Interaction method, electronic device, computer-readable storage medium, and product

Abstract

The present disclosure relates to the technical field of computers, and relates to an interaction method, an electronic device, a computer-readable storage medium, and a product. The interaction method comprises: on the basis of a task theme, generating for a user a task of each sub-period in a period; within each sub-period, displaying on a dialogue interface a first message sent by an agent to the user, the first message comprising the task of the sub-period; displaying on the dialogue interface a second message sent by the user to the agent, the second message being used for providing feedback for the task of a current sub-period; and, in response to the second message, displaying on the dialogue interface a third message sent by the agent to the user, the third message comprising the task progress of the user within the current sub-period.

Description

Interaction method, electronic device, computer-readable storage medium and product TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to an interaction method, an electronic device, a computer-readable storage medium and a product. BACKGROUND

[0002] With the development of computer and Internet technology, users can use various applications in computers, mobile phones, tablet computers and the like to learn or entertain. For example, a user can follow a fitness application to exercise, or learn English through a language learning application. Some applications provide some exercises or learning courses, and the user can follow the progress of the course to learn. Usually, these courses set a fixed interaction mode. For example, for a fitness exercise course, the user can perform an action by wearing a wearable device to reflect the exercise result of the user through the data collected by the wearable device. For example, for a learning course, the user can feed back the answers provided by the user through the submission of a form on a specified test page.

[0003] SUMMARY

[0004] This summary is provided to introduce a selection of concepts, which will be described with greater specificity below in the detailed description section. This summary does not intend to identify key or essential features of the claimed technology nor does it intend to limit the scope of the claimed technology.

[0005] According to some embodiments of the present disclosure, an interaction method is provided, comprising: generating, for a user, a task in each sub-period in a period according to a task theme; displaying, in each sub-period, a first message sent by an agent to the user in a dialogue interface, the first message comprising a task of the sub-period; displaying a second message sent by the user to the agent in the dialogue interface, the second message being used to feed back the task of the current sub-period; and displaying, in response to the second message, a third message sent by the agent to the user in the dialogue interface, the third message comprising a task progress of the user in the current sub-period.

[0006] According to some embodiments of the present disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the method of any of the embodiments described in the present disclosure based on instructions stored in the memory.

[0007] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, having stored thereon a computer program, the program being executed by a processor to perform the method of any of the embodiments described in the present disclosure.

[0008] According to some embodiments of the present disclosure, a computer program is provided, comprising instructions which, when executed by a processor, cause the processor to perform the method of any of the embodiments described in the present disclosure.

[0009] Other features, aspects, and advantages of the present disclosure will become apparent from the following detailed description of the exemplary embodiments of the present disclosure with reference made to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0010] The preferred embodiments of the present disclosure will be described herein below with reference to the accompanying drawings. The accompanying drawings are used in the description of the preferred embodiments of the present disclosure to provide a further understanding of the present disclosure, and together with the specific description of the preferred embodiments below and the appended claims, form a part of the description of the present disclosure. It should be understood that the accompanying drawings only relate to some embodiments of the present disclosure and do not limit the present disclosure. In the drawings:

[0011] FIG. 1 shows a flowchart of an interaction method according to some embodiments of the present disclosure.

[0012] FIG. 2 shows a flowchart of a task generation method according to some embodiments of the present disclosure.

[0013] FIG. 3 shows a flowchart of a user base information determination method according to some embodiments of the present disclosure.

[0014] FIG. 4 shows a flowchart of a task generation method according to some other embodiments of the present disclosure.

[0015] FIG. 5 shows a flowchart of a task progress determination method according to some embodiments of the present disclosure.

[0016] FIG. 6 shows a flowchart of a task adjustment method according to some embodiments of the present disclosure.

[0017] FIGS. 7A and 7B show schematic diagrams of a dialog interface according to some embodiments of the present disclosure.

[0018] FIG. 8 shows a structural diagram of an interaction device according to some embodiments of the present disclosure.

[0019] FIG. 9 shows a structural diagram of an electronic device according to some embodiments of the present disclosure.

[0020] FIG. 10 shows a structural diagram of a computer system according to some embodiments of the present disclosure.

[0021] It should be understood that the sizes of the various portions shown in the drawings are not necessarily drawn to scale. Identical or similar reference numerals are used to denote identical or similar components throughout the various drawings. Thus, once a component is defined in one drawing, it can not be discussed further in subsequent drawings. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, but not all the embodiments. The description of the embodiments below is actually only illustrative, but not as any limitation on the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein.

[0023] It should be understood that each of the steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. Unless otherwise specified, the relative arrangement of the components and steps set forth in these embodiments, numerical expressions, and numerical values should be interpreted as merely exemplary, not limiting the scope of the present disclosure.

[0024] The term "comprise" and variations of the term, such as "comprising", "includes", "including" and "contains", "containing", used in the present disclosure means an open term that includes at least the recited elements, but does not exclude other elements. In addition, the term "comprise" and variations of the term used in the present disclosure means an open term that includes at least the recited elements, but does not exclude other elements, i.e. "comprise but not limited to". Therefore, inclusion and inclusion are synonymous. The term "based on" means "at least partially based on".

[0025] Throughout the specification, the term "one embodiment", "some embodiments" or "embodiments" means that the specific features, structures or characteristics described in connection with the embodiment are included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Moreover, the appearance of the phrase "in one embodiment", "in some embodiments" or "in embodiments" in various places throughout the specification does not necessarily refer to the same embodiment, but can refer to one of the same embodiments.

[0026] It should be noted that the "first", "second", and the like concepts mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, "first", "second", and the like concepts are not intended to imply a given order or any other manner of given order in time, space, ranking or any other manner.

[0027] It should be noted that the modification of "one" and "multiple" mentioned in the present disclosure is illustrative rather than restrictive, and those skilled in the art should understand that "one or more" should be understood unless the context clearly indicates otherwise.

[0028] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0029] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics can be combined by any suitable means from the present disclosure that is clear to those skilled in the art.

