WO2020211529A1 - 一种服务端的派工方法、装置、计算机设备及存储介质 - Google Patents

一种服务端的派工方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2020211529A1
WO2020211529A1 PCT/CN2020/076492 CN2020076492W WO2020211529A1 WO 2020211529 A1 WO2020211529 A1 WO 2020211529A1 CN 2020076492 W CN2020076492 W CN 2020076492W WO 2020211529 A1 WO2020211529 A1 WO 2020211529A1
Authority
WO
WIPO (PCT)
Prior art keywords
server
parameter
processing
score
processing queue
Prior art date
Application number
PCT/CN2020/076492
Other languages
English (en)
French (fr)
Inventor
陈晔
潘康杰
李晓俊
杜泽炜
吴建强
叶露瑶
李敏杰
Original Assignee
深圳前海微众银行股份有限公司
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 深圳前海微众银行股份有限公司 filed Critical 深圳前海微众银行股份有限公司
Publication of WO2020211529A1 publication Critical patent/WO2020211529A1/zh

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services

Definitions

  • the present invention relates to the technical field of financial technology (Fintech), and in particular to a method, device, computer equipment and storage medium for dispatching work on a server.
  • Financial technology Fetech
  • the dispatch system in the field of financial technology includes service objects and server ends.
  • the service objects are objects that need to be processed to obtain services.
  • the server ends are the processors that provide services for the service objects.
  • the dispatch system needs to combine the service objects and the server ends. Perform matching to process the service object.
  • the dispatch system places the service object in the service object queue, and places the server in the server queue.
  • FCFS first serve
  • FCFS first serve
  • FCFS the service object of
  • the service object of is matched with the server at the head of the server queue.
  • FCFS first serve
  • the service time and service quality of each server for a service object will be greatly affected.
  • the prior art method only considers the sequence of arriving at the server queue, resulting in low overall service efficiency for dispatching workers, which is an urgent problem to be solved.
  • This application provides a method, device, computer equipment, and storage medium for dispatching workers on the server side to solve the problem that the overall service efficiency of dispatch workers is not high due to the fact that the prior art only considers the sequence of arriving at the server queue. problem.
  • the present application provides a method for dispatching work on a server, including: obtaining the parameter values of the first parameter, the second parameter, and the third parameter of each server in the processing queue; according to the first parameter, the second parameter of each server in the processing queue, The parameter value of at least one of the second parameter and the third parameter determines the score of the server, the score is a value that characterizes the service efficiency of the server, and the score is positively correlated with the service efficiency of the server;
  • the server with the highest score in the processing queue serves as the dispatching server, and the server is the server with the highest service efficiency in the processing queue.
  • the step of determining the score value of each server in the processing queue according to the parameter value of at least one of the first parameter, the second parameter and the third parameter of the server includes: according to the at least one Determine the preset function value of each parameter in the parameters; determine the score value of the server according to the preset function value of each parameter in the at least one parameter and the weight coefficient value of the parameter; wherein The weight coefficient value of each parameter in the at least one parameter is preset according to the correlation coefficient between the first parameter, the second parameter, and the third parameter of each server in the processing queue and the processing duration of the server.
  • the first parameter, the second parameter, and the third parameter of each server in the processing queue are specifically: the first parameter of the server is the upper limit of the total number of service objects that the server can serve in parallel; The second parameter of the server is the remaining number of service objects that the server can still serve in parallel at the preset time; the third parameter of the server is the cumulative duration from the time the server joins the processing queue to the preset time .
  • each server in the processing queue has been marked with a processing type each time the processing content of the service object is processed within the first preset period, and the processing type is marked according to the first parameter of each server in the processing queue ,
  • the parameter value of at least one of the second parameter and the third parameter after determining the score of the server, further includes: for each server in the processing queue, if the processing type of the server is equal to the first to be dispatched If the processing types of the workers are the same, the point value of the server is increased; otherwise, the point value of the server is decreased.
  • the method further includes: After each server in the queue processes the service object of each processing type, the priority of the server for the service object of this processing type is determined; according to the second service object to be dispatched for each service in the processing queue The priority of the server, and the number of times the second service object to be dispatched sends service requests, and the score of the server is updated.
  • the server whose score in the processing queue is less than the entry threshold of the processing queue is removed from the processing queue.
  • the score of each server in the processing queue is determined according to the parameter values of the first parameter, the second parameter, and the third parameter of the server, and the score is used to characterize the service efficiency of the server, and the score The value is positively related to the service efficiency of the server. Therefore, the server with the highest score in the processing queue is the server with the highest service efficiency in the processing queue.
  • This server is the server that dispatches work at the preset time, that is, select The server with the highest service efficiency after considering the first parameter, the second parameter and the third parameter in the processing queue improves the overall service efficiency of dispatching workers.
  • the present application provides a server dispatching device, including: an acquisition module for acquiring the parameter values of the first parameter, the second parameter, and the third parameter of each server in the processing queue; the processing module is used for processing according to the The parameter value of at least one of the first parameter, the second parameter, and the third parameter of each server in the queue determines the score of the server.
  • the score is a value representing the service efficiency of the server, and the score is equal to The service efficiency of the server is positively correlated; the server with the highest score in the processing queue is used as the dispatching server, and the server is the server with the highest service efficiency in the processing queue.
  • the processing module is specifically configured to: determine the preset function value of each parameter in the at least one parameter according to the parameter value of the parameter; according to the preset function value of each parameter in the at least one parameter , And the weight coefficient value of the parameter to determine the score value of the server; wherein, the weight coefficient value of each parameter in the at least one parameter is based on the first parameter, the second parameter and the value of each server in the processing queue
  • the correlation coefficient between the third parameter and the processing time of the server is preset.
  • the first parameter, the second parameter, and the third parameter of each server in the processing queue are specifically: the first parameter of the server is the upper limit of the total number of service objects that the server can serve in parallel; The second parameter of the server is the remaining number of service objects that the server can still serve in parallel at the preset time; the third parameter of the server is the cumulative duration from the time the server joins the processing queue to the preset time .
  • the processing module is specifically configured to: mark the processing type of each server in the processing queue that processes the processing content of the service object each time within the first preset period; For each server, if the processing type of the server is the same as the processing type of the first service object to be dispatched, the score of the server is increased; otherwise, the score of the server is decreased.
