WO2024055963A1 - 一种任务分配方法以及装置 - Google Patents

一种任务分配方法以及装置 Download PDF

Info

Publication number
WO2024055963A1
WO2024055963A1 PCT/CN2023/118260 CN2023118260W WO2024055963A1 WO 2024055963 A1 WO2024055963 A1 WO 2024055963A1 CN 2023118260 W CN2023118260 W CN 2023118260W WO 2024055963 A1 WO2024055963 A1 WO 2024055963A1
Authority
WO
WIPO (PCT)
Prior art keywords
work
portrait
task
data
target object
Prior art date
Application number
PCT/CN2023/118260
Other languages
English (en)
French (fr)
Inventor
盛镇醴
郝雪桐
周乐夔
Original Assignee
华为云计算技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202310531234.8A external-priority patent/CN117744961A/zh
Application filed by 华为云计算技术有限公司 filed Critical 华为云计算技术有限公司
Publication of WO2024055963A1 publication Critical patent/WO2024055963A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations

Definitions

  • Embodiments of the present application relate to the field of computers, and in particular, to a task allocation method and device.
  • the enterprise service market on the cloud is currently in its early stages of development.
  • Many cloud vendors have launched task allocation systems to improve task processing efficiency.
  • the sales task distribution system needs to assign sales tasks to sales personnel.
  • the sales task distribution system needs to quickly find more accurate information for each salesperson from a large number of sales tasks. In line with the sales tasks handled by sales personnel, thereby improving sales conversion rates.
  • the current task allocation system often uses rules such as random allocation, sequential allocation, and independent application to allocate tasks.
  • the assigned tasks may not match the staff, resulting in low efficiency in task processing by the staff and failure to achieve task goals.
  • the sales tasks assigned by the sales task allocation system may not be in line with the salesperson's areas of expertise, resulting in the salesperson being unable to achieve the sales target and the sales conversion rate being low.
  • Embodiments of the present application provide a task allocation method and device to improve task processing efficiency in achieving task goals.
  • the first aspect of the embodiment of the present application provides a task allocation method.
  • the method can be executed by a cloud server, or by a component of the cloud server, such as a processor, a chip or a chip system of the cloud server. It can also be executed by a cloud server that can implement Logic modules or software implementation of all or part of the cloud server functions.
  • the task allocation method provided in the first aspect includes: the cloud server receives a work task, and the work task includes one or more task targets. Obtain portraits of multiple objects, where the objects are, for example, staff members who handle tasks. The portraits include one or more of the following: age, areas of expertise and work performance, and job content that they are good at.
  • the cloud server determines the target object based on the work task and the object's portrait, and the target object is used to process the work task.
  • the cloud server pushes work tasks to the target object.
  • the cloud server can determine the target object for executing the task based on the object's portrait, thereby pushing the work task to the target object that matches the work task, thereby improving the processing efficiency of the work task.
  • the cloud server obtains the current work data of the object.
  • the current work data includes one or more of the following: current work status, last task end time, current work duration, current work end time, and current task importance. grade.
  • the cloud server determines the target object based on the task goal, the object's portrait, and current work data.
  • the cloud server can also determine the target object based on the object's current work data, so that the push of work tasks is more reasonably distributed on the premise of achieving the work task goal, further improving the achievement of the task goal.
  • the task goal of the work task may be multiple task goals.
  • Work tasks such as sales tasks and work order processing tasks.
  • the task goals of sales tasks are, for example, sales meeting the sales threshold and profit margins meeting the interest rate threshold.
  • the task goals of work order processing tasks are, for example, customer satisfaction meeting the threshold. The goal is that the total number of work orders meets the odd threshold, and the balance of task distribution meets the balance threshold.
  • the cloud server can obtain the target object based on matching multiple task goals, which improves the task goal achievement effect of the work task.
  • the cloud server obtains the work data of the target object processing work tasks.
  • the cloud server updates the portrait of the target object based on the work data and the portrait prediction model, and the portrait prediction model is used to generate the portrait of the object.
  • the cloud server can generate an updated portrait of the target object based on the work data generated by the target object processing work tasks, thereby improving the accuracy of the target object's portrait.
  • the cloud server obtains the historical work data of the object.
  • the historical work data includes one or more of the following data: order completion rate, complaint rate and sales, average call duration, speaking time ratio, and speaking keywords. , keyword occurrence time, average number of customer objections and number of discussions.
  • Feature extraction is performed based on historical work data to obtain training samples. Carry out model training based on training samples to obtain a portrait prediction model.
  • the cloud server can train a portrait prediction model based on the object's historical work data to obtain a portrait prediction model.
  • the portrait prediction model can generate a portrait based on the work data, improving the accuracy of the subject's portrait.
  • the cloud server determines the subject's training content based on the subject's portrait, and the training content is used to train the subject in work skills. Specifically, the cloud server determines the work content that the subject is not good at processing based on the subject's portrait, and generates training content based on the work content that the subject is not good at processing.
  • the cloud server can train the staff based on the portrait of the object, thereby improving the efficiency of the staff in processing work tasks.
  • the second aspect of the embodiments of the present application provides a method for generating a portrait of an object.
  • the method can be executed by a cloud server, or by a component of the cloud server, such as a processor, a chip or a chip system of the cloud server. It can also be executed by a cloud server.
  • the second aspect of the portrait generation method includes: the cloud server obtains the historical work data of the object.
  • the historical work data includes structured data and unstructured data.
  • the structured data includes one or more of the following data: order completion rate, complaint rate and sales.
  • unstructured data includes one or more of the following data: average call length, proportion of speaking time, speaking keywords, time of occurrence of keywords, average number of customer objections, and number of discussions.
  • the portrait includes labels and vectors.
  • the labels include one or more of the following: age, area of expertise, and historical work performance.
  • the vector is used to indicate the subject's work content and degree of expertise.
  • the cloud server stores the portrait of the object in the portrait database.
  • the cloud server can train a portrait prediction model based on the object's historical work data to obtain a portrait prediction model.
  • the portrait prediction model can generate a portrait based on the work data, improving the accuracy of the subject's portrait.
  • the cloud server performs feature extraction based on unstructured data to obtain training samples.
  • the cloud server performs model training based on the training samples to obtain a portrait prediction model, which is used to predict the portrait of the object.
  • the cloud server When the cloud server generates a portrait of an object based on historical work data, it inputs unstructured data into the portrait prediction model to obtain the vector of the object.
  • the cloud server can obtain the corresponding vector based on the unstructured data, thereby determining the portrait of the object based on the vector of the object, thereby improving the accuracy of the portrait.
  • the cloud server obtains the work data generated by the target object processing the work task. Generate an updated portrait of the target object based on the work data and the portrait prediction model, and modify the portrait of the target object in the portrait database based on the updated portrait.
  • the cloud server can generate an updated portrait of the object based on the work data generated by processing the work task, thereby improving the accuracy of the portrait.
  • the cloud server when the cloud server generates a portrait of an object based on historical work data, the cloud server extracts a label of the object based on structured data.
  • the cloud server can obtain the corresponding label based on the structured data, thereby determining the portrait of the object based on the label of the object, thereby improving the accuracy of the portrait.
  • the third aspect of the embodiment of the present application provides a task allocation device, including a transceiver unit and a processing unit.
  • the transceiver unit is used to receive work tasks, and the work tasks include one or more task targets.
  • the sending and receiving unit is also used to obtain portraits of multiple objects.
  • the portraits include one or more of the following: age, areas of expertise and work performance, and work content that they are good at.
  • the processing unit is used to determine the target object based on the work task and the object's portrait.
  • the target object is used to process the work task.
  • the transceiver unit is also used to push the work task to the target object.
  • the transceiver unit is also used to obtain the current work data of the object.
  • the current work data includes one or more of the following: current work status, last task end time, working hours of the day, work end time of the day, and The current task importance level; the processing unit is specifically used to determine the target object based on the task goal, the object's portrait and the current work data.
  • the transceiver unit is also used to obtain work data of the target object processing work task.
  • the processing unit is also used to update the portrait of the target object based on the work data and the portrait prediction model, and the portrait prediction model is used to generate the portrait of the object.
  • the transceiver unit is also used to obtain the historical work data of the object.
  • the historical work data includes one or more of the following data: order completion rate, complaint rate and sales, average call duration, speaking time ratio, Speaking keywords, keyword occurrence time, Average number of customer objections and discussions.
  • the processing unit is also used to extract features based on historical work data to obtain training samples.
  • the processing unit is also used to perform model training based on training samples to obtain a portrait prediction model.
  • the processing unit is also used to determine the training content of the subject based on the portrait of the subject, and the training content is used to train the subject in work skills.
  • the fourth aspect of the embodiments of the present application provides a device for generating a portrait of an object.
  • the device includes a transceiver unit and a processing unit.
  • the sending and receiving unit is used to obtain the historical work data of the object.
  • the historical work data includes structured data and unstructured data.
  • the structured data includes one or more of the following data: order completion rate, complaint rate and sales volume.
  • the unstructured data includes the following.
  • One or more data average call length, proportion of speaking time, speaking keywords, time of occurrence of keywords, average number of customer objections and number of discussions.
  • the processing unit is used to generate a portrait of the subject based on historical work data.
  • the portrait includes labels and vectors.
  • the labels include one or more of the following: age, area of expertise, and historical work performance.
  • the vector is used to indicate the subject's work content and degree of expertise.
  • the transceiver unit is also used to store the portrait of the object into the portrait database.
  • the processing unit is specifically configured to perform feature extraction based on unstructured data to obtain training samples. Model training is performed based on the training samples to obtain a portrait prediction model, which is used to predict the portrait of the object. Input unstructured data into the portrait prediction model to obtain the vector of the object.
  • the processing unit is specifically configured to obtain work data generated by the target object processing work tasks. Generate an updated portrait of the target object based on the work data and the portrait prediction model, and modify the portrait of the target object in the portrait database based on the updated portrait.
  • the processing unit is specifically configured to extract labels of objects based on structured data.
  • the fifth aspect of the embodiment of the present application provides a computing device cluster.
  • the computing device includes one or more computing devices.
  • the computing device includes a processor.
  • the processor is coupled to a memory.
  • the processor is used to store instructions. When the instructions are executed by the processor , so that the computing device cluster executes the method described in the above-mentioned first aspect or any possible implementation manner of the first aspect, or, so that the computing device cluster executes the above-mentioned second aspect or any possible implementation manner of the second aspect. the method described.