[0030] In the related art, although the application provides rich courses for the user, the user needs to learn how to use the course function of the application and provide feedback in a fixed form. Moreover, the type of course provided by the application is limited, and it is difficult to provide flexible interaction.

[0031] With the development of artificial intelligence technology, objects driven by artificial intelligence can have rich interactions with users. For example, intelligent customer service can answer questions about products generated by users, and translation assistants can translate languages input by users into other languages.

[0032] In the related art, the interaction between the user and the intelligent agent is usually within a relatively short specific period of time. For example, when the user has an interaction demand with the intelligent agent, the user finds the intelligent agent and sends a message to it, and the intelligent agent responds to the message sent by the user. After the user's inquiry is answered, the user will exit the dialogue interface, and the next time the user needs the intelligent agent, the user will actively open the dialogue interface with the intelligent agent. That is, in the current intelligent agent interaction, the intelligent agent is still in a relatively passive state. The intelligent agent in some applications can occasionally actively push messages to the user, but is usually used to push news and does not involve long-term learning plans for the user.

[0033] In order to provide a more flexible task scheduling and task completion mechanism for the user, the embodiments of the present disclosure utilize the dialogue function between the user and the intelligent agent to generate and publish tasks, and receive feedback from the user, so as to save the cost of the user's understanding, operation and execution of the task, and improve the efficiency of task completion and user experience.

[0034] First, some concepts related to the present disclosure are explained.

[0035] An agent is an entity capable of autonomously performing a task in a specific environment. The agent is capable of generating content corresponding to a dialogue based on the dialogue sent by other subjects in the dialogue scenario, such as users or agents participating in the dialogue. The agent can be implemented in software, hardware, or a combination of software and hardware. The agent can also be referred to as a digital human, a robot, an agent, a virtual agent of a machine learning model. The agent can be implemented based on a machine learning model, such as a large language model (LLM) or a foundation model. The machine learning model can be a generative model.

[0036] A generative model is used to output target content based on input information. The input information of the generative model includes the basis for processing in the generation process of the generative model, such as messages sent by other subjects in the dialogue, requirements for the output content, and the like. The generative model includes, for example, a model for generating based on text or a model for generating based on images, and the output of the generative model can include text, images, or a combination of the two. Of course, the input or output of the generative model can also be other modal data, such as audio, video, or a combination of multiple types of data. The generative model can be a single-modal model, such as a model for generating text based on text (referred to as a "text-to-text model"), a model for generating images based on images (referred to as an "image-to-image model"), or a cross-modal model, i.e., a model in which the input and output belong to different modalities, such as a model for generating images based on text (referred to as a "text-to-image model"). Alternatively, the input of the generative model can include multiple modalities, and the output can also include multiple modalities.

[0037] The following describes an embodiment of the interaction method of the present disclosure with reference to FIG. 1.

[0038] FIG. 1 shows a flowchart of an interaction method according to some embodiments of the present disclosure. As shown in FIG. 1, the interaction method of this embodiment includes steps S102-S108.

[0039] In step S102, tasks for each sub-period in a period are generated for a user according to a task theme.

[0040] The task theme is used to represent the core word, keyword, or the like of the task to be performed. Each task theme can belong to one or more task types, each task type can include one or more task themes, or include one or more subcategories, and each subcategory includes one or more task themes. For example, in the learning task type, multiple subcategories such as mathematics learning, English learning, and article learning can be included, and in English learning, multiple themes such as English words, English listening, middle school English, and college English can be included.

[0041] The task topic can be provided and input by the user, can be provided by the application with a specified task topic, or can be provided by the application with one or more candidate topics and selected by the user.

[0042] In some embodiments, step S102 is performed in response to the user sending an instruction to the agent to create a task. The user triggers the process of task generation, for example, by sending a message in the dialogue interface with the agent. Alternatively, the agent automatically performs the process of task generation in response to the display of the dialogue interface.

[0043] One agent can provide the user with one or more specified types of tasks, or one or more specified task topics. That is, when the user wants to make a plan through the agent, the user can interact with a specified type of agent. For example, when the user wants to complete the task of learning English, the user triggers the generation of the task by interacting with the "English learning" agent. Of course, some agents can also support the user's free input to generate various types of tasks without the user searching for a dedicated agent.

[0044] The generated task covers a period of time, and in each sub-period of the period, the user needs to send a message for feedback. The length of the period can be specified by the user, for example, the user sends a message "I want to make a 20-day English learning plan", and the length of the period is 20 days. Alternatively, the length of the period can be default, for example, for a task generated during the summer vacation, the period can be the summer vacation. Alternatively, the length of the period can be determined according to the task topic, for example, the agent determines the period by counting the historical tasks of the task topic, or determines the period according to the characteristics of the task topic. Similar to the length of the period, the length of the sub-period can also be determined in various ways. The length of the sub-period can be default, for example, a day or a week is set as a sub-period by default; alternatively, the length of the sub-period can be specified by the user or determined by the agent.

[0045] In some embodiments, a machine learning model (such as a generative model) can be used to generate the task. For example, the generative model is used to process the task topic, or the task topic and the user-authorized information, to obtain the generated task. For another example, a pre-set task corresponding to the task topic can be read, and the pre-set task can be adjusted according to the user-authorized information, and the adjustment process can be completed using the generative model. That is, the pre-set task and the user-authorized information are input into the generative model to obtain the adjusted task. The user-authorized information includes, for example, the user's historical dialogue with the agent, the user's publicly disclosed basic information, and the like.

[0046] When generating the task, the task of each sub-period can be directly generated, or the task of the period can be generated, and then the task is allocated to each sub-period.

[0047] The generated task includes description information of the task, which can include reference resources required by the user when performing the task, execution manners of the reference resources, and the like. For example, for a word learning task, the generated task includes a list of words that the user needs to learn every day in a period, and indicates that the user needs to memorize these words, so the reference resource is the list of words, and the execution manner is memorization; for example, for a fitness task, the task of a certain sub-period is to do 5 sets of deep squats, 5 sets of push-ups, and 2 sets of stretching, so the reference resource can include the words “deep squats”, “push-ups”, and “stretching”, and can further include specific descriptions of these actions or action essentials represented by images or videos, and the execution manner is to do these actions and the number of times each action needs to be done. For some categories, if the execution manner is very clear, the execution manner can also not be included. For example, in the case where the user clearly indicates that the current task is a word learning task, only the list of words can be displayed. Those skilled in the art can make selections as needed.