  • the processing module is further configured to: determine the priority of the server for the service object of each processing type according to the interval time after each server in the processing queue processes the service object of each processing type; The priority of the second service object to be dispatched with respect to each server in the processing queue and the number of service requests issued by the second service object to be dispatched to update the score of the server.
  • processing module is also used for:
  • the server whose score in the processing queue is less than the entry threshold of the processing queue is removed from the processing queue.
  • this application provides a computer device, including a program or instruction, and when the program or instruction is executed, the dispatch method and optional method of the server provided by this application are executed.
  • this application provides a storage medium that includes a program or instruction, and when the program or instruction is executed, the dispatch method and optional method of the server provided by this application are executed.
  • FIG. 1 is a flowchart of the steps of a method for dispatching workers on a server in an embodiment of the application;
  • FIG. 2 is a schematic diagram of the sorting of scores corresponding to a method for dispatching workers on a server according to an embodiment of the application;
  • FIG. 3 is a schematic diagram of multiple regression analysis results corresponding to a method of dispatching workers on the server according to an embodiment of the application;
  • FIG. 4 is a schematic diagram of a customer service dispatching system corresponding to a method for dispatching workers on a server in an embodiment of the application;
  • FIG. 5 is a schematic diagram of a structure corresponding to a dispatching device of a server in an embodiment of the application.
  • the dispatch system is a system that matches the service object and the server. With the development of computer technology, the dispatching system is also applied in the financial field, and the traditional financial industry is gradually transforming to Fintech. At present, the dispatch system in the field of technology and finance is also developing.
  • the service object of the dispatch system is the object that needs to be processed to obtain the service
  • the server is the processor that provides the service for the service object.
  • the process of matching the service object and the server is called dispatch.
  • the service object is a customer who needs consulting services
  • the server end is a customer service dealing with customer consulting services
  • dispatching is the process of matching the customer with the customer service.
  • the dispatch system matches the service object at the head of the service object queue with the server at the head of the server queue according to the principle of first come, first serve (FCFS).
  • FCFS first come, first serve
  • each server has only a difference in the order of arrival for the service object. But in fact, the service duration and service quality of each server to a service object will be affected by many factors. When matching different servers to a service object, the service efficiency provided by different servers will also be high or low. .
  • the prior art method only considers the factor of the order of arrival at the server queue, but does not consider other factors, so that the overall service efficiency of dispatching workers is not high.
  • the embodiment of the present application provides a method for dispatching workers on the server side, which comprehensively considers multiple factors that affect the service efficiency of the server side.
  • Fig. 1 it is a flow chart of the steps of a method for dispatching workers on a server in an embodiment of this application.
  • Step 101 Obtain parameter values of the first parameter, the second parameter, and the third parameter of each server in the processing queue.
  • Step 102 Determine the score value of the server according to the parameter value of at least one of the first parameter, the second parameter and the third parameter of each server in the processing queue, and the score value is indicative of the service efficiency of the server. Value, and the score is positively correlated with the service efficiency of the server.
  • Step 103 The server with the highest score in the processing queue is used as the dispatching server, and the server is the server with the highest service efficiency in the processing queue.
  • the service mode can either independently serve one service object for one server, or simultaneously serve multiple service objects for one server.
  • a server can queue up on multiple processing queues to process multiple service objects in parallel.
  • the service objects are sorted according to the order of entry time, and the dispatch system adjusts the entry priority of the service objects according to user attributes, such as service object grouping or service object level; on the server side, the server end The values are sorted sequentially.
  • the first parameter, the second parameter, and the third parameter are three parameters set in combination with factors that affect the dispatch sequence in the existing service scenario, and each parameter corresponds to a parameter at each moment. value.
  • steps 101 to 102 only the first parameter, the second parameter, and the third parameter are used as examples, and the number of parameters is not limited to three.
  • an optional implementation manner is to determine the score value of the server according to the following steps: determine the preset function value of the parameter according to the parameter value of each parameter in at least one parameter; The preset function value of the parameter and the weight coefficient value of the parameter determine the score of the server.
  • the first parameter, the second parameter, and the third parameter can be selected according to specific scenarios.
  • the first parameter of the server is the upper limit of the total number of service objects that the server can serve in parallel
  • the second parameter of the server is the remaining number of service objects that the server can still serve in parallel at the preset time
  • the third parameter of the server is the cumulative duration from the time the server joins the processing queue to the preset time .
  • the weight coefficient value of each of the first parameter, the second parameter, and the third parameter may be based on the first parameter, the second parameter, and the third parameter of each server in the processing queue.
  • the correlation coefficient with the processing time of the server is preset. For example, the value of the weight coefficient of a parameter with a higher correlation coefficient can be set higher.
  • the score calculation formula is:
  • S is for the score server; i is a positive integer; i X i of the parameter values for the parameters of the server; F i (X i) is a predetermined function of X i; i W is as f i (X i ) the weight coefficient value.
  • W i is preset according to the correlation coefficient between the first parameter, the second parameter and the third parameter of each server in the processing queue and the processing duration of the server. For example, the dispatching system has no priority on the dispatching of the server, and the overall service efficiency is not high. Customers with the same problem will be dispatched to different customer services, and the service is not consistent for the customer service.
  • X 1 is the upper limit of the total number of service objects that the server can serve in parallel;
  • X 2 is the remaining number of service objects that the server can also serve in parallel at the preset moment;
  • X 3 is the server that adds the processing The cumulative duration from the start time of the queue to the preset time.
  • the final dispatching server selected is: the server with higher service efficiency determined according to the preset rules of service efficiency.
  • the preset rule is: when X 1 and X 2 are the same, the smaller X 3 is, the higher the service efficiency of the server will be.
  • the dispatching server selected in other situations is also selected according to the preset rules of the actual service duration of the server and the service target. The specific rules can be set according to the needs, and will not be repeated here.
  • W 1 , W 2 , and W 3 can be either preset values or values determined according to a preset algorithm.
  • the following takes the multiple regression analysis method as an example to illustrate W 1 , W 2 , W 3 One way to determine.
  • Multiple regression analysis refers to the establishment of a linear or non-linear mathematical model quantitative relationship between multiple variables and the use of sample data for analysis by considering one variable as the dependent variable and the other one or more variables as independent variables.
