Task distribution method, storage medium and computer program product

Abstract

The present disclosure provides a task distribution method, a storage medium and a computer program product, which relate to the field of computer technology, wherein the method comprises: determining a first job task located within a time window and a second job task located outside the time window, calculating a first priority of the first job task based on a first priority determination factor, and sending the first job task to a client device according to the task time window attribute information and based on the first priority; calculating a second priority of the second job task based on a second priority determination factor, and sorting the second job task based on the second priority; monitoring the execution status of the first job task, and performing corresponding processing operations based on the execution status; the method, device, electronic device and storage medium of the present disclosure balance the problem of excessive time waste in the process of job task processing, and effectively improve the ability to process job tasks, work efficiency and task completion conversion rate.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a task distribution method, a storage medium, and a computer program product. Background Art

[0002] In each link of the real estate transaction between the client and the broker, the broker needs to handle tasks including contract signing, evaluation, face-to-face interview, loan approval, online signing, tax payment, loan release, transfer, mortgage, etc. In the daily process of brokers handling tasks, the operation assistance system can help brokers handle tasks. However, the existing operation assistance system often causes tasks to reach brokers at the same time, and there is no clear distinction between task priorities, which leads to brokers being unable to handle tasks reasonably, unable to reasonably control the time and sequence of tasks, and affecting work efficiency. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure is proposed. The embodiments of the present disclosure provide a task distribution method, a storage medium and a computer program product.

[0004] According to a first aspect of an embodiment of the present disclosure, a task distribution method is provided, including: determining a first job task located within a time window and a second job task located outside the time window based on reception time information of the job task and task time window attribute information; determining a first priority determination factor corresponding to the first job task, and calculating a first priority of the first job task based on the first priority determination factor; sending the first job task to a client device according to the task time window attribute information and based on the first priority; determining a second priority determination factor corresponding to the second job task, and calculating a second priority of the second job task based on the second priority determination factor, so as to sort the second job task based on the second priority; monitoring the execution status of the first job task, and performing corresponding processing operations based on the execution status.

[0005] Optionally, calculating the first priority of the first job task based on the first priority determination factor includes: using a logistic regression LR algorithm and calculating the task priority based on the first priority determination factor as the first priority; calculating the second priority of the second job task based on the second priority determination factor includes: using the LR algorithm and calculating the task priority based on the second priority determination factor as the second priority; wherein the first priority determination factor and the second priority determination factor include: task timeliness, task registration priority, message type, custom task weight, task historical completion rate and task attribution information.

[0006] Optionally, the task timeliness is the quotient of a first time difference and a second time difference; wherein the first time difference is the difference between the current time and the task receiving time, and the second time difference is the difference between the expiration time and the task receiving time.

[0007] Optionally, the message type includes: a notification type and a task type; the method further includes: when the message type of the received job task is a notification type, sending the job task to the client device in real time.

[0008] Optionally, using the LR algorithm to calculate task priority includes: constructing a priority ranking score calculation function based on the task timeliness, the task registration priority, the message type, the custom task weight, the task historical completion rate, the task attribution information and the initialized weight matrix; constructing a prediction function corresponding to the priority ranking score calculation function; constructing a corresponding loss function based on the prediction function; solving based on the loss function to obtain a priority ranking score; wherein the priority ranking score is used as the first priority or the second priority.

[0009] Optionally, the priority ranking score calculation function is:

[0010]

[0011] Where xi is the time limit of the ith task, t is the priority of the ith task during task registration, c is the message type of the ith task, z is the custom task weight of the ith task, h is the historical completion rate of tasks belonging to the same category as the ith task, b is the task attribution information of the ith task, w0 is the initialization weight matrix of the ith task, and w i is the weight matrix of the i-th task.

[0012] Optionally, the task time window attribute information includes: the time window period and the task capacity within the time window; determining the first job task located within the time window and the second job task located outside the time window based on the task reception time information and the task time window attribute information includes: sorting the job tasks based on the job task reception time information; determining the first job task and the second job task according to the sorting result and the time window period and the task capacity within the time window.