[0048] In some embodiments, the task can also include a task feedback manner, such as which data format of text, voice, image, video, requirement for content amount, and the like.

[0049] After generating the task of each sub-period, the task can be saved, for example, stored in a server or locally on a user device. When each sub-period arrives, the task corresponding to the current sub-period is read from the stored data and sent to the user. After initially generating the task, all tasks in the period can be sent to the user for preview, or summaries of all tasks can be sent to the user for preview, or no preview can be sent to the user.

[0050] In step S104, in each sub-period, a first message sent by the intelligent agent to the user is displayed on the dialogue interface, and the first message includes the task of the sub-period.

[0051] The first message can include one or more of text, sound, image, video, link, and file. In the absence of specific instructions, the message in the embodiments of the present disclosure refers to a dialogue message in a dialogue interface. The messages sent between the intelligent agent and the user are displayed in the dialogue interface (also referred to as the chat interface).

[0052] The task generated in step S102 can be represented in the form of a message, that is, the generated task can be directly carried by the first message and sent to the user. Alternatively, the generated task can be formatted data that includes key content of the task, such as reference resources, execution manners, and the like. Then, the formatted data is converted into the first message by a front end such as an application.

[0053] The agent sends a message in the dialogue, so that the user can receive the task of each sub-period in time if the user device allows the agent to use the notification permission. For example, the user can obtain the task of the current sub-period in time even if the user device is not used or the user uses other applications other than the application in which the agent is located.

[0054] In some embodiments, the message sent by the agent can also be marked with a type, such as a task message and a non-task message, and the user can separately set the use of the notification permission for the task message. Thus, the task message sent by the agent can be set to use the notification permission, and the non-task message can not use the notification permission, so that the user can receive the task in time while reducing the disturbance to the user.

[0055] After receiving the first message, the user can further interact with the agent for the task of the current sub-period through the dialogue with the agent. For example, the user can send a message to the agent in response to the user's doubts or in response to the user's desire to adjust the task of the current sub-period. Through semantic understanding of the message sent by the user, the agent can send a corresponding feedback message to the user.

[0056] Taking a task of the type of exercise as an example, the task of a certain day includes doing exercise A. However, when the user does the action A, the user finds that the action is not standard and cannot be corrected by himself / herself, at which time the user can send a message to the agent to ask the agent to send more reference videos, or send a video of the user doing action A to ask the agent to point out the problems therein.

[0057] Therefore, by displaying the first message sent by the agent in the dialogue interface to issue the task, the user can interact with the agent to provide more information for the user to better complete the task.

[0058] In step S106, the second message sent by the user to the agent is displayed in the dialogue interface, and the second message is used to feed back the task of the current sub-period.

[0059] In embodiments of the present disclosure, the user can send feedback through one or more messages, or can feed back in various data formats such as text, voice, image, video, and file. Moreover, if the message sent by the user does not meet the requirements of the task feedback or the user needs to further feed back more information, the agent can send a message to the user to prompt the user to meet the requirements of the feedback or the content that needs to be modified. Thus, through the dialogue interface with the agent, the user can conveniently and efficiently feed back complete information.

[0060] Since some agents support interactions other than task functions, such as chatting unrelated to the task, in addition to task functions, the message sent by the user can be analyzed semantically to determine the relevance of the content of the message to the task of the current sub-period, to determine whether the message sent by the user is feedback for the task.

[0061] In the related art, the application usually provides fixed feedback interfaces for the user to feed back the results, and these feedback interfaces include some forms with requirements such as format and word count, and data verification is performed before the form is submitted. If the content filled or uploaded by the user does not meet the requirements, it may not be possible to submit. In the embodiments of the present disclosure, the user sends a second message through the dialogue interface to feed back the task, which can more flexibly and simply send the results of the task feedback. Even if the content of the feedback does not meet the requirements, the agent can further dialogue with the user to guide the user to upload information that meets the requirements.

[0062] In step S108, in response to the second message, a third message sent by the agent to the user is displayed on the dialogue interface, and the third message includes the task progress of the user in the current sub-period.

[0063] After the user sends the second message, the agent can reply through the third message to explicitly indicate to the user whether the task in the current sub-period is completed or not, or the completion degree, so as to facilitate the user to understand the task completion situation.

[0064] In some embodiments, the second message can be parsed to determine whether the user's feedback is related to the task theme or the task in the current sub-period. In the related case, some features in the user's feedback can be further determined and matched with the features of the task to determine the completion degree of the user.

[0065] According to the needs, in addition to the progress of the sub-period, the third message can also include the total progress of the user on the task of the entire period. The agent can pass the task progress to the user through one or more messages.

[0066] The above embodiments generate tasks according to task themes, and complete task issuance and task feedback through the dialogue interface between the user and the agent, which facilitates the user to obtain and execute the task. Therefore, each link of the publication and completion of the task can be realized through the dialogue between the agent and the user, and various forms of data sent by the user can be supported. Therefore, the cost of understanding, operating and executing the task of the user is saved, and the efficiency of task completion and user experience are improved.

[0067] The following describes the task generation method of some embodiments of the present disclosure, taking the generated task including reference resources and execution modes as an example.

[0068] FIG. 2 shows a flowchart of a task generation method according to some embodiments of the present disclosure. As shown in FIG. 2, the task generation method of this embodiment includes steps S202-S206.

[0069] In step S202, a reference resource corresponding to a task theme is determined.

[0070] The reference resource refers to information that needs to be referred to when performing a task, which can be represented in any format such as text, voice, image, video, file, link, or a combination thereof. The reference resource corresponding to each task theme can be set in advance and saved. Alternatively, after determining the task theme used by the user, information related to the task theme can be searched in a resource library or a search engine.