  • Statistical analysis methods The data set used for multiple regression analysis can determine the scores according to the preset rules of service efficiency consistent with Table 1, and sort the scores from high to low, as shown in Figure 2, which is a service proposed in this embodiment of the application. Schematic diagram of the ranking of points corresponding to the end-of-the-line dispatch method.
  • the score shown in FIG. 2 is a value preset according to the order of the value of X 2 /X 1 from high to low.
  • step 102 an optional implementation is as follows:
  • the processing content of each server in the processing queue is marked each time the processing content of the service object is processed.
  • the first preset period is one day, and the server 1 processes three types of processing content of processing type 1, processing type 2, and processing type 3 within one day.
  • the score of the server is increased; otherwise, the score of the server is decreased.
  • the first service object to be dispatched needs a server to dispatch, and the processing type of the processing content of the first service object to be dispatched is processing type 1, and the selectable server in the processing queue includes server 1 Server 2 and Server 3 are three servers, of which only Server 1 has processed the processing content of processing type 1 within one day. Then based on the score determined in step 102, the score of Server 1 can be increased. And reduce the scores of server 2 and server 3.
  • the specific reduction methods and rules can be set according to specific application scenarios. For example, the processing content of more important processing types is preset to increase or decrease with a higher score.
  • step 102 Another optional implementation manner is:
  • the priority of the server for the service object of the processing type is determined.
  • the score of the second service object to be dispatched is updated according to the priority of each server in the processing queue and the number of requests made by the second service object to be dispatched. For example, if the server 1 processes the service object of processing type 1 with an interval of 5 hours, and the service object with processing type 2 has an interval of 3 hours, then set the service object of processing type 2 The priority of is higher than the priority of processing type 1 service objects. It should be noted that, considering that each server has different processing efficiency for processing content of the same processing type, each server will set the priority of the service object according to its own processing efficiency.
  • the rules for updating the score of the server can be set according to specific scenarios. For example, if the priority of the second service object to be dispatched for server 1 and server 2 in the processing queue is 8 and 10, respectively, the number of requests for the second service object to be dispatched to send service requests is 5, but Server 1 is more sensitive to the request of the second service object to be dispatched.
  • the processing type of the second service object to be dispatched is processing type 2, and the score for the request of the second service object to be dispatched is updated. Determined according to the interval time when the server has processed the processing type 2 service object. The interval time when the server 1 has processed the processing type 2 service object is shorter.
  • the value of the server 1 will increase by 10 , But the server 2 points only increase by 5. Thereby, it is possible to increase the possibility that the same type of service object is served by the same server, and improve the consistency of the service.
  • FIG. 4 is a schematic diagram of a customer service dispatching system corresponding to a method for dispatching workers on a server in an embodiment of the application. It should be noted that the dispatch system only takes the customer service dispatch system as an example, and is not limited to this system.
  • step 101 During the execution of step 101 to step 103, there is an alternative implementation manner as follows:
  • the server whose score is less than the entry threshold of the processing queue in the processing queue is removed from the processing queue, or a new server is used to replace the server whose score is less than the entry threshold. That is, a score entry threshold is set in the processing queue.
  • the score of the server is greater than or equal to the entry threshold, it indicates that the service efficiency of the server can meet the requirements, so that the server can remain in the processing queue to ensure the service quality of the server .
  • FIG. 5 it is a schematic diagram of a structure corresponding to a dispatching device of a server in an embodiment of this application.
  • the present application provides a server dispatching device, including: an obtaining module 501 for obtaining the parameter values of the first parameter, the second parameter, and the third parameter of each server in the processing queue; According to the parameter value of at least one of the first parameter, the second parameter, and the third parameter of each server in the processing queue, the score of the server is determined, and the score is a value that characterizes the service efficiency of the server, and the score The value is positively correlated with the service efficiency of the server; the server with the highest score in the processing queue is used as the dispatching server, and the server is the server with the highest service efficiency in the processing queue.
  • the processing module 502 is specifically configured to: determine the preset function value of each parameter in the at least one parameter according to the parameter value of the parameter; according to the preset function value of each parameter in the at least one parameter Value, and the weight coefficient value of the parameter, determine the score of the server.
  • the weight coefficient value of each parameter in the at least one parameter is predicted based on the correlation coefficient between the first parameter, the second parameter, and the third parameter of each server in the processing queue and the processing duration of the server.
  • the first parameter, the second parameter, and the third parameter of each server in the processing queue are specifically: the first parameter of the server is the upper limit of the total number of service objects that the server can serve in parallel; The second parameter of the server is the remaining number of service objects that the server can still serve in parallel at the preset time; the third parameter of the server is the cumulative duration from the time the server joins the processing queue to the preset time .
  • the processing module 502 is specifically configured to mark the processing type of each server in the processing queue that processes the processing content of the service object each time within the first preset period; For each server, if the processing type of the server is the same as the processing type of the first service object to be dispatched, the score of the server is increased; otherwise, the score of the server is decreased.
  • the processing module 502 is further configured to: determine the priority of the server for the service object of each processing type according to the interval time after each server in the processing queue processes the service object of the processing type; According to the priority of the second service object to be dispatched for each server in the processing queue, and the number of requests made by the second service object to be dispatched, the score of the server is updated.
  • processing module 502 is further configured to:
  • the server whose score in the processing queue is less than the entry threshold of the processing queue is removed from the processing queue.
  • the processing procedure of each module is the same as the processing procedure of the above method item, and will not be repeated here.
  • an embodiment of the present application also provides a computer device, including a program or instruction.
  • the program or instruction When the program or instruction is executed, the following method is correspondingly executed: acquiring the first parameter and second parameter of each server in the processing queue
  • the parameter value of the parameter and the third parameter, the score value of the server is determined according to the parameter value of at least one of the first parameter, the second parameter, and the third parameter of each server in the processing queue, and the score is a characterization
  • the value of the service efficiency of the server, and the score is positively related to the service efficiency of the server; the server with the highest score in the processing queue is used as the dispatching server, and the server is in the processing queue The server with the highest service efficiency.
  • an embodiment of the present application further provides a storage medium, including a program or instruction, and when the program or instruction is executed, the dispatch method described in any of FIG. 1 is executed.
  • the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

