Method, device, equipment and storage medium for prompt word management

Abstract

Embodiments of the present disclosure provide a method, device, equipment and storage medium for prompt word management. The method comprises: in response to receiving a prompt word editing request, presenting an editing interface, wherein the editing interface at least comprises an input area for receiving a target prompt word; and in response to receiving a prompt word publishing request, encapsulating the target prompt word into a callable target task based at least on user input in the editing interface, wherein a call to the target task will trigger the target prompt word to be input to a model. In this way, flexible design and management of prompt words can be achieved, and the stability, reliability, convenience and efficiency of prompt word management and model calling in actual applications can be improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatus, devices, and computer-readable storage media for prompt word management. Background Technology

[0002] With the development of machine learning technology, machine learning models can now be used to perform tasks in various application environments. Because the development and maintenance of high-performance models require significant technical and financial investment, including large datasets, high-performance computing resources, and dedicated research teams, Model as a Service (MaaS) is gradually becoming a viable solution. Users can input prompts into a model in the cloud to obtain the model's output specific to those prompts; therefore, the accuracy of the prompts directly impacts the model's output. How to conveniently and quickly manage these prompts is a key technical challenge that needs to be explored. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for managing prompt words is provided. The method includes: in response to receiving a prompt word editing request, presenting an editing interface, wherein the editing interface includes at least an input area for receiving a target prompt word; and in response to receiving a prompt word publishing request, encapsulating the target prompt word into a callable target task, at least based on user input in the editing interface, wherein invoking the target task triggers the target prompt word to be input into a model.

[0004] In a second aspect of this disclosure, an apparatus for prompt word management is provided. The apparatus includes: an interface presentation module configured to present an editing interface in response to receiving a prompt word editing request, wherein the editing interface includes at least an input area for receiving a target prompt word; and a publishing module configured to, in response to receiving a prompt word publishing request, encapsulate the target prompt word into a callable target task, at least based on user input in the editing interface, wherein invoking the target task triggers the input of the target prompt word into a model.

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

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. A computer program is stored on the medium, which can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the description in this 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

[0008] 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:

[0009] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0010] Figures 2A to 2J A schematic diagram of an example interface of a prompt word management system according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic diagram of a prompt word management process according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A flowchart of a process for managing prompt words according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A schematic structural block diagram of an apparatus for prompt word management according to certain embodiments of the present disclosure is shown; and

[0014] Figure 6 An electronic device in which one or more embodiments of the present disclosure may be implemented is shown. Detailed Implementation

[0015] 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.

[0016] 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.

[0017] 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.

[0018] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.

[0021] 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 information to the electronic device.

[0022] 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.

[0023] 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 electronic device 110 runs a prompt word management system 120. A user 140 can interact with the prompt word management system 120 via the electronic device 110 and / or attached devices of the electronic device 110. The prompt word management system 120 can provide integration of various types of functions or components to facilitate activities such as creating, modifying, and adjusting prompt words.

[0024] In some embodiments, the prompt word management system 120 may be downloaded and installed as an application on the electronic device 110. In some embodiments, the prompt word management system 120 may also be accessed in other ways, such as through a web page.

[0025] exist Figure 1 In environment 100, if the prompt management system 120 is activated, electronic device 110 can display the interface 150 of the prompt management system 120. Interface 150 may include various user interfaces provided by the prompt management system 120. Interface 150 is sometimes also referred to as a client interface.

[0026] In some embodiments, the prompt management system 120 can utilize model 130 to generate, validate, and evaluate prompts. In this document, a prompt is the input or template of the model, which can be natural language and / or other modal data, used to guide or stimulate the model to complete specific processing to obtain the desired model output. The prompt management system 120 can interact with model 130 to provide model input and obtain corresponding model output from model 130. Model 130 can run locally on electronic device 110 or on a remote server. In some embodiments, model 130 can be a machine learning model, deep learning model, learning model, neural network, etc. In some embodiments, model 130 can be based on a language model (LM). Language models, by learning from a large corpus, are capable of question answering. Model 130 can also be based on other suitable models.

[0027] Electronic device 110 can be any type of computing device, including terminal devices and / or server devices. Terminal devices 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, 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. Server devices may include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, etc. In some embodiments, the prompt word management system 120 may be implemented based on cloud services.

[0028] 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.

[0029] The core concept of Model as a Service (MAS) is to deploy models, especially top-performing models, in the cloud. Users can then access these models via APIs or SDKs to implement various functionalities. MAS allows for the rapid deployment and application of advanced AI technologies without incurring expensive R&D costs. Compared to the traditional approach of training different models for specific tasks, MAS offers advantages including lower cost, greater flexibility (users can choose suitable models and services based on their needs and adjust their usage plans at any time), ease of integration (MAS can be easily integrated with existing systems via APIs or SDKs without large-scale modifications), continuous updates (cloud-based models are regularly updated and optimized, ensuring users can enjoy the latest technological advancements), cross-platform compatibility (supporting multiple platforms and devices, facilitating cross-platform development), and enhanced security and privacy protection.

[0030] Furthermore, the use of platforms and / or systems has made model invocation very simple. Currently, model usage is mostly based on command-based and question-and-answer interactions. Users only need to design a prompt word to provide to the model to generate an answer. However, the design of prompt words requires careful consideration of many factors, such as contextual information, domain knowledge, and the model's inherent limitations. Moreover, the design of prompt words requires continuous iteration and optimization. Therefore, in practical applications, designing a high-quality prompt word to guide the model to generate more accurate and relevant answers is a rather challenging task.

