Vehicle Scheduling Method, Device and Computer Equipment Based on Temporary Tasks

Abstract

The present application relates to a vehicle scheduling method, device, computer device, and storage medium based on temporary tasks. The method includes: obtaining hard constraint information of a current temporary task; determining a historical matching task that matches the current temporary task from a pre-established historical matching table according to the hard constraint information; determining a soft constraint matching score of a vehicle-person combination corresponding to each historical matching task according to first soft constraint information of the current temporary task; determining candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequency, soft constraint matching score, vehicle-person frequency threshold, and soft constraint matching score threshold of each historical matching task; and sorting the candidate vehicle-person combinations according to the vehicle-person frequency and soft constraint matching score of each candidate vehicle-person combination to obtain a target vehicle-person combination for the current temporary task. By using this method, accurate scheduling of temporary tasks can be performed, and the accuracy of vehicle scheduling can be improved.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and particularly to a vehicle scheduling method, device, and computer device based on temporary tasks. Background Art

[0002] In the process of digital automation advancement, the big data scheduling model can better handle the allocation of people and vehicles for tasks with fixed cycles, that is, the so-called static scheduling tasks in the industry. Most static scheduling plans and schedules the drivers and vehicles for each fixed task of the whole month before the beginning of the month. However, at the present stage, the big data scheduling model does not have a sufficiently accurate people-vehicle allocation plan for temporary tasks, which is called dynamic scheduling tasks in the industry, that is, tasks initiated temporarily on the same day or the previous day.

[0003] In the task planning of vehicle and driver scheduling in logistics companies, the scheduling of temporary tasks has always been a difficult point in the industry. In particular, in complex temporary tasks, there may be a part of temporary tasks with special attributes hidden, such as planned tasks converted to temporary tasks. A planned task converted to a temporary task refers to a task that was originally planned one month or many days in advance but was cancelled due to certain unexpected reasons and then resubmitted to the model for scheduling as a temporary task.

[0004] However, the method of vehicle scheduling for planned tasks converted to temporary tasks is to input the planned task converted to a temporary task into the machine learning model for temporary tasks in the form of a temporary task, and obtain the corresponding driver and vehicle combination, resulting in low accuracy of vehicle scheduling for temporary tasks. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a vehicle scheduling method, device, computer device, and storage medium based on temporary tasks that can improve the accuracy of vehicle scheduling for temporary tasks.

[0006] A vehicle scheduling method based on temporary tasks, the method includes:

[0007] Obtain the hard constraint information of the current temporary task;

[0008] Determine the historical matching tasks that match the current temporary task from the pre-established historical matching table according to the hard constraint information;

[0009] Determine the soft constraint matching scores of the people-vehicle combinations corresponding to each of the historical matching tasks according to the first soft constraint information of the current temporary task;

[0010] Determine candidate people-vehicle combinations from the people-vehicle combinations according to the people-vehicle frequencies, the soft constraint matching scores, the people-vehicle frequency threshold, and the soft constraint matching score threshold of each of the historical matching tasks;

[0011] Sort the candidate vehicle - person combinations according to the vehicle - person frequency and soft - constraint matching scores of each candidate vehicle - person combination to obtain the target vehicle - person combination for the current temporary task.

[0012] In one embodiment, the hard - constraint information includes the origin, destination, time period, and vehicle load section; and the matching of the corresponding historical matching tasks from the pre - established historical matching table according to the hard - constraint information includes:

[0013] Match the corresponding historical matching tasks from the pre - established historical matching table according to the origin, destination, time period, and vehicle load section.

[0014] In one embodiment, the determining of the soft - constraint matching scores of the vehicle - person combinations corresponding to each historical matching task according to the first soft - constraint information of the current temporary task includes:

[0015] Obtain the second soft - constraint information of each historical matching task;

[0016] Score the first soft - constraint information and each second soft - constraint information in turn to obtain the soft - constraint matching scores of the vehicle - person combinations corresponding to each historical matching task.

[0017] In one embodiment, the soft - constraint information includes the task departure time, vehicle required tons, and scheduling type; and the scoring of the first soft - constraint information and each second soft - constraint information in turn to obtain the soft - constraint matching scores of the vehicle - person combinations corresponding to each historical matching task includes:

[0018] Perform weighted calculation according to the task departure time, vehicle required tons, and scheduling type of the first soft - constraint information and the task departure time, vehicle required tons, and scheduling type of the second soft - constraint information to determine the matching degree value between the current temporary task and each initial historical matching task;

[0019] Obtain the soft - constraint matching scores of the vehicle - person combinations corresponding to each historical matching task according to the matching degree value.

[0020] In one embodiment, the determining of the candidate vehicle - person combinations from the vehicle - person combinations according to the vehicle - person frequency, the soft - constraint matching scores, the vehicle - person frequency threshold, and the soft - constraint matching score threshold of each historical matching task includes:

[0021] Delete the historical matching tasks with vehicle - person frequency less than the vehicle - person frequency threshold according to the vehicle - person frequency of each historical matching task to obtain the initial vehicle - person combinations;

[0022] Delete the initial vehicle-person combinations with soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of each of the initial vehicle-person combinations to obtain candidate vehicle-person combinations.