[0013] Optionally, the task time window attribute information includes: task sending interval time; sending the first job task to the client device includes: sorting the first job task based on the first priority; and sending the first job task to the client device in sequence according to the sorting result and the task sending interval time.

[0014] Optionally, the processing operation includes: adding a second job task to the time window; the corresponding processing operation based on the execution status includes: when it is determined that a first job task is completed, adding a second job task to the time window.

[0015] Optionally, after a second job task is added to the time window, all job tasks in the time window are sorted according to the second priority of the second job task and the first priorities of all first job tasks remaining in the time window.

[0016] According to a second aspect of an embodiment of the present disclosure, a task distribution device is provided, including: a window task determination module, used to determine a first job task located within a time window and a second job task located outside the time window based on reception time information of the job task and task time window attribute information; a priority determination module, used to determine a first priority determination factor corresponding to the first job task, and calculate a first priority of the first job task based on the first priority determination factor; a window task sending module, used to send the first job task to a client device according to the task time window attribute information and based on the first priority; the priority determination module is also used to determine a second priority determination factor corresponding to the second job task, and calculate a second priority of the second job task based on the second priority determination factor, so as to sort the second job task based on the second priority; a monitoring and processing module, used to monitor the execution status of the first job task, and perform corresponding processing operations based on the execution status.

[0017] Optionally, the priority determination module is used to calculate the task priority using the logistic regression LR algorithm and based on the first priority determination factor as the first priority; and to calculate the task priority using the LR algorithm and based on the second priority determination factor as the second priority; wherein the first priority determination factor and the second priority determination factor include: task timeliness, task registration priority, message type, custom task weight, task historical completion rate and task attribution information.

[0018] Optionally, the task timeliness is the quotient of a first time difference and a second time difference; wherein the first time difference is the difference between the current time and the task receiving time, and the second time difference is the difference between the expiration time and the task receiving time.

[0019] Optionally, the message type includes: a notification type and a task type; the device further includes: a task real-time sending module, which is used to send the job task to the client device in real time when the message type of the received job task is a notification type.

[0020] Optionally, the priority determination module is specifically used to construct a priority ranking score calculation function according to the task timeliness, the task registration priority, the message type, the custom task weight, the task historical completion rate, the task attribution information and the initialization weight matrix; construct a prediction function corresponding to the priority ranking score calculation function; construct a corresponding loss function based on the prediction function; and solve based on the loss function to obtain a priority ranking score, wherein the priority ranking score is used as the first priority or the second priority.

[0021] Optionally, the priority ranking score calculation function is:

[0022]

[0023] Where xi is the time limit of the ith task, t is the priority of the ith task during task registration, c is the message type of the ith task, z is the custom task weight of the ith task, h is the historical completion rate of tasks belonging to the same category as the ith task, b is the task attribution information of the ith task, w0 is the initialization weight matrix of the ith task, and w i is the weight matrix of the i-th task.

[0024] Optionally, the task time window attribute information includes: the time window period and the task capacity within the time window; the window task determination module is used to sort the job tasks based on the receiving time information of the job tasks; and determine the first job task and the second job task according to the sorting result and the time window period and the task capacity within the time window.

[0025] Optionally, the task time window attribute information includes: task sending interval time; the window task sending module is used to sort the first job task based on the first priority; according to the sorting result and the task sending interval time, the first job task is sent to the client device in sequence.

[0026] Optionally, the processing operation includes: adding a second job task to the time window; the monitoring processing module is used to add a second job task to the time window when it is determined that a first job task is completed.

[0027] Optionally, the monitoring and processing module is also used to sort all the job tasks in the time window according to the second priority of the second job task and the first priority of all the first job tasks remaining in the time window after adding a second job task to the time window.

[0028] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the above method.

[0029] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for executing the above method.

[0030] Based on the task distribution method, storage medium and computer program product provided by the above embodiments of the present disclosure, by setting a time window for the job tasks, it is possible to block the job tasks outside the time window, prevent task accumulation due to too many job tasks, balance the problem of excessive waste of time in the job task processing process, reduce the work variance of task processing, and be able to coordinate and schedule job tasks more flexibly, effectively improve the ability to process job tasks, work efficiency and task completion conversion rate, and effectively improve customer experience.

