CN116402290A

CN116402290A - Task scheduling method, device, equipment and storage medium based on decision tree

Info

Publication number: CN116402290A
Application number: CN202310316054.8A
Authority: CN
Inventors: 苏晨; 郑昊敏; 李昊彦
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2023-03-16
Filing date: 2023-03-16
Publication date: 2023-07-07

Abstract

The method comprises the steps of obtaining capability data of an optional agent, determining attribute characteristics corresponding to each task to be scheduled corresponding to the optional agent, inputting the capability data and the attribute characteristics of each task to be scheduled into a preset decision tree model, obtaining priorities corresponding to each task to be scheduled output by the preset decision tree model, selecting the task to be scheduled with the highest priority from the priorities of the tasks to be scheduled, and distributing the target task to the optional agent. In addition, the present application relates to blockchain techniques in which decision tree model information may be stored in a blockchain _。 According to the embodiment of the application, the task conversion rate of the seat can be improved.

Description

Task scheduling method, device, equipment and storage medium based on decision tree

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a task scheduling method, device, equipment, and storage medium based on a decision tree.

Background

The through seat is still an important outlet channel for car insurance service, and each seat personnel may need to complete the outbound of nearly two hundred strange phones every day, and along with the aggravation of poor impression of the phone touch mode by the customer, the rejection rate of the customer is extremely high, and under strict acceptance, the seat personnel face huge pressure.

The conventional task allocation mechanism generally adopts a random allocation mode, and the next number to be dialed is just like a blind extraction box, which cannot be predicted and selected. Moreover, the simple task allocation mode is easy to cause task allocation errors or mismatching of task allocation, and greatly influences the task conversion efficiency of seat personnel.

Disclosure of Invention

The embodiment of the application aims to provide a task scheduling method, device, equipment and storage medium based on a decision tree, so as to solve the technical problem that task allocation errors or mismatching of task allocation is caused and task conversion efficiency of seat personnel is greatly affected.

In order to solve the above technical problems, the embodiments of the present application provide a task scheduling based on decision tree, which adopts the following technical scheme:

acquiring capability data of an optional agent, and determining attribute characteristics corresponding to each task to be scheduled corresponding to the optional agent, wherein the attribute characteristics comprise customer value, customer time and task difficulty corresponding to the task to be scheduled;

Inputting the capability data and the attribute characteristics of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model;

selecting the task to be scheduled with the highest priority from the priorities of the tasks to be scheduled as a target task to be scheduled;

and distributing the target scheduling task to the optional agent.

Optionally, the step of inputting the capability data and the attribute features of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model specifically includes:

calculating a first task value corresponding to the client value in each task to be scheduled based on the preset decision tree model;

if the first task value is larger than a first preset value, calculating a second task value corresponding to task difficulty in each task to be scheduled based on the preset decision tree model;

if the second task value is larger than a second preset value, calculating a third task value corresponding to the capability data of the optional seat based on the preset decision tree model;

If the third task value is larger than a third preset value, calculating a fourth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model;

and if the fourth task value is larger than a fourth preset value, setting the priority of the task to be scheduled as the highest priority.

Optionally, after the step of calculating the first task value corresponding to the client value in each task to be scheduled based on the preset decision tree model, the method further includes:

and if the first task value is smaller than or equal to a first preset value, setting the priority of the task to be scheduled as a first low priority.

Optionally, after the step of calculating the second task value corresponding to the task difficulty in each task to be scheduled based on the preset decision tree model, the method further includes:

if the second task value is smaller than or equal to a second preset value, calculating a fifth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model;

if the fifth task value is larger than a fifth preset value, setting the priority of the task to be scheduled as a high priority, wherein the high priority is smaller than the highest priority;

And if the fifth task value is smaller than or equal to a fifth preset value, setting the priority of the task to be scheduled as a second low priority, wherein the second low priority is larger than the first low priority.

Optionally, after the step of calculating the third task value corresponding to the capability data of the optional agent based on the preset decision tree model, the method further includes:

and if the third task value is smaller than or equal to a third preset value, setting the priority of the task to be scheduled as a third low priority, wherein the third priority is larger than the second priority.

