Logistics intelligent vehicle distribution method with real-time decision-making capability

Abstract

The invention discloses a logistics intelligent vehicle distribution method with a real-time decision-making capability, and relates to the technical field of logistics transportation, and the method comprises the steps: receiving and analyzing transportation plan data, automatically merging transportation plans meeting merging conditions, and extracting the key information of the merged transportation plans; collecting driver data; jointly forming a project-level real-time matching rule R4 based on the dynamic matching rule R1, the static matching rule R2 and the enterprise customization rule R3; inputting the transportation plan data and the driver data into a matching model, performing multiple rounds of screening and priority ranking according to the project-level real-time matching rule R4, and outputting an optimal vehicle and cargo matching result; and a transportation task is automatically generated according to the vehicle and cargo matching result, and monitoring and early warning are carried out on abnormal conditions based on real-time data in the transportation process. Precise matching of goods and vehicles is achieved, and the automation level, matching accuracy and exception handling timeliness of logistics transportation scheduling are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics transportation, and in particular to a logistics intelligent vehicle allocation method with real-time decision-making capability. BACKGROUND

[0002] As the core link of the modern logistics system, the scheduling efficiency and resource matching accuracy of highway transportation directly affect the operation efficiency of the entire supply chain. With the continuous expansion of China's highway transportation scale, although some enterprises have tried to electronicize the traditional paper process, there are still the following problems: Firstly, the evaluation dimension of transport capacity is single, and most systems only support the matching of basic vehicle models and cargo types, lacking comprehensive consideration of multi-dimensional data such as driver credit status, real-time location, and historical performance.

[0003] Secondly, the risk prevention and control is lagging, and it is impossible to carry out real-time early warning and processing on abnormal situations such as route deviation, loading and unloading overtime, and vehicle failure during transportation.

[0004] Thirdly, the scheduling rules are fixed and poorly adaptable, making it difficult to adapt to sudden changes in external environment such as weather, policy, and traffic conditions, resulting in a large deviation between the scheduling scheme and the actual demand.

[0005] In addition, due to the lack of real-time data perception and dynamic planning capability, there is a problem of more than 30% of transport capacity gap in peak season and more than 40% of idle rate of vehicles in off-season in terms of dynamic matching of transport capacity supply and demand.

[0006] Therefore, there is an urgent need for an intelligent vehicle allocation system that can integrate multi-source data, support dynamic rule configuration, and have real-time decision-making and abnormality early warning capability to meet the urgent needs of modern logistics for fine and intelligent scheduling management. SUMMARY

[0007] In order to solve the above technical problems, the present application provides a logistics intelligent vehicle allocation method with real-time decision-making capability, comprising the following steps: receiving and analyzing transportation plan data, automatically merging transportation plans that meet the merging conditions, and extracting key information of the merged transportation plans; collecting driver data, the driver data including driver's basic data and risk data, wherein the risk data is generated based on the driver's historical performance; generating a project's current static matching rule R2 according to the project's historical cooperation and the platform's built-in rule R, generating a dynamic matching rule R1 through real-time road information, and jointly constituting a project-level real-time matching rule R4 based on the dynamic matching rule R1, the static matching rule R2, and enterprise customized rule R3; inputting the transport plan data and the driver data into a matching model, performing multi-round screening and priority sorting according to the project-level real-time matching rule R4, and outputting an optimal vehicle-goods matching result; generating a transport task automatically according to the vehicle-goods matching result and monitoring and warning an abnormal situation based on real-time data during the transport process.

[0008] Further, the parsing step of the transport plan data comprises: a user maps a table header of a transport plan table with a general field built in a system to convert a user-defined field into a system general field; When importing the transport plan, the same order number transport plan is automatically identified and merged, and the loading and unloading locations and the cargo quantity of the same order number are automatically aggregated.

[0009] Further, the basic data collection method of the driver comprises: basic information of the driver is automatically collected through historical cooperation data of the driver and the platform, and the basic information at least includes a mobile phone number, a license plate number, a vehicle length and a vehicle type; driver certificate information is recorded to the platform by calling a certificate recognition interface to verify validity of the driver certificate; reservation information of the driver is obtained through a driver terminal APP; a location of the driver is obtained in real time through the driver terminal APP and a GPS Beidou positioning.

[0010] Further, the risk data collection method of the driver comprises: the risk data of the driver is comprehensively evaluated by the platform through a punctuality rate, a cargo damage rate, a complaint rate and whether the driver is listed in a blacklist in a historical transport process.