[0031] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] By describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0033] Figure 1 A flowchart of an embodiment of the task distribution method disclosed in the present invention;

[0034] Figure 2A A schematic diagram of processing a broker's job task in the task distribution method disclosed in the present invention;

[0035] Figure 2B It is a schematic diagram of the LR calculation process;

[0036] Figure 3 A schematic diagram of the structure of an embodiment of the task distribution device disclosed in the present invention;

[0037] Figure 4 It is a structural schematic diagram of another embodiment of the task distribution device disclosed in the present invention;

[0038] Figure 5 is a structural diagram of an embodiment of an electronic device disclosed herein. DETAILED DESCRIPTION

[0039] The exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0040] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0041] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0042] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0043] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0044] In addition, the term "and / or" in this disclosure is only a description of the association relationship of associated objects, indicating that there may be three relationships, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the associated objects before and after are in an "or" relationship.

[0045] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0046] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0047] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0048] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0049] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0050] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems or servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0051] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, target programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks can be performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0052] Application Overview

[0053] In the process of implementing the present disclosure, the inventors found that in the process of brokers handling daily work tasks, the use of the work assistance system often results in work tasks reaching the brokers at the same time, and there is no clear distinction between task priorities, resulting in the brokers being unable to handle work tasks reasonably, affecting work efficiency.

[0054] The task distribution method provided by the present invention determines a first job task located within a time window and a second job task located outside the time window, calculates a first priority of the first job task based on a first priority determination factor, and sends the first job task to a client device according to the task time window attribute information and based on the first priority; calculates a second priority of the second job task based on a second priority determination factor, and sorts the second job task based on the second priority; monitors the execution status of the first job task, and performs corresponding processing operations based on the execution status; and by setting a time window for the job task, it is possible to block the job task outside the time window, prevent task accumulation due to too many job tasks, balance the problem of excessive time waste in the job task processing process, reduce the work variance of task processing, and effectively improve the ability to process job tasks, work efficiency, and task completion conversion rate.

[0055] Exemplary Methods

[0056] The step numbers in the present disclosure, such as “step one”, “step two”, “S101”, “S102”, etc., are only for distinguishing different steps and do not represent the sequence between the steps. The order of steps with different numbers can be adjusted during execution.

[0057] Figure 1 A flowchart of an embodiment of the task distribution method disclosed in the present invention is shown in FIG. Figure 1 The method shown includes steps: S101-S105. Each step is described below.

[0058] S101, based on the receiving time information of the task and the task time window attribute information, determine a first task within the time window and a second task outside the time window. The first task and the second task can be tasks such as contract signing, evaluation, face-to-face signing, loan approval, online signing, tax payment, loan issuance, etc.

[0059] In one embodiment, the task time window attribute information includes the time window period and the task capacity within the time window, etc. The job tasks are sorted based on the receiving time information of the job tasks. According to the sorting result and the time window period and the task capacity within the time window, the first job task and the second job task are determined.

[0060] For example, the received job tasks are sorted according to the order of the receiving time of the job tasks. The time window period can be 2 hours, 3 hours, 4 hours, etc., and the task capacity in the time window can be 10, 20, 30, etc. The sorting result of the job tasks is 50 tasks in total. The time window is set with the time window period (for example, 2 hours) as the unit time, and the first 20 job tasks (the same as the time window capacity) are set as the first job tasks, and the remaining 30 job tasks are the second job tasks.

[0061] S102: Determine a first priority determination factor corresponding to a first job task, and calculate a first priority of the first job task based on the first priority determination factor.

[0062] S103: Send the first job task to the client device according to the task time window attribute information and based on the first priority.

[0063] In one embodiment, the first job tasks are sorted based on the first priority. The first job tasks are sequentially sent to the client device according to the sorting result and the task sending interval. For example, the task sending interval is 6 minutes, and according to the sorting result of the first job tasks, one first job task is sent to the client device every 6 minutes. The client device can be a mobile phone, a tablet computer, a PC, and other devices.