[0023] In one embodiment, the sorting of the candidate vehicle-person combinations according to the vehicle-person frequency and soft constraint matching score of each of the candidate vehicle-person combinations to obtain the target vehicle-person combination of the current temporary task includes:

[0024] Obtain the corresponding total soft constraint matching score according to the vehicle-person frequency and soft constraint matching score of each of the candidate vehicle-person combinations;

[0025] Sort the total soft constraint matching score through a vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task.

[0026] In one embodiment, the establishment of the historical matching table includes:

[0027] Obtain historical scheduling task information within a specified time period;

[0028] Extract the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical scheduling task information;

[0029] Determine the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks data to obtain a historical matching table.

[0030] A vehicle scheduling device based on a temporary task, the device includes:

[0031] An acquisition module, configured to acquire the task information of the current temporary task;

[0032] An acquisition module, configured to acquire the hard constraint information of the current temporary task;

[0033] A matching module, configured to determine a historical matching task that matches the current temporary task from a pre-established historical matching table according to the hard constraint information;

[0034] A scoring module, configured to determine the soft constraint matching scores of the vehicle-person combinations corresponding to each of the historical matching tasks according to the first soft constraint information of the current temporary task;

[0035] A determination module, configured to determine candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequency, the soft constraint matching score, the vehicle-person frequency threshold, and the soft constraint matching score threshold of each of the historical matching tasks;

[0036] A sorting module, configured to sort the candidate vehicle-person combinations according to the vehicle-person frequency and the soft constraint matching scores of each candidate vehicle-person combination, so as to obtain the target vehicle-person combination of the current temporary task.

[0037] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Obtain the hard constraint information of the current temporary task;

[0039] Determine the historical matching tasks that match the current temporary task from a pre-established historical matching table according to the hard constraint information;

[0040] Determine the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks according to the first soft constraint information of the current temporary task;

[0041] Determine candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequencies, the soft constraint matching scores, the vehicle-person frequency threshold, and the soft constraint matching score threshold of the historical matching tasks;

[0042] Sort the candidate vehicle-person combinations according to the vehicle-person frequencies and the soft constraint matching scores of each candidate vehicle-person combination, so as to obtain the target vehicle-person combination of the current temporary task.

[0043] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Obtain the hard constraint information of the current temporary task;

[0045] Determine the historical matching tasks that match the current temporary task from a pre-established historical matching table according to the hard constraint information;

[0046] Determine the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks according to the first soft constraint information of the current temporary task;

[0047] Determine candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequencies, the soft constraint matching scores, the vehicle-person frequency threshold, and the soft constraint matching score threshold of the historical matching tasks;

[0048] Sort the candidate vehicle-person combinations according to the vehicle-person frequencies and the soft constraint matching scores of each candidate vehicle-person combination, so as to obtain the target vehicle-person combination of the current temporary task.

[0049] The above vehicle scheduling method, device, computer equipment and storage medium based on temporary tasks obtain the hard constraint information of the current temporary task; determine the historical matching tasks that match the current temporary task from the pre-established historical matching table according to the hard constraint information; determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task according to the first soft constraint information of the current temporary task; determine the candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequencies, soft constraint matching scores, vehicle-person frequency thresholds and soft constraint matching score thresholds of each historical matching task; sort the candidate vehicle-person combinations according to the vehicle-person frequencies and soft constraint matching scores of each candidate vehicle-person combination to obtain the target vehicle-person combination for the current temporary task. By matching the hard constraint information of the current temporary task in the pre-established historical matching table and performing soft constraint scoring on the historical matching tasks according to the first soft constraint information to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks, and sorting according to the vehicle-person frequencies and soft constraint matching scores to determine the target vehicle-person combination, the accuracy of vehicle scheduling for temporary tasks is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a schematic flowchart of a vehicle scheduling method based on temporary tasks in an embodiment;

[0051] Figure 2 is a schematic flowchart of a construction method of a historical matching table in an embodiment;

[0052] Figure 3 is a schematic flowchart of a method of a schematic flowchart in another embodiment;

[0053] Figure 4 is a schematic flowchart of steps of a schematic flowchart in an embodiment;

[0054] Figure 5 is a structural block diagram of a vehicle scheduling device based on temporary tasks in an embodiment;

[0055] Figure 6 is a structural block diagram of a vehicle scheduling device based on temporary tasks in another embodiment;

[0056] Figure 7 is an internal structural diagram of computer equipment in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the objectives, technical solutions and advantages of the present application clearer, 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.

[0058] In one embodiment, as Figure 1As shown, a vehicle scheduling method based on ad-hoc tasks is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0059] Step 102, obtain the hard constraint information of the current ad-hoc task.

[0060] Among them, the current ad-hoc task can be a task temporarily initiated on the same day or the previous day, or a task that was pre-planned (for example, a task planned a month ago) and was cancelled due to certain unexpected reasons and then requested scheduling from the model again in the form of an ad-hoc task. In this embodiment, a logistics task is used as an example for illustration.

[0061] The scheduling task information of the current ad-hoc task includes hard constraint information, soft constraint information, task type, and task status, etc. Among them, the hard constraint information includes the transportation demand flow direction (i.e., from the origin to the destination), transportation time period (in hours), vehicle load section (i.e., the load range of the vehicle, for example, the vehicle load range is 1.2 tons to 2.2 tons), etc.; the soft constraint information includes the planned departure time of the vehicle, planned arrival time at the vehicle, scheduling type, etc., and the scheduling type includes normal working days and weekends, etc.; the task type includes completed status, cancelled status, and in-progress status, etc.

