WO2026000332A1 - 交互方法、电子设备、计算机可读存储介质和产品 - Google Patents

交互方法、电子设备、计算机可读存储介质和产品

Info

Publication number
WO2026000332A1
WO2026000332A1 PCT/CN2024/102294 CN2024102294W WO2026000332A1 WO 2026000332 A1 WO2026000332 A1 WO 2026000332A1 CN 2024102294 W CN2024102294 W CN 2024102294W WO 2026000332 A1 WO2026000332 A1 WO 2026000332A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
user
cycle
sub
message
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/102294
Other languages
English (en)
French (fr)
Inventor
刘思宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Priority to CN202480002209.3A priority Critical patent/CN119213751A/zh
Priority to PCT/CN2024/102294 priority patent/WO2026000332A1/zh
Publication of WO2026000332A1 publication Critical patent/WO2026000332A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
    • H04L51/043—Real-time or near real-time messaging, e.g. instant messaging [IM] using or handling presence information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
    • H04L51/10—Multimedia information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/21—Monitoring or handling of messages
    • H04L51/224—Monitoring or handling of messages providing notification on incoming messages, e.g. pushed notifications of received messages

Definitions

  • This disclosure relates to the field of computer technology, and in particular to an interaction method, electronic device, computer-readable storage medium, and product.
  • users can use various applications on their devices, such as computers, mobile phones, and tablets, for learning or entertainment.
  • users can follow fitness apps to exercise or learn English through language learning apps.
  • Some applications offer practice or learning courses, which users can follow along with.
  • these courses have fixed interaction methods.
  • users can wear wearable devices to perform exercises, and the data collected by the wearable devices reflects the user's practice results.
  • learning courses users can submit forms on designated test pages to provide feedback on their answers.
  • an interaction method comprising: generating a task for a user in each sub-cycle of a cycle based on a task theme; displaying a first message sent by an agent to the user in a dialog interface within each sub-cycle, the first message including the task of the sub-cycle; displaying a second message sent by the user to the agent in the dialog interface, the second message providing feedback on the task of the current sub-cycle; and displaying a third message sent by the agent to the user in the dialog interface in response to the second message, the third message including the user's task progress in the current sub-cycle.
  • an electronic device including: a memory; and a processor coupled to the memory, the processor being configured to perform the methods of any of the embodiments described in the present disclosure based on instructions stored in the memory.
  • a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, performs the methods of any of the embodiments described in the present disclosure.
  • a computer program comprising: instructions that, when executed by a processor, cause the processor to perform the method of any embodiment described in the present disclosure.
  • Figure 1 shows a flowchart illustrating an interaction method according to some embodiments of the present disclosure.
  • Figure 2 shows a flowchart of a task generation method according to some embodiments of the present disclosure.
  • Figure 3 shows a flowchart illustrating a method for determining user basic information according to some embodiments of the present disclosure.
  • Figure 4 shows a flowchart of a task generation method according to other embodiments of the present disclosure.
  • Figure 5 shows a flowchart illustrating a method for determining task progress according to some embodiments of the present disclosure.
  • Figure 6 shows a schematic flowchart of a task adjustment method according to some embodiments of the present disclosure.
  • Figures 7A and 7B show schematic diagrams of dialog interfaces according to some embodiments of the present disclosure.
  • Figure 8 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure.
  • Figure 9 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure.
  • Figure 10 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.
  • the term “comprising” and its variations are open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to”. Furthermore, as used in this disclosure, the term “including” and its variations are open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to”. Therefore, “comprising” and “including” are synonymous.
  • the term “based on” means “at least partially based on”.
  • the terms “one embodiment,” “some embodiments,” or “embodiment” mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; and the term “some embodiments” means “at least some embodiments.”
  • the appearance of the phrases “in one embodiment,” “in some embodiments,” or “in an embodiment” in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.
  • first,” “second,” etc. used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first,” “second,” etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.
  • AI-driven objects can engage in rich interactions with users.
  • intelligent customer service can answer users' questions about products
  • translation assistants can translate the user's input into other languages.
  • user interactions with intelligent agents typically occur within a short, specific timeframe. For example, when a user needs to interact with an intelligent agent, the user finds the agent and sends a message, which the agent then responds to. After the user's question is answered, the user exits the chat interface and actively reopens the chat interface the next time they need the agent. That is, in the current interaction, the intelligent agent remains in a relatively passive state. Some applications may occasionally push messages to users proactively, but this is usually used for news and is not relevant to users' long-term learning plans.
  • embodiments of this disclosure utilize the dialogue function between the user and the intelligent agent to generate and publish tasks, as well as receive user feedback, in order to save users the cost of understanding, operating and executing tasks, and improve the efficiency of task completion and user experience.
  • An intelligent agent is an entity capable of autonomously performing tasks within a specific environment.
  • An intelligent agent can generate corresponding content based on dialogues sent by other subjects in a conversational scenario (such as users or other intelligent agents participating in the dialogue). It can be implemented in software, hardware, or a combination of both.
  • Intelligent agents can also be referred to as digital humans, robots, agents, or virtual proxies of machine learning models. Intelligent agents can be implemented using machine learning models, such as those based on Large Language Models (LLMs) or Foundation Models. Machine learning models can be generative models.
  • Generative models are used to output target content based on input information.
  • the input information includes the processing basis of the generative model during the generation process, such as messages sent by other subjects in the dialogue, requirements for the output content, etc.
  • Generative models include, for example, models that generate text based on text or models that generate images based on images.
  • the output of a generative model can include text, images, or a combination of both.
  • the input or output of a generative model can also be data from other modalities, such as audio, video, or a combination of multiple types of data.
  • Generative models can be single-modal models, such as models that generate text from text (referred to as “text-to-text models”) or models that generate images from images (referred to as “image-to-image models”); or, generative models can be cross-modal models, that is, models whose input and output belong to different modalities, such as models that generate images from text (referred to as “text-to-text models”). (“Text-based graph model”); or, the input of a generative model can include multiple modalities, and the output can also include multiple modalities.
  • Figure 1 shows a flowchart of an interaction method according to some embodiments of the present disclosure. As shown in Figure 1, the interaction method of this embodiment includes steps S102 to S108.
  • step S102 tasks for each sub-cycle in the cycle are generated for the user based on the task topic.
  • a task topic is used to represent the core words, keywords, etc., of the task to be performed.
  • Each task topic can belong to one or more task types, and each task type can include one or more task topics, or one or more subcategories, with each subcategory including one or more task topics.
  • the task type of "learning" can include multiple subcategories such as math learning, English learning, and text learning. In English learning, it can include multiple topics such as English vocabulary, English listening, middle school English, and college English.
  • the task topic can be provided and entered by the user, or the application can provide a specified task topic, or the application can provide one or more candidate topics for the user to select.
  • step S102 is executed in response to a user sending an instruction to the agent to create a task.
  • the user may trigger the task generation process, for example, by sending a message in a dialogue interface with the agent.
  • the agent may automatically execute the task generation process in response to the display of the dialogue interface.
  • An agent can provide a user with one or more specified types of tasks, or one or more specified task topics. That is, when a user wants to create a plan through an agent, they can interact with a specific type of agent. For example, when a user wants to complete a task related to learning English, they can trigger task generation by interacting with the "English learning" agent. Of course, some agents can also support free user input to generate various tasks without requiring the user to search for a dedicated agent.
  • the generated tasks cover a period of a certain length.
  • the length of the period can be specified by the user; for example, if the user sends a message like "I want to create a 20-day plan to learn English," the period length is 20 days.
  • the period length can be a default value; for example, for a task generated during summer vacation, the period can be set to "summer vacation.”
  • the period length can be determined based on the task theme; for example, the agent can determine it by analyzing the periods of historical tasks related to that theme, or based on the characteristics of the task theme. Similar to the period length, the length of sub-periods can also be determined in various ways.
  • the length of a sub-period can be a default value, such as setting a day or a week as a sub-period; or it can be specified by the user or determined by the agent.
  • tasks can be generated using machine learning models, such as generative models.
  • Generative models are used to process task topics, or task topics and user-authorized information, to generate tasks.
  • a pre-set task corresponding to a task topic can be read, and then adjusted based on user-authorized information. This adjustment process can be accomplished using a generative model. That is, the pre-set task and user-authorized information are input into the generative model to obtain the adjusted task.
  • User-authorized information may include, for example, the user's historical dialogue with the agent and basic information publicly available to the user.
  • the generated task includes a description of the task, which may include reference resources needed by the user to perform the task and the execution method for those reference resources.
  • the generated task includes a list of words the user needs to learn each day of the cycle, and instructions for the user to memorize these words.
  • the reference resource is the word list
  • the execution method is memorization.
  • the reference resources may include the words "squat,” “push-ups,” and “stretching,” and may further include specific descriptions of these movements, or instructions for the movements represented by images or videos.
  • the execution method would be performing these movements and the number of repetitions for each movement. For certain categories, if the execution method is very explicit, it may not be required. For example, if the user clearly understands that the current task is vocabulary memorization, only the word list may be displayed. Those skilled in the art can make selections as needed.
  • the task may also include the task feedback method, such as which data format (text, voice, image, video) is used, and the content volume requirements.
  • tasks for each sub-cycle can be saved, for example, on a server or locally on the user's device.
  • the task corresponding to the current sub-cycle is retrieved from the stored data and sent to the user.
  • all tasks within the cycle can be sent to the user for preview, or a summary of all tasks can be sent for preview, or no preview can be sent to the user.
  • step S104 within each sub-cycle, the first message sent by the agent to the user is displayed on the dialogue interface.
  • the first message includes the task of the sub-cycle.
  • the first message may include one or more types of data such as text, sound, image, video, link, or file.
  • the message in the embodiments of this disclosure refers to the dialogue message in the dialogue interface. Messages sent between the agent and the user are displayed in the dialogue interface (also known as the chat interface).
  • the task generated in step S102 can be represented as a message; that is, the generated task can be directly carried and sent to the user via the first message.
  • the generated task can be formatted data, including key task information such as reference resources and execution methods. Then, the front end of an application, such as the application's front end, will format the data... The formatted data is converted into the first message.
  • the agent sends tasks via messages in the dialogue, allowing the user to receive tasks for each sub-cycle in a timely manner, provided the user device grants the agent notification permissions. For example, the user can receive tasks for the current sub-cycle even when not using the user device or when using an application other than the one the agent is using.
  • messages sent by the agent can be tagged with a type, such as task messages or non-task messages, and users can be allowed to set notification permissions for task messages individually. This allows the agent to configure task messages to use notification permissions while non-task messages do not, thus minimizing user disruption while ensuring timely task delivery.
  • the user can interact further with the agent regarding the task in the current sub-cycle through dialogue. For example, in response to a user's question or a desire to adjust the task in the current sub-cycle, the user can send a message to the agent. By semantically understanding the message sent by the user, the agent can send corresponding feedback messages to the user.
  • a day's task might include performing fitness exercise A.
  • a user finds their form incorrect while performing exercise A and cannot correct it themselves, they can send a message to the AI agent requesting more reference videos, or send a video of themselves performing exercise A and ask the AI agent to point out the problems.
  • step S106 a second message sent by the user to the agent is displayed on the dialogue interface.
  • the second message is used to provide feedback on the task of the current sub-cycle.
  • users can send feedback through one or more messages, and can also provide feedback in various data formats such as text, voice, images, videos, and files. Furthermore, if the message sent by the user does not meet the requirements of the task feedback, or if the user needs to provide more detailed information, the intelligent agent can send another message to the user to remind them of the required feedback or the content that needs to be modified. Therefore, providing task feedback through a dialogue interface with the intelligent agent can conveniently and efficiently assist users in providing complete information.
  • semantic analysis can be performed on user-sent messages to determine the relevance of the message content to the task of the current sub-cycle, thereby judging whether the user-sent message is a response to the task.
  • applications typically provide fixed feedback interfaces for users to provide feedback.
  • These feedback interfaces include forms with requirements such as format and word count, and data validation is performed before form submission. If the user... If the information filled in or uploaded does not meet the requirements, submission may fail.
