Task scheduling method and related device

Abstract

The embodiment of the invention provides a task scheduling method and a related device, and the method comprises the steps: obtaining a plurality of interaction tasks in a current scheduling queue; dividing the plurality of interaction tasks into a plurality of target task sets according to preset business elements; obtaining a scheduling configuration table; determining a target resource constraint condition; binding a plurality of target value quantized values under a plurality of interaction conditions for each target task set; and inputting the target resource constraint condition and the plurality of target task sets into a pre-trained task scheduling model, and calculating to obtain a target interaction time and a target interaction mode of each target task set. According to the method, the server can divide the multiple tasks in the scheduling queue into the task sets according to the business elements, the target interaction time and the target interaction mode of each task set are calculated through the task scheduling model when the sum of the target value quantized values is maximum, the intelligence of scheduling calculation of the server is improved, and the interaction operation efficiency is improved.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a task scheduling method and related devices. Background Art

[0002] With the development of the Internet, outbound telephone call interaction tasks have become an important way to connect businesses and serve customers in various fields. The scheduling method adopted in the current interactive job scheduling system is to send each single interactive task to the task scheduling model for calculation to obtain the interaction time and interaction method required for each interactive task. However, the interactive job scheduling system generates millions of interactive tasks every day, and this scheduling method is very inefficient. Summary of the invention

[0003] The embodiments of the present application provide a task scheduling method and related devices, wherein the server can divide multiple tasks in a queue into task sets according to business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is maximized through a task scheduling model, which is beneficial to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations.

[0004] In a first aspect, an embodiment of the present application provides a task scheduling method, which is applied to a server in an interactive job scheduling system, comprising:

[0005] Get multiple interactive tasks in the current scheduling queue;

[0006] Dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements;

[0007] Acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information;

[0008] Determining target resource constraints according to the resource information in the scheduling configuration table;

[0009] Bind multiple target value quantization values ​​under multiple interaction conditions to each target task set. The interaction conditions include interaction time and interaction mode. Each interaction condition corresponds to a target value quantization value.

[0010] Inputting the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model, and calculating the target interaction time and target interaction mode of each target task set;

[0011] The target interaction time and the target interaction mode are updated into the task information of each interactive task in the target task set.

[0012] In a second aspect, an embodiment of the present application provides a task scheduling device, which is applied to a server in an interactive job scheduling system, and the device includes an acquisition unit, a division unit, a determination unit, a binding unit, a calculation unit, and an adjustment unit; wherein:

[0013] The acquisition unit is used to acquire multiple interactive tasks in the current scheduling queue;

[0014] The division unit is used to divide the multiple interactive tasks into multiple target task sets according to preset business elements;

[0015] The acquisition unit is further used to acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information;

[0016] The determining unit is used to determine the target resource constraint condition according to the resource information in the scheduling configuration table;

[0017] The binding unit is used to bind multiple target value quantization values ​​under multiple interaction conditions to each target task set, where the interaction conditions include interaction time and interaction mode, and each interaction condition corresponds to a target value quantization value;

[0018] The calculation unit is used to input the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model to calculate the target interaction time and target interaction mode of each target task set;

[0019] The adjustment unit is used to update the target interaction time and the target interaction mode into the task information of each interaction task in the target task set.

[0020] A third aspect of the present application provides an electronic device, comprising: a processor and a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for some or all of the steps described in the first aspect.

[0021] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program enables a computer to execute instructions of some or all of the steps described in the first aspect of the embodiment of the present application.

[0022] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0023] It can be seen that in the embodiment of the present application, the server in the interactive job scheduling system first obtains multiple interactive tasks in the current scheduling queue, then divides the multiple interactive tasks into multiple target task sets according to the preset business elements, and then obtains the scheduling configuration table, and further, according to the resource information in the scheduling configuration table, determines the target resource constraint conditions, and further, binds multiple target value quantization values ​​under multiple interaction conditions to each target task set, and then inputs the target resource constraint conditions and multiple target task sets into the pre-trained task scheduling model, calculates the target interaction time and target interaction mode of each target task set, and finally, updates the target interaction time and target interaction mode to the task information of each interactive task in the target task set. The server can divide the multiple tasks in the scheduling queue into task sets according to the business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is maximized through the task scheduling model, which is conducive to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1A It is a schematic diagram of the architecture of an interactive job scheduling system provided in an embodiment of the present application;

[0026] Figure 1B It is a schematic diagram of an interface for resource information configuration provided in an embodiment of the present application;

[0027] Figure 2 It is a flowchart of a task scheduling method provided in an embodiment of the present application;

[0028] Figure 3 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0029] Figure 4 It is a block diagram of the functional units of a task scheduling device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0032] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0033] In the embodiments of the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist at the same time; B exists alone. Among them, A and B can be singular or plural.

