Method and apparatus for information processing, and device and storage medium

By receiving user input in the application creation platform and converting it into richer prompt word input, the problem of low-code platforms understanding user input in specific scenarios is solved, improving model processing efficiency and accuracy, and improving user experience.

WO2024240105A1PCT designated stage expired Publication Date: 2024-11-28LEMON INC(GB) +1

Patent Information

Application Number
PCT/CN2024/094159
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-19
Filing Date
2024-05-20
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Application creation platforms, especially low-code platforms, are difficult to understand user input in specific scenarios through preset content, and cannot accurately determine and execute tasks in user intentions, resulting in low-efficiency model processing and inaccurate output.

Method used

By receiving user input, determining the matching target prompt word input, adjusting and expanding, it is provided to the model to obtain more accurate task execution instructions, and improving the model's understanding of user needs.

Benefits of technology

Improve model processing efficiency and output accuracy, enhance user experience, and ensure that task execution meets user expectations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024094159_28112024_PF_FP_ABST
    Figure CN2024094159_28112024_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the embodiments of the present disclosure are a method and apparatus for information processing, and a device and a storage medium. The method comprises: receiving a first user input, wherein the first user input comprises first description information related to a task on an application creation platform; determining a target prompt word input, which matches the first user input, wherein the target prompt word input comprises second description information related to the task, and the second description information comprises at least one of the following: description information which is obtained after adjustment to at least part of the first description information, or extended description of at least part of the first description information; and providing the target prompt word input to a model, so as to obtain an instruction, which is output by the model and related to an execution operation for the task. In this way, a user input is converted into a prompt word input, which is informative and easier to understand by a model, such that an output of the model is more accurate, thereby improving the efficiency and accuracy of task processing, and improving the usage experience of a user.
Need to check novelty before this filing date? Find Prior Art

Description

Method, apparatus, device and storage medium for information processing

[0001] This application claims priority to the Chinese invention patent application entitled “Methods, devices, equipment and storage media for information processing” and application number 202310576150.6, filed on May 19, 2023. The entire contents of that application are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for application processing. Background Art

[0003] With the rapid development of internet technology, a wide variety of applications have become essential tools in our daily lives. Different applications have distinct functions, allowing users to perform specific tasks or services through specialized applications. Application creation platforms, particularly low-code platforms, support efficient application development, enabling operations such as application creation and functional adjustments.

[0004] Summary of the Invention

[0005] In a first aspect of the present disclosure, a method for information processing is provided. The method includes: receiving first user input, the first user input including first descriptive information related to a task on an application creation platform; determining a target prompt word input that matches the first user input, the target prompt word input including second descriptive information related to the task, the second descriptive information including at least one of the following: descriptive information obtained by adjusting at least a portion of the first descriptive information, or an expanded description of at least a portion of the first descriptive information; and providing the target prompt word input to a model to obtain, as output by the model, an indication of an execution operation for the task.

[0006] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: an input receiving module configured to receive a first user input, the first user input including first descriptive information related to a task on an application creation platform; a prompt word determining module configured to determine a target prompt word input that matches the first user input, the target prompt word input including second descriptive information related to the task, the second descriptive information including at least one of the following: descriptive information obtained by adjusting at least a portion of the first descriptive information, or an expanded description of at least a portion of the first descriptive information; and a prompt word providing module configured to provide the target prompt word input to a model to obtain an indication of an execution operation of the task output by the model.

[0007] In a third aspect of the present 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.

[0008] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0009] It should be understood that the content described in this section is not intended to limit the key features or important 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 easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG2 shows a flowchart of an information processing process according to some embodiments of the present disclosure;

[0013] FIG3 is a schematic diagram showing an example flow of information processing according to some embodiments of the present disclosure;

[0014] FIG4 is a schematic diagram showing an example mapping relationship between user input and prompt word input according to some embodiments of the present disclosure;

[0015] FIG5 shows a schematic structural block diagram of an apparatus for information processing according to some embodiments of the present disclosure; and

[0016] FIG6 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0017] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part 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 be included below.

[0019] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0020] It is understandable 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 relevant provisions.