Optionally, after the step of calculating the fourth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model, the method further includes:

and if the fourth task value is smaller than or equal to a fourth preset value, setting the priority of the task to be scheduled as a fourth low priority, wherein the fourth priority is larger than the third priority.

Optionally, the preset decision tree model is constructed by the following steps:

acquiring a preset number of historical task scheduling data, wherein the historical task scheduling data comprise historical attribute characteristics and historical scheduling results corresponding to each historical task;

Determining attribute weights corresponding to the historical attribute features according to the historical scheduling results, and determining priority levels corresponding to the historical tasks according to the attribute weights and the historical scheduling results;

calculating information gain of each historical attribute characteristic based on each attribute weight and each priority level, and constructing nodes of a decision tree according to each information gain and each historical attribute characteristic;

and constructing the preset decision tree model according to the constructed nodes and the priority levels.

In order to solve the above technical problem, an embodiment of the present application further provides a task scheduling device based on a decision tree, including:

the system comprises an acquisition module, a scheduling module and a scheduling module, wherein the acquisition module is used for acquiring capability data of an optional agent and determining attribute characteristics corresponding to each task to be scheduled, which correspond to the optional agent, wherein the attribute characteristics comprise customer value, customer time and task difficulty corresponding to the task to be scheduled;

the input module is used for inputting the capability data and the attribute characteristics of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model;

The selecting module is used for selecting the task to be scheduled with the highest priority from the priorities of the tasks to be scheduled as a target task to be scheduled;

and the allocation module is used for allocating the target scheduling task to the optional agent.

To solve the above technical problem, an embodiment of the present application further provides a computer device, including a memory and a processor, where the memory stores computer readable instructions, and the processor implements the steps of the decision tree-based task scheduling method as described in any of the above when executing the computer readable instructions.

To solve the above technical problem, embodiments of the present application further provide a computer readable storage medium, where computer readable instructions are stored on the computer readable storage medium, where the computer readable instructions implement steps of the decision tree based task scheduling method as described in any of the above when executed by a processor.

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

according to the technical scheme, the capability data of the optional agents are obtained, the attribute characteristics corresponding to each task to be scheduled corresponding to the optional agents are determined, the attribute characteristics comprise the client value, the client time and the task difficulty corresponding to the task to be scheduled, then the capability data and the attribute characteristics of each task to be scheduled are input into a preset decision tree model, the priority corresponding to each task to be scheduled output by the preset decision tree model is obtained, finally the task to be scheduled with the highest priority is selected from the priority of each task to be scheduled to serve as a target scheduling task, and the target scheduling task is distributed to the optional agents. Therefore, more and more efficient working modes and plans can be provided for the seat than before; and the scheduling task is obtained by calculation based on the decision tree model, so that the highest input-output ratio of each task processed by the agent can be ensured, high-value tasks can be completed as much as possible in a limited time, and the task conversion rate of the agent is improved.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a decision tree based task scheduling method according to the present application;

FIG. 3 is a flow chart of another embodiment of a decision tree based task scheduling method according to the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a decision tree based task scheduling device according to the present application;

FIG. 5 is a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the

terminal devices

101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the

terminal devices

101, 102, 103.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the

terminal devices

101, 102, 103.

It should be noted that, the method provided in the embodiments of the present application is generally performed by the server/terminal device, and accordingly, the apparatus is generally configured in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of a decision tree based task scheduling method according to the present application is shown. The task scheduling method based on the decision tree comprises the following steps:

Step S201, capability data of the optional agents are obtained, and attribute characteristics corresponding to each task to be scheduled corresponding to the optional agents are determined, wherein the attribute characteristics comprise customer value, customer time and task difficulty corresponding to the task to be scheduled.

In this embodiment, the electronic device (e.g., the server/terminal device shown in fig. 1) on which the decision tree-based task scheduling method operates may receive the capability data through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.

