Logistics transportation resource processing method and device, computer equipment and storage medium

Abstract

The invention relates to a logistics transportation resource processing method. The method comprises the steps of obtaining basic transportation resource information according to material information of a logistics transportation task and logistics transportation information; if the logistics transportation task meets a preset urgent task condition, obtaining predicted urgent resource information through an urgent resource prediction model; obtaining predicted insurance resource information through the insurance resource prediction model; inputting the predicted urgent resource information, the predicted insurance resource information and the basic transportation resource information into a rule engine corresponding to the logistics transportation task to obtain adjusted transportation resource information of the logistics transportation task; and according to historical transportation resource information of a historical logistics transportation task matched with the logistics transportation task, performing verification processing on the adjusted transportation resource information to obtain target transportation resource information. By adopting the method, the accuracy of dynamic adjustment of the logistics transportation resource information can be improved.

Description

Technical Field

[0001] This application relates to the field of logistics technologies, and particularly to a method, device, computer equipment, storage medium, and computer program product for processing logistics transportation resources. Background Art

[0002] Material transportation is often affected by various factors, such as the urgency of the project, sudden road control during transportation, and large fluctuations in oil prices. Moreover, the materials themselves are diverse in types and have different characteristics, and different requirements for protection conditions and transportation conditions.

[0003] In the traditional logistics transportation resource calculation system, resource calculation mainly relies on static price lists. Such price lists are usually formulated based on past business data and experience, with a long update cycle, and may be adjusted only once every few months or even years. The traditional method of determining logistics transportation resources using fixed price lists cannot respond in a timely manner to the changes in actual transportation and lacks the ability to dynamically adjust logistics transportation resources in real time. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for processing logistics transportation resources that can improve the accuracy of dynamically adjusting logistics transportation resource information in response to the above technical problems.

[0005] In a first aspect, this application provides a method for processing logistics transportation resources. The method includes:

[0006] Obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task;

[0007] If the logistics transportation task meets the preset urgent task conditions, obtain the predicted urgent resource information of the logistics transportation task through an urgent resource prediction model;

[0008] Obtain the predicted insurance resource information of the logistics transportation task through an insurance resource prediction model;

[0009] Input the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task;

[0010] Perform verification processing on the adjusted transportation resource information according to the historical transportation resource information of the historical logistics transportation task that matches the logistics transportation task to obtain the target transportation resource information of the logistics transportation task.

[0011] In one embodiment, before obtaining the predicted urgent resource information of the logistics transportation task through the urgent resource prediction model if the logistics transportation task meets the preset urgent task conditions, the following steps are further included:

[0012] Input the importance and time constraint information of the logistics transportation task into the urgent type prediction model to obtain the predicted urgent type of the logistics transportation task;

[0013] If it is detected that the predicted urgent type matches the target urgent type corresponding to the urgent task conditions, confirm that the logistics transportation task meets the urgent task conditions.

[0014] In one embodiment, obtaining the predicted urgent resource information of the logistics transportation task through the urgent resource prediction model includes:

[0015] Use the target urgent resource information as the constraint condition of the urgent resource prediction model to obtain the constrained urgent resource prediction model; the urgent resource prediction model is trained from the initial urgent resource prediction model through historical total logistics information, historical urgent types, and the historical urgent resource information corresponding to the historical urgent types;

[0016] Input the predicted urgent type and the current total logistics information into the constrained urgent resource prediction model to obtain the predicted urgent resource information of the logistics transportation task.

[0017] In one embodiment, obtaining the predicted insurance resource information of the logistics transportation task through the insurance resource prediction model includes:

[0018] Obtain the predicted transportation risk information of the logistics transportation task according to the material information and the logistics transportation information;

[0019] Input the material resource information and the predicted transportation risk information of the logistics transportation task into the insurance resource prediction model to obtain the predicted insurance resource information of the logistics transportation task;

[0020] Among them, the insurance resource prediction model is trained from the constrained insurance resource prediction model through historical material resource information and historical transportation risk information; the constrained insurance resource prediction model is obtained by processing the initial insurance resource prediction model with the basic insurance resource information as the constraint condition.

[0021] In one embodiment, inputting the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task includes:

[0022] Obtain the environmental control resource information and transportation road condition resource information of the logistics transportation task;

[0023] Through the rule engine corresponding to the logistics transportation task, according to the predicted urgent resource information, the predicted insurance resource information, the environmental control resource information and the transportation road condition resource information, perform resource adjustment processing on the basic transportation resource information to obtain the adjusted transportation resource information of the logistics transportation task.

[0024] In one embodiment, according to the historical transportation resource information of the historical logistics transportation task matching the logistics transportation task, perform verification processing on the adjusted transportation resource information to obtain the target transportation resource information of the logistics transportation task, including:

[0025] From the historical logistics transportation tasks, screen out the target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation task;

[0026] Obtain the average transportation resource information of the target historical logistics transportation task; the average transportation resource information is used to determine the verification passing condition corresponding to the adjusted transportation resource information;

[0027] If the adjusted transportation resource information does not meet the verification passing condition, adjust the adjusted transportation resource information to obtain the target transportation resource information that meets the verification passing condition.

[0028] In a second aspect, the present application also provides a logistics transportation resource processing device. The device includes:

[0029] A basic resource determination module, configured to obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task;

[0030] An urgent resource determination module, configured to, if the logistics transportation task meets the preset urgent task condition, obtain the predicted urgent resource information of the logistics transportation task through an urgent resource prediction model;

[0031] An insurance resource determination module, configured to obtain the predicted insurance resource information of the logistics transportation task through an insurance resource prediction model;

[0032] A basic resource adjustment module, configured to input the predicted urgent resource information, the predicted insurance resource information and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task;

[0033] A target resource determination module, configured to perform a verification process on the adjusted transport resource information according to the historical transport resource information of the historical logistics transport task that matches the logistics transport task, so as to obtain the target transport resource information of the logistics transport task.