[0062] Step 104, determine the historical matching task that matches the current ad-hoc task from the pre-established historical matching table according to the hard constraint information.

[0063] Among them, the historical matching table is pre-established, and the historical matching table stores data such as the hard constraint information of the cancelled planned scheduling task, the soft constraint information of the completed ad-hoc scheduling task, and the active vehicle-person combinations.

[0064] Specifically, when obtaining the task information of the current ad-hoc task, it is necessary to identify whether the current ad-hoc task is a planned task converted to an ad-hoc task. According to the hard constraint information such as the origin, destination, time period, and vehicle load section in the task information, the corresponding initial historical matching task is matched from the pre-established historical matching table. According to the soft constraint information such as the task departure time, vehicle demand tons, and scheduling type in the task information, the historical matching task that matches the current ad-hoc task is determined from the initial historical matching task.

[0065] Optionally, if there is no initial historical matching task in the pre-established historical matching table that matches the hard constraint information of the current temporary task, the task information of the current temporary task is sent to the traditional scheduling model to obtain the target vehicle-person combination for the current temporary task. The traditional scheduling model selects a suitable vehicle-person combination from the existing vehicle-person combinations to achieve optimal utilization of manpower and vehicles. For example, if there are vehicle A and person A, vehicle B and person B at the current logistics site, but the subsequent tasks of combination A are relatively heavy today, the traditional scheduling model will give priority to recommending vehicle B and person B.

[0066] Step 106: Determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task according to the first soft constraint information of the current temporary task.

[0067] The soft constraint matching score is obtained by scoring the soft constraint information of the current temporary task and the soft constraint information of the historical matching task. It can be obtained according to the task departure time, vehicle demand tons, and scheduling type of the current temporary task and the task departure time, vehicle demand tons, and scheduling type of each historical matching task. The soft constraint matching score can be calculated by the following formula:

[0068] Soft constraint matching score = |Current temporary task departure time (minutes) - Historical matching task departure time (minutes)| * (-a) + |Current temporary task vehicle demand tons - Historical matching task vehicle tons| * (-b) + c (scheduling type)

[0069] Where a, b, and c are adjustable parameters, and the scheduling type can be both weekdays or weekends.

[0070] Specifically, according to the first soft constraint information of the current temporary task, obtain the second soft constraint information of each historical matching task. By scoring the first soft constraint information and the second soft constraint information, the matching degree between the current temporary task and each historical matching task can be obtained, that is, determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task. For example, the more consistent the tonnage of the required vehicle in the soft constraint information, the higher the score; the closer the departure time in minutes, the higher the score; the higher the score when the task occurs on the same weekday or weekend, that is, the higher the matching degree between the current temporary task and each historical matching task. According to the matching degree, the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task can be obtained.

[0071] Step 108: Determine the candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequency, soft constraint matching score, vehicle-person frequency threshold, and soft constraint matching score threshold of each historical matching task.

[0072] Among them, the vehicle-person frequency refers to the number of times different vehicle-person combinations appear in historical matching tasks that match the hard constraint information. The soft constraint matching score threshold is used to characterize the relevance between the vehicle-person combination and the current temporary task. If the soft constraint matching score of the vehicle-person combination is less than the soft constraint matching score threshold, it indicates that the relevance between the vehicle-person combination and the current temporary task is low. Optionally, the soft constraint matching score thresholds in different regions are also different. Specifically, obtain the vehicle-person frequency and soft constraint matching scores of each vehicle-person combination corresponding to each historical matching task. According to the vehicle-person frequency of each historical matching task, delete the historical matching tasks with a vehicle-person frequency less than the vehicle-person frequency threshold to obtain the initial vehicle-person combinations; according to the soft constraint matching scores of each initial vehicle-person combination, delete the initial vehicle-person combinations with a soft constraint matching score less than the soft constraint matching score threshold to obtain candidate vehicle-person combinations.

[0073] Step 110: Sort the candidate vehicle-person combinations according to the vehicle-person frequency and soft constraint matching scores of each candidate vehicle-person combination to obtain the target vehicle-person combination for the current temporary task.

[0074] Specifically, according to the vehicle-person frequency and soft constraint matching scores of each candidate vehicle-person combination, obtain the corresponding total soft constraint matching score; sort the total soft constraint matching score through the vehicle-person recommendation model in the restoration mode to obtain the target vehicle-person combination for the current temporary task. The restoration mode is to learn the recent scheduling habits to make vehicle-person recommendations. For example, if the flow direction of similar time periods in the recent period of the current task is all towards the A vehicle-person combination, although the number of tasks of the A vehicle-person combination is more than that of the B vehicle-person combination, the A vehicle-person combination will still be recommended.

[0075] In the above vehicle scheduling method based on a temporary task, through the hard constraint information of the current temporary task; determine the historical matching tasks that match the current temporary task from the pre-established historical matching table; according to the first soft constraint information of the current temporary task, determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task; according to the vehicle-person frequency, soft constraint matching scores, vehicle-person frequency threshold, and soft constraint matching score threshold of each historical matching task, determine candidate vehicle-person combinations from the vehicle-person combinations; sort the candidate vehicle-person combinations according to the vehicle-person frequency and soft constraint matching scores of each candidate vehicle-person combination to obtain the target vehicle-person combination for the current temporary task. By matching the hard constraint information of the current temporary task in the pre-established historical matching table, performing soft constraint scoring on the historical matching tasks according to the first soft constraint information to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks; sorting the vehicle-person frequency and soft constraint matching scores through the vehicle-person recommendation model in the restoration mode to determine the target vehicle-person combination, which improves the accuracy of vehicle scheduling for temporary tasks.