[0034] In the embodiment of the present application, the symbol " / " can indicate that the objects associated with each other are in an "or" relationship. In addition, the symbol " / " can also indicate a division sign, that is, performing a division operation. For example, A / B can indicate A divided by B.

[0035] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0036] In the embodiments of the present application, "equal to" can be used in conjunction with greater than, and is applicable to the technical solution adopted when greater than, and can also be used in conjunction with less than, and is applicable to the technical solution adopted when less than. When equal to is used in conjunction with greater than, it is not used in conjunction with less than; when equal to is used in conjunction with less than, it is not used in conjunction with greater than.

[0037] In order to better understand the solutions of the embodiments of the present application, the electronic devices, related concepts and backgrounds that may be involved in the embodiments of the present application are first introduced below.

[0038] The electronic device of the application embodiment is a device with wireless communication function, which can be called terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal equipment, vehicle-mounted terminal equipment, industrial control terminal equipment, UE unit, UE station, mobile station, remote station, remote terminal equipment, mobile device, UE terminal equipment, wireless communication equipment, UE agent or UE device, etc. The terminal device can be fixed or mobile. It should be noted that the terminal device can support at least one wireless communication technology, such as LTE, new radio (NR), wideband code division multiple access (WCDMA), etc. For example, the terminal device may be a mobile phone, a tablet computer (pad), a desktop computer, a laptop computer, an all-in-one computer, a vehicle-mounted terminal, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, an electronic device or other processing device connected to a wireless modem, a wearable device, a terminal device in a future mobile communication network, or a terminal device in a future evolved public mobile land network (PLMN), etc. The electronic device may be a server in an interactive job scheduling system.

[0039] See also Figure 1A , Figure 1A Schematic diagram of the architecture of an interactive job scheduling system provided by an embodiment of the present application. Figure 1AAs shown, the interactive operation scheduling system 1 includes a server 10, an agent terminal 20 and a service terminal 30, and the server 10 is communicatively connected with the agent terminal 20 and the service terminal 30 respectively.

[0040] The agent terminal 20 is used to receive user calls transferred by the server 10, initiate outbound calls by performing interactive tasks, and receive outbound calls, so that the agent can communicate with the user through the outbound call.

[0041] The service end 30 is used to configure the resource information that can be dispatched by the queue every day, resource information human resource information and line resource information, as well as to configure preset service elements.

[0042] The server 10 may distribute the interactive tasks to a plurality of agent terminals 20 , and the agent terminals 20 execute the interactive tasks and dial the telephone number of the user recorded in the task information of the interactive tasks; the server 10 may also transfer the user call connected by the AI ​​to the agent terminal 20 .

[0043] See also Figure 1B , Figure 1B This is a schematic diagram of an interface for resource information configuration provided in an embodiment of the present application. The interface includes queue name, queue description, and resource configuration. Resource configuration includes configuring human resources and line resources. Configuring human resources includes configuring the number of people, standard working hours, overtime number of people, and overtime hours. Configuring line resources includes configuring machine concurrency, machine standard working hours, overtime machine concurrency, and machine overtime hours.

[0044] In a possible example, the server 10 in the interactive job scheduling system 1 first obtains multiple interactive tasks in the current scheduling queue, and then the server 10 divides the multiple interactive tasks into multiple target task sets according to the preset business elements. The server 10 then obtains the scheduling configuration table. Further, the server 10 determines the target resource constraint conditions according to the resource information in the scheduling configuration table. Further, the server 10 binds multiple target value quantization values ​​under multiple interaction conditions to each target task set. The server 10 then inputs the target resource constraint conditions and the multiple target task sets into a pre-trained task scheduling model, calculates the target interaction time and target interaction mode of each target task set, and finally, the server 10 updates the target interaction time and target interaction mode to the task information of each interactive task in the target task set. The server 10 can divide the multiple tasks in the scheduling queue into task sets according to the business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is the largest through the task scheduling model, which is conducive to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations.

[0045] See also Figure 2 , Figure 21 is a flow chart of a task scheduling method provided in an embodiment of the present application, which is applied to a server in an interactive job scheduling system, and the method includes:

[0046] Step S201, obtaining multiple interactive tasks in the current scheduling queue.

[0047] Among them, the interactive job scheduling system manages multiple cases to be interacted with configured by the business end in a queue manner. The cases to be interacted with can generate corresponding interactive tasks, thereby realizing queue management of multiple interactive tasks; the contact strategies for the cases to be interacted with in the same queue are the same, for example: outbound call contact, social media push contact, mobile phone message contact, etc., which are not limited here.