  • the user sends a second message through a dialogue interface to provide feedback on the task, which allows for more flexible and convenient delivery of task feedback results. Even if the feedback does not meet the requirements, the intelligent agent can guide the user to upload compliant information through further dialogue.
  • step S108 in response to the second message, a third message sent by the agent to the user is displayed on the dialog interface.
  • the third message includes the user's task progress in the current sub-cycle.
  • the agent can reply with a third message to clarify whether the task for the current sub-cycle has been completed, or what the completion rate is, so that the user can understand the task completion status.
  • the second message can be parsed to determine whether the user's feedback is relevant to the task topic or to the task of the current sub-cycle. If relevant, certain features in the user's feedback can be further identified and matched with task features to determine the user's completion level.
  • the third message can also include the user's overall progress for the task throughout the entire cycle.
  • An agent can communicate task progress to the user through one or more messages.
  • the above embodiments generate tasks based on task themes and utilize a dialogue interface between the user and the intelligent agent to complete task assignment and feedback, facilitating task acquisition and execution for the user.
  • all stages of task assignment and completion can be achieved through dialogue with the intelligent agent, supporting various forms of data sent by the user. Therefore, it saves users the cost of understanding, operating, and executing tasks, improving task completion efficiency and user experience.
  • the following describes a method for generating tasks according to some embodiments of this disclosure, using the example of generated tasks including reference resources and execution methods.
  • FIG. 2 shows a flowchart illustrating a task generation method according to some embodiments of the present disclosure. As shown in Figure 2, the task generation method of this embodiment includes steps S202 to S206.
  • step S202 the reference resources corresponding to the task topic are determined.
  • Reference resources refer to information needed when performing a task. They can be represented in any format, or a combination thereof, such as text, audio, images, video, files, and links. Reference resources for each task topic can be pre-set and saved. Alternatively, after determining the task topic to be used by the user, information related to that topic can be searched in a resource library or search engine.
  • reference resources may also meet other conditions.
  • resources corresponding to the task topic can be determined first; then, reference resources can be determined from the resources corresponding to the task topic based on at least one of the user's basic information and the length of the period.
  • Resources corresponding to the task topic can be preset, or resources can be searched in a resource library or search engine using the task topic or related terms.
  • the length of the period can serve as a basis for determining the amount of reference resources. For example, all other things being equal, the length of the period is positively correlated with the amount of resources. Of course, the length of the period can also affect the type of reference resources. For instance, for the task of "watching movies," a shorter period can provide users with a list of classic films; a longer period can provide users with a list of both classic and niche films.
  • User basic information represents the user's existing foundational knowledge or skills in the given task topic. This can be expressed through scores, grades, or specific descriptions. For example, the basic information of a primary school student and a university student will differ when developing an English learning plan, thus requiring different reference resources.
  • basic user information within a task topic is determined based on at least one of the following: historical interaction records between the agent and the user, and user attribute information authorized by the user.
  • Historical interaction records may include, for example, chat logs between the user and the current agent or other agents, or information about the user creating an agent; these historical interaction records should be authorized by the user.
  • Historical interaction records can be obtained from all chat logs between the user and agents, or from chat logs related to the task topic.
  • User attribute information may include, for example, hobbies and personal descriptions that the user has filled out and authorized to be made public in the application. Alternatively, it may be user profile information generated based on various user actions within the application, authorized by the user.
  • Figure 3 shows a flowchart illustrating a method for determining user basic information according to some embodiments of the present disclosure. As shown in Figure 3, the method for determining user basic information in this embodiment includes steps S302 to S304.
  • step S302 the agent sends one or more questions related to the task topic to the user in the dialogue interface.
  • step S302 can be executed in response to the user selecting a task topic.
  • step S302 can be executed in response to a dialogue between the agent and the user involving a task topic.
  • One or more questions can be determined based on one or more dimensions of the task theme, which may include information such as time, difficulty, and objective data. For example, for a task theme related to English learning, questions could include how many years one has studied English, what exams one has passed, and one's vocabulary size. Furthermore, these questions could also be tests. These questions can be carried out through messages sent by the agent.
  • step S304 based on the user's answer to the question, the user's basic information in the task topic is determined.
  • the user's answer can be carried through messages sent by the user. That is, the agent and the user engage in dialogue to answer questions about the task topic. One way to determine this is based on the user giving an affirmative answer, or a correct answer.
  • the answers provided determine the user's basic information, allowing for an accurate assessment of the information the user already possesses. Alternatively, based on the user's answers, a score or grade can be calculated as the user's basic information.
  • basic user information can be determined in a way that is easy for the user to understand and provide feedback on. Furthermore, the determined basic information can indirectly improve the accuracy of task generation. Therefore, this improves task generation efficiency and the user's interactive experience.
  • step S204 the execution method for the reference resource is determined according to the task type to which the task topic belongs.
  • Different task types can be configured with the same or different execution methods.
  • the execution method for the reference resource corresponding to each task type can be pre-specified.
  • the task type to which the task topic belongs can be pre-defined or obtained through semantic analysis or classification of the task topic.
  • semantic analysis a semantic analysis model or a generative model can be used.
  • classification a classification model can be used to divide the task topic into one or more pre-defined task types.
  • the execution method for the reference resource will be to complete a test corresponding to the reference resource, such as memorizing words or reciting poems. If the task theme is exercise, the execution method will be to send the user images or videos of performing actions corresponding to the reference resource, such as uploading fitness images or videos. If the task theme is appreciation, the execution method will be to send the user's understanding of the reference resource, such as sending a review of a movie or book.
  • step S206 tasks for each sub-cycle within the cycle are generated for the user based on reference resources and execution methods. For example, the reference resources and execution methods for the current sub-cycle are indicated in the tasks of each sub-cycle.
  • tasks including reference resources and execution methods can be generated, so that when a task is published, the content of the task and how to complete the task can be effectively conveyed to the user, reducing the user's understanding cost and improving the efficiency of task execution.
  • FIG 4 shows a flowchart illustrating a task generation method according to other embodiments of the present disclosure. As shown in Figure 4, the task generation method of this embodiment includes steps S402 to S406.
  • step S402 based on the task topic and the length of the cycle, the tasks for the cycle and the task quantity for each sub-cycle are generated.
  • the tasks for the cycle include one or more sub-tasks.
  • Generating periodic tasks based on the task theme and cycle length means generating all tasks for the entire cycle and dividing them into one or more subtasks according to independent and divisible units. For example, if the entire cycle's tasks... If the goal is to watch 25 movies, then watching 1 movie can be considered a sub-task.
  • Task workload can be measured using various dimensions, such as the time required to complete the task, physical exertion, the amount of feedback content, the number of reference resources, and so on.
  • determining the workload for each sub-cycle it can be based on the characteristics of the task topic. For example, for learning-related tasks, the workload for each sub-cycle can be determined according to the Ebbinghaus forgetting curve to improve learning efficiency; for appreciation-related tasks such as watching movies, the workload for each sub-cycle can be the same. That is, the workload for each sub-cycle within a cycle can be set to be the same or different.
  • the task load for each sub-cycle can be determined using a machine learning model. For example, by inputting the task topic and cycle length into a generative model or other machine learning model, and instructing the model to generate the task load for each sub-cycle that matches the characteristics of the task topic, the task load for each sub-cycle can be determined from the output of the generative model.
  • step S404 the task quantity of each subtask in the identified periodic task is determined.
  • the workload of each subtask it can be determined by the quantity or volume of reference resources for the subtask, or by combining reference resources and execution methods.
  • the quantity of reference resources can be directly used to determine the workload.
  • a machine learning model can be used to process the reference resources and execution methods of the subtask to obtain the workload of the subtask.
  • step S406 one or more subtasks are assigned to each sub-cycle based on the task volume of each sub-cycle and the task volume of each subtask, thereby generating the task for each sub-cycle. That is, the task volume of the task assigned to each sub-cycle matches the task volume corresponding to that sub-cycle. Matching means that the two are equal, or the difference is less than a specified value.
  • the above embodiments allocate the tasks of the cycle to each sub-cycle according to the workload of each sub-task, thereby generating a task arrangement that conforms to the characteristics of the task theme, improving the user's task execution efficiency, and thus enhancing the user experience.
  • Figure 5 shows a flowchart illustrating a method for determining task progress according to some embodiments of the present disclosure. As shown in Figure 5, the method for determining task progress in this embodiment includes steps S502 to S504.
  • step S502 the second message is identified to determine the user-provided feedback on the task within the current sub-cycle.
  • the identification of the content of the second message can be achieved through machine learning models or matching algorithms.
  • semantic recognition of the text or matching of keywords within the text can be performed.
  • speech recognition can be performed to convert the speech into text.
  • features such as pitch, rhythm, and style in the sound can be identified to determine the content of the feedback.
  • image processing can be performed on frames in the image or video, such as object recognition, image segmentation, image classification, or extraction of features such as color and texture from the image. For video, the time information corresponding to the processing result can be further determined.
  • target features of the multimedia content in the second message are identified based on the type of target features corresponding to the task topic; based on the target features, feedback to the task within the current sub-cycle is determined.
  • target features corresponding to a task theme can be pre-defined.
  • the target features are those related to the user's actions in the video, while sound or color features are relatively less important.
  • the contour and line features in the image are the target features.
  • the feedback for the task can be determined. For example, when determining whether a user's pose in an image is accurate, the user's pose can be determined based on information such as the location of key points in the image or the angle between the lines connecting key points.
  • the following examples illustrate how task feedback is determined based on target features, using several types of task topics as examples. For instance, in response to a learning task topic, the user's accuracy is determined based on target features as feedback for the task within the current sub-cycle; in response to a movement task topic, the accuracy and intensity of the user's actions are determined based on target features as feedback for the task within the current sub-cycle; and in response to an appreciation task topic, the semantic matching degree between the second message and the task within the current sub-cycle is determined based on target features as feedback for the task within the current sub-cycle.
  • step S504 based on the feedback, the user's task progress within the current sub-cycle is determined.
  • Task progress can be determined based on the feedback itself; for example, the content mentioned in the feedback can be used as the task progress.
  • the feedback can be compared or calculated with the tasks in the sub-cycle to determine the task progress; for example, the ratio of the task amount in the feedback to the task amount in the sub-cycle can be used as the task progress.
  • the content of the user's feedback that is, the content related to task completion in the message sent by the user—can be determined first, and then the task progress can be determined based on this feedback. This allows for accurate identification of task progress and improves user interaction efficiency.
  • tasks matching the task theme can be generated, or in some practical... In some embodiments, tasks can be generated based on the user's basic information. However, during task execution, users may encounter difficulties completing the task for various reasons, or the task may be too simple for them. Therefore, in some embodiments of this disclosure, tasks that are about to be released (i.e., unreleased tasks in the current sub-cycle) can be adjusted according to the user's task progress.
  • An embodiment of the task adjustment method of this disclosure is described below with reference to Figure 6.
  • Figure 6 shows a flowchart illustrating a task adjustment method according to some embodiments of the present disclosure. As shown in Figure 6, the task adjustment method of this embodiment includes steps S602 to S606.
  • step S602 within each sub-cycle, in response to the user's task progress in the completed sub-cycle being lower than a first threshold or higher than a second threshold, the task of the generated sub-cycle is adjusted.
  • the first threshold is lower than the second threshold. That is, if a task is completed too quickly or too slowly, adjustments can be made to the task that is about to be released.
  • Task progress can be represented numerically, in terms of levels, or in natural language. It can simply represent the data or information a user has completed, such as accuracy or the number of movements performed during exercise. Alternatively, task progress can be determined based on the data or information the user has completed and the data or information corresponding to the sub-cycle task. For example, if a user performed 5 sets of movements, and the task requires 10 sets, the task progress for that movement can be determined as 50% or "incomplete.”
