CN113139795A - Business process task scheduling system, equipment and method based on personal schedule assistant - Google Patents

Business process task scheduling system, equipment and method based on personal schedule assistant Download PDF

Info

Publication number
CN113139795A
CN113139795A CN202110501155.3A CN202110501155A CN113139795A CN 113139795 A CN113139795 A CN 113139795A CN 202110501155 A CN202110501155 A CN 202110501155A CN 113139795 A CN113139795 A CN 113139795A
Authority
CN
China
Prior art keywords
task
business process
time
completion time
feedback
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110501155.3A
Other languages
Chinese (zh)
Inventor
王伟
曹健
林树鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangyin Zhuri Information Technology Co ltd
Original Assignee
Jiangyin Zhuri Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangyin Zhuri Information Technology Co ltd filed Critical Jiangyin Zhuri Information Technology Co ltd
Publication of CN113139795A publication Critical patent/CN113139795A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
    • G06Q10/1093—Calendar-based scheduling for persons or groups
    • G06Q10/1097—Task assignment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Optimization (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Operations Research (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Economics (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Marketing (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a service flow task scheduling system based on a personal schedule assistant, which comprises a personal schedule assistant subsystem and a service process task scheduling engine subsystem, wherein the personal schedule assistant subsystem is configured to execute task completion time, user interaction and task scheduling; wherein the business process task scheduling engine subsystem is configured to perform task pre-allocation, task allocation, and task completion time prediction.