[0064] S104, determining a second priority determination factor corresponding to the second job task, and calculating a second priority of the second job task based on the second priority determination factor, so as to sort the second job task based on the second priority.

[0065] S105: monitor the execution status of the first job task, and perform corresponding processing operations based on the execution status.

[0066] In one embodiment, the execution status of the first job task is monitored, and the execution status can be execution completed or execution incomplete. When the execution status of a first job is execution completed, the processing operation performed is to add the second job task to the time window. When the execution status of a first job is execution incomplete, if it is determined that the first job task has a risk of expiration, an expiration warning message is sent to the client device.

[0067] After a second job task is added to the time window, all job tasks in the time window are sorted according to the second priority of the second job task and the first priorities of all first job tasks remaining in the time window.

[0068] In one embodiment, the broker is used as a dimension to distinguish between the job tasks that the current broker has received and the ones that have not been received. Figure 2AAs shown, tasks are divided into tasks that the broker has received or is ready to send in sequence and tasks that the broker has not received. For tasks that the broker has not received, the priority of tasks outside the time window is calculated offline and sorted.

[0069] For the tasks that the broker receives or is about to send, monitor and calculate the timeliness of the tasks within the time window in real time. Task timeliness = current time - received time + expiration reminder time. If there is a risk of expiration of the task, send a reminder message to the broker to remind the broker to complete the task as soon as possible. Monitor the broker status in real time, replace the completed tasks within the current time window, and send new tasks to the broker.

[0070] In one embodiment, the second job tasks outside the time window are calculated and sorted offline by total amount, and the first job tasks within the time window are sent to the broker in sequence at time intervals, and the broker's completion status is tracked in real time. The second job tasks outside the time window are in a blocked state to avoid the accumulation of broker tasks until the first job tasks within the time window are completed. The second job tasks outside the time window are added to the time window, and all tasks that have not been sent within the time window are re-sorted in real time. If the time window is about to enter the next cycle or the broker has not completed the task within the effective time, the broker is reminded to complete a certain first job task as soon as possible. When the time window enters the next cycle, it returns to step S101 and processes in a loop.

[0071] The task distribution method disclosed in the present invention designs a time window for the total amount of tasks of the broker. The task time window attribute is configurable, and a blocking waiting operation can be implemented. Tasks outside the time window are forced to wait, thereby preventing task accumulation due to too many tasks of the broker.

[0072] In one embodiment, the same set of priority determination rules are used for sorting the first job task and the second job task, and factors such as the timeliness of the broker's job task, task type, message type, and task triggering reason are used as sorting factors (priority determination factors) to complete the task sorting within and outside the time window.

[0073] The task priority is calculated based on the first priority determination factor using the logistic regression LR algorithm as the first priority. The task priority is calculated based on the second priority determination factor using the LR algorithm as the second priority. Logistic regression LR is a classification model in machine learning. The first priority determination factor and the second priority determination factor include task timeliness, task registration priority, message type, custom task weight, task historical completion rate, and task attribution information.

[0074] The task expiration is the quotient of the first time difference and the second time difference, the first time difference is the difference between the current time and the task receiving time, and the second time difference is the difference between the expiration time and the task receiving time. The message type includes the notification type and the task type. When the message type of the received job task is the notification type, the job task is sent to the client device in real time.

[0075] A variety of LR algorithms can be used to calculate task priorities. For example, based on task timeliness, task registration priority, message type, custom task weight, task historical completion rate, task attribution information, and initial weight matrix, a priority ranking score calculation function is constructed; a prediction function corresponding to the priority ranking score calculation function is constructed; a corresponding loss function is constructed based on the prediction function; and a solution is performed based on the loss function to obtain a priority ranking score.

[0076] In one embodiment, six priority determination factors are determined as artificial feature variables, namely, task timeliness (x1), priority at task registration (t), message type (notification type, task type) (c), custom task weight (z), task historical completion rate (h), and task attribution information (b). Task timeliness is used to determine the timeliness of the task itself and plays an important role in priority determination. The calculation formula for task timeliness is as follows.