  • a completed sub-cycle can be one or more sub-cycles that are most recent to the present, or it can be all completed sub-cycles.
  • step S604 the first message is determined based on the adjusted task of the sub-cycle.
  • the number of tasks in the current sub-cycle can be reduced; in response to a task progress exceeding a threshold, the number of tasks in the current sub-cycle can be increased.
  • the agent can send a confirmation message to the user to inquire whether the task needs adjustment. Then, the agent receives the user's message and processes it using a semantic analysis model to confirm user confirmation. If the user confirms, the first message is determined based on the adjusted task; if the user does not wish to adjust, for example, by sending a rejection message or not responding to the agent's inquiry, the first message is determined based on the task before adjustment.
  • step S606 the first message sent by the agent to the user is displayed on the dialogue interface.
  • the tasks to be released can be flexibly adjusted according to the user's task progress, thereby improving the flexibility of task generation and release, improving the user's task execution efficiency, and improving the user experience.
  • one or more candidate topics provided by the agent are displayed in the dialog interface; a task topic is determined from the candidate topics based on user input. For example, candidate topics may be displayed when a user first opens the dialog interface with the agent, or when a user opens the dialog interface again after a period of inactivity with the agent.
  • Figures 7A and 7B illustrate schematic diagrams of dialog interfaces according to some embodiments of the present disclosure.
  • the agent can send a dialogue message 71 to the user, indicating that it has the function of generating task plans. Then, selection controls 72 to 74 can be displayed, each control including a task topic: "TOEFL,” “IELTS,” and "Business English.” The user can confirm the selected task topic by sending a message. For example, in the example of Figure 7A, the user can trigger control 72 to select the task topic "TOEFL,” or they can directly send message 75 to indicate that the task topic "TOEFL" has been selected.
  • tasks for each sub-cycle can be generated and distributed within each sub-cycle.
  • the agent can send message 76 to the user to indicate the tasks the user needs to complete in the first sub-cycle, i.e., the first day.
  • the tasks for this sub-cycle include a list of words as a reference resource, and the execution method of "learning 25 new words every day and reviewing 25 words learned in the previous days every day".
  • users can send feedback via the messaging control 77. For example, a user can send a message to instruct the agent to generate test questions, and then send the answers to complete the test.
  • Figure 7B illustrates other content of the dialogue interface 7.
  • component 78 can be displayed in the dialogue interface 7 to confirm with the user whether they allow sending task-related push notifications. If the user allows push notifications, the system can send push messages to remind the user when a task needs to be issued in each sub-cycle.
  • Figure 8 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure.
  • the interactive device 8 of this embodiment includes: a generation module 801, configured to generate tasks for each sub-cycle of a cycle for the user based on a task theme; and a first display module 802, configured to display on a dialog interface in each sub-cycle.
  • the system includes a first message sent by the intelligent agent to the user, which includes the task of the sub-cycle; a second display module 803, configured to display a second message sent by the user to the intelligent agent in the dialogue interface, which is used to provide feedback on the task of the current sub-cycle; and a third display module 804, configured to display a third message sent by the intelligent agent to the user in response to the second message, which includes the user's task progress in the current sub-cycle.
  • the generation module 801 is further configured to: determine a reference resource corresponding to the task topic; determine the execution method of the reference resource according to the task type to which the task topic belongs; and generate a task for each sub-cycle in the cycle for the user based on the reference resource and the execution method.
  • the generation module 801 is further configured to: determine resources corresponding to the task topic; and determine reference resources from the resources corresponding to the task topic based on at least one of the user's basic information and the length of the period.
  • the interaction device 8 further includes a first determining module 805, configured to determine the user's basic information in the task topic based on at least one of the following: historical interaction records between the agent and the user, and attribute information of the user authorized by the user.
  • the first determining module 805 is further configured to: in response to the user selecting a task topic, display an agent in a dialog interface sending one or more questions associated with the task topic to the user; and determine the user's basic information in the task topic based on the user's answers to the questions.
  • the generation module 801 is further configured to: in response to the task topic being of the learning type, determine the execution method of the reference resource as completing the test corresponding to the reference resource; in response to the task topic being of the motion type, determine the execution method of the reference resource as sending an image or video of the user performing an action corresponding to the reference resource; in response to the task topic being of the appreciation type, determine the execution method of the reference resource as sending information about the user's understanding of the reference resource.
  • the generation module 801 is further configured to: generate tasks for a period and the amount of tasks for each sub-period based on the task topic and the length of the period, wherein the tasks for a period include one or more sub-tasks; identify the amount of tasks for each sub-task in the tasks for a period; and allocate one or more sub-tasks to each sub-period based on the amount of tasks for each sub-period and the amount of tasks for each sub-task to generate tasks for each sub-period.
  • the first display module 802 is further configured to: adjust the task of the generated sub-cycle in each sub-cycle in response to the user's task progress in the completed sub-cycle being lower than a first threshold or higher than a second threshold; determine a first message based on the adjusted task of the sub-cycle; and display the first message sent by the agent to the user on the dialogue interface.
  • the interactive device 8 further includes: a second determining module 806, configured to determine the second message.
  • the system identifies user feedback on tasks within the current sub-cycle; based on this feedback, it determines the user's task progress within the current sub-cycle.
  • the second message includes multimedia content
  • the second determining module 806 is further configured to: identify target features of the multimedia content in the second message according to the type of target features corresponding to the task topic; and determine feedback for the task in the current sub-cycle according to the target features.
  • the second determining module 806 is further configured to: determine the user's accuracy based on target features in response to the task topic belonging to the learning type, as feedback for the task in the current sub-cycle; determine the accuracy and intensity of the user's actions based on target features in response to the task topic belonging to the movement type, as feedback for the task in the current sub-cycle; and determine the semantic matching degree between the second message and the task in the current sub-cycle based on target features in response to the task topic belonging to the appreciation type, as feedback for the task in the current sub-cycle.
  • the interaction device 8 further includes: a third determining module 807, configured to, in response to the dialogue interface being first triggered by the user within a specified time period, display one or more candidate topics provided by the agent in the dialogue interface; and determine a task topic from the candidate topics based on the user's input.
  • a third determining module 807 configured to, in response to the dialogue interface being first triggered by the user within a specified time period, display one or more candidate topics provided by the agent in the dialogue interface; and determine a task topic from the candidate topics based on the user's input.
  • the above-described units are merely logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above-described units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the units shown in the accompanying drawings with dashed lines indicate that these units may not actually exist, and the operations/functions they perform can be implemented by the processing circuitry itself.
  • the device may also include a memory that can store various information generated by the device and its constituent units during operation, programs and data used for operation, data to be transmitted by the communication unit, etc.
  • the memory can be volatile memory and/or non-volatile memory.
  • the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SRAM static random access memory
  • ROM read-only memory
  • flash memory flash memory
  • the device may also include a communication unit that can be used to communicate with other devices.
  • the communication unit can be implemented in a manner known in the art, such as including communication components such as antenna arrays and/or radio frequency links, various types of interfaces, communication units, etc. These will not be described in detail here.
  • the device may also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, etc. These will not be described in detail here.
  • Figure 9 shows a schematic diagram of the structure of an electronic device according to some embodiments of this disclosure.
  • the electronic device 9 can be various types of devices, such as mobile terminals including, but not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers.
  • the electronic device 9 may include a display panel for displaying data and/or execution results utilized in the scheme according to this disclosure.
  • the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel.
  • the display panel can be not only a planar panel, but also a curved panel, or even a spherical panel.
  • the electronic device 9 of this embodiment includes a memory 91 and a processor 92 coupled to the memory 91. It should be noted that the components of the electronic device 9 shown in FIG9 are merely exemplary and not limiting; the electronic device 9 may also have other components depending on the actual application requirements.
  • the processor 92 can control other components in the electronic device 9 to perform desired functions.
  • memory 91 is used to store one or more computer-readable instructions.
  • processor 92 executes the computer-readable instructions, the computer-readable instructions are executed by processor 92 to implement the method according to any of the above embodiments.
  • processor 92 executes the computer-readable instructions
  • the computer-readable instructions are executed by processor 92 to implement the method according to any of the above embodiments.
  • processor 92 and memory 91 can communicate with each other directly or indirectly.
  • processor 92 and memory 91 can communicate via a network.
  • the network can include wireless networks, wired networks, and/or any combination of wireless and wired networks.
  • Processor 92 and memory 91 can also communicate with each other via a system bus, which is not limited in this disclosure.
  • processor 92 can be embodied in various suitable processors, processing devices, such as central processing unit (CPU), graphics processing unit (GPU), network processor (NP), etc.; it can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • the central processing unit (CPU) can be an x86 or ARM architecture, etc.
  • memory 91 can include any combination of various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • Memory 91 can include, for example, system memory, which stores, for example, the operating system, application programs, boot loader, database, and other programs. Various application programs and various data can also be stored in the storage medium.
  • FIG. 10 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.
  • the Central Processing Unit (CPU) 1001 performs various processes according to a program stored in the Read-Only Memory (ROM) 1002 or a program loaded from the Storage Section 1008 into the Random Access Memory (RAM) 1003.
  • the RAM 1003 also stores data required as needed when the CPU 1001 performs various processes, etc.
  • the CPU is merely exemplary and can also be other types of processors, such as the various processors described above.
  • the ROM 1002, RAM 1003, and Storage Section 1008 can be various forms of computer-readable storage media, as described below. It should be noted that although the ROM 1002, RAM 1003, and storage device 1008 are shown separately in Figure 10, one or more of them may be combined or located in the same or different memories or storage modules.
  • CPU 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004.
  • Input/output interface 1005 is also connected to bus 1004.
  • input section 1006 such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.
  • output section 1007 including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.
  • storage section 1008 including hard disks, magnetic tapes, etc.
  • communication section 1009 including network interface cards such as LAN cards, modems, etc.
  • the communication section 1009 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the computer system 100 shown in Figure 10 communicate via bus 1004, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and/or any combination of wireless and wired networks.
  • drive 1010 is also connected to input/output interface 1005.
  • Removable media 1011 such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1010 as needed, so that computer programs read from them can be installed into storage section 1008 as needed.
  • the program constituting the software can be installed from a network such as the Internet or from a storage medium such as removable media 1011.
  • embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts.
  • the computer program can be downloaded and installed from a network via communication device 1009, or installed from storage device 1008, or installed from ROM 1002.
  • the computer program is executed by CPU 1001, it performs the functions defined in the methods of this disclosure embodiment.
  • a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof.
  • a computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code.
  • Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
  • the aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.
  • a computer program comprising: instructions that, when executed by a processor, cause the processor to perform the method of any of the above embodiments.
  • the instructions may be embodied in computer program code.
  • computer program code for performing the operations of this disclosure can be written in one or more programming languages or a combination thereof.
  • These programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as C or similar languages.
  • the program code can be executed entirely on a user's computer, partially on a user's computer, as a standalone software package, or partially on a user's computer and partially on a remote computing facility. It can be executed on the machine or entirely on a remote computer or server.
  • the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function.
  • the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
  • modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware.
  • the names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.
  • exemplary hardware logic components include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.
  • FPGAs field-programmable gate arrays
  • ASICs application-specific integrated circuits
  • ASSPs application-specific standard products
  • SoCs system-on-a-chip
  • CPLDs complex programmable logic devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开涉及交互方法、电子设备、计算机可读存储介质和产品，涉及计算机技术领域。交互方法包括：根据任务主题，为用户生成周期中的每个子周期的任务；在每个子周期内，在对话界面显示智能体向所述用户发送的第一消息，第一消息包括所述子周期的任务；在对话界面显示用户向智能体发送的第二消息，第二消息用于对当前的子周期的任务进行反馈；响应于第二消息，在对话界面显示智能体向用户发送的第三消息，第三消息包括用户在当前的子周期内的任务进度。