Description

Business process task scheduling system, equipment and method based on personal schedule assistant
Technical Field
The invention relates to the technical field of business process task allocation, in particular to a business process task scheduling system, equipment and method based on personal schedule assistant.
Background
In the business process, how to select proper personnel for different tasks is an important problem. The state of the personnel changes at any moment, and some emergency situations can occur, so that the task cannot be completed on time.
At present, the methods for distributing personnel in the business process mainly include: (1) and (4) judging the personnel and the task condition by the system, and directly distributing the task to the proper personnel. (2) And sending the tasks to be received to all the candidate personnel by the system, and receiving and submitting the tasks by the waiting personnel. The push-pull mode and the push-pull mode have respective advantages and disadvantages, the push-pull distribution mode is distributed by the system, the system can be ensured to be relatively stable, all tasks are ensured to be charged by personnel, the conditions of the personnel are not considered, the flexibility is not realized, and the complex industrial production environment is difficult to adapt. The pull allocation is relatively flexible but may result in a task that is unattended. And in both cases, the situation that when the assigned personnel can not complete the task in case of emergency, other people can not be handed over in time can not be handled.
Disclosure of Invention
One of the objectives of the present invention is to provide a system, a device and a method for scheduling tasks of a business process based on a personal calendar assistant, which can implement a push-pull combination and an automatic feedback coordination allocation manner, wherein a user interacts with the personal calendar assistant, the personal calendar assistant automatically feeds back to a task scheduling engine of the business process, the task scheduling engine selects suitable personnel according to the feedback and the prediction result, and performs real-time replacement when the allocated personnel cannot complete the tasks in time.
In order to achieve at least one of the above objects, the present invention provides a personal calendar assistant-based business process task scheduling system, which includes a personal calendar assistant subsystem and a business process task scheduling engine subsystem,
the system comprises a personal schedule assistant subsystem, a business process task scheduling engine subsystem and a business process task scheduling engine subsystem, wherein the personal schedule assistant subsystem is configured to execute task completion time, user interaction and task scheduling, when a task in personal schedule assistance arrives, the personal schedule assistant subsystem executes interaction with a user, acquires information fed back by the user, and schedules the task according to task priority;
the business process task scheduling engine subsystem is configured to execute task pre-allocation, task allocation and task completion time prediction, when a task arrives, the task enters a pre-allocation stage, the task is pre-allocated to all candidates, and feedback information of a user is acquired within a set time range; and after the business process task scheduling engine subsystem acquires all feedback information, the task enters a distribution stage, and the optimal personnel are selected to distribute the task.
In some embodiments, the personal calendar assistant subsystem includes a user interaction unit, a task prediction unit, and a task scheduling unit, the user interaction unit is configured to perform interaction with a user, obtain current task information, task information adjustment, and personal assistant adjustment, the task prediction unit is configured to predict task completion time, and the task scheduling unit is configured to perform sequencing on task execution sequence, feed back with the business process task scheduling engine subsystem, and feed back task information in real time.
In some embodiments, the user interaction unit of the personal calendar assistant subsystem comprises a task real-time acquisition module, a task real-time adjustment module and a personal assistant configuration module, wherein the task real-time acquisition module is used for acquiring the conditions of pre-assigned tasks and assigned tasks of a user in real time; the task real-time adjusting module is used for executing task adjustment and task rejection, wherein the task adjustment includes the adjustment of task priority and predicted completion time, the priority is the priority degree of the task, the predicted completion time is the completion time predicted according to the system, the dynamic adjustment is executed in response to the actual condition requirement of the user, the task rejection is the requirement in response to the emergency task condition of the user, the user is allowed to reject to accept the task, and the personal schedule assistant subsystem feeds back the task scheduling engine subsystem to the business process; the personal schedule assistant configuration module is used for setting the maximum workload and the default priority, wherein the workload is the workload measurement of the task, the maximum workload is the sum of the maximum task workloads allowed to be accepted by the user and is evaluated by the system, and the default priority is the default priority when the task arrives.
In some embodiments, wherein for a current pre-assigned task and an assigned task, the task prediction unit of the personal calendar assistant subsystem builds a task completion time prediction algorithm model that predicts the time that a task needs to consume when it arrives or when it adjusts.
In some embodiments, the task prediction unit includes a task completion time prediction algorithm model data acquisition module, where the task completion time prediction algorithm model data acquisition module acquires all instances of the task type, and acquires task workloads and task completion times under the instances, where the workloads are measured according to the workload, the task workload of an instance is the sum of the workloads of the personnel receiving the task, and the task completion time is the time required for task completion.
In some embodiments, the task prediction unit further comprises a task completion time prediction algorithm model training module that trains a regression model based on workload and completion time
T～aL+∈
Wherein T is the completion time, L is the workload, a is the coefficient of L, epsilon is the residual error of the regression model, and the regression coefficient of the workload is obtained by training the model.
In some embodiments, wherein the task prediction unit further comprises a task completion time prediction module that predicts a completion time of the person under the task of the task type with a current person workload as an input
Figure BDA0003056364070000033
Wherein
Figure BDA0003056364070000034
Regression coefficients for the workload are obtained for the training model.
In some embodiments, the task scheduling unit of the personal calendar assistant subsystem comprises a task ordering module and an automatic feedback module, wherein the task ordering module orders tasks according to priorities set by a user, and determines a priority for performing tasks when pre-assigned tasks arrive or in response to a task modification operation of the user; and the automatic feedback module and the service process task scheduling engine subsystem execute pre-distribution task feedback interaction and distributed task feedback interaction.
In some embodiments, the automatic feedback module includes a pre-assigned task feedback module and an assigned task feedback module, the pre-assigned task feedback module performs feedback at a pre-assigned task stage of the business process task scheduling engine subsystem, and performs feedback automatically when it is detected that a user determines a task or when a waiting time is over, and the assigned task feedback module performs feedback to the business process task scheduling engine subsystem to instruct the business process task scheduling engine subsystem to reschedule a task when it is detected that the user cannot complete the task in time or the user refuses to accept the task when it is detected that the business process task scheduling engine subsystem allocates the task to the user.
In some embodiments, wherein the task ranking module of the task scheduling unit of the personal calendar assistant subsystem performs task ranking, wherein the task ranking module is configured to: receiving the businessTask k distributed by the task process task scheduling engine subsystem; if the current personnel do not execute the task, the task is taken as the task to be executed currently; if the current person is performing n tasks, wherein the workload of the n tasks is L1,L2,…,LnPriority is K1,K2,…,KnPredicted completion time is T1,T2,…,TnThe workload of task k is LkPriority is KkPredicted completion time is TkJudging whether the personnel reaches the maximum working load, if so
Figure BDA0003056364070000031
Entering the task into the next round of judgment; if it is not
Figure BDA0003056364070000032
Judging whether the task priority meets the condition; if the task priority
Figure BDA0003056364070000041
The task enters the next round of judgment, if the task priority
Figure BDA0003056364070000042
Then the task is taken as the currently executed task; when the task k enters the next round of judgment, the time is pushed to the completion of one task, and the predicted completion time of the task is increased
Figure BDA0003056364070000043
Namely, it is
Figure BDA0003056364070000044
At the moment, the information that the personnel finish a task is received, and whether the task k is used as the task executed in the round or not is judged again; and so on until the j-th cycle task k allows to join the task; calculating the final task completion time Tk。
In some embodiments, the business process task scheduling engine subsystem comprises a current task completion time prediction unit, a task pre-allocation scheduling unit, and a task allocation scheduling unit, wherein the current task completion time prediction unit is configured to predict a current task completion time; wherein the task pre-allocation scheduling unit is configured to perform task pre-allocation, requiring candidates to feed back an expected completion time; and the task allocation scheduling unit is configured to execute task allocation, and select corresponding personnel to execute allocation according to the predicted time and the feedback result.
In some embodiments, the current task completion time prediction unit of the business process task scheduling engine subsystem comprises a historical data acquisition module, wherein the historical data acquisition module acquires historical data of a specific person p and a specific task k, including n business process contexts C1,C2,…,CnThe personnel workload L and the completion time T of the corresponding task.