[0011] Further, the step of performing multi-round screening and priority sorting according to the project-level real-time matching rule R4 comprises: (a) the matching model acquires the dynamic matching rule R1, screens the transport plan data or the driver data according to a rule automatically added in the dynamic matching rule R1, and eliminates a driver and / or a vehicle not meeting the rule; (b) a static matching rule R2 is executed to screen a line, a vehicle length and a vehicle type, a delivery time and a reservation arrival time, and a reservation matching range in sequence, and output the transport plan data and the driver data meeting the requirements; (c) the enterprise customized rule R3 is executed to match one transport plan data to the driver data most meeting the project-level real-time matching rule R4.

[0012] Further, the step (a) specifically comprises: The high-risk drivers include blacklisted drivers, drivers with incomplete or expired certificates; The driver history and risk formula is used to calculate the driver history and risk formula, and the calculation result is compared with the risk threshold value, and the driver with a calculation result less than the risk threshold value is removed; The real-time road conditions are obtained through the road interface, and the dynamic matching rule R1 is used to judge the road allowed vehicle length, vehicle type and vehicle load, and the driver data that does not meet the requirements is removed.

[0013] Further, the driver history and risk formula is:

[0014] In the formula, represents the historical cooperation score of the driver and a specific customer; represents the historical cooperation score of the driver and a specific customer; represents the historical average cooperation score of the driver and a specific customer; represents the global historical cooperation score of the platform; , , respectively, , , is the weight of, .

[0015] Further, the step (b) specifically includes: When performing line matching in the static matching rule R2, the line matching is divided into province matching, province-city matching and province-city-district matching, the loading and unloading locations are split by the transportation plan data, and the pre-booking line in the driver data is automatically grouped and matched; When performing vehicle length and type matching in the static matching rule R2, the driver's license information is called according to the vehicle length and type filled in the driver data, and it is judged whether they are consistent. If they are not consistent, they are directly removed. If they are consistent, consistency matching is performed with the vehicle length and type in the split field of the transportation plan data; the transportation plan data and the driver data that successfully match are automatically checked for delivery time and pre-booking arrival time; When performing delivery time and pre-booking arrival time checking in the static matching rule R2, the delivery time in the split field of the transportation plan data and the pre-booking arrival time in the driver data are compared. If the pre-booking arrival time of the driver is not later than the delivery time, the matching is successful, and the pre-booking matching range restriction rule is entered; When the pre-appointment matching range limit rule in the static matching rule R2 is executed, the real-time distance between the driver and the loading location is calculated by acquiring the real-time location of the driver, and the driver data whose real-time distance does not meet the pre-appointment matching range is filtered.

[0016] Further, when the line matching in the static matching rule R2 is executed, the matching of the province, city and district is preferentially performed, and if the matching of the province, city and district fails, the matching of the province and city, and the matching of the province are automatically degraded in turn.

[0017] Further, for the drivers screened through all rules, the driver data with the highest priority is selected for matching by sorting according to the pre-appointment initiation time, the pre-appointment arrival time and the historical pre-appointment matching success rate in the driver data through a priority calculation formula; wherein the priority calculation formula is:

[0018] In the formula, The final priority score is represented, and the higher the value is, the higher the priority is; , The weight coefficient is represented to adjust the relative importance of the pre-appointment initiation time and the pre-appointment arrival time in the priority score; A very large future timestamp constant is represented; The pre-appointment arrival time is represented; The pre-appointment initiation time is represented; The historical pre-appointment matching success rate is represented.

[0019] Further, the abnormal situation in the transportation process is monitored and warned based on real-time data, and specifically includes: The abnormal situation in the execution process of the transportation task is monitored in real time; When the abnormal situation is monitored, the warning information is sent to the enterprise through at least one of the following modes: short message, APP push or voice notification, and the corresponding abnormal data is recorded in the driver historical performance data and applied to subsequent rule matching.

[0020] Further, the abnormal situation in the transportation task execution process includes at least one of the following: driver tardiness, trajectory deviation, long-time stay, cargo damage and loading and unloading overtime.

[0021] Compared with the prior art, the embodiments of the present application have the following beneficial effects: The present application realizes accurate matching of goods and vehicles by constructing intelligent matching strategies of transportation plan data and driver data under relevant rules, and improves the automation level, matching accuracy and timeliness of abnormal processing of logistics transportation scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description only represent some of the embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative efforts based on these drawings also belong to the protection scope of the present application.