Description

交互方法、电子设备、计算机可读存储介质和产品 技术领域
本公开涉及计算机技术领域，特别涉及一种交互方法、电子设备、计算机可读存储介质和产品。
背景技术
随着计算机和互联网技术的发展，用户可以使用计算机、手机、平板电脑等用户设备中的各类应用进行学习或娱乐。例如，用户可以跟随健身应用进行运动，或者通过语言学习应用学习英语。一些应用提供了一些练习或者学习课程，用户可以跟随课程的进度来进行学习。通常，这些课程设置了固定的交互方式。例如，对于健身练习课程，用户可以通过佩戴可穿戴设备执行动作，以通过可穿戴设备采集的数据反映用户的练习结果。又例如，对于学习课程，用户可以在指定的测试页面通过提交表单的方式反馈用户提供的答案。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
根据本公开的一些实施例，提供了一种交互方法，包括：根据任务主题，为用户生成周期中的每个子周期的任务；在每个子周期内，在对话界面显示智能体向所述用户发送的第一消息，第一消息包括所述子周期的任务；在对话界面显示用户向智能体发送的第二消息，第二消息用于对当前的子周期的任务进行反馈；响应于第二消息，在对话界面显示智能体向用户发送的第三消息，第三消息包括用户在当前的子周期内的任务进度。
根据本公开的一些实施例，提供一种电子设备，包括：存储器；和耦接至存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行本公开中所述的任一实施例的方法。
根据本公开的一些实施例，提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时执行本公开中所述的任一实施例的方法。
根据本公开的一些实施例，提供一种计算机程序，包括：指令，所述指令当由处理器执行时使所述处理器执行本公开中所述的任一实施例的方法。
通过以下参照附图对本公开的示例性实施例的详细描述，本公开的其它特征、方面及其优点将会变得清楚。
附图说明
下面参照附图说明本公开的优选实施例。此处所说明的附图用来提供对本公开的进一步理解，各附图连同下面的具体描述一起包含在本说明书中并形成说明书的一部分，用于解释本公开。应当理解的是，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开构成限制。在附图中：
图1示出了根据本公开一些实施例的交互方法的流程示意图。
图2示出了根据本公开一些实施例的任务生成方法的流程示意图。
图3示出了根据本公开一些实施例的用户基础信息确定方法的流程示意图。
图4示出了根据本公开另一些实施例的任务生成方法的流程示意图。
图5示出了根据本公开一些实施例的任务进度的确定方法的流程示意图。
图6示出了根据本公开一些实施例的任务调整方法的流程示意图。
图7A和7B示出了根据本公开一些实施例的对话界面的示意图。
图8示出了根据本公开一些实施例的交互装置的结构示意图。
图9示出了根据本公开一些实施例的电子设备的结构示意图。
图10示出了根据本公开一些实施例的计算机系统的结构示意图。
应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不一定是按照实际的比例关系绘制的。在各附图中使用了相同或相似的附图标记来表示相同或者相似的部件。因此，一旦某一项在一个附图中被定义，则在随后的附图中可能不再对其进行进一步讨论。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，但是显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。以下对实施例的描述实际上也仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。应当理解的是，本公开可以通过各种形式来实现，而且不应该被解 释为限于这里阐述的实施例。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值应被解释为仅仅是示例性的，不限制本公开的范围。
本公开中使用的术语“包括”及其变型意指至少包括后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包括但不限于”。此外，本公开使用的术语“包含”及其变型意指至少包含后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包含但不限于”。因此，包括与包含是同义的。术语“基于”意指“至少部分地基于”。
整个说明书中所称“一个实施例”、“一些实施例”或“实施例”意味着与实施例结合描述的特定的特征、结构或特性被包括在本发明的至少一个实施例中。例如，术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。而且，短语“在一个实施例中”、“在一些实施例中”或“在实施例中”在整个说明书中各个地方的出现不一定全都指的是同一个实施例，但是也可以指同一个实施例。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。除非另有指定，否则“第一”、“第二”等概念并非意图暗示如此描述的对象必须按时间上、空间上、排名上的给定顺序或任何其他方式的给定顺序。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图对本公开的实施例进行详细说明，但是本公开并不限于这些具体的实施例。下面这些具体实施例可以相互结合，对于相同或者相似的概念或过程可能在某些实施例不再赘述。此外，在一个或多个实施例中，特定的特征、结构或特性可以由本领域的普通技术人员从本公开将清楚的任何合适的方式组合。
在相关技术中，虽然应用会为用户提供丰富的课程，但是用户需要学习如何使用应用的课程功能、以及通过固定形式进行反馈。并且，应用提供的课程类型有限，难以提供灵活的交互。
随着人工智能技术的发展，以人工智能驱动的对象可以与用户进行丰富的交互。例如，智能客服可以根据用户产生的关于产品的问题进行解答，翻译助手可以将用户输入的语言翻译为其他语种。
在相关技术中，用户与智能体的交互通常处于一个较短的特定时间段内。例如，当用户产生与智能体的交互需求时，用户找到智能体并向其发送消息，智能体对用户发送的消息进行响应。在用户的询问得到解答之后，用户会退出对话界面，在下一次需要智能体时，再主动地打开与该智能体的对话界面。即，在当前的智能体交互中，智能体还是处于一个相对比较被动的状态。一些应用中的智能体也能够偶尔主动地向用户推送消息，但是通常用于推送新闻，对于用户的长期学习计划没有涉及。
为了给用户提供更加灵活的任务编排和任务完成机制，本公开的实施例利用用户与智能体的对话功能生成和发布任务、以及接收用户的反馈，以节约用户的理解、操作和执行任务的成本，提高任务完成的效率和用户体验。
首先，对本公开所涉及的一些概念进行解释。
智能体是能够在特定环境中自主执行任务的实体。智能体能够基于对话场景中的其他主体(例如参与对话的用户或智能体)发送的对话，生成与之对应的内容。其可以以软件、硬件或者软件和硬件结合的方式实现。智能体又可以被称为数字人、机器人、代理、机器学习模型的虚拟代理。智能体可以依托于机器学习模型实现，例如基于大语言模型(Large Language Model，简称：LLM)或者基础模型(Foundation Model)实现。机器学习模型可以是生成式模型。
生成式模型用于基于输入的信息，输出目标内容。生成式模型输入的信息包括生成式模型在生成过程中的处理依据，例如对话中的其他主体发送的消息、对输出的内容的要求等等。生成式模型例如包括基于文本进行生成的模型、或基于图像进行生成的模型，生成式模型的输出可以包括文本、图像或二者的结合。当然，生成式模型的输入或输出也可以是其他模态的数据，如音频、视频或者多种类型的数据的结合。生成式模型可以为单一模态的模型，例如基于文本生成文本的模型(简称“文生文模型”)、基于图像生成图像的模型(简称“图生图模型”)；或者，生成式模型也可以是跨模态的模型，即输入和输出属于不同模态的模型，例如基于文本生成图像的模型(简称 “文生图模型”)；再或者，生成式模型的输入可以包括多个模态，输出也可以包括多个模态。
下面参考图1描述本公开交互方法的实施例。
图1示出了根据本公开一些实施例的交互方法的流程示意图。如图1所示，该实施例的交互方法包括步骤S102至S108。
在步骤S102中，根据任务主题，为用户生成周期中的每个子周期的任务。
任务主题用于表示所要执行的任务的核心词、关键词等等，每个任务主题可以属于一个或多个任务类型，每个任务类型下可以包括一个或多个任务主题，或者包括一个或多个子类别，每个子类别包括一个或多个任务主题。例如，在学习这一任务类型中，可以包括数学学习、英语学习、文章学习等多个子类别，在英语学习中又可以包括英语单词、英语听力、中学英语、大学英语等多个主题。
任务主题可以由用户提供并输入，也可以由应用提供指定的任务主题，还可以由应用提供一个或多个候选的主题并由用户选择。
在一些实施例中，响应于用户向智能体发送创建任务的指示，执行步骤S102。用户例如通过在与智能体的对话界面中发送消息来触发任务生成的过程。或者，响应于对话界面的显示，智能体自动地执行任务生成的过程。
一个智能体可以向用户提供指定的一个或多个类型的任务，或者，一个或多个指定的任务主题。即，用户在想要通过智能体制定计划时，可以与指定类型的智能体进行交互。例如，用户想要完成学英语的任务时，通过与“英语学习”智能体交互来触发任务的生成。当然，一些智能体也可以支持用户的自由输入来生成各类任务，而无需用户去搜索专用的智能体。
生成的任务覆盖了一定长度的周期，在该周期中的每个子周期中，用户需要发送用于反馈的消息。周期的长度可以由用户指定，例如用户发送了一条“我想制定一个20天学英语的计划”，则周期的长度是20天。又或者，周期的长度可以是默认的，例如对于暑假期间生成的任务，周期可以是暑假。再或者，周期的长度可以根据任务主题确定，例如，智能体通过统计该任务主题的历史任务的周期确定，或者根据任务主题的特点确定。与周期的长度类似的，子周期的长度的确定也可以使用多种方式。子周期的长度可以是默认的，例如默认设置一天或一周为一个子周期；或者，也可以由用户指定或者由智能体确定。
在一些实施例中，可以利用机器学习模型(诸如生成式模型)生成任务。例如， 利用生成式模型对任务主题、或者对任务主题和经用户授权的信息进行处理，以获得生成的任务。又例如，可以读取预先设置的与任务主题对于的任务，再根据经用户授权的信息，对预先设置的任务进行调整，该调整过程可以使用生成式模型完成。即，将预先设置的任务以及经用户授权的信息输入到生成式模型中，以得到调整后的任务。经用户授权的信息例如包括用户与智能体的历史对话、用户公开的基本信息等。