[0021] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0022] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0023] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0024] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0025] Application creation platforms, especially low-code platforms, find it difficult to understand user input in specific scenarios through pre-built content generation capabilities. For example, an application creation platform or the model it uses can understand user input such as "place the OK button on this page at the bottom of the page and select it by default," or "execute user input process A when the user clicks this button," because these inputs clearly indicate specific tasks. However, an application creation platform or the model it uses cannot understand user input that is strongly related to a specific domain or scenario, such as "make this e-commerce recommendation page more consistent with e-commerce usage habits" or "make this page a page style that allows for easy viewing of ultrasound results." This results in the application creation platform being unable to determine and execute the tasks indicated by user input through its own understanding capabilities or the understanding capabilities learned by the model.

[0026] According to an embodiment of the present disclosure, an improved scheme for information processing in an application creation platform is provided. According to the scheme, a first user input including first descriptive information related to a task on the application creation platform is received. A target prompt word input that matches the first user input is determined. The target prompt word input is provided to a model to obtain, with the help of the model, instructions for performing operations on the task. In this way, the received user input is converted into a prompt word input that is richer in information and easier for the model to understand, and the model is used to understand the task indicated by the user's needs. This helps to assist the model in understanding the user input, making model processing more efficient, model output more accurate, and in line with user expectations, thereby improving the user experience.

[0027] Figure 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, an application creation platform 110 can provide an application development and deployment environment. In some embodiments, the application creation platform 110 can be a low-code platform that provides a collection of tools for application development. The application creation platform 110 can support visual development of applications, allowing developers to skip the manual coding process and speed up the application development cycle and cost. The application creation platform 110 can support any appropriate platform for users to develop applications, for example, it can include a platform based on Application Platform as a Service (aPaaS).

[0028] The application creation platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device 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 systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the application creation platform 110 can be implemented based on cloud services.

[0029] The application creation platform 110 may be deployed locally on the user's terminal device and / or may be supported by a remote server. In some embodiments, the terminal device may run a client for the application creation platform 110, which may support user interaction with the application creation platform 110. When the application creation platform 110 runs locally on the user's terminal device, the user may directly interact with the local application creation platform 110 using the client. When the application creation platform 110 runs on a server device, the server device may, based on a communication connection with the terminal device, provide services to the client running on the terminal device.

[0030] The application creation platform 110 may be deployed with a digital assistant 120. A user 140 may interact with the digital assistant 120 via the application creation platform 110. The digital assistant 120 is used to engage in a conversation with the user 140. The client of the application creation platform 110 may present an interaction window, such as a conversation window, between the user 140 and the digital assistant 120 in the client interface. As an intelligent assistant, the digital assistant 120 has intelligent conversation and information processing capabilities. The user 140 may enter conversation messages in the conversation window, and the digital assistant 120 may provide reply messages in response to the user's conversation messages.

[0031] In the application creation platform 110, the digital assistant 120 can be called or awakened by an appropriate means (e.g., a shortcut key, a button, or voice) to present a conversation window with the user. In some embodiments, the digital assistant 120 can be included as a contact of the user in the contact list of the current user in the application creation platform 110, or included in the information flow of the chat component. By selecting the digital assistant 120, a conversation window with the digital assistant 120 can be opened. In some embodiments, the digital assistant 120 can also be started in one or more components supported by the application creation platform 110, thereby presenting a conversation window with the digital assistant 120.

[0032] The application creation platform 110 can obtain the interaction information between the user 140 and the digital assistant 120 in the conversation window (including conversation messages from the user and reply messages from the digital assistant 120). In some embodiments, the application creation platform 110 can use the model 125 to understand the user's conversation messages and determine the next operation to be performed. The application creation platform 110 can interact with the model 125 to provide model input to the model 125 and obtain corresponding model output from the model 125. The model 125 can run locally on the application creation platform 110 or on a remote server. In some embodiments, the model 125 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model 125 can be based on a language model (LM). The language model can have question-and-answer capabilities by learning from a large amount of corpus. The model 125 can also be based on other appropriate models.

[0033] Database 130 is used to store data or information required for application processing operations performed by application creation platform 110. For example, database 130 may store code and description information corresponding to each functional block that constitutes an application. Application creation platform 110 may also perform operations such as calling, adding, deleting, and updating the functional blocks in database 130. Database 130 may also store executable operations for different functional blocks. For example, when creating application 150, application creation platform 110 may call the corresponding functional blocks from database 130 to build application 150.

[0034] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0035] Some example embodiments of the present disclosure will be described in detail below with reference to examples in the accompanying drawings.

[0036] 2 shows a flow chart of a process 200 of information processing according to some embodiments of the present disclosure. The process 200 may be implemented at the application creation platform 110. For ease of discussion, the process 200 will be described with reference to the environment 100 of FIG.

