Method, apparatus, device and storage medium for template creation

Abstract

According to embodiments of the present disclosure, a method, device, equipment and storage medium for template creation are provided. The method comprises: obtaining conversation information between a user and an agent, the conversation information indicating a task executed by the agent based on an instruction of the user; presenting template configuration information generated based on the conversation information, the template configuration information comprising at least one of a demand instruction for the agent and a task execution plan for the agent based on the demand instruction, the demand instruction being determined based on an instruction initiated by the user in the conversation information; and creating a task template based on the template configuration information.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatus, electronic devices, computer-readable storage media, and computer program products for template creation. Background Technology

[0002] With the development of information technology, an increasing number of intelligent systems are capable of completing various complex tasks based on user input. These systems typically interact with users in a dialogue format, generating responses based on the user's natural language requests, thus forming a question-and-answer dialogue. However, in practical applications, users often aim for more than just a response; they expect the system to comprehensively plan and execute a task. Therefore, improving the quality and efficiency of completing a complete task has become a crucial issue. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for template creation is provided, comprising: acquiring session information between a user and an agent, the session information instructing the agent to perform a task based on instructions from the user; presenting template configuration information generated based on the session information, the template configuration information including at least one of a requirement instruction for the agent and a task execution plan obtained by the agent based on the requirement instruction, the requirement instruction being determined based on an instruction initiated by the user in the session information; and, in response to confirmation of the template configuration information, creating a task template based on the template configuration information.

[0004] In a second aspect of this disclosure, an apparatus for template creation is provided, comprising: a session information acquisition module configured to acquire session information between a user and an agent, the session information instructing the agent to perform a task based on the user's instructions; a template configuration information presentation module configured to present template configuration information generated based on the session information, the template configuration information including at least one of a requirement instruction for the agent and a task execution plan obtained by the agent based on the requirement instruction, the requirement instruction being determined based on an instruction initiated by the user in the session information; and a task template creation module configured to create a task template based on the template configuration information.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] According to a fifth aspect of this disclosure, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method of the first aspect.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A flowchart illustrating an example process for template creation according to some embodiments of this disclosure is shown;

[0012] Figures 3A to 3H A schematic diagram of an example interface for template creation and template application according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A flowchart of a process for template creation according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A block diagram of an apparatus for template creation according to some embodiments of the present disclosure is shown; and

[0015] Figure 6 A block diagram of an electronic device capable of implementing one or more embodiments of the present disclosure is shown. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0018] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0019] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information, thereby enabling the user to choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers or storage media that perform the operation of the technical solution disclosed herein, based on the prompt message.

[0022] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0023] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0024] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0025] A neural network is a machine learning network based on deep learning. A neural network processes input and provides a corresponding output, typically consisting of an input layer, an output layer, and one or more hidden layers between the input and output layers. Neural networks used in deep learning applications often include many hidden layers, thus increasing the network's depth. The layers of a neural network are connected sequentially, so that the output of the previous layer is provided as the input to the next layer. The input layer receives the input to the neural network, while the output layer's output serves as the final output. Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each node processing the input from the layer above.

[0026] Machine learning typically comprises three phases: training, testing, and application (also known as inference). In the training phase, a given model is trained using a large amount of training data, iteratively updating its parameter values ​​until the model can consistently generate inferences that meet the expected goals from the training data. Through training, the model can be considered to have learned the relationship between inputs and outputs (also known as the input-output mapping) from the training data. The parameter values ​​of the trained model are determined. In the testing phase, test inputs are applied to the trained model to test whether it can provide the correct output, thus determining the model's performance. In the application phase, the model can be used to process actual inputs based on the trained parameter values ​​to determine the corresponding output.

[0027] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In this example environment 100, an application 125 is installed on a terminal device 110. A user 140 can interact with the application 125 via the terminal device 110 and / or an attached device of the terminal device 110.

[0028] In some embodiments, application 125 can be downloaded and installed on terminal device 110. In some embodiments, application 125 can also be accessed in other ways, such as through a web page. Figure 1In environment 100, in response to application 125 being launched, terminal device 110 can display the interface 150 of application 125.

[0029] In some embodiments, terminal device 110 may be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 may also support any type of user-facing interface (such as "wearable" circuitry).

[0030] In some embodiments, terminal device 110 communicates with server 130 to provide services to application 125. Terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 can also support any type of user-facing interface (such as "wearable" circuitry). Application 125 can be various types of computing systems / servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0031] In embodiments of this disclosure, application 125 can provide interaction functionality with an intelligent agent. Application 125 can be an application dedicated to providing intelligent agent services, or an application integrated with an intelligent agent (i.e., it can provide functions or services other than those of an intelligent agent). Although Figure 1 The image shows a single application, but in reality, multiple applications can be installed on the terminal device 110.

[0032] In this disclosure, agents 160-1, 160-2, ..., 160-N (collectively or individually referred to as agent 160) can be deployed locally on terminal device 110 or remotely. In the case of remote deployment, terminal device 110 can directly invoke the agent or invoke the agent via server 130.

[0033] In embodiments of this disclosure, agent 160 may possess intelligent dialogue and task processing capabilities. Terminal device 110 provides an interface 150 that can present interactions with agent 160. In interface 150, user 140 can submit task requests to agent 160 by inputting natural language input (text or voice input), and can also upload online or offline file conversations to instruct agent 160 to assist in completing various tasks.

[0034] In embodiments of this disclosure, during interaction with user 140, agent 160 can respond to user 140's requests and handle tasks instructed by the user. In some embodiments, during task processing, agent 160 can invoke one or more tools 165-1, 165-2, ... 165-M (collectively or individually referred to as tools 165) to assist in task execution and the provision of task results, as needed by the task. These tools 165 can be any type of tool, such as weather query tools, flight query tools, information search tools, online or offline databases, image processing tools, chart generation tools, web page creation tools, etc.

[0035] In some embodiments, environment 100 may further include a management node for a plurality of agents 160-1, 160-2, ... 160-N, which can interact with the agents 160-1, 160-2, ... 160-N. In some examples, the management node may, in response to a task request from user 140, determine the task requirements corresponding to the task request. The management node may then, based on the task requirements, assign the task request to the agent 160 that matches the task requirements, requesting that agent 160 to perform the task. In other examples, the management node may also determine an execution plan for the task based on the task requirements. The execution plan may indicate one or more subtasks required to complete the task. The management node may assign the one or more subtasks to one or more agents 160, which will then execute their respective subtasks. Regarding the management node, in some examples, the management node may be implemented by one of the agents 160-1, 160-2, ... 160-N (in this case, agent 160 is also referred to as management agent 160). In other examples, management nodes can be implemented using machine learning models, such as language models (LM) or large language models (LLM).