[0034] Thirdly, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0035] Obtain the basic transport resource information of the logistics transport task according to the material information and the logistics transport information of the logistics transport task;

[0036] If the logistics transport task meets the preset urgent task conditions, obtain the predicted urgent resource information of the logistics transport task through an urgent resource prediction model;

[0037] Obtain the predicted insurance resource information of the logistics transport task through an insurance resource prediction model;

[0038] Input the predicted urgent resource information, the predicted insurance resource information, and the basic transport resource information into the rule engine corresponding to the logistics transport task to obtain the adjusted transport resource information of the logistics transport task;

[0039] Perform a verification process on the adjusted transport resource information according to the historical transport resource information of the historical logistics transport task that matches the logistics transport task, so as to obtain the target transport resource information of the logistics transport task.

[0040] Fourthly, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the following steps are implemented:

[0041] Obtain the basic transport resource information of the logistics transport task according to the material information and the logistics transport information of the logistics transport task;

[0042] If the logistics transport task meets the preset urgent task conditions, obtain the predicted urgent resource information of the logistics transport task through an urgent resource prediction model;

[0043] Obtain the predicted insurance resource information of the logistics transport task through an insurance resource prediction model;

[0044] Input the predicted urgent resource information, the predicted insurance resource information, and the basic transport resource information into the rule engine corresponding to the logistics transport task to obtain the adjusted transport resource information of the logistics transport task;

[0045] Verify the adjusted transportation resource information based on the historical transportation resource information of the historical logistics transportation tasks that match the logistics transportation task, to obtain the target transportation resource information of the logistics transportation task.

[0046] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0047] Obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task;

[0048] If the logistics transportation task meets the preset urgent task conditions, obtain the predicted urgent resource information of the logistics transportation task through an urgent resource prediction model;

[0049] Obtain the predicted insurance resource information of the logistics transportation task through an insurance resource prediction model;

[0050] Input the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task;

[0051] Verify the adjusted transportation resource information based on the historical transportation resource information of the historical logistics transportation tasks that match the logistics transportation task, to obtain the target transportation resource information of the logistics transportation task.

[0052] The above-mentioned logistics transportation resource processing method, device, computer equipment, storage medium and computer program product obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task; if the logistics transportation task meets the preset urgent task conditions, the predicted urgent resource information of the logistics transportation task is obtained through the urgent resource prediction model; the predicted insurance resource information of the logistics transportation task is obtained through the insurance resource prediction model; the predicted urgent resource information, the predicted insurance resource information and the basic transportation resource information are input into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task; the adjusted transportation resource information is verified according to the historical transportation resource information of the historical logistics transportation task matching the logistics transportation task to obtain the target transportation resource information of the logistics transportation task. By using this method, the basic transportation resource information of the logistics transportation task is first determined through the material information and the logistics transportation information, then the predicted urgent resource information of the logistics transportation task is determined according to the actual urgent situation, and the predicted insurance resource information of the logistics transportation task is determined according to the actual insurance situation. Furthermore, through the rule engine, the basic transportation resource information is dynamically adjusted by using the predicted urgent resource information and the predicted insurance resource information, and finally the adjusted transportation resource information is verified, so as to output the target transportation resource information of the logistics transportation task. This not only dynamically adjusts the transportation resource information by using the actual urgent situation and insurance situation, but also further ensures the accuracy of the transportation resource information through the verification mechanism, improving the accuracy and reliability of the dynamic adjustment of the logistics transportation resource information. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 FIG. is an application environment diagram of the logistics transportation resource processing method in an embodiment;

[0054] Figure 2 FIG. is a schematic flowchart of the logistics transportation resource processing method in an embodiment;

[0055] Figure 3 FIG. is a schematic flowchart of the steps of obtaining the predicted urgent resource information of the logistics transportation task through the urgent resource prediction model in an embodiment;

[0056] Figure 4 FIG. is a schematic flowchart of the logistics transportation resource processing method in another embodiment;

[0057] Figure 5 FIG. is a schematic flowchart of the logistics transportation resource processing method in yet another embodiment;

[0058] Figure 6 FIG. is a structural block diagram of the logistics transportation resource processing device in an embodiment;

[0059] Figure 7Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0062] The logistics transportation resource processing method provided in the embodiments of the present application can be applied to, for example Figure 1 the application environment shown in the figure. Among them, the vehicle-mounted terminal 101 communicates with the server 102 through a network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or can be placed in the cloud or other network servers. Among them, the vehicle-mounted terminal 101 can be but is not limited to various intelligent vehicle-mounted devices, etc. The server 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and can also be implemented by an independent server or a server cluster composed of multiple servers.

[0063] In one embodiment, as Figure 2 shown in the figure, a logistics transportation resource processing method is provided. Taking the method applied to Figure 1 the server in the figure as an example for illustration, the method includes the following steps:

[0064] Step S201: Obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task.

[0065] Among them, the logistics transportation task refers to the task of transporting materials to the destination. For example, the logistics transportation task can be to transport the specified materials from City A to City B.

[0066] Among them, the material information refers to the information describing the situation of the materials. For example, the material information can include information such as the weight, volume, value, storage conditions, and attributes of the materials.

[0067] Among them, the logistics transportation information refers to the information describing the situation of the logistics transportation. For example, the logistics transportation information includes information such as the logistics transportation distance.

[0068] Among them, the transportation resource information refers to the information describing the resources required for transporting materials. In practical applications, the basic transportation resource information can represent the basic freight of the logistics transportation task.

[0069] Specifically, the server can collect vehicle information such as the form speed, fuel consumption, and location of the vehicle through the on-vehicle sensors and positioning systems installed on the vehicle, and can also collect material information such as the weight, volume, value, storage conditions, and attributes of the materials carried by the vehicle through the material packaging sensors installed on the vehicle; then the in-vehicle terminal of the vehicle transmits the obtained vehicle information, material information, and the pre-entered logistics transportation information to the server. The server can store the received data in the database; the server extracts the material information and logistics transportation information from the database and preprocesses them, and then calculates the basic transportation resource information of the logistics transportation task based on the unit material basic resource rate and the preprocessed material information, as well as the unit transportation basic resource rate and the preprocessed logistics transportation information. Among them, the unit material basic resource rate and the unit transportation basic resource rate can be obtained through historical transportation resource information, current logistics transportation cost analysis, and modeling.