在生成任务时，可以直接生成每个子周期的任务，也可以生成周期的任务，再将任务分配到各个子周期中。
生成的任务包括对任务的描述信息，可以包括用户执行任务时所需要的参考资源、对参考资源的执行方式等。例如对于单词学习任务，生成的任务包括用户在周期内的每一天需要学习的单词列表，以及指示用户需要记忆这些单词，那么参考资源为单词列表，执行方式为记忆；又例如对于健身任务，某个子周期的任务是做5组深蹲、5组俯卧撑、2组拉伸，则参考资源可以包括“深蹲”“俯卧撑”“拉伸”这几个词语，还可以进一步包括对这些动作的具体描述、或者以图像或视频表示的动作要领，执行方式则为做这些动作、以及每个动作需要做的次数。对于某些类别，如果执行方式是非常明确的，也可以不包括执行方式。例如，在用户明确当前是背单词任务的情况下，可以只显示单词列表。本领域技术人员可以根据需要进行选择。
在一些实施例中，任务还可以包括任务反馈方式，例如是通过文本、语音、图像、视频中的哪种数据格式，对内容量的要求等。
在生成每个子周期的任务后，可以将其保存，例如存储在服务器或者是用户设备本地。在每个子周期到来时，从存储的数据中读取与当前的子周期对应的任务、并发送给用户。在初始生成任务后，可以先将周期内的所有任务发送给用户预览，或者将所有任务的摘要发送给用户预览，也可以不发送给用户预览。
在步骤S104中，在每个子周期内，在对话界面显示智能体向用户发送的第一消息，第一消息包括子周期的任务。
第一消息可以包括文本、声音、图像、视频、链接、文件中的一种或多种数据。在没有特别说明的情况下，本公开的实施例中的消息是指对话界面中的对话消息。智能体与用户之间发送的消息会被显示在对话界面(又称聊天界面)中。
步骤S102生成的任务可以是以消息的形式表示的，即，生成的任务可以直接通过第一消息承载并发送给用户。又或者，生成的任务可以是格式化的数据，其中包括了任务的关键内容，例如参考资源、执行方式等信息。然后，由诸如应用的前端将格 式化的数据转换为第一消息。
智能体通过对话中的消息发送任务，从而在用户设备允许智能体使用通知权限的情况下，用户可以及时地接收每个子周期的任务。例如，用户在未使用用户设备、或者在使用智能体所在应用之外的其他应用的情况下，也能够及时地获取当前子周期的任务。
在一些实施例中，还可以为智能体发送的消息标记类型，例如标记为任务消息和非任务消息，并允许用户单独地对任务消息进行使用通知权限的设置。从而，可以设置智能体发送的任务消息使用通知权限、非任务消息不使用通知权限，从而在减少对用户打扰的同时，能够使用户及时接收到任务。
在接收到第一消息后，用户可以通过与智能体对话，针对当前子周期的任务进行进一步交互。例如，响应于用户存在疑问，或响应于用户希望调整当前子周期的任务，用户可以向智能体发送消息。通过对用户发送的消息的语义理解，智能体可以向用户发送对应的反馈消息。
以运动类型的任务为例，某天的任务包括做健身动作A。但是，用户在做动作A时，发觉动作不标准、又无法自行更正，此时，可以向智能体发送消息，请智能体发送更多的参考视频，或者，发送自己做动作A的视频请智能体指出其中的问题。
因此，通过在对话界面显示智能体发送的第一消息来下发任务，能够方便用户与智能体进行交互，以为用户提供更多信息，以更好地完成任务。
在步骤S106中，在对话界面显示用户向智能体发送的第二消息，第二消息用于对当前的子周期的任务进行反馈。
在本公开的实施例中，用户可以通过一条或多条消息发送反馈，也可以通过文本、语音、图像、视频、文件等多种数据格式进行反馈。并且，如果用户发送的消息不符合任务反馈的要求，或者需要用户进一步反馈更丰富的信息，智能体可以再向用户发送消息，以提示用户进行反馈的要求，或者需要修改的内容。从而，通过与智能体的对话界面进行任务反馈，可以方便、高效地协助用户反馈完整的信息。
由于某些智能体除了具备任务功能之外，也支持用户与其进行任务之外的其他交互，例如与任务无关的聊天。因此，可以对用户发送的消息进行语义分析，确定消息的内容与当前子周期的任务的相关性，来判断用户发送的消息是否是针对任务的反馈。
在相关技术中，应用通常提供固定的反馈界面供用户反馈结果，这些反馈界面包括一些表单，具有格式、字数等要求，并且在提交表单之前进行数据验证。如果用户 填写或上传的内容不符合要求，可能出现无法提交的情况。而在本公开的实施例中，用户通过对话界面发送第二消息以进行任务的反馈，能够更灵活、简便地发送任务反馈的结果。即使是反馈的内容不符合要求，智能体也可以通过与用户进一步进行对话，来指导用户上传符合要求的信息。
在步骤S108中，响应于第二消息，在对话界面显示智能体向用户发送的第三消息，第三消息包括用户在当前的子周期内的任务进度。
在用户发送第二消息后，智能体可以通过第三消息进行回复，以向用户明确是否完成了当前子周期的任务、或者完成度是多少，便于用户了解任务完成情况。
在一些实施例中，可以对第二消息进行解析，以确定用户的反馈是否与任务主题相关、或者是否与当前子周期的任务相关。在相关的情况下，还可以进一步确定用户的反馈中的一些特征，并将其与任务的特征进行匹配，来确定用户的完成度。
根据需要，除了在子周期的进度以外，第三消息还可以包括用户对整个周期的任务的总进度。智能体可以通过一条或多条消息来向用户传递任务进度。
上述实施例根据任务主题生成任务，并利用用户与智能体的对话界面完成任务下发和任务反馈，便于用户获取和执行任务。从而，任务的发布和完成的各个环节都可以通过与智能体之间的对话实现，能够支持用户发送的多种形式的数据。因此，节约了用户的理解、操作和执行任务的成本，提高了任务完成的效率和用户体验。
下面以生成的任务包括参考资源和执行方式为例，描述本公开一些实施例的任务生成的方法。
图2示出了根据本公开一些实施例的任务生成方法的流程示意图。如图2所示，该实施例的任务生成方法包括步骤S202至S206。
在步骤S202中，确定与任务主题对应的参考资源。
参考资源是指执行任务时需要参照的信息，其可以以文本、语音、图像、视频、文件、链接等任意格式或其组合表示。可以预先设置每个任务主题对应的参考资源并将其保存。也可以在确定用户使用的任务主题后，在资源库或者搜索引擎中搜索与任务主题相关的信息。
参考资源除了需要与任务主题匹配之外，还可以符合其他的条件。在一些实施例中，可以先确定与任务主题对应的资源；再根据用户的基础信息、周期的长度中的至少一项，从与任务主题对应的资源中确定参考资源。可以预先设置与任务主题对应的资源，或者在资源库或搜索引擎中使用任务主题或任务主题的关联词搜索资源。
周期的长度可以作为参考资源的资源量的确定依据，例如在其他条件不变的情况下，周期的长度与资源量成正相关关系。当然，周期的长度也可以影响参考资源的类型。例如，对于“看电影”任务，在周期的长度比较短的情况下，可以为用户提供看经典电影的清单；在周期的长度比较长的情况下，可以为用户提供看经典电影和小众电影的清单。
用户的基础信息用于表示用户在该任务主题中已经具备的基础知识或基础能力，其可以通过分数、等级或者具体描述来表示。例如，对于一个小学生用户和一个大学生用户，在制定英语学习计划时，其基础信息是不同的，因此为用户提供的参考资源也是不同的。
在一些实施例中，根据智能体与用户的历史交互记录、经用户授权的用户的属性信息中的至少一项，确定用户在任务主题中的基础信息。历史交互记录例如为用户与当前智能体或其他的智能体的聊天记录，或者是用户创建智能体的信息，该历史交互记录应该是被用户授权的。历史交互记录可以从用户与智能体的所有聊天记录中获取，也可以是从与该任务主题相关的聊天记录中获取。用户的属性信息例如包括用户在应用中填写并授权公开的爱好、个人描述等信息。或者，是经用户授权的、根据用户在应用中的各类操作生成的用户画像信息。
图3示出了根据本公开一些实施例的用户基础信息确定方法的流程示意图。如图3所示，该实施例的用户基础信息的确定方法包括步骤S302至S304。
在步骤S302中，在对话界面显示智能体向用户发送一个或多个与任务主题关联的提问。
例如，可以响应于用户选择任务主题，执行步骤S302。或者，也可以是响应于智能体和用户的对话涉及任务主题，执行步骤S302。
一个或多个提问可以根据任务主题的一个或多个维度确定，这些维度可以包括时间、难度、客观数据等信息。例如，对于英语学习类型的任务主题，可以提出诸如学习了几年英语、通过了什么考试、词汇量等问题。此外，这些问题也可以是一些测试。这些问题可以通过智能体发送的消息承载。
在步骤S304中，基于用户发送的对提问的解答，确定用户在任务主题中的基础信息。
用户的解答可以通过用户发送的消息承载。即，智能体和用户通过对话的方式，完成有关于任务主题的问答。一种确定方式为，基于用户给出肯定回答、或者是正确 回答的问题，确定用户的基础信息，以准确地确定用户已掌握的信息。另一种确定方式为，基于用户的解答，计算用户的分数或等级，作为用户的基础信息。
通过使用智能体与用户对话的方式完成对用户基础信息的确定，可以以用户易于理解和反馈的方式，确定用户的基础信息。并且，确定的基础信息能够间接地提高任务生成的准确性。因此提高了任务生成的效率以及用户的交互体验。
在步骤S204中，根据任务主题所属的任务类型，确定对参考资源的执行方式。
不同的任务类型可以设置相同或者不同的执行方式。每种任务类型对应的对参考资源的执行方式可以是预先指定的。任务主题所属的任务类型可以是预先设定的，也可以是通过对任务主题进行语义分析或分类得到的。在进行语义分析时，可以使用语义分析模型或者生成式模型。在进行分类时，可以使用分类模型，以将任务主题划分到预设的多个任务类型中的一个或多个。
下面示例性地描述几种任务类型所对应的对参考资源的执行方式。
响应于任务主题属于学习类型，将对参考资源的执行方式确定为完成与参考资源对应的测试，例如单词默写、诗句背诗等。响应于任务主题属于运动类型，将对参考资源的执行方式确定为发送用户执行与参考资源对应的动作的图像或视频，例如上传健身的图像或者视频。响应于任务主题属于鉴赏类型，将对参考资源的执行方式确定为发送用户对参考资源的理解信息，例如发送电影或者书籍的读后感。
在步骤S206中，基于参考资源和执行方式，为用户生成周期中的每个子周期的任务。例如，在每个子周期的任务中指示当前子周期的参考资源以及执行方式。
通过上述实施例，能够生成包括参考资源和执行方式的任务，使得在发布任务时，能够将任务的内容以及如何完成任务有效地传递给用户，降低了用户的理解成本，提高了任务执行的效率。