Specifically, the execution body of the embodiment of the present application is a terminal device, where the terminal device includes but is not limited to: computing devices such as desktop computers, notebooks, palmtops, cloud servers, and the like. The terminal equipment acquires capability data of the optional agents, and determines attribute characteristics corresponding to each task to be scheduled, wherein the attribute characteristics comprise customer value, customer time and task difficulty corresponding to the task to be scheduled. If there is only one task to be scheduled, the priority of the task to be scheduled is the highest priority. That is, in the present application, the tasks to be scheduled corresponding to the optional agents include at least two.

In this embodiment, before scheduling tasks for optional agents, it is necessary to determine which agents in the service system are assignable, that is, the optional agents described above. In general, since the data volume of the service system is extremely large, the number of optional agents is determined according to the activity information on the service system. That is, a certain condition needs to be set to screen out a suitable seat person as the optional seat. For example, an operator who is performing an operator task cannot be an optional operator, and the like, and is not limited thereto.

Further, when the number of the optional agents is at least two, capability data of each optional agent and attribute features of each task to be scheduled corresponding to each optional agent need to be acquired.

Step S202, inputting the capability data and the attribute characteristics of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model.

It may be understood that, after the terminal device obtains the attribute features corresponding to each task to be scheduled corresponding to the optional agents, that is, obtains the corresponding client value, client time and task difficulty of each task to be scheduled, the capability data and the corresponding client value, client time and task difficulty of each task to be scheduled may be input into a preset decision tree model, where the preset decision tree model uses the capability data and the corresponding client value, client time and task difficulty of each task to be scheduled as nodes and uses the corresponding task priority as a decision result, and the preset decision tree model may then match the capability data and the corresponding client value, client time and task difficulty of each task to be scheduled with each node in a decision tree, so as to determine the priority level corresponding to each task to be scheduled.

The priority level is used here to represent the task processing order of the tasks to be scheduled. For example, the task to be scheduled corresponding to a priority level higher than 90% is a superior processing order, the task to be scheduled corresponding to a priority level between 75% and 90% is a good processing order, the task to be scheduled corresponding to a priority level between 60% and 75% is a medium processing order, the task to be scheduled corresponding to a priority level lower than 60% is a bad processing order, and in the actual scheduling process, scheduling is performed according to a superior processing order > a good processing order > a medium processing order > a bad processing order. The conversion rates of the corresponding tasks are, in order, high-grade conversion rate, good-grade conversion rate, medium-grade conversion rate and poor-grade conversion rate according to the scheduling sequence.

Step S203, selecting the task to be scheduled with the highest priority from the priorities of the tasks to be scheduled as a target task to be scheduled;

and step S204, distributing the target scheduling task to the optional agents.

In this embodiment, after the priorities of the tasks to be scheduled are obtained, the task to be scheduled with the highest priority is selected from the priorities of the tasks to be scheduled, and is used as the target task. And then the target scheduling task is distributed to the optional agents, namely the target scheduling task can be highlighted in a service system, and the target scheduling task has the corresponding identification of the optional agents, so that the optional agents can select the task with the highest priority from a plurality of tasks to be scheduled in a service system.

Of course, in the application, since the number of tasks to be scheduled corresponding to the optional agents may be multiple, after the priorities of the tasks to be scheduled are calculated through the preset decision tree model, all the tasks to be scheduled are ordered according to the priority, so that the optional agents can select tasks which are properly matched from the tasks to be scheduled according to the ordering result, and the task conversion rate of the agents is improved.

Further, when the task to be scheduled is newly added in the service system, the priority of the task to be scheduled is calculated again through a preset decision tree model, and the task to be scheduled is reordered according to the calculated priority.

In addition, a large amount of customer insurance data collected by the business system has a deeper meaning, the data can be used for presuming the potential demands and product preferences of users, and companies can be assisted in designing more personalized insurance products which meet the demands of the users.