[0031] According to embodiments of this disclosure, an improved scheme for prompt word management is proposed. In embodiments of this disclosure, in response to receiving a prompt word editing request, an editing interface is presented, including at least an input area for receiving target prompt words. In response to receiving a prompt word publishing request, the target prompt word is encapsulated into a callable target task, based at least on user input in the editing interface. Calling the target task triggers the input of the target prompt word into the model. Thus, prompt words can be flexibly designed and managed, and can be encapsulated into callable tasks, which simplifies model invocation and helps improve the stability, reliability, convenience, and efficiency of prompt word management and model invocation in practical applications.

[0032] Some exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0033] In embodiments of this disclosure, when the prompt management system 120 is in operation, in response to receiving a prompt editing request, the prompt management system 120 presents an editing interface that includes at least an input area for receiving the target prompt. The prompt editing request may include, for example, a task creation request for a new prompt and a task modification request for an existing prompt. Taking a prompt editing request as an example of a creation request for a new prompt, the target prompt is the new prompt to be created, and the prompt management system 120 may present an editing interface that includes an input area for receiving the new prompt.

[0034] Furthermore, in response to receiving a prompt word publishing request, the prompt word management system 120 obtains a callable target task based on the target prompt word, at least based on user input in the editing interface. For example, the target prompt word can be encapsulated into a piece of code corresponding to the callable task. By triggering the call to this code, the corresponding target prompt word can be input into the model. For example, if the target prompt word indicates a prompt word associated with article translation, a target task instructing the translation of an article can be generated based on the target prompt word and the model's calling parameters, and the model then executes the target task. Regarding the specific method by which the model executes the target task, in response to invoking the target task, the target prompt word is input into the model. The model can perform the operation indicated by the target task based on the target prompt word. For example, based on the target prompt word, the model can perform the translation of an article.

[0035] The following will combine Figures 2A to 2J The following describes an example interface of a prompt word management system according to some embodiments of the present disclosure. Figures 2A to 2J Schematic diagrams of examples of editing interfaces according to some embodiments of the present disclosure are shown. Figures 2A to 2J The editing interface shown corresponds to the prompt word management system 120, which integrates multiple different types of components. It should be understood that... Figures 2A to 2J The editing interface shown is merely an example; various interface designs are possible in practice. The graphic elements within the interface can have different arrangements and visual representations, one or more elements can be omitted or replaced, and one or more other elements may also be present. The embodiments disclosed herein are not limited in this respect.

[0036] In some embodiments, when the prompt word management system 120 is in operation, the prompt word management system 120 may display the following: Figure 2AThe editing interface 200A shown is used to receive prompt word editing requests. In some embodiments, since the prompt word management system 120 supports multi-environment applications, the target environment for the task application needs to be determined before performing tasks such as creating new prompt words using the prompt word management system. In some embodiments, in response to detecting a trigger operation on the environment selection control 201, multiple candidate environments to be selected (such as...) are presented. Figure 2A (As shown on Region A, Region B, and Region C). The system can determine the target environment for the task application in response to a selection of a candidate environment. For example, in response to a click on a candidate environment on Region A, it can be determined as the target environment for the task application. Thus, a target environment that meets the regional requirements can be selected based on user needs and the actual application environment.

[0037] In some embodiments, the prompt word management system 120 may also display a task list including at least one task that has been created. For example... Figure 2A As shown, the editing interface 200A displays two task lists: "My Task List" and "Public Task List." In one example, "My Task List" could be a list of tasks created by the current user corresponding to the prompt word management system 120, while "Public Task List" could be a list of tasks created by users other than the current user and made public so that the current user can access them. It is understood that other task lists may also be displayed, or only one task list containing all tasks may be displayed; this disclosure does not limit this. In response to detecting a trigger operation on "My Task List" or "Public Task List," the display can switch to show at least one task within the corresponding task list. Figure 2A The image shows an example of presenting at least one task included in "My Task List", which includes Task A, Task B, Task C, and Task D.

[0038] The task list includes a task ID and task name for identifying tasks, task keywords indicating important task information (e.g., required model, task purpose), task creation time, update time, and creator. The task creation time is the initial creation time of the task, and the task update time is the last update time of the task. In some embodiments, at least one operation control may be presented in association with at least one task included in the task list. In some embodiments, the editing interface 200A includes at least one delete control 205 indicating the deletion of a task, and the at least one delete control 205 corresponds to at least one task in the task list. In response to detecting a trigger operation on the delete control 205, it can be determined that a task deletion request for the corresponding task has been received. In response to the task deletion request, the corresponding task will be removed from the editing interface 200A.

[0039] In some embodiments, the editing interface 200A may further include at least one modification control 204 associated with at least one task included in the task list, wherein the at least one modification control 204 corresponds to at least one task in the task list. In some embodiments, the editing interface 200A further includes a creation control 203. It is understood that the editing interface 200A may also include other operation controls, and this disclosure is not limiting in this regard. In some embodiments, in response to detecting a trigger operation on the creation control 203, it can be determined that a task creation request for a new prompt word has been received. In response to detecting a trigger operation on the modification control 204, it can be determined that a task modification request for an existing prompt word has been received.

[0040] In some embodiments, since tasks are associated with prompt words, task creation requests and / or task modification requests for tasks can be understood as prompt word creation requests and / or modification requests. Such creation and modification requests both fall under the category of prompt word editing requests. That is, in response to detecting a triggering operation on the creation control 203 and / or modification control 204, prompt word editing requests (creation requests and / or modification requests) for prompt words can be received.