[0048] Among them, the interactive task can be an outbound call task. The outbound call task can be a direct call from the agent to the user, or an AI intelligent customer service to call the user and play a preset voice after the call is connected, or an AI intelligent customer service to call the user and transfer the call to the agent on the agent side after the call is connected; the interactive task can also be a social media information push task, a mobile phone information sending task, etc., which is not limited here.

[0049] Step S202: dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements.

[0050] The preset business elements include at least one of the following: customer groups, market areas, sales channels and business stages. Customer groups include new customers and old customers. Market areas include market research, channel development, brand promotion, etc. Sales channels include online sales and offline stores. Business stages include potential customer development, sales follow-up, contract signing and after-sales service. For example, multiple interactive tasks are divided according to business stages to obtain potential customer development task sets, sales follow-up task sets, contract signing task sets and after-sales service task sets.

[0051] Step S203, obtaining a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information.

[0052] The server is connected to the business end through communication, and the scheduling configuration table is a table for the business end to configure the resources that can be scheduled on the day. Human resource information includes the number of agents, standard working hours, number of overtime workers, and overtime working hours. Line resources include the number of concurrent AI machine customer service, machine working hours, number of concurrent overtime workers, and machine overtime working hours.

[0053] Step S204: determining target resource constraint conditions according to the resource information in the scheduling configuration table.

[0054] Among them, the working time and duration of the agents configured on the business side and the working time and duration of the AI ​​intelligent customer service are all set in advance, so the corresponding target resource constraints can be determined based on the resource information.

[0055] Step S205 , binding multiple target value quantization values ​​under multiple interaction conditions to each target task set, where the interaction conditions include interaction time and interaction mode, and each interaction condition corresponds to a target value quantization value.

[0056] Among them, the target task set has different target value quantification values ​​under different interaction times and interaction modes. The target value quantification value can be a weighted loan amount, a deposit amount, a loan amount, etc., which is not limited here. For example, when the interaction time is 9:00-12:00 and the interaction mode is automatic voice, the value of the weighted loan amount is 1000, when the interaction time is 12:00-14:00 and the interaction mode is manual seat, the value of the weighted loan amount is 1200, and when the interaction time is 14:00-18:00 and the interaction mode is automatic voice, the value of the weighted loan amount is 1100.

[0057] Among them, the interaction time range and interaction mode of each task in the same task set are the same. Therefore, by connecting the task scheduling model in the form of task sets, the computational efficiency of the task scheduling model can be improved.

[0058] Step S206: input the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model to calculate the target interaction time and target interaction mode of each target task set.

[0059] Among them, the task scheduling model is used to calculate the target interaction time and target interaction mode corresponding to each target task set when the sum of the target value quantization values ​​of each target task set is maximized under resource constraints. For example, the multiple target task sets include the first target task set, the second target task set, and the third target task set. The target interaction time of the first target task set is calculated to be 14:00-18:00, and the interaction mode is automatic voice. The target interaction time of the second target task is 9:00-12:00, and the interaction mode is manual seat. The target interaction time of the third target task is 12:00-14:00, and the interaction mode is automatic voice. The task scheduling model is trained in advance with the training set data.

[0060] Step S207: updating the target interaction time and the target interaction mode into the task information of each interactive task in the target task set.

[0061] It can be seen that in the embodiment of the present application, the server in the interactive job scheduling system first obtains multiple interactive tasks in the current scheduling queue, then divides the multiple interactive tasks into multiple target task sets according to the preset business elements, and then obtains the scheduling configuration table, and further, according to the resource information in the scheduling configuration table, determines the target resource constraint conditions, and further, binds multiple target value quantization values ​​under multiple interaction conditions to each target task set, and then inputs the target resource constraint conditions and multiple target task sets into the pre-trained task scheduling model, calculates the target interaction time and target interaction mode of each target task set, and finally, updates the target interaction time and target interaction mode to the task information of each interactive task in the target task set. The server can divide the multiple tasks in the scheduling queue into task sets according to the business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is maximized through the task scheduling model, which is conducive to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations.

[0062] In one possible example, in terms of dividing the multiple interactive tasks into multiple target task sets according to preset business elements, the above method may include the following steps: dividing the multiple interactive tasks into multiple first task sets according to the preset business elements, each first task set including at least one interactive task; performing the following operations on each first task set to obtain multiple second task sets: determining the target number of interactive tasks in the first task set currently being processed; when it is determined that the target number is greater than a first preset threshold, determining multiple sub-business elements of the target business element corresponding to the first task set currently being processed; dividing the multiple interactive tasks in the first task set currently being processed according to the multiple sub-business elements to obtain multiple second task sets; when it is determined that the target number is less than a second preset threshold, determining whether to discard the first task set currently being processed; when it is determined that the target number is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, using the first task set currently being processed as the second task set; using the multiple second task sets as the target task set.