[0076] In one embodiment, as Figure 2As shown, a method for establishing a historical matching table is provided. In this embodiment, this method is exemplified by being applied to a terminal. In this embodiment, the method includes the following steps:

[0077] Step 202, obtain historical scheduling task information within a specified time period.

[0078] Among them, the specified time period is set according to the actual business scenario requirements and data credibility. For example, in the logistics scenario, the specified time period for a set point can be 30 days. The scheduling task information includes hard constraint information, soft constraint information, task type, task status, and vehicle-person combination information, etc. Among them, the hard constraint information includes the origin, destination, transportation time period, vehicle load segment, etc.; the soft constraint information includes the planned departure time, planned arrival time, scheduling type of the vehicle, etc., and the scheduling type includes normal working days and weekends, etc.; the task type includes the completed status, cancelled status, and in-progress status, etc. Optionally, there is no corresponding vehicle-person combination information for temporarily initiated tasks.

[0079] Step 204, extract the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical scheduling task information.

[0080] Specifically, according to the specified time period set on the terminal, obtain the historical scheduling task information within the specified time period from the historical database, and extract the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date according to the task type in the scheduling task information.

[0081] Step 206, determine the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks data, and obtain the historical matching table.

[0082] Specifically, obtain the scheduling task information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks, compare the hard constraint information (such as the origin, destination, transportation time period, vehicle load segment) of the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date, extract the soft constraint information and vehicle-person information of the completed temporary scheduling tasks that match the hard constraint information of the cancelled planned scheduling tasks, perform activity detection on the vehicle-person information of the extracted completed temporary scheduling tasks, obtain the activity of the vehicle-person combination in each vehicle-person information, when the activity is greater than the preset activity value, determine this vehicle-person combination as an active vehicle-person combination, and obtain the historical matching table of the planned-to-temporary task according to the hard constraint information of the cancelled planned scheduling tasks and the soft constraint information and active vehicle-person combination of the completed temporary scheduling task. Optionally, the historical matching table can be updated according to a preset duration to ensure the accuracy of the data in the historical matching table, and the preset duration can be but not limited to 1 day.

[0083] In the above method for establishing the historical matching table, by obtaining the cancelled scheduled shift tasks and the completed temporary shift tasks on the same date from the historical database, by comparing the hard constraint information of the cancelled scheduled shift tasks and the completed temporary shift tasks data, obtaining the soft constraint information and vehicle-person information of the temporary shift tasks that match the hard constraint information, by performing activity detection on the vehicle-person information, obtaining the active vehicle-person combinations, and obtaining the historical matching table of the planned-to-temporary tasks based on the hard constraint information of the cancelled scheduled shift tasks, the soft constraint information of the completed temporary shift tasks, and the active vehicle-person combinations. By pre-establishing the historical matching table, similarity matching can be performed on the received new tasks to lock whether the new tasks are also planned-to-temporary tasks and determine the type of tasks.

[0084] In another embodiment, as Figure 3 shown, a vehicle scheduling method based on temporary tasks is provided. In this embodiment, an example is given where this method is applied to a terminal. In this embodiment, the method includes the following steps:

[0085] Step 302, obtain the task information of the current temporary task.

[0086] Step 304, according to the origin, destination, time period, and vehicle load section, match the corresponding historical matching tasks from the pre-established historical matching table.

[0087] Step 306, obtain the second soft constraint information of each historical matching task.

[0088] Among them, the second soft constraint information includes the soft constraint information of the historical matching task, including the planned departure time, planned arrival time, scheduling type, etc. of the vehicle.

[0089] Step 308, score the first soft constraint information of the current temporary task and each second soft constraint information in turn to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task.

[0090] Specifically, perform weighted calculation according to the task departure time, vehicle demand tons, and scheduling type of the first soft constraint information and the task departure time, vehicle demand tons, and scheduling type of the second soft constraint information to determine the matching degree value of the current temporary task and each initial historical matching task. Obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task according to the matching degree value.

[0091] Step 310, delete the historical matching tasks with the vehicle-person frequency less than the vehicle-person frequency threshold according to the vehicle-person frequency of each historical matching task to obtain the initial vehicle-person combination.

[0092] Step 312: Delete the initial vehicle-person combinations with soft constraint matching scores less than the soft constraint matching score threshold based on the soft constraint matching scores of each initial vehicle-person combination, and obtain candidate vehicle-person combinations.

[0093] Step 314: Obtain the corresponding total soft constraint matching score based on the vehicle-person frequency and soft constraint matching score of each candidate vehicle-person combination.

[0094] Step 316: Sort the total soft constraint matching score through the vehicle-person recommendation model to obtain the target vehicle-person combination for the current temporary task.

