Method and apparatus for assigning tasks, and device, medium and program product

Abstract

The embodiments of the present disclosure relate to a method and apparatus for assigning tasks, and a device, a medium and a program product. The method comprises: on the basis of a description of a target task and information of a plurality of task executors, generating a thought chain related to the target task. The method further comprises: on the basis of the thought chain, determining, by means of a task processing model, a task executor associated with the target task among the plurality of task executors. In addition, the method further comprises assigning the target task to the determined task executor. On the basis of the embodiments of the present disclosure, tasks are intelligently assigned by means of a task processing model, such that the efficiency of task assignment can be improved, thereby helping to improve the quality of task execution. In addition, the method of generating a thought chain on the basis of a description of a target task and task executor information, thereby assigning tasks by means of a task processing model can ensure that the tasks are assigned to suitable task executors, and helps to reduce the cost of model training and improves the user experience.

Description

Method, apparatus, device, medium and program product for allocating tasks TECHNICAL FIELD

[0001] The present disclosure relates generally to the field of computers, and more specifically, to a method, apparatus, device, medium and program product for allocating tasks. BACKGROUND

[0002] With the continuous advancement of technology, machine learning models have become more complex and powerful. In order to fully exert the performance of these models, it is necessary to provide more rich and accurate labeled data, which has prompted the emergence and development of data labeling tasks. Data labeling task refers to the process of classifying, marking, annotating or annotating data, so that machine learning models can understand and use these data.

[0003] Data labeling plays a crucial role in many fields such as image, text, audio, video, etc. In the field of text, data labeling may involve marking entities in sentences such as names, places, organization names, etc. In the field of image, data labeling may include marking key information such as objects, scenes, etc. in the image. Data labeling tasks are usually completed by professional annotators or teams who use specialized labeling tools or platforms to perform labeling work. During the labeling process, it is necessary to ensure the accuracy, consistency and completeness of the labeling to ensure that the trained machine learning model has high performance and reliability.

[0004] SUMMARY

[0005] Embodiments of the present disclosure provide a method, apparatus, device, medium and program product for allocating tasks.

[0006] According to a first aspect of the disclosure, a method for allocating tasks is provided. The method includes generating a thought chain related to a target task based on a description of the target task and information of a plurality of task performers. The method further includes determining, by a task processing model, a task performer associated with the target task from the plurality of task performers based on the thought chain. In addition, the method further includes allocating the target task to the determined task performer.

[0007] In a second aspect of the disclosure, an apparatus for allocating tasks is provided. The apparatus includes a thought chain generation module configured to generate a thought chain related to a target task based on a description of the target task and information of a plurality of task performers. The apparatus further includes a task performer determination module configured to determine, by a task processing model, a task performer associated with the target task from the plurality of task performers based on the thought chain. In addition, the apparatus further includes a target task allocation module configured to allocate the target task to the determined task performer.

[0008] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes a processor and a memory coupled with the processor, the memory having stored therein instructions which, when executed by the processor, cause the electronic device to perform the method according to the first aspect.

[0009] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to the first aspect.

[0010] In a fifth aspect of the present disclosure, a computer program product is provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions that, when executed, cause a computer to perform the method according to the first aspect.

[0011] The summary is presented to introduce some aspects of the disclosure in a simplified form that are further described below in the detailed description. The summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF DRAWINGS

[0012] The above and other features, aspects and advantages of various embodiments of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements, wherein:

[0013] FIG. 1 shows a schematic diagram of an example environment in which various embodiments of the present disclosure can be implemented;

[0014] FIG. 2 shows a flowchart of a method for allocating a task according to some embodiments of the present disclosure;

[0015] FIG. 3 shows a schematic diagram of an architecture for allocating a task by an agent according to certain embodiments of the present disclosure;

[0016] FIG. 4A shows a schematic diagram of a thought chain for allocating a task according to certain embodiments of the present disclosure;

[0017] FIG. 4B shows a schematic diagram of outputting a recommended allocation result and a recommended allocation reason according to a thought chain according to certain embodiments of the present disclosure;

[0018] FIG. 5 shows a block diagram of an apparatus for allocating a task according to certain embodiments of the present disclosure; and

[0019] FIG. 6 shows a block diagram of an electronic device according to certain embodiments of the present disclosure.

[0020] The same or similar reference numerals in all the drawings denote the same or similar elements. DETAILED DESCRIPTION

[0021] It can be understood that the data involved in the technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and relevant provisions.

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0023] In the description of embodiments of the present disclosure, the term "comprising" and similar terms are to be understood as open-ended, i.e., "including but not limited to". The term "based on" is to be understood as "based at least in part on". The term "one embodiment" or "the embodiment" is to be understood as "at least one embodiment". The terms "first", "second" and the like can refer to different or identical objects unless otherwise explicitly stated. Other explicit and implicit definitions can also be included below.

[0024] In order to ensure that the machine learning model trained by the execution result of the target task has high performance and reliability, the target task is usually completed by professional task executors or teams. In the related art, the information features of all task executors performing the target task are usually fused with the information features of the target task to be processed, and then trained in a related model, so that the task executor suitable for the target task can be found when applied. The disadvantages of this method are obvious: first, since the number of task executors performing the target task is limited, and this method requires a large amount of training data, it may cause overfitting, and these data need complicated feature transformation or encoding, which leads to the inability to improve the efficiency of task allocation. Secondly, considering the mobility of task executors performing the target task, whenever there is a personnel change, the information features of the personnel will also change, which will cause the trained model to be invalid, so that a new model needs to be trained again, wasting time and effort.

[0025] To this end, an embodiment of the present disclosure provides a method for allocating a task. In this method, a task executor is intelligently recommended for a target task by a task processing model based on a thought chain generated according to a description of the target task and information of the task executor, so that the target task is allocated to the suitable task executor.

[0026] Embodiments of the present disclosure can improve the efficiency of task allocation and make the workflow more automated and efficient by intelligently allocating tasks based on thought chains through a task processing model. Moreover, by matching the description of the target task with the information of the task performer (such as skills, expertise, etc.), the task can be allocated to the appropriate task performer, which improves the quality and efficiency of task execution. In addition, when the task demand or personnel capacity changes, the task allocation strategy can be quickly adjusted through the task processing model to adapt to the new situation.

[0027] FIG. 1 shows a schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented. As shown in FIG. 1, after the task allocation system 110 obtains the information 102 of multiple task performers and the descriptions 104 of multiple tasks, it can recommend a relevant task performer for each task in parallel, and then allocate the task to the corresponding task performer at 120.

[0028] Referring to FIG. 1, in some embodiments, the task allocation system 110 can be an intelligent system configured with a task processing model. An intelligent agent is an intelligent entity capable of perceiving the environment, making decisions, and performing actions. It is usually based on machine learning technology and has autonomy and adaptability. It can autonomously learn and improve in a specific task or field. In some embodiments, the task processing model can be a machine learning-based model trained on large-scale data, such as a language model or a multi-modal model.

[0029] Continuing to refer to FIG. 1, in some embodiments, the information 102 of the task performer can include the skills of the task performer (such as language, expertise, etc.), past experience (such as experience in what type of task), historical task type and accuracy (such as the mode of accuracy on the picture classification task being above 98%, while most other task performers are below 98%). In some embodiments, the task description 104 can include the standard operating procedure (SOP) of the task, the terms followed by the task (such as confidential information), the type of the task (such as labeling classification, rewriting, or extraction), the information of the task itself (such as video, text, picture, etc.), and unstructured description (such as description for video or picture), etc.

[0030] The task allocation system 110 shown in FIG. 1 can recommend a relevant task performer for each task based on the information 102 of the task performer and the descriptions 104 of multiple tasks. Then, at 120, each task can be allocated to the corresponding task performer. The task allocation system 110 can efficiently match tasks and task performers to ensure that each task is properly handled.

[0031] It should be understood that the architecture and functionality of the example environment 100 is described for illustrative purposes only and is not meant to limit the scope of the present disclosure. Embodiments of the present disclosure can be applied to other environments with different structures and / or functionalities.

[0032] The method according to embodiments of the present disclosure will be described in detail below in conjunction with FIG. 2 to FIG. 6. For ease of understanding, the specific data mentioned in the following description are all exemplary and are not used to limit the protection scope of the present disclosure. It can be understood that the following described embodiments can also include additional actions not shown and / or can omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0033] FIG. 2 shows a flowchart of a method 200 for assigning tasks according to some embodiments of the present disclosure. The method 200 can be performed by an apparatus for assigning tasks, which can be implemented by software and / or hardware. Next, the method 200 is schematically described taking the apparatus for assigning tasks as the execution subject. Referring to FIG. 2, the method 200 can include block 202, block 204, and block 206.

[0034] At block 202, a thinking chain related to a target task is generated based on a description of the target task and information of a plurality of task performers. For one target task, there can be a plurality of task performers to choose from. In some embodiments, the target task can be a task to be assigned, such as a labeling task or an auditing task, and the task performer is a person responsible for performing the task, such as a labeling person or an auditing person. The description of the target task covers a plurality of aspects of information closely related to the target task. In some embodiments, the description of the target task can be various descriptions related to the target task, such as a standard execution document of the target task or the content of the target task or the type of the target task, etc. These task descriptions help to understand the nature and requirements of the task. In some embodiments, the information of the task performer can be the skill or past experience of the task performer or the type and accuracy of the historically performed tasks, etc. In some embodiments, the thinking chain at least includes the description of the target task and the information of the task performer. In some embodiments, the thinking chain related to the target task refers to a series of logically related thinking steps or ideas related to the target task, which can guide the task processing model to determine the task performer related to the target task for the target task. In some embodiments, a plurality of thinking chains associated with a plurality of target tasks can be determined in parallel.

[0035] At block 204, based on the thought chain, a task performer associated with the target task is determined from a plurality of task performers by a task processing model. That is, the task processing model selects a task performer associated with the target task from a plurality of task performers according to the thought chain for the target task. In some embodiments, the task processing model can be a machine learning based model trained by large-scale data, which can be a language model, and can also be a multi-modal model. In some embodiments, a plurality of associated task performers can be determined in parallel for a plurality of target tasks. In some embodiments, there can be feedback information of error samples in the thought chain.

[0036] At block 206, the target task is assigned to the determined task performer. After the task performer associated with the target task is determined for the target task, the target task can be assigned to the task performer. In some embodiments, a plurality of target tasks can be assigned to a plurality of task performers in parallel.

[0037] Embodiments of the present disclosure intelligently assign tasks based on thought chains by a task processing model, which can improve the efficiency of task assignment and make the workflow more automated and efficient. Moreover, matching according to the description of the target task and the information of the task performer (such as skill specialty, etc.) can ensure that the task is assigned to a suitable task performer, and such personalized task assignment can improve the quality and efficiency of task execution. In addition, when the task demand or personnel capacity changes, the task assignment strategy can be quickly adjusted by the task processing model to adapt to the new situation.

[0038] FIG. 3 shows a schematic diagram of an architecture 300 for assigning tasks by an intelligent agent according to certain embodiments of the present disclosure. The process of assigning tasks by an intelligent agent according to some embodiments of the present disclosure will be described below taking a target task as an annotation task as an example, so in the description related to FIG. 3, the task performer can be referred to as an annotator.

[0039] In combination with FIG. 1, FIG. 3 shows a reference architecture of the task assignment system 110. The task assignment system 110 is configured with a task processing model 310, a storage 320, and a planning component 330. In some embodiments, the task processing model 310 can be a machine learning based model trained by large-scale data, which can be a multi-modal task processing model for understanding picture text and other modal content data, and can also be a language model. In some embodiments, the task processing model 310 can be a model for generating text from input text, a model for generating text from input text and image, and a model for generating image from input text. In some embodiments, the task processing model 310 can be switched according to the type of the target task, such as using a language model for a text classification task.

[0040] With continued reference to FIG. 3, in some embodiments, the memory 320 is divided into short-term memory 322 and long-term memory 324. In some embodiments, the memory duration of the memory 320 can be set by the expiration duration of the database, for example, the expiration duration of the long-term memory is set to 1 month, and the expiration duration of the short-term memory is set to 1 day. By distinguishing the long-term memory from the short-term memory, the storage cost can be saved, thereby improving the running efficiency of the task processing model 310.

[0041] As shown in FIG. 3, in some embodiments, the original content of the task, the information of the category of the task can be stored in the short-term memory 322. In some embodiments, the results of the labeling of the task performer, i.e., the labeling personnel, the verification results of the quality assurance (QA), and the like can also be stored in the short-term memory 322.

[0042] With continued reference to FIG. 3, in some embodiments, the long-term memory 324 stores the information of the specialties of the labeling personnel, the language skills, and the like, and can also store the statistical information of the performance of the labeling personnel in various types of tasks in the historical labeling tasks. For example, the average value, the median, the mode, and the variance of the accuracy rate of the labeling personnel 1 in the short text classification task are 0.98, 0.94, 0.95, and 1.2, respectively. For another example, the average value, the median, the mode, and the variance of the labeling duration of the labeling personnel 1 are 30 seconds, 40 seconds, 33 seconds, and 8.4, respectively. In some embodiments, the statistical information of the labeling personnel can be periodically updated, for example, daily updated. In some embodiments, the long-term memory 324 can also store the standard operating procedure (SOP) of the labeling task, and the standard operating document can be updated as the type of the labeling task changes.

[0043] With continued reference to FIG. 3, in some embodiments, when preparing to perform the assigned labeling task, the relevant information of the labeling personnel, such as the skill and the like, can be pre-stored in the in-memory database of the memory 320. These databases can be NoSQL databases, for example, can be in-memory data structure storage systems (such as Redis) or document-oriented NoSQL databases (such as MongoDB) and the like. In some embodiments, if there is also the labeling information of the historical task of the labeling personnel, it can also be saved in the database of the memory 320. In some embodiments, the relevant information about the labeling personnel is stored in the database of the memory 320 in a discrete manner, for example, “she is good at mathematics” can be stored in the database of the memory 320 as a discrete feature A. In some embodiments, when preparing to perform the assigned labeling task, the description related to the labeling task can also be stored in the memory 320. Some standard operating documents about the labeling task can be stored in the long-term memory 324, and some original content of the labeling task, the type of the task can be stored in the short-term memory 322.

[0044] As shown in FIG. 3, when a labeler needs to be assigned to label task B in the labeling tasks 340, the task assignment system 110 retrieves various relevant descriptions about the labeling task B and calls information of all labelers and historical labeling performance (if any) from the database of the storage 320 to generate a thought chain about the labeling task B. In some embodiments, discrete features of information about the labelers in the storage 320 need to be converted into textual descriptions to participate in the construction of the thought chain, for example, feature A can be converted into a textual description of “she is good at math”. In some embodiments, the planning component 330 can be used to generate the thought chain about the labeling task B, and the planning component 330 can also generate the thought chain 334 about the labeling task B according to some set templates. In some embodiments, some error feedback 332 about the labeling task can be stored in the storage 320 after being verified by quality assurance, and can be called by the planning component 330 to generate the thought chain 334 about the labeling task B when assigning the relevant labeling task (such as the labeling task B is a labeling task of the same type as the error feedback 332).

[0045] In conjunction with FIG. 4A, FIG. 4A shows a schematic diagram of a thought chain 400A for assigning a task according to some embodiments of the present disclosure. In the display interface 402A, the thought chain 334 about the labeling task B is shown, which includes a recommendation instruction 410A, a task prompt 420A about the labeling task B, a prompt 430A about all labelers, and a feedback prompt 440A. In some embodiments, exemplary feedback, which refers to a well-done task, can also be added to the thought chain 334. In the recommendation instruction 410A, there can be an instruction of “please output the ID of a suitable labeler”. In some embodiments, the instruction can be replaced according to the scenario of the target task.

[0046] With continued reference to FIG. 4A, in some embodiments, the task prompt 420A can include a task description 422A about the labeling task B, for example, the type is a text classification task, and the content of the task is the Portuguese text “Qual é a autonomia da bateria deste computador portátil”. In some embodiments, the task prompt 420A can also include a standard operating procedure 424A of the labeling task B, which indicates that the text is classified into three categories according to the rules, which are asking product information, requesting help, and providing feedback.

[0047] With continued reference to FIG. 4A, for the labeling task B, the prompts 430A for all the labelers (1 to N) can be included in the prompt for the labelers. The prompt 432A for labeler 1 includes the relevant information for labeler 1, “She is very proficient in Portuguese, she was born in a Portuguese-speaking area, her historical accuracy rate for short text classification is 98%, and the processing time is 23 seconds.” The prompt 434A for labeler N includes the relevant information for labeler N, “He is good at Latin. Recently, his task accuracy rate for short text classification is 94%, and the processing time is 30 seconds.” In some embodiments, the feedback prompts 440A are error feedbacks 332 for some labeling tasks, for example, the feedback prompt 440A shows some historical mistakes of labeler 3 for short text classification, labeler 3 incorrectly labeled the text as “feedback” for text classification in Portuguese, while the quality assurance (QA) label is “request help.” In some embodiments, the feedback prompt 440A can also be that an inappropriate labeler is assigned for a task or a task is difficult, so that the labeling result is not ideal, and the like. By adding the feedback, a higher labeling accuracy and a shorter processing time can be obtained, thereby improving the overall efficiency of the labeling task. In some embodiments, if there is no error feedback 332 related to the labeling task B, there can be no error feedback prompt 440A in the thought chain 334. In some embodiments, the parameters of the task processing model 310 can be adjusted according to the feedback of the quality assurance.

[0048] By directly inputting the original data to implement the method of assigning labelers for a target task, it can be ensured that the input description of the target task, the information of the labelers, and the output recommended result and recommended reason are controllable, thereby improving the efficiency of system operation and enhancing the user experience.

[0049] The output of the recommended assignment result and the recommended assignment reason 400B according to the thought chain will be described below in conjunction with FIG. 4B. Referring to FIG. 4B, in the display interface 402B, the recommended reason 410B and the recommended result 420B are displayed. The recommended reason 410B output by the task processing model 310A can clearly and explicitly show why labeler 1 is the suitable person to label the task B, rather than other labelers, thereby improving the interpretability of the system. In some embodiments, if it is set that the recommended reason 410B does not need to be output, the recommended result 420B can be directly output.

[0050] Referring back to FIG. 3, after assigning the labeling task B to the labeler 1, the labeling result 350 of the labeler 1 on the labeling task B can be sampled, for example, the labeling result 350 can be sampled at a certain ratio, for example, 1%, and the accuracy of the labeling of the labeler 1 on the labeling task B can be determined by quality assurance. In some embodiments, the determination information of the quality assurance will be stored in the memory data to form the short-term memory 322 for subsequent allocation tasks.

[0051] With continued reference to FIG. 3, in some embodiments, if there are 500 labelers, the information of the 500 labelers can be divided into 10 batches of 50 labelers each to perform selection of relevant labelers for the labeling task B by the task recommendation system 110, and from the labelers determined to be relevant to the labeling task B in each batch, the final labeler suitable for the labeling task B is determined. By this method of recommending suitable labelers for target tasks, controllability of the recommendation can be ensured, and compared with the method of recommending suitable labeling tasks for labelers, the overall inference efficiency is improved, thereby providing a better experience for users.

[0052] In some embodiments, there can be many target tasks in the task 340, and the task recommendation system 110 can determine in parallel which labeler matches the target tasks, thereby allocating the target tasks to the corresponding labelers. It can be understood that the target task can also be other tasks, for example, an audit task, etc.

[0053] By configuring the system with the task processing model 310 to recommend suitable labelers for target labeling tasks, a large amount of sample data is not required, and the labelers are not sensitive to changes, so that the recommendation and allocation of tasks can be realized even in the case of changes in labelers.

[0054] FIG. 5 shows a block diagram of an apparatus 500 for allocating tasks according to certain embodiments of the present disclosure. As shown in FIG. 5, the apparatus 500 includes a thought chain generation module 502 configured to generate a thought chain associated with a target task based on a description of the target task and information of a plurality of task performers. The apparatus 500 further includes a task performer determination module 504 configured to determine, based on the thought chain, a task performer associated with the target task from the plurality of task performers by a task processing model. In addition, the apparatus 500 further includes a target task allocation module 506 configured to allocate the target task to the determined task performer.

[0055] In some embodiments, the thought chain generation module 502 comprises: an information acquisition module configured to acquire information of the plurality of task performers from the long-term memory of the memory; an error feedback acquisition module configured to acquire error feedback from the short-term memory of the memory, the error feedback at least comprising an error execution result and an error reason; and an agent thought chain generation module configured to generate, by a planning component of the agent, the thought chain based on the information, the description, and the error feedback.

[0056] In some embodiments, the task performer determination module 504 comprises: a task processing model task performer determination module configured to determine, by the task processing model, the task performer associated with the target task based on the thought chain.

[0057] In some embodiments, the task processing model task performer determination module comprises: a reason determination module configured to determine, by the task processing model, the task performer associated with the target task and a reason based on the thought chain in response to the target task being a predetermined task.

[0058] In some embodiments, the target task assignment module 506 comprises: a labeling result acquisition module configured to acquire a labeling result of the target task by the determined task performer; and a feedback determination module configured to determine feedback for the labeling result based on the labeling result and store the feedback to the short-term memory.

[0059] In some embodiments, the feedback determination module comprises: a sampling module configured to sample the labeling result according to a predetermined proportion; a feedback generation module configured to generate the feedback based on the determined reason; and an adjustment module configured to adjust parameters of the task processing model based on the feedback.

[0060] In some embodiments, the feedback determination module further comprises an update module configured to update the error feedback to the planning component of the agent in response to the labeling result being inconsistent with a quality-assured labeling result.

[0061] In some embodiments, the apparatus 500 further comprises: a data storage module configured to store the preprocessed data in a unified format in the memory of the agent, the preprocessed data at least comprising the information of the task performer and the description.

[0062] In some embodiments, the apparatus 500 further comprises: a long-term memory determination module configured to determine the memory as the long-term memory in response to a database expiration time length of the memory satisfying a first time length condition; and a short-term memory determination module configured to determine the memory as the short-term memory in response to the database expiration time length satisfying a second time length condition.

[0063] In some embodiments, the thought chain generation module 502 further includes a discrete feature generation module configured to generate a plurality of discrete features for the plurality of task performers based on the information of the plurality of task performers, and a discrete feature conversion module configured to convert the plurality of discrete features for the plurality of task performers into a plurality of text descriptions.

[0064] In some embodiments, the apparatus 500 further includes a splitting module configured to split the plurality of task performers into a plurality of groups according to a unit quantity in response to the quantity of the plurality of task performers reaching a first predetermined quantity, a determining module configured to determine, by the intelligent agent, a plurality of candidate task performers based on the split plurality of groups in batches, and a second task performer determination module configured to determine the task performer associated with the target task from the plurality of candidate task performers.

[0065] FIG. 6 shows a block diagram of an electronic device 600 according to certain embodiments of the present disclosure. The device 600 can be a device or apparatus described in embodiments of the present disclosure. As shown in FIG. 6, the device 600 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 or loaded from a storage unit 606 into a random access memory (RAM) 603. Various programs and data required for operation of the device 600 can also be stored in the RAM 603. The CPU / GPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604. Although not shown in FIG. 6, the device 600 can also include a coprocessor.

[0066] A plurality of components in the device 600 are connected to the I / O interface 605, including an input unit 606 such as a keyboard, a mouse, etc., an output unit 607 such as various types of displays, a speaker, etc., a storage unit 608 such as a magnetic disk, an optical disk, etc., and a communication unit 609 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0067] The various methods or processes described above can be performed by the CPU / GPU 601. For example, in some embodiments, a method can be implemented as a computer software program tangibly embodied in a machine readable medium, such as the storage 608. In some embodiments, portions of the computer program or all of the computer program can be loaded onto the device 600 via the ROM 602 and / or the communications unit 609. When a computer program is loaded onto the RAM 603 and executed by the CPU / GPU 601, one or more steps or actions of the methods or processes described above can be performed.

[0068] In some embodiments, the methods and processes described above can be tied to a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions tangibly embodied therein.

[0069] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or punched tape, a

[0070] The computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0071] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including object oriented programming languages and conventional procedural programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0072] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0073] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0074] The computer program product of the second aspect can include a computer readable storage medium. The computer readable storage medium can include instructions. The instructions can include one or both of: instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data; and instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data.

[0075] Embodiments of the present disclosure have been described above, with the understanding that these embodiments are exemplary only, and are not restrictive, and are not limited to the disclosed embodiments. Many modifications and changes to the described embodiments are possible, without departing from the scope and spirit of the described embodiments. The selection of terms to be used herein is intended to best explain the principles of the embodiments, practical application, or technical improvement over the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1.A method for task assignment, comprising: generating a thought chain related to a target task based on a description of the target task and information of a plurality of task performers; determining, by a task processing model, a task performer associated with the target task from the plurality of task performers based on the thought chain; and assigning the target task to the determined task performer. 2.The method of claim 1, wherein generating a thought chain related to a target task based on a description of the target task and information of a plurality of task performers comprises: acquiring the information of the plurality of task performers from a long-term memory of a storage; acquiring error feedback from a short-term memory of the storage, the error feedback comprising at least an error execution result and an error reason; and generating, by a planning component of an intelligent agent, the thought chain based on the information, the description, and the error feedback. 3.The method of claim 2, wherein the intelligent agent is configured with the task processing model, and wherein determining, by a task processing model, a task performer associated with the target task from the plurality of task performers based on the thought chain comprises: determining, by the task processing model, the task performer associated with the target task based on the thought chain. 4.The method of claim 3, wherein determining, by a task processing model, a task performer associated with the target task from the plurality of task performers comprises: in response to the target task being a predetermined task, determining, by the task processing model, the task performer associated with the target task based on the thought chain and a determination reason. 5.The method of claim 4, wherein assigning the target task to the determined task performer comprises: acquiring a labeling result of the target task by the determined task performer; and determining a feedback for the labeling result based on the labeling result and storing the feedback to the short-term memory. 6.The method of claim 5, wherein determining a feedback for the labeling result based on the labeling result comprises: sampling the labeling result according to a predetermined proportion; generating the feedback based on the determination reason; and adjusting parameters of the task processing model based on the feedback. 7.The method of claim 6, further comprising: in response to the labeling result being inconsistent with a quality-assured labeling result, updating error feedback to the planning component of the intelligent agent. 8.The method of claim 1, further comprising: storing pre-processed data in a uniform format to a storage of an intelligent agent, the pre-processed data comprising at least the information of the task performers and the description. 9.The method of claim 8, further comprising: in response to a database expiration time length of the storage satisfying a first time length condition, determining the storage as a long-term memory; and in response to the database expiration time length satisfying a second time length condition, determining the storage as a short-term memory. 10.The method of claim 8, wherein generating the thought chain related to the target task based on the description of the target task and the information of the plurality of task performers comprises: generating a plurality of discrete features for the plurality of task performers based on the information of the plurality of task performers; and converting the plurality of discrete features for the plurality of task performers into a plurality of textual descriptions. 11.The method of claim 1, further comprising: splitting the plurality of task performers into a plurality of groups in a unit number in response to a number of the plurality of task performers reaching a first predetermined number; determining a plurality of candidate task performers based on the plurality of split groups by the agent in batches; and determining the task performer associated with the target task from the plurality of candidate task performers. 12.An apparatus for allocating a task, comprising: a thought chain generating module configured to generate a thought chain related to a target task based on a description of the target task and information of a plurality of task performers; a task performer determining module configured to determine a task performer associated with the target task from the plurality of task performers based on the thought chain by a task processing model; and a target task allocating module configured to allocate the target task to the determined task performer. 13.An electronic device, comprising: a processor; and a memory coupled with the processor, the memory having stored therein instructions that, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1 to 11. 14.A computer readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 11. 15.A computer program product tangibly stored on a non-transitory computer readable medium and comprising computer-executable instructions that, when executed, cause a computer to perform steps of the method according to any one of claims 1 to 11. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​

Images