In some optional implementations of this embodiment, the step of inputting the capability data and the attribute features of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model specifically includes:

step S2021, calculating a first task value corresponding to the client value in each task to be scheduled based on the preset decision tree model;

step S2022, if the first task value is greater than a first preset value, calculating a second task value corresponding to a task difficulty in each task to be scheduled based on the preset decision tree model;

step S2023, if the second task value is greater than a second preset value, calculating a third task value corresponding to the capability data of the optional agent based on the preset decision tree model;

step S2024, if the third task value is greater than a third preset value, calculating a fourth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model;

in step S2025, if the fourth task value is greater than the fourth preset value, the priority of the task to be scheduled is set to the highest priority.

The steps are as follows:

based on the preset decision tree model, calculating a first task value corresponding to the client value in each task to be scheduled, where the calculating of the client value in each task to be scheduled requires continuous quantization, for example: when calculating the client value, the client with estimated premium value greater than 5000 yuan or historical applied total amount exceeding 15000 yuan can be considered as a high-value client, at this time, the calculated first task value is 1, and the client with estimated premium value less than 5000 yuan or historical applied total amount not exceeding 15000 yuan is a low-value client, at this time, the calculated first task value is 0. Here, the quantized values of the estimated premium value and the historical applied total amount are particularly required to be obtained empirically.

After the first task value is obtained, comparing the first task value with a first preset value, wherein the first preset value is 0. If the first task value is larger than a first preset value, calculating a second task value corresponding to task difficulty in each task to be scheduled based on the preset decision tree model; and if the first task value is smaller than or equal to a first preset value, setting the priority of the task to be scheduled as a first low priority.

In this embodiment, when calculating the second task value corresponding to the task difficulty in each task to be scheduled based on the preset decision tree model, the task difficulty needs to be quantified, and in particular, the task difficulty may be set according to the manner of quantifying the client value, which is not described herein in detail.

That is, when the task difficulty is a high-difficulty task, the calculated second task value is "1", and when the task difficulty is a low-difficulty task, the calculated second task value is "0". After the second task value is obtained, comparing the second task value with a second preset value, wherein the second preset value is 0. If the second task value is larger than a second preset value, calculating a third task value corresponding to the capability data of the optional seat based on the preset decision tree model; and if the second task value is smaller than or equal to a second preset value, calculating a fifth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model. If the client time is proper, the fifth task value is "1", and if the client time is improper, the fifth task value is "0". The term "suitable" refers to whether the current time of the optional agent is suitable for contacting the customer, for example, ten am is defined as suitable for contacting the customer, 6 pm is defined as unsuitable for contacting the customer, etc.

After a fifth task value is obtained, comparing the fifth task value with a fifth preset value, wherein the fifth preset value is 0, and when the fifth task value is larger than the fifth preset value, setting the priority of the task to be scheduled as a high priority, wherein the high priority is smaller than the highest priority; and if the numerical value of the fifth task is smaller than or equal to a fifth preset value, setting the priority of the task to be scheduled as a second low priority, wherein the second low priority is larger than the first low priority.

Further, when calculating a third task value corresponding to the capability data of the optional agent based on the preset decision tree model, if the capability data of the optional agent is higher than task difficulty, the third task value is "1"; and if the capability data of the optional agent is lower than the task difficulty, the third task value is 0. And after the third task value is obtained, comparing the third task value with a third preset value, wherein the third preset value is 0.

If the third task value is larger than a third preset value, calculating a fourth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model, and if the third task value is smaller than or equal to the third preset value, setting the priority of the task to be scheduled as a third low priority, wherein the third priority is larger than the second priority.

And when calculating a fourth task value corresponding to the client time in each task to be scheduled based on the preset decision tree model, if the client time is proper, the fourth task value is '1', and if the client time is improper, the fourth task value is '0'.

After a fourth task value is obtained, comparing the fourth task value with a fourth preset value, wherein the fourth preset value is 0, and when the fourth task value is larger than the fourth preset value, setting the priority of the task to be scheduled as the highest priority, wherein the highest priority is larger than the high priority; and if the fourth task value is smaller than or equal to a fourth preset value, setting the priority of the task to be scheduled as a fourth low priority, wherein the fourth low priority is larger than the third low priority.