[0041] In some embodiments, prompt editing requests can also be received in other ways. For example, a prompt editing request can be determined to have been received in response to the detection of a voice or gesture corresponding to the prompt editing request, or the detection of a click on a corresponding physical control. The voice or gesture here can be pre-set, or include pre-set keywords / key actions. For example, a prompt editing request can be determined to have been received in response to the detection of the voice phrases "create task" or "modify task A".

[0042] It is important to note that when a prompt word editing request is a modification request for an already created task (e.g., a task modification request received in response to a detected triggering action on the modification control 204), the prompt word management system 120 can also determine the current user's permissions. Specifically, a task can be one created by the current user (e.g., ...). Figure 2A The tasks shown in "My Task List" can be at least one task, or tasks created by other users and made public so that the current user can access them (e.g., tasks listed in "My Task List"). Figure 2A (At least one task included in the "Public Task List" shown). For tasks created by the user, it can be understood that the user has the highest editing authority, and can modify them. However, for tasks created by other users and made public so that the current user can access them, the prompt word management system 120 needs to determine the current user's permissions to determine whether the current user is qualified to edit them. It is understood that different users may have different permissions for the same task; for example, user A may have editing permissions, while user B may only have usage permissions and not editing permissions. For tasks that have already been created, the prompt word management system 120 may present the editing interface only if it determines that the user has editing permissions for the created task. It is understood that for the case of creating a new task, the prompt word management system 120 may directly present the editing interface without verifying editing permissions. Thus, different users can have different permissions for the same task, which helps different users in a team to share tasks, achieve rapid collaboration and effective communication, and improve the efficiency of prompt word management.

[0043] In some embodiments, the editing interface 200A may further include a help control 202. In response to detecting a trigger operation on the help document control 202, the interface can switch to a document display interface (not shown in the figure). This document interface may include, for example, text and / or image information for prompting the user about interactive methods of the prompt management system 120, prompt creation steps, prompt modification steps, etc. The trigger operations here include, but are not limited to, click operations, long press operations, swipe operations, double-click operations, etc.

[0044] In some embodiments, upon receiving a prompt word editing request, in response to the prompt word editing request, the following can be displayed: Figure 2B The editing interface 200B is shown. For example, in response to detecting a triggered operation for creating control 203 and / or modifying control 204, the following can be presented: Figure 2BThe editing interface 200B is shown. The editing interface 200B may include a task definition area 210. In some embodiments, the task definition area 210 is used to receive a task identifier for a target task, which can be used for subsequent invocations of the target task. Specifically, when a target task needs to be invoked, the invocation can be performed based on the target task's task identifier, which helps improve the efficiency of task invocation. The task identifier here includes at least one of the task name and task description. It is understood that different tasks have different task identifiers (i.e., the task name and at least one of the task description are different).

[0045] The editing interface 200B includes an input area 215. In some embodiments, the input area 215 can be used to receive a template of a target prompt word. This template can be used to define the structure of the target prompt word, including one or more variables contained in the target prompt word. Thus, instead of defining a one-time, complete prompt word, by designing a template, the values ​​of corresponding variables can be filled into the template in a specific application to obtain a complete prompt word input to the model. The prompt word management system 120, in response to detecting user input in the input area 215, determines the user input as the received template of the target prompt word. The input area 215 can also present the received template of the target prompt word to the user. Figure 2B As shown, the template for the target prompt word received by input area 215 is, for example, "It needs to implement the echo function based on the message, and must return the original text without adding any other content. message: {{msg}} echo: ".

[0046] Because the target prompt may contain at least one variable (such as...) Figure 2B As shown in the message, to limit the variables and make subsequent assignments to the variables more accurate, the editing interface 200B may also include a variable definition area 220. In some embodiments, the variable definition area 220 is used to receive the definition of at least one variable involved in the target prompt, including but not limited to the variable's name (i.e., variable name), variable description, variable default value, etc. Figure 2BAs shown, the variable definition can specify the variable name as "msg" and the variable description as "the message returned by echo". If user input is received in the "Default Value of Variable" field, the received user input can be determined as the default value for the variable. If no user input is received in the "Default Value of Variable" field, after the prompt word is published, in response to the detection of a call to the target task, an assignment prompt message can be presented to prompt the user to assign a value to at least one variable. The presentation methods here include, but are not limited to, voice, vibration, message box, pop-up window, etc. The user can manually assign a value to at least one variable based on the assignment prompt message, or instruct the prompt word management system 120 to automatically assign a value based on the associated database.

[0047] The editing interface 200B also includes a model configuration area 230. In some embodiments, the model configuration area 230 can be used to receive a selection of a target model. When a target task is subsequently invoked, the target keywords will be input into the target model selected in the model configuration area 230. Figure 2B As shown, the model configuration area 230 may include a model selection entry 231. In response to a click operation on the model selection entry 231, multiple models may be presented, and in response to a selection operation on a particular model (e.g., model A), it is determined as the target model to which the corresponding prompt word will be input. In some embodiments, the model selection entry 231 may also present a pre-set default model, which is the target model.

[0048] In some embodiments, to ensure the accuracy of subsequent task invocation and task execution, the model configuration area 230 is also used to receive the definition of processing parameters for the target model. For example... Figure 2B As shown, the model configuration area 230 may include settings for parameters such as degree, maximum length, stopping sequence, top, existence penalty, and frequency penalty.

[0049] For example, the parameters that can be configured in the model configuration area 230 may include a temperature parameter. Temperature controls the diversity and creativity of the generated text. Its value typically ranges from 0.1 to 1, representing the degree of randomness in text generation. Lower values ​​result in more conservative and predictable text, while higher values ​​result in bolder and more unpredictable text. For instance, if the temperature is set to 0.5, the generated text will have some creativity and variation, but will still maintain a certain level of coherence and readability. Conversely, if the temperature is set to 1, the generated text will be more random and unpredictable, potentially containing strange sentences and meaningless content. Therefore, the temperature value needs to be adjusted according to specific needs and application scenarios to achieve the best results.