[0063] Among them, after multiple interactive tasks are divided into multiple first task sets according to preset business elements, the number of interactive tasks included in the first task set may be too many or too few. If the number of interactive tasks is too small, the purpose of improving work efficiency cannot be achieved. If the number of interactive tasks is too large, the interactive time will be too concentrated and the interactive mode will be too single. Therefore, when the target number of interactive tasks in the target task set is greater than the first preset threshold, it means that the number of interactive tasks in the first task set is too large, and the interactive tasks in the first task set can be further refined. The method is to determine multiple sub-business elements of the target business element corresponding to the first task set currently being processed, and divide the multiple interactive tasks in the first task set according to the multiple sub-business elements to obtain multiple second task sets. For example: when the target business element is an old user, the multiple sub-business elements of the old user can be high-value users, medium-value users and low-value users. When the target number is less than the second preset threshold, it means that the number of interactive tasks in the first task set is too small, then consider discarding the first task set, or merge multiple first task sets whose target numbers are less than the second preset threshold.

[0064] Among them, the first preset threshold is greater than the second preset threshold. The first preset threshold and the second preset threshold can be set manually or by system default, and are not limited here.

[0065] It can be seen that in this example, the server can divide multiple interactive tasks into target tasks according to preset business elements, and connect them to the task scheduling model through the task set. Compared with the single interactive task connection task scheduling model, it is beneficial to improve the efficiency and intelligence of the server scheduling calculation.

[0066] In one possible example, with respect to determining whether to discard the first task set currently being processed, the method may include the following steps: determining a task label for each interactive task in the first task set currently being processed, the task label including a task level, and the task level being used to characterize the importance of the interactive task; if the task level of any interactive task is greater than or equal to a preset level, using the first task set currently being processed as the second task set; if the task level of each interactive task is less than the preset level, discarding the first task set currently being processed.

[0067] Among them, when judging whether to discard the task set, it is necessary to consider whether there are interactive tasks with high task levels in the task set. The higher the task level, the more important the interactive task is and the more necessary it is to execute it. If so, the first task set currently being processed will not be discarded. If not, the first task set currently being processed will be discarded.

[0068] Among them, the preset level can be task setting or system default, and is not limited here. For example: the task levels from low to high are A, B, C, D, E and G, and the preset level can be E.

[0069] It can be seen that in this example, the server can determine whether to discard the first task set currently being processed according to the task level, which is conducive to improving the intelligence of the server task set division.

[0070] In one possible example, in terms of binding multiple target value quantization values ​​under multiple interaction conditions for each target task set, the above method may include the following steps: obtaining a task set combination template, the task set combination template including a business tag and corresponding multiple records, each record including an interaction condition and a corresponding target value quantization value; determining a target business tag matching each target task set; and binding the target value quantization value under the interaction condition corresponding to the target business tag to each target task set.

[0071] Among them, business tags include at least one of the following: customer groups, market areas, sales channels and business stages. Customer groups include new customers and old customers. Market areas include market research, channel expansion, brand promotion, etc. Sales channels include online sales and offline stores. Business stages include potential customer development, sales follow-up, contract signing and after-sales service.

[0072] Among them, the task set combination template can be a template pre-prepared based on historical data. The task set combination template includes a business label and corresponding multiple records, each record includes an interaction condition and a corresponding target value quantification value. For example: the business label is an old customer, and there are three records. Record 1: the interaction time is 9:00-12:00, the interaction method is automatic voice, and the value of the weighted loan amount (target value quantification value) is 1000; Record 2: the interaction time is 12:00-14:00, the interaction method is manual seat, and the value of the weighted loan amount is 1200; Record 3: the interaction time is 14:00-18:00, and the interaction method is automatic voice, and the value of the weighted loan amount is 1100.

[0073] It can be seen that in this example, by binding multiple target value quantization values ​​under multiple interaction conditions to each target task set, the task scheduling model can calculate the target interaction conditions of each target task set when the sum of the target value quantization values ​​of multiple target task sets is maximized, that is, the target interaction time and target interaction mode, which is conducive to improving the efficiency and intelligence of server scheduling calculations.