[0077]

[0078] The priority at task registration is the priority defined at task registration, which plays a decisive role in priority determination. The priority at task registration can be an enumeration value {1,2,3,4,5}, and the default is 3. Message type: Notification type messages do not participate in priority determination and are sent to brokers in real time; for task type messages, they participate in priority determination calculation. Custom task weight: The business party needs to participate in the calculation when urgently processing tasks sent to brokers, and the default value is 1. Task attribution: When there is a connection between job tasks, it participates in priority determination calculation; for example, the completion of job task 1 triggers job task 2.

[0079] Based on the dimensions of training speed, resource consumption, explainability, and large broker coverage, the LR algorithm is used as the task priority determination algorithm to convert the task timeliness into a binary classification problem for judgment. The calculation process of the LR algorithm is as follows: Figure 2B As shown, the final priority obtained is urgent or non-urgent information.

[0080] The LR calculation process formula is shown in formula (1-2) and (1-2), and the priority ranking score calculation function is:

[0081]

[0082] Where xi is the time limit of the ith task, t is the priority of the ith task during task registration, c is the message type of the ith task, z is the custom task weight of the ith task, h is the historical completion rate of tasks belonging to the same category as the ith task, b is the task attribution information of the ith task, w0 is the initialization weight matrix of the ith task, and w i is the weight matrix of the i-th task.

[0083] P = Softmax(y) (1-3);

[0084] Formula (1-2) is the formula for calculating the priority ranking score. After obtaining the score, the priority classification is determined according to the subsequent probability value. Substituting formula (1-2) into (1-3) can obtain formula (1-4). Formula (1-3) and formula (1-4) are both probability normalization formulas, the purpose of which is to probabilistically map the priority ranking score obtained by formula (1-2) to the [0,1] interval.

[0085]

[0086] The loss function is shown in formula (1-5):

[0087] l=-∑g i ln(p i ) (1-5);

[0088] Among them, gi indicates whether it is a correct result. The correct result gi is 1, otherwise it is 0.

[0089] Substituting formula (1-4) into formula (1-5) yields formula (1-6), which is used to obtain the gradient vector of the loss function (modifying w along the direction of the gradient vector has the largest rate of change and w changes the fastest).

[0090]

[0091] Among them, formula (1-5) and formula (1-6) are loss calculation formulas. The loss is continuously accumulated to the weight matrix wi to achieve the purpose of updating wi, so that the next prediction is more accurate. For the partial derivative of the loss function w, according to the chain rule, we can get formula (1-7):

[0092]

[0093] According to formula (1-7), we can find the sub-terms respectively and find the partial derivative of y according to formula (1-6) to get formula (1-8):

[0094]

[0095] Taking the partial derivative of formula (1-2) with respect to w, we can obtain formula (1-9):

[0096]

[0097] Substituting formulas (1-8) and (1-9) into formula (1-7), we can obtain the gradient vector calculation method, where P is the predicted value and G is the standard value.

[0098]

[0099] Formula (1-7) and Formula (1-10) are both partial derivative calculation formulas for the weight matrix wi of the loss function calculation formula of Formula (1-5), with the goal of making the weight matrix wi reach the final state wi as quickly as possible; Formula (1-8) and Formula (1-9) are partial interpretations of the chain derivative sub-items of Formula (1-7). Formula (1-10) is the result vector of Formula (1-5), and the largest item is taken as the priority ranking score.

[0100] For example, define a task as x, the vector as [1,1], and the corresponding weight matrix as w[0,1]; task timeliness (x): x / 4 (task reception time is 12:00, expiration time is 24:00, and current time is 15:00); registration priority (t): 3; message type (notification type, task type) (c): task type; task historical completion rate (h): assumption 1; task attribution (b): assumption that task 1 triggers the task attribution coefficient to be -0.5; initialize the weight matrix (w0): assumption 0.