[0023] Figure 1 The flow chart of the present application is disclosed. DETAILED DESCRIPTION

[0024] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description only represent some of the embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative efforts based on these drawings also belong to the protection scope of the present application.

[0025] The present application aims to provide a logistics intelligent vehicle allocation method with real-time decision-making capability, an intelligent vehicle allocation system capable of fusing multi-source data, supporting dynamic rule configuration, and having real-time decision-making and abnormality early warning capabilities, so as to meet the urgent needs of modern logistics for fine and intelligent scheduling management.

[0026] Please refer to Figure 1 The logistics intelligent vehicle allocation method mainly includes the following steps: S1, receiving and analyzing transportation plan data P, automatically merging transportation plans meeting the merging conditions, and extracting the key information of the merged transportation plans.

[0027] In a further scheme, the analyzing step of the transportation plan data P includes: S11, the user maps the table header of the transportation plan table with the general field built in the system, so as to convert the user-defined field into the system general field.

[0028] S12, when importing the transportation plan, automatically identifying and merging the transportation plans of the same order number, and automatically adding the loading and unloading locations and the cargo quantity of the same order number.

[0029] The fields identified by the analysis of the transportation plan data P include but are not limited to the delivery time, the plan number, the loading and unloading locations, the cargo name, the cargo category, the cargo unit, the cargo unit price, the vehicle length and type, and the loading and unloading mode.

[0030] Firstly, the user imports the table header of the offline transportation plan form into the system, and maps the Chinese fields of the table header with the general fields built-in the system according to the relationship, such as: shipping address (table header of the user form) - loading location (general field built-in the system). In this way, when the user form is imported subsequently, the system directly converts the fields customized by the user into the general fields of the system according to the preset mapping relationship, ensuring the accuracy of the subsequent matching fields, and also solving the problem of individualization of the fields of different user forms.

[0031] Secondly, when the transportation plan data P is imported into the system, the system automatically merges the transportation plan data P that meets the merging conditions. The merging conditions refer to the fields with the same column values in the user form, which are not limited to the order number.

[0032] In a specific example, when the order number fields are consistent, the key information of the order number fields is extracted and automatically merged, such as automatically merging the loading and unloading locations and automatically adding the cargo quantities. In this way, the user does not need to manually merge, improving the efficiency of the user in subsequent vehicle allocation.

[0033] It should be noted that the order number fields of the user include not only the unique order number field, but also the order number fields of the consignor and the third party.

[0034] S2, automatically collecting driver data D, wherein the driver data D includes basic data and risk data of the driver.

[0035] The basic data of the driver includes the driver's name, mobile phone number, license plate number, vehicle length and type, reservation route, reservation arrival time, driver positioning information, driving license, and road transport permit, etc.

[0036] The risk data of the driver is generated based on the historical performance of the driver.

[0037] S21, the method for collecting the basic data of the driver includes: The basic information of the driver is automatically collected through the historical cooperation data of the driver and the platform, which at least includes the mobile phone number, license plate number, and vehicle length and type.

[0038] The validity of the driver's certificate is verified through the certificate recognition interface, and the driver's certificate information is recorded to the platform as one of the basic information for subsequent matching.

[0039] The reservation information of the driver is obtained through the driver terminal APP, which includes the reservation route and the reservation arrival time. When the logistics enterprise plan is issued subsequently, the driver will be directly matched from the reservation drivers.

[0040] Under the premise of the driver's consent and authorization, the driver's position is obtained in real time through the driver terminal APP and the GPS Beidou positioning.

[0041] S22, the driver's risk data collection method comprises: In the logistics transportation process, the transportation quality and timeliness of the driver are crucial, and the system will automatically collect the risk data of the driver. Through the platform, the on-time rate, the cargo damage rate, the complaint rate and whether the driver is listed in the blacklist at each transportation node in the historical transportation process of the driver are captured to comprehensively evaluate the risk data of the driver. This is matched as a general rule in the subsequent rule matching process.

[0042] S3, according to the project historical cooperation situation and the platform built-in rule R, the current static matching rule R2 of the project is generated, the dynamic matching rule R1 is generated by acquiring real-time road information, and the dynamic matching rule R1, the static matching rule R2 and the enterprise customized rule R3 are used to jointly constitute the project-level real-time matching rule R4.

