantify the risk, and the emergency response mechanism is quickly activated to re-plan the route, dispatch vehicles and notify all parties, successfully avoiding losses, effectively ensuring transportation safety and efficiency, and highlighting the key role of the present invention in complex urban transportation scenarios.

[0029] Embodiment 2: Inter-regional long-distance transportation of construction materials Project background: A construction company undertook a large-scale cross-provincial construction project, which required transporting a large amount of stone and wood building materials from suppliers in different regions to the construction site. The transportation process had to cross mountain roads and complex highway conditions, and the transportation cycle was long. During this period, there were many uncertain factors, such as bad weather and changes in road conditions, which put extremely high demands on transportation safety and efficiency.

[0030] Implementation process Multi-source data acquisition (S100): Highly sensitive vibration sensors and tilt sensors are installed on cargo packaging, and transport vehicles are equipped with a full set of advanced sensors. In-depth data cooperation is established with the meteorological departments and traffic management departments of the passing areas, and access is also provided to professional map platforms. During an important task of transporting stone, when the transport vehicle was driving on a mountainous road, it encountered strong winds. The sensors on the vehicle immediately detected the intensified vibration of the vehicle body and the change in the tilt angle of the cargo caused by the strong wind. At the same time, the meteorological department provided detailed weather change trends for the next few days through data sharing, including possible snowfall and temperature drop information. These data provided key basis for subsequent transportation decisions.

[0031] Knowledge graph construction (S200): Process the massive amount of data collected in detail, use efficient named entity recognition technology to accurately identify the core entities of "strong wind", "mountainous road" and "stone transportation" from complex text data, and set the collected text data set as , the identified entity set is , the calculation formula is: , when the entity In text The value is 1 when it appears in the , otherwise it is 0. Exceeding the set threshold , include it in the final entity set Then, we use semantic analysis technology combined with rich historical data to deeply quantify the relationship between entities. and "Risk of falling stone" , calculate the relationship strength , the formula is: , determine the relationship between "strong wind" and "risk of falling stones", for "mountain roads" and factors such as "increased transportation difficulty" and "vehicle wear and tear" , calculate the relationship strength , the formula is: , for vehicle failure and “repair time, probability of cargo damage” , through the strength of the relationship Determine the relationship between vehicle failure and "repair time and cargo damage probability", the calculation formula is: ,Finally, the graph database technology is used to construct the ,transportation knowledge graph and create an efficient index. In the graph, the ,“strong wind” node and the “stone falling risk” node are closely connected ,through strong correlation edges, which intuitively present the potential risk ,relationship.

[0032] Real-time data integration (S300): The central data processing unit receives data from vehicle and cargo sensors in real time, uses an intelligent data cleaning algorithm to remove invalid information, and accurately classifies and labels the new data according to the standards of the knowledge graph. For example, based on the current strong wind data and the vibration and tilt of the cargo, the feature extraction function is used to extract the risk feature vector of the stone material that may fall due to strong wind during transportation. Suppose the knowledge graph is ,in is a collection of nodes, is the edge set, and the identified entity set is , guided by the knowledge graph, define the feature extraction function , the real-time data vector Mapping to feature vector The calculation formula is: , providing strong support for risk analysis.

[0033] Risk analysis and prediction (S400): The extracted feature vectors are connected to the knowledge graph system. With the help of the reasoning function of the knowledge graph, the potential transportation risks are deeply mined by combining rules and probabilistic reasoning. The reasoning function is set as , with the feature vector and knowledge graph As input, output potential risk set , the calculation formula is: , using the risk quantitative assessment formula to build a risk assessment model, and conduct quantitative assessment on the mined potential risks. Suppose the mined potential risk set is , introducing quantitative values ​​for risk assessment , the calculation formula is: After analysis and calculation, the risk assessment value of stone falling in this transportation task is 0.75. According to the risk level classification rules, when When the risk is high, the system immediately issues a strong warning, reminding relevant personnel to attach great importance to it and take prompt measures to deal with it.

[0034] Emergency response (S500): After receiving the warning, the system quickly adjusts the transportation route according to the road condition information stored in the knowledge graph and the real-time road condition monitoring data, selects a flatter and more sheltered road, and appropriately reduces the speed to reduce the risk. At the same time, the system notifies the driver through various communication methods to strengthen the inspection and fixation of the goods to ensure the safety of the goods, and uses the APP push to promptly inform the consignee of possible transportation delays and detailed reasons to gain the other party's understanding. In addition, the system quickly dispatches spare vehicles with protective equipment and maintenance tools to follow, so as to provide timely and effective support in emergencies. Through a full range of emergency response measures, the risks are successfully reduced, the safe transportation of construction materials is ensured, the losses caused by risk events are reduced, the transportation efficiency and customer satisfaction are improved, and a solid guarantee is provided for the smooth development of cross-regional construction projects.

[0035] In summary, the cross-regional long-distance transportation project of building materials has fully verified the advantages of the present invention. Multi-source data collection captures key information under complex road conditions and weather conditions, providing a basis for decision-making. The knowledge graph construction accurately analyzes the relationship between "strong wind-stone falling" and "mountainous roads-transportation difficulty", enhances the risk prediction ability, and real-time data integration extracts effective features. The risk analysis and prediction formula calculates that the stone falling risk of 0.75 is a high risk. The emergency response quickly adjusts the route, strengthens cargo management, and allocates resources to reduce risks, reduce losses, and ensure smooth transportation. This strongly proves that the present invention can effectively deal with the uncertainty in long-distance transportation and improve transportation reliability and customer satisfaction.