  • the sixth aspect of the embodiment of the present application provides a computer-readable storage medium on which instructions are stored.
  • the computer executes the method described in the first aspect or any possible implementation manner of the first aspect. method, or to cause the computer to execute the method described in the above second aspect or any possible implementation manner of the second aspect.
  • the seventh aspect of the embodiment of the present application provides a computer program product.
  • the computer program product includes instructions. When the instructions are executed, the computer implements the method of the first aspect or any of the possible implementations of the first aspect. method, or to enable the computer to implement the method of the second aspect or the method described in any possible implementation manner of the second aspect.
  • Figure 1 is a schematic system architecture diagram of a task allocation system provided by an embodiment of the present application.
  • Figure 2 is a schematic flowchart of a task allocation method provided by an embodiment of the present application.
  • Figure 3 is a schematic flow chart of another task allocation method provided by an embodiment of the present application.
  • Figure 4 is a schematic flowchart of a portrait generation method provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of another image generation method provided by an embodiment of the present application.
  • Figure 6 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • Figure 7 is a schematic structural diagram of a computing device provided by an embodiment of the present application.
  • Figure 8 is a schematic structural diagram of a computing device cluster provided by an embodiment of the present application.
  • Figure 9 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application.
  • Embodiments of the present application provide a task allocation method and device to improve the processing efficiency of work tasks.
  • a portrait refers to a description of a person or object, which can be a manually set label or a numerical vector automatically generated by an algorithm.
  • a labeled portrait is a portrait of a salesperson: 25 years old, good at the transportation industry, with sales of 50 million in the past year.
  • Numerical vectorized portraits can be calculated by algorithms into multi-dimensional numerical vectors to facilitate processing by computing devices.
  • Structured data refers to data composed of items and their corresponding values, which can generally be displayed through tables.
  • Unstructured data refers to data with free and unfixed content.
  • data such as images, text, and voice are typical unstructured data.
  • FIG. 1 is a schematic diagram of a system architecture applied by a task allocation method according to an embodiment of the present application.
  • the task allocation system 100 includes a data acquisition module 101 , a portrait generation and update module 102 , a task matching module 103 , a task push module 104 and a data collection module 105 .
  • the functions of each module are introduced in detail below.
  • the data acquisition module 101 is used to obtain the initial label of the object.
  • the initial label may be a label set by the system maintenance personnel for the object.
  • the data acquisition module 101 is also used to obtain historical work data of the object from the database. Historical work data such as order completion rate, complaint rate and sales volume, average call duration, speaking time ratio, speaking keywords, keyword occurrence time, average Number of customer objections and number of discussions.
  • the portrait generation and update module 102 is used to generate a portrait of the subject based on the subject's work data. When there is no historical work data of the object in the database, the portrait generation and update module 102 is used to use the initial label set by the user as the portrait of the object. The portrait generation and update module 102 is also used to regularly generate updated portraits of the object based on the work data in the database, thereby updating the portrait database.
  • the task allocation module 103 is configured to determine the target object for processing the work task based on the portrait of the object generated by the portrait generation and update module 102 . Specifically, the task allocation module 103 is also used to obtain the current work data of the object, and match the target object of the work task based on the portrait of the object, the current work data and the task target of the work task.
  • Current work data includes, for example, the current work status, the end time of the previous task, the working hours of the day, the end time of the work of the day, and the importance level of the current task.
  • the task pushing module 104 is used to push the work task to the target object for processing the work task determined by the task allocation module 103 .
  • the task pushing module 104 is also used to push the matching degree between the target object and the work task to the target object.
  • the data collection module 105 is used to collect work data generated by object processing work tasks, and store the work data generated by processing work tasks in a database.
  • task allocation system can be integrated into various business systems through integration, such as customer relationship management (customer relationship management, CRM) systems and office automation (office automation, OA) systems. and enterprise resource planning (ERP) systems.
  • CRM customer relationship management
  • OA office automation
  • ERP enterprise resource planning
  • Figure 2 is a schematic flowchart of a task allocation method provided by an embodiment of the present application.
  • the task allocation method provided by the embodiment of this application includes the following steps:
  • 201 Receive a work task, which includes one or more task goals.
  • the cloud server receives a work task, which includes one or more task targets.
  • Work tasks such as sales tasks and work order processing tasks.
  • the task goals of sales tasks are, for example, sales meeting the sales threshold and profit margins meeting the interest rate threshold.
  • the task goals of work order processing tasks are, for example, customer satisfaction meeting the threshold. The goal is that the total number of work orders meets the odd threshold, and the balance of task distribution meets the balance threshold.
  • FIG 3 is a schematic flowchart of sales task allocation provided by an embodiment of the present application.
  • the work task takes a sales task as an example.
  • the cloud server receives the sales task.
  • the sales task includes one or more sales goals, for example, sales reach 5 million and profit margin reaches 10 %.
  • the cloud server needs to determine the salesperson to perform the sales task based on the sales target of the sales task.
  • the cloud server obtains the object's portrait from the database.
  • the object includes workers who perform work tasks.
  • the object's portrait includes labels and vectors.
  • the label includes one or more of the following: age, area of expertise, and historical work performance.
  • the vector is used to indicate the content and degree of the subject's expertise.
  • the cloud server obtains the portrait of the salesperson from the portrait data, and obtains the current work data of the salesperson.
  • the portrait of the salesperson such as age, Labels such as specializing in sales areas, historical sales, and numerical vectors indicating that sales personnel are good at selling content, current work data such as current work status, last task end time, day's work duration, day's work end time, and current task importance level.
  • the cloud server determines the target object based on the task goal and the object's portrait, and the target object is the person handling the work task.
  • the cloud server when the cloud server determines the target object based on the task goal and the object's portrait, the cloud server obtains the object's current working data.
  • the current working data includes one or more of the following: current working status, previous Task end time, day's work duration, day's work end time and current task importance level.
  • the cloud server determines the target object based on the object's current work data, the object's portrait, and the task goal.
  • the task allocation module of the cloud server inputs the object's portrait and the object's current work data into the task allocation schedule, solves the target object based on the task goal, and obtains the target object that best matches the work task when the workload is appropriate.
  • the cloud server determines the target salesperson to handle the sales task based on the sales target of the sales task, current work data and the portrait of the salesperson. Specifically, the cloud server inputs the salesperson's portrait and sales task into the task allocator, calculates the sales targets that different salespersons may achieve by handling the sales task, and then obtains the recommended ranking of salespersons suitable for handling the sales task based on the calculation results.
  • the cloud server filters the salespeople in the recommended ranking based on the salesperson's current work data and determines the target salesperson. For example, the cloud server sorts the recommended salespersons and prioritizes salespersons whose current working status is idle and who work less hours that day as target salespersons.
  • the cloud server pushes work tasks to the target object. Specifically, the task push module of the cloud server pushes the work task to the target object according to the target object code output by the scheduler.
  • the task pushing module of the cloud server can also push the task target and the push reason of the work task to the target object.
  • the push reason is such as the matching degree between the work task and the target object.
  • the target object processes the work task, generates work data, and stores the work data in the database.
  • the cloud server generates an updated portrait of the target object based on the work data and the portrait prediction model, and updates the portrait in the portrait database based on the updated portrait.
  • the work data includes structured data and unstructured data.
  • the structured data includes one or more of the following data: order completion rate, complaint rate and sales volume.
  • the unstructured data includes one or more of the following. Item data: average call length, proportion of speaking time, speaking keywords, time of occurrence of keywords, average number of customer objections and number of discussions.
  • the cloud server pushes the sales task to the target salesperson, and the target salesperson processes the sales task.
  • the cloud server collects the sales data generated by the target salesperson's execution of the sales task, and stores the sales data in the database as historical work data.
  • the sales data generated by the target salesperson's execution of sales tasks include sales volume, order rate, complaint rate, average sales call length, proportion of salesperson talking time, sales keywords, sales keyword occurrence time, average number of customer objections, and Number of discussions, etc.
  • the cloud server can determine the target object for executing the task based on the object's portrait, thereby pushing the work task to the object that can achieve the task goal, thus improving the processing efficiency of the work task.
  • the task allocation method provided by the embodiment of the present application is introduced above.
  • the object portrait generation method provided by the embodiment of the present application is introduced below.
  • FIG. 4 illustrates a method for generating an object portrait according to an embodiment of the present application.
  • the object portrait generation method provided by the embodiment of the present application includes the following steps:
  • the data acquisition module of the cloud server obtains the historical work data of the object.
  • the historical work data includes structured data and unstructured data.
  • structured data includes one or more of the following data: order completion rate, complaint rate and sales
  • unstructured data includes one or more of the following data: average call length, proportion of speaking time, speaking keywords, keywords Time of occurrence, average number of customer objections, and number of discussions.
  • the data acquisition module of the cloud server obtains the initial label of the object from the system interaction page.
  • the initial label can be a label generated by the system based on the basic information of the object, or it can It is a label manually added to the object by the system maintainer, and there is no specific limit.
  • FIG. 5 illustrates a method for generating an object portrait according to an embodiment of the present application.
  • the cloud server obtains the historical work data of each salesperson among n salespersons, where the historical work data such as order completion rate, complaint rate, Sales volume, average sales call length, proportion of sales staff talking time, sales speaking keywords, sales keyword occurrence time, average number of customer objections and number of discussions.
  • the cloud server obtains the initial tag of the salesperson, or adds an initial tag to the salesperson, and the initial tag is the portrait of the salesperson.
  • the cloud server generates a portrait of the subject based on historical work data.
  • the portrait includes labels and vectors.
  • the labels include one or more of the following: age, area of expertise, and historical work performance.
  • the vector is used to indicate the subject's work content and degree of expertise.
  • the vector includes Multidimensional numeric vector.
  • the cloud server extracts features from unstructured data in historical work data to obtain training samples, and performs model training based on the training samples to obtain a portrait prediction model.
  • the cloud server inputs unstructured data into the portrait prediction model to obtain the object's vector, which is used as the object's portrait. This vector is used to indicate the work content that the object is good at. And the degree of proficiency.