[0037] In block 210 , the application creation platform 110 receives a first user input including first descriptive information related to a task on the application creation platform 110 .

[0038] In some embodiments, the client corresponding to the application creation platform 110 can present a conversation window between the user 140 and the digital assistant 120 on the client interface. The conversation window can be of any shape, any size, any color, and any position. The conversation window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. The conversation message in the conversation window may include content in one or more formats, such as text, images, audio, video, and the like. The digital assistant 120 can be used to interact with the user 140 during the application processing process of the application creation platform 110. The application creation platform 110 can, for example, receive first user input through the conversation window.

[0039] The first user input received by the application creation platform 110 may be a message input by the user 140 in the input box of the conversation window or through other means (e.g., voice input, etc.). In some embodiments, the user input may include multimodal input, such as text input (e.g., input in the form of natural language), voice input, image input, video input, etc.

[0040] The application creation platform 110 can determine the specific task indicated by the task through the interaction between the user 140 and the digital assistant 120. The first user input can indicate any task to be performed on the application creation platform. In some embodiments, the indicated task may include an application processing task for processing a specific application or a portion of an application. In some embodiments, the task may include a creation task for a target application (e.g., creating a new application), or an adjustment task for at least a portion of a target application (e.g., an adjustment task for a page, a data table, or an operation control of the target application).

[0041] In some embodiments, the application creation platform 110 can use the model 125 to understand user input and determine the response to the user input. In some embodiments, if certain user input is directly input to the model 124, it may be difficult for the model 125 to accurately understand it, especially when the user input involves specific scenarios and specific fields. For example, if the first user input received by the application creation platform 110 is "make this e-commerce recommended page more in line with e-commerce usage habits," the model 125 may not be able to accurately determine how the user 140 specifically wants to adjust the interface. In this case, if the descriptive information in the user input is directly used as the input of the model 125, the obtained model output may be unsatisfactory, resulting in the final task execution failing to meet user needs. In the embodiments of the present disclosure, the application creation platform 110 does not directly provide the information in the user input directly to the model 125 for processing. Instead, the user input is converted into a prompt word input that is richer in information and easier for the model to understand, and is provided to the model 125 for processing, and the task execution operation is determined based on the output of the model 125.

[0042] At block 220, the application creation platform 11 determines a target prompt word input that matches the first user input. The determined target prompt word input includes second descriptive information related to the task, and the second descriptive information includes at least one of the following: a description obtained by adjusting at least a portion of the first descriptive information, or an expanded description of at least a portion of the first descriptive information.

[0043] In embodiments of the present disclosure, the first descriptive information input by the user can be adjusted and / or expanded to obtain second descriptive information, so that the prompt word input containing the second descriptive information is easier for the model to understand, thereby enabling the model to provide accurate and expected model output. In some embodiments, the user's intent can be more clearly expressed by adjusting part of the description in the first descriptive information input by the user. In some embodiments, part or all of the first descriptive information can be expanded. The expanded description can be an explanation or assistance of the first descriptive information or the task it indicates. For example, it can be an explanation or definition of certain terms in the first descriptive information, a specific example, and / or additional contextual information. For example, if the user input is "make this e-commerce recommended page more in line with e-commerce usage habits," the second descriptive information input for the target prompt word may include a sample page that meets e-commerce usage habits and / or a detailed definition of the sample page layout that meets e-commerce usage habits. The expanded description in the second descriptive information can enable the subsequent model 125 to better understand the specific task in a specific scenario or domain, thereby better determining the execution operation of the task, thereby assisting the application creation platform 110 in executing the corresponding task.

[0044] In some embodiments, one or more prompt word inputs can be configured and stored in a prompt word library accessible to the application creation platform 110. Figure 3 shows a schematic diagram of an example process 300 of information processing according to some embodiments of the present disclosure. As shown in Figure 3, the application creation platform 110 can receive a user input from a user 140, "Make this e-commerce recommended page more in line with e-commerce usage habits." The application creation platform 110 can determine the prompt word input 310-1 to which the user input is mapped from the prompt word library 320. The prompt word library 320 here can be included in the database 130 of Figure 1, or be independent of the database 130. The prompt word library 320 includes multiple prompt word inputs 310 (for example, prompt word inputs 310-1, 310-2, ..., 310-N, where N is a positive integer greater than 1).