[0095] In the above vehicle scheduling method based on a temporary task, the corresponding historical matching tasks are matched from a pre-established historical matching table according to the departure place, destination, time period, and vehicle load section of the current temporary task, and scored according to the first soft constraint information of the current temporary task and the second soft constraint information of the historical matching task to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task; candidate vehicle-person combinations are obtained according to the vehicle-person frequency and vehicle-person frequency threshold of each historical matching task, as well as the soft constraint matching score and soft constraint matching score threshold, and the corresponding total soft constraint matching score is obtained according to the vehicle-person frequency and soft constraint matching score of each candidate vehicle-person combination. The total soft constraint matching score is sorted through the vehicle-person recommendation model to obtain the target vehicle-person combination for the current temporary task. The historical matching table can effectively identify special tasks with the characteristics of planned to temporary, and the total soft constraint matching score is sorted through the vehicle-person recommendation model in the restoration mode, which improves the vehicle-person matching rate and the accuracy of temporary task scheduling.

[0096] In one embodiment, as Figure 4 shown, a vehicle scheduling step based on a temporary task is provided. In this embodiment, an example is given where this method is applied to a terminal. In this embodiment, this step includes the following:

[0097] Step 402: Establish a historical matching table.

[0098] Specifically, obtain the historical scheduling task information within a specified time period; extract the cancelled planned scheduling tasks and the corresponding completed temporary scheduling tasks on the same date from the historical scheduling task information; determine the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks data to obtain the historical matching table.

[0099] Step 404: Obtain the hard constraint information of the current temporary task.

[0100] Step 406: Determine whether there is a historical matching task that matches the hard constraint information of the current temporary task. If so, execute Step 408; otherwise, execute Step 410.

[0101] Specifically, it is detected whether there is a historical matching task in the pre-established historical matching table that matches the hard constraint information such as the origin, destination, time period, and vehicle load segment. When a historical matching task corresponding to the above is matched from the pre-established historical matching table according to the origin, destination, time period, and vehicle load segment, step 410 is executed; otherwise, step 408 is executed.

[0102] Step 408: Input the task information of the current temporary task into the traditional scheduling model for scheduling.

[0103] Step 410: Obtain the first soft constraint information of the current temporary task and the second soft constraint information of the historical matching task, and perform scoring on the soft constraint information to obtain a soft constraint matching score; then execute step 412.

[0104] Specifically, obtain the second soft constraint information of each historical matching task; score the first soft constraint information and each second soft constraint information in turn, and perform weighted calculation according to the task departure time, vehicle demand tons, and scheduling type of the first soft constraint information and the task departure time, vehicle demand tons, and scheduling type of the second soft constraint information to determine the matching degree value of the current temporary task with each initial historical matching task; obtain the soft constraint matching score of the corresponding vehicle-person combination for each historical matching task according to the matching degree value.

[0105] Step 412: Determine whether the threshold is met. If so, execute step 414; otherwise, execute step 408.

[0106] Specifically, obtain the vehicle-person frequency, soft constraint matching score, vehicle-person frequency threshold, and soft constraint matching score threshold of each historical matching task. According to the vehicle-person frequency of each historical matching task, delete the historical matching tasks with a vehicle-person frequency less than the vehicle-person frequency threshold to obtain an initial vehicle-person combination; according to the soft constraint matching scores of each initial vehicle-person combination, delete the initial vehicle-person combinations with a soft constraint matching score less than the soft constraint matching score threshold to obtain candidate vehicle-person combinations.

[0107] Step 414: Obtain the corresponding total soft constraint matching score according to the vehicle-person frequency and soft constraint matching score of each candidate vehicle-person combination.

[0108] Step 416: Sort the total soft constraint matching scores through the vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task.

[0109] In the above vehicle scheduling steps based on temporary tasks, by obtaining the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical database, and by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks data, the soft constraint information and vehicle-person information of the temporary scheduling tasks that match the hard constraint information are obtained. By detecting the activity of the vehicle-person information, the active vehicle-person combinations are obtained. According to the hard constraint information of the cancelled planned scheduling tasks, the soft constraint information of the completed temporary scheduling tasks, and the active vehicle-person combinations, a historical matching table for planned task transfer to temporary tasks is obtained.

[0110] According to the origin, destination, time period, and vehicle load section of the current temporary task, the corresponding historical matching tasks are matched from the pre-established historical matching table. Scores are given according to the first soft constraint information of the current temporary task and the second soft constraint information of the historical matching tasks to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task. According to the vehicle-person frequency and vehicle-person frequency threshold of each historical matching task, as well as the soft constraint matching score and soft constraint matching score threshold, candidate vehicle-person combinations are obtained. According to the vehicle-person frequency and soft constraint matching score of each candidate vehicle-person combination, the corresponding total soft constraint matching score is obtained. The total soft constraint matching score is sorted by the vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task. Through the historical matching table, special tasks with the characteristics of planned task transfer to temporary tasks can be effectively identified, and the total soft constraint matching score is sorted by the vehicle-person recommendation model in the restoration mode, which improves the vehicle-person matching rate and the accuracy of temporary task scheduling.

[0111] It should be understood that although Figures 1-4 the steps in the flowchart of Figures 1-4 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0112] In one embodiment, as Figure 5 shown, a vehicle scheduling device based on temporary tasks is provided, including: an acquisition module 502, a matching module 504, a scoring module 506, a determination module 508, and a sorting module 510, where:

[0113] The acquisition module 502 is used to acquire the hard constraint information of the current temporary task;

[0114] A matching module 504, configured to determine a historical matching task that matches the current temporary task from a pre-established historical matching table according to the hard constraint information.

[0115] A scoring module 506, configured to determine a soft constraint matching score of the vehicle-driver combination corresponding to each historical matching task according to the first soft constraint information of the current temporary task.