  • the cloud server when the cloud server generates a portrait of an object based on historical work data, the cloud server extracts structured data based on historical work data, obtains a label of the object, and uses the label as the portrait of the object.
  • the cloud server inputs the unstructured data in the historical work data into the portrait prediction model.
  • the portrait prediction model outputs based on the unstructured data in the historical work data.
  • a portrait of a salesperson which is in vector form and is used to indicate what the salesperson is good at and how well he is good at it.
  • the cloud server before the cloud server obtains the portrait of the salesperson based on the portrait prediction model, the cloud server performs feature extraction based on historical work data to obtain training samples and test samples.
  • the training sample includes part of the historical work.
  • the training sample pairs of data and vectors, and the test samples include test sample pairs of some historical working data and vectors.
  • the cloud server trains the portrait prediction model based on the training samples, and tests the trained portrait prediction model based on the test samples. When the prediction accuracy of the portrait prediction model reaches the target accuracy, the training of the portrait prediction model ends.
  • the cloud server After the cloud server generates the portrait of the object, it stores the portrait of the object in the portrait database.
  • the cloud server can update the portrait in the portrait database. Specifically, the cloud server obtains the work data generated by the target object processing work tasks, generates an updated portrait of the target object based on the work data and the portrait prediction model, and modifies it according to the updated portrait. The portrait of the target object in the portrait database.
  • step g of the example shown in Figure 5 the cloud server obtains the portrait of the salesperson based on the portrait prediction model and stores the portrait of the salesperson in the portrait database. Therefore, when the cloud server distributes sales tasks, the cloud server can directly obtain the portrait of the salesperson from the portrait database, and perform task matching based on the portrait of the salesperson.
  • the cloud server can train a portrait prediction model based on the historical work data of the object, and obtain a portrait prediction model.
  • the portrait prediction model can generate a portrait based on the work data, improving the accuracy of the subject's portrait. .
  • FIG. 6 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • the device 600 It includes a transceiver unit 601 and a processing unit 602.
  • the device is used to implement each step performed by the cloud server in the above task allocation method embodiment, specifically:
  • the transceiver unit 601 is used to receive work tasks, which include one or more task targets.
  • the transceiver unit 601 is also used to obtain portraits of multiple objects.
  • the portraits include one or more of the following: age, areas of expertise and work performance, and work content of expertise.
  • the processing unit 602 is used to determine the target object based on the work task and the portrait of the object.
  • the target object is used to process the work task.
  • the transceiver unit 601 is also used to push the work task to the target object.
  • the transceiver unit 601 is also used to obtain the current work data of the object.
  • the current work data includes one or more of the following: current work status, last task end time, day's work duration, and day's work end time. and the current task importance level; the processing unit 602 is specifically configured to determine the target object based on the task goal, the object's portrait, and the current work data.
  • the transceiver unit 601 is also used to obtain the work data of the target object processing work task.
  • the processing unit 602 is also used to update the portrait of the target object based on the work data and the portrait prediction model, and the portrait prediction model is used to generate the portrait of the object.
  • the transceiver unit 601 is also used to obtain the historical work data of the object.
  • the historical work data includes one or more of the following data: order completion rate, complaint rate and sales volume, average call duration, and speaking time ratio. , speaking keywords, keyword occurrence time, average number of customer objections and number of discussions.
  • the processing unit 602 is also used to perform feature extraction based on historical work data to obtain training samples.
  • the processing unit 602 is also used to perform model training based on training samples to obtain a portrait prediction model.
  • the processing unit 602 is also configured to determine the training content of the subject based on the portrait of the subject, and the training content is used to train the subject in work skills.
  • the device is used to implement each step performed by the cloud server in the above embodiment of the portrait generation method, specifically:
  • the transceiver unit 601 is used to obtain the historical work data of the object.
  • the historical work data includes structured data and unstructured data.
  • the structured data includes one or more of the following data: order completion rate, complaint rate and sales volume.
  • the unstructured data includes One or more of the following data: average call length, proportion of speaking time, speaking keywords, time of occurrence of keywords, average number of customer objections and number of discussions.
  • the processing unit 602 is used to generate a portrait of the subject based on historical work data.
  • the portrait includes labels and vectors.
  • the labels include one or more of the following: age, field of expertise, and historical work performance.
  • the vector is used to indicate the subject's work content and degree of expertise. .
  • the transceiver unit 601 is also used to store the portrait of the object into the portrait database.
  • the processing unit 602 is specifically configured to perform feature extraction based on unstructured data to obtain training samples. Model training is performed based on the training samples to obtain a portrait prediction model, which is used to predict the portrait of the object. Input unstructured data into the portrait prediction model to obtain the vector of the object.
  • the processing unit 602 is specifically configured to obtain work data generated by the target object processing work tasks. Generate an updated portrait of the target object based on the work data and the portrait prediction model, and modify the portrait of the target object in the portrait database based on the updated portrait.
  • the processing unit 602 is specifically configured to extract labels of objects based on structured data.
  • each unit in the device can be a separate processing element, or it can be integrated and implemented in a certain chip of the device.
  • it can also be stored in the memory in the form of a program, and a certain processing element of the device can call and execute the unit. Function.
  • all or part of these units can be integrated together or implemented independently.
  • the processing element described here can also be a processor, which can be an integrated circuit with signal processing capabilities.
  • each step of the above method or each unit above can be implemented by an integrated logic circuit of hardware in the processor element or implemented in the form of software calling through the processing element.
  • FIG. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present application.
  • the computing device 700 includes: a processor 701, a memory 702, a communication interface 703 and a bus 704.
  • the processor 701, the memory 702 and the communication interface 703 are coupled through a bus (not labeled in the figure).
  • the memory 702 stores instructions. When the execution instructions in the memory 702 are executed, the computing device 700 executes the method executed by the cloud server in the above method embodiment.
  • the computing device 700 may be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or one or more microprocessors (digital signal processors) , DSP), or, one or more field programmable gate arrays (FPGA), or a combination of at least two of these integrated circuit forms.
  • ASICs application specific integrated circuits
  • DSP digital signal processors
  • FPGA field programmable gate arrays
  • the unit in the device can be implemented in the form of a processing element scheduler
  • the processing element can be a general processor, such as a central processing unit (Central Processing Unit, CPU) or other processors that can call programs.
  • CPU central processing unit
  • these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).
  • SOC system-on-a-chip
  • the processor 701 can be a central processing unit (CPU), or other general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or an on-site processor.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA Field programmable gate array
  • a general-purpose processor can be a microprocessor or any conventional processor.
  • Memory 702 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically removable memory. Erase electrically programmable read-only memory (EPROM, EEPROM) or flash memory.
  • Volatile memory can be random access memory (RAM), which is used as an external cache.
  • RAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • Double data rate synchronous dynamic random access memory double data date SDRAM, DDR SDRAM
  • enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM
  • synchronous link dynamic random access memory direct rambus RAM, DR RAM
  • the memory 702 stores executable program code, and the processor 701 executes the executable program code to respectively implement the functions of the aforementioned transceiver module, adaptive module and transcoding module, thereby implementing the aforementioned task allocation method or portrait generation method. That is, the memory 702 stores instructions for executing the above-mentioned task allocation method or portrait generation method.
  • the communication interface 703 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the computing device 700 and other devices or communication networks.
  • the bus 704 may also include a power bus, a control bus, a status signal bus, etc.
  • the bus can be a peripheral component interconnect express (PCIe) bus, an extended industry standard architecture (EISA) bus, a unified bus (unified bus, Ubus or UB), or a computer quick link (compute express link (CXL), cache coherent interconnect for accelerators (CCIX), etc.
  • PCIe peripheral component interconnect express
  • EISA extended industry standard architecture
  • CXL computer quick link
  • CXL cache coherent interconnect for accelerators
  • the bus can be divided into address bus, data bus, control bus, etc.
  • FIG. 8 is a schematic diagram of a computing device cluster provided by an embodiment of the present application.
  • the computing device cluster 800 includes at least one computing device 700 .
  • the computing device cluster 800 includes at least one computing device 700 .
  • the memory 702 in one or more computing devices 700 in the computing device cluster 800 may store the same instructions for performing the above method embodiments.
  • the memory 702 of one or more computing devices 700 in the computing device cluster 800 may also store part of the instructions for executing the above method.
  • a combination of one or more computing devices 700 may jointly execute instructions for performing the methods described above.
  • the memory 702 in different computing devices 700 in the computing device cluster 800 can store different instructions, respectively used to execute part of the functions of the above-mentioned apparatus. That is, the instructions stored in the memory 702 in different computing devices 700 can implement the collection. function of one or more modules in the development unit and processing unit.
  • one or more computing devices 700 in the computing device cluster 800 may be connected through a network.
  • the network may be a wide area network or a local area network, etc.
  • FIG. 9 is a schematic diagram of computer devices in a computer cluster being connected through a network according to an embodiment of the present application.
  • two computing devices 700A and 700B are connected through a network.
  • the connection to the network is made through a communication interface in each computing device.
  • the memory in the computing device 700A stores instructions for performing the functions of the transceiver module.
  • instructions for performing the functions of the processing module are stored in memory in computing device 700B.
  • computing device 700A shown in FIG. 9 may also be performed by multiple computing devices.
  • the functions of computing device 700B may also be performed by multiple computing devices.
  • a computer-readable storage medium is also provided.
  • Computer-executable instructions are stored in the computer-readable storage medium.
  • the processor of the device executes the computer-executed instructions
  • the device executes the above method embodiment.
  • a computer program product includes computer-executable instructions, and the computer-executable instructions are stored in a computer-readable storage medium.
  • the processor of the device executes the computer execution instruction
  • the device executes the method executed by the cloud server in the above method embodiment.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the units described 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 they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the above integrated units can be implemented in the form of hardware or software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or contributes to the existing technology, 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 storage medium , including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disk or optical disk and other media that can store program code. .