[0071] In addition to matching the task theme, the reference resource can also meet other conditions. In some embodiments, the resource corresponding to the task theme can be determined first; then the reference resource is determined from the resource corresponding to the task theme according to at least one of the user's basic information and the length of the period. The resource corresponding to the task theme can be set in advance, or the resource can be searched in a resource library or a search engine using the task theme or associated words of the task theme.

[0072] The length of the period can be used as a basis for determining the resource amount of the reference resource, for example, under the condition that other conditions remain unchanged, the length of the period is positively correlated with the resource amount. Of course, the length of the period can also affect the type of reference resource. For example, for the task of "watching movies", in the case of a relatively short period, a list of classic movies can be provided for the user; in the case of a relatively long period, a list of classic movies and niche movies can be provided for the user.

[0073] The user's basic information is used to represent the user's basic knowledge or basic ability in this task theme, which can be represented by a score, a level, or a specific description. For example, for a primary school student user and a college student user, their basic information is different when making an English learning plan, so the reference resources provided for the users are also different.

[0074] In some embodiments, the basic information of the user in the task topic is determined according to at least one of historical interaction records of the agent with the user, and attribute information of the user authorized by the user. The historical interaction records are, for example, chat records of the user with the current agent or other agents, or information created by the user for the agent, which should be authorized by the user. The historical interaction records can be obtained from all chat records of the user with the agent, or from chat records related to the task topic. The attribute information of the user includes, for example, hobbies, personal descriptions and other information filled in by the user in the application and authorized to be public. Alternatively, it is user portrait information generated according to various operations of the user in the application and authorized by the user.

[0075] FIG. 3 shows a flowchart of a method for determining user basic information according to some embodiments of the present disclosure. As shown in FIG. 3, the method for determining user basic information of this embodiment includes steps S302 to S304.

[0076] In step S302, the agent sends one or more questions associated with the task topic to the user in the dialogue interface.

[0077] For example, step S302 can be performed in response to the user selecting the task topic. Alternatively, step S302 can also be performed in response to the dialogue between the agent and the user involving the task topic.

[0078] The one or more questions can be determined according to one or more dimensions of the task topic, which can include time, difficulty, objective data and other information. For example, for an English learning type of task topic, questions such as how many years of English learning, what exams have been passed, vocabulary size, etc. can be asked. In addition, these questions can also be some tests. These questions can be carried by messages sent by the agent.

[0079] In step S304, the basic information of the user in the task topic is determined based on the answers sent by the user to the questions.

[0080] The answers of the user can be carried by messages sent by the user. That is, the agent and the user complete the question and answer about the task topic through dialogue. One determination method is to determine the basic information of the user based on the questions to which the user gives affirmative answers or correct answers, so as to accurately determine the information mastered by the user. Another determination method is to calculate the score or level of the user based on the answers of the user as the basic information of the user.

[0081] By using the way of the agent conversing with the user to determine the basic information of the user, the basic information of the user can be determined in a manner easy for the user to understand and feedback. Moreover, the determined basic information can indirectly improve the accuracy of task generation. Therefore, the efficiency of task generation and the interactive experience of the user are improved.

[0082] In step S204, the execution manner of the reference resource is determined according to the task type to which the task theme belongs.

[0083] Different task types can be set with the same or different execution manners. The execution manner of the reference resource corresponding to each task type can be specified in advance. The task type to which the task theme belongs can be preset, or can be obtained by performing semantic analysis or classification on the task theme. When performing semantic analysis, a semantic analysis model or a generative model can be used. When performing classification, a classification model can be used to divide the task theme into one or more of the preset task types.

[0084] The execution manner of the reference resource corresponding to several task types is described below.

[0085] In response to the task theme belonging to the learning type, the execution manner of the reference resource is determined as completing a test corresponding to the reference resource, such as word dictation, poem recitation, etc. In response to the task theme belonging to the sports type, the execution manner of the reference resource is determined as sending an image or video of the user performing an action corresponding to the reference resource, such as uploading an image or video of fitness. In response to the task theme belonging to the appreciation type, the execution manner of the reference resource is determined as sending the user's understanding information of the reference resource, such as sending a reading after a movie or a book.

[0086] In step S206, the task of each sub-period in the period is generated for the user based on the reference resource and the execution manner. For example, the reference resource of the current sub-period and the execution manner are indicated in the task of each sub-period.

[0087] Through the above embodiment, the task including the reference resource and the execution manner can be generated, so that when the task is published, the content of the task and how to complete the task can be effectively delivered to the user, reducing the understanding cost of the user and improving the efficiency of task execution.

[0088] When generating the task, each sub-period task can be directly generated, or all tasks can be generated first and then distributed to each sub-period. The implementation method of the latter way is described below with reference to FIG. 4.

[0089] FIG. 4 shows a flowchart of a task generation method according to some embodiments of the present disclosure. As shown in FIG. 4, the task generation method of this embodiment includes steps S402 to S406.

[0090] In step S402, a periodic task and a task amount of each sub-period are generated according to a task theme and a length of the period, the periodic task including one or more sub-tasks.

[0091] Generating the periodic task according to the task theme and the length of the period refers to generating all tasks of the entire period, and dividing the tasks into one or more sub-tasks as independent and divisible units. For example, if the task of the entire period is to watch 25 movies, watching one movie can be regarded as a sub-task.

[0092] The task amount can be measured in multiple dimensions, such as the time, physical effort, or content amount of feedback consumed to complete the task, the number of reference resources, and the like. When determining the task amount of each sub-period, the characteristics of the task theme can be determined. For example, for learning types, the task amount of each sub-period can be determined according to the Ebbinghaus forgetting curve to improve learning efficiency; for appreciation tasks such as watching movies, the task amount of each sub-period can be the same. That is, the task amount of each sub-period in the period can be set to be the same or different.

[0093] When determining the task amount of each sub-period, a machine learning model can be used. For example, the task theme and the length of the period are input into a generative model or other machine learning model, and the machine learning model is instructed to generate a task amount of each sub-period that meets the characteristics of the task theme. The determination result of the task amount of each sub-period can be obtained from the output of the generative model.