[0036] In some embodiments, agent 160 may be constructed based on one or more machine learning models. In some embodiments, the machine learning model upon which agent 160 is based may include at least a language model (LM). These machine learning models include content-generative models capable of generating corresponding outputs based on model inputs. In some embodiments, the language model-based machine learning model may receive text-modal model inputs (e.g., natural language and / or machine language) and / or non-text-modal model inputs (e.g., images, speech, video, etc.), and may obtain corresponding model outputs based on the model inputs and prompts, thereby completing the task execution. Here, prompts are used to guide the machine learning model to generate solutions to the user queries indicated by the model inputs. In application scenarios supporting user dialogue, user 140's input may be provided to machine learning model 160 as at least a part of the model inputs (other parts may include prompts). This user input is considered a question or query request. Based on the model outputs, corresponding responses may be provided to user 140.

[0037] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0038] As briefly mentioned earlier, users may initiate task requests within the application. In some scenarios, users can input task requirements through the application's user interface, and the agent can provide services that meet those requirements. However, the agent's response to the same input may vary, and the quality of the response is closely related to the user's task requirements. Therefore, to obtain satisfactory task execution results, users may need to continuously adjust their input instructions through multiple rounds of dialogue with the agent until the agent correctly understands the task requirements. Consequently, the same process may need to be repeated the next time the current user or another user expects to perform the same task. This leads to a decrease in overall task efficiency.

[0039] According to some embodiments of this disclosure, an improved scheme for template creation is proposed. According to the scheme of this disclosure, session information between a user and an intelligent agent is obtained, and the session information instructs the intelligent agent to complete a task based on the user's instructions. Accordingly, template configuration information generated based on the session information is presented, and the template configuration information includes at least one of a requirement instruction for the intelligent agent and a task execution plan obtained by the intelligent agent based on the requirement instruction. The requirement instruction is determined based on the instruction initiated by the user in the session information. Further, a task template is created based on the template configuration information.

[0040] In this way, by creating templates using template configuration information generated from the dialogue between the user and the agent, the quality of responses and the efficiency of answering users can be improved. Thus, when a task in which the user interacts with the agent can be completed efficiently or satisfactorily, the user can choose to create a task template from the high-quality conversation information corresponding to this task, thereby promoting the efficient completion of subsequent similar tasks in a similar manner. In this way, different task templates can be flexibly created and used for interactions with the agent for different user groups or usage scenarios, which can meet differentiated task needs and improve task execution efficiency.

[0041] In this disclosure, "trigger" refers to one or more interactive actions performed by a user on a terminal device. Furthermore, these interactive actions may be triggered within the same user interface / pop-up window or within different user interfaces / pop-up windows. This disclosure is not limited in this respect.

[0042] Some embodiments of this disclosure will now be described with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of this disclosure are not limited in this respect. Furthermore, in the following description, example embodiments will be primarily described with respect to terminal device 110. It should be understood that the actions described with respect to terminal device 110 may also be performed by application 125 on terminal device 110, or may be performed by application 125 in conjunction with its server (e.g., server 130).

[0043] In this document, terminal device 110 deploys an application 125 that supports task processing functions. User 140 can use application 125 to process tasks, such as, but not limited to, information query (e.g., obtaining real-time information such as weather forecasts and news summaries), data processing (e.g., analyzing quarterly sales reports), code execution (e.g., generating and executing simple code snippets), etc. However, these are merely examples, and this disclosure does not limit them. During the execution of the above tasks, application 125 can call a template matching the task to complete the task. The following will refer to... Figures 3E to 3H This describes how to call the template that matches the task to complete the task.

[0044] The following is for reference first. Figure 2 This disclosure describes the process used to create task templates. Figure 2 A flowchart of an example process 200 for template creation according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to... Figure 1These embodiments are described in the context of environment 100. These embodiments can be implemented in... Figure 1 There are 110 terminal devices.

[0045] In the discussion of process 200, for better understanding, we will combine... Figures 3A to 3D This will explain some embodiments of the present disclosure used for creating templates. Figures 3A to 3D Schematic diagrams of example interfaces 300A to 300D for template creation according to some embodiments of the present disclosure are shown. These example interfaces can be presented by application 125 in terminal device 110.

[0046] In embodiments of this disclosure, terminal device 110 can acquire session information between user 140 and intelligent agent 160 for creating a task template. In some examples, during interaction between user 140 and intelligent agent 160, terminal device 110 can automatically create a task template based on the session information between user 140 and intelligent agent 160. In some examples, user 140 can initiate a creation instruction for creating a task template. If terminal device 110 receives a task template creation instruction, it can acquire the session information between the user and the intelligent agent for creating the task template. In some embodiments, the session information between user 140 and intelligent agent 160 instructs intelligent agent 160 to complete a task based on user 140's instructions. In some examples, the session information may include instructions sent by user 140 indicating user needs and responses provided by intelligent agent 160 to those instructions. The session information may also include relevant information about intelligent agent 160 performing the task.

[0047] In example process 200, at block 210, user 140 can send instructions to agent 160 via input controls, indicating user needs. In some embodiments, user 140 can initiate a session with agent 160 and, during the session, can send instructions to agent 160 to instruct agent 160 to perform corresponding tasks based on the input instructions. Figure 3AAs shown, in example interface 300A, user 140 can input command 311 based on an input control (e.g., input box 310). Although not shown in the figure, in addition to direct input in the text input box, the input control can also support other input methods, such as voice input, or providing commands by uploading attachments, providing web links, etc. Accordingly, terminal device 110 can present a response message 312 for command 311 in interface 300A. In this scenario, both the user-input command 311 and the agent's response message 312 can be identified as conversation information between user 140 and agent 160. Accordingly, relevant information used by agent 160 to complete the task indicated by command 311 (this information may not be displayed to the user through the conversation) can also be identified as part of the conversation information.