[0045] The application creation platform 110 can determine the target prompt word input that matches the current first user input from one or more prompt word inputs. In some embodiments, the application creation platform 110 can select the target prompt word input that matches the first user input from one or more prompt word inputs. The selected target prompt word input can be, for example, the prompt word input that has the highest degree of match with the first user input (and is higher than a predetermined threshold). The degree of match here indicates the semantic relevance between the first user input and the prompt word input. The application creation platform 110 determines the semantic relevance between the user input and the prompt word input based on various methods. The higher the semantic relevance, the closer the expression of the first user input and the prompt word input is, and thus the two are considered to be more matched. For example, each prompt word input and the first user input can be converted into a semantic vector representing their semantics, and the degree of match between the prompt word input and the first user input can be determined by calculating the distance between the semantic vector of each prompt word input and the semantic vector of the first user input. The target prompt word input can be the prompt word input that has a higher degree of match with the first user input (for example, the highest degree of match and higher than a predetermined threshold).

[0046] In some embodiments, a mapping relationship between user input and prompt word input can be configured, and the mapping relationship can be stored in a prompt word library accessible to the application creation platform 110. The mapping relationship can include a mapping between one or more candidate user inputs and one or more prompt word inputs. In the mapping relationship, the user input and the prompt word input can be a one-to-one mapping relationship or a many-to-one mapping relationship. In the mapping relationship, the candidate user input can be a form related to the prompt word input that the user may input. The candidate user input included in the mapping relationship can be a multimodal form, such as text input (for example, input in the form of natural language), voice input, image input, video input, and the like. In some embodiments, the mapping relationship can be a mapping relationship between a natural language sequence and a prompt word input, that is, the prompt word can be mapped to one or more natural language sequences.

[0047] In the example of FIG3 , the prompt word library 320 may include a mapping relationship between natural language sequences and prompt word inputs. As shown in FIG3 , prompt word input 310-1 is mapped to natural language sequence 312-1. Although not shown, one or more other prompt word inputs 310 in the prompt word library 320 may also be mapped to one or more natural language sequences.

[0048] In some embodiments, taking into account that different users may express the same task differently, the same prompt word input in the mapping relationship can be mapped to multiple candidate user inputs (e.g., multiple natural language sequences), that is, the user input and the prompt word input are in a many-to-one relationship. For example, multiple natural language sequences such as "page layout recommended by e-commerce", "style of e-commerce recommended page", and "recommended page that conforms to e-commerce scenarios" can correspond to the same prompt word input, which can include specific descriptive information about adjusting the page to the page layout recommended by e-commerce. It should be understood that one or some prompt word inputs in the mapping relationship can also be mapped to a single candidate user input, and the scope of the embodiments of the present disclosure is not limited to this.

[0049] Figure 4 illustrates an example mapping relationship 400 between user input and prompt word input, according to some embodiments of the present disclosure. As shown in Figure 4 , mapping relationship 400 may include multiple candidate user inputs and multiple prompt word inputs, each of which may be mapped to one or more candidate user inputs. For example, user inputs 11 through 1N may be mapped to prompt word input 1; user inputs 21 through 2N may be mapped to prompt word input 2, and so on.

[0050] In some embodiments, if a mapping relationship between user input and prompt word input is pre-established, the application creation platform 110 can determine a target prompt word input that matches the first user input based on the mapping relationship. Specifically, the application creation platform 110 can determine a target user input that matches the first user input from the mapping relationship, and determine the prompt word input to which the target user input is mapped in the mapping relationship as the target prompt word input. The target user input can be selected based on the degree of match between the first user input and each candidate user input in the mapping relationship. The degree of match here indicates the degree of correlation between the first user input and the candidate user inputs.

[0051] In an embodiment where the user input is in the form of a natural language, the degree of match may indicate the semantic relevance between the first user input and the candidate user input. The application creation platform 110 determines the semantic relevance between two natural language sequences based on various methods. The higher the semantic relevance, the closer the expression of the first user input and the natural language sequence is, and thus the two are considered to be more matched. For example, each natural language sequence and the first user input in the mapping relationship can be converted into a semantic vector representing its semantics, and the degree of match between the natural language sequence and the first user input is determined by calculating the distance between the semantic vector of each natural language sequence and the semantic vector of the first user input. The target user input may be a natural language sequence that has a higher degree of match with the first user input (for example, the highest degree of match and higher than a predetermined threshold).

[0052] In some embodiments, if the first user input and / or the candidate user input in the mapping relationship is in other modalities, such as images, videos, etc., the degree of match between the first user input and the candidate user input in the mapping relationship can also be determined based on the data correlation algorithm under the corresponding modality, thereby selecting the corresponding target prompt word input.