[0116] A determination module 508, configured to determine candidate vehicle-driver combinations from the vehicle-driver combinations according to the vehicle-driver frequency of each historical matching task, the soft constraint matching score, a vehicle-driver frequency threshold, and a soft constraint matching score threshold.

[0117] A sorting module 510, configured to sort the candidate vehicle-driver combinations according to the vehicle-driver frequency and the soft constraint matching score of each candidate vehicle-driver combination, so as to obtain the target vehicle-driver combination of the current temporary task.

[0118] In the above vehicle scheduling device based on a temporary task, through the hard constraint information of the current temporary task, a historical matching task that matches the current temporary task is determined from a pre-established historical matching table; according to the first soft constraint information of the current temporary task, a soft constraint matching score of the vehicle-driver combination corresponding to each historical matching task is determined; according to the vehicle-driver frequency of each historical matching task, the soft constraint matching score, the vehicle-driver frequency threshold, and the soft constraint matching score threshold, candidate vehicle-driver combinations are determined from the vehicle-driver combinations; according to the vehicle-driver frequency and the soft constraint matching score of each candidate vehicle-driver combination, the candidate vehicle-driver combinations are sorted to obtain the target vehicle-driver combination of the current temporary task. By matching the hard constraint information of the current temporary task in the pre-established historical matching table and performing soft constraint scoring on the historical matching tasks according to the first soft constraint information to obtain the soft constraint matching score of the vehicle-driver combination corresponding to the historical matching task; by sorting the vehicle-driver frequency and the soft constraint matching score of the vehicle-driver recommendation model in the restoration mode to determine the target vehicle-driver combination, the accuracy of vehicle scheduling for temporary tasks is improved.

[0119] In one embodiment, as Figure 6 shown, a vehicle scheduling device based on a temporary task is provided. In addition to including a first acquisition module 502, a matching module 504, a second acquisition module 506, a determination module 508, and a sorting module 510, it further includes: a calculation module 512, a comparison module 514, and an extraction module 516, where:

[0120] In one embodiment, the matching module 504 is further configured to match a historical matching task corresponding to the departure according to the departure place, the destination, the time period, and the vehicle load section from a pre-established historical matching table.

[0121] In one embodiment, the obtaining module 502 is further configured to obtain the second soft constraint information of each of the historical matching tasks.

[0122] The scoring module 506 is further configured to score the first soft constraint information and each of the second soft constraint information in sequence to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each of the historical matching tasks.

[0123] The calculation module 512 is configured to perform weighted calculation based on the task departure time, vehicle demand tons, and scheduling type of the first soft constraint information and the task departure time, vehicle demand tons, and scheduling type of the second soft constraint information to determine the matching degree value between the current temporary task matching and each of the initial historical matching tasks.

[0124] The scoring module 506 is further configured to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each of the historical matching tasks according to the matching degree value.

[0125] The comparison module 514 is configured to delete the historical matching tasks with the vehicle-person frequency less than the vehicle-person frequency threshold according to the vehicle-person frequency of each of the historical matching tasks to obtain the initial vehicle-person combinations; and delete the initial vehicle-person combinations with the soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of each of the initial vehicle-person combinations to obtain the candidate vehicle-person combinations.

[0126] The sorting module 510 is further configured to obtain the corresponding total soft constraint matching score according to the vehicle-person frequency and soft constraint matching score of each of the candidate vehicle-person combinations; and sort the total soft constraint matching score through the vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task.

[0127] In one embodiment, the obtaining module 502 is further configured to obtain the historical scheduling task information within a specified time period.

[0128] The extraction module 516 extracts the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical scheduling task information.

[0129] The comparison module 518 is further configured to determine the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling task data to obtain a historical matching table.

[0130] In one embodiment, by obtaining the cancelled scheduled shift tasks and the completed temporary shift tasks on the same date from the historical database, by comparing the hard constraint information of the cancelled scheduled shift tasks and the completed temporary shift tasks data, obtaining the soft constraint information and vehicle and driver information of the temporary shift tasks that match the hard constraint information, by detecting the activity of the vehicle and driver information, obtaining the active vehicle and driver combinations, and obtaining the historical matching table of the planned-to-temporary tasks based on the hard constraint information of the cancelled scheduled shift tasks, the soft constraint information of the completed temporary shift tasks, and the active vehicle and driver combinations.

[0131] According to the origin, destination, time period, and vehicle load section of the current temporary task, match the corresponding historical matching tasks from the pre-established historical matching table, score according to the first soft constraint information of the current temporary task and the second soft constraint information of the historical matching tasks, and obtain the soft constraint matching scores of the vehicle and driver combinations corresponding to each historical matching task; according to the vehicle and driver frequency and vehicle and driver frequency threshold of each historical matching task, as well as the soft constraint matching score and soft constraint matching score threshold, obtain the candidate vehicle and driver combinations, obtain the corresponding total soft constraint matching scores according to the vehicle and driver frequency and soft constraint matching scores of each candidate vehicle and driver combination, sort the total soft constraint matching scores through the vehicle and driver recommendation model, obtain the target vehicle and driver combination of the current temporary task, and through the historical matching table, can effectively identify the special tasks with the characteristics of planned-to-temporary, and sort the total soft constraint matching scores through the vehicle and driver recommendation model in the restoration mode, improving the vehicle and driver matching rate and the accuracy of temporary task scheduling.