In some embodiments, the current task completion time prediction unit of the business process task scheduling engine subsystem further comprises a current task completion time prediction model training module, wherein the current task completion time prediction model training module is configured to train the current task completion time prediction model according to the acquired n business process contexts C1,C2,…,CnPersonnel load L, completion time T, training a regression model, wherein the formula of the regression model is as follows:
Figure BDA0003056364070000045
wherein, aiRepresenting the ith business process context CiB represents the coefficient of the workload L, and e represents the regression equation residuals, respectively. Training get Business Process context C1,C2,…,CnRegression coefficient of
Figure BDA0003056364070000046
And regression coefficient of workload
Figure BDA0003056364070000047
In some embodiments, the current task completion time prediction unit of the business process task scheduling engine subsystem further comprises a current task completion time prediction module that predicts the current task completion time as a business process context c1,c2…, person load l as input, predicting the completion time of different persons using a machine learning model
Figure BDA0003056364070000048
The task pre-allocation scheduling unit of the business process task scheduling engine subsystem comprises a candidate pre-allocation module and a task pushing module, wherein the candidate pre-allocation module traverses personnel in sequence and adds all candidates into a pre-allocation queue; and assuming that the pre-distribution queue is not empty, setting waiting time by the task pushing module, pushing the tasks to the personal schedule assistant subsystems of all the personnel in the pre-distribution queue, and indicating the personal schedule assistant subsystems to feed back results of completing the tasks in the waiting time.
In some embodiments, the task allocation scheduling unit of the business process task scheduling engine subsystem comprises a candidate predicted time calculation module, wherein the feedback time validity determination module is configured to:
obtaining the feedback time T of the corresponding personnelRJudging whether the feedback of the personnel is effective or not; the effective judgment formula of the feedback time is as follows:
Figure BDA0003056364070000051
where n is the amount of history data, k is the threshold for the amount of history, εTIs the ratio of the maximum effective feedback time under the condition that n is less than or equal to k, TcPredicting the time of different persons; r is the historical performance rate, theta is the performance rate threshold,
Figure BDA0003056364070000052
in order to be a historical prediction value,
Figure BDA0003056364070000053
alpha is the amplification factor for the historical feedback value.
In some embodiments, the task allocation scheduling unit of the business process task scheduling engine subsystem further comprises a feedback time validity determination module configured to:
when n is less than or equal to k, the promised time TRIs greater than the predicted time TcThe user feedback is effective according to the specific proportion;
when n is larger than k and the historical performance rate r is smaller than or equal to theta, the personnel feedback is invalid;
when n is>k, the historical performance rate r>At theta, according to the historical performance rate r and the historical predicted value
Figure BDA0003056364070000054
Historical feedback values
Figure BDA0003056364070000055
And judging whether the personnel side is effective or not.
In some embodiments, the task allocation scheduling unit of the business process task scheduling engine subsystem further includes a weighted integration module, and if the human feedback is valid, the weighted integration module performs weighted integration on the feedback time and the predicted time according to a historical performance rate and a performance rate threshold to obtain an integrated time.
In some embodiments, the task allocation scheduling unit of the business process task scheduling engine subsystem further includes a sorting task allocation module, and the sorting task allocation module performs descending sorting on the personnel according to the obtained integration time, and selects the personnel with the smallest integration time value to allocate the tasks.
According to another aspect of the present invention, there is also provided a method for scheduling a business process task based on a personal calendar assistant, the method for scheduling a business process task based on a personal calendar assistant comprising the following steps:
when the task arrives, the task scheduling engine acquires all candidates of the task and sends a pre-distribution task to personal schedule assistants of the candidates;
the personal schedule assistant of the candidate receives the pre-distributed task, performs interaction with the user, coordinates task priority, task exclusivity and task prediction completion time;
the personal schedule assistant determines the task execution sequence according to the priority, calculates the final predicted completion time of the task, and feeds back the final predicted completion time to a business process task scheduling engine;
the business process task scheduling engine calculates the integration completion time according to the predicted completion time, the historical performance rate and the feedback time, sorts the candidates, selects the first optimal candidate, and pushes the distributed tasks and the integration completion time of the tasks to the personal schedule assistant of the first optimal candidate;
the personal schedule assistant of the distributor receives the distributed task, interacts with the user and indicates the user to complete the task within the integration completion time; if the user can not complete the task within the integration completion time, the personal schedule assistant sends a new task which can not be completed on time to the business process task scheduling engine and sends feedback completion time;
the business process task scheduling engine takes the feedback completion time as the integration completion time of the first optimal candidate, sorts all candidates, selects the second optimal candidate, and pushes the distributed tasks and the integration completion time of the tasks to the personal schedule assistant of the second optimal candidate; if the second best candidate is not the first best candidate, notifying the first best candidate that the task is finished by other people;
and
and acquiring feedback information of personnel for completing the corresponding tasks, and informing the personal schedule assistant by the task scheduling engine in the business process to finish the tasks.
In some embodiments, the method for scheduling tasks based on a workflow of a personal calendar assistant further comprises a task prediction step of the personal calendar assistant, wherein the task prediction step of the personal calendar assistant comprises the following steps:
obtaining the task typeAll m instances under k, and acquiring the task workload L ═ L under m instances1,l2,…,lmAnd a task completion time T ═ T1,t2,…,tm. The method comprises the steps that a working load is measured according to the working amount of a task, the working load l of the task of an example is the sum of the working loads of personnel when the task is received, and the task completion time is the time required for task completion;
training a regression model according to workload L and completion time T
T～aL+∈
Wherein a is the coefficient of L, epsilon is the residual error of the regression model, and the regression coefficient of the workload L is obtained by training the model
Figure BDA0003056364070000061
And
with the current staff workload l as input, the completion time of the staff under the k-type task is predicted
Figure BDA0003056364070000062
Figure BDA0003056364070000071
In some embodiments, the method for scheduling tasks in a workflow based on a personal calendar assistant further comprises a task ordering step, wherein the task ordering step comprises the following steps:
the business process task scheduling engine distributes a task k to the personal schedule assistant;
if the current personnel do not execute the task, the task k is taken as the task to be executed currently;
if the current person is performing n tasks, wherein the workload of the n tasks is L1,L2,…,LnPriority is K1,K2,…,KnPredicted completion time is T1,T2,…,TnThe workload of task k is LkPriority is KkPredicted completion time is TkJudgment of a person beingWhether the maximum workload W is reached; if it is not
Figure BDA0003056364070000072
Figure BDA0003056364070000073
Entering the task into the next round of judgment; if it is not
Figure BDA0003056364070000074
Judging whether the task priority meets the condition; if the task priority
Figure BDA0003056364070000075
The task enters the next round of judgment, if the task priority
Figure BDA0003056364070000076
Then the task is taken as the currently executed task;
and
when the task k enters the next round of judgment, the time is pushed to the completion of one task, and the predicted completion time of the task is increased
Figure BDA0003056364070000077
Namely, it is
Figure BDA0003056364070000078
At the moment, the personnel finish a task and judge whether the task k is taken as the task executed by the round again; and so on until task k is allowed to join the task at cycle j. Calculating the final task completion time Tk。
In some embodiments, the method for scheduling task of business process based on personal calendar assistant further comprises a step of predicting task scheduling engine of business process, the step of predicting task scheduling engine of business process comprises the following steps:
obtaining historical data of a specific person p and a specific task k, including n business process contexts C1,C2,…,CnPersonnel workload L and completion time of the corresponding taskT；
According to the obtained n business process contexts C1,C2,…,CnPersonnel load L, completion time T, training a regression model, wherein the formula of the regression model is as follows:
Figure BDA0003056364070000079
wherein, aiRepresenting the ith business process context CiB represents the coefficient of the workload L, and the epsilon represents the regression equation residual respectively; training get Business Process context C1,C2,…,CnRegression coefficient of
Figure BDA00030563640700000710
And regression coefficient of workload
Figure BDA00030563640700000711
And
in business process context c1,c2…, person load l as input, predicting the completion time of different persons using a machine learning model
Figure BDA0003056364070000081
In some embodiments, the method for scheduling tasks in a business process based on a personal calendar assistant further comprises a task pre-allocation scheduling step, wherein the task pre-allocation scheduling step comprises the following steps:
traversing the personnel in sequence, and adding all candidates into a pre-distribution queue;
and
assuming the pre-allocation queue is not empty, the latency T is setwPushing tasks to the personal assistants of all people in the pre-assigned queue requires that the personal assistants wait for a time TwAnd internally feeding back the result of the completed task.