[0074] In a possible example, after obtaining the task set combination template, the above method may include the following steps: if it is determined that the currently processed target task set does not have a business tag that matches the task set, discarding the currently processed target task set; and marking the currently processed task set.

[0075] Among them, if it is determined that the target task set currently being processed does not have a business tag that matches the task set, it means that there is no corresponding historical statistical data in the task set combination template. At this time, the target task set currently being processed can be discarded, and the task scheduling model calculation is not entered. The target task set currently being processed is marked with a label of "no historical statistical data". The business end will subsequently configure the interaction time and interaction method.

[0076] It can be seen that in this example, the server can discard the target task set that does not match the current processing, avoiding exceptions when the target value quantization value cannot be bound to the target task set for model calculation, which is beneficial to improving the stability of the server's scheduling calculation.

[0077] In one possible example, in terms of determining the target resource constraint conditions based on the resource information in the scheduling configuration table, the above method may include the following steps: extracting the human resource information and the line resource information in the scheduling configuration table; determining the human resource constraint conditions based on the human resource information; determining the line resource constraint conditions based on the line resource information; and using the human resource constraint conditions and the line resource constraint conditions as the target resource constraint conditions.

[0078] Among them, human resources information includes morning resources and noon resources. Morning resources include the standard full-day hours and overtime hours of human resources. Noon resources include the evening overtime hours of human resources and 5 / 9 of the corresponding human input time during execution. The line resource information page includes morning resources and noon resources. Morning resources include the standard full-day hours and overtime hours of AI smart customer service. Noon resources include the evening overtime hours of AI smart customer service and 5 / 9 of the corresponding human input time during execution.

[0079] Among them, the human resource constraint conditions include the morning resource constraint conditions and the noon resource constraint conditions. The morning resource constraint conditions are that the actual utilization of human resources in the morning is less than or equal to the total duration of morning resources, and the total duration of morning resources is the sum of the standard duration of human resources throughout the day and overtime hours, in seconds. The noon resource constraint conditions are that the actual utilization of human resources at noon is less than or equal to the total duration of noon resources, and the total duration of noon resources is the sum of the overtime hours of human resources at night and 5 / 9 of the corresponding human input time during execution, in seconds. Similarly, the line resource constraint conditions include the morning resource constraint conditions and the noon resource constraint conditions. The morning resource constraint conditions are that the actual utilization of line resources in the morning is less than or equal to the total duration of morning resources, and the total duration of morning resources is the sum of the standard duration of AI intelligent customer service throughout the day and overtime hours, in seconds. The noon resource constraint conditions are that the actual utilization of line resources at noon is less than or equal to the total duration of noon resources, and the total duration of noon resources is the sum of the overtime hours of AI intelligent customer service at night and 5 / 9 of the corresponding human input time during execution, in seconds.

[0080] It can be seen that in this example, the server determines the human resource constraint conditions and the line resource constraint conditions respectively based on the resource information, which is conducive to improving the intelligence of the server in determining the resource constraint conditions.

[0081] In a possible example, before obtaining multiple interactive tasks in the current scheduling queue, the above method may include the following steps: obtaining multiple cases to be interacted with; dividing the multiple cases to be interacted with into multiple case sets according to customer characteristics, business characteristics and preset diversion rules; generating interactive tasks for the cases to be interacted with in each case set, and using the set of interactive tasks as a scheduling queue.

[0082] Among them, customer characteristics include but are not limited to age, gender, region, occupation, income level, purchase history, consumption preferences, loyalty level, social media activity, etc., business characteristics include but are not limited to product type, sales channel, promotion activity type, marketing time period, sales target, etc., and preset diversion rules are pre-set, for example: giving priority to new customers in calls to introduce product purchase discounts.

[0083] It can be seen that in this example, the server manages interactive cases in a queue manner, which is conducive to improving the stability of server scheduling.

[0084] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, which is applied to a server in an interactive job scheduling system; Figure 3 As shown, the electronic device includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs are configured to execute the following steps by the processor:

[0085] Get multiple interactive tasks in the current scheduling queue;

[0086] Dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements;

[0087] Acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information;

[0088] Determining target resource constraints according to the resource information in the scheduling configuration table;

[0089] Bind multiple target value quantization values ​​under multiple interaction conditions to each target task set. The interaction conditions include interaction time and interaction mode. Each interaction condition corresponds to a target value quantization value.

[0090] Inputting the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model, and calculating the target interaction time and target interaction mode of each target task set;

[0091] The target interaction time and the target interaction mode are updated into the task information of each interactive task in the target task set.