Abstract

一种服务端的派工方法、装置、计算机设备及存储介质，用于解决现有技术中派工的整体服务效率不高的问题。方法为：获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值（101）；根据处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关（102）；将处理队列中分值最高的服务端作为派工的服务端，该服务端为处理队列中服务效率最高的服务端（103）。本方法将处理队列中服务效率最高的服务端作为派工的服务端，因此能够提升派工的整体服务效率。

Description

一种服务端的派工方法、装置、计算机设备及存储介质
相关申请的交叉引用
本申请要求在2019年04月18日提交中国专利局、申请号为201910314246.9、申请名称为“一种服务端的派工方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及金融科技(Fintech)技术领域，尤其涉及一种服务端的派工方法、装置、计算机设备及存储介质。
背景技术
随着计算机技术的发展，越来越多的技术应用在金融领域，传统金融业正在逐步向金融科技(Finteh)转变。目前，金融科技领域的派工系统包括服务对象和服务端，服务对象为需要被处理获取服务的对象，服务端是为服务对象提供服务的处理者，派工系统中需要将服务对象和服务端进行匹配，从而对服务对象进行处理。
现有技术中，派工系统将服务对象放置在服务对象队列，将服务端放置在服务端队列，按照先来先服务(first come first serve，FCFS)的原则，将位于服务对象队列的队首的服务对象与位于服务端队列的队首的服务端进行匹配。现有技术的方法中，各个服务端对于服务对象来说，除到达服务端队列的先后顺序外，没有其它差异，但实际上各个服务端对一个服务对象的服务时长和服务质量等会受到多个因素的影响，而现有技术的方法仅考虑了到达服务端队列的先后顺序这一因素，导致其派工的整体服务效率不高，这是一个亟待解决的问题。
发明内容
本申请提供一种服务端的派工方法、装置、计算机设备及存储介质，用以解决现有技术仅考虑到达服务端队列的先后顺序这一因素所导致的派工的整体服务效率不高的技术问题。
本申请提供一种服务端的派工方法，包括：获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值；根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；将所述处理队列中分值最高的服务端作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
可选的，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值的步骤包括：根据所述至少一个参数中每个参数的参数值，确定该参数的预设函数值；根据所述至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值；其中，所述至少一个参数中每个参数的权重系数值是根据所述处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。
可选的，所述处理队列中每个服务端的第一参数、第二参数和第三参数具体为：该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
可选的，所述处理队列中每个服务端在第一预设周期内每次处理服务对象的处理内容均已被标记处理类型，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值之后，还包括：针对所述处理队列中的每个服务端，若该服务端的处理 类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
可选的，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值之后，还包括：根据所述处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级；根据第二待派工服务对象对于所述处理队列中每个服务端的优先级，以及所述第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。
可选的，按照预设周期，将所述处理队列中分值小于所述处理队列的进入阈值的服务端，移出所述处理队列。
本申请实施例中，根据处理队列中每个服务端的第一参数、第二参数和第三参数的参数值，确定该服务端的分值，通过该分值表征该服务端的服务效率，且该分值与该服务端的服务效率呈正相关，因此，处理队列中分值最高的服务端即为处理队列中服务效率最高的服务端，将该服务端作为在预设时刻派工的服务端，即选择处理队列中考虑了第一参数、第二参数和第三参数之后服务效率最高的服务端，从而提升了派工的整体服务效率。
本申请提供一种服务端的派工装置，包括：获取模块，用于获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值；处理模块，用于根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
可选的，所述处理模块具体用于：根据所述至少一个参数中每个参数的参数值，确定该参数的预设函数值；根据所述至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值；其中，所述至少一个参数中每个参数的权重系数值是根据所述处理队列中每个服务端的第 一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。
可选的，所述处理队列中每个服务端的第一参数、第二参数和第三参数具体为：该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
可选的，所述处理模块具体用于：对所述处理队列中每个服务端在第一预设周期内每次处理服务对象的处理内容的处理类型进行标记；针对所述处理队列中的每个服务端，若该服务端的处理类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
可选的，所述处理模块还用于：根据所述处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级；根据第二待派工服务对象对于所述处理队列中每个服务端的优先级，以及所述第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。
可选的，所述处理模块还用于：