In some embodiments, the method for scheduling tasks in a business process based on a personal calendar assistant further comprises a task allocation scheduling step, wherein the task allocation scheduling step comprises the following steps:
calculating the predicted time T of the corresponding candidatec；
Obtaining the feedback time T of the corresponding personnelRJudging whether the feedback of the personnel is effective or not; the judgment formula for the effective feedback time is as follows:
Figure BDA0003056364070000082
where n is the amount of history data, k is the threshold for the amount of history, εTIs the ratio of the maximum effective feedback time under the condition that n is less than or equal to k, TcPredicting the time of different persons; r is historical performance rate, theta is performance rate threshold, Tpre_cFor historical predicted values, Tpre_RIs a historical feedback value, and alpha is an amplification factor;
when n is less than or equal to k, the promised time TRIs greater than the predicted time TcThe user feedback is effective according to the specific proportion;
when n is larger than k and the historical performance rate r is smaller than or equal to theta, the personnel feedback is invalid;
when n is>k, the historical performance rate r>At theta, according to the historical performance rate r and the historical predicted value Tpre_cHistorical feedback value Tpre_RJudging whether the personnel side is effective or not;
if the personnel feedback is effective, the feedback time T is determined according to the historical performance rate r and the performance rate threshold thetaRAnd predicting time TcPerforming weighted integration to obtain integration time;
and
and sorting the personnel in a descending order according to the integration time, and selecting the personnel with the minimum integration time value to distribute tasks.
According to another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the method for scheduling tasks in a business process based on a personal calendar assistant.
According to another aspect of the present invention, there is also provided a business process task scheduling apparatus based on a personal calendar assistant, including:
a memory for storing a software application,
a processor for executing the software application,
and correspondingly executing the steps in the method for scheduling the business process tasks based on the personal calendar assistant by each program of the software application program.
Drawings
FIG. 1 is an architecture diagram of a personal calendar assistant based business process task scheduling system, according to one embodiment of the present invention.
Fig. 2 is an overall flowchart of a method for scheduling tasks in a personal calendar assistant-based business process according to an embodiment of the present invention.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It is understood that the terms "a" and "an" should be interpreted as meaning that a number of one element or element is one in one embodiment, while a number of other elements is one in another embodiment, and the terms "a" and "an" should not be interpreted as limiting the number.
The present invention relates to a computer program. Fig. 1 is an architecture diagram of a task scheduling system based on a personal calendar assistant according to a preferred embodiment of the present invention. The business process task scheduling system based on the personal schedule assistant can realize a push-pull combination and automatic feedback coordination distribution mode, a user interacts with the personal schedule assistant, the personal schedule assistant automatically feeds back to a business process task scheduling engine (task scheduling engine for short), the task scheduling engine selects proper personnel according to feedback and prediction results, and the personnel can be replaced in real time when the distributed personnel can not complete tasks in time.
Specifically, the business process task scheduling system based on the personal calendar assistant comprises a personal calendar assistant subsystem and a business process task scheduling engine subsystem. The personal calendar assistant subsystem is configured to perform task completion time, user interaction, and task scheduling. When the task in the personal schedule assistant arrives, the personal schedule assistant subsystem performs interaction with the user to acquire information fed back by the user, performs scheduling on the task according to task priority, predicts the completion time of the task according to the user feedback, performs scheduling on the task, and performs interaction with the business process task scheduling engine subsystem.
The business process task scheduling engine subsystem is configured to perform task pre-allocation, task allocation, and task completion time prediction. When the task arrives, the task enters a pre-distribution stage, the task is pre-distributed to all candidates, and feedback information of the user is acquired within a set time range; and after the business process task scheduling engine subsystem acquires all feedback information, the task enters a distribution stage, and the optimal personnel are selected to distribute the task.
Specifically, the personal schedule assistant subsystem comprises a user interaction unit, a task prediction unit and a task scheduling unit. The user interaction unit is configured to perform interaction with a user, obtain current task information, task information adjustment, and personal assistant adjustment. The task prediction unit is configured to predict a task completion time. The task scheduling unit is configured to perform sequencing on task execution sequence, and feeds back task information in real time with the service process task scheduling engine subsystem.
More specifically, the user interaction unit of the personal calendar assistant subsystem comprises a task real-time acquisition module, a task real-time adjustment module and a personal assistant configuration module. The task real-time acquisition module is used for acquiring the pre-distributed tasks and the distributed tasks of the user in real time. And the task real-time adjusting module is used for executing task adjustment and task rejection. Preferably, in a particular embodiment, performing task adjustments includes performing task priority and performing adjustments of projected completion time. The priority is the priority of the task, and can be divided into four levels of a/B/C/D (a > B > C > D), for example. The projected completion time is adjusted to perform dynamic adjustments in response to the user's actual situation requirements based on the system predicted completion time. And the task refusing is to respond to the requirement of the user on the emergency task condition, allow the user to refuse to accept the task, and feed back to the business process task scheduling engine subsystem through the personal schedule assistant subsystem. The personal schedule assistant configuration module is used for setting the maximum workload W and the default priority K: the system evaluates that the maximum workload W is the sum of the maximum task workloads allowed to be accepted by the user; the default priority K is the default priority at which the task arrives.
More specifically, for the current pre-assigned task and the assigned task, the task prediction unit of the personal calendar assistant subsystem builds a task completion time prediction algorithm model to predict the time that the task needs to consume when the task arrives or when the task is adjusted. The task prediction unit comprises a task completion time prediction algorithm model data acquisition module, a task completion time prediction algorithm model training module and a task completion time prediction module.
In a specific embodiment, the task completion time prediction algorithm model data obtaining module obtains all m instances of the task type k, and obtains the task workload L ═ L of the m instances1,l2,…,lmAnd a task completion time T ═ T1,t2,…,tm. The working load is measured according to the working amount of the task, the working load l of the example is the total working load of the personnel when the task is received, and the task completion time is the time required by the task completion.
Further, the task completion time prediction algorithm model training module trains a regression model according to the workload L and the completion time T
T～aL+∈
Wherein a is the coefficient of L, epsilon is the residual error of the regression model, and the regression coefficient of the workload L is obtained by training the model
Figure BDA0003056364070000111
Further, the task completion time prediction module takes the current working load l of the personnel as input and predicts the completion time of the personnel under the task of the type k
Figure BDA0003056364070000112
More specifically, the task scheduling unit of the personal calendar assistant subsystem includes a task ordering module and an automatic feedback module. The task ordering module orders the tasks according to the priority set by the user, and determines the priority order of the tasks when the pre-distributed tasks arrive or the task modification operation responding to the user is performed. And the automatic feedback module and the service process task scheduling engine subsystem execute pre-distribution task feedback interaction and distributed task feedback interaction.
More specifically, the automatic feedback module comprises a pre-allocation task feedback module and an allocated task feedback module, the pre-allocation task feedback module performs feedback at a pre-allocation task stage of the business process task scheduling engine subsystem, and when a task determined by a user is detected or the waiting time T is detectedwAnd automatically executing feedback when finishing. When the distributed task feedback module distributes the tasks to the users by the business process task scheduling engine subsystem, when the fact that the users cannot complete the tasks in time due to factors such as emergency tasks or the like or the users refuse to accept the tasks is detected, the distributed task feedback module feeds back to the business process task scheduling engine subsystem to indicate the business process task scheduling engine subsystem to reschedule the tasks.
More specifically, the task ordering module of the task scheduling unit of the personal calendar assistant subsystem performs task ordering, and the specific implementationIn an example, the task ordering module receives a task k distributed by the business process task scheduling engine subsystem; if the current personnel do not execute the task, the task k is taken as the task to be executed currently; if the current person is performing n tasks, wherein the workload of the n tasks is L1,L2,…,LnPriority is K1,K2,…,KnPredicted completion time is T1,T2,…,TnThe workload of task k is LkPriority is KkPredicted completion time is TkAnd judging whether the personnel reach the maximum workload W. If it is not
Figure BDA0003056364070000113
The task is entered into the next round of decision. If it is not
Figure BDA0003056364070000114
And judging whether the task priority meets the condition. If the task priority
Figure BDA0003056364070000121
The task enters the next round of judgment, if the task priority
Figure BDA0003056364070000122