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请实施例公开了一种任务分配方法，用于提升工作任务的处理效率。本申请实施例方法包括：接收工作任务，工作任务包括一个或多个任务目标；获取多个对象的画像，画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容；根据工作任务和对象的画像确定目标对象，目标对象用于处理工作任务；向目标对象推送工作任务。

Description

一种任务分配方法以及装置
本申请要求于2022年09月13日提交中国专利局、申请号为202211110544.4、发明名称为“一种任务分配方法以及装置”的中国专利申请的优先权和2023年05月11日提交中国专利局、申请号为202310531234.8、发明名称为“一种任务分配方法以及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及计算机领域，尤其涉及一种任务分配方法以及装置。
背景技术
目前云上的企业服务市场处于发展初期，很多云厂商推出了任务分配系统，通过任务分配系统提升任务处理效率。例如，企业市场的产品或解决方案销售任务分配中，销售任务分配系统需要向销售人员分配销售任务，为了实现销售目标，销售任务分配系统需要为每个销售人员快速的从海量销售任务中找到更符合销售人员处理的销售任务，从而提升推销转化率。
目前的任务分配系统往往采用随机分配、顺序分配、自主申领等规则方式进行任务分配，分配的任务可能与工作人员不匹配，导致工作人员对任务处理的效率低，无法达成任务目标。例如，在销售任务分配过程，销售任务分配系统分配的销售任务可能因为不符合销售人员的擅长领域，导致销售人员无法达成销售目标，推销转化率低。
发明内容
本申请实施例提供了一种任务分配方法以及装置，用于提升实现任务目标的任务处理效率。
本申请实施例第一方面提供了一种任务分配方法，该方法可以由云服务器执行，也可以由云服务器的部件，例如云服务器的处理器、芯片或芯片系统等执行，还可以由能实现全部或部分云服务器功能的逻辑模块或软件实现。第一方面提供的任务分配方法包括：云服务器接收工作任务，工作任务包括一个或多个任务目标。获取多个对象的画像，其中对象例如处理任务的工作人员，画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容。云服务器根据工作任务和对象的画像确定目标对象，目标对象用于处理工作任务。云服务器向目标对象推送工作任务。
本申请实施中云服务器能够基于对象的画像确定执行任务的目标对象，从而将工作任务推送至与工作任务匹配的目标对象，从而提升了工作任务的处理效率。
一种可能的实施方式中，云服务器获取对象的当前工作数据，当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级。云服务器根据任务目标和对象的画像确定目标对象的过程中，云服务器根据任务目标、对象的画像和当前工作数据确定目标对象。
本申请实施例中云服务器还能够基于对象的当前工作数据确定目标对象，从而使得工作任务的推送在达成工作任务目标的前提下分配更加合理，进一步提升了任务目标的达成效果。
一种可能的实施方式中，工作任务的任务目标可以是多个任务目标。工作任务例如销售任务和工单处理任务，销售任务的任务目标例如，销售额满足销售额阈值的目标、利润率满足利率阈值的目标，工单处理任务的任务目标例如，客户满意度满足阈值的目标，工单总数满足单数阈值的目标、任务分配均衡度满足均衡度阈值的目标。
本申请实施例中云服务器可以基于多个任务目标匹配得到目标对象，提升了工作任务的任务目标达成效果。
一种可能的实施方式中，云服务器获取目标对象处理工作任务的工作数据。云服务器基于工作数据和画像预测模型更新目标对象的画像，画像预测模型用于生成对象的画像。
本申请实施例中云服务器能够根据目标对象处理工作任务所产生的工作数据，生成目标对象的更新画像，提升了目标对象的画像准确性。
一种可能的实施方式中，云服务器获取对象的历史工作数据，历史工作数据包括以下一项或多项数据：成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。基于历史工作数据进行特征提取，得到训练样本。基于训练样本进行模型训练，得到画像预测模型。
本申请实施例中云服务器能够基于对象的历史工作数据训练画像预测模型，得到画像预测模型，画像预测模型能够基于工作数据生成画像，提升了对象的画像准确性。
一种可能的实施方式中，云服务器根据对象的画像确定对象的培训内容，培训内容用于对对象进行工作技能培训。具体的，云服务器根据对象的画像确定出对象的不擅长处理的工作内容，基于不擅长处理的工作内容生成培训内容。
本申请实施例中云服务器能够基于对象的画像对工作人员进行培训，提升工作人员对工作任务的处理效率。
本申请实施例第二方面提供了一种对象的画像生成方法，该方法可以由云服务器执行，也可以由云服务器的部件，例如云服务器的处理器、芯片或芯片系统等执行，还可以由能实现全部或部分云服务器功能的逻辑模块或软件实现。第二方面的画像生成方法包括：云服务器获取对象的历史工作数据，历史工作数据包括结构化数据和非结构数据，结构化数据包括以下一项或多项数据：成单率、投诉率和销售额，非结构数据包括以下一项或多项数据：平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。基于历史工作数据生成对象的画像，画像包括标签和向量，标签包括以下一项或多项：年龄、擅长领域和历史工作业绩，向量用于指示对象的擅长工作内容和擅长程度。云服务器将对象的画像存储至画像数据库。
本申请实施例中云服务器能够基于对象的历史工作数据训练画像预测模型，得到画像预测模型，画像预测模型能够基于工作数据生成画像，提升了对象的画像准确性。
一种可能的实施方式中，云服务器基于非结构化数据进行特征提取，得到训练样本。云服务器基于训练样本进行模型训练，得到画像预测模型，画像预测模型用于预测对象的画像。云服务器基于历史工作数据生成对象的画像的过程中，将非结构化数据输入画像预测模型，得到对象的向量。
本申请实施例中云服务器能够基于非结构数据得到对应的向量，从而基于对象的向量确定对象的画像，提升了画像的准确性。
一种可能的实施方式中，云服务器获取目标对象处理工作任务产生的工作数据。基于工作数据和画像预测模型生成目标对象的更新画像，根据更新画像修改画像数据库中目标对象的画像。
本申请实施例中云服务器能够基于处理工作任务产生的工作数据，生成对象的更新画像，提升了画像的准确性。
一种可能的实施方式中，云服务器基于历史工作数据生成对象的画像的过程中，云服务器基于结构化数据提取对象的标签。
本申请实施例中云服务器能够基于结构化数据得到对应的标签，从而基于对象的标签确定对象的画像，提升了画像的准确性。
本申请实施例第三方面提供了一种任务分配装置，包括收发单元和处理单元。收发单元用于接收工作任务，工作任务包括一个或多个任务目标。收发单元还用于获取多个对象的画像，画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容。处理单元，用于根据工作任务和对象的画像确定目标对象，目标对象用于处理工作任务，收发单元还用于向目标对象推送工作任务。
一种可能的实施方式中，收发单元还用于获取对象的当前工作数据，当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级；处理单元具体用于根据任务目标、对象的画像和当前工作数据确定目标对象。
一种可能的实施方式中，收发单元还用于获取目标对象处理工作任务的工作数据。处理单元还用于基于工作数据和画像预测模型更新目标对象的画像，画像预测模型用于生成对象的画像。
一种可能的实施方式中，收发单元还用于获取对象的历史工作数据，历史工作数据包括以下一项或多项数据：成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、 平均客户异议数量和讨论次数。处理单元还用于基于历史工作数据进行特征提取，得到训练样本。处理单元还用于基于训练样本进行模型训练，得到画像预测模型。
一种可能的实施方式中，处理单元还用于根据对象的画像确定对象的培训内容，培训内容用于对对象进行工作技能培训。
本申请实施例第四方面提供了一种对象的画像生成装置，该装置包括收发单元和处理单元。收发单元用于获取对象的历史工作数据，历史工作数据包括结构化数据和非结构数据，结构化数据包括以下一项或多项数据：成单率、投诉率和销售额，非结构数据包括以下一项或多项数据：平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。处理单元用于基于历史工作数据生成对象的画像，画像包括标签和向量，标签包括以下一项或多项：年龄、擅长领域和历史工作业绩，向量用于指示对象的擅长工作内容和擅长程度。收发单元还用于将对象的画像存储至画像数据库。
一种可能的实施方式中，处理单元具体用于基于非结构化数据进行特征提取，得到训练样本。基于训练样本进行模型训练，得到画像预测模型，画像预测模型用于预测对象的画像。将非结构化数据输入画像预测模型，得到对象的向量。
一种可能的实施方式中，处理单元具体用于获取目标对象处理工作任务产生的工作数据。基于工作数据和画像预测模型生成目标对象的更新画像，根据更新画像修改画像数据库中目标对象的画像。
一种可能的实施方式中，处理单元具体用于基于结构化数据提取对象的标签。
本申请实施例第五方面提供了一种计算设备集群，计算设备包括一个或多个计算设备，计算设备包括处理器，处理器与存储器耦合，处理器用于存储指令，当指令被处理器执行时，以使得计算设备集群执行上述第一方面或第一方面任意一种可能的实施方式所述的方法，或者，以使得计算设备集群执行上述第二方面或第二方面任意一种可能的实施方式所述的方法。
本申请实施例第六方面提供了一种计算机可读存储介质，其上存储有指令，指令被执行时，以使得计算机执行上述第一方面或第一方面任意一种可能的实施方式所述的方法，或者，以使得计算机执行上述第二方面或第二方面任意一种可能的实施方式所述的方法。
本申请实施例第七方面提供了一种计算机程序产品，计算机程序产品中包括指令，指令被执行时，以使得计算机实现上述第一方面方法或第一方面任意一种可能的实施方式所述的方法，或者，以使得计算机实现上述第二方面方法或第二方面任意一种可能的实施方式所述的方法。
可以理解，上述提供的任意一种任务分配装置、画像生成装置、计算设备集群、计算机可读介质或计算机程序产品等所能达到的有益效果可参考对应的方法中的有益效果，此处不再赘述。
附图说明
图1为本申请实施例提供的一种任务分配系统的系统架构示意图；
图2为本申请实施例提供的一种任务分配方法的流程示意图；
图3为本申请实施例提供的另一种任务分配方法的流程示意图；
图4为本申请实施例提供的一种画像生成方法的流程示意图；
图5为本申请实施例提供的另一种画像生成方法的流程示意图；
图6为本申请实施例提供的一种装置结构示意图；
图7为本申请实施例提供的一种计算设备的结构示意图；
图8为本申请实施例提供的一种计算设备集群的结构示意图；
图9为本申请实施例提供的另一种计算设备集群的结构示意图。
具体实施方式
本申请实施例提供了一种任务分配方法以及装置，用于提升工作任务的处理效率。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外， 术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
首先，介绍本申请实施例涉及的部分术语，方便本领域技术人员理解方案。
画像是指对人或者物的描述，可以是人工设定的标签，也可以是通过算法自动生成的数值向量。标签化的画像例如，一个销售人员的画像：25岁、擅长交通行业、过去一年销售额5000万。数值向量化的画像可以由算法计算得多维数值向量，方便计算设备处理。
结构化数据是指数据由条目及其对应的值组成数据，一般可以通过表格展现。
非结构化数据是指内容自由不固定的数据，例如，图像、文本、语音等数据就是典型的非结构化数据。
下面结合附图介绍本申请实施例提供的任务分配方法以及装置。
请参阅图1，图1为本申请实施例提供一种任务分配方法所应用的系统架构示意图。在图1所示的示例中，任务分配系统100包括数据获取模块101、画像生成与更新模块102、任务匹配模块103、任务推送模块104和数据收集模块105。下面具体介绍各个模块的功能。
数据获取模块101用于获取对象的初始标签，该初始标签可以是系统维护人员为对象设置的标签。数据获取模块101还用于从数据库中获取对象的历史工作数据，历史工作数据例如成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。
画像生成与更新模块102用于根据对象的工作数据生成对象的画像。当数据库中不存在对象的历史工作数据时，画像生成与更新模块102用于将用户设置的初始标签作为对象的画像。画像生成与更新模块102还用于定期根据数据库中的工作数据生成对象的更新画像，从而更新画像数据库。
任务分配模块103用于根据画像生成与更新模块102生成的对象的画像确定出处理工作任务的目标对象。具体的，任务分配模块103还用于获取对象的当前工作数据，基于对象的画像、当前工作数据和工作任务的任务目标匹配处理工作任务的目标对象。当前工作数据例如，当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级。
任务推送模块104用于将工作任务推送至任务分配模块103确定出的处理工作任务的目标对象。任务推送模块104还用于向目标对象推送目标对象与工作任务的匹配度。
数据收集模块105用于收集对象处理工作任务产生的工作数据，并将处理工作任务产生的工作数据存储至数据库。
需要说明的是，本申请实施例提供的任务分配系统可以通过集成的方式集成到各个中业务系统，业务系统例如客户关系管理(customer relationship management，CRM)系统、办公自动化(office automation，OA)系统和企业资源计划系统(enterprise resource planning，ERP)系统。
请参阅图2，图2为本申请实施例提供的一种任务分配方法的流程示意图。在图2所示的示例中，本申请实施例提供的任务分配方法包括以下步骤：
201.接收工作任务，工作任务包括一个或多个任务目标。
云服务器接收工作任务，工作任务包括一个或多个任务目标。工作任务例如销售任务和工单处理任务，销售任务的任务目标例如，销售额满足销售额阈值的目标、利润率满足利率阈值的目标，工单处理任务的任务目标例如，客户满意度满足阈值的目标、工单总数满足单数阈值的目标、任务分配均衡度满足均衡度阈值的目标。
请参阅图3，图3为本申请实施例提供的一种销售任务分配的流程示意图。在图3所示的示例中，在步骤a中，工作任务以销售任务为例，云服务器接收销售任务，销售任务包括一个或多个销售目标，例如，销售额达到500万，利润率达到10％。
在图3所示的示例中，云服务器需要根据销售任务的销售目标确定执行该销售任务的销售人员。
202.获取对象的画像。
云服务器从数据库中获取对象的画像，对象包括执行工作任务的工作人员，对象的画像包括标签和向量。其中，标签包括以下一项或多项：年龄、擅长领域和历史工作业绩，向量用于指示对象的擅长工作内容和擅长程度。
请继续参阅图3，在图3所示的示例中，在步骤b至c中，云服务器获取从画像数据获取销售人员的画像，并获取销售人员的当前工作数据，销售人员的画像例如年龄、擅长销售领域、历史销售额等标签和指示销售人员擅长销售内容的数值向量，当前工作数据例如当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级。
203.根据任务目标和对象的画像确定目标对象。
云服务器根据任务目标和对象的画像确定目标对象，目标对象为处理工作任务的人员。
一种可能的实施方式中，云服务器根据任务目标和对象的画像确定目标对象的过程中，云服务器获取对象的当前工作数据，当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级。云服务器根据对象的当前工作数据、对象的画像和任务目标确定目标对象。
具体的，云服务器的任务分配模块将对象的画像和对象的当前工作数据输入至任务分配调度，基于任务目标求解目标对象，得到在工作量合适的情况下与工作任务最匹配的目标对象。
请继续参阅图3，在3所示的示例中，在步骤d中，云服务器基于销售任务的销售目标、当前工作数据和销售人员的画像确定处理销售任务的目标销售人员。具体的，云服务器将销售人员的画像和销售任务输入至任务分配器，计算不同销售人员处理该销售任务可能达成的销售目标，从而根据计算结果得到适合处理该销售任务的销售人员推荐排序。
之后，云服务器根据销售人员的当前工作数据对推荐排序中的销售人员进行筛选，确定目标销售人员。例如，云服务器按照推荐销售人员排序优先将当前工作状态处于空闲和当天工作时长较少的销售人员作为目标销售人员。
204.向目标对象推送工作任务。
云服务器向目标对象推送工作任务。具体的，云服务器的任务推送模块根据调度器输出的目标对象代号向目标对象推送工作任务。
一种可能的实施方式中，云服务器的任务推送模块还可以向目标对象推送任务目标以及工作任务的推送原因，推送原因例如工作任务与目标对象的匹配度。
一种可能的实施方式中，云服务器向目标对象推送工作任务之后，目标对象处理工作任务，生成工作数据，并将工作数据存储至数据库。云服务器基于工作数据和画像预测模型生成目标对象的更新画像，并基于更新画像对画像数据库中的画像进行更新。
本申请实施例中工作数据包括结构化数据和非结构化数据，其中，结构化数据包括以下一项或多项数据：成单率、投诉率和销售额，非结构数据包括以下一项或多项数据：平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。
请继续参阅图3，在图3所示示例的步骤e至步骤f中，云服务器将销售任务推送至目标销售人员，由目标销售人员处理该销售任务。在目标销售人员处理销售任务的过程中，云服务器手机目标销售人员执行销售任务产生的销售数据，并将销售数据作为历史工作数据存储至数据库。
其中，目标销售人员执行销售任务产生的销售数据例如销售额、成单率、投诉率、销售平均通话时长、销售人员说话时间比例、销售关键词、销售关键词发生时点、平均客户异议数量和讨论次数等。
从以上实施例可以看出，本申请实施中云服务器能够基于对象的画像确定执行任务的目标对象，从而将工作任务推送至能达成任务目标的对象，从而提升了工作任务的处理效率。
以上介绍了本申请实施例提供的任务分配方法，下面介绍本申请实施例提供的对象的画像生成方法。
请参阅图4，图4为本申请实施例提供的一种对象的画像生成方法。在图4所示的示例中，本申请实施例提供的对象的画像生成方法包括以下步骤：
401.获取对象的历史工作数据。
云服务器的数据获取模块获取对象的历史工作数据，历史工作数据包括结构化数据和非结构数据。其中，结构化数据包括以下一项或多项数据：成单率、投诉率和销售额，非结构数据包括以下一项或多项数据：平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。
一种可能的实施方式中，当对象不存在历史工作数据时，云服务器的数据获取模块从系统交互页面获取对象的初始标签，该初始标签可以是系统基于对象的基本信息生成的标签，也可以是系统的维护人员为对象手工添加的标签，具体不作限定。
请参阅图5，图5为本申请实施例提供的一种对象的画像生成方法。在图5所示示例的步骤a至d中，以销售任务分配为例，云服务器获取n个销售人员中每个销售人员的历史工作数据，其中，历史工作数据例如成单率、投诉率、销售额、销售平均通话时长、销售人员说话时间比例、销售说话关键词、销售关键词发生时点、平均客户异议数量和讨论次数。
在图5所示的示例中，当销售人员不存在历史工作数据时，云服务器获取该销售人员的初始标签，或者为销售人员添加初始标签，该初始标签即为销售人员的画像。
402.基于历史工作数据生成对象的画像。
云服务器基于历史工作数据生成对象的画像，画像包括标签和向量，标签包括以下一项或多项：年龄、擅长领域和历史工作业绩，向量用于指示对象的擅长工作内容和擅长程度，向量包括多维度数值向量。
一种可能的实施方式中，云服务器对历史工作数据中的非结构数据进行特征提取，得到训练样本，并根据训练样本进行模型训练，得到画像预测模型。云服务器根据基于历史工作数据生成对象的画像的过程中，云服务器将非结构化数据输入画像预测模型，得到对象的向量，将该向量作为对象的画像，该向量用于指示对象擅长的工作内容以及擅长程度。
一种可能的实施方式中，云服务器根据基于历史工作数据生成对象的画像的过程中，云服务器基于历史工作数据的结构化数据进行提取，得到对象的标签，将该标签作为对象的画像。
请继续参阅图5，在图5所示示例的步骤e至f中，云服务器将历史工作数据的中非结构化数据输入画像预测模型，画像预测模型基于历史工作数据中的非结构化数据输出销售人员的画像，该画像为向量形式，用于指示销售人员的擅长工作内容以及擅长程度。
需要说明的是，在图5所示的示例中，云服务器基于画像预测模型得到销售人员的画像之前，云服务器基于历史工作数据进行特征提取，得到训练样本和测试样本，训练样本包括部分历史工作数据与向量的训练样本对，测试样本包括部分历史工作数据与向量的测试样本对。云服务器基于训练样本训练画像预测模型，基于测试样本测试训练后的画像预测模型，当画像预测模型的预测准确度达到目标准确度时，结束对画像预测模型的训练。
403.将对象的画像存储至画像数据库。
云服务器生成对象的画像之后，将对象的画像存储至画像数据库。
本申请实施例中云服务器能够画像数据库中的画像进行更新，具体的，云服务器获取目标对象处理工作任务产生的工作数据，基于工作数据和画像预测模型生成目标对象的更新画像，根据更新画像修改画像数据库中目标对象的画像。
请继续参阅图5，在图5所示示例的步骤g中，云服务器基于画像预测模型得到销售人员的画像，并将销售人员的画像存储至画像数据库。以使得云服务器在进行销售任务分配时，云服务器能够直接从画像数据库中获取销售人员的画像，并基于销售人员的画像进行任务匹配。
从以上实施例中可以看出，本申请实施例中云服务器能够基于对象的历史工作数据训练画像预测模型，得到画像预测模型，画像预测模型能够基于工作数据生成画像，提升了对象的画像准确性。
以上介绍了本申请实施例提供的任务分配方法和画像生成方法，下面结合附图介绍本申请实施例提供的装置。
请参阅图6，图6为本申请实施例提供的一种装置的结构示意图。在图6所示的示例中，该装置600 包括收发单元601和处理单元602。
在一个可选的实施例中，该装置用于实现上述任务分配方法实施例中云服务器所执行的各个步骤，具体的：
收发单元601用于接收工作任务，工作任务包括一个或多个任务目标。收发单元601还用于获取多个对象的画像，画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容。处理单元602，用于根据工作任务和对象的画像确定目标对象，目标对象用于处理工作任务，收发单元601还用于向目标对象推送工作任务。
一种可能的实施方式中，收发单元601还用于获取对象的当前工作数据，当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级；处理单元602具体用于根据任务目标、对象的画像和当前工作数据确定目标对象。
一种可能的实施方式中，收发单元601还用于获取目标对象处理工作任务的工作数据。处理单元602还用于基于工作数据和画像预测模型更新目标对象的画像，画像预测模型用于生成对象的画像。
一种可能的实施方式中，收发单元601还用于获取对象的历史工作数据，历史工作数据包括以下一项或多项数据：成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。处理单元602还用于基于历史工作数据进行特征提取，得到训练样本。处理单元602还用于基于训练样本进行模型训练，得到画像预测模型。
一种可能的实施方式中，处理单元602还用于根据对象的画像确定对象的培训内容，培训内容用于对对象进行工作技能培训。
在另一个可选的实施例中，该装置用于实现上述画像生成方法实施例中云服务器所执行的各个步骤，具体的：
收发单元601用于获取对象的历史工作数据，历史工作数据包括结构化数据和非结构数据，结构化数据包括以下一项或多项数据：成单率、投诉率和销售额，非结构数据包括以下一项或多项数据：平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数。处理单元602用于基于历史工作数据生成对象的画像，画像包括标签和向量，标签包括以下一项或多项：年龄、擅长领域和历史工作业绩，向量用于指示对象的擅长工作内容和擅长程度。收发单元601还用于将对象的画像存储至画像数据库。
一种可能的实施方式中，处理单元602具体用于基于非结构化数据进行特征提取，得到训练样本。基于训练样本进行模型训练，得到画像预测模型，画像预测模型用于预测对象的画像。将非结构化数据输入画像预测模型，得到对象的向量。
一种可能的实施方式中，处理单元602具体用于获取目标对象处理工作任务产生的工作数据。基于工作数据和画像预测模型生成目标对象的更新画像，根据更新画像修改画像数据库中目标对象的画像。
一种可能的实施方式中，处理单元602具体用于基于结构化数据提取对象的标签。
应理解以上装置中单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且装置中的单元可以全部以软件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分单元以软件通过处理元件调用的形式实现，部分单元以硬件的形式实现。例如，各个单元可以为单独设立的处理元件，也可以集成在装置的某一个芯片中实现，此外，也可以以程序的形式存储于存储器中，由装置的某一个处理元件调用并执行该单元的功能。此外这些单元全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件又可以成为处理器，可以是一种具有信号的处理能力的集成电路。在实现过程中，上述方法的各步骤或以上各个单元可以通过处理器元件中的硬件的集成逻辑电路实现或者以软件通过处理元件调用的形式实现。
值得说明的是，对于上述方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明本申请并不受所描述的动作顺序的限制，其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本发明本申请所必须的。
本领域的技术人员根据以上描述的内容，能够想到的其他合理的步骤组合，也属于本发明本申请的保护范围内。其次，本领域技术人员也应该熟悉，说明书中所描述的实施例均属于优选实施例，所涉及 的动作并不一定是本发明本申请所必须的。
请参阅图7，图7为本申请实施例提供的一种计算设备的结构示意图。如图7所示，该计算设备700包括：处理器701、存储器702、通信接口703和总线704，处理器701、存储器702与通信接口703通过总线(图中未标注)耦合。存储器702存储有指令，当存储器702中的执行指令被执行时，计算设备700执行上述方法实施例中云服务器所执行的方法。
计算设备700可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(application specific integrated circuit，ASIC)，或，一个或多个微处理器(digital signal processor，DSP)，或，一个或者多个现场可编程门阵列(field programmable gate array，FPGA)，或这些集成电路形式中至少两种的组合。再如，当装置中的单元可以通过处理元件调度程序的形式实现时，该处理元件可以是通用处理器，例如中央处理器(central processing unit，CPU)或其它可以调用程序的处理器。再如，这些单元可以集成在一起，以片上系统(system-on-a-chip，SOC)的形式实现。
处理器701可以是中央处理单元(central processing unit，CPU)，还可以是其它通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其它可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。通用处理器可以是微处理器，也可以是任何常规的处理器。
存储器702可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
存储器702中存储有可执行的程序代码，处理器701执行该可执行的程序代码以分别实现前述收发模块、自适应模块和转码模块的功能，从而实现上述任务分配方法或画像生成方法。也即，存储器702上存有用于执行上述任务分配方法或画像生成方法的指令。
通信接口703使用例如但不限于网络接口卡、收发器一类的收发模块，来实现计算设备700与其他设备或通信网络之间的通信。
总线704除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。总线可以是快捷外围部件互连标准(peripheral component interconnect express，PCIe)总线，或扩展工业标准结构(extended industry standard architecture，EISA)总线、统一总线(unified bus，Ubus或UB)、计算机快速链接(compute express link，CXL)、缓存一致互联协议(cache coherent interconnect for accelerators，CCIX)等。总线可以分为地址总线、数据总线、控制总线等。
请参阅图8，图8为本申请实施例提供的一种计算设备集群的示意图。如图8所示，该计算设备集群800包括至少一台计算设备700。
如图8所示，所述计算设备集群800包括至少一个计算设备700。计算设备集群800中的一个或多个计算设备700中的存储器702中可以存有相同的用于执行上述方法实施例的指令。
在一些可能的实现方式中，该计算设备集群800中的一个或多个计算设备700的存储器702中也可以分别存有用于执行上述方法的部分指令。换言之，一个或多个计算设备700的组合可以共同执行用于执行上述方法的指令。
需要说明的是，计算设备集群800中的不同的计算设备700中的存储器702可以存储不同的指令，分别用于执行上述装置的部分功能。也即，不同的计算设备700中的存储器702存储的指令可以实现收 发单元和处理单元中的一个或多个模块的功能。
在一些可能的实现方式中，计算设备集群800中的一个或多个计算设备700可以通过网络连接。其中，所述网络可以是广域网或局域网等等。
请参阅图9，图9为本申请实施例提供的一种计算机集群中的计算机设备通过网络连接的示意图。如图9所示，两个计算设备700A和700B之间通过网络进行连接。具体地，通过各个计算设备中的通信接口与所述网络进行连接。
在一种可能的实现方式中，计算设备700A中的存储器中存有执行收发模块的功能的指令。同时，计算设备700B中的存储器中存有执行处理模块的功能的指令。
应理解，图9中示出的计算设备700A的功能也可以由多个计算设备完成。同样，计算设备700B的功能也可以由多个计算设备完成。
在本申请的另一个实施例中，还提供一种计算机可读存储介质，计算机可读存储介质中存储有计算机执行指令，当设备的处理器执行该计算机执行指令时，设备执行上述方法实施例中云服务器所执行的方法。
在本申请的另一个实施例中，还提供一种计算机程序产品，该计算机程序产品包括计算机执行指令，该计算机执行指令存储在计算机可读存储介质中。当设备的处理器执行该计算机执行指令时，设备执行上述方法实施例中云服务器所执行的方法。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，read-only memory)、随机存取存储器(RAM，random access memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (13)

  1. 一种任务分配方法，其特征在于，包括：
    接收工作任务，所述工作任务包括一个或多个任务目标；
    获取多个对象的画像，所述画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容；
    根据所述工作任务和所述对象的画像确定目标对象，所述目标对象用于处理所述工作任务；
    向所述目标对象推送所述工作任务。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取对象的当前工作数据，所述当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级；
    所述根据所述任务目标和所述对象的画像确定目标对象包括：
    根据所述任务目标、所述对象的画像和所述当前工作数据确定目标对象。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    获取所述目标对象处理所述工作任务的工作数据；
    基于所述工作数据和画像预测模型更新所述目标对象的画像，所述画像预测模型用于生成所述对象的画像。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    获取所述对象的历史工作数据，所述历史工作数据包括以下一项或多项数据：成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数；
    基于所述历史工作数据进行特征提取，得到训练样本；
    基于所述训练样本进行模型训练，得到所述画像预测模型。
  5. 根据权利要求1至4中任意一项所述的方法，其特征在于，所述方法还包括：
    根据所述对象的画像确定所述对象的培训内容，所述培训内容用于对所述对象进行工作技能培训。
  6. 一种任务分配装置，其特征在于，包括：
    收发单元，用于接收工作任务，所述工作任务包括一个或多个任务目标；
    所述收发单元还用于获取多个对象的画像，所述画像包括以下一项或多项：年龄、擅长领域和工作业绩、擅长工作内容；
    处理单元，用于根据所述工作任务和所述对象的画像确定目标对象，所述目标对象用于处理所述工作任务；
    所述收发单元还用于向所述目标对象推送所述工作任务。
  7. 根据权利要求6所述的装置，其特征在于，所述收发单元还用于：
    获取对象的当前工作数据，所述当前工作数据包括以下一项或多项：当前工作状态、上一任务结束时间、当天工作时长、当天工作结束时间和当前任务重要等级；
    所述处理单元具体用于：
    根据所述任务目标、所述对象的画像和所述当前工作数据确定目标对象。
  8. 根据权利要求6或7所述的装置，其特征在于，所述收发单元还用于：
    获取所述目标对象处理所述工作任务的工作数据；
    所述处理单元还用于基于所述工作数据和画像预测模型更新所述目标对象的画像，所述画像预测模型用于生成所述对象的画像。
  9. 根据权利要求8所述的装置，其特征在于，所述收发单元还用于：
    获取所述对象的历史工作数据，所述历史工作数据包括以下一项或多项数据：成单率、投诉率和销售额、平均通话时长、说话时间比例、说话关键词、关键词发生时点、平均客户异议数量和讨论次数；
    所述处理单元还用于基于所述历史工作数据进行特征提取，得到训练样本；
    所述处理单元还用于基于所述训练样本进行模型训练，得到所述画像预测模型。
  10. 根据权利要求6至9中任意一项所述的装置，其特征在于，所述处理单元还用于：
    根据所述对象的画像确定所述对象的培训内容，所述培训内容用于对所述对象进行工作技能培训。
  11. 一种计算设备集群，其特征在于，包括一个或多个计算设备，所述计算设备包括处理器，所述处理器与存储器耦合，所述处理器用于存储指令，当所述指令被所述处理器执行时，以使得所述计算设备集群执行权利要求1至5中任一项所述的方法。
  12. 一种计算机可读存储介质，其上存储有指令，其特征在于，所述指令被执行时，以使得计算机执行权利要求1至5中任一项所述的方法。
  13. 一种计算机程序产品，所述计算机程序产品中包括指令，其特征在于，所述指令被执行时，以使得计算机实现权利要求1至5中任一项所述的方法。
PCT/CN2023/118260 2022-09-13 2023-09-12 一种任务分配方法以及装置 WO2024055963A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202211110544 2022-09-13
CN202211110544.4 2022-09-13
CN202310531234.8A CN117744961A (zh) 2022-09-13 2023-05-11 一种任务分配方法以及装置
CN202310531234.8 2023-05-11

Publications (1)

Publication Number Publication Date
WO2024055963A1 true WO2024055963A1 (zh) 2024-03-21

Family

ID=90274270

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/118260 WO2024055963A1 (zh) 2022-09-13 2023-09-12 一种任务分配方法以及装置

Country Status (1)

Country Link
WO (1) WO2024055963A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112150023A (zh) * 2020-09-29 2020-12-29 壹链盟生态科技有限公司 任务分配方法、装置及存储介质
CN113393060A (zh) * 2021-08-16 2021-09-14 深圳市信润富联数字科技有限公司 任务分配方法、装置、电子设备及存储介质
US20210365963A1 (en) * 2017-08-24 2021-11-25 Ping An Technology (Shenzhen) Co., Ltd. Target customer identification method and device, electronic device and medium
CN113947322A (zh) * 2021-10-25 2022-01-18 国能大渡河大数据服务有限公司 一种基于FP-Growth算法的画像匹配方法及系统
CN114091886A (zh) * 2021-11-16 2022-02-25 国网山东省电力公司营销服务中心(计量中心) 一种供电所台区现场作业智能派工方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210365963A1 (en) * 2017-08-24 2021-11-25 Ping An Technology (Shenzhen) Co., Ltd. Target customer identification method and device, electronic device and medium
CN112150023A (zh) * 2020-09-29 2020-12-29 壹链盟生态科技有限公司 任务分配方法、装置及存储介质
CN113393060A (zh) * 2021-08-16 2021-09-14 深圳市信润富联数字科技有限公司 任务分配方法、装置、电子设备及存储介质
CN113947322A (zh) * 2021-10-25 2022-01-18 国能大渡河大数据服务有限公司 一种基于FP-Growth算法的画像匹配方法及系统
CN114091886A (zh) * 2021-11-16 2022-02-25 国网山东省电力公司营销服务中心(计量中心) 一种供电所台区现场作业智能派工方法及系统

Similar Documents

Publication Publication Date Title
US20180150783A1 (en) Method and system for predicting task completion of a time period based on task completion rates and data trend of prior time periods in view of attributes of tasks using machine learning models
WO2018126953A1 (zh) 种子人群扩散方法、装置、信息投放系统以及存储介质
JP6152173B2 (ja) 商品検索結果の順位付け
CN109697522B (zh) 一种数据预测的方法和装置
US20210103858A1 (en) Method and system for model auto-selection using an ensemble of machine learning models
CN110995459B (zh) 异常对象识别方法、装置、介质及电子设备
WO2020110664A1 (ja) 受注予測モデルの生成方法、受注予測モデル、受注予測装置、受注予測方法および受注予測プログラム
US20200334615A1 (en) Predicting Business-Agnostic Contact Center Expected Wait Times With Deep Neural Networks
WO2019041523A1 (zh) 电子装置、语音导航需求预测方法和存储介质
CN112215448A (zh) 分配客服的方法和装置
US20220245679A1 (en) Systems and methods for forecasting campaign parameters using machine learning architectures and techniques
CN109426983A (zh) 闪购活动自动生成方法及装置、存储介质、电子设备
US8862609B2 (en) Expanding high level queries
US11334790B1 (en) System and method for recurrent neural networks for forecasting of consumer goods' sales and inventory
WO2024055963A1 (zh) 一种任务分配方法以及装置
TWI752367B (zh) 基於自然語言處理的智能對話管理方法及系統
CN111159355A (zh) 客户投诉单处理方法及装置
CN113360672B (zh) 用于生成知识图谱的方法、装置、设备、介质和产品
CN115202847A (zh) 任务的调度方法和装置
US20110208738A1 (en) Method for Determining an Enhanced Value to Keywords Having Sparse Data
CN114581130A (zh) 基于客户画像的银行网点派号方法及装置、存储介质
CN117744961A (zh) 一种任务分配方法以及装置
WO2023144949A1 (ja) リスク対処支援装置、学習装置、リスク対処支援方法、学習方法及びプログラム
US20220398524A1 (en) Consumer interaction agent management platform
Yin et al. A dynamic MADM method for the selection of a big data service provider

Legal Events

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

Ref document number: 23864695

Country of ref document: EP

Kind code of ref document: A1