[0048] In block 211, terminal device 110 receives a creation instruction for creating a task template. In some embodiments, terminal device 110 may support users initiating creation instructions in various ways. (See also...) Figure 3A If the terminal device 110 determines that at least one dialogue between the user 140 and the agent 160 has been completed, it can present a creation control 313 for creating a task template. In some embodiments, when the user 140 and the agent 160 have completed one round of dialogue, the terminal device 110 can present the creation control 313 in association with the input box 310. Of course, when the user 140 and the agent 160 have completed multiple rounds of dialogue, the terminal device 110 can also present the creation control 313 in association with the input box 310. Subsequently, the user 140 can trigger the creation control 313 to initiate a creation instruction for creating a task template. In this way, providing the creation control during the dialogue between the user 140 and the agent 160 facilitates the user initiating a creation instruction for creating a task template. Furthermore, it also facilitates the user initiating a creation instruction for creating a task template based on the dialogue information. This can improve the quality of processing other tasks that match the task template.

[0049] In some embodiments, terminal device 110 may present a prompt message associated with creation control 313. The prompt message may indicate the ability to create a task template based on session information. For example, when creation control 313 is presented for the first time, terminal device 110 may present a prompt message associated with creation control 313. This informs user 140 that the function of creating templates based on session information is enabled. That is, a task template can be created based on the result of agent 160 completing the current task. In some examples, terminal device 110 may also present a prompt message associated with creation control 313. This guides user attention to creation control 313. Of course, these prompt messages are merely examples. Any prompt message that emphasizes the creation control can be used.

[0050] Continue back Figure 2 In process 200, in box 212, if the terminal device 110 receives a trigger from user 140 to create control 313, it can generate template configuration information based on the session information between user 140 and agent 160. (Refer to...) Figure 3B Terminal device 110 can present template configuration information generated based on session information in interface 300B (e.g., it can be called configuration interface).

[0051] The template configuration information includes a requirement instruction 321 for agent 160. In some embodiments, the requirement instruction 321 may include prompt text 323 describing the requirement instruction. The prompt text 323 may, for example, indicate a description of the task that agent 160 needs to complete. In some examples, the requirement instruction 323 may include experience summarized by agent 160 based on session information. The template configuration information includes a task execution plan 322 obtained by agent 160 based on the requirement instruction 321. That is, terminal device 110 can generate a task execution plan 322 according to the requirement instruction 321. The task execution plan 322 is used to guide agent 160 to complete the task indicated by requirement instruction 321, including the subtasks included in the task and the execution steps of each subtask, and how each execution step is completed. For example, agent 160 can complete the task indicated by requirement instruction 321 according to task execution plan 322. By providing a task execution plan in the task template, the agent can execute new tasks by following the task execution plan in the task template. This saves the agent from the specific process of parsing requirement instructions and generating task execution plans.

[0052] In some embodiments, the demand instruction 321 may include at least one template parameter. The parameter value of the template parameter included in the demand instruction 321 may indicate that it can be configured when the task template is used to perform a task. In some embodiments, in a scenario where a task template is used to perform a task, the terminal device 110 may determine the parameter value of the template parameter included in the task template. Reference will be made below. Figures 3E to 3H The description details how the template parameter values ​​are determined. In some examples, the template parameters can be determined by agent 160 based on session information. Template parameters can also be configured by user 140, for example, user 140 can select a text fragment from prompt text 323 as the template parameter.

[0053] In box 213, terminal device 110 can determine whether the demand instruction 321 has been modified. During the task template creation process, user 140 can modify the prompt text 323 in the demand instruction 321. During task template creation, user 140 can perform editing operations on template parameters, such as adding or deleting template parameters. If terminal device 110 determines that the demand instruction 321 has not been modified, it can proceed to box 214. In box 214, if terminal device 110 has not received a modification instruction for the demand instruction 321, it can create a task template based on the current template configuration information. In some examples, if the demand instruction 321 has not been modified, the task execution plan included in the current task template is in a usable state. (See reference...) Figure 3B If the demand instruction 321 is not modified, the terminal device 110 can create a task template based on the demand instruction 321 and task execution plan 322 generated by the intelligent agent 160 if it receives a trigger on the creation control 324.

[0054] In some embodiments, if the terminal device 110 determines that the demand instruction 321 has been modified, it can proceed to block 215. In block 215, if the terminal device 110 receives a modification instruction for the demand instruction 321, it can create a task template based on the modified template configuration information. In some examples, if the demand instruction 321 has been modified, the task execution plan included in the current task template is in an unusable state. In some embodiments, if the terminal device 110 determines that the task execution plan 322 is in an unusable state, it can cancel the presentation of the task execution plan 322. In some embodiments, continue referring to... Figure 3B In a scenario where the demand instruction 321 is modified, if the terminal device 110 receives a trigger to create the control 324, it can create a task template based on the modified demand instruction 321 and the updated task execution plan 322. The terminal device 110 can update the task execution plan 322 according to the modified demand instruction 321.

[0055] In some embodiments, continue to refer to Figure 3BIn a scenario where the requirement instruction 321 included in the task template is edited, if the terminal device 110 receives a trigger on the creation control 324, it can create the task template based on the edited requirement instruction 321. In this scenario, the created task template may not include the task execution plan 322. It can also be understood that the task execution plan in the created task template is in an unusable state. Correspondingly, while the task execution plan 322 is in an unusable state, if the terminal device 110 receives an application instruction to execute a target task using the task template, the terminal device 110 can utilize the intelligent agent 160 to execute the target task based on the edited requirement instruction 321. In this way, the quality of the response result and the efficiency of responding to the user can be improved.

[0056] The following will refer to Figures 3B to 3C This describes how to perform editing operations on template parameters.

[0057] In some embodiments, if the terminal device 110 receives a predetermined operation on a text segment in the prompt text 323, it can identify the text segment as a template parameter in at least one template parameter. As an example, the predetermined operation could, for instance, indicate a highlighting operation on the text segment. Figures 3B to 3C In the example interfaces 300B to 300C shown, user 140 can underline text fragment 325 within the prompt text 323 to use it as a template parameter. As an example, preset actions may also include any other suitable actions capable of selecting text fragments within the prompt text 323, such as double-clicking, swiping, etc. In some examples, terminal device 110 may display a prompt message 329 on interface 300 to inform user 140 that a preset action can be used to add parameters. This provides users with a convenient and quick way to add parameters.

[0058] Reference Figures 3B to 3C Terminal device 110 can present template parameters in a predetermined style 331 within the demand instruction 321. The predetermined style 331 can be referred to as an embedding character, and can be presented as, for example, "{parameter name}". If terminal device 110 receives an operation from user 140 to add text fragment 325 as a template parameter, it can switch the presentation style of text fragment 325 to the predetermined style 331. This makes it easier for the user to know which template parameters are included in the demand instruction.