[0101] Substituting the above values ​​into formula (1-2) yields [-0.5, 0.25], and probabilizing the result yields [0.33, 0.71]. Assuming the prediction is correct, gi is 1 and the loss is -ln(0.71), or 3.424. The result of calculation by formula (1-2) is a 1x2 vector, in which the largest item is the priority ranking score (urgent or non-urgent). By introducing a penalty and reward measure for task priority to provide feedback to the business side, the priority of the task registration can be modified in a threshold manner through the adoption of brokers and weekly and monthly statistics on task completion, thereby modifying the future priority ranking of the task.

[0102] Exemplary Devices

[0103] In one embodiment, Figure 3As shown, the present disclosure provides a task distribution device, including: a window task determination module 401, a priority determination module 402, a window task sending module 403, and a monitoring processing module 404. The window task determination module 401 determines a first job task located within a time window and a second job task located outside the time window based on the receiving time information of the job task and the task time window attribute information.

[0104] The priority determination module 402 determines a first priority determination factor corresponding to the first job task, and calculates a first priority of the first job task based on the first priority determination factor. The window task sending module 403 sends the first job task to the client device according to the task time window attribute information and based on the first priority;

[0105] The priority determination module 402 determines a second priority determination factor corresponding to the second job task, and calculates a second priority of the second job task based on the second priority determination factor, so as to sort the second job task based on the second priority. The monitoring processing module 404 monitors the execution status of the first job task, and performs corresponding processing operations based on the execution status.

[0106] In one embodiment, the task time window attribute information includes the time window period and the task capacity within the time window. The window task determination module 401 sorts the job tasks based on the receiving time information of the job tasks, and determines the first job task and the second job task according to the sorting result and the time window period and the task capacity within the time window.

[0107] The task time window attribute information includes the task sending interval time, and the window task sending module 403 sorts the first job tasks based on the first priority, and sends the first job tasks to the client device in sequence according to the sorting result and the task sending interval time. The processing operation includes adding the second job task to the time window, and the monitoring processing module 404 adds a second job task to the time window when determining that a first job task is completed.

[0108] After adding a second job task to the time window, the monitoring processing module 404 sorts all the job tasks in the time window according to the second priority of the second job task and the first priorities of all the remaining first job tasks in the time window.

[0109] The priority determination module 402 uses the logistic regression LR algorithm and calculates the task priority based on the first priority determination factor as the first priority. The priority determination module 402 uses the LR algorithm and calculates the task priority based on the second priority determination factor as the second priority, wherein the first priority determination factor and the second priority determination factor include task timeliness, task registration priority, message type, custom task weight, task historical completion rate, and task attribution information.

[0110] The task distribution device also includes a task real-time sending module 405, such as Figure 4 The message type includes a notification type and a task type. When the message type of the received job task is a notification type, the task real-time sending module 405 sends the job task to the client device in real time.

[0111] In one embodiment, the priority determination module 402 constructs a priority ranking score calculation function according to the task timeliness, the priority at the time of task registration, the message type, the custom task weight, the task historical completion rate, the task attribution information, and the initialization weight matrix. The priority determination module 402 constructs a prediction function corresponding to the priority ranking score calculation function; the priority determination module 402 constructs a corresponding loss function according to the prediction function, and solves based on the loss function to obtain a priority ranking score.

[0112] Figure 5 is a structural diagram of an embodiment of the electronic device disclosed in the present invention, such as Figure 5 As shown, the electronic device 51 includes one or more processors 511 and a memory 512 .

[0113] The processor 511 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 51 to perform desired functions.

[0114] The memory 512 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory, for example, may include: random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory, for example, may include: read-only memory (ROM), hard disk, and flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 511 may run the program instructions to implement the task distribution method of each embodiment of the present disclosure above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0115] In one example, the electronic device 51 may also include: an input device 513 and an output device 514, etc., which are interconnected through a bus system and / or other forms of connection mechanisms (not shown). In addition, the input device 513 may also include, for example, a keyboard, a mouse, etc. The output device 514 may output various information to the outside. The output device 514 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0116] Of course, to simplify, Figure 5 Only some of the components related to the present disclosure in the electronic device 51 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 51 may also include any other appropriate components.