在生成任务时，可以直接生成每个子周期的任务，也可以先生成全部任务、再将其分配到每一个子周期中。下面参考图4示例性地描述后一种方式的实现方法。
图4示出了根据本公开另一些实施例的任务生成方法的流程示意图。如图4所示，该实施例的任务生成方法包括步骤S402至S406。
在步骤S402中，根据任务主题以及周期的长度，生成周期的任务、以及每个子周期的任务量，周期的任务包括一个或多个子任务。
根据任务主题以及周期的长度生成周期的任务，是指生成整个周期的所有任务，并且按照独立可分割的单元，划分为一个或多个子任务。例如，如果整个周期的任务 是观看25部电影，那么观看1部电影可以视为一个子任务。
任务量可以使用多种维度来衡量，例如完成任务需要消耗的时间、体力或者反馈的内容量、参考资源的数量等等。确定每个子周期的任务量时，可以根据任务主题的特点确定。例如，对于学习类型，可以根据艾宾浩斯记忆曲线来确定每个子周期的任务量，以提高学习效率；对于观看电影等鉴赏类的任务，可以令每个子周期的任务量相同。即，周期中每个子周期的任务量可以设置为相同或者不同。
在确定每个子周期的任务量时，可以利用机器学习模型获得。例如，将任务主题、周期长度输入到生成式模型等机器学习模型中，并指示机器学习模型生成符合任务主题的特点的、每个子周期的任务量，则可以从生成式模型的输出中获取对每个子周期的任务量的确定结果。
在步骤S404中，识别周期的任务中，每个子任务的任务量。
在确定每个子任务的任务量时，可以通过子任务的参考资源的数量或者内容量确定，或者结合参考资源和执行方式来确定。例如，可以直接将参考资源的数量确定为任务量。又例如，可以利用机器学习模型对子任务的参考资源和执行方式进行处理，以获得子任务的任务量。
在步骤S406中，根据每个子周期的任务量以及每个子任务的任务量，将一个或多个子任务分配到每个子周期中，以生成每个子周期的任务。即，被分配到每个子周期的任务的任务量，与该子周期对应的任务量匹配。匹配是指二者相等，或者是差值小于指定的值。
上述实施例根据每个子任务的任务量，将周期的任务分配到每个子周期中，从而能够生成符合任务主题的特点的任务安排，提高了用户的任务执行效率，因此能够提升用户体验。
以上是对任务生成阶段的一些实施例的介绍。下面参考图5示例性地描述确定任务进度的实施例。
图5示出了根据本公开一些实施例的任务进度的确定方法的流程示意图。如图5所示，该实施例的任务进度的确定方法包括步骤S502至S504。
在步骤S502中，对第二消息进行识别，以确定用户提供的、对当前的子周期内的任务的反馈。
对第二消息的内容的识别可以通过机器学习模型或者匹配算法等实现。
响应于第二消息包括文本，可以对文本进行语义识别或者匹配文本中的关键字， 以确定反馈的内容。响应于第二消息包括语音，可以对语音进行语音识别以将其转换为文本。响应于第二消息包括声音，可以识别声音中的音调、节奏、风格等特征，以利用识别的特征确定反馈的内容。响应于第二消息包括图像或视频，可以对图像或视频中的帧进行图像处理，例如目标识别、图像分割、图像分类，或者从图像中提取颜色、纹理等特征。对于视频，还可以进一步确定处理结果所对应的时间信息。
对于声音、图像、视频等多媒体内容，可以通过识别多媒体内容中的目标特征来确定对任务的反馈。在一些实施例中，根据与任务主题对应的目标特征的类型，识别第二消息中的多媒体内容的目标特征；根据目标特征，确定对当前的子周期内的任务的反馈。
任务主题对应的目标特征的类型可以是预先设置的。例如，对于运动类任务，目标特征为视频中与用户动作相关的特征，其声音特征或者颜色特征相对不是很重要。又例如，对于绘画鉴赏类特征，如果用户上传自己临摹的图画，则图像中的轮廓特征和线条特征为目标特征。
根据目标特征的取值、数量等信息，可以确定任务的反馈。例如，在确定用户在图像中的姿态是否准确时，可以根据图像中的关键点的位置、或者关键点的连线之间的角度等信息，确定用户的姿态。
下面结合几种类型的任务主题，示例性地描述根据目标特征确定任务反馈的方式。例如，响应于任务主题属于学习类型，根据目标特征确定用户的准确率，以作为对当前的子周期内的任务的反馈；响应于任务主题属于运动类型，根据目标特征确定用户的动作的准确度和运动强度，以作为对当前的子周期内的任务的反馈；响应于任务主题属于鉴赏类型，根据目标特征确定第二消息的语义与当前的子周期内的任务的匹配度，以作为对当前的子周期内的任务的反馈。
在步骤S504中，基于反馈，确定用户在当前的子周期内的任务进度。
可以根据反馈本身确定任务进度，例如，将反馈中涉及的内容本身作为任务进度。或者，也可以将反馈与子周期的任务进行对比或计算，以确定任务进度，例如确定反馈中的任务量与子周期的任务的任务量的比值，作为任务进度。
通过上述实施例，可以先确定用户的反馈的内容，即用户发送的消息中与完成任务相关的内容，再基于该反馈确定任务进度。从而，能够准确地对任务进度进行识别，提高用户的交互效率。
虽然在任务生成阶段，可以根据任务主题生成与之相匹配的任务，或者在一些实 施例中还可以根据用户的基础信息生成任务。但是用户在执行任务的过程中，仍有可能出于多种原因，使得用户完成任务有困难，或者任务对于用户过于简单。因此，在本公开的一些实施例中，可以根据用户的任务进度，对即将发布的任务(即当前子周期的未发布的任务)进行调整。下面参考图6描述本公开任务调整方法的实施例。
图6示出了根据本公开一些实施例的任务调整方法的流程示意图。如图6所示，该实施例的任务调整方法包括步骤S602至S606。
在步骤S602中，在每个子周期内，响应于用户在已结束的子周期中的任务进度低于第一阈值、或高于第二阈值，对生成的子周期的任务进行调整。
第一阈值低于第二阈值。即，任务完成过快或过慢时，可以对即将发布的任务进行调整。
任务进度可以使用数值、等级或者自然语言表示。其可以单纯地表征用户完成任务的数据或信息，例如准确率、运动时所做的动作数量等等。或者，任务进度也可以基于用户完成任务的数据或信息与子周期的任务所对应的数据或信息确定。例如，用户做了5组动作，而任务规定需要做10组，则该动作的任务进度可以确定为50％，也可以确定为“未完成”。
已结束的子周期可以是距离当前最近的一个或多个子周期，也可以是全部已结束的子周期。
在步骤S604中，基于子周期的调整后的任务确定第一消息。
例如，响应于任务进度低于阈值，可以减少当前子周期的任务；响应于任务进度高于阈值，可以增加当前子周期的任务。
根据需要，在确定需要调整任务、但调整实施之前，可以控制智能体向用户发送确认消息，以询问用户是否需要对任务进行调整。然后，接收用户发送的消息并使用语义分析模型进行处理，以确认用户是否确认该调整。如果用户确认，则基于调整后的任务确定第一消息；如果用户不希望调整，例如发送了表示拒绝的消息或者不回复智能体发送的询问消息，则基于调整之前的任务确定第一消息。
在步骤S606中，在对话界面显示智能体向用户发送的第一消息。
通过上述实施例，能够根据用户的任务进度灵活地对即将发布的任务进行调整，从而提高了任务的生成和发布的灵活性，提高了用户的任务执行效率，提高了用户体验。
下面结合本公开一些实施例的对话界面的示意图，示例性地描述用户与智能体的 交互过程。
在一些实施例中，响应于对话界面在指定时间长度内首次被用户触发，在对话界面中显示智能体提供的一个或多个候选的主题；基于用户的输入，从候选的主题中确定任务主题。例如，用户首次打开与该智能体的对话界面时，或者用户一段时间未与该智能体对话后又打开对话界面时，可以显示候选的主题。图7A和7B示出了根据本公开一些实施例的对话界面的示意图。
例如，用户首次打开与智能体“每日单词”的对话界面7，智能体“每日单词”可以向用户发送对话消息71，以表示其具备生成任务计划的功能。然后，可以显示选择控件72至74，每个控件包括一个任务主题，分别为“托福”“雅思”“商务英语”。用户可以通过发送消息来确定所选择的任务主题。例如，在图7A的示例中，用户可以触发控件72以选择任务主题“托福”，或者也可以直接发送消息75以表示选择了任务主题“托福”。
当然，图7A利用选择控件72至74与用户交互只是一种示例。根据需要，也可以不显示消息71以及72至74，直接由用户发送消息以指示用户选择的任务主题。
在确定任务主题后，可以生成各个子周期的任务，并在各个子周期下发。例如，智能体可以向用户发送消息76，以表明第一个子周期即第一天用户需要完成的任务。在该示例中，该子周期的任务包括作为参考资源的单词列表、以及作为执行方式的“每天学习25个新单词，每天复习前几天学过的25个单词”。
用户在完成任务后，例如完成单词的学习后，可以通过消息发送控件77发送反馈。例如，用户可以发送消息以指示智能体为自己出测试题，然后用户发送答案以完成测试。
图7B示出了对话界面7的其他内容。如图7B所示，在智能体首次发送任务后，可以在对话界面7显示组件78，以向用户确认是否允许发送与任务相关的推送。在用户允许推送的情况下，在每个子周期中需要下发任务时，可以通过系统推送消息来提醒用户。
以上对本公开的方法实施例进行了示例性的描述。下面进一步描述用于执行上述实施例的装置和设备。
图8示出了根据本公开一些实施例的交互装置的结构示意图。如图8所示，该实施例的交互装置8包括：生成模块801，被配置为根据任务主题，为用户生成周期中的每个子周期的任务；第一显示模块802，被配置为在每个子周期内，在对话界面显 示智能体向用户发送的第一消息，第一消息包括子周期的任务；第二显示模块803，被配置为在对话界面显示用户向智能体发送的第二消息，第二消息用于对当前的子周期的任务进行反馈；第三显示模块804，被配置为响应于第二消息，在对话界面显示智能体向用户发送的第三消息，第三消息包括用户在当前的子周期内的任务进度。
在一些实施例中，生成模块801进一步被配置为：确定与任务主题对应的参考资源；根据任务主题所属的任务类型，确定对参考资源的执行方式；基于参考资源和执行方式，为用户生成周期中的每个子周期的任务。
在一些实施例中，其中，生成模块801进一步被配置为：确定与任务主题对应的资源；根据用户的基础信息、周期的长度中的至少一项，从与任务主题对应的资源中确定参考资源。
在一些实施例中，交互装置8还包括：第一确定模块805，被配置为根据智能体与用户的历史交互记录、经用户授权的用户的属性信息中的至少一项，确定用户在任务主题中的基础信息。
在一些实施例中，第一确定模块805进一步被配置为：响应于用户选择任务主题，在对话界面显示智能体向用户发送一个或多个与任务主题关联的提问；基于用户发送的对提问的解答，确定用户在任务主题中的基础信息。