[0050] For example, the parameters that can be configured in the model configuration area 230 may also include a maximum length parameter. The maximum length refers to the maximum length of the generated text. The length of the generated text can be controlled by setting the maximum length. If the maximum length is set to 100, the generated text will not exceed 100 characters. This parameter helps control the length of the generated text to suit different application scenarios. For example, if short text needs to be generated, the maximum length can be set to 50, while if long text needs to be generated, the maximum length can be set to 500 or higher.

[0051] For example, the parameters that can be configured in the model configuration area 230 may also include a Stopsequences parameter. Stopsequences specify the flags at which text generation stops. When any of the flags specified in the stopsequences appears in the generated text, the API stops generating text and returns the result. This parameter can be used to control the length and content of the generated text, and to avoid generating meaningless or incoherent text. For example, if the stopsequences are set to common period flags such as ".", "?", or "!", the API will stop generating a complete sentence to avoid generating excessively long or incomplete text.

[0052] For example, the model configuration area 230 can also configure a Top P parameter. Top P controls the diversity and predictability of the generated text. Specifically, Top P is a decimal between 0 and 1, indicating that only the top P words with the highest probabilities are considered when generating text. For example, if Top P is set to 0.5, only the top 50% of words with the highest probabilities are considered, while words with lower probabilities are ignored. This can make the generated text more predictable, but may also lead to text that is too monotonous and lacks creativity. Therefore, depending on the specific application scenario and needs, the value of Top P can be adjusted appropriately to balance the diversity and predictability of the text.

[0053] For example, the parameters that can be configured in the model configuration area 230 may also include a presence penalty parameter. The presence penalty controls whether the generated text contains specific words or phrases. A higher presence penalty value makes it less likely that the generated text will contain those words or phrases. This parameter can be used to control the style and content of the generated text, making it more suitable for specific needs. For example, if you need to generate text about healthy eating, you can set a presence penalty to ensure that unhealthy foods or drinks do not appear in the generated text.

[0054] For example, the parameters that can be configured in the model configuration region 230 may also include a frequency penalty parameter. The frequency penalty is used to control the frequency of repeated words in the generated text. Setting a high frequency penalty value will minimize the repetition of the same words in the generated text, thus making the generated text more diverse and richer. Conversely, setting a low frequency penalty value may result in a large number of repeated words in the generated text, making the generated text simpler and more repetitive. Therefore, by adjusting the frequency penalty parameter, the diversity and complexity of the generated text can be controlled.

[0055] In response to a setting operation received at at least one setting entry, processing parameters for the target model regarding degree, maximum length, stopping sequence, top, presence penalty, frequency penalty, etc., can be determined. In some embodiments, default parameters can be provided, which the user can modify to determine the processing parameters for the target model. It is understood that the configurable processing parameters may differ for different models. In some embodiments, when the target task is subsequently invoked, the target model will process the target prompt words according to the defined processing parameters to perform the target task. In some embodiments, the target model determined in the model configuration area 230 can also be used for subsequent verification, evaluation, etc., of the target prompt word template.

[0056] like Figure 2B As shown, in some embodiments, the editing interface 200B may further include an editing control presentation area 240. The editing control presentation area 240 may display a save control 241. In some embodiments, in response to detecting a trigger operation on the save control 241, it can be determined that a save request for the target prompt word has been received. Information such as the template of the target prompt word determined in the editing interface 200B, the definition of variables, and the processing parameters of the model can be saved. In some embodiments, this information will be saved to the draft box for continued editing later.

[0057] A verification control 242 may also be displayed in the editing control rendering area 240. In some embodiments, before the target prompt is published, i.e., before the prompt publication request is received, in response to detecting a triggering operation on the verification control 242, it can be determined that a verification request for the target prompt has been received. In response to receiving the verification request for the target prompt, at least based on user input in the editing interface, the target prompt is input into the model, and model output for the target prompt is received from the model. Furthermore, the received model output may also be displayed in the editing interface 200B. Figure 2CAs shown, in response to receiving a trigger operation on the verification control 242, it can be determined that a verification request for the target prompt word has been received. Further, in response to the verification request for the target prompt word, a verification area 250 is presented in the editing interface 200B. The verification area 250 includes a variable presentation area 251, which can present the assignment of values ​​to variables in the template for the target prompt word based on user input (this assignment is the user input). The verification area 250 also includes a template presentation area 252 for presenting the template for the target prompt word and an output presentation area 253 for presenting the model output received from the model for the target prompt word. In some embodiments, the verification area 250 also presents a cancellation control 254 and a start debugging control 255. In response to detecting a trigger operation on the cancellation control 254, the verification of the target prompt word can be terminated. It is understood that after verification is cancelled, the editing interface 200B will stop presenting the verification area 250. In response to a detected trigger operation on the start debugging control 255, verification of the target prompt word can begin. The values ​​of the variables presented in the variable presentation area 251 are assigned to the template shown in the template presentation area 252 to obtain the target prompt word, which is then input into the model. Model output for the target prompt word can be received from the model and presented in the output presentation area 253. Therefore, the user can determine whether the template of the target prompt word needs adjustment based on the model output presented in the output presentation area 253. By repeating this verification operation multiple times, a prompt word template that meets the user's needs can be obtained, improving the accuracy of the final generated prompt word.