[0132] For the specific limitations of the vehicle scheduling device based on temporary tasks, reference can be made to the limitations of the vehicle scheduling method based on temporary tasks in the above text, which will not be elaborated here. Each module in the above vehicle scheduling device based on temporary tasks can be implemented in whole or in part by software, hardware, and their combinations. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0133] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 7As shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, operator networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a vehicle scheduling method based on temporary tasks. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball, or touchpad set on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0134] 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.

[0135] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0136] Obtain the hard constraint information of the current temporary task;

[0137] Determine the historical matching tasks that match the current temporary task from the pre-established historical matching table according to the hard constraint information;

[0138] According to the first soft constraint information of the current temporary task, determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task;

[0139] Determine the candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequencies, soft constraint matching scores, vehicle-person frequency thresholds, and soft constraint matching score thresholds of each historical matching task;

[0140] Sort the candidate vehicle-person combinations according to the vehicle-person frequencies and soft constraint matching scores of each candidate vehicle-person combination to obtain the target vehicle-person combination of the current temporary task.

[0141] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0142] Match the corresponding historical matching tasks from the pre-established historical matching table according to the origin, destination, time period, and vehicle load segment.

[0143] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0144] Obtain the second soft constraint information of each historical matching task;

[0145] Score the first soft constraint information and each second soft constraint information in turn to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task.

[0146] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0147] Perform weighted calculations based on the task departure time, vehicle demand tons, and scheduling type of the first soft constraint information and the task departure time, vehicle demand tons, and scheduling type of the second soft constraint information to determine the matching degree values between the current temporary task and each initial historical matching task;

[0148] Obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task according to the matching degree values.

[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0150] Delete the historical matching tasks with vehicle-person frequencies less than the vehicle-person frequency threshold according to the vehicle-person frequencies of each historical matching task to obtain the initial vehicle-person combinations;

[0151] Delete the initial vehicle-person combinations with soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of each initial vehicle-person combination to obtain the candidate vehicle-person combinations.

[0152] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0153] Obtain the corresponding total soft constraint matching scores according to the vehicle-person frequencies and soft constraint matching scores of each candidate vehicle-person combination;

[0154] Sort the total soft constraint matching scores through the vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task.

[0155] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0156] Obtain the historical scheduling task information within a specified time period;

[0157] Extract the cancelled planned scheduling tasks and the corresponding completed temporary scheduling tasks on the same date from the historical scheduling task information;

[0158] By comparing the hard constraint information of the cancelled scheduled tasks and the completed ad-hoc scheduled task data, the corresponding soft constraint information and vehicle-person information are determined to obtain a historical matching table.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0160] Obtain the hard constraint information of the current ad-hoc task;

[0161] Determine the historical matching tasks that match the current ad-hoc task from the pre-established historical matching table according to the hard constraint information;

[0162] According to the first soft constraint information of the current ad-hoc task, determine the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task;

[0163] Determine the candidate vehicle-person combinations from the vehicle-person combinations according to the vehicle-person frequencies, soft constraint matching scores, vehicle-person frequency thresholds, and soft constraint matching score thresholds of each historical matching task;

[0164] Sort the candidate vehicle-person combinations according to the vehicle-person frequencies and soft constraint matching scores of each candidate vehicle-person combination to obtain the target vehicle-person combination of the current ad-hoc task.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0166] Match the corresponding historical matching tasks from the pre-established historical matching table according to the origin, destination, time period, and vehicle load section.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0168] Obtain the second soft constraint information of each historical matching task;

[0169] Score the first soft constraint information and each second soft constraint information in turn to obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task.

[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0171] Perform weighted calculation according to the task departure time, vehicle demand tons, and scheduling type of the first soft constraint information and the task departure time, vehicle demand tons, and scheduling type of the second soft constraint information to determine the matching degree values of the current ad-hoc task and each initial historical matching task;

[0172] Obtain the soft constraint matching scores of the vehicle-person combinations corresponding to each historical matching task according to the matching degree values.

[0173] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0174] Delete the historical matching tasks with the vehicle-person frequencies less than the vehicle-person frequency threshold according to the vehicle-person frequencies of each historical matching task to obtain the initial vehicle-person combinations;

[0175] Delete the initial vehicle-person combinations with the soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of each initial vehicle-person combination to obtain the candidate vehicle-person combinations.

[0176] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0177] Obtain the corresponding total soft constraint matching scores according to the vehicle-person frequencies and soft constraint matching scores of each candidate vehicle-person combination;

[0178] Sort the total soft constraint matching scores through the vehicle-person recommendation model to obtain the target vehicle-person combination of the current temporary task.

[0179] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0180] Obtain the historical scheduling task information within a specified time period;

[0181] Extract the cancelled planned scheduling tasks and the corresponding completed temporary scheduling tasks on the same date from the historical scheduling task information;

[0182] Determine the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling task data to obtain the historical matching table.

[0183] 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, storage, 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 memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. 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.

[0184] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of 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 recorded in this specification.

[0185] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. 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 patent of the present application shall be subject to the appended claims.