[0070] In practical applications, the server can extract the preprocessed material weight, material volume, and logistics transportation distance from the database. The server can calculate the basic transportation resource information through the following formula: Basic transportation resource information = material weight × unit weight basic rate + material volume × unit volume basic rate + logistics transportation distance × unit distance basic rate.

[0071] Step S202, if the logistics transportation task meets the preset urgent task conditions, then obtain the predicted urgent resource information of the logistics transportation task through the urgent resource prediction model.

[0072] Among them, the urgent task condition refers to the judgment condition set for the urgency of the task. The urgent task condition is used to judge whether the task (such as a logistics transportation task) belongs to an urgent task.

[0073] Among them, the urgent resource prediction model refers to a model used to predict the resources required for an urgent transportation of a task (such as a logistics transportation task).

[0074] Among them, the predicted urgent resource information refers to the ratio of the additional resources predicted to be required when a task (such as a logistics transportation task) is transported urgently.

[0075] Specifically, if it is detected that the logistics transportation task meets the preset urgent task conditions, it means that the logistics transportation task belongs to an urgent task, and the server can use the urgent resource prediction model to predict the urgent resource information; if it is detected that the logistics transportation task does not meet the urgent task conditions, it means that the logistics transportation task does not belong to an urgent task, and the server can directly set the predicted urgent resource information of the logistics transportation task to 0, that is, there is no need to generate additional urgent resources.

[0076] Step S203: Obtain the predicted insurance resource information of the logistics transportation task through the insurance resource prediction model.

[0077] Among them, the material resource condition refers to the judgment condition for analyzing the material value size of the logistics transportation task.

[0078] Among them, the insurance resource prediction model refers to a model used to predict the dynamic adjustment ratio of insurance resources for a task (such as a logistics transportation task). The insurance resource prediction model can be constructed based on a gradient boosting tree.

[0079] Among them, the predicted insurance resource information refers to the dynamically adjusted ratio predicted for the insurance resources of a task (such as a logistics transportation task).

[0080] Specifically, the server can pre-train an insurance resource prediction model, and the insurance resource prediction model has at least one constraint condition, which can be used to constrain the numerical range of the predicted insurance resource information output by the insurance resource prediction model (such as 0.5% - 2%). Further, the server can first determine whether the material value information in the material information of the logistics transportation task exceeds the preset value threshold; if the material value information exceeds the value threshold, the server predicts the insurance resource adjustment ratio corresponding to the logistics transportation task through the insurance resource prediction model. For example, when the material resource information of the logistics transportation task is relatively high, the insurance resources of the logistics transportation task can be dynamically increased through the insurance resource information, and when the material resource information of the logistics transportation task is relatively low, the insurance resources of the logistics transportation task can be dynamically reduced through the insurance resource information. Finally, the model outputs the predicted insurance resource information of the logistics transportation task. If the material value information does not exceed the value threshold, the server can not adjust the insurance resources, that is, set the predicted insurance resource information to the default value.

[0081] Step S204: Input the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task.

[0082] Among them, the rule engine is a component embedded in the application. The rule engine uses predefined semantic modules to write and execute business decisions separated from the program code. The rule engine can accept data input, interpret business rules, and make decisions based on these rules.

[0083] Specifically, the server can pre-set corresponding rule engines for different task types respectively. The server obtains the rule engine corresponding to the logistics transportation task according to the task type of the logistics transportation task. The dynamic adjustment rules of resource information are configured in the rule engine. The server can input the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine, and can also input other relevant information into the rule engine. Through comprehensive decision-making by the rule engine, calculate the total resources required after considering various influencing factors, and finally output the adjusted transportation resource information of the logistics transportation task.

[0084] Step S205: According to the historical transportation resource information of the historical logistics transportation task that matches the logistics transportation task, perform a verification process on the adjusted transportation resource information to obtain the target transportation resource information of the logistics transportation task.

[0085] Among them, the historical logistics transportation task refers to the logistics transportation task that has been completed within the historical time period.

[0086] The server can also verify the adjusted transportation resource information to ensure that the transportation resource information is still within a reasonable range after multiple dynamic adjustments. Specifically, the server can retrieve from the historical database the historical logistics transportation task that matches the logistics transportation task, for example, it can be task type matching, transportation scale matching, etc.; then the server calculates a reasonable range based on the historical transportation resource information of one or more matching historical logistics transportation tasks; furthermore, verify whether the adjusted transportation resource information is still within the reasonable range. If it is still within the reasonable range, the server can set the adjusted transportation resource information as the target transportation resource information of the logistics transportation task. If it is not within the reasonable range, the server can adjust the transportation resource information again and output the final target transportation resource information.

[0087] Furthermore, the server can perform visualization processing on the target resource information to obtain the visualization result of the target resource information. The server can display the visualization result through the user's terminal, or can send the visualization result to the vehicle-mounted terminal for the display screen associated with the vehicle-mounted terminal to display the visualization result. Among them, the visualization result also shows the details of each resource information that makes up the target resource information, such as the basic transportation resource information, the predicted urgent resource information, and the predicted insurance resource information; the visualization result can also include a corresponding analysis report.

[0088] For example, the visualization result of the target resource information can display the details of the target resource information in the form of a structured table, including the values of various resources, calculation formulas and bases, and attach an analysis report on the composition of the target resource information.