Then the task is taken as the currently executed task; when the task k enters the next round of judgment, the time is pushed to the completion of one task, and the predicted completion time of the task is increased
Figure BDA0003056364070000123
Namely, it is
Figure BDA0003056364070000124
At this time, the person completes a task and re-determines whether the task k is the task to be executed in the round. And so on until task k is allowed to join the task at cycle j. Calculating the final task completion time Tk。
Furthermore, the business process task scheduling engine subsystem comprises a current task completion time prediction unit, a task pre-allocation scheduling unit and a task allocation scheduling unit. The current task completion time prediction unit is configured to predict a current task completion time. The task pre-allocation scheduling unit is configured to perform task pre-allocation, requiring candidates to feed back an expected completion time. The task allocation scheduling unit is configured to perform task allocation, and corresponding personnel are selected to perform allocation according to the predicted time and the feedback result.
Specifically, the current task completion time prediction unit of the business process task scheduling engine subsystem includes a historical data acquisition module, a current task completion time prediction model training module, and a current task completion time prediction module.
In a specific embodiment, the historical data acquisition module acquires historical data of a specific person p and a specific task k, including n business process contexts C1,C2,…,CnThe personnel workload L and the completion time T of the corresponding task.
Further, the current task completion time prediction model training module obtains n business process contexts C1,C2,…,CnPersonnel load L, completion time T, training a regression model, wherein the formula of the regression model is as follows:
Figure BDA0003056364070000125
wherein, aiRepresenting the ith business process context CiB represents the coefficient of the workload L, and e represents the regression equation residuals, respectively. Training get Business Process context C1,C2,…,CnRegression coefficient of
Figure BDA0003056364070000126
And regression coefficient of workload
Figure BDA0003056364070000127
Further, it is characterized byThe current task completion time prediction module uses the business process context c1,c2…, person load l as input, predicting the completion time of different persons using a machine learning model
Figure BDA0003056364070000128
Specifically, the task pre-allocation scheduling unit of the business process task scheduling engine subsystem comprises a candidate pre-allocation module and a task pushing module, wherein the candidate pre-allocation module traverses the personnel in sequence and adds all the candidates into a pre-allocation queue. Assuming that the pre-distribution queue is not empty, the task pushing module sets a waiting time Tw, pushes tasks to the personal schedule assistant subsystems of all the personnel in the pre-distribution queue and indicates the personal schedule assistant subsystems to wait for a time TwAnd internally feeding back the result of the completed task.
Specifically, the task allocation scheduling unit of the business process task scheduling engine subsystem includes a candidate prediction time calculation module, a feedback time effective judgment module, a weighted integration module, and a sequencing task allocation module.
In a specific embodiment, the candidate prediction time calculation module calculates the prediction time T of the corresponding candidatec。
Further, the feedback time effective judgment module acquires the feedback time T of the corresponding personnelRAnd judging whether the feedback of the personnel is effective or not. The effective judgment formula of the feedback time is as follows:
Figure BDA0003056364070000131
where n is the amount of history data, k is the threshold for the amount of history, εTIs the ratio of the maximum effective feedback time under the condition that n is less than or equal to k, TcPredicting the time of different persons; r is the historical performance rate, theta is the performance rate threshold,
Figure BDA0003056364070000132
in order to be a historical prediction value,
Figure BDA0003056364070000133
is a historical feedback value, and alpha is an amplification factor;
the feedback time validity determination module is configured to:
when n is less than or equal to k, the promised time TRIs greater than the predicted time TcThe user feedback is effective according to the specific proportion;
when n is larger than k and the historical performance rate r is smaller than or equal to theta, the personnel feedback is invalid;
when n is>k, the historical performance rate r>At theta, according to the historical performance rate r and the historical predicted value
Figure BDA0003056364070000134
Historical feedback values
Figure BDA0003056364070000135
And judging whether the personnel side is effective or not.
Further, if the personnel feedback is effective, the weighted integration module is used for feeding back the feedback time T according to the historical performance rate r and the threshold thetaRAnd predicting time TcPerforming weighted integration into an integration time TI。
Further, the sorting task allocation module is used for allocating tasks according to TISorting the personnel in descending order, selecting TIMinimal personnel assignment tasks.
According to another aspect of the invention, the invention also provides a business process task scheduling method based on the personal calendar assistant. Fig. 2 is a flow chart of the scheduling method of the business process task based on the pda according to the present invention, which illustrates a solution for controlling or processing the external object or the internal object of the computer by executing the computer program compiled according to the above flow based on the processing flow of the computer program to solve the problems proposed by the present invention. It should be understood that the term "computer" as used herein refers not only to desktop computers, notebook computers, tablet computers, etc., but also includes other intelligent electronic devices capable of operating according to programs and processing data.
Specifically, as shown in fig. 2, the method for scheduling a task in a business process based on a personal calendar assistant includes the following steps:
s100: when the task arrives, the task scheduling engine acquires all candidates of the task and sends a pre-distribution task to personal schedule assistants of the candidates;
s200: the personal schedule assistant of the candidate receives the pre-distributed task, performs interaction with the user, coordinates task priority, task exclusivity and task prediction completion time;
s300: the personal schedule assistant determines the task execution sequence according to the priority, calculates the final predicted completion time of the task, and feeds back the final predicted completion time to a business process task scheduling engine;
s400: the business process task scheduling engine calculates the integration completion time T according to the predicted completion time, the historical performance rate and the feedback timeISorting the candidates, selecting the optimal candidate o, and pushing the distributed tasks and the task integration completion time T to the personal schedule assistant of the optimal candidateI；
S500: the distributor's personal calendar assistant accepts the distributed tasks, interacts with the user, and indicates that the user is at TIThe task is completed within time; if the user has the situation of emergency task and the like, the user can not be in TIIf the task is completed within the time, the personal schedule assistant sends a new task which cannot be completed on time to the service process task scheduling engine and sends feedback completion time;
s600: the business process task scheduling engine takes the feedback completion time as the integration completion time of the candidate o, sorts all the candidates, selects the optimal candidate, and pushes the distributed task and the integration completion time T of the task to the personal schedule assistant of the optimal candidateI(ii) a If the optimal candidate is not candidate o, notifying candidate o that the task is completed by others;
s700: and acquiring feedback information of personnel for completing the corresponding tasks, and informing the personal schedule assistant by the task scheduling engine in the business process to finish the tasks.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
It can be understood by those skilled in the art that the method for scheduling task of workflow based on pda of the present invention can be realized by hardware, software, or combination of hardware and software. The present invention can be realized in a centralized fashion in at least one computer system, or in a distributed fashion where different elements are spread across several interconnected computer systems. Any kind of computer system or other apparatus adapted for carrying out the methods described herein is suited. A typical combination of hardware and software could be a general purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the methods described herein.
A typical combination of hardware and software could be a general purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the method for scheduling tasks in a workflow based on a personal calendar assistant as disclosed herein.
The present invention can be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein. The computer program product is embodied in one or more computer-readable storage media having computer-readable program code embodied therein. According to another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, is capable of performing the steps of the method for scheduling tasks in a workflow of a personal calendar assistant according to the present invention. Computer storage media is media in computer memory for storage of some discrete physical quantity. Computer storage media includes, but is not limited to, semiconductors, magnetic disk storage, magnetic cores, magnetic drums, magnetic tape, laser disks, and the like. It will be appreciated by persons skilled in the art that computer storage media are not limited by the foregoing examples, which are intended to be illustrative only and not limiting of the invention.
According to another aspect of the present invention, there is also provided a business process task scheduling apparatus based on a personal calendar assistant, the business process task scheduling apparatus based on a personal calendar assistant including: a software application, a memory for storing the software application, and a processor for executing the software application. And each program of the software application program can correspondingly execute the steps in the method for scheduling the business process task based on the personal schedule assistant.
It will be appreciated by those skilled in the art that the present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products according to the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and/or block diagram block or blocks.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.