[0094] In step S404, the task amount of each sub-task in the periodic task is identified.

[0095] When determining the task amount of each sub-task, the number or content amount of reference resources of the sub-task can be determined, or the reference resources and the execution method can be combined to determine the task amount. For example, the number of reference resources can be directly determined as the task amount. For another example, a machine learning model can be used to process the reference resources and the execution method of the sub-task to obtain the task amount of the sub-task.

[0096] In step S406, one or more sub-tasks are assigned to each sub-period according to the task amount of each sub-period and the task amount of each sub-task, to generate the task of each sub-period. That is, the task amount of the task assigned to each sub-period matches the task amount corresponding to the sub-period. The match refers to the equality of the two, or the difference is less than a specified value.

[0097] The above embodiment allocates periodic tasks to each sub-period according to the task amount of each sub-task, so as to generate a task arrangement that conforms to the characteristics of the task theme, improve the task execution efficiency of the user, and thus improve the user experience.

[0098] The above is the introduction of some embodiments of the task generation stage. The following describes an embodiment of determining the task progress with reference to FIG. 5.

[0099] FIG. 5 shows a flowchart of a method for determining the task progress according to some embodiments of the present disclosure. As shown in FIG. 5, the method for determining the task progress of this embodiment includes steps S502-S504.

[0100] In step S502, the second message is identified to determine the feedback provided by the user on the task in the current sub-period.

[0101] The identification of the content of the second message can be implemented by a machine learning model or a matching algorithm.

[0102] In response to the second message including text, the text can be subjected to semantic recognition or matching of keywords in the text to determine the content of the feedback. In response to the second message including voice, the voice can be subjected to voice recognition to convert it into text. In response to the second message including sound, the features such as tone, rhythm, and style in the sound can be identified to determine the content of the feedback by using the identified features. In response to the second message including an image or a video, the frames in the image or the video can be subjected to image processing such as object recognition, image segmentation, and image classification, or features such as color and texture can be extracted from the image. For a video, the time information corresponding to the processing result can be further determined.

[0103] For multimedia content such as sound, image, and video, the feedback on the task can be determined by identifying the target features in the multimedia content. In some embodiments, the target features in the multimedia content in the second message are identified according to the type of target features corresponding to the task theme, and the feedback on the task in the current sub-period is determined according to the target features.

[0104] The type of target features corresponding to the task theme can be pre-set. For example, for a sports task, the target features are the features in the video related to the user's action, and the sound features or color features are relatively unimportant. For example, for a painting appreciation task, if the user uploads a picture that he / she imitates, the contour features and line features in the image are the target features.

[0105] According to the value, quantity and other information of the target feature, the feedback of the task can be determined. For example, when determining whether the posture of the user in the image is accurate, the position of the key point in the image or the angle between the lines of the key points can be used to determine the posture of the user.

[0106] The manner of determining the feedback of the task according to the target feature will be described below in combination with several types of task subjects. For example, in response to the task subject belonging to the learning type, the accuracy of the user is determined according to the target feature as the feedback of the task in the current sub-period; in response to the task subject belonging to the sports type, the accuracy and the movement intensity of the action of the user are determined according to the target feature as the feedback of the task in the current sub-period; in response to the task subject belonging to the appreciation type, the matching degree of the semantic of the second message and the task in the current sub-period is determined according to the target feature as the feedback of the task in the current sub-period.

[0107] In step S504, the task progress of the user in the current sub-period is determined based on the feedback.

[0108] The task progress can be determined according to the feedback itself, for example, the content involved in the feedback is taken as the task progress. Alternatively, the feedback can also be compared or calculated with the task in the sub-period to determine the task progress, for example, the ratio of the task amount in the feedback to the task amount of the task in the sub-period is determined as the task progress.

[0109] Through the above embodiment, the content of the feedback of the user, that is, the content related to the completion of the task in the message sent by the user, can be determined first, and then the task progress is determined based on the feedback. Therefore, the task progress can be accurately identified, and the interaction efficiency of the user can be improved.

[0110] Although in the task generation stage, the task matched with the task subject can be generated, or in some embodiments, the task can also be generated according to the basic information of the user. However, the user may still have difficulty in completing the task due to various reasons, or the task may be too simple for the user. Therefore, in some embodiments of the present disclosure, the task to be published (i.e., the un-published task in the current sub-period) can be adjusted according to the task progress of the user. The embodiment of the task adjustment method of the present disclosure will be described below with reference to FIG. 6.

[0111] FIG. 6 shows a flowchart of the task adjustment method according to some embodiments of the present disclosure. As shown in FIG. 6, the task adjustment method of this embodiment includes steps S602 to S606.

[0112] In step S602, in each sub-period, the task of the generated sub-period is adjusted in response to the task progress of the user in the ended sub-period being lower than a first threshold or higher than a second threshold.

[0113] The first threshold is lower than the second threshold. That is, when the task is completed too quickly or too slowly, the task to be issued can be adjusted.

[0114] The task progress can be represented by a numerical value, a level, or natural language. It can simply represent data or information about the user's completion of the task, such as accuracy, the number of actions performed during exercise, and the like. Alternatively, the task progress can be determined based on data or information about the user's completion of the task and data or information corresponding to the task of the sub-period. For example, the user has performed 5 sets of actions, while the task requires 10 sets, and the task progress of the action can be determined as 50%, or as "not completed".

[0115] The completed sub-periods can be the one or more sub-periods closest to the present, or all completed sub-periods.

[0116] In step S604, a first message is determined based on the adjusted task of the sub-period.

[0117] For example, in response to the task progress being lower than the threshold, the task of the current sub-period can be reduced; in response to the task progress being higher than the threshold, the task of the current sub-period can be increased.