[0092] It can be seen that in the embodiment of the present application, the electronic device first obtains multiple interactive tasks in the current scheduling queue, then divides the multiple interactive tasks into multiple target task sets according to preset business elements, and then obtains the scheduling configuration table, and further, according to the resource information in the scheduling configuration table, determines the target resource constraint conditions, and further, binds multiple target value quantization values ​​under multiple interaction conditions to each target task set, and then inputs the target resource constraint conditions and multiple target task sets into the pre-trained task scheduling model, calculates the target interaction time and target interaction mode of each target task set, and finally, updates the target interaction time and target interaction mode to the task information of each interactive task in the target task set. The server can divide the multiple tasks in the scheduling queue into task sets according to business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is maximized through the task scheduling model, which is conducive to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations.

[0093] In a possible example, in the aspect of dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements, the program includes instructions for executing the following steps:

[0094] Dividing the plurality of interactive tasks into a plurality of first task sets according to the preset business elements, each first task set including at least one interactive task;

[0095] Perform the following operations on each first task set to obtain multiple second task sets:

[0096] determining a target number of interactive tasks in a first task set currently being processed;

[0097] When it is determined that the target quantity is greater than a first preset threshold, determining a plurality of sub-business elements of the target business element corresponding to the first task set currently being processed;

[0098] Dividing the multiple interactive tasks in the currently processed first task set according to the multiple sub-business elements to obtain multiple second task sets;

[0099] When it is determined that the target quantity is less than a second preset threshold, determining whether to discard the first task set currently being processed;

[0100] When it is determined that the target quantity is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, the currently processed first task set is used as the second task set;

[0101] The plurality of second task sets are used as the target task sets.

[0102] In a possible example, in terms of determining whether to discard the first task set currently being processed, the program includes instructions for executing the following steps:

[0103] Determine a task label for each interactive task in the first task set currently being processed, wherein the task label includes a task level, and the task level is used to characterize the importance of the interactive task;

[0104] If the task level of any interactive task is greater than or equal to a preset level, the currently processed first task set is used as the second task set;

[0105] If the task level of each interactive task is less than the preset level, the first task set currently being processed is discarded.

[0106] In a possible example, in terms of binding multiple target value quantification values ​​under multiple interaction conditions to each target task set, the program includes instructions for executing the following steps:

[0107] Acquire a task set combination template, wherein the task set combination template includes a business tag and a plurality of corresponding records, each record including an interaction condition and a corresponding target value quantization value;

[0108] Determine the target business label that matches each target task set;

[0109] The target value quantization value under the interaction condition corresponding to the target service tag is bound to each target task set.

[0110] In a possible example, after obtaining the task set combination template, the program further includes instructions for executing the following steps:

[0111] If it is determined that the target task set currently being processed does not have a service tag matching the task set, the target task set currently being processed is discarded;

[0112] Marks the currently processed task set.

[0113] In a possible example, in determining the target resource constraint condition according to the resource information in the scheduling configuration table, the program further includes instructions for executing the following steps:

[0114] Extracting the human resource information and the line resource information in the scheduling configuration table;

[0115] Determining human resource constraints based on the human resource information;

[0116] Determining line resource constraint conditions according to the line resource information;

[0117] The human resource constraint condition and the line resource constraint condition are used as the target resource constraint condition.

[0118] In a possible example, before acquiring multiple interactive tasks in the current scheduling queue, the program further includes instructions for executing the following steps:

[0119] Get multiple cases to be interacted with;

[0120] Dividing the multiple cases to be interacted into multiple case sets according to customer characteristics, business characteristics and preset diversion rules;

[0121] Generate interactive tasks for the cases to be interacted in each case set, and use the set of interactive tasks as a scheduling queue.

[0122] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0123] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0124] In the case of dividing each functional module into corresponding functional modules, Figure 4 A functional unit block diagram of a task scheduling device is given, such as Figure 4As shown, the server is applied to the interactive job scheduling system; the device includes an acquisition unit 401, a division unit 402, a determination unit 403, a binding unit 404, a calculation unit 405 and an adjustment unit 406; wherein,

[0125] The acquisition unit 401 is used to acquire multiple interactive tasks in the current scheduling queue;

[0126] The division unit 402 is used to divide the multiple interactive tasks into multiple target task sets according to preset business elements;

[0127] The acquisition unit 401 is further used to acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information;

[0128] The determining unit 403 is used to determine the target resource constraint condition according to the resource information in the scheduling configuration table;

[0129] The binding unit 404 is used to bind multiple target value quantization values ​​under multiple interaction conditions to each target task set, where the interaction conditions include interaction time and interaction mode, and each interaction condition corresponds to a target value quantization value;

[0130] The calculation unit 405 is used to input the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model to calculate the target interaction time and target interaction mode of each target task set;

[0131] The adjusting unit 406 is configured to update the target interaction time and the target interaction mode into the task information of each interaction task in the target task set.