[0053] In the example of FIG3 , the user input "Make this e-commerce recommended page more in line with e-commerce user habits" can be matched to the natural language sequence "e-commerce recommended page layout" in the mapping relationship, and the prompt word input 310-1 is mapped to this natural language sequence. Therefore, the application creation platform 110 can determine that the prompt word input 310-1 is the prompt word input matched by the user input.

[0054] As described above, a certain prompt word input in the mapping relationship can be mapped to multiple candidate user inputs (for example, multiple natural language sequences). In such a case, for the prompt word input, the application creation platform 110 can determine the degree of match between the first user input and the multiple candidate user inputs in the mapping relationship. The application creation platform 110 can select the target user input that matches the first user input from the multiple candidate user inputs based on the determined degree of match. Exemplarily, the application creation platform 110 can determine the candidate user input with the highest degree of match between the first user input and the first user input as the target user input that matches the first user input. Further, the application creation platform 110 can, in response to determining that the first user input matches the target user input in the mapping relationship, determine the prompt word input to which the target user input is mapped from the mapping relationship as the target prompt word input. As shown in Figure 4, if the target user input is user input 21, the application creation platform 110 can select prompt word input 2 to which user input 21 is mapped from the multiple prompt word inputs included in the mapping relationship 400, and use prompt word input 2 as the target prompt word input.

[0055] In certain embodiments, the mapping relationships corresponding to different fields (or scenarios) may be different. For example, the mapping relationships corresponding to the medical field and the gaming field are different. In particular, in different mapping relationships, different prompt word inputs may be configured. To ensure the accuracy of the prompt word input ultimately determined, the mapping relationship here may be specific to the target domain relevant to the application creation platform. That is, the prompt word input included in the mapping relationship is the prompt word input for the target domain, which helps to improve subsequent accurate model generation determined by model 125.

[0056] In some embodiments, the configured prompt word input, or the mapping relationship between the user input and the prompt word input, can be updated during use. The generation and update of the prompt word input or the mapping relationship will be described in more detail below.

[0057] Referring back to FIG. 2 , after determining the target prompt word input, in block 230 , the application creation platform 110 provides the target prompt word input to the model 125 to obtain an instruction output by the model 125 regarding the execution operation of the task.

[0058] Because the target prompt word input includes more supplements and extensions to the task the user desires to perform, model 125 can more accurately understand the user's expectations from the target prompt word input, thereby determining instructions for executing the task. The instructions for executing the task can be provided as model output by model 125 to application creation platform 110. For example, in the example of Figure 3, prompt word input 310-1 can be provided to model 125 as the target prompt word input to which the user input is mapped, so that model 125 outputs instructions for executing the task.

[0059] After receiving the instructions for the execution operation of the task provided by the model 125, in some embodiments, the application creation platform 110 can present the instructions for the execution operation of the task as a reply to the first user input. For example, in the example of Figure 3, if the user enters the conversation message "Make this e-commerce recommended page more in line with e-commerce usage habits" in the conversation window with the digital assistant, a reply to the conversation message can be presented based on the output of the model 125. In some embodiments, the application creation platform 110 can determine the specific execution operation of the task indicated by the first user input based on the instructions for the execution operation of the task provided by the model 125. The operation performed by the application creation platform 110 can be the operation provided by the model 125, or it can be an operation adjusted based on the provided execution operation. Of course, the application creation platform 110 can also directly execute the execution operation of the task indicated by the model 125.

[0060] In some embodiments, after the application creation platform 110 obtains the instructions regarding the task from the model 125, it can also present a response to the first user input through the conversation window between the user 140 and the digital assistant 120. The response here includes at least instructions for executing the task (e.g., describing how to execute the task specifically) and / or an indication of the task execution result. In this way, the user can promptly understand how the task will be executed, the execution results, etc.

[0061] The following will describe how to generate and update prompt word inputs, and / or the mapping relationship between user input and prompt word inputs. In some embodiments, the prompt word inputs in the prompt word library can be obtained by pre-populating prompt words associated with user inputs in related fields into the input template of model 125 through prompt word engineering. The prompt words here can be specific words pre-defined in the related fields. The prompt word input can be an input form that conforms to model 125. In some embodiments, the prompt word inputs, and / or the mapping relationship between user input and prompt word inputs can be pre-determined by staff in the related fields and directly provided to the application creation platform 110. For example, in Figure 3, they can be provided by prompt word engineers 330 (also referred to as prompt word developers). Prompt word engineers 330 can, for example, determine each prompt word input, and / or the candidate user inputs to which the prompt word inputs are mapped, through offline communication or through instructions in other fields.