[0118] As needed, before determining that the task needs to be adjusted and before the adjustment is implemented, the agent can be controlled to send a confirmation message to the user to ask whether the user needs to adjust the task. Then, the message sent by the user is received and processed using a semantic analysis model to confirm whether the user confirms the adjustment. If the user confirms, the first message is determined based on the adjusted task; if the user does not want to adjust, for example, sends a message indicating refusal or does not reply to the inquiry message sent by the agent, the first message is determined based on the task before the adjustment.

[0119] In step S606, the first message sent by the agent to the user is displayed on the dialogue interface.

[0120] Through the above embodiments, the task to be issued can be flexibly adjusted according to the task progress of the user, thereby improving the flexibility of task generation and issuance, improving the task execution efficiency of the user, and improving the user experience.

[0121] The interaction process between the user and the agent will be described exemplarily below in conjunction with a schematic diagram of a dialogue interface of some embodiments of the present disclosure.

[0122] In some embodiments, one or more candidate topics provided by the agent are displayed in the conversation interface in response to the conversation interface being triggered by the user for the first time within a specified length of time; the task topic is determined from the candidate topics based on the input of the user. For example, the candidate topics can be displayed when the user opens the conversation interface with the agent for the first time, or when the user opens the conversation interface after a period of time without conversing with the agent. FIGS. 7A and 7B show schematic diagrams of a conversation interface according to some embodiments of the present disclosure.

[0123] For example, when the user opens the conversation interface 7 with the agent “Daily Words” for the first time, the agent “Daily Words” can send a conversation message 71 to the user to indicate that it has the function of generating a task plan. Then, selection controls 72 to 74 can be displayed, each including a task topic, namely “TOEFL”, “IELTS”, and “Business English”. The user can determine the selected task topic by sending a message. For example, in the example of FIG. 7A, the user can trigger the control 72 to select the task topic “TOEFL”, or can directly send a message 75 to indicate that the task topic “TOEFL” is selected.

[0124] Of course, FIG. 7A is only an example of interacting with the user using the selection controls 72 to 74. According to needs, the message 71 and the controls 72 to 74 can not be displayed, and the user can directly send a message to indicate the task topic selected by the user.

[0125] After the task topic is determined, tasks for each sub-period can be generated and issued under each sub-period. For example, the agent can send a message 76 to the user to indicate that the user needs to complete the tasks in the first sub-period, i.e., the first day. In this example, the tasks in the sub-period include a list of words as a reference resource, and “learn 25 new words every day, and review 25 words learned in the previous days every day” as an execution mode.

[0126] After the user completes the tasks, for example, after completing the learning of words, the user can send feedback through a message sending control 77. For example, the user can send a message to indicate that the agent generates test questions for the user, and then the user sends answers to complete the test.

[0127] FIG. 7B shows other contents of the conversation interface 7. As shown in FIG. 7B, after the agent sends the tasks for the first time, a component 78 can be displayed in the conversation interface 7 to confirm with the user whether to allow sending of a push related to the tasks. In the case where the user allows the push, when the tasks need to be issued in each sub-period, the user can be reminded by a system push message.

[0128] The method embodiments of the present disclosure are described above by way of example. The apparatus and device for performing the above embodiments are further described below.

[0129] FIG. 8 shows a structural schematic diagram of an interaction device according to some embodiments of the present disclosure. As shown in FIG. 8, the interaction device 8 of this embodiment includes: a generation module 801 configured to generate, for a user, a task in each sub-period of a period according to a task theme; a first display module 802 configured to display, in each sub-period, a first message sent by an agent to the user in a dialogue interface, the first message including the task of the sub-period; a second display module 803 configured to display, in the dialogue interface, a second message sent by the user to the agent, the second message being used to feed back the task of the current sub-period; and a third display module 804 configured to display, in the dialogue interface, a third message sent by the agent to the user in response to the second message, the third message including a task progress of the user in the current sub-period.

[0130] In some embodiments, the generation module 801 is further configured to: determine a reference resource corresponding to the task theme; determine an execution manner of the reference resource according to a task type to which the task theme belongs; and generate, for the user, the task in each sub-period of the period based on the reference resource and the execution manner.

[0131] In some embodiments, the generation module 801 is further configured to: determine a resource corresponding to the task theme; and determine the reference resource from the resource corresponding to the task theme according to at least one of the following: basic information of the user, and length of the period.

[0132] In some embodiments, the interaction device 8 further includes: a first determination module 805 configured to determine, for the user, the basic information in the task theme according to at least one of the following: historical interaction records of the agent and the user, and attribute information of the user authorized by the user.

[0133] In some embodiments, the first determination module 805 is further configured to: in response to the user selecting the task theme, display, in the dialogue interface, one or more questions associated with the task theme sent by the agent to the user; and determine, based on an answer of the user to the question, the basic information of the user in the task theme.

[0134] In some embodiments, the generation module 801 is further configured to: in response to the task theme belonging to a learning type, determine the execution manner of the reference resource as completing a test corresponding to the reference resource; in response to the task theme belonging to a sports type, determine the execution manner of the reference resource as sending an image or a video of the user performing an action corresponding to the reference resource; and in response to the task theme belonging to an appreciation type, determine the execution manner of the reference resource as sending understanding information of the user on the reference resource.

[0135] In some embodiments, the generating module 801 is further configured to: generate, according to the task theme and the length of the cycle, the task of the cycle and the task amount of each sub-cycle, the task of the cycle including one or more sub-tasks; identify the task amount of each sub-task in the task of the cycle; and allocate the one or more sub-tasks into each sub-cycle according to the task amount of each sub-cycle and the task amount of each sub-task, to generate the task of each sub-cycle.

[0136] In some embodiments, the first displaying module 802 is further configured to: in each sub-cycle, in response to the task progress of the user in the ended sub-cycle being lower than a first threshold or higher than a second threshold, adjust the generated task of the sub-cycle; determine a first message based on the adjusted task of the sub-cycle; and display the first message sent by the intelligent agent to the user in the dialogue interface.

[0137] In some embodiments, the interaction device 8 further comprises a second determining module 806 configured to identify a second message to determine the feedback of the user on the task in the current sub-cycle; and determine the task progress of the user in the current sub-cycle based on the feedback.