[0059] In some embodiments, template parameters can be presented in the editing area 332. Template parameters determined by the agent 160 and those added by the user 140 can both be presented in the editing area 332. The user 140 can perform editing operations on the template parameters via the editing area 332, such as editing the name, description, deleting, etc. Alternatively, the user 140 can also perform editing operations based on the template parameters presented in the prompt text 323. For example, deleting parameters and / or text fragments after underlining, copying parameters and / or text fragments after underlining, etc. The terminal device 110 can generate names for the template parameters according to predetermined values. Thus, the user can edit the template parameters in a convenient and quick manner.

[0060] The above describes the editing operations performed on the requirement instructions; the following text will continue to refer to... Figure 2 and Figure 3D To describe how to obtain the task execution plan 322.

[0061] In some embodiments, terminal device 110 may determine task execution plan 322 based on session information. In some examples, terminal device 110 may obtain task execution plan 322 based on the process of agent 160 completing the task indicated by demand instruction 321. The task execution plan 322 obtained by terminal device 110 may be generated at the server (e.g., server 130). In some examples, during the process of terminal device 110 obtaining task execution plan 322, interface 300B (e.g., a configuration interface) may be canceled to allow task execution plan 322 to be generated in the background.

[0062] In some embodiments, when the demand instruction 321 is edited, the terminal device 110 can determine that the current task execution plan 322 is unusable. In some examples, if the demand instruction 321 is edited, the current task execution plan 322 is in a failed state. The terminal device 110 can regenerate the task execution plan 322 using the intelligent agent 160 based on the edited demand instruction 321. That is, the terminal device 110 can update the task execution plan 322 using the intelligent agent 160 according to the edited demand instruction. Accordingly, after the task execution plan 322 is updated, the terminal device 110 can determine that the updated task execution plan is usable. Figure 3C As shown, in the scenario where user 140 adds the template parameter "{CCC}", if terminal device 110 receives a trigger on the creation control 324, it can obtain the task execution plan 322 based on the edited requirement instruction 321. Thus, when executing a task using the task template, the updated task execution plan ensures that the task result better meets the user's needs.

[0063] In some embodiments, if the terminal device 110 receives an edit to the session information, it can determine that the task execution plan is unusable. Further, the terminal device 110 can generate a task execution plan using the agent 160 based on the edited session information. After the task execution plan is generated, the terminal device 110 can determine that the updated task execution plan is usable. As an example, see... Figure 3D Suppose that user 140, after initiating a template creation request based on the current session interface 300D, continues to interact with agent 160 within the session interface 300D. For example, user 140 inputs more instructions (e.g., instruction 342) to correct or supplement previous requests. In this scenario, terminal device 110 can present an update control 341 in the session interface 300D for updating the task execution plan. If terminal device 110 receives a trigger on update control 341, it can update the task execution plan 322 based on the newly input instruction (e.g., instruction 342). This allows users to easily update task templates in real time.

[0064] Continuing with example process 200, in box 220, terminal device 110 can receive a selection of a task template. If terminal device 110 receives a selection of a task template, process 200 can proceed to box 221. In box 221, terminal device 110 can determine whether the task execution plan 322 for the current task template has been generated. If the task execution plan 322 for the current task template has been generated, the task template can be applied. If the task execution plan 322 for the current task template has not been generated, process 200 can proceed to box 223.

[0065] In some embodiments, at box 223, terminal device 110 may present a prompt message indicating that the task execution plan 322 of the task template is unavailable. In some examples, user 140 may initiate an update request for the task execution plan 322 based on this prompt message, so that terminal device 110 can update the task execution plan 322 based on the edited request instruction 321 or session information. At box 224, terminal device 110 may determine whether user 140 accepts the updated task execution plan 322. If user 140 accepts the updated task execution plan, process 200 may return to box 212. Understandably, terminal device 110 may create a task template based on the updated task execution plan. If user 140 does not accept the updated task execution plan, process 200 may proceed to box 225. At box 225, terminal device 110 does not update the current task template.

[0066] In the example embodiments described in boxes 221-224 above, when the requirement instruction already exists but the task execution plan is being generated, the task template can be configured to be unusable or in an incomplete creation state. Since the task template has not been completely created, it cannot be presented to the user for selection and use.

[0067] However, as described in other embodiments above, in scenarios where the requirement instructions included in the task template are edited, although the task execution plan is not generated (i.e., it is in an unusable state), if the user still chooses to create a task template, then the task template can be created solely based on the edited requirement instructions. In this scenario, the created task template may not include the task execution plan, but it can still be presented to the user for selection and use. In scenarios where a task template including an unusable task execution plan is selected, refer to... Figure 3E and Figure 3H When terminal device 110 executes a target task using a task template (e.g., task template 350) that does not include a task execution plan, terminal device 110 can execute the target task based on the requirement instructions 321 included in the task template. During the execution of the target task, terminal device 110 can use an agent to generate a task execution plan for the target task. That is, even when the task template only includes requirement instructions and not a task execution plan, a new task can still be executed by reusing the previous requirement instructions. Compared to scenarios where users need to manually input all requirement instructions when triggering a new task, the use of such task templates can still improve task execution efficiency.

[0068] Furthermore, the terminal device 110 can update the task execution plan of the task template based on the task execution plan for the target task. For example, when using the task template to complete the target task, the terminal device 110 can update the task execution plan 322 corresponding to the task template according to the target task execution plan generated by the intelligent agent 160 during the execution of the target task. For example, the target task execution plan can be included in the task execution plan of the task template. At this time, the task execution plan of the task template can be considered complete. Accordingly, the terminal device 110 can determine the updated task execution plan as usable.

[0069] In some examples, if a task execution plan for the target task has been generated, an add control 382 can be presented in the user-agent conversation interface. User 140 can choose to trigger the add control 382 to add the target task execution plan to the task template, thus giving the task template complete template configuration information. In some examples, if the target task execution plan has been generated, it can be automatically added to the task template, or a confirmation control can be displayed to allow the user to easily confirm whether to add the target task execution plan to the task template, thereby giving the task template complete template configuration information. In this way, based on the updated task execution plan, the task results can better meet the user's needs, and the quality of the response results and the efficiency of responding to the user can be improved.