[0117] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the task distribution method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0118] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0119] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps of the task distribution method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0120] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive enumeration) of readable storage media can include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0121] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0122] The task distribution method, storage medium and computer program product in the above-mentioned embodiments can block the job tasks outside the time window by setting a time window for the job tasks, prevent the task accumulation due to too many job tasks, balance the problem of excessive waste of time in the job task processing process, reduce the work variance of task processing, and can more flexibly coordinate and schedule job tasks, effectively improve the ability to process job tasks, work efficiency and task completion conversion rate, and effectively improve customer experience.

[0123] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0124] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present disclosure are intended only as illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems may be connected, arranged, and configured in any manner. Words such as "include," "comprise," "have," and the like are open words, meaning "including but not limited to," and may be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and may be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and may be used interchangeably therewith.

[0125] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0126] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0127] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, etc., will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0128] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A task distribution method, comprising: Based on the receiving time information of the job task and the task time window attribute information, determine a first job task located within the time window and a second job task located outside the time window; Determining a first priority determination factor corresponding to the first job task, and calculating a first priority of the first job task based on the first priority determination factor; Sending the first job task to a client device according to the task time window attribute information and based on the first priority; Determining a second priority determination factor corresponding to the second job task, and calculating a second priority of the second job task based on the second priority determination factor, so as to sort the second job task based on the second priority; Monitoring the execution status of the first job task, and performing corresponding processing operations based on the execution status; The processing operation includes: adding a second job task to the time window; the corresponding processing operation based on the execution status includes: when it is determined that a first job task is completed, adding a second job task to the time window; The task time window attribute information includes the time window period and the task capacity within the time window; the determination of the first job task located within the time window and the second job task located outside the time window based on the receiving time information of the job task and the task time window attribute information includes: sorting the job tasks based on the receiving time information of the job tasks, and determining the first job task and the second job task according to the sorting results and the time window period and the task capacity within the time window.

2. The method according to claim 1, wherein calculating the first priority of the first job task based on the first priority determination factor comprises: Calculate the task priority by using a logistic regression LR algorithm and based on the first priority determination factor as the first priority; The calculating the second priority of the second job task based on the second priority determination factor comprises: The task priority is calculated using the LR algorithm and based on the second priority determination factor as the second priority; wherein the first priority determination factor and the second priority determination factor include: task timeliness, task registration priority, message type, custom task weight, task historical completion rate and task attribution information.

3. The method of claim 2, wherein: The task timeliness is the quotient of the first time difference and the second time difference; wherein the first time difference is the difference between the current time and the task receiving time, and the second time difference is the difference between the expiration time and the task receiving time.

4. The method of claim 2, wherein: The message types include: notification type and task type; the method further includes: When the message type of the received job task is a notification type, the job task is sent to the client device in real time.

5. The method according to claim 2, wherein the step of calculating the task priority using the LR algorithm comprises: Constructing a priority ranking score calculation function according to the task timeliness, the task registration priority, the message type, the custom task weight, the task historical completion rate, the task attribution information and the initialization weight matrix; constructing a prediction function corresponding to the priority ranking score calculation function; Constructing a corresponding loss function according to the prediction function; Solving based on the loss function to obtain a priority ranking score; The priority ranking score is used as the first priority or the second priority.

6. The method of claim 5, wherein: The priority ranking score calculation function is: Where xi is the time limit of the ith task, t is the priority of the ith task during task registration, c is the message type of the ith task, z is the custom task weight of the ith task, h is the historical completion rate of tasks belonging to the same category as the ith task, b is the task attribution information of the ith task, w0 is the initialization weight matrix of the ith task, and w i is the weight matrix of the i-th task.

7. The method of claim 1, further comprising: After a second job task is added to the time window, all job tasks in the time window are sorted according to the second priority of the second job task and the first priorities of all first job tasks remaining in the time window.

8. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the method according to any one of claims 1 to 7.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method described in any one of claims 1 to 7 is implemented.

Images