在一些实施例中，生成模块801进一步被配置为：响应于任务主题属于学习类型，将对参考资源的执行方式确定为完成与参考资源对应的测试；响应于任务主题属于运动类型，将对参考资源的执行方式确定为发送用户执行与参考资源对应的动作的图像或视频；响应于任务主题属于鉴赏类型，将对参考资源的执行方式确定为发送用户对参考资源的理解信息。
在一些实施例中，生成模块801进一步被配置为：根据任务主题以及周期的长度，生成周期的任务、以及每个子周期的任务量，周期的任务包括一个或多个子任务；识别周期的任务中，每个子任务的任务量；根据每个子周期的任务量以及每个子任务的任务量，将一个或多个子任务分配到每个子周期中，以生成每个子周期的任务。
在一些实施例中，第一显示模块802进一步被配置为：在每个子周期内，响应于用户在已结束的子周期中的任务进度低于第一阈值、或高于第二阈值，对生成的子周期的任务进行调整；基于子周期的调整后的任务确定第一消息；在对话界面显示智能体向用户发送的第一消息。
在一些实施例中，交互装置8还包括：第二确定模块806，被配置为对第二消息 进行识别，以确定用户提供的、对当前的子周期内的任务的反馈；基于反馈，确定用户在当前的子周期内的任务进度。
在一些实施例中，第二消息包括多媒体内容，第二确定模块806进一步被配置为：根据与任务主题对应的目标特征的类型，识别第二消息中的多媒体内容的目标特征；根据目标特征，确定对当前的子周期内的任务的反馈。
在一些实施例中，第二确定模块806进一步被配置为：响应于任务主题属于学习类型，根据目标特征确定用户的准确率，以作为对当前的子周期内的任务的反馈；响应于任务主题属于运动类型，根据目标特征确定用户的动作的准确度和运动强度，以作为对当前的子周期内的任务的反馈；响应于任务主题属于鉴赏类型，根据目标特征确定第二消息的语义与当前的子周期内的任务的匹配度，以作为对当前的子周期内的任务的反馈。
在一些实施例中，交互装置8还包括：第三确定模块807，被配置为响应于对话界面在指定时间长度内首次被用户触发，在对话界面中显示智能体提供的一个或多个候选的主题；基于用户的输入，从候选的主题中确定任务主题。
应注意，上述各个单元仅是根据其所实现的具体功能划分的逻辑模块，而不是用于限制具体的实现方式，例如可以以软件、硬件或者软硬件结合的方式来实现。在实际实现时，上述各个单元可被实现为独立的物理实体，或者也可由单个实体(例如，处理器(CPU或DSP等)、集成电路等)来实现。此外，上述各个单元在附图中用虚线示出指示这些单元可以并不实际存在，而它们所实现的操作/功能可由处理电路本身来实现。
此外，尽管未示出，该设备也可以包括存储器，其可以存储由设备、设备所包含的各个单元在操作中产生的各种信息、用于操作的程序和数据、将由通信单元发送的数据等。存储器可以是易失性存储器和/或非易失性存储器。例如，存储器可以包括但不限于随机存储存储器(RAM)、动态随机存储存储器(DRAM)、静态随机存取存储器(SRAM)、只读存储器(ROM)、闪存存储器。当然，存储器可也位于该设备之外。可选地，尽管未示出，但是该设备也可以包括通信单元，其可用于与其它装置进行通信。在一个示例中，通信单元可以被按照本领域已知的适当方式来实现，例如包括天线阵列和/或射频链路等通信部件，各种类型的接口、通信单元等等。这里将不再详细描述。此外，设备还可以包括未示出的其它部件，诸如射频链路、基带处理单元、网络接口、处理器、控制器等。这里将不再详细描述。
本公开的一些实施例还提供一种电子设备。图9示出了根据本公开一些实施例的电子设备的结构示意图。例如，在一些实施例中，电子设备9可以为各种类型的设备，例如可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。例如，电子设备9可以包括显示面板，以用于显示根据本公开的方案中所利用的数据和/或执行结果。例如，显示面板可以为各种形状，例如矩形面板、椭圆形面板或多边形面板等。另外，显示面板不仅可以为平面面板，也可以为曲面面板，甚至球面面板。
如图9所示，该实施例的电子设备9包括：存储器91以及耦接至该存储器91的处理器92。应当注意，图9所示的电子设备9的组件只是示例性的，而非限制性的，根据实际应用需要，该电子设备9还可以具有其他组件。处理器92可以控制电子设备9中的其它组件以执行期望的功能。
在一些实施例中，存储器91用于存储一个或多个计算机可读指令。处理器92用于运行计算机可读指令时，计算机可读指令被处理器92运行时实现根据上述任一实施例所述的方法。关于该方法的各个步骤的具体实现以及相关解释内容可以参见上述的实施例，重复之处在此不作赘述。
例如，处理器92和存储器91之间可以直接或间接地互相通信。例如，处理器92和存储器91可以通过网络进行通信。网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。处理器92和存储器91之间也可以通过系统总线实现相互通信，本公开对此不作限制。
例如，处理器92可以体现为各种适当的处理器、处理装置等，诸如中央处理器(CPU)、图形处理器(Graphics Processing Unit，GPU)、网络处理器(NP)等；还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。中央处理元(CPU)可以为X86或ARM架构等。例如，存储器91可以包括各种形式的计算机可读存储介质的任意组合，例如易失性存储器和/或非易失性存储器。存储器91例如可以包括系统存储器，系统存储器例如存储有操作系统、应用程序、引导装载程序(Boot Loader)、数据库以及其他程序等。在存储介质中还可以存储各种应用程序和各种数据等。
另外，根据本公开的一些实施例，根据本公开的各种操作/处理在通过软件和/或 固件实现的情况下，可从存储介质或网络向具有专用硬件结构的计算机系统，例如图10所示的计算机系统100安装构成该软件的程序，该计算机系统在安装有各种程序时，能够执行各种功能，包括诸如前文所述的功能等等。图10示出了根据本公开一些实施例的计算机系统的结构示意图。
在图10中，中央处理单元(CPU)1001根据只读存储器(ROM)1002中存储的程序或从存储部分1008加载到随机存取存储器(RAM)1003的程序执行各种处理。在RAM 1003中，也根据需要存储当CPU 1001执行各种处理等时所需的数据。中央处理单元仅仅是示例性的，其也可以是其它类型的处理器，诸如前文所述的各种处理器。ROM 1002、RAM 1003和存储部分1008可以是各种形式的计算机可读存储介质，如下文所述。需要注意的是，虽然图10中分别示出了ROM 1002、RAM 1003和存储装置1008，但是它们中的一个或多个可以合并或者位于相同或不同的存储器或存储模块中。
CPU 1001、ROM 1002和RAM 1003经由总线1004彼此连接。输入/输出接口1005也连接到总线1004。
下述部件连接到输入/输出接口1005：输入部分1006，诸如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等；输出部分1007，包括显示器，比如阴极射线管(CRT)、液晶显示器(LCD)，扬声器，振动器等；存储部分1008，包括硬盘，磁带等；和通信部分1009，包括网络接口卡比如LAN卡、调制解调器等。通信部分1009允许经由网络比如因特网执行通信处理。容易理解的是，虽然图10中示出计算机系统100中的各个装置或模块是通过总线1004来通信的，但它们也可以通过网络或其它方式进行通信，其中，网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。
根据需要，驱动器1010也连接到输入/输出接口1005。可拆卸介质1011比如磁盘、光盘、磁光盘、半导体存储器等等根据需要被安装在驱动器1010上，使得从中读出的计算机程序根据需要被安装到存储部分1008中。
在通过软件实现上述系列处理的情况下，可以从网络比如因特网或存储介质比如可拆卸介质1011安装构成软件的程序。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实 施例中，该计算机程序可以通过通信装置1009从网络上被下载和安装，或者从存储装置1008被安装，或者从ROM 1002被安装。在该计算机程序被CPU 1001执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，在本公开的上下文中，计算机可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是，但不限于：电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
在一些实施例中，还提供了一种计算机程序，包括：指令，指令当由处理器执行时使处理器执行上述任一个实施例的方法。例如，指令可以体现为计算机程序代码。
在本公开的实施例中，可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算 机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络(包括局域网(LAN)或广域网(WAN))连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块、部件或单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块、部件或单元的名称在某种情况下并不构成对该模块、部件或单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示例性的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
以上描述仅为本公开的一些实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
在本文提供的描述中，阐述了许多特定细节。然而，理解的是，可以在没有这些特定细节的情况下实施本发明的实施例。在其他情况下，为了不模糊该描述的理解，没有对众所周知的方法、结构和技术进行详细展示。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是 有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上示例仅是为了进行说明，而不是为了限制本公开的范围。本领域的技术人员应该理解，可在不脱离本公开的范围和精神的情况下，对以上实施例进行修改。本公开的范围由所附权利要求来限定。