[0070] In some embodiments, the template configuration information for a task template also includes authorization information regarding the scope of usability of the task template. (See also...) Figure 3B User 140 can choose whether to make the task template public based on the authorization control 326. In some embodiments, if the terminal device 110 receives a publishing instruction for the task template, it can configure the task template to be applicable within a user scope, which can be specifically specified by the publishing instruction. For example, the user scope may include, but is not limited to, fully public, partially public, visible only to the user, etc. In some embodiments, after the template is published, the creator of the task template (e.g., user 140) can also update the user scope to which the task template is applicable.

[0071] Continuing with example process 200, in box 230, terminal device 110 can receive permissions configured by user 140 regarding the scope of access to the task template. If user 140 configures the scope of access to the task template to public, then process 200 can proceed to box 231. In box 231, if terminal device 110 determines that the scope of access to the task template is configured to public, it can allow any user to perform interactions with the task template, such as, but not limited to, viewing, applying, sharing, etc.

[0072] If user 140 configures the accessibility of the task template to personal, then process 200 can proceed to box 232. In box 232, if terminal device 110 determines that the accessibility of the task template is configured to personal, it can allow user 140 to interact with the task template, such as interactions including but not limited to updating, viewing, applying, sharing, etc. If user 140 configures the accessibility of the task template to the users to whom it is shared, then process 200 can proceed to box 233. In box 233, if terminal device 110 determines that the task template is shared with other users, it can allow other users to interact with the task template, such as interactions including but not limited to viewing, applying, sharing, etc. In some examples, the users to whom the task template is shared can add the task template to their corresponding task template library. In some examples, if the creator (e.g., user 140) updates the task template, the task template at the user authorized to use the task template can also be updated in real time.

[0073] In some embodiments, refer to Figure 3B The task template configuration information also includes a name 327 for the task template. The name 327 can be determined by the agent 160 based on session information. Based on this, the user 140 can edit the name 327 of the task template. The task template configuration information also includes a label 328 for the task template. The label 328 can be determined by the agent 160 based on session information. Based on this, the user 140 can reselect the label 328 of the task template. In some examples, the label of the task template can indicate the category of the task template. This allows the user to clearly understand the constituent elements of the task template, thereby preventing the loss of key information or incorrect settings.

[0074] The above reference Figure 2 and Figures 3A to 3D The creation of task templates has been described; more references will follow below. Figures 3E to 3H This describes how to apply the task template. Figures 3E to 3H Schematic diagrams of example interfaces 300E to 300H for template applications according to some embodiments of the present disclosure are shown.

[0075] In some embodiments, if the terminal device 110 determines that the task template has been created, it can add the task template to the task template library. The task template library may include at least one task template applicable during the task execution process of the intelligent agent 160. The task template library may include templates shared by other users with user 140, and task templates created by user 140 itself. Figure 3EAs shown, the terminal device 110 can display these task templates in the template management interface 300E. In some embodiments, the terminal device 110 can display task templates according to their priority. For example, the terminal device 110 can display task templates according to the number of times they have been favorited. The terminal device 110 can also display task templates according to the order in which they were created.

[0076] In some examples, for a task template saved by user 140, terminal device 110 can display the number of times it has been created in association with the task template. For a task template created by user 140, terminal device 110 can display the number of times the task template has been saved in association with the task template. User 140 can search for task templates based on the search control 351 presented in the template management interface 300E. In some embodiments, the task template library may include various categories of task templates, such as, but not limited to, task templates for code generation, task templates for data analysis, templates for project Q&A, task templates for document writing, task templates for research and analysis, and so on.

[0077] In the template management interface 300E, the terminal device 110 can display information associated with any task template, including the task template's name, tags, generated output (e.g., a PDF document or any other suitable output), favorites control, favorite value, creator's image, share control, open control, and so on. For ease of description, the following explanation will use the task template created by user 140 (i.e., task template 350) as an example.

[0078] Reference Figures 3E to 3F In the example interfaces 300E to 300F shown, if the terminal device 110 receives a trigger on the task template 350, it can present the details interface 300F of the task template 350. For example, the user 140 can click to open the control 352 to view the details interface 300F of the task template 350. The terminal device 110 can display the template configuration information of the task template 350 in the details interface 300F, such as the requirement instruction 321 and the task execution plan 322. In some embodiments, if the task execution plan 322 of the current task template has not been generated, the terminal device 110 can display a prompt message informing the user that the task execution plan has not been generated.

[0079] Furthermore, if the terminal device 110 receives an application instruction from the application task template 350 to execute the target task, it can execute the target task using the intelligent agent 160, at least based on the template configuration information. (See also...) Figure 3FThe terminal device 110 can display at least one template parameter to be configured in the details interface 300F, such as template parameter 361, template parameter 362, etc. The terminal device 110 can determine the parameter values ​​of each template parameter through the details interface 300F.

[0080] As an example, terminal device 110 can determine the parameter values ​​of each template parameter based on the parameter values ​​previously filled in for task template 350. For instance, assuming that user 140 previously filled in the parameter value of template parameter 361 when executing task XX for application task template 350, then terminal device 110 can determine the current parameter value of template parameter 361 based on that parameter value. In some examples, when the current parameter value is determined based on the parameter values ​​previously filled in by user 140, terminal device 110 can display a prompt message 364. This allows user 140 to know that the currently displayed parameter value is determined based on the previously filled parameter values. In some examples, user 140 can edit the parameter value determined by the previously filled parameter values.

[0081] As an example, user 140 can configure the parameter values ​​of the template parameters themselves. For instance, user 140 can input the parameter values ​​for template parameter 361 via input area 363. Input area 363 can support text input, such as entering text in a text input box, and can also support voice input, such as by triggering a voice control. In addition, input area 363 can also provide upload control 366 to support uploading attachments to indicate the parameter values ​​configured by the user.

[0082] Furthermore, after the parameter values ​​corresponding to each template parameter are determined, if the terminal device 110 receives a trigger on the sending control 365, it can receive an application instruction for executing the target task using the application task template 350. Correspondingly, if the terminal device 110 receives a trigger on the sending control 365, it can execute the target task based on the parameter values ​​of each template parameter and the template configuration information. That is, the terminal device 110 can execute the target task according to the template configuration information and parameter values ​​of the template parameters of the task template 350. It should be understood that the details interface 300F is only an example. In other examples, after the user 140 clicks on the application task template 350, only a list of template parameters that the user needs to configure can be presented, without needing to display the request instruction 321 and execution plan 322. In this way, the flexibility, accuracy, and adaptability of executing tasks using task templates can be improved.