[0089] In the above method for processing logistics transportation resources, based on the material information and logistics transportation information of the logistics transportation task, the basic transportation resource information of the logistics transportation task is obtained; if the logistics transportation task meets the preset urgent task conditions, the predicted urgent resource information of the logistics transportation task is obtained through the urgent resource prediction model; the predicted insurance resource information of the logistics transportation task is obtained through the insurance resource prediction model; the predicted urgent resource information, the predicted insurance resource information and the basic transportation resource information are input into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task; according to the historical transportation resource information of the historical logistics transportation task matching the logistics transportation task, the adjusted transportation resource information is verified to obtain the target transportation resource information of the logistics transportation task. By using this method, first, the basic transportation resource information of the logistics transportation task is determined through the material information and the logistics transportation information, then the predicted urgent resource information of the logistics transportation task is determined according to the actual urgent situation, and the predicted insurance resource information of the logistics transportation task is determined according to the actual insurance situation. Furthermore, through the rule engine, the basic transportation resource information is dynamically adjusted by using the predicted urgent resource information and the predicted insurance resource information. Finally, the adjusted transportation resource information is verified to output the target transportation resource information of the logistics transportation task. This not only dynamically adjusts the transportation resource information by using the actual urgent situation and insurance situation, but also further ensures the accuracy of the transportation resource information through the verification mechanism, improving the accuracy and reliability of the dynamic adjustment of the logistics transportation resource information.

[0090] In one embodiment, before the step S202 above, if the logistics transportation task meets the preset urgent task conditions, and the predicted urgent resource information of the logistics transportation task is obtained through the urgent resource prediction model, it further includes: inputting the importance degree and time constraint information of the logistics transportation task into the urgent type prediction model to obtain the predicted urgent type of the logistics transportation task; if it is detected that the predicted urgent type matches the target urgent type corresponding to the urgent task conditions, it is confirmed that the logistics transportation task meets the urgent task conditions.

[0091] Among them, the importance degree is used to represent the importance level of the logistics transportation task.

[0092] Among them, the time constraint information refers to the information describing the time limit of the logistics transportation task. The time constraint information can be used to constrain the relative time relationship between different tasks. For example, the time constraint information can be that "after task A is completed, task B must start within 2 days"; the time constraint information can also be used to constrain the time length of the task, such as "the transportation time of task C shall not exceed 7 days"; the time constraint time can also be used to constrain the specific time point of the task, such as "task D must be completed before XXXX year XX month XX day X hour".

[0093] Among them, the urgent type prediction model refers to a model used to predict the urgent type of a task.

[0094] Specifically, when setting a logistics transportation task, the importance and time constraint information corresponding to the task can also be set; then the server can extract its importance and time constraint information from the logistics transportation task; then the server inputs the importance and time constraint information of the logistics transportation task into the urgent type prediction model to predict whether the logistics transportation task is an urgent task through the urgent type prediction model. If it is an urgent task, its specific urgent type can also be listed, and finally the predicted urgent type of the logistics transportation task is output. One or more urgent types are preset in advance, and then the server obtains the target urgent type. For example, the target urgent type can include "ordinary urgent", "special urgent", etc. If it is detected that the output predicted urgent type meets any one of the target urgent types, it is confirmed that the logistics transportation task belongs to an urgent task, that is, the logistics transportation task meets the urgent task conditions. If it is detected that the output predicted urgent type does not match all of the target urgent types, for example, the predicted urgent type is "not urgent", it is confirmed that the logistics transportation task does not belong to an urgent task, that is, the logistics transportation task does not meet the urgent task conditions.

[0095] In this embodiment, the urgent type prediction model can comprehensively analyze the importance, necessity and urgency of the logistics transportation task based on the importance and time constraint information of the logistics transportation task, rather than only analyzing the urgent situation from the time in the traditional technology, effectively improving the accuracy of the output predicted urgent type, and then can accurately judge whether the logistics transportation task meets the urgent task conditions, providing a precise and reliable processing basis for subsequent urgent resource prediction.

[0096] In one embodiment, as Figure 3 shown, in the above step S202, the predicted urgent resource information of the logistics transportation task is obtained through the urgent resource prediction model, which specifically includes the following contents:

[0097] Step S301: Use the target urgent resource information as the constraint condition of the urgent resource prediction model to obtain the constrained urgent resource prediction model. The urgent resource prediction model is trained from the initial urgent resource prediction model using historical total logistics information, historical urgent types, and historical urgent resource information corresponding to the historical urgent types.

[0098] Among them, the target urgent resource information refers to the urgent resource information in a historical time period relatively close to the current time period. For example, the target urgent resource information can be the average urgent resource information of the previous month, previous week, or previous day.

[0099] Among them, the historical total logistics information refers to the information describing the overall transportation situation of logistics in the historical time period.

[0100] Specifically, the server can pre - use the gradient boosting algorithm and / or reinforcement learning to construct the initial urgent resource prediction model. Then, from the logistics platform associated with the server, it can extract the historical total logistics information in each historical time period, and can also extract the historical urgent types set under the historical total logistics information at that time, as well as extract the historical urgent resource information corresponding to each historical urgent type in this historical time period. The server uses the historical total logistics information, historical urgent types, and historical urgent resource information corresponding to the historical urgent types as sample features to iteratively train the initial urgent resource prediction model, and finally trains the urgent resource prediction model.

[0101] Furthermore, to enable the urgent resource prediction model to more accurately understand the resource change problem caused by the current situation and historical situation, and to avoid the trained urgent resource prediction model from only predicting fixed urgent resource information based on the urgent type and total logistics information, after training the urgent resource prediction model, the server can also construct a constraint condition based on the target urgent resource information to obtain an urgent constraint condition. The server uses the urgent constraint condition to constrain the prediction ratio adjustment of the urgent resource prediction model, thereby obtaining the constrained urgent resource prediction model.

[0102] Step S302: Input the predicted urgent type and the current total logistics information into the constrained urgent resource prediction model to obtain the predicted urgent resource information of the logistics transportation task.

[0103] Specifically, the server inputs the predicted urgent type and the current total logistics information into the constrained urgent resource prediction model, so as to perform urgent resource prediction processing based on the predicted urgent type and the current total logistics information through the constrained urgent resource prediction model, and finally output the predicted urgent resource information of the logistics transportation task.