[0132] It can be seen that the task scheduling device described in the embodiment of the present application first obtains multiple interactive tasks in the current scheduling queue, then divides the multiple interactive tasks into multiple target task sets according to preset business elements, and then obtains the scheduling configuration table. Further, according to the resource information in the scheduling configuration table, the target resource constraint conditions are determined, and further, multiple target value quantization values ​​under multiple interactive conditions are bound to each target task set, and then the target resource constraint conditions and multiple target task sets are input into the pre-trained task scheduling model to calculate the target interaction time and target interaction mode of each target task set. Finally, the target interaction time and target interaction mode are updated to the task information of each interactive task in the target task set. The server can divide the multiple tasks in the scheduling queue into task sets according to business elements, and calculate the target interaction time and target interaction mode of each task set when the sum of the target value quantization values ​​is maximized through the task scheduling model, which is conducive to improving the intelligence of the server scheduling calculation and the efficiency of interactive operations.

[0133] In a possible example, in the aspect of dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements, the dividing unit 402 is specifically configured to:

[0134] Dividing the plurality of interactive tasks into a plurality of first task sets according to the preset business elements, each first task set including at least one interactive task;

[0135] Perform the following operations on each first task set to obtain multiple second task sets:

[0136] determining a target number of interactive tasks in a first task set currently being processed;

[0137] When it is determined that the target quantity is greater than a first preset threshold, determining a plurality of sub-business elements of the target business element corresponding to the first task set currently being processed;

[0138] Dividing the multiple interactive tasks in the currently processed first task set according to the multiple sub-business elements to obtain multiple second task sets;

[0139] When it is determined that the target quantity is less than a second preset threshold, determining whether to discard the first task set currently being processed;

[0140] When it is determined that the target quantity is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, the currently processed first task set is used as the second task set;

[0141] The plurality of second task sets are used as the target task sets.

[0142] In a possible example, in the aspect of determining whether to discard the first task set currently being processed, the determining unit 407 is specifically configured to:

[0143] Determine a task label for each interactive task in the first task set currently being processed, wherein the task label includes a task level, and the task level is used to characterize the importance of the interactive task;

[0144] If the task level of any interactive task is greater than or equal to a preset level, the currently processed first task set is used as the second task set;

[0145] If the task level of each interactive task is less than the preset level, the first task set currently being processed is discarded.

[0146] In a possible example, in terms of binding multiple target value quantization values ​​under multiple interaction conditions for each target task set, the binding unit 404 is specifically used to:

[0147] Acquire a task set combination template, wherein the task set combination template includes a business tag and a plurality of corresponding records, each record including an interaction condition and a corresponding target value quantization value;

[0148] Determine the target business label that matches each target task set;

[0149] The target value quantization value under the interaction condition corresponding to the target service tag is bound to each target task set.

[0150] In a possible example, after obtaining the task set combination template, the judging unit 407 is specifically configured to:

[0151] If it is determined that the target task set currently being processed does not have a service tag matching the task set, the target task set currently being processed is discarded;

[0152] Marks the currently processed task set.

[0153] In a possible example, in determining the target resource constraint condition according to the resource information in the scheduling configuration table, the determining unit 403 is further specifically configured to:

[0154] Extracting the human resource information and the line resource information in the scheduling configuration table;

[0155] Determining human resource constraints based on the human resource information;

[0156] Determining line resource constraint conditions according to the line resource information;

[0157] The human resource constraint condition and the line resource constraint condition are used as the target resource constraint condition.

[0158] In a possible example, before acquiring multiple interactive tasks in the current scheduling queue, the dividing unit 402 is further specifically configured to:

[0159] Get multiple cases to be interacted with;

[0160] Dividing the multiple cases to be interacted into multiple case sets according to customer characteristics, business characteristics and preset diversion rules;

[0161] Generate interactive tasks for the cases to be interacted in each case set, and use the set of interactive tasks as a scheduling queue.

[0162] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0163] The electronic device provided in this embodiment is used to execute the above-mentioned task scheduling method, and thus can achieve the same effect as the above-mentioned implementation method.

[0164] In the case of an integrated unit, the electronic device may include a processing module, a storage module and a communication module. The processing module may be used to control and manage the actions of the electronic device, for example, it may be used to support the electronic device to execute the steps performed by the above-mentioned functional unit. The storage module may be used to support the electronic device to execute stored program codes and data, etc. The communication module may be used to support the communication between the electronic device and other devices.