That is, the priorities of the respective tasks to be scheduled are ordered from high to low as the highest priority, high priority, fourth low priority, third low priority, second low priority, and first low priority. In actual sorting, the tasks to be sorted can be distributed to the optional agents according to the sorting, and in addition, when the optional agents complete the tasks with the highest priority, the tasks with the highest priority are the tasks with the lowest priority and are moved to the completed task list.

Therefore, the priority of the scheduling task can be obtained through the calculation of the decision tree model, the highest input-output ratio of each task processed by the agent is ensured, high-value tasks can be completed as much as possible within a limited time, and the task conversion rate of the agent is improved.

Based on the above embodiment, as shown in the figure, the embodiment of the present application may further construct a preset decision tree model through the following steps:

step S101, acquiring a preset number of historical task scheduling data, wherein the historical task scheduling data comprises historical attribute characteristics and historical scheduling results corresponding to each historical task;

step S102, determining attribute weights corresponding to the historical attribute features according to the historical scheduling results, and determining priority levels corresponding to the historical tasks according to the attribute weights and the historical scheduling results;

step S103, calculating information gain of each history attribute characteristic based on each attribute weight and each priority level, and constructing nodes of a decision tree according to each information gain and each history attribute characteristic;

step S104, constructing the preset decision tree model according to the constructed nodes and the priority levels.

The steps are as follows:

in this scenario, when the preset decision tree model is constructed, historical task scheduling data may be first obtained, where each obtained historical task scheduling data may include a historical attribute feature and a historical scheduling result corresponding to each historical task, where the historical scheduling result may include a scheduling success and a scheduling failure; secondly, big data analysis can be carried out on all history scheduling results to determine the scheduling success rate of the history tasks corresponding to the history attribute features, and attribute weights corresponding to the history attribute features can be determined according to the scheduling success rate of the history attribute features, for example, big data analysis can be carried out on all history scheduling results to determine the scheduling success rate of the history attribute features, namely, the number of the history tasks which contain the history attribute features and are successfully distributed can be obtained, and the total number of the history tasks is calculated, so that the scheduling success rate containing the history attribute features is obtained, the higher the scheduling success rate is, the higher the attribute weights corresponding to the history attribute features are, and conversely, the lower the scheduling success rate is, the lower the attribute weights corresponding to the history attribute features are.

And determining the priority level of each historical task according to the corresponding final scheduling success rate, so as to accurately analyze the task level of each historical task by comprehensively considering a plurality of attribute features and attribute weights corresponding to the attribute features and ensure the rationality and the effectiveness of task level determination.

Each level of non-leaf node of the decision tree can be constructed according to the information gain of each history attribute feature, wherein the higher the information gain is, the higher the number of node levels of the history attribute feature corresponding to the information gain in the decision tree is, for example, the history attribute feature can be firstly ordered according to the information gain, then the judging condition can be determined according to each history task schedule data, so that each level of non-leaf node of the decision tree can be constructed according to the ordered history attribute feature and the judging condition, and the decision result corresponding to each leaf node in the constructed decision tree can be determined according to the priority level corresponding to each history allocation task. Each non-leaf node is a historical attribute feature, the connection line between the nodes can be the judging condition required to be met from the previous node to the next node, each leaf node is a decision result, and the decision result is a priority level corresponding to all the judging conditions from the root node to the leaf node. After a decision tree taking the historical attribute features as nodes and taking the priority level as a decision result is obtained, the decision tree can be determined as the preset decision tree model, the node position of each attribute feature in the decision tree can be accurately determined through calculation of attribute entropy and information gain, the judgment condition in the decision process can be accurately determined, the construction accuracy of the preset decision tree model is ensured, and the task level determination accuracy in a task to be distributed is improved.

In the scene, the attribute weight of each attribute feature is determined by carrying out big data analysis on a large amount of historical task scheduling data, and the information gain of each historical task scheduling data is obtained through calculation, so that the node position of each attribute feature in a decision tree is accurately determined according to the information gain and the attribute weight, the accuracy of construction of a preset decision tree model can be ensured, and the accuracy of task grade determination in a subsequent task to be distributed is improved.