[0104] In this embodiment, by using the target urgent resource information as a constraint condition for the urgent resource prediction model, the obtained constrained urgent resource prediction model can adapt to the actual urgent resource situation, dynamically adjust and predict the changes in the current urgent resource information for each urgent type, thereby greatly improving the accuracy of the predicted urgent resource information output.

[0105] In one embodiment, for step S203 above, the predicted insurance resource information of the logistics transportation task is obtained through the insurance resource prediction model, which specifically includes the following content: based on the material information and the logistics transportation information, the predicted transportation risk information of the logistics transportation task is obtained; the material resource information and the predicted transportation risk information of the logistics transportation task are input into the insurance resource prediction model to obtain the predicted insurance resource information of the logistics transportation task; among them, the insurance resource prediction model is trained through the historical material resource information and the historical transportation risk information to obtain the constrained insurance resource prediction model; the constrained insurance resource prediction model is obtained by processing the initial insurance resource prediction model with the basic insurance resource information as the constraint condition.

[0106] Among them, the predicted transportation risk information is used to represent the prediction of the dangerous risk of the logistics transportation task.

[0107] Among them, the basic insurance resource information refers to the information describing the proportional range of the insurance resources. For example, the basic insurance resource information can be (0.5% - 2%).

[0108] Specifically, the server can construct a basic model structure based on algorithms such as gradient boosting trees, and then the server obtains the initial insurance resource prediction model; different from the urgent resources, the insurance resources usually have a fixed proportional range, so the server can preset the basic insurance resources in advance, and then construct a constraint condition based on the basic insurance resources to obtain the insurance constraint condition. The server also adds the insurance constraint condition as a part of the model structure to the initial insurance resource prediction model to obtain the constrained insurance resource prediction model, so that the insurance resource information output by the constrained insurance resource prediction model each time can be within the proportional range corresponding to the insurance constraint condition.

[0109] Furthermore, if it is detected that the material value information in the material information exceeds the value threshold, the server can first predict the risk level of the logistics transportation task based on the material information and the logistics transportation information, and then the server obtains the predicted transportation risk information of the logistics transportation task. Then the server takes the material resource information and the predicted transportation risk information of the logistics transportation task as input data and inputs them into the insurance resource prediction model together. The insurance resource prediction model performs insurance resource prediction processing based on the material resource information and the predicted transportation risk information, and finally outputs the predicted insurance resource information of the logistics transportation task.

[0110] In this embodiment, by setting constraint conditions for the basic insurance resources of the initial insurance resources prediction model, the insurance resources information output by the constrained insurance resources prediction model can be within the basic range. In addition, the dynamic adjustment range of the insurance resources is comprehensively predicted by means of the predicted transportation risk information, thereby further improving the dynamic adjustment accuracy of the predicted insurance resources information.

[0111] In one embodiment, in step S204 above, the predicted urgent resources information, the predicted insurance resources information, and the basic transportation resources information are input into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resources information of the logistics transportation task, which specifically includes the following contents: Obtain the environmental control resources information and the transportation road condition resources information of the logistics transportation task; Through the rule engine corresponding to the logistics transportation task, perform resource adjustment processing on the basic transportation resources information according to the predicted urgent resources information, the predicted insurance resources information, the environmental control resources information, and the transportation road condition resources information to obtain the adjusted transportation resources information of the logistics transportation task.

[0112] Among them, the environmental control resources information refers to the additional resource ratio required to meet the special environmental requirements for maintaining the transported materials. For example, assume that the logistics transportation task is to transport fresh food materials, and the fresh food materials need to be transported in a cold chain and the shelf life of the fresh food materials is extended by maintaining a low temperature environment. Then the materials required to maintain the low temperature environment are the environmental control resources information of this logistics transportation task.

[0113] Among them, the transportation road condition resources information refers to the resource ratio of the increased transportation cost due to the transportation road conditions. For example, the transportation road condition resources information can be the increased ratio of the transportation cost, such as 10%.

[0114] In addition to using the predicted urgent resources information, the predicted insurance resources information, and the basic transportation resources information for resource adjustment, the server can also use other information for resource adjustment together to improve the accuracy of resource adjustment. Specifically, when the transported materials corresponding to the logistics transportation task have special environmental requirements, the server can also calculate the environmental control resources information of this logistics transportation task according to the energy consumption data of the environmental control equipment associated with the environmental requirements and the usage duration of the environmental control equipment. The server can also analyze whether the logistics transportation task needs to increase additional transportation road condition resources information based on the real-time transportation road condition information. For example, the server can input the real-time transportation road condition information into a road condition resources prediction model (such as the gradient boosting algorithm) to analyze the relationship between the congestion duration and the detour distance of the road condition and the increase in transportation cost through the road condition resources prediction model, so as to output the transportation road condition resources information. For example, assume that the road condition resources prediction model predicts that the increase in congestion duration leads to a 10% increase in transportation cost, then an additional 10% of the corresponding cost needs to be added to the basic freight, that is, the transportation road condition resources information is 10%.

[0115] Further, the server inputs the predicted urgent resource information, predicted insurance resource information, environmental control resource information, and transportation condition resource information into the rule engine corresponding to the logistics transportation task, and automatically adjusts the additional costs generated due to changes in various factors through this rule engine, so as to calculate and superimpose the basic transportation resource information to obtain the adjusted transportation resource information of the logistics transportation task.

[0116] For example, the rule engine can multiply the basic transportation resource information by the predicted urgent resource information to obtain the adjusted urgent resource; multiply the basic transportation resource information by the predicted insurance resource information to obtain the adjusted insurance resource; multiply the basic transportation resource information by the environmental control resource information to obtain the adjusted environmental control resource; multiply the basic transportation resource information by the transportation condition resource information to obtain the adjusted transportation condition resource; and finally add the adjusted urgent resource, adjusted insurance resource, adjusted environmental control resource, and adjusted transportation condition resource to obtain the adjusted transportation resource information.