[0138] In some embodiments, the second message includes multimedia content, and the second determining module 806 is further configured to: identify a target feature of the multimedia content in the second message according to the type of the target feature corresponding to the task theme; and determine the feedback on the task in the current sub-cycle according to the target feature.

[0139] In some embodiments, the second determining module 806 is further configured to: in response to the task theme belonging to a learning type, determine the accuracy of the user according to the target feature as the feedback on the task in the current sub-cycle; in response to the task theme belonging to a sports type, determine the accuracy of the action and the movement strength of the user according to the target feature as the feedback on the task in the current sub-cycle; and in response to the task theme belonging to an appreciation type, determine the matching degree between the semantics of the second message and the task in the current sub-cycle according to the target feature as the feedback on the task in the current sub-cycle.

[0140] In some embodiments, the interaction device 8 further comprises a third determining module 807 configured to: in response to the dialogue interface being triggered by the user for the first time within a specified time length, display one or more candidate themes provided by the intelligent agent in the dialogue interface; and determine the task theme from the candidate themes based on the input of the user.

[0141] It should be noted that the above-mentioned various units are only logical modules according to the specific functions they implement, and are not intended to limit the specific implementation manner, for example, they can be implemented in software, hardware or a combination of software and hardware. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned various units are indicated by dashed lines in the drawings, indicating that these units can not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0142] In addition, although not shown, the device can also include a memory, which can store various information generated by the device, the units included in the device in operation, programs and data for operation, data to be transmitted by the communication unit, etc. The memory can be a volatile memory and / or a non-volatile memory. For example, the memory can include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), a flash memory. Of course, the memory can also be located outside the device. Alternatively, although not shown, the device can also include a communication unit, which can be used for communication with other devices. In one example, the communication unit can be implemented in a suitable manner known in the art, for example, including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. Here will not be described in detail. In addition, the device can also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. Here will not be described in detail.

[0143] Some embodiments of the present disclosure also provide an electronic device. FIG. 9 shows a structural schematic diagram of an electronic device according to some embodiments of the present disclosure. For example, in some embodiments, the electronic device 9 can be various types of devices, for example, can include but not limited to various types of mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and various types of fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 9 can include a display panel for displaying data and / or execution results utilized in the scheme according to the present disclosure. For example, the display panel can be various shapes, such as a rectangular panel, an oval panel, or a polygonal panel, etc. In addition, the display panel can not only be a flat panel, but also a curved panel, or even a spherical panel.

[0144] As shown in FIG. 9, 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 FIG. 9 are merely exemplary and non-limiting, and the electronic device 9 can also have other components according to actual application needs. The processor 92 can control other components in the electronic device 9 to perform desired functions.

[0145] In some embodiments, the memory 91 is configured to store one or more computer readable instructions. When the processor 92 executes the computer readable instructions, the computer readable instructions are executed by the processor 92 to implement the method according to any of the above embodiments. For specific implementation of each step of the method and related explanations, please refer to the above embodiments, and the repeated parts will not be described here.

[0146] For example, the processor 92 and the memory 91 can directly or indirectly communicate with each other. For example, the processor 92 and the memory 91 can communicate through a network. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 92 and the memory 91 can also communicate with each other through a system bus, and the present disclosure does not limit the processor 92 and the memory 91.

[0147] For example, the processor 92 can be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processing unit (NP), etc.; and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic component, a discrete hardware component. The central processing unit (CPU) can be X86 or ARM architecture, etc. For example, the memory 91 can include any combination of various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The memory 91 may, for example, include system memory, which stores, for example, an operating system, application programs, a boot loader, a database, and other programs, etc. Various application programs and various data, etc. can also be stored in the storage medium.

[0148] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, when implemented by software and / or firmware, can be installed from a storage medium or a network to a computer system with a dedicated hardware structure, such as the computer system 100 shown in FIG. 10, which, when various programs are installed, can perform various functions, including functions such as those described above, etc. FIG. 10 shows a structural schematic diagram of a computer system according to some embodiments of the present disclosure.

[0149] In FIG. 10, a central processing unit (CPU) 1001 performs various processing in accordance with a program stored in a read only memory (ROM) 1002 or a program loaded from a storage section 1008 to a random access memory (RAM) 1003. In the RAM 1003, data required when the CPU 1001 performs various processing and the like is also stored as necessary. The central processing unit is merely exemplary, and can also be other types of processors, such as the various processors described above. The ROM 1002, the RAM 1003, and the storage section 1008 can be various forms of computer readable storage media, as described below. Note that, although the ROM 1002, the RAM 1003, and the storage 1008 are shown separately in FIG. 10, one or more of them can be combined or located in the same or different memory or storage modules.

[0150] The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output interface 1005 is also connected to the bus 1004.

[0151] The following components are connected to the input / output interface 1005: an input section 1006, such as a touch panel, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; an output section 1007, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage section 1008, including a hard disk, a magnetic tape, and the like; and a communication section 1009, including a network interface card, such as a LAN card, a modem, and the like. 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 are shown in FIG. 10 as communicating via the bus 1004, they can also communicate through a network or other means, where the network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0152] A drive 1010 is also connected to the input / output interface 1005 as necessary. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is attached to the drive 1010 as necessary, so that a computer program read therefrom is installed in the storage section 1008 as necessary.

[0153] In the case where the above-described series of processing is implemented by software, the program constituting the software can be installed from a network, such as the Internet, or a storage medium, such as the removable medium 1011.

[0154] According to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the CPU 1001, the above-described functions defined in the methods of the embodiments of the present disclosure are executed.

[0155] Note that, in the context of the present disclosure, a computer readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable medium can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport 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 can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency), or any suitable combination thereof.

[0156] The above-described computer readable medium can be included in the above-described electronic device; or can exist separately from the electronic device and not be assembled into the electronic device.

[0157] In some embodiments, a computer program including instructions which, when executed by a processor, causes the processor to carry out the method of any of the above embodiments is also provided. For example, the instructions can be embodied in a computer program code.

