CN-122018746-A - Method, apparatus, device, storage medium and program product for managing prompt words

CN122018746ACN 122018746 ACN122018746 ACN 122018746ACN-122018746-A

Abstract

Embodiments of the present disclosure provide methods, apparatus, devices, storage media, and program products for hint word management. The method includes providing a creation page for the creation of a hint word in response to a resource creation request of the hint word, receiving, via a creation interface, the created target hint word and identification information of the target hint word, and adding the received target hint word and identification information to a hint word library in response to a validation instruction, the hint word library including at least one hint word, each hint word selectable for association into a machine learning model based function, the associated hint word provided as an input to a machine learning model. Thus, for machine learning model based functions (e.g., digital assistant, workflow nodes), the hint words can be saved in a hint word library for reuse by the user in creating the function.

Inventors

YAO HUI
CHEN QINGHONG
PENG YIRAN
Hao Zhenfei
LI CHENGWU

Assignees

北京字跳网络技术有限公司

Dates

Publication Date: 20260512
Application Date: 20241111

Claims (13)

1. A method of alert word management, comprising: responding to a resource creation request of the prompt word, and providing a creation interface for the creation of the prompt word; receiving the created target prompt word and the identification information of the target prompt word via the creation interface, and In response to the confirmation indication, adding the received target prompt word and the identification information to a prompt word library, the prompt word library including at least one prompt word, each prompt word selectable to be associated into a machine learning model-based function, the associated prompt word provided as an input to the machine learning model.
2. The method of claim 1, further comprising: In a first editing interface of a first function, responding to the trigger of the prompt word stock, and presenting at least one prompt word in the prompt word stock; responding to the application request of the first prompt word in the at least one prompt word, inserting the first prompt word into the area corresponding to the prompt word editing in the editing interface, and The first function is created based at least on the first hint word or the edited first hint word, the first hint word or the edited first hint word is capable of being input to a first machine learning model associated with the first function, and an output of the first function is determined based on an output of the first machine learning model.
3. The method of claim 2, wherein presenting the at least one hint word comprises: Presenting the at least one hint word in response to a trigger to the hint word library, and In response to a prompt word of the at least one prompt word being selected, presenting a preview of the selected prompt word.
4. The method of claim 2, wherein presenting the at least one hint word comprises: In response to a trigger to the alert word library, the at least one alert word is presented by type, wherein each alert word is categorized into at least one of a plurality of types.
5. The method of claim 2, wherein triggering of the hint word library is initiated via: triggering a first prompt thesaurus entry in the first editing interface; and selecting the type of the prompt word resource in the resource adding interface.
6. The method of claim 1, wherein providing a creation interface for hint word creation comprises: Presenting a second editing interface of a second function, wherein the second editing interface at least comprises inputted second prompt words; Providing a creation interface for creating the prompt word in response to receiving a resource creation request of the prompt word via a second editing interface of the second function, the creation interface at least comprising an import control, and And in response to detecting the triggering of the import control, inserting the second prompt word into the area for inputting the prompt word in the creation interface.
7. The method of claim 1, wherein permissions for at least one of application, editing, deletion of a hint word in the hint word library are based on a role of a user.
8. The method of claim 1, wherein the identification information includes at least one of a hint word name and description information, and Wherein the creation interface includes at least a first area for entry of a hint word, and the creation interface further includes at least one of a second area for entry of a hint word name and a third area for entry of descriptive information.
9. The method of claim 1, wherein the function based on a machine learning model comprises at least one of a digital assistant, a workflow node in a workflow.
10. An apparatus for alert word management, comprising: a creation interface providing module configured to provide a creation interface for the creation of the hint word in response to a resource creation request of the hint word; A receiving module configured to receive the created target prompt word and the identification information of the target prompt word via the creation interface, and An adding module configured to add the received target alert word and the identification information to an alert word library in response to a confirmation indication, the alert word library comprising at least one alert word, each alert word selectable to be associated into a machine learning model based function, the associated alert word provided as an input to the machine learning model.
11. An electronic device, comprising: 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, which when executed by the at least one processing unit, cause the electronic device to perform the method of any one of claims 1 to 9.
12. A computer readable storage medium having stored thereon a computer program executable by a processor to implement the method of any of claims 1 to 9.
13. A computer program product comprising computer executable instructions which when executed by a processor implement the method of any one of claims 1 to 9.

Description

Method, apparatus, device, storage medium and program product for managing prompt words Technical Field Example embodiments of the present disclosure relate generally to the field of computers and, more particularly, relate to methods, apparatuses, devices, computer-readable storage media and computer program products for alert word management. Background With the rapid development of computer technology, the application of machine learning models is also becoming wider, wherein the prompt words are key tools for interacting with the machine learning models. The accurate prompt word is not only the key of the optimization generation task, but also the core for determining the output quality of the machine learning model. For example, a machine learning model-based digital assistant can understand and reply to interactive messages entered by a user in natural language based on the machine learning model. Therefore, the high-quality prompt words can obviously improve the understanding depth of the machine learning model to the task, thereby promoting the generation of high-quality content. Disclosure of Invention In a first aspect of the present disclosure, a method of alert word management is provided. The method includes providing a creation page for the creation of a hint word in response to a resource creation request of the hint word, receiving, via a creation interface, the created target hint word and identification information of the target hint word, and adding the received target hint word and identification information to a hint word library in response to a validation instruction, the hint word library including at least one hint word, each hint word selectable for association into a machine learning model based function, the associated hint word provided as an input to a machine learning model. In a second aspect of the present disclosure, an apparatus for hint word management is provided. The device comprises a creation interface providing module, a receiving module and an adding module, wherein the creation interface providing module is configured to respond to a resource creation request of a prompt word and provide a creation page for the creation of the prompt word, the receiving module is configured to receive a created target prompt word and identification information of the target prompt word through the creation interface, the adding module is configured to respond to a confirmation instruction and add the received target prompt word and the identification information into a prompt word library, the prompt word library comprises at least one prompt word, each prompt word can be selected to be associated with a function based on a machine learning model, and the associated prompt word is provided as input of the machine learning model. In a third aspect of the present disclosure, an electronic device is provided. The apparatus 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. The instructions, when executed by at least one processing unit, cause the electronic device to perform the method of the first aspect. In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer readable storage medium has stored thereon a computer program executable by a processor to implement the method of the first aspect. In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product comprises computer executable instructions which, when executed by a processor, implement the method of the first aspect. It should be understood that what is described in this section is not intended to limit the key features or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. Drawings The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, wherein like or similar reference numerals denote like or similar elements, in which: FIG. 1 illustrates a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented; 2A-2G illustrate schematic diagrams of example interfaces for hint word management, according to some embodiments of the present disclosure; 3A-6 illustrate schematic diagrams of example interfaces for creating new hint words or editing specific functions according to some embodiments of the present disclosure; 7A-7E illustrate schematic diagrams of example interfaces for comment functionality on a hint word according to some embodiments of the present disclosure; FIG. 8 illustrates a flowchart of