Claims (26)

1. A business process task scheduling system based on personal calendar assistant is characterized in that the business process task scheduling system based on personal calendar assistant comprises a personal calendar assistant subsystem and a business process task scheduling engine subsystem,
the system comprises a personal schedule assistant subsystem, a business process task scheduling engine subsystem and a business process task scheduling engine subsystem, wherein the personal schedule assistant subsystem is configured to execute task completion time, user interaction and task scheduling, when a task in personal schedule assistance arrives, the personal schedule assistant subsystem executes interaction with a user, acquires information fed back by the user, and schedules the task according to task priority;
the business process task scheduling engine subsystem is configured to execute task pre-allocation, task allocation and task completion time prediction, when a task arrives, the task enters a pre-allocation stage, the task is pre-allocated to all candidates, and feedback information of a user is acquired within a set time range; and after the business process task scheduling engine subsystem acquires all feedback information, the task enters a distribution stage, and the optimal personnel are selected to distribute the task.
2. The system of claim 1, wherein the personal calendar assistant subsystem comprises a user interaction unit, a task prediction unit, and a task scheduling unit, the user interaction unit is configured to interact with a user to obtain current task information, task information adjustment, and personal assistant adjustment, the task prediction unit is configured to predict task completion time, and the task scheduling unit is configured to order task execution sequence, and feed back task information in real time with the business process task scheduling engine subsystem.
3. The system of claim 2, wherein the user interaction unit of the pda subsystem comprises a task real-time obtaining module, a task real-time adjusting module, and a pda configuration module, the task real-time obtaining module is used for obtaining the pre-assigned tasks and the assigned tasks of the user in real time; the task real-time adjusting module is used for executing task adjustment and task rejection, wherein the task adjustment includes the adjustment of task priority and predicted completion time, the priority is the priority degree of the task, the predicted completion time is the completion time predicted according to the system, the dynamic adjustment is executed in response to the actual condition requirement of the user, the task rejection is the requirement in response to the emergency task condition of the user, the user is allowed to reject to accept the task, and the personal schedule assistant subsystem feeds back the task scheduling engine subsystem to the business process; the personal schedule assistant configuration module is used for setting the maximum workload and the default priority, wherein the workload is the workload measurement of the task, the maximum workload is the sum of the maximum task workloads allowed to be accepted by the user and is evaluated by the system, and the default priority is the default priority when the task arrives.
4. The personal calendar assistant-based business process task scheduling system of claim 2, wherein the task prediction unit of the personal calendar assistant subsystem builds a task completion time prediction algorithm model for current pre-assigned tasks and assigned tasks, predicting the time that a task needs to consume when it arrives or when it adjusts.
5. The personal calendar assistant-based business process task scheduling system of claim 4, wherein the task prediction unit comprises a task completion time prediction algorithm model data acquisition module, wherein the task completion time prediction algorithm model data acquisition module acquires all instances under the task type, acquires task workload and task completion time under each instance, wherein the workload is measured according to workload, the task workload of an instance is the sum of the workloads of people who receive the task, and the task completion time is the time required for task completion.
6. The personal calendar assistant-based business process task scheduling system of claim 5, wherein the task prediction unit further comprises a task completion time prediction algorithm model training module that trains a regression model as a function of workload and completion time
T～aL+∈
Wherein T is the completion time, L is the workload, a is the coefficient of L, epsilon is the residual error of the regression model, and the regression coefficient of the workload is obtained by training the model.
7. The personal calendar assistant-based business process task scheduling system of claim 6, wherein the task prediction unit further comprises a task completion time prediction module that predicts a completion time of the person under the task of the task type with a current person workload as an input
Figure FDA0003056364060000021
Wherein
Figure FDA0003056364060000022
Regression coefficients for the workload are obtained for the training model.
8. The personal calendar assistant-based business process task scheduling system of claim 2, wherein the task scheduling unit of the personal calendar assistant subsystem comprises a task ranking module and an automatic feedback module, wherein the task ranking module ranks tasks according to a priority set by a user, determines a priority for performing tasks when pre-assigned tasks arrive or in response to a task modification operation by the user; and the automatic feedback module and the service process task scheduling engine subsystem execute pre-distribution task feedback interaction and distributed task feedback interaction.
9. The personal calendar assistant-based business process task scheduling system of claim 8, wherein the automatic feedback module comprises a pre-assigned task feedback module and an assigned task feedback module, the pre-assigned task feedback module performs feedback at a pre-assigned task stage of the business process task scheduling engine subsystem and automatically performs feedback when detecting that a user determines a task or when waiting time ends, the assigned task feedback module feeds back to the business process task scheduling engine subsystem to instruct the business process task scheduling engine subsystem to reschedule a task when the business process task scheduling engine subsystem assigns a task to a user and when detecting that a user cannot complete a task in time or a user refuses to accept a task.
10. The personal calendar assistant-based business process task scheduling system of claim 8, wherein the task ranking module of the task scheduling unit of the personal calendar assistant subsystem performs task ranking, wherein the task ranking module is configured to: receiving a task k distributed by the business process task scheduling engine subsystem; if the current personnel do not execute the task, the task is taken as the task to be executed currently; if the current person is performing n tasks, wherein the workload of the n tasks is L1，L2，...，LnPriority is K1，K2，...，KnPredicted completion time is T1，T2，...，TnThe workload of task k is LkPriority is KkPredicted completion time is TkJudging whether the personnel reaches the maximum working load, if so
Figure FDA0003056364060000031
Entering the task into the next round of judgment; if it is not
Figure FDA0003056364060000032
Judging whether the task priority meets the condition; if the task priority
Figure FDA0003056364060000033
The task enters the next round of judgment, if the task priority
Figure FDA0003056364060000034
Then the task is taken as the currently executed task; when the task k enters the next round of judgment, the time is pushed to the completion of one task, and the predicted completion time of the task is increased
Figure FDA0003056364060000035
Namely, it is
Figure FDA0003056364060000036
Figure FDA0003056364060000037
At the moment, the information that the personnel finish a task is received, and whether the task k is used as the task executed in the round or not is judged again; and so on until the j-th cycle task k allows to join the task; calculating the final task completion time Tk。
11. The personal calendar assistant-based business process task scheduling system of any one of claims 1 to 10, wherein the business process task scheduling engine subsystem comprises a current task completion time prediction unit, a task pre-allocation scheduling unit, and a task allocation scheduling unit, wherein the current task completion time prediction unit is configured to predict a current task completion time; wherein the task pre-allocation scheduling unit is configured to perform task pre-allocation, requiring candidates to feed back an expected completion time; and the task allocation scheduling unit is configured to execute task allocation, and select corresponding personnel to execute allocation according to the predicted time and the feedback result.
12. The personal calendar assistant-based business process task scheduling system of claim 11, wherein the current task completion time prediction unit of the business process task scheduling engine subsystem comprises a historical data acquisition module, wherein the historical data acquisition module acquires historical data of a specific person p and a specific task k, including n business process contexts C1，C2，...，CnThe personnel workload L and the completion time T of the corresponding task.
13. The personal calendar assistant-based business process task scheduling system of claim 12, wherein the current task completion time prediction unit of the business process task scheduling engine subsystem further comprises a current task completion time prediction model training module, wherein the current task completion time prediction model training module trains the current task completion time prediction model according to the acquired n business process contexts C1，C2，...，CnPersonnel load L, completion time T, training a regression model, wherein the formula of the regression model is as follows:
Figure FDA0003056364060000041
wherein, aiRepresenting the ith business process context CiB represents the coefficient of the workload L, and e represents the regression equation residuals, respectively. Training get Business Process context C1，C2，...，CnRegression coefficient of
Figure FDA0003056364060000042
And regression coefficient of workload
Figure FDA0003056364060000043
14. The personal calendar assistant-based business process task scheduling system of claim 13, wherein the current task completion time prediction unit of the business process task scheduling engine subsystem further comprises a current task completion time prediction module that predicts a current task completion time in a business process context c1，c2,., person load 1 is used as input, and machine learning model is used to predict completion time of different persons
Figure FDA0003056364060000044
Figure FDA0003056364060000045
The task pre-allocation scheduling unit of the business process task scheduling engine subsystem comprises a candidate pre-allocation module and a task pushing module, wherein the candidate pre-allocation module traverses personnel in sequence and adds all candidates into a pre-allocation queue; and assuming that the pre-distribution queue is not empty, setting waiting time by the task pushing module, pushing the tasks to the personal schedule assistant subsystems of all the personnel in the pre-distribution queue, and indicating the personal schedule assistant subsystems to feed back results of completing the tasks in the waiting time.
15. The personal calendar assistant-based business process task scheduling system of claim 11, wherein the task allocation scheduling unit of the business process task scheduling engine subsystem comprises a candidate predicted time calculation module, wherein the feedback time validity determination module is configured to:
obtaining the feedback time T of the corresponding personnelRJudging whether the feedback of the personnel is effective or not; the effective judgment formula of the feedback time is as follows:
Figure FDA0003056364060000046
where n is the amount of history data, k is the threshold for the amount of history, εTIs the ratio of the maximum effective feedback time under the condition that n is less than or equal to k, TcPredicting the time of different persons; r is the historical performance rate, theta is the performance rate threshold,
Figure FDA0003056364060000051
in order to be a historical prediction value,
Figure FDA0003056364060000052
alpha is the amplification factor for the historical feedback value.
16. The personal calendar assistant-based business process task scheduling system of claim 15, wherein the task allocation scheduling unit of the business process task scheduling engine subsystem further comprises a feedback time validity determination module configured to:
when n is less than or equal to k, the promised time TRIs greater than the predicted time TcThe user feedback is effective according to the specific proportion;
when n is larger than k and the historical performance rate r is smaller than or equal to theta, the personnel feedback is invalid;
when n is larger than k and the historical performance rate r is larger than theta, the historical performance rate r and the historical predicted value are used
Figure FDA0003056364060000053
Historical feedback values
Figure FDA0003056364060000054
And judging whether the personnel side is effective or not.
17. The personal calendar assistant-based business process task scheduling system of claim 16, wherein the task allocation scheduling unit of the business process task scheduling engine subsystem further comprises a weighted integration module that performs weighted integration on the feedback time and the predicted time according to a historical performance rate and a performance rate threshold to obtain an integrated time if there is a human feedback available.
18. The personal calendar assistant-based business process task scheduling system of claim 17, wherein the task allocation scheduling unit of the business process task scheduling engine subsystem further comprises a sorting task allocation module, the sorting task allocation module performs descending sorting on the personnel according to the obtained integration time, and selects the personnel with the smallest integration time value to allocate the tasks.
19. A business process task scheduling method based on a personal schedule assistant is characterized by comprising the following task scheduling steps:
when the task arrives, the task scheduling engine acquires all candidates of the task and sends a pre-distribution task to personal schedule assistants of the candidates;
the personal schedule assistant of the candidate receives the pre-distributed task, performs interaction with the user, coordinates task priority, task exclusivity and task prediction completion time;
the personal schedule assistant determines the task execution sequence according to the priority, calculates the final predicted completion time of the task, and feeds back the final predicted completion time to a business process task scheduling engine;
the business process task scheduling engine calculates the integration completion time according to the predicted completion time, the historical performance rate and the feedback time, sorts the candidates, selects the first optimal candidate, and pushes the distributed tasks and the integration completion time of the tasks to the personal schedule assistant of the first optimal candidate;
the personal schedule assistant of the distributor receives the distributed task, interacts with the user and indicates the user to complete the task within the integration completion time; if the user can not complete the task within the integration completion time, the personal schedule assistant sends a new task which can not be completed on time to the business process task scheduling engine and sends feedback completion time;
the business process task scheduling engine takes the feedback completion time as the integration completion time of the first optimal candidate, sorts all candidates, selects the second optimal candidate, and pushes the distributed tasks and the integration completion time of the tasks to the personal schedule assistant of the second optimal candidate; if the second best candidate is not the first best candidate, notifying the first best candidate that the task is finished by other people;
and
and acquiring feedback information of personnel for completing the corresponding tasks, and informing the personal schedule assistant by the task scheduling engine in the business process to finish the tasks.
20. The method of personal calendar assistant-based business process task scheduling as set forth in claim 19, wherein the method of personal calendar assistant-based business process task scheduling further comprises a personal calendar assistant task prediction step, the personal calendar assistant task prediction step comprising the steps of:
acquiring all m instances under the task type k, and acquiring the task workload L ═ L under the m instances1，l2，...，lmAnd a task completion time T ═ T1，t2，...，tm(ii) a The method comprises the steps that a working load is measured according to the working amount of a task, the working load l of the task of an example is the sum of the working loads of personnel when the task is received, and the task completion time is the time required for task completion;
training a regression model according to workload L and completion time T
T～aL+∈
Wherein a is the coefficient of L, epsilon is the residual error of the regression model, and the regression coefficient of the workload L is obtained by training the model
Figure FDA0003056364060000061
And
with the current staff workload l as input, the completion time of the staff under the k-type task is predicted
Figure FDA0003056364060000062
Figure FDA0003056364060000063
21. The method of claim 19, wherein the method further comprises a task ranking step, the task ranking step comprising the steps of:
the business process task scheduling engine distributes a task k to the personal schedule assistant;
if the current personnel do not execute the task, the task k is taken as the task to be executed currently;
if the current person is performing n tasks, wherein the workload of the n tasks is L1，L2，...，LnPriority is K1，K2，...，KnPredicted completion time is T1，T2，...，TnThe workload of task k is LkPriority is KkPredicted completion time is TkJudging whether the personnel reach the maximum work load W; if it is not
Figure FDA0003056364060000071
Figure FDA0003056364060000072
Entering the task into the next round of judgment; if it is not
Figure FDA0003056364060000073
Judging whether the task priority meets the condition; if the task priority
Figure FDA0003056364060000074
The task enters the next round of judgment, if the task priority
Figure FDA0003056364060000075
Then the task is taken as the currently executed task;
and
when the task k enters the next round of judgment, the time is pushed to the completion of one task, and the predicted completion time of the task is increased
Figure FDA0003056364060000076
Namely, it is
Figure FDA0003056364060000077
At the moment, the personnel finish a task and judge whether the task k is taken as the task executed by the round again; by the way of analogy, the method can be used,until the task k is allowed to be added to the task in the j-th cycle; calculating the final task completion time Tk。
22. The personal calendar assistant-based business process task scheduling method of claim 19, wherein the personal calendar assistant-based business process task scheduling method further comprises a business process task scheduling engine predicting step comprising the steps of:
obtaining historical data of a specific person p and a specific task k, including n business process contexts C1，C2，...，CnThe personnel workload L and the completion time T of the corresponding task;
according to the obtained n business process contexts C1，C2，...，CnPersonnel load L, completion time T, training a regression model, wherein the formula of the regression model is as follows:
Figure FDA0003056364060000078
wherein, aiRepresenting the ith business process context CiB represents the coefficient of the workload L, and the epsilon represents the regression equation residual respectively; training get Business Process context C1，C2，...，CnRegression coefficient of
Figure FDA0003056364060000079
And regression coefficient of workload
Figure FDA00030563640600000710
And
in business process context c1，c2,., person load 1 is used as input, and machine learning model is used to predict completion time of different persons
Figure FDA00030563640600000711
23. The method for scheduling tasks in a personal calendar assistant-based business process according to claim 19, wherein the method for scheduling tasks in a personal calendar assistant-based business process further comprises a task pre-allocation scheduling step, the task pre-allocation scheduling step comprising the steps of:
traversing the personnel in sequence, and adding all candidates into a pre-distribution queue;
and
assuming the pre-allocation queue is not empty, the latency T is setwPushing tasks to the personal assistants of all people in the pre-assigned queue requires that the personal assistants wait for a time TwAnd internally feeding back the result of the completed task.
24. The method of claim 23, wherein the method further comprises a task allocation scheduling step, the task allocation scheduling step comprising the steps of:
calculating the predicted time T of the corresponding candidatec；
Obtaining the feedback time T of the corresponding personnelRJudging whether the feedback of the personnel is effective or not; the judgment formula for the effective feedback time is as follows:
Figure FDA0003056364060000081
where n is the amount of history data, k is the threshold for the amount of history, εTIs the ratio of the maximum effective feedback time under the condition that n is less than or equal to k, TcPredicting the time of different persons; r is historical performance rate, theta is performance rate threshold, Tpre_cFor historical predicted values, Tpre_RIs a historical feedback value, and alpha is an amplification factor;
when n is less than or equal to k, the promised time TRIs greater than the predicted time TcThe user feedback is effective according to the specific proportion;
when n is larger than k and the historical performance rate r is smaller than or equal to theta, the personnel feedback is invalid;
when n is larger than k and the historical performance rate r is larger than theta, the historical performance rate r and the historical predicted value T are usedpre_cHistorical feedback value Tpre_RJudging whether the personnel side is effective or not;
if the personnel feedback is effective, the feedback time T is determined according to the historical performance rate r and the performance rate threshold thetaRAnd predicting time TcPerforming weighted integration to obtain integration time;
and
and sorting the personnel in a descending order according to the integration time, and selecting the personnel with the minimum integration time value to distribute tasks.
25. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for scheduling tasks for a business process of a personal calendar assistant based on a personal calendar assistant as claimed in claims 19 to 24.
26. A personal calendar assistant-based business process task scheduling apparatus, comprising:
a memory for storing a software application,
a processor for executing the software application,
wherein each program of the software application correspondingly performs the steps of the method for scheduling tasks in a workflow based on a personal calendar assistant as claimed in claims 19 to 24.
CN202110501155.3A 2021-01-28 2021-05-08 Business process task scheduling system, equipment and method based on personal schedule assistant Pending CN113139795A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2021101166714 2021-01-28
CN202110116671 2021-01-28