按照预设周期，将所述处理队列中分值小于所述处理队列的进入阈值的服务端，移出所述处理队列。
可选的，本申请提供一种计算机设备，包括程序或指令，当所述程序或指令被执行时，通过本申请提供的服务端的派工方法及可选方法被执行。
可选的，本申请提供一种存储介质，包括程序或指令，当所述程序或指令被执行时，通过本申请提供的服务端的派工方法及可选方法被执行。
附图说明
图1为本申请实施例中一种服务端的派工方法的步骤流程图；
图2为本申请实施例提出的一种服务端的派工方法对应的分值排序示意图；
图3为本申请实施例提出的一种服务端的派工方法对应的多元回归分析结果的示意图；
图4为本申请实施例中一种服务端的派工方法对应的一种客服派工系统的示意图；
图5为本申请实施例中一种服务端的派工装置对应的结构示意图。
具体实施方式
为了更好的理解上述技术方案，下面将结合说明书附图及具体的实施方式对上述技术方案进行详细的说明，应当理解本申请实施例以及实施例中的具体特征是对本申请技术方案的详细的说明，而不是对本申请技术方案的限定，在不冲突的情况下，本申请实施例以及实施例中的技术特征可以相互结合。
派工系统是一种将服务对象和服务端进行配对的系统。随着计算机技术的发展，派工系统也应用在金融领域，而传统金融业正在逐步向金融科技(Fintech)转变。目前，科技金融领域的派工系统也在发展。派工系统的服务对象为需要被处理获取服务的对象，服务端是为服务对象提供服务的处理者，将服务对象和服务端进行匹配的过程称为派工。举例来说，在客服派工系统中，服务对象为需要获取咨询服务的客户，服务端为处理客户咨询服务的客服，派工即为将客户与客服进行匹配的过程。
现有技术中，派工系统按照先来先服务(first come first serve，FCFS)的原则，将位于服务对象队列的队首的服务对象与位于服务端队列的队首的服务端进行匹配。这种方法下，各个服务端对于服务对象来说，仅有到达先后顺序上的差异。但实际上各个服务端对一个服务对象的服务时长和服务质量等会受到多个因素的影响，当给一个服务对象匹配不同的服务端时，不同的服务器提供的服务效率也会有高有低。现有技术的方法仅考虑了到达服务端队列的先后顺序这一因素，而未考虑其它因素，从而会使得派工的整体服务效率不高。
为此，本申请实施例提供一种服务端的派工方法，综合考虑影响服务端的服务效率的多个因素。如图1所示，为本申请实施例中一种服务端的派工方法的步骤流程图。
步骤101：获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值。
步骤102：根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关。
步骤103：将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
需要说明的是，步骤101～步骤103的过程中，服务方式既可以为一个服务端独立服务一个服务对象，也可以为一个服务端同时服务多个服务对象。派工系统中，当服务端同时服务多个服务对象时，一个服务端可以在多个处理队列上排队，以用于并行处理多个服务对象。
在用户侧，服务对象根据进线时间的先后顺序进行排序，派工系统根据用户属性，如服务对象分组或者服务对象等级等调整服务对象的进线优先级；在服务端侧，服务端根据分值先后进行排序。
步骤101中，需要说明的是，第一参数、第二参数和第三参数是结合现有服务场景中影响派工顺序的因素设置的三个参数，每个参数在每个时刻都对应一个参数值。步骤101～步骤102中仅以第一参数、第二参数和第三参数举例说明，参数并不限定是三个。
步骤102中，一种可选实施方式为，按照以下步骤确定该服务端的分值：根据至少一个参数中每个参数的参数值，确定该参数的预设函数值；根据至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值。其中，第一参数、第二参数和第三参数可根据具体场景进行选取，举例来说，具体为：该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并 行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
另外，在该可选实施方式下，第一参数、第二参数和第三参数中每个参数的权重系数值，可以根据处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数进行预设。举例来说，可以将相关性系数较高的参数权重系数值也设的较高。
下面以一种具体情形举例说明该可选实施方式：
根据分值计算公式确定处理队列中每个服务端的分值。
作为一种示例，分值计算公式为：
Figure PCTCN2020076492-appb-000001
其中，S为该服务端的分值；i为正整数；X i为该服务端的第i个参数的参数值；f i(X i)为X i的预设函数；W i为f i(X i)的权重系数值。
分值计算公式中W i是根据所述处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。举例来说，派工系统对服务端的派工没有优先级，整体服务效率不高，相同问题的客户进线会派工到不同客服，对客服来说服务不连贯。
Figure PCTCN2020076492-appb-000002
其中，X 1为该服务端能够并行服务的服务对象的总数量上限；X 2为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；X 3为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
如表1所示，为根据服务队列中服务端的参数选择派工的服务端的不同情形，最终选择的派工服务端为：按照服务效率的预设规则确定的服务效率较高的服务端。以情形1为例，预设规则为：在X 1和X 2相同时，X 3越小的服务端服务效率越高。其它情形选择出的派工服务端，也是根据服务端实际服务的服务时长和服务对象等因素的预设规则选择的，具体规则可根据需要设定，在此不再赘述。
Figure PCTCN2020076492-appb-000003
表1
在实际使用过程中，由于X 1和X 2存在相关性，线性模型的分值计算公式在部分派工场景中无法得到预期的结果。例如，当两者同比例增加时，权重系数值需要有所不同。为了减少X 1和X 2的相关性，增大X 2对权重值的影响，同时减小X 1和X 2的相关性对分值的影响，在该可选实施方式中，用X 2与X 1的比值替换X 1，从而得到公式(2)。需要说明的是，减少相关性的变形公式不限于参数X 1与X 2，表达式也不限于公式(2)。