It should be emphasized that, to further ensure the privacy and security of the above-mentioned decision tree model information, the above-mentioned decision tree model information may also be stored in a node of a blockchain.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 4, as an implementation of the method shown in fig. 2, the application provides an embodiment of a task scheduling device based on a decision tree, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device is specifically applicable to various electronic devices.

As shown in fig. 4, the task scheduling device 400 based on the decision tree according to the present embodiment includes: an acquisition module 401, an input module 402, a selection module 403 and an allocation module 404. Wherein:

The acquiring module 401 is configured to acquire capability data of an optional agent, and determine attribute features corresponding to each task to be scheduled corresponding to the optional agent, where the attribute features include a client value, a client time and a task difficulty corresponding to the task to be scheduled;

the input module 402 is configured to input the capability data and the attribute and the feature of each task to be scheduled into a preset decision tree model, so as to obtain a priority corresponding to each task to be scheduled output by the preset decision tree model;

a selecting module 403, configured to select, from the priorities of the tasks to be scheduled, a task to be scheduled with a highest priority as a target task to be scheduled;

an allocation module 404, configured to allocate the target scheduling task to the optional agent.

According to the technical scheme, capability data of a selectable agent are obtained through an obtaining module 401, attribute features corresponding to each task to be scheduled corresponding to the selectable agent are determined, the attribute features comprise client values, client time and task difficulty corresponding to the task to be scheduled, the capability data and the attribute features of each task to be scheduled are input into a preset decision tree model through an input module 402, priorities corresponding to the tasks to be scheduled output by the preset decision tree model are obtained, finally, the task to be scheduled with the highest priority is selected from the priorities of the tasks to be scheduled through a selecting module 403 to serve as a target scheduling task, and the target scheduling task is distributed to the selectable agent through a distributing module 404. Therefore, more and more efficient working modes and plans can be provided for the seat than before; and the scheduling task is obtained by calculation based on the decision tree model, so that the highest input-output ratio of each task processed by the agent can be ensured, high-value tasks can be completed as much as possible in a limited time, and the task conversion rate of the agent is improved.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 5, fig. 5 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only computer device 6 having components 61-63 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 61 includes at least one type of readable storage media including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal memory unit of the computer device 6 and an external memory device. In this embodiment, the memory 61 is typically used for storing an operating system and various application software installed on the computer device 6, such as computer readable instructions of a decision tree-based task scheduling method. Further, the memory 61 may be used to temporarily store various types of data that have been output or are to be output.

The processor 62 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute computer readable instructions stored in the memory 61 or process data, such as computer readable instructions for executing the decision tree-based task scheduling method.

The network interface 63 may comprise a wireless network interface or a wired network interface, which network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of a decision tree-based task scheduling method as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. A task scheduling method based on a decision tree, comprising the steps of:

and distributing the target scheduling task to the optional agent.

2. The task scheduling method based on decision tree according to claim 1, wherein the step of inputting the capability data and the attribute features of each task to be scheduled into a preset decision tree model to obtain the priority corresponding to each task to be scheduled output by the preset decision tree model specifically includes:

3. The decision tree based task scheduling method according to claim 2, further comprising, after the step of calculating a first task value corresponding to a customer value in each of the tasks to be scheduled based on the preset decision tree model:

4. A decision tree based task scheduling method according to claim 3, further comprising, after the step of calculating a second task value corresponding to a task difficulty in each of the tasks to be scheduled based on the preset decision tree model:

5. The decision tree based task scheduling method according to claim 4, further comprising, after the step of calculating a third task value corresponding to the capability data of the optional agent based on the preset decision tree model:

6. The decision tree based task scheduling method according to claim 5, further comprising, after the step of calculating a fourth task value corresponding to a client time in each of the tasks to be scheduled based on the preset decision tree model:

7. Decision tree based task scheduling method according to any one of claims 1 to 6, wherein the preset decision tree model is constructed by:

8. A decision tree-based task scheduling device, comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the decision tree based task scheduling method of any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the decision tree based task scheduling method of any one of claims 1 to 7.