Claims (16)

  1. 一种交互方法，包括：
    根据任务主题，为用户生成周期中的每个子周期的任务；
    在每个子周期内，在对话界面显示智能体向所述用户发送的第一消息，所述第一消息包括所述子周期的任务；
    在所述对话界面显示所述用户向所述智能体发送的第二消息，所述第二消息用于对当前的子周期的任务进行反馈；
    响应于所述第二消息，在所述对话界面显示所述智能体向所述用户发送的第三消息，所述第三消息包括所述用户在所述当前的子周期内的任务进度。
  2. 根据权利要求1所述的交互方法，其中，所述根据任务主题，为用户生成周期中的每个子周期的任务包括：
    确定与所述任务主题对应的参考资源；
    根据所述任务主题所属的任务类型，确定对所述参考资源的执行方式；
    基于所述参考资源和所述执行方式，为所述用户生成周期中的每个子周期的任务。
  3. 根据权利要求2所述的交互方法，其中，所述确定与所述任务主题对应的参考资源包括：
    确定与所述任务主题对应的资源；
    根据所述用户的基础信息、所述周期的长度中的至少一项，从与所述任务主题对应的资源中确定所述参考资源。
  4. 根据权利要求3所述的交互方法，还包括：
    根据所述智能体与所述用户的历史交互记录、经所述用户授权的所述用户的属性信息中的至少一项，确定所述用户在所述任务主题中的基础信息。
  5. 根据权利要求4所述的交互方法，其中，根据所述智能体与所述用户的历史交互记录，确定所述用户在所述任务主题中的基础信息包括：
    响应于所述用户选择所述任务主题，在所述对话界面显示所述智能体向所述用户发送一个或多个与所述任务主题关联的提问；
    基于所述用户发送的对所述提问的解答，确定所述用户在所述任务主题中的基础信息。
  6. 根据权利要求2至5中任一项所述的交互方法，其中，所述根据所述任务主 题所属的任务类型，确定对所述参考资源的执行方式包括：
    响应于所述任务主题属于学习类型，将对所述参考资源的执行方式确定为完成与所述参考资源对应的测试；
    响应于所述任务主题属于运动类型，将对所述参考资源的执行方式确定为发送所述用户执行与所述参考资源对应的动作的图像或视频；
    响应于所述任务主题属于鉴赏类型，将对所述参考资源的执行方式确定为发送所述用户对所述参考资源的理解信息。
  7. 根据权利要求1至6中任一项所述的交互方法，其中，所述根据任务主题，为所述用户生成周期中的每个子周期的任务包括：
    根据所述任务主题以及所述周期的长度，生成所述周期的任务、以及每个子周期的任务量，所述周期的任务包括一个或多个子任务；
    识别所述周期的任务中，每个子任务的任务量；
    根据每个子周期的任务量以及所述每个子任务的任务量，将所述一个或多个子任务分配到每个子周期中，以生成每个子周期的任务。
  8. 根据权利要求1至7中任一项所述的交互方法，其中，所述在每个子周期内，在对话界面显示智能体向所述用户发送的第一消息包括：
    在每个子周期内，响应于所述用户在已结束的子周期中的任务进度低于第一阈值、或高于第二阈值，对生成的所述子周期的任务进行调整；
    基于所述子周期的调整后的任务确定所述第一消息；
    在所述对话界面显示所述智能体向所述用户发送的所述第一消息。
  9. 根据权利要求1至8中任一项所述的交互方法，还包括：
    对所述第二消息进行识别，以确定所述用户提供的、对所述当前的子周期内的任务的反馈；
    基于所述反馈，确定所述用户在所述当前的子周期内的任务进度。
  10. 根据权利要求9所述的交互方法，其中，所述第二消息包括多媒体内容，所述对所述第二消息进行识别，以确定所述用户提供的、对所述当前的子周期内的任务的反馈包括：
    根据与所述任务主题对应的目标特征的类型，识别所述第二消息中的所述多媒体内容的目标特征；
    根据所述目标特征，确定对所述当前的子周期内的任务的反馈。
  11. 根据权利要求10所述的交互方法，其中，所述根据所述目标特征，确定对所述当前的子周期内的任务的反馈包括：
    响应于所述任务主题属于学习类型，根据所述目标特征确定所述用户的准确率，以作为对所述当前的子周期内的任务的反馈；
    响应于所述任务主题属于运动类型，根据所述目标特征确定所述用户的动作的准确度和运动强度，以作为对所述当前的子周期内的任务的反馈；
    响应于所述任务主题属于鉴赏类型，根据所述目标特征确定所述第二消息的语义与所述当前的子周期内的任务的匹配度，以作为对所述当前的子周期内的任务的反馈。
  12. 根据权利要求1至11中任一项所述的交互方法，还包括：
    响应于所述对话界面在指定时间长度内首次被所述用户触发，在所述对话界面中显示所述智能体提供的一个或多个候选的主题；
    基于所述用户的输入，从所述候选的主题中确定所述任务主题。
  13. 一种电子设备，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行如权利要求1至12中任一项所述的交互方法。
  14. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现权利要求1至12中任一项所述的交互方法。
  15. 一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机实现权利要求1至12中任一项所述的交互方法。
  16. 一种计算机程序，包括：
    指令，所述指令当由处理器执行时使所述处理器执行根据权利要求1至12中任一项所述的交互方法。
PCT/CN2024/102294 2024-06-28 2024-06-28 交互方法、电子设备、计算机可读存储介质和产品 Pending WO2026000332A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202480002209.3A CN119213751A (zh) 2024-06-28 2024-06-28 交互方法、电子设备、计算机可读存储介质和产品
PCT/CN2024/102294 WO2026000332A1 (zh) 2024-06-28 2024-06-28 交互方法、电子设备、计算机可读存储介质和产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/102294 WO2026000332A1 (zh) 2024-06-28 2024-06-28 交互方法、电子设备、计算机可读存储介质和产品

Publications (1)

Publication Number Publication Date
WO2026000332A1 true WO2026000332A1 (zh) 2026-01-02

Family

ID=94050120

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/102294 Pending WO2026000332A1 (zh) 2024-06-28 2024-06-28 交互方法、电子设备、计算机可读存储介质和产品

Country Status (2)

Country Link
CN (1) CN119213751A (zh)
WO (1) WO2026000332A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110399197A (zh) * 2019-07-30 2019-11-01 北京达佳互联信息技术有限公司 任务显示的方法、终端、服务器及介质
US20210081878A1 (en) * 2019-09-17 2021-03-18 International Business Machines Corporation Automatic generation of tasks and retraining machine learning modules to generate tasks based on feedback for the generated tasks
CN114971689A (zh) * 2022-04-26 2022-08-30 北京百度网讯科技有限公司 任务处理方法、装置、设备和存储介质
CN115185705A (zh) * 2021-04-06 2022-10-14 腾讯科技（深圳）有限公司 一种消息通知方法、装置、介质及设备
CN117789947A (zh) * 2023-12-25 2024-03-29 杭州康明信息技术有限公司 任务生成方法以及装置、计算设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110399197A (zh) * 2019-07-30 2019-11-01 北京达佳互联信息技术有限公司 任务显示的方法、终端、服务器及介质
US20210081878A1 (en) * 2019-09-17 2021-03-18 International Business Machines Corporation Automatic generation of tasks and retraining machine learning modules to generate tasks based on feedback for the generated tasks
CN115185705A (zh) * 2021-04-06 2022-10-14 腾讯科技（深圳）有限公司 一种消息通知方法、装置、介质及设备
CN114971689A (zh) * 2022-04-26 2022-08-30 北京百度网讯科技有限公司 任务处理方法、装置、设备和存储介质
CN117789947A (zh) * 2023-12-25 2024-03-29 杭州康明信息技术有限公司 任务生成方法以及装置、计算设备及介质

Also Published As

Publication number Publication date
CN119213751A (zh) 2024-12-27

Similar Documents

Publication Publication Date Title
CN110476173B (zh) 利用强化学习的分层设备放置
CN117520497A (zh) 大模型交互处理方法、系统、终端、设备及介质
CN111666416B (zh) 用于生成语义匹配模型的方法和装置
US11468880B2 (en) Dialog system training using a simulated user system
US20240378394A1 (en) Reducing computational resource usage via training and/or utilizing large language models
WO2025161295A1 (zh) 搜索方法、装置、计算机可读存储介质和计算机程序产品
US20250139162A1 (en) Systems and methods for browser extensions and large language models for interacting with video streams
CN112580359A (zh) 计算机实施的方法、训练系统和计算机程序产品
US20250181622A1 (en) Method and system for dialogue data generation and processing
WO2026066806A1 (zh) 智能体的配置方法、电子设备、存储介质和产品
WO2026081624A1 (zh) 交互方法及装置、计算机可读存储介质
US20210073664A1 (en) Smart proficiency analysis for adaptive learning platforms
CN119046406A (zh) 数据查询方法、模型训练方法、装置、设备和介质
CN120151561A (zh) 基于多智能体协作的视频生成方法、装置、智能体及设备
CN118551057A (zh) 任务执行方法、装置、设备、介质和程序产品
CN115310582A (zh) 用于训练神经网络模型的方法和装置
WO2025241513A1 (zh) 文本生成方法、装置及系统、计算设备、可读存储介质
WO2026000332A1 (zh) 交互方法、电子设备、计算机可读存储介质和产品
CN117236805B (zh) 电力设备控制方法、装置、电子设备和计算机可读介质
WO2025222452A1 (zh) 交互方法、装置、电子设备、存储介质和程序产品
WO2025222439A1 (zh) 多媒体内容的推荐方法、装置、电子设备、存储介质
WO2025255811A1 (zh) 通话方法、电子设备、存储介质和产品
CN118714397A (zh) 生成视频的方法、装置、设备和介质
CN117251639A (zh) 内容推荐方法、推荐模型的训练方法、装置、介质及设备
WO2023244538A1 (en) Generating cross-domain guidance for navigating hci's

Legal Events

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

Ref document number: 24943923

Country of ref document: EP

Kind code of ref document: A1