[0083] In some examples, during the creation of task template 350, user 140 can configure the role of agent 160; for example, agent 160 can be configured as an expert agent in a specific industry. When applying task template 350, user 140 can adjust the role configuration of agent 160. An editing control 367 is provided in the details interface 300F of task template 350. User 140 can edit the configuration information of task template 350 via the editing control 367. Accordingly, terminal device 110 can execute the target task using agent 160 based on the edited configuration information.

[0084] In some embodiments, when the task template 350 does not include the task execution plan 322 (or the task execution plan 322 is unavailable), if the task template 350 is selected to execute the target task, the terminal device 110 can utilize the agent 160 to execute the target task based on the determined demand instruction 321 and the parameter values ​​of the template parameters in the current task template. The specific process for determining the parameter values ​​of the template parameters can be referred to the description above, and will not be repeated here. In this case, during the execution of the target task, the agent 160 may still need to generate a task execution plan based on the demand instruction, and then complete each task based on the task execution plan.

[0085] In some embodiments, if the terminal device 110 receives an application instruction, it may create a session to interact with the agent 160. In this session, the agent 160 performs a target task based on the task template 350. For example... Figure 3G As shown, if terminal device 110 determines that a session has been created, it can present a prompt panel 371 in the template management interface 300G. The prompt panel 371 may include a viewing control 372. If terminal device 110 receives a trigger on the viewing control 372, it can present the session. Terminal device 110 in Figure 3H The interface 300H shown can display a conversation between user 140 and agent 160. This conversation can include at least one of the following: the execution process and the execution result of agent 160 on the target task.

[0086] Reference Figures 3F to 3H In scenarios where the application task template 350 fails to complete the target task, if the terminal device 110 receives a trigger on the viewing control 372, it can display the process 381 of the agent 160 executing the target task on the interface 300H. Conversely, in scenarios where the application task template 350 completes the target task, if the terminal device 110 receives a trigger on the viewing control 372, it can display the process 381 of the agent 160 executing the target task and the execution result for the target task on the interface 300H. This enhances the user's understanding of the task execution process and makes the results more convincing.

[0087] In summary, creating templates using template configuration information generated from the dialogue between the user and the agent can improve the quality of responses and the efficiency of answering user questions. Thus, when a task involving user-agent interaction can be completed efficiently or satisfactorily, the user can choose to create a task template from the high-quality conversation information corresponding to this task, thereby promoting the efficient completion of subsequent similar tasks in a similar manner. In this way, different task templates can be flexibly created and used for interaction with the agent for different user groups or usage scenarios, which can meet differentiated task needs and improve task execution efficiency.

[0088] Figure 4 A flowchart of a template creation process 400 according to some embodiments of the present disclosure is shown. Process 400 can be implemented at terminal device 110. Reference is made below. Figure 1 Describe the process 400.

[0089] In box 410, terminal device 110 acquires session information between the user and the intelligent agent. The session information instructs the intelligent agent to complete the task based on the user's instructions. Thus, the session information between the user and the intelligent agent can be used to initiate the creation instruction of a task template, providing the user with a convenient and quick creation method.

[0090] In box 420, terminal device 110 presents template configuration information generated based on conversation information. The template configuration information includes at least one of a demand instruction for the agent and a task execution plan obtained by the agent based on the demand instruction. The demand instruction is determined based on instructions initiated by the user in the conversation information. Thus, by creating templates using template configuration information generated from the dialogue information between the user and the agent, the quality of the response results and the efficiency of responding to the user can be improved.

[0091] In box 430, terminal device 110 creates a task template based on template configuration information. Thus, if a task involving user interaction with the agent can be completed efficiently or satisfactorily, the user can choose to create a task template from the high-quality session information corresponding to this task execution, thereby promoting the efficient completion of subsequent similar tasks in a similar manner.

[0092] In some embodiments, the requirement instruction includes at least one of the following: prompt text describing the requirement instruction, at least one template parameter, and the parameter value of the at least one template parameter being configurable when the task template is selected for task execution. This facilitates user understanding of the content included in the task template's configuration information.

[0093] In some embodiments, at least one template parameter is determined by identifying a text fragment as a template parameter among at least one template parameter in response to a predetermined operation on the prompt text. This provides users with a convenient and quick way to add parameters.

[0094] In some embodiments, at least one template parameter is presented in an editing area, where editing of the at least one template parameter is received, and the at least one template parameter is presented in a predetermined style in the requirement instruction. This approach facilitates user editing of parameters and allows users to easily identify which template parameters are included in the requirement instruction.

[0095] In some embodiments, a task execution plan is obtained by: determining the task execution plan as unusable in response to editing the requirement instructions or session information in the task template; regenerating the task execution plan using an agent based on the edited requirement instructions or session information; and determining the regenerated task plan as usable in response to determining that the generation of the task execution plan is complete. Thus, when executing a task using the task template, the updated task execution plan ensures that the task outcome better meets the user's needs.

[0096] In some embodiments, creating a task template includes: determining a task execution plan as unavailable in response to editing a requirement instruction in the task template; and creating the task template based on the edited requirement instruction. This improves the quality of responses and the efficiency of responding to users.

[0097] In some embodiments, process 400 further includes: in response to receiving an application instruction to execute a target task using a task template while the task execution plan is unavailable, executing the target task using an agent based on the edited requirement instruction. This improves the efficiency of responding to users.

[0098] In some embodiments, creating a task template further includes: in response to the completion of the target task, updating the task execution plan corresponding to the task template based on the target task execution plan generated by the agent during the execution of the target task, wherein the task execution plan is determined to be usable upon completion of the update. This allows the updated task execution plan to better meet the user's needs.

[0099] In some embodiments, process 400 further includes: in response to the selection of a task template, determining whether the task execution plan of the task template has been generated; and in response to the task execution plan not being generated, presenting a first prompt message, the first prompt message indicating that the task execution plan of the task template is unavailable. This allows the user to be aware that the task execution plan of the current task template has not been generated.

[0100] In some embodiments, the task template creation instruction is received by: presenting a creation control for creating a task template in response to the completion of at least one dialogue between the user and the agent; and receiving the task template creation instruction in response to triggering the creation control. Thus, providing the creation control during a dialogue between the user 140 and the agent 160 facilitates the user initiating a task template creation instruction.

[0101] In some embodiments, the template configuration information further includes: authorization information regarding the scope of use of the task template, the name of the task template, or a tag for the task template. This allows users to clearly understand the constituent elements of the task template, thereby preventing the loss of key information or incorrect settings.