[0158] In an embodiment of the disclosure, computer program code to carry out operations of the disclosure can be written in one or more programming languages, or combinations thereof, including object oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0159] The flow diagrams and the block diagrams in the drawings are illustrations of possible architectures, functions, and operations for systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0160] The modules, components or units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module, component or unit does not constitute a limitation on the module, component or unit itself.

[0161] The functionality described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, non- transitory machine-readable media can include RAM, ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray, or another non-transitory medium suitable for storing non-transitory program code, wherein the above aforementioned memory is on a machine readable medium.

[0162] The above description is only some embodiments of the present disclosure and an explanation of the principles of the technology used. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with each other to form technical solutions with similar functions disclosed in the present disclosure (but not limited to).

[0163] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

[0164] In addition, while operations are depicted in a particular order, this should not be understood as requiring these operations to be performed in the particular order shown or in sequential order, as some other operations can be performed in parallel or concurrently. Additionally, although described above in the context of certain implementations, it should be appreciated that certain features of the implementations described above can be combined with or substituted for features of other implementations described above. For example, the features of one implementation can be applied to another implementation. Furthermore, while the above examples are described in the context of particular implementations, those skilled in the art will appreciate that the above examples are illustrative only and not exclusive. Many other implementations are possible without departing from the scope and spirit of the disclosure.

[0165] While certain aspects of the disclosure have been described above with particular emphasis, it will be appreciated that the examples provided are for illustration only and are not limiting of the scope of the disclosure. Those skilled in the art will understand that modifications can be made in the above embodiments without departing from the scope and spirit of the disclosure. The scope of the disclosure is defined by the appended claims.

Claims

1. An interaction method, comprising: Based on the task theme, generate tasks for each sub-cycle within the user's cycle; Within each sub-cycle, the first message sent by the agent to the user is displayed on the dialogue interface, the first message including the task of the sub-cycle; The dialogue interface displays a second message sent by the user to the agent, which is used to provide feedback on the task of the current sub-cycle. 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 including the user's task progress in the current sub-cycle.

2. The interaction method according to claim 1, wherein, The process of generating tasks for each sub-cycle within a user's cycle based on the task theme includes: Identify the reference resources corresponding to the task topic; Based on the task type to which the task topic belongs, determine the execution method for the reference resource; Based on the reference resources and the execution method, tasks for each sub-cycle in the user's cycle are generated.

3. The interaction method according to claim 2, wherein, The reference resources corresponding to the task topic include: Identify the resources corresponding to the task topic; The reference resource is 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.

4. The interaction method according to claim 3 further includes: Based on at least one of the following: the historical interaction records between the agent and the user, and the attribute information of the user authorized by the user, the basic information of the user in the task topic is determined.

5. The interaction method according to claim 4, wherein, Based on the historical interaction records between the agent and the user, the user's basic information in the task topic is determined as follows: In response to the user selecting the task topic, the agent displays on the dialog interface that it sends one or more questions related to the task topic to the user. Based on the user's answer to the question, the user's basic information in the task topic is determined.

6. The interaction method according to any one of claims 2 to 5, wherein, The step of determining the execution method for the reference resource based on the task type to which the task topic belongs includes: Since the task topic belongs to the learning type, the execution method for the reference resource is determined to be to complete the test corresponding to the reference resource; In response to the fact that the task topic belongs to the motion type, the execution method of the reference resource is determined to send an image or video of the user performing an action corresponding to the reference resource; Since the task topic belongs to the appreciation type, the execution method for the reference resource is determined to be sending the user's understanding information about the reference resource.

7. The interaction method according to any one of claims 1 to 6, wherein, The process of generating tasks for each sub-cycle within the user's cycle based on the task theme includes: Based on the task topic and the length of the period, generate the tasks for the period and the task quantity for each sub-period, wherein the tasks for the period include one or more sub-tasks; Identify the workload of each subtask within the tasks of the cycle; Based on the task volume of each sub-cycle and the task volume of each sub-task, the one or more sub-tasks are allocated to each sub-cycle to generate the task for each sub-cycle.

8. The interaction method according to any one of claims 1 to 7, wherein, The first message sent by the agent to the user in the dialogue interface during each sub-cycle includes: 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 message is determined based on the adjusted task of the sub-cycle; The first message sent by the agent to the user is displayed in the dialogue interface.

9. The interaction method according to any one of claims 1 to 8, further comprising: The second message is identified to determine the user's feedback on the task within the current sub-cycle; Based on the feedback, the user's task progress within the current sub-cycle is determined.

10. The interaction method according to claim 9, wherein, The second message includes multimedia content, and the step of identifying the second message to determine the user-provided feedback on the task within the current sub-cycle includes: Identify the target features of the multimedia content in the second message based on the type of target features corresponding to the task theme; Based on the target characteristics, the feedback for the task within the current sub-cycle is determined.

11. The interaction method according to claim 10, wherein, The step of determining the feedback for the task within the current sub-cycle based on the target characteristics includes: In response to the task topic belonging to the learning type, the user's accuracy is determined based on the target characteristics as feedback for the task in the current sub-cycle; In response to the task theme being a type of exercise, the accuracy and intensity of the user's actions are determined based on the target characteristics as feedback for the task within the current sub-cycle. In response to the task topic belonging to the appreciation type, the semantic matching degree between the second message and the task in the current sub-cycle is determined according to the target features, as feedback to the task in the current sub-cycle.

12. The interaction method according to any one of claims 1 to 11, further comprising: In response to the dialog interface being triggered by the user for the first time within a specified time period, one or more candidate topics provided by the agent are displayed in the dialog interface; The task topic is determined from the candidate topics based on the user's input.

13. An electronic device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the interaction method as described in any one of claims 1 to 12 based on instructions stored in the memory.

14. A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the interactive method of any one of claims 1 to 12.

15. A computer program product, when run on a computer, causes the computer to implement the interactive method of any one of claims 1 to 12.

16. A computer program comprising: Instructions, which, when executed by a processor, cause the processor to perform the interaction method according to any one of claims 1 to 12.

Images