[0036] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for managing the logistics and transportation of building materials, characterized in that: The specific steps of this management method are: S100, multi-source data collection: Through cooperation with meteorological, traffic management departments and map platforms, and deployment of data collection equipment on vehicles and cargo packaging, multi-source data on weather, road conditions, vehicle status and cargo status in the transportation of construction materials are collected; S200, knowledge graph construction: pre-process the collected multi-source data, use named entity recognition technology to identify relevant entities from text data, use semantic analysis technology to mine the relationship between weather and material risks, road conditions and transportation impacts, vehicle failures and related factors, use graph database technology, use the identified entities as nodes of the graph, and the relationship between entities as edges. The weight of the edge is determined according to the calculated relationship strength. The transportation knowledge graph is constructed and indexes are created for the nodes and edges. Information is regularly extracted from newly collected multi-source data and newly occurring transportation event-related data, and new entities and new relationships between entities are re-identified and analyzed to update the knowledge graph. S300, real-time data integration: Receive collected data in real time, remove duplicates, errors and incomplete parts through cleaning, classify and annotate new data according to the entity and relationship standards of the knowledge graph, and extract transportation risk characteristics from multi-source real-time data; S400, risk analysis and prediction: the extracted features are connected to the constructed knowledge graph system, and the potential transportation risks are mined by combining rules and probabilistic reasoning with the knowledge graph. The risk assessment model is constructed using the risk quantitative assessment formula. The potential risks mined are quantitatively assessed using the risk assessment model, and the risks are divided into different levels according to the risk quantification value. S500 emergency response: Once a risk warning occurs, the transportation route is automatically adjusted according to the knowledge graph and real-time road conditions, spare vehicles are dispatched according to the vehicle condition and the urgency of the task, and drivers, consignees and managers are notified via SMS and APP push to inform them of the risk details and response measures.

2. A construction material logistics and transportation management method according to claim 1, characterized in that: In the S100, the data collection devices used in the multi-source data collection are a speed sensor, an engine status sensor, a tire pressure sensor, a temperature and humidity sensor, a temperature and humidity sensor, a vibration sensor, and a tilt sensor.

3. A construction material logistics and transportation management method according to claim 1, characterized in that: In S200, the named entity recognition technology is used to identify relevant entities from text data in the knowledge graph construction. Suppose the collected text data set is , the identified entity set is , the calculation formula is: ,in, Representing Entities The weight of Is text data The weight of Indicates the total amount of text data collected. is a matching function, when the entity In text The value is 1 when it appears in the , otherwise it is 0. Exceeding the set threshold , include it in the final entity set .

4. A construction material logistics and transportation management method according to claim 1, characterized in that: S200, quantification of the relationship between weather and material risks in knowledge graph construction, for weather phenomena and building materials risks , defining the strength of the relationship between them The calculation formula is: ,in is the total number of historical transport events, It is The weight of a historical event, is the impact assessment function, according to Weather phenomena in historical events Risks to building materials The actual impact is scored in the range of [0, 1].

5. A construction material logistics and transportation management method according to claim 1, characterized in that: S200, quantification of the relationship between road conditions and transportation impact in knowledge graph construction, for road condition events and transportation factors , the strength of its relationship The calculation formula is: ,in, Is related to road events The number of relevant historical records, It is The weight of the historical records, is the impact evaluation function, according to Traffic events in history Factors affecting transportation The influence degree is scored, and the value range is [0, 1].

6. A construction material logistics and transportation management method according to claim 1, characterized in that: S200, quantification of the relationship between vehicle failure and related factors in knowledge graph construction, for vehicle failure type and related factors , the strength of the relationship between them The calculation formula is: ,in is the number of historical cases related to vehicle failures, It is The weight of historical cases, is the correlation evaluation function, according to Vehicle failure types in historical cases Related factors The correlation degree is scored, and the value range is [0, 1].

7. A construction material logistics and transportation management method according to claim 1, characterized in that: In S300, the extraction of transportation risk features in real-time data integration, the knowledge graph is assumed to be ,in is a collection of nodes, is the edge set, and the identified entity set is , guided by the knowledge graph, define the feature extraction function , the real-time data vector Mapping to feature vector The calculation formula is: ,in, is the weight coefficient, Is a node in the knowledge graph and The strength of the relationship between represents the total number of entities identified, is the set of identified entities The entity.

8. A construction material logistics and transportation management method according to claim 1, characterized in that: In S400, the mining of potential transportation risks in risk analysis and prediction is performed, and the inference function is assumed to be , with the feature vector and knowledge graph As input, output potential risk set , the calculation formula is: ,in is the weight coefficient determined according to the risk association rules in the knowledge graph. is the value of the risk characteristic vector, It is a feature-related node in the knowledge graph and risk nodes The strength of the relationship between Represents the total number of risk characteristics.

9. A construction material logistics and transportation management method according to claim 1, characterized in that: In the above S400, a risk assessment model is constructed by using a risk quantification assessment formula in risk analysis and prediction. Suppose the potential risk set mined is , introducing quantitative values ​​for risk assessment , the calculation formula is: ,in is a natural constant, is the potential risk value mined, is the intercept term, The original potential risk value The weight coefficient of represents the number of other influencing factors introduced, Representative An additional influencing factor, Corresponding to additional influencing factors The weight coefficient of .

10. A construction material logistics and transportation management method according to claim 1, characterized in that: In the above S400, the risk level is divided in the risk analysis and prediction, and the risk quantification value is set to , low risk: when When the risk level is low, it is medium risk. , which is a medium risk level; high risk: when , which is a high risk level.

Images