[0117] In this embodiment, through the rule engine corresponding to the logistics transportation task, according to the predicted urgent resource information, predicted insurance resource information, environmental control resource information, and transportation condition resource information, the basic transportation resource information is comprehensively adjusted, so that the calculated adjusted transportation resource information fully considers the influence of various factors on the transportation resources of the logistics transportation task, realizes the dynamic adjustment of the transportation resources, and improves the accuracy of the adjusted transportation resource information.

[0118] In one embodiment, in the above step S205, according to the historical transportation resource information of the historical logistics transportation task matching the logistics transportation task, the adjusted transportation resource information is verified to obtain the target transportation resource information of the logistics transportation task, which specifically includes the following contents: screening out the target historical logistics transportation task matching the logistics transportation information of the logistics transportation task from the historical logistics transportation tasks; obtaining the transportation resource mean information of the target historical logistics transportation task; the transportation resource mean information is used to determine the verification passing condition corresponding to the adjusted transportation resource information; if the adjusted transportation resource information does not meet the verification passing condition, the adjusted transportation resource information is adjusted to obtain the target transportation resource information that meets the verification passing condition.

[0119] Among them, the logistics transportation information also includes information such as transportation type, transportation route, and transportation scale.

[0120] Among them, the verification passing condition refers to the verification condition set for the transportation resource information, which can be used to judge whether the adjusted transportation resource information is reasonable. For example, the verification passing condition can be set as not exceeding the target ratio of the transportation resource mean information.

[0121] Specifically, multiple historical logistics transportation tasks are stored in the historical database; the server can retrieve from the historical database the target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation task. For example, it can retrieve one or more historical logistics transportation tasks with the same transportation type, transportation route, and / or transportation scale as the logistics transportation task and set them as the target logistics transportation tasks. Then, calculate the mean and variance of the target transportation resource information of all the target logistics transportation tasks to obtain the transportation resource mean information and transportation resource variance information of the target historical logistics transportation tasks. If it is detected that the adjusted transportation resource information does not exceed the target ratio (e.g., ±20%) of the transportation resource mean information, it is confirmed that the adjusted transportation resource information meets the verification passing condition, and the adjusted transportation resource information is determined as the target transportation resource information. If it is detected that the adjusted transportation resource information does not meet the verification passing condition, the adjusted transportation resource information is retroactively adjusted, or the adjusted transportation resource information can also be adjusted with reference to the transportation resource mean information and transportation resource variance information to obtain the target transportation resource information that meets the verification passing condition.

[0122] In this embodiment, the transportation resource mean information of the target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation task is used to verify the adjusted transportation resource information, so as to output the target transportation resource information of the logistics transportation task. Through the verification mechanism, the accuracy of the transportation resource information is further ensured, and the accuracy and reliability of the dynamic adjustment of the logistics transportation resource information are improved.

[0123] In one embodiment, as Figure 4 shown, another method for processing logistics transportation resources is provided. Taking the method applied to the Figure 1 server in it as an example for illustration, it includes the following steps:

[0124] Step S401: Obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task.

[0125] Step S402: If the logistics transportation task meets the preset urgent task condition, use the target urgent resource information as the constraint condition of the urgent resource prediction model to obtain the constrained urgent resource prediction model.

[0126] Step S403: Input the predicted urgent type and the current total logistics information into the constrained urgent resource prediction model to obtain the predicted urgent resource information of the logistics transportation task.

[0127] Step S404: Obtain the predicted transportation risk information of the logistics transportation task according to the material information and logistics transportation information.

[0128] Step S405: Input the material resource information and predicted transportation risk information of the logistics transportation task into the insurance resource prediction model to obtain the predicted insurance resource information of the logistics transportation task.

[0129] Step S406: Obtain the environmental control resource information and transportation road condition resource information of the logistics transportation task.

[0130] Step S407: Through the rule engine corresponding to the logistics transportation task, according to the predicted urgent resource information, predicted insurance resource information, environmental control resource information and transportation road condition resource information, perform resource adjustment processing on the basic transportation resource information to obtain the adjusted transportation resource information of the logistics transportation task.

[0131] Step S408: From the historical logistics transportation tasks, screen out the target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation task.

[0132] Step S409: Obtain the average transportation resource information of the target historical logistics transportation task; the average transportation resource information is used to determine the passing condition for verification corresponding to the adjusted transportation resource information.

[0133] Step S410: If the adjusted transportation resource information does not meet the passing condition for verification, adjust the adjusted transportation resource information to obtain the target transportation resource information that meets the passing condition for verification.

[0134] The above logistics transportation resource processing method can achieve the following beneficial effects: First, determine the basic transportation resource information of the logistics transportation task through the material information and logistics transportation information, then determine the predicted urgent resource information of the logistics transportation task according to the actual urgent situation, and determine the predicted insurance resource information of the logistics transportation task according to the actual insurance situation. Furthermore, through the rule engine, use the predicted urgent resource information and predicted insurance resource information to dynamically adjust the basic transportation resource information, and finally verify the adjusted transportation resource information, so as to output the target transportation resource information of the logistics transportation task. It not only dynamically adjusts the transportation resource information using the actual urgent situation and insurance situation, but also further ensures the accuracy of the transportation resource information through the verification mechanism, improving the accuracy and reliability of the dynamic adjustment of the logistics transportation resource information.

[0135] To more clearly illustrate the logistics transportation resource processing method provided by the embodiments of the present disclosure, the following uses a specific embodiment to specifically describe the above logistics transportation resource processing method. As Figure 5 shown, another logistics transportation resource processing method is provided, which specifically includes the following content:

[0136] (1) The data acquisition module uses various sensors and data interfaces to collect transportation data. Vehicle speed, fuel consumption, location and other information are obtained through vehicle sensors and GPS; material packaging sensors are used to measure material weight, volume, value and special attributes; dynamic data such as oil prices, road conditions, and transportation supply and demand are obtained from third-party interfaces. The collected data is transmitted to the data processing module, and outliers are removed through a cleaning algorithm. After format conversion and standardization, it is stored in a distributed database according to the data model.