公式(2)中，W 1、W 2、W 3既可以是预设值，也可以是根据预设算法确定的值，下面以多元回归分析方法为例，说明W 1、W 2、W 3的一种确定方法。多元回归分析是指在相关变量中将一个变量视为因变量，其他一个或多个变量视为自变量，建立多个变量之间线性或非线性数学模型数量关系式并利用样本数据进行分析的统计分析方法。用于多元回归分析的数据集可根据与表1一致的服务效率的预设规则确定分数，并按分数从高到低排序，具体如图2所示，为本申请实施例提出的一种服务端的派工方法对应的分值排序示意图。图2所示的分值是根据X 2/X 1的值从高到低的顺序预先设定的值。
对图2中的数据集进行多元回归分析可得到W 1、W 2，再将得到的W 1、W 2代入公式(2)，并再次用多元回归分析得到W 3。多元回归的一种工具为Excel数据分析功能中的多元分析工具，其分析结果如图3所示。通过图2的数据 集最终确定的分值计算公式为：
Figure PCTCN2020076492-appb-000004
如表2所示，为根据服务队列中服务端的参数以及公式(3)确定的派工的服务端的不同情形。
Figure PCTCN2020076492-appb-000005
表2
在步骤102之后，一种可选实施方式如下：
在第一预设周期内，对处理队列中每个服务端每次处理服务对象的处理内容标记处理类型。举例来说，第一预设周期为1天，服务端1在1天内处理了处理类型1、处理类型2、处理类型3三种类型的处理内容。
针对处理队列中的每个服务端，若该服务端的处理类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
举例来说，第一待派工服务对象需要一个服务端派工，且第一待派工服务对象的处理内容的处理类型为处理类型1，处理队列中可选择的服务端有服务端1、服务端2和服务端3三个服务端，其中只有服务端1在1天内处理过处理类型1的处理内容，那么在步骤102确定的分值基础上，则可以增加服务端1的分值，并减少服务端2和服务端3的分值。具体减少方式和规则可 根据具体应用场景设定，如预设较重要处理类型的处理内容增加或减少的分值较高。
在步骤102之后，另一种可选的实施方式为：
根据处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级。之后，再根据第二待派工服务对象对于处理队列中每个服务端的优先级，以及第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。举例来说，服务端1处理了内容为处理类型1的服务对象的间隔时长为5小时，处理了内容为处理类型2的服务对象的间隔时长为3小时，则设定处理类型2的服务对象的优先级高于处理类型1的服务对象的优先级。需要说明的是，考虑到每个服务端处理同一种处理类型的处理内容的服务对象的处理效率不同，因此，每个服务端都会根据自身处理效率设定服务对象的优先级。之后，更新该服务端的分值的规则可根据具体场景设定。举例来说，若第二待派工服务对象对于处理队列中服务端1和服务端2的优先级分别为8和10，第二待派工服务对象发出服务请求的请求次数为5次，但是服务端1对第二待派工服务对象的请求更为敏感，举例来说，第二待派工服务对象的处理类型为处理类型2，对第二待派工服务对象的请求更新的分值根据服务端处理过处理类型2服务对象的间隔时长确定，服务端1处理过处理类型2服务对象的间隔时长更短，第二待派工服务对象每请求1次，服务端1分值增加10，但是服务端2分值只增加5。从而，能够增加相同类型的服务对象被同一个服务端服务的可能性，提升服务的连贯性。
图4为本申请实施例中一种服务端的派工方法对应的一种客服派工系统的示意图。需要说明的是，该派工系统仅以客服派工系统为例，不限于该系统。
在步骤101～步骤103的执行过程中，还有一种可选实施方式为：
按照预设周期，将所述处理队列中分值小于所述处理队列的进入阈值的服务端，移出所述处理队列，或者采用新的服务端替换所述分值小于进入阈 值的服务端。也就是在处理队列设置一个分值的进入阈值，当服务端的分值大于或等于进入阈值时，说明服务端的服务效率能够达到要求，从而服务端可以保留在处理队列中，保证了服务端的服务质量。
如图5所示，为本申请实施例中一种服务端的派工装置对应的结构示意图。
本申请提供一种服务端的派工装置，包括：获取模块501，用于获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值；处理模块502，用于根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
可选的，所述处理模块502具体用于：根据所述至少一个参数中每个参数的参数值，确定该参数的预设函数值；根据所述至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值。
可选的，所述至少一个参数中每个参数的权重系数值是根据所述处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。
可选的，所述处理队列中每个服务端的第一参数、第二参数和第三参数具体为：该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
可选的，所述处理模块502具体用于：对所述处理队列中每个服务端在第一预设周期内每次处理服务对象的处理内容的处理类型进行标记；针对所述处理队列中每个服务端，若该服务端的处理类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
可选的，所述处理模块502还用于：根据所述处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级；根据第二待派工服务对象对于所述处理队列中每个服务端的优先级，以及所述第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。
可选的，所述处理模块502还用于：
按照预设周期，将所述处理队列中分值小于所述处理队列的进入阈值的服务端，移出所述处理队列。
各个模块的处理过程与上述方法项的处理过程一致，此处不做赘述。
基于同一发明构思，本申请实施例还提供一种计算机设备，包括程序或指令，当所述程序或指令被执行时，相应执行如下方法：获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值，根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
基于同一发明构思，本申请实施例还提供一种存储介质，包括程序或指令，当所述程序或指令被执行时，执行图1任意所述的派工方法。
最后应说明的是：本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或 方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (13)