[0062] In some embodiments, during the process of the application creation platform 110 executing various tasks instructed by the user, new prompt word inputs and / or candidate user inputs mapped to the prompt word inputs may be generated by collecting user feedback information on the tasks.

[0063] Take the generation of the "target prompt word input" mapped to the first user input mentioned above as an example. The application creation platform 110 can obtain a second user input including descriptive information of a task of the same type as the first user input task. The application creation platform 110 can obtain user feedback information (referred to as "second user feedback information" in this article for the sake of distinction). The second user feedback information is feedback for the reply to the second user input, and the second user input includes descriptive information of a task of the same type as the task. That is, other users expect to perform similar tasks in the application creation platform 110, and after the application creation platform 110 performs the task with the help of the model 125, the user feedback information can be collected.

[0064] In some embodiments, the application creation platform 110 may determine second user feedback information based on a user operation behavior detected after the second user input indicates or completes the execution of the task. This user operation behavior may, for example, be feedback entered by user 140 in the conversation window, such as a user expressing approval or liking of the execution of the task or the result of the task execution. In some embodiments, if the task has been completed according to the indicated operations, the application creation platform 110 may determine that the user is dissatisfied with the execution of the task provided by the model 125 in response to detecting the user's cancellation or deletion of one or more execution operations of the task.

[0065] The application creation platform 110 can generate a target prompt word input based at least on the second user feedback information. In some embodiments, if the second user feedback information indicates that the execution of the task does not meet the expected goal, the application creation platform 110 can determine that there is a need to generate a target prompt word input. In some cases, if no prompt word input that matches the second user input has been found before, the application creation platform 110 will generate the input of the model 125 based on the descriptive information in the second user input, which may cause the model 125 to be unable to accurately understand the task to be performed by the user, resulting in the execution of the task not being satisfactory to the user. In an embodiment of the present disclosure, by collecting user feedback, a new prompt word input can be created, and / or a new prompt word input and user input can be added in the mapping relationship. In this way, the new prompt word input can be used to improve the efficiency and user satisfaction of subsequent similar tasks.

[0066] In some embodiments, the target cue word input may be provided by a cue word engineer (e.g., cue word engineer 330 in FIG3 ). For example, the second user input and / or second user feedback information may be presented to the cue word engineer to instruct the cue word engineer to generate a new cue word input.

[0067] In some embodiments, if a mapping relationship between user input and prompt word input is required, then after generating a target prompt word input that matches the second user input, the application creation platform 110 may also generate at least one candidate user input to which the target prompt word input is mapped in the mapping relationship. In some embodiments, the application creation platform 110 may obtain multiple different second user inputs and generate target prompt word inputs that match these multiple second user inputs. Based on the multiple second user inputs, the application creation platform 110 may determine multiple candidate user inputs to which the target prompt word input is mapped.

[0068] In some embodiments, during the operation of the application creation platform 110 , one or more prompt word inputs and / or one or more candidate user inputs mapped thereto (in examples using mapping relationships) may be continuously added, deleted, or updated.

[0069] Assuming the first user input mentioned above as an example, the first user input indicates a task on the application creation platform 110. As described above, the first user input is converted into a target prompt word input and provided to the model 125, and an instruction for executing the task is obtained from the model 125. Based on this, in some embodiments, the application creation platform 110 can obtain first user feedback information regarding the task. In some embodiments, the application creation platform 110 can receive a reply from the user 140 in the conversation window and use it as the first user feedback information regarding the task. In some embodiments, the application creation platform 110 can also determine the first user feedback information based on user operation behavior detected after the instruction or completion of the task execution operation. This user operation behavior can be, for example, feedback entered by the user 140 in the conversation window, such as expressing approval or satisfaction with the task execution operation or the task execution result. In some embodiments, if the task has been completed according to the indicated operations, the application creation platform 110 can determine that the user is dissatisfied with the task execution operation provided by the model 125 in response to detecting that the user has revoked or deleted one or more execution operations for the task.