[0043] It should be noted that the platform will generate the current static matching rule R2 of the project according to the project historical cooperation situation and the platform built-in rule R, but the static matching rule R2 cannot adapt to sudden conditions such as weather changes, policy adjustments, driver transportation risks, etc. Therefore, the dynamic matching rule R1 is generated by acquiring road information, judging the allowed vehicle load, road passing time, etc., and finally the enterprise customized rule R3. Through R1+R2+R3, the project-level real-time matching rule R4 is composed. At the same time, with the real-time adjustment of the subsequent historical transaction data and the dynamic matching rule R1, the project-level real-time matching rule R4 is constantly improved and verified.

[0044] Specifically, the steps of multi-round screening and priority sorting according to the project-level real-time matching rule R4 include: (a) The matching model acquires the dynamic matching rule R1, and screens the transportation plan data P or the driver data D according to the rules automatically added in the dynamic matching rule R1, and eliminates the drivers and / or vehicles that do not meet the rules.

[0045] In a further scheme: The dynamic matching rule R1 is used to eliminate high-risk drivers, wherein the high-risk drivers include blacklisted drivers, drivers with incomplete or expired certificates.

[0046] For the drivers passing the dynamic matching rule R1, the driver historical performance and risk formula are calculated, and the calculation result is compared with the risk threshold T, and the drivers with a calculation result less than the risk threshold T are eliminated. The driver historical performance and risk formula are:

[0047] In the formula, This represents the driver's historical cooperation score with a specific customer, and it accounts for the largest proportion, emphasizing the direct performance of the driver's past cooperation with that customer. It is the average of the performance ratings of all historical orders between the driver and this customer (e.g., a comprehensive rating of on-time rate, damage rate, and complaint rate). Represented as The historical average cooperation score for a specific client project reflects the overall cooperation standard for that client project. The value represents the historical average score of all drivers working with this client, reflecting the overall requirements or difficulty of the client's project. This represents the platform's overall historical cooperation score, used to balance individual differences between customers and drivers. The value is the average cooperation score of all completed orders on the platform; , , They are respectively , , The weight, and .

[0048] Real-time traffic conditions are obtained through the road interface, and dynamic matching rule R1 is used to determine the permitted vehicle length, type, and load of vehicles on the road, and vehicles that do not meet the requirements in the driver data D are removed.

[0049] (b) Execute static matching rule R2 to filter the route, vehicle length and type, delivery time and scheduled arrival time, and scheduled matching range in sequence, and output the transportation plan data P and driver data D that meet the requirements.

[0050] Further plans include: When executing route matching in static matching rule R2, route matching is divided into province matching, province-city matching, and province-city / district matching. The loading and unloading locations are split into fields in the transportation plan data P and automatically grouped for matching with the reserved routes in the driver data D. Specifically, when executing route matching in static matching rule R2, province-city / district matching is prioritized. If province-city / district matching fails, it automatically degrades to province-city matching and then province matching.

[0051] When performing vehicle length and vehicle type matching in static matching rule R2, the driver's license information is first retrieved based on the vehicle length and vehicle type filled in during the appointment in driver data D. If they are inconsistent, the vehicle is directly removed. If they are consistent, then the vehicle length and vehicle type fields in the transportation plan data P are matched for consistency. The successfully matched transportation plan data P and driver data D automatically enter the verification of delivery time and appointment time.

[0052] When performing the shipment time and appointment time check in the static matching rule R2, the obtained shipment time in the split field in the transport plan data P is compared with the appointment time in the driver data D. If the appointment time of the driver is not later than the shipment time, the matching is successful, and the appointment matching range limitation rule is entered.

[0053] When performing the appointment matching range limitation rule in the static matching rule R2, the real-time position of the driver is obtained, the real-time distance between the driver and the loading location is calculated, and the driver data D that does not satisfy the real-time distance in the appointment matching range is filtered. For example, the real-time position of the current driver must satisfy a distance of 200 KM from the loading location. If not, the driver data D is automatically filtered.

[0054] In a further solution, the following steps are performed: After all the filtering rules are screened, there may be a scenario that one transport plan data P corresponds to multiple driver data D. Therefore, the priority of the driver data D needs to be sorted, so as to obtain one driver data D that best matches the transport plan data P.