[0102] In some embodiments, process 400 further includes: in response to the completion of task template creation, adding the task template to a task template library, the task template library including at least one task template applicable to the agent's task execution. Thus, a convenient and efficient management method can be provided for task templates.

[0103] In some embodiments, process 400 further includes: in response to triggering a task template, presenting a details interface of the task template, the details interface including template configuration information; and in response to an application instruction to execute a target task using the task template, executing the target task using an agent, at least based on the template configuration information. In this way, by using a task template to execute a task, the efficiency of task execution and the quality of task results can be improved.

[0104] In some embodiments, performing a target task based at least on template configuration information includes: presenting at least one template parameter to be configured; determining the parameter value of each of the at least one template parameter; and performing the target task based on the parameter value of each of the at least one template parameter and the template configuration information. This approach can improve the flexibility, accuracy, and adaptability of performing tasks using task templates.

[0105] In some embodiments, the parameter values ​​of each template parameter in at least one template parameter are determined based on at least one of the following: parameter values ​​historically populated for the task template, or parameter values ​​configured by the user. This approach improves the flexibility, accuracy, and adaptability of performing tasks using task templates.

[0106] In some embodiments, process 400 further includes: in response to an application instruction, creating a session for interaction with the agent, wherein the agent performs a target task based on a task template in the session; in response to the creation of the session, presenting a prompt panel including a viewing control; and in response to triggering the viewing control, presenting the session, which includes at least one of the agent's execution process of the target task and the execution result. This enhances the user's understanding of the task execution process and makes the results more convincing.

[0107] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes.

[0108] Figure 5 A schematic structural block diagram of an apparatus 500 for template creation according to certain embodiments of the present disclosure is shown. The apparatus 500 may be implemented as or included in a terminal device 110. Various modules / components in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0109] like Figure 5 As shown, the device 500 includes a conversation information acquisition module 510, configured to acquire conversation information between a user and an agent, the conversation information instructing the agent to complete a task based on the user's instructions. The device 500 also includes a template configuration information presentation module 520, configured to present template configuration information generated based on the conversation information, the template configuration information including at least one of a requirement instruction for the agent and a task execution plan obtained by the agent based on the requirement instruction, the requirement instruction being determined based on the instruction initiated by the user in the conversation information. The device 500 also includes a task template creation module 530, configured to create a task template based on the template configuration information. Thus, by creating templates using template configuration information generated from the dialogue information between the user and the agent, the quality of the response results and the efficiency of responding to the user can be improved.

[0110] In some embodiments, the requirement instruction includes at least one of the following: prompt text describing the requirement instruction, at least one template parameter, and the parameter value of the at least one template parameter being configurable when the task template is selected for task execution. This facilitates user understanding of the content included in the task template's configuration information.

[0111] In some embodiments, at least one template parameter is determined by identifying a text fragment as a template parameter among at least one template parameter in response to a predetermined operation on the prompt text. This provides users with a convenient and quick way to add parameters.

[0112] In some embodiments, at least one template parameter is presented in an editing area, where editing of the at least one template parameter is received. This facilitates user editing of the parameter.

[0113] In some embodiments, at least one template parameter is presented in a predetermined style in the requirement instruction and / or editing area. This makes it easy for users to know which template parameters are included in the requirement instruction.

[0114] In some embodiments, the template configuration information presentation module 520 is further configured to, in response to editing of the requirement instructions or session information in the task template, determine the task execution plan as unusable; and, based on the edited requirement instructions or session information, regenerate the task execution plan using an agent; and, in response to determining that the generation of the task execution plan is complete, determine the regenerated task plan as usable. Thus, when performing a task using the task template, the updated task execution plan enables the task results to better meet the user's needs.

[0115] In some embodiments, the task template creation module 530 is further configured to, in response to editing of the requirement instructions in the task template, determine the task execution plan as unusable; and create the task template based on the edited requirement instructions. This improves the quality of the response results and the efficiency of responding to users.

[0116] In some embodiments, the apparatus 500 further includes a template task execution module configured to, in response to receiving an application instruction to execute a target task using a task template while the task execution plan is unavailable, utilize an agent to execute the target task based on an edited requirement instruction. This improves the efficiency of responding to users.

[0117] In some embodiments, the task template creation module 530 is further configured to update the task execution plan corresponding to the task template based on the target task execution plan generated by the agent during the execution of the target task in response to the completion of the target task. Upon completion of the task execution plan update, the task execution plan is determined to be usable. Thus, the updated task execution plan enables the task results to better meet the user's needs.

[0118] In some embodiments, the device 500 further includes a prompt information presentation module, configured to determine whether the task execution plan of the task template has been generated in response to the selection of the task template; and to present a first prompt information in response to the task execution plan not being generated, the first prompt information being used to indicate that the task execution plan of the task template is in an unusable state. This allows the user to be aware that the task execution plan of the current task template has not been generated.

[0119] In some embodiments, the task template creation instruction is received by: presenting a creation control for creating a task template in response to the completion of at least one dialogue between the user and the agent; and receiving the task template creation instruction in response to triggering the creation control. Thus, providing the creation control during a dialogue between the user 140 and the agent 160 facilitates the user initiating a task template creation instruction.

[0120] In some embodiments, the prompting module is further configured to present a second prompt in association with the creation control, the second prompt indicating the ability to create a task template based on session information. This guides the user's attention to the creation control 313.

[0121] In some embodiments, the template configuration information further includes: authorization information regarding the scope of use of the task template, the name of the task template, or a tag for the task template. This allows users to clearly understand the constituent elements of the task template, thereby preventing the loss of key information or incorrect settings.

[0122] In some embodiments, the device 500 further includes a template adding module, configured to add the task template to a task template library in response to the completion of task template creation. The task template library includes at least one task template applicable to the task execution of the agent. Thus, a convenient and efficient management method can be provided for task templates.

[0123] In some embodiments, the device 500 further includes a template application module, configured to, in response to the triggering of a task template, present a details interface of the task template, the details interface including template configuration information; and, in response to an application instruction to execute a target task using the task template, execute the target task using an agent, at least based on the template configuration information. In this way, by applying task templates to execute tasks, the efficiency of task execution and the quality of task results can be improved.