[0070] The application creation platform 110 can then determine adjustments to the target prompt word input based at least on the first user feedback information. In some embodiments, the application creation platform 110 can determine that the target prompt word input needs to be adjusted if the first user feedback information indicates that the execution of the task does not meet the expected goal. In this case, if the first user feedback information can indicate an adjustment method, the application creation platform 110 can directly adjust the target prompt word input based on the adjustment method indicated by the first user feedback information. In some embodiments, if the first user feedback information cannot indicate an adjustment method, the application creation platform 110 can present clarification guidance to the user to guide the user to clarify the desired adjustment method.

[0071] In some embodiments, if it is determined that the target prompt word input needs to be adjusted, the application creation platform 110 can present a prompt word adjustment instruction to a prompt word engineer (such as prompt word engineer 330 in FIG3 ), indicating that a certain prompt word input (i.e., the target prompt word input) needs to be adjusted. In some embodiments, the application creation platform 110 can also present user feedback information to the prompt word engineer to help the prompt word engineer understand how to adjust the target prompt word input. The target prompt word input adjusted by the prompt word engineer can be stored in the prompt word library.

[0072] In some embodiments, when a mapping relationship between user input and prompt word input is used, in addition to or as an alternative to updating the prompt word input, the user input to which one or more prompt word inputs are mapped may also be updated similarly based on user feedback. For example, for a certain prompt word input, one or more user inputs to which the prompt word input is mapped may be added, deleted, or modified.

[0073] By updating the prompt word input in the prompt word library based on user feedback during operation, and / or the mapping relationship between user input and prompt word input, user expectations in specific fields and scenarios and the user's expression method when inputting can be synchronized in real time, so that model 125 always maintains an accurate understanding of user input.

[0074] According to embodiments of the present disclosure, received user input can be converted into prompt word input that is easier for the model to understand and then provided to the model, allowing the model to understand the task indicated by the user's needs. Since user input is converted into prompt word input that is richer in information and easier for the model to understand, this can make model processing more efficient and model output more accurate, thereby improving the efficiency and accuracy of task processing on the application creation platform.

[0075] 5 shows a schematic structural block diagram of an apparatus 500 for information processing according to some embodiments of the present disclosure. The apparatus 500 may be implemented in or included in the application creation platform 110. Each module / component in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0076] As shown in the figure, the device 500 includes an input receiving module 510, which is configured to receive a first user input, wherein the first user input includes first descriptive information related to a task on the application creation platform. The device 500 also includes a prompt word determination module 520, which is configured to determine a target prompt word input that matches the first user input, wherein the target prompt word input includes second descriptive information related to the task, wherein the second descriptive information includes at least one of the following: descriptive information obtained by adjusting at least a portion of the first descriptive information, or an expanded description of at least a portion of the first descriptive information. The device 500 also includes a prompt word providing module 530, which is configured to provide the target prompt word input to the model to obtain an indication of the execution operation of the task output by the model.

[0077] In some embodiments, the prompt word determination module 520 includes: a sequence determination module, configured to determine, in the mapping relationship between user input and prompt word input, that the first user input matches the target user input in the mapping relationship; and a target prompt word input determination module, configured to determine, from the mapping relationship, the prompt word input to which the target user input is mapped as the target prompt word input.

[0078] In some embodiments, the mapping relationship includes a mapping relationship between a natural language sequence and a prompt word input.

[0079] In some embodiments, in a mapping relationship, the target prompt word input is mapped to multiple candidate user inputs, and the sequence determination module includes: a matching degree determination module, configured to determine the matching degree between the first user input and each of the multiple candidate user inputs; and a sequence selection module, configured to select a target user input that matches the first user input from the multiple candidate user inputs based on the determined matching degree.

[0080] In some embodiments, the task includes a creation task for a target application, or an adjustment task for at least a portion of a target application.

[0081] In some embodiments, the mapping relationship is specific to a target domain associated with the application creation platform.

[0082] In some embodiments, the apparatus 500 further includes: a reply presentation module configured to present a reply to the first user input, the reply including an indication of an execution operation of the task, or including an indication of a task execution result of the task.

[0083] In some embodiments, the apparatus 500 further includes: a feedback information obtaining module configured to obtain first user feedback information for the task; and an adjustment determination module configured to determine an adjustment to the target prompt word input based at least on the first user feedback information.

[0084] In some embodiments, the feedback information obtaining module includes: a feedback information determining module configured to determine first user feedback information based on a user operation behavior detected after the instruction or completion of the execution operation of the task.

[0085] In some embodiments, the adjustment determination module includes: a determination module configured to determine that the target prompt word input is to be adjusted if the first user feedback information indicates that the execution of the task does not meet the expected goal.