[0055] For the driver screened by all the rules, the appointment initiation time, the appointment time, and the historical appointment matching success rate in the driver data D are sorted by the priority calculation formula, and the driver data with the highest priority is selected for matching. The priority calculation formula is as follows:

[0056] In the formula, the final priority score is represented by The higher the value is, the higher the priority is. , The weight coefficient is represented by The larger the value is, the earlier the related appointment time is. The appointment time is represented by The smaller the value is, the earlier the appointment time is. The appointment initiation time is represented by The smaller the value is, the earlier the appointment initiation time is. The historical appointment matching success rate is represented by The smaller the value is, the lower the historical appointment matching success rate is.

[0057] (c) The enterprise customized rule R3 is performed, so that one transport plan data P is matched to the driver data D that best matches the project-level real-time matching rule R4.

[0058] S3, input the transportation plan data and the driver data into a matching model, perform multi-round screening and priority sorting according to the project-level real-time matching rule R4, and output an optimal vehicle-goods matching result.

[0059] It should be noted that although each enterprise customized rule can be different, the purpose is to obtain the final accurate matching result after the transportation plan data P and the corresponding driver data D are matched by the above R1+R2+R3 multi-rule dynamic matching. In other words, one transportation plan data P will finally be matched to the driver data D that best meets the project-level real-time matching rule R4.

[0060] S4, automatically generate a transportation task according to the vehicle-goods matching result, and monitor and warn abnormal situations based on real-time data during the transportation process.

[0061] In a further scheme, the transportation plan data P and the corresponding driver data D generate a transportation task T, and all subsequent behaviors of the driver can be operated based on the transportation task T on the APP, including order acceptance, arrival time, transportation clock-in, etc. At the same time, the system will automatically monitor some abnormal situations during the transportation process, and record the abnormal situations to the driver historical performance data, so as to provide a data basis for subsequent rule matching.

[0062] Specifically, the abnormal situations of the transportation task in the execution process are monitored in real time; when the abnormal situation is detected, at least one of the following modes is used to send a warning information to the enterprise: short message, APP push or voice notification, and the corresponding abnormal data is recorded to the driver historical performance data for subsequent rule matching.

[0063] Among them, the abnormal situations in the execution process of the transportation task include driver tardiness, trajectory deviation, long-time stay, cargo damage, loading and unloading overtime, etc.

[0064] The intelligent vehicle matching method realizes accurate matching of goods and vehicles, improves the automation level, matching accuracy and timeliness of abnormal handling of logistics transportation scheduling; at the same time, through forward-looking reservation and planning, the idle rate of transportation capacity is reduced.

[0065] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A logistics intelligent vehicle allocation method with real-time decision-making capability, characterized in that, The method comprises the following steps: receiving and analyzing transportation plan data, automatically merging transportation plans that meet the merging conditions, and extracting key information of the merged transportation plans; collecting driver data, including driver's basic data and risk data, wherein the risk data is generated based on the driver's historical performance; generating a project's current static matching rule R2 based on the project's historical cooperation and the platform's built-in rule R, generating a dynamic matching rule R1 based on real-time road information, and combining the dynamic matching rule R1, the static matching rule R2, and the enterprise's customized rule R3 to form a project-level real-time matching rule R4; inputting the transportation plan data and the driver data into a matching model, performing multiple rounds of screening and priority sorting based on the project-level real-time matching rule R4, and outputting the optimal vehicle-load matching result; automatically generating a transportation task based on the vehicle-load matching result and monitoring and warning abnormal situations based on real-time data during transportation.

2. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1, characterized in that, The analysis step of the transportation plan data comprises: users map the table headers of the transportation plan table with the system's built-in general fields to convert user-defined fields into system general fields; when importing transportation plans, automatically identify and merge transportation plans with the same order number, aggregate the loading and unloading locations of the same order number, and automatically add the quantity of goods.

3. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1, characterized in that, The method for collecting the driver's basic data comprises: automatically collecting the driver's basic information through the driver's historical cooperation data with the platform, including at least mobile phone number, license plate number, vehicle length and type; verifying the validity of the driver's certificate by calling the certificate recognition interface and recording the driver's certificate information to the platform; obtaining the driver's reservation information through the driver's terminal APP; real-time obtaining the driver's location through the driver's terminal APP and GPS Beidou positioning.

4. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1 or 3, characterized in that, The method for collecting the driver's risk data comprises: comprehensively evaluating the driver's risk data by grabbing the driver's punctuality rate, damage rate, complaint rate, and whether he is listed in the blacklist in the historical transportation process through the platform.

5. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1, characterized in that, The step of performing multiple rounds of screening and priority sorting based on the project-level real-time matching rule R4 comprises: (a) the matching model obtains the dynamic matching rule R1, screens the transportation plan data or the driver data according to the automatically added rules in the dynamic matching rule R1, and eliminates drivers and / or vehicles that do not meet the rules; (b) executing the static matching rule R2, sequentially screening the route, vehicle length and type, delivery time and reservation arrival time, and reservation matching range, and outputting the transportation plan data and the driver data that meet the requirements; (c) executing the enterprise's customized rule R3, so that one transportation plan data is matched to the driver data that best meets the project-level real-time matching rule R4.

6. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 5, characterized in that, The step (a) specifically comprises: eliminating high-risk drivers using the dynamic matching rule R1; the high-risk drivers include blacklisted drivers, drivers with incomplete or expired certificates; For the driver passing through the dynamic matching rule R1, the driver history performance and risk formula are calculated again, and the calculation result is compared with the risk threshold, and the driver with a calculation result less than the risk threshold is removed; Through the road interface, the real-time road condition is obtained, the dynamic matching rule R1 is used to judge the length of the vehicle allowed by the road, the vehicle type and the vehicle load, and the vehicle data that does not meet the requirements in the driver data is removed.

7. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 6, characterized in that, The driver history performance and risk formula is: wherein, represents the historical cooperation score for the driver with the particular customer; represents the historical cooperation score for the driver with the particular customer; represents the historical average cooperation score for the driver with the particular customer project; represents the platform global historical cooperation score; , , are, respectively, , , are weights, and .

8. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 5, characterized in that, The step (b) specifically includes: When performing line matching in the static matching rule R2, the line matching is divided into province matching, province-city matching and province-city-district matching, the loading and unloading locations are split by the transportation plan data, and the pre-booking line in the driver data is automatically grouped and matched; When performing length of vehicle and vehicle type matching in the static matching rule R2, the length of vehicle and vehicle type filled in the pre-booking in the driver data is called to judge whether it is consistent with the driver's driving license information, if not, it is directly removed, if consistent, consistency matching is performed with the length of vehicle and vehicle type in the split field of the transportation plan data; the transportation plan data and the driver data matched successfully automatically enter the delivery time and pre-booking arrival time verification; When performing delivery time and pre-booking arrival time verification in the static matching rule R2, the delivery time in the split field of the obtained transportation plan data is compared with the pre-booking arrival time in the driver data, if the pre-booking arrival time of the driver is not later than the delivery time, the matching is successful, and the pre-booking matching range limitation rule is entered; When performing the pre-booking matching range limitation rule in the static matching rule R2, the real-time position of the driver is obtained, the real-time distance between the driver and the loading location is calculated, and the driver data whose real-time distance does not meet the pre-booking matching range is filtered.

9. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 8, characterized in that, When performing line matching in the static matching rule R2, the matching of the province, city and district is preferentially performed, if the province-city-district matching fails, it is automatically degraded to province-city matching and province matching.

10. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 5 or 8, characterized in that, For the driver screened out by all rules, the pre-booking initiation time, pre-booking arrival time and historical pre-booking matching success rate in the driver data are sorted by a priority calculation formula, and the driver data with the highest priority is selected for matching; wherein the priority calculation formula is: wherein, is expressed as a final priority score, with higher values indicating higher priority; , is expressed as a weight coefficient to adjust the relative importance of the appointment initiation time, appointment attendance time in the priority score; is expressed as a large future timestamp constant; is expressed as the appointment attendance time; is expressed as the appointment initiation time; is expressed as the historical appointment match success rate.

11. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1, characterized in that, The monitoring and early warning of abnormal situations based on real-time data in the transportation process specifically includes: Real-time monitoring of abnormal situations in the execution process of the transportation task; When the abnormal situation is monitored, the early warning information is sent to the enterprise by at least one of the following ways: short message, APP push or voice notification, and the corresponding abnormal data is recorded in the driver history performance data and applied to subsequent rule matching.

12. The logistics intelligent vehicle allocation method with real-time decision capability according to claim 1, characterized in that, The abnormal situation in the execution process of the transportation task includes at least one of the following: driver tardiness, trajectory deviation, long-time stay, cargo damage and loading and unloading overtime.

Images