  1. 一种服务端的派工方法，其特征在于，包括：
    获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值；
    根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；
    将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
  2. 如权利要求1所述的方法，其特征在于，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值的步骤包括：
    根据所述至少一个参数中每个参数的参数值，确定该参数的预设函数值；
    根据所述至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值；其中，所述至少一个参数中每个参数的权重系数值是根据所述处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。
  3. 如权利要求1所述的方法，其特征在于，所述处理队列中每个服务端的第一参数、第二参数和第三参数具体为：
    该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
  4. 如权利要求1-3任一所述的方法，其特征在于，所述处理队列中每个服务端在第一预设周期内每次处理服务对象的处理内容均已被标记处理类型，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值之后，还包括：
    针对所述处理队列中每个服务端，若该服务端的处理类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
  5. 如权利要求4所述的方法，其特征在于，所述根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值之后，还包括：
    根据所述处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级；
    根据第二待派工服务对象对于所述处理队列中每个服务端的优先级，以及所述第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。
  6. 如权利要求1-3任一所述的方法，其特征在于，还包括：
    按照第二预设周期，将所述处理队列中分值小于所述处理队列的进入阈值的服务端，移出所述处理队列。
  7. 一种服务端的派工装置，其特征在于，包括：
    获取模块，用于获取处理队列中每个服务端的第一参数、第二参数和第三参数的参数值；
    处理模块，用于根据所述处理队列中每个服务端的第一参数、第二参数和第三参数中至少一个参数的参数值，确定该服务端的分值，该分值为表征该服务端服务效率的数值，且该分值与该服务端服务效率呈正相关；将所述处理队列中分值最高的服务端，作为派工的服务端，该服务端为所述处理队列中服务效率最高的服务端。
  8. 如权利要求7所述的装置，其特征在于，所述处理模块具体用于：
    根据所述至少一个参数中每个参数的参数值，确定该参数的预设函数值；根据所述至少一个参数中每个参数的预设函数值，以及该参数的权重系数值，确定该服务端的分值；其中，所述至少一个参数中每个参数的权重系数值是根据所述处理队列中每个服务端的第一参数、第二参数和第三参数与该服务端的处理时长的相关性系数预设的。
  9. 如权利要求7所述的装置，其特征在于，所述处理队列中每个服务端的第一参数、第二参数和第三参数具体为：
    该服务端的第一参数为该服务端能够并行服务的服务对象的总数量上限；该服务端的第二参数为该服务端在预设时刻还能够并行服务的服务对象的剩余数量；该服务端的第三参数为该服务端加入所述处理队列的开始时刻至所述预设时刻的累计时长。
  10. 如权利要求7-9任一所述的装置，其特征在于，所述处理模块具体用于：
    对所述处理队列中每个服务端在第一预设周期内每次处理服务对象的处理内容的处理类型进行标记；
    针对所述处理队列中每个服务端，若该服务端的处理类型与第一待派工服务对象的处理类型相同，则增加该服务端的分值；否则，则减少该服务端的分值。
  11. 如权利要求10所述的装置，其特征在于，所述处理模块还用于：
    根据所述处理队列中每个服务端处理每种处理类型服务对象之后的间隔时长，确定该服务端对于该种处理类型服务对象的优先级；
    根据第二待派工服务对象对于所述处理队列中每个服务端的优先级，以及所述第二待派工服务对象发出服务请求的请求次数，更新该服务端的分值。
  12. 一种计算机设备，其特征在于，包括程序或指令，当所述程序或指令被执行时，如权利要求1至6中任意一项所述的方法被执行。
  13. 一种存储介质，其特征在于，包括程序或指令，当所述程序或指令被执行时，如权利要求1至6中任意一项所述的方法被执行。
PCT/CN2020/076492 2019-04-18 2020-02-24 一种服务端的派工方法、装置、计算机设备及存储介质 WO2020211529A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910314246.9A CN110084498A (zh) 2019-04-18 2019-04-18 一种服务端的派工方法、装置、计算机设备及存储介质
CN201910314246.9 2019-04-18