[0086] In some embodiments, the device 500 also includes: a second user feedback information acquisition module, configured to obtain second user feedback information, the second user feedback information is feedback in response to the second user input, and the second user input includes description information of a task of the same type as the task; a prompt word input generation module, configured to generate a target prompt word input based at least on the second user feedback information.

[0087] The modules included in the device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the modules in the device 500 can be implemented at least in part 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 the like.

[0088] FIG6 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 600 shown in FIG6 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 600 shown in FIG6 can be used to run the application creation platform 110 of FIG1 .

[0089] As shown in FIG6 , electronic device 600 is 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 real or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 600.

[0090] The electronic device 600 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 600.

[0091] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG6 , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 620 may include a computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0092] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0093] The input device 650 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 660 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 600, or with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0094] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0095] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0096] 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 device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0097] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0098] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented using a dedicated hardware-based system that performs the function or action of the specification, or can be implemented using a combination of dedicated hardware and computer instructions.

[0099] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not 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 selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: receiving a first user input, the first user input comprising first description information related to a task on an application creation platform; Determining a target prompt word input matching the first user input, the target prompt word input including second description information related to the task, the second description information including at least one of the following: description information obtained by adjusting at least a portion of the first description information, or an extended description of at least a portion of the first description information; as well as The target cue word input is provided to a model to obtain an indication of an execution operation of the task output by the model.

2. The method according to claim 1, wherein determining the target prompt word input comprises: In a mapping relationship between user input and prompt word input, determining that the first user input matches a target user input in the mapping relationship; as well as The prompt word input to which the target user input is mapped is determined from the mapping relationship to serve as the target prompt word input. 3 . The method according to claim 2 , wherein the mapping relationship comprises a mapping relationship between a natural language sequence and a prompt word input.

4. The method according to claim 2, wherein in the mapping relationship the target prompt word input is mapped to a plurality of candidate user inputs, and wherein determining the target user input comprises: Determining a degree of match between the first user input and each of the plurality of candidate user inputs; as well as Based on the determined degree of matching, the target user input matching the first user input is selected from the plurality of candidate user inputs. 5 . The method according to claim 1 , wherein the task comprises a creation task for a target application, or an adjustment task for at least a part of the target application. The method according to claim 2 , wherein the mapping relationship is specific to a target domain related to the application creation platform.

7. The method according to claim 1, further comprising: A reply to the first user input is presented, the reply including the indication of the execution operation of the task, or including an indication of the task execution result of the task.

8. The method according to claim 1, further comprising: Obtaining first user feedback information for the task; as well as An adjustment to the target prompt word input is determined based at least on the first user feedback information.

9. The method according to claim 8, wherein obtaining the first user feedback information comprises: The first user feedback information is determined based on a user operation behavior detected after the instruction or completion of the execution operation of the task.

10. The method of claim 8, wherein determining an adjustment to the target prompt word input comprises: If the first user feedback information indicates that the execution of the task does not meet the expected goal, it is determined that the target prompt word input needs to be adjusted.

11. The method according to claim 1, further comprising: Obtaining second user feedback information, where the second user feedback information is feedback on a reply to a second user input, and the second user input includes description information of a task of the same type as the task; The target prompt word input is generated based at least on the second user feedback information.

12. An apparatus for information processing, comprising: An input receiving module, configured to receive a first user input, wherein the first user input includes first description information related to a task on the application creation platform; a prompt word determination module configured to determine a target prompt word input matching the first user input, wherein the target prompt word input includes second description information related to the task, wherein the second description information includes at least one of the following: description information obtained by adjusting at least a portion of the first description information, or adjusting at least a portion of the first description information. an extended description of at least one part; as well as The prompt word providing module is configured to provide the target prompt word input to the model to obtain the instruction of the execution operation of the task output by the model.

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

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

Citation Information

Patent Citations

  • Information processing method and device, equipment and storage medium

    CN119003039A

  • Assistant software development method and system based on artificial intelligence and storage medium

    CN108628607A

  • Voice instruction recommendation method and device and electronic equipment

    CN113987130A

  • Application page development method, device and system, computing equipment and storage medium

    CN115857920A

Cited By

  • Report generation method and device, equipment and storage medium

    CN119808742A

  • Method and device for constructing business model, equipment and storage medium

    CN120560620A

  • Data display method and device based on large language model, medium and equipment

    CN120688455A

  • Image processing method and apparatus, device, medium, and program product

    WO2026157713A1