[0058] like Figure 2D As shown, the editing control rendering area 240 may also display an evaluation control 243. In some embodiments, in response to detecting a trigger operation on the evaluation control 243, it can be determined that an evaluation request for the target prompt word has been received. In response to receiving the evaluation request for the target prompt word, an evaluation input area can be presented. The evaluation input area can be used to receive evaluation data for the target prompt word, where the evaluation data indicates multiple values ​​of at least one variable involved in the template of the target prompt word. Further, an evaluation result for the target prompt word will be generated based on the evaluation data. Figure 2D As shown, in response to receiving a trigger operation on the evaluation control 243, it can be determined that an evaluation request for the target prompt word has been received. In response to receiving the evaluation request, evaluation prompt information 260 can be displayed on the editing interface 200B. Evaluation prompt information 260 can indicate to the user that an evaluation set template for evaluation is being generated by displaying text such as "Evaluation set template being generated." In response to the completion of evaluation set template generation, the display of evaluation prompt information 260 can be canceled. Furthermore, it can display text such as... Figure 2E The evaluation input area shown is 270.

[0059] like Figure 2E As shown, in response to receiving a request for Figure 2D The triggering operation of the evaluation control shown indicates that an evaluation request for the target prompt word has been received. In response to receiving the evaluation request, the editing interface 200B can present the evaluation input area 270. The model configuration area 230 and the evaluation input area 270 may include, for example, at least an evaluation set input entry 271, an evaluation set upload control 272, and an evaluation control 273. The evaluation set input entry 271 can be used to receive evaluation data (also referred to as the evaluation set) for the target prompt word. This evaluation data can indicate multiple values ​​of at least one variable involved in the template of the target prompt word. For example, the evaluation data can indicate three values ​​for variable A: a, b, and c.

[0060] In some embodiments, the evaluation data required for the evaluation can be manually entered by the user in the evaluation set input field 271. In some embodiments, in response to detecting a trigger operation on the evaluation set upload control 272, a selection page for existing evaluation data can be presented, and then, in response to the user's selection of a certain evaluation data, the target evaluation data required for the evaluation can be determined. In some embodiments, the evaluation set input field 271 can also be used to present the evaluation data entered by the user or the target evaluation data selected by the user through the evaluation set upload control 272. Figure 2F As shown, the evaluation data to be used for evaluation, evaluation set A, can be displayed at the evaluation set input point 271.

[0061] In some embodiments, once the evaluation data required for the evaluation is determined, an evaluation of the target prompt word can be performed in response to a detected trigger operation on the evaluation control 273. In some embodiments, in response to a detected trigger operation on the evaluation control 273, the editing interface 200B can display as follows: Figure 2G The evaluation prompt area 280 shown is used to prompt the user that an evaluation of the target prompt word is currently being performed. In some embodiments, the evaluation prompt area 280 may include a cancel control 281. In response to detecting a trigger operation on the cancel control 281, the presentation of the evaluation prompt area 280 is canceled. In some embodiments, canceling the presentation of the evaluation prompt area 280 also stops the evaluation of the template for the target prompt word.

[0062] In some embodiments, in response to a detected trigger operation on the cancel control 281, only the evaluation prompt area 280 is canceled, without affecting the execution of the evaluation. In this case, after the evaluation prompt area 280 is canceled, the editing interface 200B can display evaluation prompt information in the evaluation input area 270. Figure 2HAs shown, a message such as "Evaluation in progress" can be displayed at the evaluation set input field 271 to inform the user that an evaluation of the target prompt word is currently being performed. Additionally, an evaluation termination control 274 can be displayed in the evaluation input area 270. In response to a detected triggering operation on the evaluation termination control 274, the evaluation of the template for the target prompt word stops. It is understood that after the evaluation stops, the display of a message such as "Evaluation in progress" at the evaluation set input field 271 will also cease.

[0063] Regarding the specific method of evaluation execution, in some embodiments, evaluation results can be generated based on evaluation data for the target prompt words. Specifically, multiple test prompt words are generated by assigning values ​​to at least one variable using multiple values ​​for at least one variable in the evaluation data. For example, assigning values ​​a, b, and c to variable A in the template can yield three different test prompt words. These multiple test prompt words are then input into the model so that the model generates model outputs for each test prompt word. The multiple model outputs for the test prompt words are retrieved from the model, and evaluation results are generated based on these multiple model outputs. In some embodiments, an access point for the evaluation results can also be provided in the editing interface 200B. Figure 2I As shown, in response to receiving multiple outputs from the model, evaluation results can be generated based on these multiple model outputs. In response to the generation of evaluation results, the editing interface 200B can present an access point 275 for the evaluation results in the evaluation input area 270. Access point 275 can be used to present the generated evaluation results. In response to receiving a trigger operation on the evaluation results presented in access point 275, detailed content of the evaluation results can be presented. Furthermore, a prompt message such as "Evaluation results have been updated in this document" can be displayed at access point 275 to inform the user that the evaluation results have been generated and can be viewed. This can be considered a completion of one evaluation of the target prompt word. Therefore, by using an evaluation set containing a large dataset to evaluate the prompt words to be published, it is possible to determine whether the quality of the prompt words meets expectations, which helps to improve the quality of the prompt words and thus improve the quality of subsequent task execution.

[0064] It should be noted that in the above-mentioned verification and / or evaluation of target prompt words, the prompt word management system 120 can be integrated with other tools and applications to achieve an automated workflow. That is, it can automatically perform verification and / or evaluation of target prompt words in response to user triggering of corresponding controls, which can reduce the required manpower and help improve the efficiency of verification and / or evaluation.

[0065] It should be noted that, although Figure 2EAlthough not shown, the editing interface 200B may still include a task definition area 210 and a model configuration area 230, as shown in subsequent figures. In some embodiments, the editing interface 200B also includes a sliding control 206. In response to detecting an up or down operation on the sliding control 206, other content may be presented in the editing interface 200B. It is understood that other content may also be presented in the editing interface 200B in response to detecting a trigger operation on the corresponding physical control, and / or in response to detecting a sliding operation in the editing interface 200B (e.g., presenting the task definition area 210 in response to detecting a down operation).

[0066] For a target prompt word that has completed verification and / or evaluation, in response to receiving a prompt word publishing request, the target prompt word is encapsulated into a callable target task. In some embodiments, in response to the completion of verification and / or evaluation, the editing interface 200B will present a publishing control. In response to detecting a trigger operation on the publishing control, it is determined that a prompt word publishing request has been received. In some embodiments, the publishing control may only be presented in the editing interface 200B if verification and / or evaluation is completed. Alternatively or additionally, in some embodiments, the publishing control may also always be presented in the editing interface 200B, even if the target prompt word has not completed verification and / or evaluation, in response to detecting a trigger operation on the publishing control, it can still determine that a prompt word publishing request has been received, and then encapsulate the target prompt word into a callable target task.

[0067] like Figure 2J As shown, the editing control display area 240 of the editing interface 200B can also display a publishing control 244. It should be noted that, although... Figure 2J The evaluation input area 270 is not shown, but upon completion of the evaluation, it can be displayed in the editing interface 200B in response to receiving a pull-down operation on the sliding control 206, detecting a trigger operation on the corresponding physical control, and / or detecting an up-swipe operation in the editing interface 200B. A trigger operation on the publishing control 244 can be detected to determine that a prompt word publishing request has been received.

[0068] In some embodiments, before triggering the publish control, the user can also select the version number of the target task to be packaged. For example... Figure 2IAs shown, the editing interface 200B can also display a version selection entry 207. In response to a detected trigger operation on the version selection entry 207, at least one version number can be displayed, such as "$DEV, 3, 2, 1". It's important to note that when the version number selection entry 207 corresponds to the development identifier "DEV", it indicates that the system is currently in development mode, meaning it's editing the target prompt word but hasn't been released. In this case, task invocation for the target prompt word is not possible; only editing, verification, and evaluation operations are allowed. When the version number selection entry 207 corresponds to a version number other than "DEV", for example, "1", it means the target task is associated with version number 1.

[0069] In some embodiments, when it is determined that the target task is associated with a specific, non-developmental version number, the editing interface 200B may also present a version disable flag 208. In response to detecting a triggering operation on the version disable flag 208, the currently selected version number is disabled. In some embodiments, the editing interface 200B also presents a status indicator control 209, which indicates the current version status. For example, the status indicator control 209 may present three states: DEV, active, and disabled.

[0070] It's important to note that regarding the version number associated with the target task, when the prompt editing request is a task creation request, the target task is associated with a first version number in response to the prompt release request. This first version number can be any version number. When the prompt editing request is a modification request for an already created task, the target task is associated with a second version number in response to the prompt release request. This second version number is different from the version number of the already created task. For example, during the creation phase of the target task, the version number associated with the target task can be 1; during the modification phase, the modified target task can be associated with version numbers 2, 3, 4, and so on. Therefore, target tasks at different stages can be associated with different version numbers, which helps users find target tasks later. For instance, if a user wants to find the target task after its second modification, the user can directly search for the modified target task from among multiple target tasks based on the version number associated with it.

[0071] In some embodiments, since the version numbers associated with target tasks at different stages are different (e.g., the target task in the creation stage and the target task in the first modification stage), the target task can also be invoked based on its version number. This allows for convenient and quick determination of the target task to be invoked from multiple target tasks, enables invocation of target tasks from different historical versions, and helps improve the efficiency of target task invocation.

[0072] refer to Figure 3 , Figure 3 A schematic diagram of a prompt word management process 300 according to some embodiments of the present disclosure is shown. Process 300 can be implemented in a prompt word management system 120. For ease of discussion, reference will be made to... Figure 1 The environment 100 is used to describe the process 300.

[0073] In box 310, the prompt word management system 120 creates a target task in response to the received user input.

[0074] In box 320, the prompt management system 120 responds to user input in the prompt management system 120 and defines a prompt template, which is the template of the target prompt.

[0075] In box 330, in response to receiving an evaluation request for the prompt word, the prompt word management system 120 performs an evaluation operation on the prompt word to evaluate the actual effect of the prompt word.

[0076] In box 340, it is determined whether the prompt word meets the launch criteria. In some embodiments, the actual effect of the prompt word can be evaluated to determine whether it meets user expectations, and if it meets expectations, it is determined that the launch criteria have been met. Further, in box 350, the prompt word that has met the launch criteria can be published.

[0077] In some embodiments, if the actual results obtained from the evaluation do not meet expectations, it can be determined that the launch standard has not been met. The prompt word management system 120 can prompt the user to modify the prompt word template. That is, return to the steps shown in execution box 320. In some embodiments, the evaluation steps shown in box 330 and the judgment steps shown in box 340 can be continued on the modified prompt word template until the modified prompt word template meets the launch standard and can be published.

[0078] In some embodiments, in addition to performing the evaluation method shown in box 33 on the prompt words, verification can also be performed on them to determine their actual effect.

[0079] In summary, according to the embodiments of this disclosure, prompt words can be flexibly designed and managed, and prompt words can be encapsulated into callable tasks. This makes model invocation very simple and can improve the stability, reliability, convenience and efficiency of prompt word management and model invocation in practical applications.

[0080] It should be understood that some embodiments of this disclosure have been described above with reference to specific examples in the accompanying drawings, but these specific examples are not intended to limit the scope of the embodiments of this disclosure. The described embodiments can also be implemented in various other variations.

[0081] Figure 4 A flowchart of a process 400 for prompt word management according to some embodiments of the present disclosure is shown. Process 400 can be implemented in a prompt word management system 120. Reference is made below. Figure 1 Describe the process 400.

[0082] In box 410, the prompt management system 120 responds to receiving a prompt editing request by presenting an editing interface, wherein the editing interface includes at least an input area for receiving the target prompt.

[0083] In box 420, in response to receiving a prompt word publishing request, the prompt word management system 120 encapsulates the target prompt word into a callable target task, based at least on user input in the editing interface, wherein calling the target task will trigger the target prompt word to be input into the model.

[0084] In some embodiments, the editing interface further includes a variable definition area for receiving definitions of at least one variable involved in the target prompt, wherein a call to the target task will trigger the assignment of at least one variable and the input of the target prompt with the assigned at least one variable into the model.

[0085] In some embodiments, the editing interface further includes a model definition area for receiving a selection of a target model, wherein an invocation of a target task will trigger a target prompt to be input into the selected target model.

[0086] In some embodiments, the model definition area is further used to receive the definition of processing parameters for the target model, and wherein an invocation of the target task will trigger the target model to process the target prompt word according to the defined processing parameters.

[0087] In some embodiments, the editing interface further includes a task definition area for receiving a task identifier of a target task, and wherein invoking the target task includes invoking the target task based on the task identifier of the target task.

[0088] In some embodiments, the input area is used to receive a template for a target prompt word, the template defining the structure of the target prompt word.

[0089] In some embodiments, process 400 further includes: before receiving a prompt word publishing request, in response to receiving a verification request for a target prompt word, inputting the target prompt word into the model based at least on user input in the editing interface; receiving model output for the target prompt word from the model; and presenting the received model output.

[0090] In some embodiments, process 400 further includes: if the prompt word editing request is a task creation request, associating the target task with a first version number in response to the prompt word release request; and if the prompt word editing request is a modification request for an already created task, associating the target task with a second version number, which is different from the version number of the already created task, in response to the prompt word release request.

[0091] In some embodiments, invoking a target task includes invoking the target task based on its version number.

[0092] In some embodiments, process 400 further includes: in response to receiving an evaluation request for a target prompt word, presenting an evaluation input area; receiving evaluation data for the target prompt word in the evaluation input area, the evaluation data indicating multiple values ​​of at least one variable involved in the target prompt word; generating an evaluation result for the target prompt word based on the evaluation data; and providing an access point for the evaluation result.

[0093] In some embodiments, generating evaluation results includes: generating multiple test prompts by assigning values ​​to at least one variable using multiple values ​​for at least one variable in the evaluation data; inputting the multiple test prompts into a model; receiving multiple model outputs for the test prompts from the model; and generating evaluation results based on the multiple model outputs.

[0094] In some embodiments, presenting the editing interface includes: determining the permissions of the user who initiated the prompt editing request if the prompt editing request is a modification request for an already created task; and presenting the editing interface if the user has an editing request for an already created task.

[0095] In some embodiments, process 400 further includes: presenting a task list on the prompt word management system, the task list including at least one task that has been created.

[0096] Figure 5 A schematic structural block diagram of a device 500 for prompt word management according to certain embodiments of the present disclosure is shown. The device 500 may be implemented as or included in a prompt word management system 120. Various modules / components in the device 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0097] As shown in the figure, device 500 includes an interface presentation module 510 configured to present an editing interface in response to receiving a prompt word editing request, wherein the editing interface includes at least an input area for receiving the target prompt word. Device 700 also includes a publishing module 520 configured to, in response to receiving a prompt word publishing request, encapsulate the target prompt word into a callable target task based at least on user input in the editing interface, wherein calling the target task will trigger the target prompt word to be input into the model.

[0098] In some embodiments, the editing interface further includes a variable definition area for receiving definitions of at least one variable involved in the target prompt, wherein a call to the target task will trigger the assignment of at least one variable and the input of the target prompt with the assigned at least one variable into the model.

[0099] In some embodiments, the editing interface further includes a model definition area for receiving a selection of a target model, wherein an invocation of a target task will trigger a target prompt to be input into the selected target model.

[0100] In some embodiments, the model definition area is further used to receive the definition of processing parameters for the target model, and wherein an invocation of the target task will trigger the target model to process the target prompt word according to the defined processing parameters.

[0101] In some embodiments, the editing interface further includes a task definition area for receiving a task identifier of a target task, and wherein invoking the target task includes invoking the target task based on the task identifier of the target task.

[0102] In some embodiments, the input area is used to receive a template for a target prompt word, the template defining the structure of the target prompt word.

[0103] In some embodiments, the apparatus 500 further includes: a prompt word input module configured to, in response to receiving a verification request for a target prompt word, input a target prompt word into the model based at least on user input in the editing interface before receiving a prompt word publishing request; an output receiving module configured to receive model output for the target prompt word from the model; and an output rendering module configured to render the received model output.

[0104] In some embodiments, the apparatus 500 further includes: a first association module configured to associate a target task with a first version number in response to a prompt release request when the prompt editing request is a task creation request; and a second association module configured to associate a target task with a second version number in response to a prompt release request when the prompt editing request is a modification request for an already created task, the second version number being different from the version number of the already created task.

[0105] In some embodiments, invoking a target task includes invoking the target task based on its version number.

[0106] In some embodiments, the apparatus 500 further includes: an evaluation area presentation module configured to present an evaluation input area in response to receiving an evaluation request for a target prompt word; an evaluation data receiving module configured to receive evaluation data for the target prompt word in the evaluation input area, the evaluation data indicating multiple values ​​of at least one variable involved in the target prompt word; an evaluation result generation module configured to generate an evaluation result for the target prompt word based on the evaluation data; and an access point providing module configured to provide an access point for the evaluation result.

[0107] In some embodiments, the evaluation result generation module includes: a test prompt word generation module, configured to generate multiple test prompt words by assigning values ​​to at least one variable using multiple values ​​for at least one variable in the evaluation data; an input module, configured to input the multiple test prompt words into the model respectively; a receiving module, configured to receive multiple model outputs for the test prompt words from the model; and a generation module, configured to generate evaluation results based on the multiple model outputs.

[0108] In some embodiments, the interface presentation module 510 includes: a permission determination module configured to determine the permissions of the user initiating the prompt editing request when the prompt editing request is a modification request for an already created task; and a presentation module configured to present an editing interface if the user has an editing request for an already created task.

[0109] In some embodiments, the device 500 further includes a task list presentation module configured to present a task list on a prompt word management system, the task list including at least one task that has been created.

[0110] The modules and / or units included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules and / or units 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 modules and / or units 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.

[0111] 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 Electronic device 110 and / or a combination of other electronic devices.

[0112] 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 Electronic devices 110.

[0113] like Figure 6 As 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 processors or processing units 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 610 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.

[0114] 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.

[0115] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6As 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 managing prompt words, executed by a prompt word management system, the method comprising: In response to receiving a prompt word editing request, an editing interface is presented, wherein the editing interface includes at least an input area and a variable definition area, the input area is used to receive a template of the target prompt word, the template defines the structure of the target prompt word and includes the name of at least one variable contained in the target prompt word, and the variable definition area is used to receive the definition of the at least one variable in the target prompt word; as well as In response to receiving a prompt word publishing request, and based at least on user input in the editing interface, the target prompt word is encapsulated into a callable target task, wherein invoking the target task triggers the target prompt word to be input into the model, and the model performs the operation indicated by the target task based on the target prompt word. The invocation of the target task will trigger the presentation of assignment prompt information, which is used to prompt the user to assign a value to at least one variable. The assignment value of each of the at least one variable is determined based on the user's interaction, and the target prompt word with the assigned value of the at least one variable is input into the model.

2. The method according to claim 1, wherein the editing interface further includes a model definition area for receiving a selection of a target model, and The invocation of the target task will trigger the input of the target prompt word into the selected target model.

3. The method according to claim 2, wherein the model definition region is further configured to receive the definition of processing parameters for the target model, and The invocation of the target task will trigger the target model to process the target prompt word according to the defined processing parameters.

4. The method according to claim 1, wherein the editing interface further includes a task definition area for receiving the task identifier of the target task, and The invocation of the target task includes invoking the target task based on its task identifier.

5. The method according to claim 1, further comprising: Before receiving the prompt word publishing request, in response to receiving a verification request for the target prompt word, the target prompt word is input into the model based at least on user input in the editing interface; Receive model output for the target prompt word from the model; as well as Present the received model output.

6. The method according to claim 1, further comprising: If the prompt word editing request is a task creation request, in response to the prompt word release request, the target task is associated with a first version number; as well as If the prompt word editing request is a modification request for an already created task, in response to the prompt word publishing request, the target task is associated with a second version number, which is different from the version number of the already created task.

7. The method of claim 6, wherein invoking the target task includes invoking the target task according to the version number of the target task.

8. The method according to claim 1, further comprising: In response to receiving an evaluation request for the target prompt word, an evaluation input area is presented; The evaluation input area receives evaluation data for the target prompt word, the evaluation data indicating multiple values ​​of at least one variable involved in the target prompt word; Based on the evaluation data, an evaluation result is generated for the target prompt word; as well as Provide access to the evaluation results.

9. The method according to claim 8, wherein generating the evaluation result comprises: Multiple test prompt words are generated by assigning values ​​to the at least one variable using multiple values ​​for the at least one variable in the evaluation data; Input the multiple test prompt words into the model respectively; Receive multiple model outputs for the test prompt words from the model; as well as The evaluation results are generated based on the outputs of the multiple models.

10. The method of claim 1, wherein presenting the editing interface comprises: If the prompt word editing request is a modification request for an already created task, determine the permissions of the user who initiated the prompt word editing request; as well as If the user has editing permissions for the created task, the editing interface is displayed.

11. The method according to claim 1, further comprising: A task list is presented on the prompt word management system, the task list including at least one task that has been created.

12. An apparatus for managing prompt words, comprising: The interface presentation module is configured to present an editing interface in response to receiving a prompt word editing request. The editing interface includes at least an input area and a variable definition area. The input area is used to receive a template of the target prompt word. The template defines the structure of the target prompt word and includes the name of at least one variable contained in the target prompt word. The variable definition area is used to receive the definition of the at least one variable in the target prompt word. as well as The publishing module is configured to, in response to receiving a prompt word publishing request, encapsulate the target prompt word into a callable target task, based at least on user input in the editing interface, wherein invoking the target task triggers the target prompt word to be input into the model, and the model performs the operation indicated by the target task based on the target prompt word. The invocation of the target task will trigger the presentation of assignment prompt information, which is used to prompt the user to assign a value to at least one variable. The assignment value of each of the at least one variable is determined based on the user's interaction, and the target prompt word with the assigned value of the at least one variable is input into the model.

13. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 11.

Images