Publications (1)

Publication Number Publication Date
WO2020211529A1 true WO2020211529A1 (zh) 2020-10-22

Family

ID=67415541

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/076492 WO2020211529A1 (zh) 2019-04-18 2020-02-24 一种服务端的派工方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN110084498A (zh)
WO (1) WO2020211529A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110084498A (zh) * 2019-04-18 2019-08-02 深圳前海微众银行股份有限公司 一种服务端的派工方法、装置、计算机设备及存储介质
CN110807578A (zh) * 2019-10-16 2020-02-18 上海易点时空网络有限公司 服务订单分配方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140149249A1 (en) * 2009-12-09 2014-05-29 Allconnect, Inc. Systems and methods for managing and/or recommending third party products and services provided to a user
CN108288196A (zh) * 2017-01-09 2018-07-17 阿里巴巴集团控股有限公司 一种业务对象的推荐方法和装置
CN109242275A (zh) * 2018-08-21 2019-01-18 平安科技（深圳）有限公司 任务分配方法、装置及存储介质
CN109359798A (zh) * 2018-08-21 2019-02-19 平安科技（深圳）有限公司 任务分配方法、装置及存储介质
CN110084498A (zh) * 2019-04-18 2019-08-02 深圳前海微众银行股份有限公司 一种服务端的派工方法、装置、计算机设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101729267A (zh) * 2008-10-31 2010-06-09 华为技术有限公司 一种排队方法和装置
CN104618492B (zh) * 2015-02-11 2018-02-06 北京金和软件股份有限公司 一种基于多个服务器的数据处理系统
CN106327064A (zh) * 2016-08-12 2017-01-11 北京东方车云信息技术有限公司 一种服务端的派单方法及系统
CN109615213B (zh) * 2018-12-06 2022-04-29 广东金赋科技股份有限公司 一种运维服务任务的智能分配方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140149249A1 (en) * 2009-12-09 2014-05-29 Allconnect, Inc. Systems and methods for managing and/or recommending third party products and services provided to a user
CN108288196A (zh) * 2017-01-09 2018-07-17 阿里巴巴集团控股有限公司 一种业务对象的推荐方法和装置
CN109242275A (zh) * 2018-08-21 2019-01-18 平安科技（深圳）有限公司 任务分配方法、装置及存储介质
CN109359798A (zh) * 2018-08-21 2019-02-19 平安科技（深圳）有限公司 任务分配方法、装置及存储介质
CN110084498A (zh) * 2019-04-18 2019-08-02 深圳前海微众银行股份有限公司 一种服务端的派工方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN110084498A (zh) 2019-08-02

Similar Documents

Publication Publication Date Title
CN109558989B (zh) 排队时间预测方法、装置、设备及计算机可读存储介质
WO2019127875A1 (zh) 专属坐席池分配方法、电子装置及计算机可读存储介质
WO2020211529A1 (zh) 一种服务端的派工方法、装置、计算机设备及存储介质
WO2019144516A1 (zh) 坐席分配方法、电子装置及计算机可读存储介质
TW201835789A (zh) 評分模型的建立、用戶信用的評估方法及裝置
CN106874112B (zh) 一种结合负载均衡的工作流回填方法
CN109214772B (zh) 项目推荐方法、装置、计算机设备及存储介质
CN105893263A (zh) 一种测试任务调度方法
CN106874100A (zh) 计算资源分配方法及装置
WO2021057465A1 (zh) 一种对深度学习模型进行并行处理的方法及装置
US11822965B2 (en) Machine learning task compartmentalization and classification
CN114675975A (zh) 一种基于强化学习的作业调度方法、装置及设备
EP3885910A1 (en) Dynamic quality of service management for deep learning training communication
CN111736959B (zh) 异构集群下考虑数据亲和性的Spark任务调度方法
CN116909751A (zh) 一种云计算系统中的资源分配方法
CN109145207B (zh) 一种基于分类指标预测的信息个性化推荐方法及装置
WO2023077815A1 (zh) 一种处理敏感数据的方法及装置
US20200314019A1 (en) Managing bandwidth based on user behavior
KR20200104734A (ko) 이종 gpu 클러스터 환경에서 동기식 분산 학습의 스트래글러 해결을 위한 배치 오케스트레이션 서버
WO2018205890A1 (zh) 一种分布式系统的任务分配方法及系统及其计算机可读存储介质和计算机设备
US11544332B2 (en) Bipartite graph construction
US10552485B1 (en) Performance percentile determination and display
CN103885837B (zh) 一种多线程处理数据的方法及装置
CN113641670B (zh) 数据存储及数据检索方法、装置、电子设备及存储介质
JPWO2019059135A1 (ja) 情報処理装置、情報処理システム、情報処理方法およびプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20790572

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 31.01.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20790572

Country of ref document: EP

Kind code of ref document: A1