[0137] (2) The billing calculation module extracts the pre-processed material weight and volume and the transportation distance calculated based on the vehicle trajectory from the database. The basic freight is calculated using the following formula: Basic freight = material weight × basic rate per unit weight + material volume × basic rate per unit volume + logistics transportation distance × basic rate per unit distance. Calculate the basic freight.

[0138] (3) The rule engine module analyzes the elements of the transportation task, and through the gradient boosting algorithm and reinforcement learning, determines whether it is an urgent task based on priority and time constraints, and dynamically adjusts the urgent billing rules. It is no longer limited to the preset fixed mode of 30% for ordinary urgent and 50% for special urgent, but intelligently optimizes the cost ratio based on historical data and real-time logistics and resource changes. For the characteristics of materials, if the value is higher than the threshold, the gradient boosting tree model will dynamically adjust the insurance resource information based on the historical transportation risk and insurance payment situation. The range of insurance resource information is (0.5%-2%), and more accurate prediction insurance resource information is generated; when the materials have special environmental requirements, the model accurately calculates the special environmental control resource information based on the equipment usage time and energy consumption data of similar tasks in the past, and generates more targeted resource instructions. Combined with road condition information, the gradient boosting algorithm comprehensively analyzes the relationship between congestion duration and detour distance and the increase in transportation costs. For example, if the model predicts that the increase in congestion duration will lead to a 10% increase in transportation costs, the corresponding additional fees will be added to the basic freight, that is, the adjustment instructions for transportation road condition resource information are obtained.

[0139] (4) The billing calculation module adjusts the basic freight rate according to the instructions of the rule engine. Expedited resource information is calculated by multiplying the basic freight rate by the surcharge ratio; the additional insurance resource information of high-value materials is accumulated by multiplying the material value by the ratio; special environmental control resource information is added based on the equipment duration and energy consumption calculation; the resource information increased due to road conditions is calculated based on the congestion duration and detour distance and incorporated into the total resource information. After a series of calculations and superposition, the adjusted freight rate is obtained.

[0140] (5) The billing calculation module initiates verification of the freight after preliminary adjustment. Retrieve the freight of transportation tasks of the same type, on the same route, and of similar scale from the historical database, calculate the mean and variance, and compare with the current freight. If it exceeds the mean ± 20%, conduct a retrospective check. At the same time, refer to the industry authoritative standards and the freight of peers to ensure that the adjusted freight is within a reasonable range. After passing the verification, output the final freight to the user interaction module.

[0141] (6) The user interaction module displays the details of the freight in a structured table, including the values of various resource information, calculation formulas, and bases, and attaches an analysis report on the composition of the target freight.

[0142] In this embodiment, first determine the basic freight of the logistics transportation task through the material information and logistics transportation information, then determine the predicted urgent resource information of the logistics transportation task according to the actual urgent situation, and determine the predicted insurance resource information of the logistics transportation task according to the actual insurance situation. Furthermore, through the rule engine, use the predicted urgent resource information and predicted insurance resource information to dynamically adjust the basic freight, and finally verify the adjusted freight, so as to output the target freight of the logistics transportation task. This not only dynamically adjusts the freight using the actual urgent situation and insurance situation, but also further ensures the accuracy of the freight through the verification mechanism, improving the accuracy and reliability of the dynamic adjustment of logistics freight.

[0143] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps in other steps.

[0144] Based on the same inventive concept, the embodiment of the present application also provides a logistics transportation resource processing device for implementing the above-mentioned logistics transportation resource processing method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following logistics transportation resource processing device can refer to the limitations on the logistics transportation resource processing method in the above text, and will not be repeated here.

[0145] In one embodiment, as Figure 6As shown, a logistics transportation resource processing device 600 is provided, including: a basic resource determination module 601, an urgent resource determination module 602, an insurance resource determination module 603, a basic resource adjustment module 604, and a target resource determination module 605, where:

[0146] The basic resource determination module 601 is configured to obtain the basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task.

[0147] The urgent resource determination module 602 is configured to, if the logistics transportation task meets the preset urgent task conditions, obtain the predicted urgent resource information of the logistics transportation task through the urgent resource prediction model.

[0148] The insurance resource determination module 603 is configured to obtain the predicted insurance resource information of the logistics transportation task through the insurance resource prediction model.

[0149] The basic resource adjustment module 604 is configured to input the predicted urgent resource information, the predicted insurance resource information, and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task.

[0150] The target resource determination module 605 is configured to perform a verification process on the adjusted transportation resource information according to the historical transportation resource information of the historical logistics transportation task matching the logistics transportation task to obtain the target transportation resource information of the logistics transportation task.

[0151] In one embodiment, the logistics transportation resource processing device 600 further includes an urgent condition judgment module, configured to input the importance and time constraint information of the logistics transportation task into the urgent type prediction model to obtain the predicted urgent type of the logistics transportation task; if it is detected that the predicted urgent type matches the target urgent type corresponding to the urgent task conditions, it is confirmed that the logistics transportation task meets the urgent task conditions.

[0152] In one embodiment, the urgent resource determination module 602 is further configured to use the target urgent resource information as a constraint condition of the urgent resource prediction model to obtain a constrained urgent resource prediction model; the urgent resource prediction model is obtained by training the initial urgent resource prediction model through historical total logistics information, historical urgent types, and historical urgent resource information corresponding to the historical urgent types; input the predicted urgent type and the current total logistics information into the constrained urgent resource prediction model to obtain the predicted urgent resource information of the logistics transportation task.

[0153] In one embodiment, the insurance resource determination module 603 is further configured to obtain the predicted transportation risk information of the logistics transportation task according to the material information and the logistics transportation information; input the material resource information and the predicted transportation risk information of the logistics transportation task into the insurance resource prediction model to obtain the predicted insurance resource information of the logistics transportation task; wherein, the insurance resource prediction model is trained by using the historical material resource information and the historical transportation risk information to process the constrained insurance resource prediction model; the constrained insurance resource prediction model is obtained by processing the initial insurance resource prediction model with the basic insurance resource information as the constraint condition.