[0165] Among them, the processing module can be a processor or a controller. It can implement or execute various exemplary logic boxes, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory. The communication module can specifically be a device that interacts with other electronic devices, such as a radio frequency circuit, a Bluetooth chip, a Wi-Fi chip, etc.

[0166] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0167] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes a control platform.

[0168] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0171] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0173] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0174] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0175] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A task scheduling method, characterized in that: The server used in the interactive job scheduling system includes: Get multiple interactive tasks in the current scheduling queue; Dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements; Acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information; Determining target resource constraints according to the resource information in the scheduling configuration table; Bind multiple target value quantization values ​​under multiple interaction conditions to each target task set. The interaction conditions include interaction time and interaction mode. Each interaction condition corresponds to a target value quantization value. Inputting the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model, and calculating the target interaction time and target interaction mode of each target task set; The target interaction time and the target interaction mode are updated into the task information of each interactive task in the target task set.

2. The method according to claim 1, characterized in that The dividing the plurality of interactive tasks into a plurality of target task sets according to preset business elements includes: Dividing the plurality of interactive tasks into a plurality of first task sets according to the preset business elements, each first task set including at least one interactive task; Perform the following operations on each first task set to obtain multiple second task sets: determining a target number of interactive tasks in a first task set currently being processed; When it is determined that the target quantity is greater than a first preset threshold, determining a plurality of sub-business elements of the target business element corresponding to the first task set currently being processed; Dividing the multiple interactive tasks in the currently processed first task set according to the multiple sub-business elements to obtain multiple second task sets; When it is determined that the target quantity is less than a second preset threshold, determining whether to discard the first task set currently being processed; When it is determined that the target quantity is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, the currently processed first task set is used as the second task set; The plurality of second task sets are used as the target task sets.

3. The method according to claim 2, characterized in that The determining whether to discard the first task set currently being processed includes: Determine a task label for each interactive task in the first task set currently being processed, wherein the task label includes a task level, and the task level is used to characterize the importance of the interactive task; If the task level of any interactive task is greater than or equal to a preset level, the currently processed first task set is used as the second task set; If the task level of each interactive task is less than the preset level, the first task set currently being processed is discarded.

4. The method according to claim 1, characterized in that: The step of binding multiple target value quantification values ​​under multiple interaction conditions to each target task set includes: Acquire a task set combination template, wherein the task set combination template includes a business tag and a plurality of corresponding records, each record including an interaction condition and a corresponding target value quantization value; Determine the target business label that matches each target task set; The target value quantization value under the interaction condition corresponding to the target service tag is bound to each target task set.

5. The method according to claim 4, characterized in that After obtaining the task set combination template, the method further includes: If it is determined that the target task set currently being processed does not have a service tag matching the task set, the target task set currently being processed is discarded; Marks the currently processed task set.

6. The method according to claim 1, characterized in that Determining the target resource constraint condition according to the resource information in the scheduling configuration table includes: Extracting the human resource information and the line resource information in the scheduling configuration table; Determining human resource constraints based on the human resource information; Determining line resource constraint conditions according to the line resource information; The human resource constraint condition and the line resource constraint condition are used as the target resource constraint condition.

7. The method according to claim 1, characterized in that Before acquiring the multiple interactive tasks in the current scheduling queue, the method further includes: Get multiple cases to be interacted with; Dividing the multiple cases to be interacted into multiple case sets according to customer characteristics, business characteristics and preset diversion rules; Generate interactive tasks for the cases to be interacted in each case set, and use the set of interactive tasks as a scheduling queue.

8. A task scheduling device, characterized in that: A server applied to an interactive job scheduling system; the device comprises an acquisition unit, a division unit, a determination unit, a binding unit, a calculation unit and an adjustment unit; wherein, The acquisition unit is used to acquire multiple interactive tasks in the current scheduling queue; The division unit is used to divide the multiple interactive tasks into multiple target task sets according to preset business elements; The acquisition unit is further used to acquire a scheduling configuration table, wherein the scheduling configuration table includes resource information, and the resource information includes human resource information and line resource information; The determining unit is used to determine the target resource constraint condition according to the resource information in the scheduling configuration table; The binding unit is used to bind multiple target value quantization values ​​under multiple interaction conditions to each target task set, where the interaction conditions include interaction time and interaction mode, and each interaction condition corresponds to a target value quantization value; The calculation unit is used to input the target resource constraint condition and the multiple target task sets into a pre-trained task scheduling model to calculate the target interaction time and target interaction mode of each target task set; The adjustment unit is used to update the target interaction time and the target interaction mode into the task information of each interactive task in the target task set.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the programs include instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images