Claims

1. A vehicle scheduling method based on temporary tasks, characterized in that, The method includes: Obtaining the hard constraint information of the current temporary task; the hard constraint information includes the origin, destination, time period, and vehicle load section; Determining a historical matching task that matches the current temporary task from a pre-established historical matching table according to the hard constraint information; Determining the soft constraint matching scores of the vehicle and driver combinations corresponding to each of the historical matching tasks according to the first soft constraint information of the current temporary task, including: obtaining the second soft constraint information of each of the historical matching tasks according to the first soft constraint information of the current temporary task, scoring the first soft constraint information and the second soft constraint information to obtain the matching degree between the current temporary task and each of the historical matching tasks, and determining the soft constraint matching scores of the vehicle and driver combinations corresponding to each of the historical matching tasks according to the matching degree value; the soft constraint information includes the task departure time, the required vehicle tonnage, and the scheduling type; Deleting the historical matching tasks with the vehicle and driver frequency less than the vehicle and driver frequency threshold according to the vehicle and driver frequencies of each of the historical matching tasks to obtain an initial vehicle and driver combination; deleting the initial vehicle and driver combinations with the soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of each of the initial vehicle and driver combinations to obtain candidate vehicle and driver combinations; Sorting the candidate vehicle and driver combinations according to the vehicle and driver frequencies and soft constraint matching scores of each of the candidate vehicle and driver combinations to obtain the target vehicle and driver combination of the current temporary task; Among them, the establishment of the historical matching table includes: Obtaining the historical scheduling task information within a specified time period; Extracting the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical scheduling task information; Determining the corresponding soft constraint information and vehicle and driver information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks to obtain a historical matching table.

2. The method according to claim 1, characterized in that, The scoring of the first soft constraint information and the second soft constraint information to obtain the matching degree between the current temporary task and each of the historical matching tasks, that is, determining the soft constraint matching scores of the vehicle and driver combinations corresponding to each of the historical matching tasks, includes: Performing weighted calculation according to the task departure time, the required vehicle tonnage, and the scheduling type of the first soft constraint information and the task departure time, the required vehicle tonnage, and the scheduling type of the second soft constraint information to determine the matching degree value between the current temporary task and each of the historical matching tasks; Obtaining the soft constraint matching scores of the vehicle and driver combinations corresponding to each of the historical matching tasks according to the matching degree value.

3. The method according to claim 1, characterized in that, The sorting of the candidate vehicle and driver combinations according to the vehicle and driver frequencies and soft constraint matching scores of each of the candidate vehicle and driver combinations to obtain the target vehicle and driver combination of the current temporary task includes: Obtaining the corresponding total soft constraint matching score according to the vehicle and driver frequencies and soft constraint matching scores of each of the candidate vehicle and driver combinations; Sorting the total soft constraint matching score through a vehicle and driver recommendation model to obtain the target vehicle and driver combination of the current temporary task.

4. The method according to claim 1, characterized in that, It also includes: Performing similarity matching on the received new task through the historical matching table to lock whether the new task is a planned task transferred to a temporary task and determine the type of the task.

5. The method according to any one of claims 1-4, further comprising: If there is no historical matching task in the historical matching table that matches the hard constraint information of the current temporary task, input the task information of the current temporary task into the traditional scheduling model for scheduling.

6. A vehicle scheduling device based on temporary tasks, characterized in that, The device includes: An acquisition module, configured to acquire the task information of the current temporary task; An acquisition module, configured to acquire the hard constraint information of the current temporary task; the hard constraint information includes the origin, destination, time period, and vehicle load segment; A matching module, configured to determine, according to the hard constraint information, a historical matching task that matches the current temporary task from a pre-established historical matching table; A scoring module, configured to determine the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks according to the first soft constraint information of the current temporary task, including: acquiring the second soft constraint information of each historical matching task according to the first soft constraint information of the current temporary task, scoring the first soft constraint information and the second soft constraint information to obtain the matching degree between the current temporary task and each historical matching task, and determining the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks according to the matching degree value; the soft constraint information includes the task departure time, the required vehicle tonnage, and the scheduling type; A determination module, configured to delete the historical matching tasks with the vehicle-person frequency less than the vehicle-person frequency threshold according to the vehicle-person frequencies of the historical matching tasks to obtain an initial vehicle-person combination; and delete the initial vehicle-person combinations with the soft constraint matching scores less than the soft constraint matching score threshold according to the soft constraint matching scores of the initial vehicle-person combinations to obtain candidate vehicle-person combinations; A sorting module, configured to sort the candidate vehicle-person combinations according to the vehicle-person frequencies and the soft constraint matching scores of the candidate vehicle-person combinations to obtain the target vehicle-person combination of the current temporary task; Among them, the establishment of the historical matching table includes: Acquiring the historical scheduling task information within a specified time period; Extracting the cancelled planned scheduling tasks and the completed temporary scheduling tasks on the same date from the historical scheduling task information; Determining the corresponding soft constraint information and vehicle-person information by comparing the hard constraint information of the cancelled planned scheduling tasks and the completed temporary scheduling tasks to obtain a historical matching table.

7. The device according to claim 6, characterized in that, The scoring module is specifically configured to: Perform weighted calculation according to the task departure time, the required vehicle tonnage, and the scheduling type of the first soft constraint information and the task departure time, the required vehicle tonnage, and the scheduling type of the second soft constraint information to determine the matching degree value between the current temporary task and each historical matching task; Obtain the soft constraint matching scores of the vehicle-person combinations corresponding to the historical matching tasks according to the matching degree value.

8. The device according to claim 6 or 7, characterized in that, It further includes a module for: Performing similarity matching on the received new task through the historical matching table to lock whether the new task is a planned-to-temporary task and determine the type of the task.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

Images