[0154] In one embodiment, the basic resource adjustment module 604 is further configured to obtain the environmental control resource information and the transportation road condition resource information of the logistics transportation task; perform resource adjustment processing on the basic transportation resource information according to the predicted urgent resource information, the predicted insurance resource information, the environmental control resource information and the transportation road condition resource information through the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task.

[0155] In one embodiment, the target resource determination module 605 is further configured to screen out the target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation task from the historical logistics transportation tasks; obtain the transportation resource average information of the target historical logistics transportation tasks; the transportation resource average information is used to determine the verification pass condition corresponding to the adjusted transportation resource information; if the adjusted transportation resource information does not meet the verification pass condition, adjust the adjusted transportation resource information to obtain the target transportation resource information that meets the verification pass condition.

[0156] Each module in the above logistics transportation resource processing device can be implemented in whole or in part by software, hardware and their combination. Each of the above modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0157] In one embodiment, a computer device is provided. The computer device can be a server, and a server side is installed on the server. Its internal structure diagram can be as Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as material information, logistics transportation information, basic transportation resource information, and target transportation resource information. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for processing logistics transportation resources.

[0158] Those skilled in the art can understand that Figure 7 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0159] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0160] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0161] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0162] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0163] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0164] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for processing logistics and transportation resources, characterized in that: The method comprises: According to the material information and logistics transportation information of the logistics transportation task, basic transportation resource information of the logistics transportation task is obtained; If the logistics and transportation task meets the preset expedited task conditions, the predicted expedited resource information of the logistics and transportation task is obtained through the expedited resource prediction model; Obtaining predicted insurance resource information for the logistics transportation task through an insurance resource prediction model; Input the predicted expedited resource information, the predicted insurance resource information and the basic transportation resource information into the rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task; The adjusted transportation resource information is verified based on the historical transportation resource information of the historical logistics transportation tasks that match the logistics transportation tasks to obtain the target transportation resource information of the logistics transportation tasks.

2. The method according to claim 1, characterized in that If the logistics transportation task meets the preset expedited task condition, before obtaining the predicted expedited resource information of the logistics transportation task through the expedited resource prediction model, the method further includes: Inputting the importance and time constraint information of the logistics transportation task into the expedited type prediction model to obtain the predicted expedited type of the logistics transportation task; If it is detected that the predicted expedited type matches the target expedited type corresponding to the expedited task condition, it is confirmed that the logistics transportation task meets the expedited task condition.

3. The method according to claim 2, characterized in that The predicted expedited resource information of the logistics transportation task is obtained through the expedited resource prediction model, including: The target expedited resource information is used as a constraint condition of the expedited resource prediction model to obtain a constrained expedited resource prediction model; the expedited resource prediction model is obtained by training an initial expedited resource prediction model through historical total logistics information, historical expedited types, and historical expedited resource information corresponding to the historical expedited types; The predicted expedited type and the current total logistics information are input into the constrained expedited resource prediction model to obtain the predicted expedited resource information of the logistics transportation task.

4. The method according to claim 1, characterized in that: The predicted insurance resource information of the logistics transportation task is obtained through the insurance resource prediction model, including: Obtaining predicted transportation risk information of the logistics transportation task according to the material information and the logistics transportation information; Inputting the material resource information of the logistics transportation task and the predicted transportation risk information into the insurance resource prediction model to obtain the predicted insurance resource information of the logistics transportation task; Among them, the insurance resource prediction model is obtained by training the constrained insurance resource prediction model through historical material resource information and historical transportation risk information; the constrained insurance resource prediction model is obtained by processing the initial insurance resource prediction model with basic insurance resource information as a constraint condition.

5. The method according to claim 1, characterized in that: The step of inputting the predicted expedited resource information, the predicted insurance resource information and the basic transportation resource information into a rule engine corresponding to the logistics transportation task to obtain the adjusted transportation resource information of the logistics transportation task includes: Acquire environmental control resource information and transportation road condition resource information of the logistics transportation task; Through the rule engine corresponding to the logistics transportation task, the basic transportation resource information is adjusted according to the predicted expedited resource information, the predicted insurance resource information, the environmental control resource information and the transportation road condition resource information to obtain the adjusted transportation resource information of the logistics transportation task.

6. The method according to claim 1, characterized in that The process of verifying the adjusted transportation resource information according to the historical transportation resource information of the historical logistics transportation task that matches the logistics transportation task to obtain the target transportation resource information of the logistics transportation task includes: Filtering out target historical logistics transportation tasks that match the logistics transportation information of the logistics transportation tasks from the historical logistics transportation tasks; Obtaining the mean information of transportation resources of the target historical logistics transportation task; the mean information of transportation resources is used to determine the verification pass condition corresponding to the adjusted transportation resource information; If the adjusted transportation resource information does not satisfy the verification pass condition, the adjusted transportation resource information is adjusted to obtain target transportation resource information that satisfies the verification pass condition.

7. A logistics transportation resource processing device, characterized in that: The device comprises: A basic resource determination module is used to obtain basic transportation resource information of the logistics transportation task according to the material information and logistics transportation information of the logistics transportation task; An expedited resource determination module is used to obtain predicted expedited resource information of the logistics transportation task through an expedited resource prediction model if the logistics transportation task meets the preset expedited task conditions; An insurance resource determination module, used to obtain predicted insurance resource information of the logistics transportation task through an insurance resource prediction model; A basic resource adjustment module, used to input the predicted expedited resource information, the predicted insurance resource information and the basic transportation resource information into a rule engine corresponding to the logistics transportation task, to obtain the adjusted transportation resource information of the logistics transportation task; The target resource determination module is used to verify the adjusted transportation resource information based on the historical transportation resource information of the historical logistics transportation tasks that match the logistics transportation tasks, so as to obtain the target transportation resource information of the logistics transportation tasks.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images