Publications (1)

Publication Number Publication Date
CN113139795A true CN113139795A (en) 2021-07-20

Family

ID=76816984

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110501155.3A Pending CN113139795A (en) 2021-01-28 2021-05-08 Business process task scheduling system, equipment and method based on personal schedule assistant

Country Status (1)

Country Link
CN (1) CN113139795A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320329A (en) * 2008-07-08 2008-12-10 中国科学院软件研究所 Preemptive manpower resource collocation method and system based on task priority
US20130246116A1 (en) * 2012-03-16 2013-09-19 International Business Machines Corporation Assisting user to schedule a meeting with the best candidate from a list of individuals based on past communication history, calendar information and user's rules
CN106663246A (en) * 2014-08-28 2017-05-10 谷歌公司 Systems and methods for biasing task assistance auto-complete suggestions
KR20170110921A (en) * 2016-03-24 2017-10-12 한국전자통신연구원 Apparatus and method for recommending schedule to user using asscociation pattern learning
CN107392425A (en) * 2017-06-15 2017-11-24 中国烟草总公司 A kind of the tobacco business project implementation SOP management method and system
CN109784646A (en) * 2018-12-14 2019-05-21 深圳壹账通智能科技有限公司 Method for allocating tasks, device, storage medium and server
CN110648047A (en) * 2019-08-16 2020-01-03 深圳市轱辘汽车维修技术有限公司 Task scheduling method, device, system and storage medium
CN110736478A (en) * 2018-07-20 2020-01-31 华北电力大学 unmanned aerial vehicle assisted mobile cloud-aware path planning and task allocation scheme
CN111401845A (en) * 2020-03-17 2020-07-10 支付宝(杭州)信息技术有限公司 Service processing method and device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320329A (en) * 2008-07-08 2008-12-10 中国科学院软件研究所 Preemptive manpower resource collocation method and system based on task priority
US20130246116A1 (en) * 2012-03-16 2013-09-19 International Business Machines Corporation Assisting user to schedule a meeting with the best candidate from a list of individuals based on past communication history, calendar information and user's rules
CN106663246A (en) * 2014-08-28 2017-05-10 谷歌公司 Systems and methods for biasing task assistance auto-complete suggestions
KR20170110921A (en) * 2016-03-24 2017-10-12 한국전자통신연구원 Apparatus and method for recommending schedule to user using asscociation pattern learning
CN107392425A (en) * 2017-06-15 2017-11-24 中国烟草总公司 A kind of the tobacco business project implementation SOP management method and system
CN110736478A (en) * 2018-07-20 2020-01-31 华北电力大学 unmanned aerial vehicle assisted mobile cloud-aware path planning and task allocation scheme
CN109784646A (en) * 2018-12-14 2019-05-21 深圳壹账通智能科技有限公司 Method for allocating tasks, device, storage medium and server
CN110648047A (en) * 2019-08-16 2020-01-03 深圳市轱辘汽车维修技术有限公司 Task scheduling method, device, system and storage medium
CN111401845A (en) * 2020-03-17 2020-07-10 支付宝(杭州)信息技术有限公司 Service processing method and device

Similar Documents

Publication Publication Date Title
Cho et al. A robust adaptive scheduler for an intelligent workstation controller
Subtil et al. A practical approach to truck dispatch for open pit mines
Joseph et al. Analysis of dynamic due-date assignment models in a flexible manufacturing system
Rewers et al. A study of priority rules for a levelled production plan
El Mouayni et al. Jobs scheduling within Industry 4.0 with consideration of worker’s fatigue and reliability using Greedy Randomized Adaptive Search Procedure
CN107193655A (en) A kind of fair resource dispatching method towards big data processing based on utility function
FLEMING’S The new method of adaptive CPU scheduling using fonseca and fleming’s genetic algorithm
CN113592319A (en) INSGA-II-based flexible job shop scheduling method and device under complex constraint
Rezaeiahari et al. An optimization model for scheduling patients in destination medical centers
CN106934539A (en) It is a kind of with limited and expense restriction workflow schedule method
Biele et al. Decomposition methods for cost and tardiness reduction in aircraft manufacturing flow lines
Zayas-Caban et al. Optimal control of an emergency room triage and treatment process
Ahn et al. A smart elevator scheduler that considers dynamic changes of energy cost and user traffic
CN113139795A (en) Business process task scheduling system, equipment and method based on personal schedule assistant
US20240004707A1 (en) Methods and systems for energy-efficient scheduling of periodic tasks on a group of processing devices
CN112700169B (en) Business process task allocation method and system based on prediction and personnel feedback
CN112990624A (en) Task allocation method, device, equipment and storage medium
CN112794172B (en) Data portrait and information portrait value alternating current conversion oriented carrying method and system
Zhang et al. Intelligent dispatching in dynamic stochastic job shops
Deshpande et al. Coordinated problem solving through resource sharing in a distributed environment
CN101582831B (en) Scheduling method of grid resources of multi-Qos
Kumar et al. Simulation-based comparative analysis of the performance of a flexible manufacturing system operating under part movement policy and tool movement policy
El-Bouri et al. Cooperative dispatching for minimizing mean flowtime in a dynamic flowshop
CN112559144A (en) Intelligent sharing device scheduling method facing data and information rights and interests exchange
Yousefli et al. A new heuristic model for fully fuzzy project scheduling

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination