Task processing method and device, electronic equipment and storage medium

Through the construction of the digital human platform and the application of large language models, the limitations of digital humans handling complex tasks are solved, automatic decomposition and collaborative work of tasks are realized, and task completion efficiency and application areas are improved.

CN119067419AInactive Publication Date: 2024-12-03CHENGDU MINGTU TECH CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411578762.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-07
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing digital people can only complete simple tasks, have great application limitations, are difficult to handle complex tasks, and lack efficient task decomposition and collaboration mechanisms.

Method used

By building a digital person platform, using large language models and intention recognition models, decompose tasks based on the job characteristics and work ability of digital persons, and realize collaborative work between multiple digital persons, automatically decompose and assign tasks, ensuring the smoothness of complex projects Finish.

Benefits of technology

It realizes that digital people automatically decompose and collaborate on completing complex tasks without manual participation, improve task completion efficiency and application areas, and save manual time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067419A_ABST
    Figure CN119067419A_ABST
Patent Text Reader

Abstract

The invention relates to the field of digital people, and discloses a task processing method and device, electronic equipment and a storage medium. The method applied to a digital person platform side comprises the following steps: obtaining a to-be-executed item and characteristics of a digital person executing the to-be-executed item, wherein the characteristics of the digital person comprise post characteristics of the digital person; decomposing the to-be-executed item according to the characteristics to obtain a decomposition task; and sending the decomposition task to the digital person with the corresponding feature. In this way, a digital human platform capable of enabling a plurality of digital humans to interact is constructed. The digital person platform gathers a plurality of digital persons, decomposes a project according to post features of the digital persons, sends decomposed tasks to the corresponding skilled digital persons, and can cooperate with the plurality of digital persons to complete one project, so that even a relatively complex project can be completed by the digital persons automatically, thereby saving labor time and improving project efficiency. And the project completion efficiency is accelerated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of digital humans, and in particular to a method and device for processing tasks, an electronic device, and a storage medium. Background Art

[0002] At present, with the rapid development of artificial intelligence, a new technology called digital human has emerged. Digital human is an intelligent entity that can achieve goals autonomously and has the ability to plan and execute. Without human intervention, digital human can make plans and complete specific tasks by itself. For example, digital human can judge whether the call process is professional, and if it is not professional, what non-compliant areas exist. However, a single digital human can only complete simple tasks, while actual tasks are often very complex, which makes the application of digital human very limited.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] The embodiments of the present application provide a method and device for processing tasks, an electronic device, and a storage medium, so as to enable a digital human to participate in more tasks and expand the application of the digital human.

[0006] An embodiment of the present application provides a method for processing tasks, which is applied to a digital human platform. The method includes: obtaining features of a project to be executed and a digital human who executes the project to be executed, wherein the features of the digital human include job features of the digital human; decomposing the project to be executed according to the features to obtain decomposed tasks; and sending the decomposed tasks to the digital human with corresponding features.

[0007] In the above implementation, a digital human platform that enables multiple digital humans to interact is constructed. The digital human platform brings together multiple digital humans, decomposes the project according to the job characteristics of the digital humans, and sends the decomposed tasks to the corresponding digital humans who are good at them. It is possible to coordinate multiple digital humans to complete a project, so that even a relatively complex project can be completed automatically by digital humans, thereby saving manual time and speeding up the efficiency of completing the project.

[0008] Furthermore, decomposing the items to be executed according to the features to obtain decomposed tasks includes: combining the features of the digital human, the items to be executed and a first preset prompt template to obtain information to be input; the first preset prompt template is used to describe decomposing the items to be executed into multiple decomposed tasks according to the features of the digital human; inputting the information to be input into a preset large language model to obtain decomposed tasks corresponding to the features of each of the digital humans.

[0009] In the above implementation, the large language model has the ability to understand and generate text. After training, the large language model can understand what content needs to be completed in the project to be executed, and automatically split the project to be executed to obtain decomposed tasks. In this way, the project to be executed can be automatically decomposed without human intervention.

[0010] Furthermore, the method for processing tasks also includes: obtaining question information from a digital person; sending the question information to a target digital person, triggering the target digital person to reply to the question information; the target digital person is the digital person who executes the project to be executed.

[0011] In the above implementation, by receiving the question information of the digital human and sending the question information to the corresponding digital human to trigger the corresponding digital human to reply, multiple digital humans can interact with each other without human participation, thereby realizing collaborative work among multiple digital humans.

[0012] Furthermore, sending the question information to a target digital person includes: when the question information includes a target digital person who specifies an answer, sending the question information to the target digital person who specifies an answer; when the question information does not include a target digital person who specifies an answer, sending the question information to a preset target digital person.

[0013] In the above implementation, according to the content of different question information, the question information is sent to the corresponding digital human, which can facilitate the digital human to obtain corresponding replies from specific digital human, which is conducive to speeding up the efficiency of communication and making the experience of using digital human for interaction better.

[0014] An embodiment of the present application provides a method for processing tasks, which is applied to a digital human. The method includes: receiving a decomposed task; obtaining the working ability of the digital human; determining whether the digital human can execute the decomposed task based on the working ability; and feeding back execution information to a digital human platform based on whether the decomposed task can be executed.

[0015] In the embodiment of the present application, the digital human is constructed by the user according to his / her own user portrait, that is to say, different digital humans will have different knowledge and abilities. When a decomposition task is assigned to a digital human, the digital human may not necessarily be able to complete the decomposition task. Therefore, after receiving the decomposition task, the digital human needs to determine whether it can complete the decomposition task according to its own ability, and feedback the execution information, so that the users corresponding to other digital humans can quickly grasp the situation of the entire project, so that the project can be successfully completed.

[0016] Furthermore, determining whether the digital human can perform the decomposed task based on the working ability includes: using a preset intention recognition model to identify alternative capabilities corresponding to the decomposed task; if the alternative capabilities exist in the working ability of the digital human, determining that the digital human can perform the decomposed task; otherwise, determining that the digital human cannot perform the decomposed task.

[0017] In the embodiment of the present application, the capabilities required for the decomposition task can be automatically identified through the intention recognition model, so that it can be automatically determined whether the digital human can complete the corresponding decomposition task based on the capabilities of the digital human and the identified capabilities.

[0018] Furthermore, execution information is fed back to the digital human platform based on whether the decomposed task can be executed, including: if the decomposed task can be executed, executing the decomposed task, and feeding back the completion status of the decomposed task to the digital human platform as the execution information; and / or, if the decomposed task cannot be executed, feeding back the inability to execute the decomposed task as the execution information to the digital human platform.

[0019] In the above implementation, the execution status of each part of the overall project can be understood by sending different execution situations to the digital human platform, so as to facilitate the adjustment of the distribution of decomposed tasks to ensure that the project can be completed.

[0020] Furthermore, the method for processing tasks also includes: when the decomposed task cannot be executed, obtaining the working ability of the target digital human; determining the alternative digital human corresponding to the decomposed task based on the working ability; the alternative digital human is one of the target digital humans; and recommending the alternative digital human to execute the decomposed task as the execution information to the digital human platform.

[0021] In the above implementation, by recommending other digital humans to perform the decomposed tasks when the corresponding decomposed tasks cannot be performed, it is possible to facilitate digital humans to complete all decomposed tasks, thereby enabling the overall project to be completed smoothly.

[0022] The embodiment of the present application provides a device for processing tasks, which is applied to a digital human platform, and the device includes: a first acquisition module, which is used to obtain the characteristics of the project to be executed and the digital human who executes the project to be executed, and the characteristics of the digital human include the job characteristics of the digital human; a decomposition module, which is used to decompose the project to be executed according to the characteristics to obtain the decomposed tasks; an execution module, which is used to send the decomposed tasks to the digital human with corresponding characteristics, and receive the feedback results of the digital human on the decomposed tasks.

[0023] The embodiment of the present application provides a device for processing tasks, which is applied to a digital human. The device includes: a receiving module, which is used to receive a decomposed task; a second acquisition module, which is used to acquire the working ability of the digital human; a determination module, which is used to determine whether the digital human can execute the decomposed task according to the working ability; and a feedback module, which is used to feedback execution information to the digital human platform according to whether the decomposed task can be executed.

[0024] An embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method for processing the above-mentioned task.

[0025] An embodiment of the present application provides a storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions enable the processor to implement the method for processing the above-mentioned task.

[0026] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] One or more embodiments are exemplarily described by corresponding drawings, and these exemplary descriptions and drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are considered similar elements, and the drawings do not constitute a scale limitation, and wherein: Figure 1 is a schematic diagram of a method for processing tasks provided in an embodiment of the present application; Figure 2 is a schematic diagram of another method for processing tasks provided in an embodiment of the present application; Figure 3 This is a schematic diagram of an interface of a project group provided in an embodiment of the present application; Figure 4 is a schematic diagram of a device for processing tasks provided in an embodiment of the present application; Figure 5 is a schematic diagram of another device for processing tasks provided in an embodiment of the present application; Figure 6 It is a schematic diagram of an electronic device provided in an embodiment of the present application.

[0028] Reference numerals: 1: first acquisition module; 2: decomposition module; 3: execution module; 4: receiving module; 5: second acquisition module; 6: determination module; 7: feedback module; 8: communication interface; 9: bus; 10: processor; 11: memory. DETAILED DESCRIPTION

[0029] In order to be able to understand the features and technical contents of the embodiments of the present application in more detail, the implementation of the embodiments of the present application is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present application. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0030] The terms "first", "second", etc. in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present application described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0031] Unless otherwise stated, the term "plurality" means two or more.

[0032] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0033] In some embodiments, the digital human platform is a platform for multiple digital humans to interact. The digital human platform can be set on a computer or server. The digital human platform and the digital humans can communicate via HTTP (Hypertext Transfer Protocol).

[0034] In some embodiments, in response to a user's creation instruction, a digital person is created on the digital person platform. The creation instruction includes the job position of the digital person being created. In response to the user's document upload instruction, the document is uploaded to the digital person's knowledge management library. Among them, documents representing the user's behavior data can be uploaded. Among them, the behavior data, for example: browsing history, purchase records, click behavior, interaction records, etc. It is also possible to upload documents representing the knowledge possessed by the user, such as: books that the user has studied. Of course, it can also be other documents, such as: documents on the work status sorted out by the user himself. Or, logs written by the user himself, etc.

[0035] The created digital human can obtain the document content of the knowledge management library for intelligent learning, so that the image of the created digital human is more suitable for the user, and the created digital human can automatically answer questions or perform tasks according to the document content of the knowledge management library. It can be understood that in addition to the documents uploaded by the user, the digital human can also learn the knowledge provided by the digital human platform. Alternatively, the digital human can directly obtain public knowledge from the Internet for learning.

[0036] In the above embodiment, the document upload instruction also includes a document tag. The document tag is used to refer to the role that the document can be used for display. For example: if the document is tagged as a colleague, the document content can only be displayed to the digital person representing the colleague. If the document is tagged as a friend, the document content can only be displayed to the digital person representing the friend.

[0037] Embodiment 1 The present application provides a method for processing tasks, which is applied to the digital human platform. Figure 1 As shown, Figure 1 A flowchart of a method for processing a task provided in an embodiment of the present application includes: Step S101, obtaining the features of the project to be executed and the digital human executing the project to be executed.

[0038] Among them, the characteristics of digital people include the job characteristics of digital people. It can be understood that the job characteristics can be the job position of the digital person, or the job position and job responsibilities of the digital person.

[0039] For example, job positions include teacher, engineer, marketing specialist, etc. Job responsibilities include, for example, understanding the characteristics of the company's products, formulating product promotion strategies and sales support plans.

[0040] It can be understood that the characteristics of digital humans can also include: learning characteristics, life characteristics, health characteristics, social characteristics, etc. Among them, learning characteristics, for example: liking literary readings, liking popular science knowledge, etc. Life characteristics, for example: watching short videos at night, reading in the morning, etc. Health characteristics, for example: no disease, high blood pressure, etc. Social characteristics, for example: telephone social networking, network social networking, etc. Various characteristics can be defined by the user when creating a digital human, or the digital human can extract various characteristics from the document content of the knowledge management library.

[0041] Among them, the pending projects can be projects that need to be completed in the Digital Human Platform. The pending projects can be uploaded to the Digital Human Platform by the users themselves. For example, the pending projects can be the development of an education platform, which can be decomposed into multiple tasks, such as the interface design of the education platform, the function realization of the education platform, and the function testing of the education platform.

[0042] In some embodiments, a user may create a project group on the Digital Human Platform. In this case, the Digital Human who created the project group will be directly located in the project group. The remaining Digital Humans are then dragged into the project group. Then, the user associates the project to be executed with the project group. At this point, all Digital Humans in the project group are Digital Humans who execute the project to be executed. At this point, the Digital Human who created the project group is the administrator of the project group.

[0043] For example, the to-be-executed projects can be displayed on a preset display interface, and the user clicks on the to-be-executed projects and project groups to achieve association between the to-be-executed projects and project groups. The preset display interface can be a display screen of a computer.

[0044] Step S102, decomposing the items to be executed according to the features to obtain decomposed tasks.

[0045] In some embodiments, step S102 may include: combining the characteristics of the digital human, the project to be executed and the first preset prompt template to obtain information to be input; the first preset prompt template is used to describe decomposing the project to be executed into multiple decomposed tasks according to the characteristics of the digital human; inputting the information to be input into the preset large language model to obtain the decomposed tasks corresponding to the characteristics of each digital human.

[0046] Among them, a large language model, such as ChatGPT (a chatbot program), can be trained by collecting many projects and the sub-projects of each project. The large language model can be decomposed into projects based on the decomposition logic of various projects.

[0047] Exemplarily, the characteristics of the digital person, the project to be executed and the first preset prompt template are combined, that is, the characteristics of the digital person are filled in the place where the characteristics are described in the first preset prompt template, and the project to be executed is filled in the place where the project to be executed is described in the first preset prompt template. The first preset prompt template, for example: please decompose the project "to be filled in and to be executed" into multiple decomposed tasks according to the following characteristics "characteristics to be filled in". Assume that the characteristics of the digital person are front-end positions and back-end positions. The project to be executed is a project to develop an education platform. After the characteristics of the digital person, the project to be executed and the first preset prompt template are combined, the information to be input is obtained, for example: please decompose the project "development of an education platform" into multiple decomposed tasks according to the following characteristics "front-end positions" and "back-end positions". The information to be input is input into the preset large language model to obtain decomposed tasks such as: designing the display interface of the education platform and designing the workflow of the functional modules of the education platform.

[0048] Step S103, sending the decomposition task to the digital human with corresponding characteristics.

[0049] It can be understood that the large language model decomposes the project to be executed according to the job characteristics, and can decompose it into N decomposition tasks, where the number N is less than or equal to the number of digital people executing the project to be executed.

[0050] In some embodiments, the method for processing a task further includes: obtaining question information from a digital person; sending the question information to a target digital person, triggering the target digital person to reply to the question information; the target digital person is the digital person who executes the project to be executed. In this way, the user triggers the digital person representing himself to ask questions to other digital people, and the other digital people answer. The user who asks the question can directly obtain the corresponding reply without the user being asked participating in the answer. This can save the time for the user who asks the question to obtain the reply, and also save the time for the user being asked to answer.

[0051] The digital person asking the question may be a digital person executing the project to be executed. The question sent to the target digital person may be one or more digital persons executing the project to be executed.

[0052] In the above embodiment, obtaining the question information of the digital human may be: obtaining the sending information sent by the digital human to the digital human platform. Using a preset question recognition model, determining whether the sending information includes a question. If the sending information includes a question, determining that the sending information is a question information.

[0053] The information sent by the digital human to the digital human platform can be information sent by the user operating the digital human, or information sent by the digital human when replying to other digital human’s question information. It can also be execution information of the digital human’s feedback after executing the decomposed task.

[0054] Wherein, determining whether the sent information includes a question by using a preset question recognition model may include: determining whether the sent information includes a target digital person who specifies an answer. If the sent information includes a target digital person who specifies an answer, the sent information is determined to be a question. If the sent information does not include a target digital person who specifies an answer, determining whether the sent information includes a question by using a preset question recognition model.

[0055] It is understandable that the question recognition model can be obtained by the following method: inputting the text with whether the question label is included into a preset first training model for training to obtain the question recognition model. The preset first training model can be a neural network model, or other models that can be trained to perform question recognition.

[0056] In the above embodiment, sending the question information to the target digital person includes: when the question information includes a target digital person who specifies the answer, sending the question information to the target digital person who specifies the answer; when the question information does not include a target digital person who specifies the answer, sending the question information to the preset target digital person.

[0057] The designated answer can be represented by a designated symbol, for example, when the @ symbol appears in the question information, the target digital person following the @ symbol is the target digital person for the designated answer. Alternatively, the target digital person for the designated answer can be directly indicated in the question information, for example, please ask digital person D to reply to the current work progress. In this case, digital person D is the target digital person for the designated answer.

[0058] It is understood that the user can set in advance in the project group which one or several target digital people will respond if the question information does not include a target digital person to answer. For example, the administrator can be set as the preset target digital person. Then, if the digital person in the project group sends a question information and does not specify a target digital person to answer, the administrator will answer the question information.

[0059] Exemplarily, there are digital humans A, B and C in the project group of the project to be executed. Among them, digital human B is an administrator. Assume that the preset target digital human is the administrator. The user operates digital human A to send a message "Please introduce the large language model." The question recognition model determines that the message contains a question, the message is a question message, and the question message does not specify a target digital human to answer. At this time, digital human B answers the question message. Assume that the user operates digital human C to send a message "Please introduce the large language model, @digital human A". At this time, digital human A is specified in the message, and at this time, digital human A answers the question message.

[0060] In some embodiments, the digital person who receives the question information will reply to the question information. Wherein, if the digital person who receives the question information cannot answer the question information, the digital person can recommend other target digital persons to reply.

[0061] The recommended target digital person can be determined by: using a preset position matching recognition model to identify the question information, and obtaining the expected consulting position corresponding to the question information. The target digital person with the same or similar position as the expected consulting position is used as the recommended digital person.

[0062] It can be understood that the position matching recognition model can be obtained in the following manner: input the text with the expected consulting position label into the preset second training model for training to obtain the position matching recognition model. The preset second training model can be a neural network model, or other models that can be trained to identify consulting positions. In this way, there may be a situation where the user asks an inappropriate question to the object. By having the digital person who receives the question information recommend a suitable target digital person to answer, the efficiency of the interaction can be improved.

[0063] In some embodiments, before replying to a question, the digital person can identify the role tag of the digital person who sent the question and reply using the content of the document corresponding to the document tag that is the same as the role tag. It can be understood that the role tag of the digital person is the relationship between digital persons, such as colleagues, friends, etc.

[0064] Embodiment 2 The present application provides a method for processing tasks, which is applied to digital humans. Figure 2 As shown, Figure 2 A flowchart of a method for processing a task provided in an embodiment of the present application includes: Step S201, receiving a decomposed task.

[0065] It can be understood that decomposed tasks are tasks after the project to be executed is decomposed.

[0066] Step S202, obtaining the working ability of the digital human.

[0067] The working ability can be pre-set by the user when setting up the digital human, or can be identified by the digital human based on the knowledge management library.

[0068] It can be understood that work capability is a set of skills or permissions that a user needs to complete a specific work task. For example, work capability can be one or more of software operation capability, professional skills, collaboration capability, and any other specific capabilities related to job responsibilities. Among them, software operation capability, for example, using Excel (spreadsheet) to perform complex data pivoting. Professional skills, for example, financial analysis. Collaboration capability, for example, cross-departmental communication and coordination.

[0069] Step S203, determining whether the digital human can perform the decomposed task according to the working ability.

[0070] In some embodiments, step S203 may be: using a preset intention recognition model to identify alternative capabilities corresponding to the decomposition task; if there are alternative capabilities in the digital human's working capabilities, determining that the digital human can perform the decomposition task; otherwise, determining that the digital human cannot perform the decomposition task.

[0071] The intent recognition model can be integrated into the digital human, or the digital human platform can be equipped with the intent recognition model, which can be implemented by the digital human calling the intent recognition model of the digital human platform. For example, assuming that a decomposition task is a project report, the alternative capabilities corresponding to the decomposition task identified by the intent recognition model may involve document writing, PPT (slide) production, data visualization, etc.

[0072] It can be understood that sample tasks can be obtained, and the sample tasks with intent labels can be input into a preset natural language model for training to obtain an intent recognition model.

[0073] Step S204: Feedback execution information to the digital human platform based on whether the decomposed task can be executed.

[0074] In some embodiments, step S204 may include: if the decomposed task can be executed, executing the decomposed task, and sending the completion status of the decomposed task to the digital human platform as execution information. And / or, if the decomposed task cannot be executed, feeding back the inability to execute the decomposed task as execution information to the digital human platform.

[0075] For example, assume that the decomposition task assigned to the digital human is to write a project establishment report. The digital human will bring in the basic project knowledge related to the project to be executed in the knowledge management library, and enable AI (Artificial Intelligence) writing capabilities, for example: calling a preset writing template to produce a project establishment report. After the project establishment report is completed, the project establishment report is fed back to the digital human platform as execution information.

[0076] In some embodiments, step S204 may also include: when the decomposed task cannot be performed, obtaining the working ability of the target digital human; determining the alternative digital human corresponding to the decomposed task according to the working ability; the alternative digital human is one of the target digital humans; and recommending the alternative digital human to perform the decomposed task as execution information to the digital human platform.

[0077] In the above embodiment, determining the candidate digital humans corresponding to the decomposed tasks according to the work capabilities may be to determine the target digital humans whose work capabilities include the alternative capabilities as the candidate digital humans.

[0078] It can be understood that the execution information belongs to the information sent by the digital human to the digital human platform. Therefore, the information will be identified according to the logic in the first embodiment to confirm whether it is a question information. If it is a question information, it will be sent to the target digital human according to the question information. No further details will be given here.

[0079] Exemplarily, a user creates a digital person representing himself on the digital person platform. Meanwhile, multiple projects are pre-set on the digital person platform. One of the users creates a project group on the digital person platform, and then the user selects the project to be executed as the to-be-executed project and associates it with the project group, and pulls the remaining digital people related to the to-be-executed project into the project group. The digital person platform obtains the characteristics of the digital people in the project group. And decomposes the to-be-executed project into multiple decomposition tasks according to the characteristics of the digital people. And sends the decomposition tasks to the digital people with corresponding characteristics. After receiving the corresponding decomposition tasks, the digital people judge whether the decomposition tasks can be completed according to the working ability of the digital people themselves. If they can be completed, the digital people themselves perform the decomposition tasks and feedback the completion of the decomposition tasks. If they cannot be completed, the digital people can check whether there are alternative digital people with matching capabilities according to the working abilities of other digital people in the project group. And recommend the alternative digital people to perform the decomposition tasks. During the entire project completion process, the user can operate the digital people to ask questions, and the corresponding digital people will reply to them, so as to keep abreast of the progress of the to-be-executed projects. At this time, the digital people directly reply to the question information, without the need for the user who created the digital person who replied to the question to answer. Ability to save time for users who create digital humans that respond to questions.

[0080] Exemplary, combined Figure 3 As shown, Figure 3 The following is a schematic diagram of the project group interface. Figure 3As shown, the project group is the Digital Human Product Department. The avatar of the digital human created by the user is displayed on the left end of the display interface, and the basic information of the project group, such as group member information, group name, etc., is displayed on the right end of the display interface. The communication process of each digital human is displayed in the middle of the display interface. For example: Digital A@Digital Human B to answer questions. Digital Human B cannot answer the question, so Digital Human B replies that it cannot answer the question temporarily and recommends Digital Human C to answer. Digital Human C can answer the question and directly responds to the question. At the bottom of the communication process, there is also an input box, in which the user can enter text to trigger the digital human representing the user to send a message. At the same time, prompt information is also set in the input box, for example: enter the content you want to know.

[0081] It can be understood that in the process of the digital human executing the pending project, the user can continuously update the knowledge management library of the digital human so that the digital human can better complete the decomposed tasks corresponding to the pending project.

[0082] Embodiment 3 Based on the same inventive concept, the present application embodiment provides a task processing device, which is applied to the digital human platform. Figure 4 As shown, the device for processing tasks includes: a first acquisition module 1, a decomposition module 2 and an execution module 3. The first acquisition module 1 is used to obtain the features of the project to be executed and the digital person who executes the project to be executed, and the features of the digital person include the job features of the digital person; the decomposition module 2 is used to decompose the project to be executed according to the features to obtain the decomposed tasks; the execution module 3 is used to send the decomposed tasks to the digital person with the corresponding features, and receive the feedback results of the digital person on the decomposed tasks.

[0083] In some embodiments, the decomposition module 2 is used to decompose the items to be executed according to the characteristics to obtain the decomposition tasks in the following manner: the characteristics of the digital person, the items to be executed and the first preset prompt template are combined to obtain the information to be input; the first preset prompt template is used to describe the decomposition of the items to be executed into multiple decomposition tasks according to the characteristics of the digital person; the information to be input is input into the preset large language model to obtain the decomposition tasks corresponding to the characteristics of each digital person.

[0084] In some embodiments, the device for processing tasks also includes: a question collaboration device, used to obtain question information from a digital person; send the question information to a target digital person, triggering the target digital person to reply to the question information; the target digital person is the digital person who executes the project to be executed.

[0085] In some embodiments, the question collaboration device is used to send the question information to the target digital person in the following manner: when the question information includes a target digital person with a specified answer, the question information is sent to the target digital person with the specified answer; when the question information does not include a target digital person with a specified answer, the question information is sent to a preset target digital person.

[0086] It can be understood that the various embodiments described in the first embodiment are also applicable to the third embodiment if there is no conflict. Based on the consideration of brevity of description, they will not be repeated here.

[0087] Embodiment 4 Based on the same inventive concept, the present application embodiment provides a task processing device, which is applied to a digital human. Figure 5 As shown, the device for processing tasks includes: a receiving module 4, a second acquisition module 5, a determination module 6 and a feedback module 7. The receiving module 4 is used to receive the decomposed task; the second acquisition module 5 is used to obtain the working ability of the digital human; the determination module 6 is used to determine whether the digital human can perform the decomposed task according to the working ability; the feedback module 7 is used to feedback the execution information to the digital human platform according to whether the decomposed task can be executed.

[0088] In some embodiments, the determination module 6 is used to determine whether the digital human can perform the decomposition task according to the working ability in the following manner: using a preset intention recognition model to identify alternative abilities corresponding to the decomposition task; if there are alternative abilities in the working ability of the digital human, determining that the digital human can perform the decomposition task; otherwise, determining that the digital human cannot perform the decomposition task.

[0089] In some embodiments, the feedback module 7 is used to feedback execution information to the digital human platform according to whether the decomposed task can be executed in the following manner: if the decomposed task can be executed, the decomposed task is executed, and the completion status of the decomposed task is given to the digital human platform as execution information; and / or, if the decomposed task cannot be executed, the inability to execute the decomposed task is fed back to the digital human platform as execution information.

[0090] In some embodiments, the feedback module 7 is also used to obtain the work ability of the target digital human when the decomposition task cannot be performed; determine the alternative digital human corresponding to the decomposition task according to the work ability; the alternative digital human is one of the target digital humans; and recommend the alternative digital human to perform the decomposition task as execution information to the digital human platform.

[0091] It can be understood that the various embodiments described in the second embodiment are also applicable to the fourth embodiment if there is no conflict. Based on the consideration of brevity of description, they will not be repeated here.

[0092] Combination Figure 6As shown, an embodiment of the present application provides an electronic device, including a processor 10 and a memory 11. Optionally, the device may also include a communication interface 8 and a bus 9. The processor 10, the communication interface 8, and the memory 11 may communicate with each other through the bus 9. The communication interface 8 may be used for information transmission. The processor 10 may call the logic instructions in the memory 11 to execute the method for processing tasks in the above embodiment.

[0093] In addition, the logic instructions in the above-mentioned memory 11 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0094] The memory 11 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 10 executes functional applications and data processing by running the program instructions / modules stored in the memory 11, that is, implementing the method for processing tasks in the above embodiments.

[0095] The memory 11 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 11 may include a high-speed random access memory and may also include a non-volatile memory.

[0096] The electronic device may be a computer or a server, etc.

[0097] An embodiment of the present application provides a storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the method for executing the above-mentioned processing task.

[0098] An embodiment of the present application provides a computer program product, which includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is caused to perform the method for processing the above-mentioned task.

[0099] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0100] The technical solution of the embodiment of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for 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 method described in the embodiment of the present application. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0101] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0102] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. At the same time, the above embodiments can be combined with each other to form new embodiments without conflict.

Claims

1. A method for processing a task, characterized in that: Applied to a digital human platform, the digital human platform is a platform for multiple digital humans to interact; the method comprises: Acquire the project to be executed and the characteristics of the digital person who executes the project to be executed, wherein the characteristics of the digital person include the job characteristics of the digital person; Decompose the items to be executed according to the characteristics to obtain decomposed tasks; The decomposed task is sent to the digital human with corresponding features.

2. The method according to claim 1, characterized in that Decomposing the items to be executed according to the features to obtain decomposed tasks includes: The characteristics of the digital human, the project to be executed and a first preset prompt template are combined to obtain information to be input; the first preset prompt template is used to describe decomposing the project to be executed into multiple decomposed tasks according to the characteristics of the digital human; The information to be input is input into a preset large language model to obtain decomposition tasks corresponding to the features of each digital human.

3. The method according to claim 1, characterized in that The method further comprises: Get the question information of the digital person; The question information is sent to a target digital person, triggering the target digital person to reply to the question information; the target digital person is the digital person who executes the project to be executed.

4. The method according to claim 3, characterized in that Sending the question information to the target digital person includes: In the case where the question information includes a target digital person specifying an answer, sending the question information to the target digital person specifying an answer; In the case that the question information does not include a target digital person specifying an answer, the question information is sent to a preset target digital person.

5. A method for processing a task, characterized in that: Applied to digital humans, the method comprises: Receive decomposition tasks; Obtaining the working capabilities of the digital human; Determining whether the digital human can perform the decomposed task according to the working ability; Feedback execution information to the digital human platform based on whether the decomposed task can be executed.

6. The method according to claim 5, characterized in that Determining whether the digital human can perform the decomposed task according to the working ability includes: Using a preset intention recognition model to identify alternative capabilities corresponding to the decomposed task; In the case where the alternative capability exists in the working capability of the digital human, it is determined that the digital human can perform the decomposed task; otherwise, it is determined that the digital human cannot perform the decomposed task.

7. The method according to claim 5, characterized in that Feedback execution information to the digital human platform based on whether the decomposed task can be executed includes: If the decomposed task can be executed, execute the decomposed task and send the completion status of the decomposed task as the execution information to the digital human platform; and / or, In the case where the decomposed task cannot be executed, the inability to execute the decomposed task will be fed back to the digital human platform as the execution information.

8. The method according to claim 7, characterized in that The method further comprises: In the case where the decomposed task cannot be performed, obtaining the working ability of the target digital human; Determine the candidate digital person corresponding to the decomposed task according to the work capability; the candidate digital person is one of the target digital people; The alternative digital human is recommended to perform the decomposed task as the execution information to the digital human platform.

9. A device for processing tasks, characterized in that: Applied to a digital human platform, the digital human platform is a platform for multiple digital humans to interact; the device includes: A first acquisition module is used to acquire the project to be executed and the characteristics of the digital person who executes the project to be executed, wherein the characteristics of the digital person include the position characteristics of the digital person; A decomposition module, used for decomposing the items to be executed according to the features to obtain decomposed tasks; An execution module is used to send the decomposition task to the digital human with corresponding characteristics, and receive feedback results of the digital human on the decomposition task.

10. A device for processing tasks, characterized in that: Applied to digital human, the device comprises: A receiving module, used for receiving decomposed tasks; A second acquisition module, used to acquire the working ability of the digital human; A determination module, used to determine whether the digital human can perform the decomposed task according to the working ability; The feedback module is used to feed back execution information to the digital human platform based on whether the decomposed task can be executed.

11. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method for processing tasks as claimed in any one of claims 1 to 8.

12. A storage medium, characterized in that: The storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions enable the processor to implement the method for processing tasks described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Robot scheduling method, electronic equipment and computer readable storage medium

    CN110270998A

  • Cluster robot scheduling method, device, system and equipment and computer readable storage medium

    CN111079990A

  • Process task execution control method, device and equipment

    CN113051019A

  • Robot complex operation skill representation method and device, intelligent terminal and medium

    CN114043478A

  • Robot scheduling method, system and equipment and storage medium

    CN114240157A