[0124] In some embodiments, the template application module is further configured to present at least one template parameter to be configured; determine the parameter value of each of the at least one template parameter; and execute the target task based on the parameter value of each of the at least one template parameter and the template configuration information. This approach can improve the flexibility, accuracy, and adaptability of performing tasks using task templates.

[0125] In some embodiments, the parameter values ​​of each template parameter in at least one template parameter are determined based on at least one of the following: parameter values ​​historically populated for the task template, or parameter values ​​configured by the user. This approach improves the flexibility, accuracy, and adaptability of performing tasks using task templates.

[0126] In some embodiments, the device 500 further includes a session presentation module configured to create a session for interaction with the agent in response to an application instruction, wherein the agent performs a target task based on a task template in the session; present a prompt panel including a viewing control in response to the creation of the session; and present the session in response to triggering the viewing control, the session including at least one of the agent's execution process of the target task and the execution result. This enhances the user's understanding of the task execution process and makes the results more convincing.

[0127] In some embodiments, the apparatus 500 further includes a template publishing module configured to configure a task template as applicable to a user scope in response to a publishing instruction for the task template, wherein the user scope is specified by the publishing instruction. This enables large-scale reuse of task templates and reduces repetitive costs.

[0128] The units and / or modules included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in device 500 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0129] It should be understood that one or more steps in the above methods can be performed by suitable electronic devices or combinations of electronic devices. Such electronic devices or combinations of electronic devices may include, for example, […]. Figure 1 Terminal device 110 and server 130.

[0130] Figure 6 A block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 6 The electronic device 600 shown can be used to achieve Figure 1 Terminal device 110 or server 130, or Figure 5 The device 500.

[0131] like Figure 6As shown, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processing units or processors 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit 670 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0132] Electronic device 600 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data and accessible within electronic device 600.

[0133] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0134] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0135] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0136] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0137] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0138] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0139] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0141] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for template creation, comprising: In response to the task template creation instruction, the conversation information between the user and the agent is obtained. The conversation information instructs the agent to complete the task based on the user's instructions. The conversation information includes the instructions sent by the user, the responses provided by the agent to the instructions, and relevant information about the agent's task execution. Present template configuration information generated based on the session information. The template configuration information includes at least one of a demand instruction for the agent and a task execution plan. The demand instruction is determined based on the session information, and the task execution plan is obtained based on the process by which the agent completes the task indicated by the demand instruction. as well as The task template is created based on the template configuration information.

2. The method of claim 1, wherein the demand instruction comprises at least one of the following: The prompt text used to describe the required instructions. At least one template parameter, the value of which can be configured when the task template is selected for task execution.

3. The method of claim 2, wherein the at least one template parameter is determined in the following manner: In response to a predetermined operation on a text fragment in the prompt text, the text fragment is identified as a template parameter among the at least one template parameter.

4. The method of claim 2, wherein the at least one template parameter is presented in an editing area, and editing of the at least one template parameter is received in the editing area, and The at least one template parameter is presented in a predetermined style in the requirement instruction.

5. The method of claim 1, wherein the task execution plan is obtained based on the following: In response to editing the requirement instruction or the session information in the task template, the task execution plan is determined to be unusable. Based on the edited requirement instructions or the session information, the task execution plan is regenerated using the intelligent agent; as well as In response to the determination that the task execution plan has been generated, the regenerated task execution plan is determined to be in a usable state.

6. The method of claim 5, further comprising: In response to the selection of the task template, determine whether the task execution plan of the task template has been generated completely; as well as In response to the fact that the task execution plan has not been generated, a first prompt message is displayed, which is used to indicate that the task execution plan of the task template is in an unusable state.

7. The method of claim 1, wherein creating the task template comprises: In response to the editing of the requirement instruction in the task template, the task execution plan is determined to be unusable. as well as The task template is created based on the edited requirement instructions.

8. The method according to claim 7, further comprising: In response to receiving an application instruction to execute the target task using the task template while the task execution plan is in an unavailable state. Based on the edited requirement instructions, the agent executes the target task.

9. The method of claim 8, wherein creating the task template further comprises: In response to the completion of the target task, the task execution plan corresponding to the task template is updated based on the target task execution plan generated by the agent during the execution of the target task. Once the task execution plan is updated, the task execution plan is determined to be usable.

10. The method of claim 1, wherein the task template creation instruction is received in the following manner: In response to the completion of at least one dialogue between the user and the agent, a creation control for creating the task template is presented; and In response to the triggering of the creation control, the creation instruction of the task template is received.

11. The method according to claim 1, wherein the template configuration information further includes: Authorization information regarding the scope of use of the task template. The name of the task template, or The tags of the task template.

12. The method according to claim 1, further comprising: In response to the completion of the creation of the task template, the task template is added to the task template library, which includes at least one task template that can be applied in the task execution of the agent.

13. The method according to claim 1, further comprising: In response to the triggering of the task template, a details interface of the task template is displayed, the details interface including the template configuration information; In response to an application instruction to execute a target task using the task template, the agent executes the target task based at least on the template configuration information.

14. The method of claim 13, wherein performing the target task based at least on the template configuration information comprises: Present the at least one template parameter to be configured; Determine the parameter values ​​for each of the at least one template parameter; as well as The target task is executed based on the parameter values ​​of each of the at least one template parameter and the template configuration information.

15. The method of claim 13, wherein the parameter value of each template parameter in the at least one template parameter is determined based on at least one of the following: For the historical parameter values ​​filled in for the task template, or The parameter values ​​configured by the user.

16. The method of claim 13, further comprising: In response to the application instruction, a session is created for interaction with the agent, wherein the agent performs the target task based on the task template in the session; In response to the creation of the session, a prompt panel is presented, the prompt panel including viewing controls; as well as In response to a triggering of the viewing control, the session is presented, the session including at least one of the agent's execution process and execution result of the target task.

17. An apparatus for template creation, comprising: The session information acquisition module is configured to acquire session information between the user and the agent in response to the creation instruction of the task template. The session information instructs the agent to complete the task based on the user's instructions. The session information includes the instructions sent by the user, the responses provided by the agent to the instructions, and relevant information on the agent's task execution. The template configuration information presentation module is configured to present template configuration information generated based on the session information. The template configuration information includes at least one of a demand instruction for the agent and a task execution plan. The demand instruction is determined based on the session information, and the task execution plan is obtained based on the process by which the agent completes the task indicated by the demand instruction. as well as The task template creation module is configured to create the task template based on the template configuration information.

18. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 16 when executed by the at least one processor.

19. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 16.

20. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 16.

Images