Methods, apparatus, devices, and storage media for information processing

Abstract

Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for information processing. The method includes receiving a first user input, which includes first descriptive information relating to a task on an application creation platform; determining a target prompt word input that matches the first user input, wherein the target prompt word input includes second descriptive information relating to the task, the second descriptive information including at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information and an extended description of at least a portion of the first descriptive information; and providing the target prompt word input to a model to obtain an indication of the task execution operation output by the model. As a result, by converting user input into a more informative and model-readable prompt word input, the model output becomes more accurate, the efficiency and precision of task processing improve, and the user experience is enhanced.

Description

Technical Field

[0001] (Cross - reference to related applications) This application claims the priority of a Chinese patent application for invention with an application number of 202310576150.6 and a title of "Method, Apparatus, Device, and Storage Medium for Information Processing", which was filed on May 19, 2023. The entire content of the said application is incorporated herein by reference.

[0002] (Field of the Invention) Exemplary embodiments of the present disclosure generally relate to the field of computers, and particularly to a method, an apparatus, a device, and a computer - readable storage medium for application processing.

Background Art

[0003] With the rapid development of Internet technology, various applications have already become important tools in people's daily lives. Different applications have different functions, and users can realize specific tasks or services through specific applications with specific functions. Application creation platforms, especially low - code platforms, support the efficient development of applications by users and can realize operations such as application creation and application function adjustment.

Summary of the Invention

[0004] A first aspect of this disclosure provides a method for information processing. This method includes receiving a first user input containing first descriptive information relating 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 containing second descriptive information relating to the task, the second descriptive information containing at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information, or an extended description of at least a portion of the first descriptive information, and providing the target prompt word input to a model to obtain an indication of a task execution operation output by the model.

[0005] A second aspect of the present disclosure provides an apparatus for information processing. The apparatus includes an input receiving module configured to receive a first user input including first descriptive information relating to a task on an application creation platform; a prompt word determination module configured to determine a target prompt word input that matches the first user input, wherein the target prompt word input includes second descriptive information relating to a task, the second descriptive information including at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information, or an extended 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 a task execution operation output by the model.

[0006] A third aspect of this disclosure provides an electronic device, which 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 cause the electronic device to perform the method of the first aspect when executed by the at least one processing unit.

[0007] A fourth aspect of this disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method of the first aspect is realized.

[0008] It should be understood that the content described in this section is not intended to limit any essential or important features of the embodiments of this disclosure, nor to limit the scope of this disclosure. Other features of this disclosure will be readily apparent from the following description. [Brief explanation of the drawing]

[0009] The above and other features, advantages and aspects of each embodiment of this disclosure will become more apparent when viewed in conjunction with the drawings and the following detailed description. In the drawings, the same or similar drawing marks represent the same or similar elements.

[0010] [Figure 1] A schematic diagram of an exemplary environment capable of realizing the embodiments of this disclosure is shown. [Figure 2] A flowchart of the information processing process according to some embodiments of this disclosure is shown. [Figure 3] The following are schematic diagrams illustrating exemplary information processing flows according to several embodiments of this disclosure. [Figure 4] The following are schematic diagrams illustrating exemplary mapping relationships between user input and prompt word input according to several embodiments of this disclosure. [Figure 5] The following are exemplary structural block diagrams of devices for information processing according to several embodiments of this disclosure. [Figure 6] A block diagram of an electronic device capable of carrying out one or more embodiments of this disclosure is shown. [Modes for carrying out the invention]

[0011] Embodiments of this disclosure will be described in more detail below with reference to the accompanying drawings. While specific embodiments of this disclosure are illustrated in the accompanying drawings, this disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments should be understood as being provided for the purpose of providing a more thorough and complete understanding of this disclosure. 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.

[0012] In describing embodiments of this disclosure, the terms “including” and “embodiments” are understood to have an open-ended inclusion, i.e., “including, but not limited to.” The term “based on” is understood to mean “based at least in part.” The terms “one embodiment” or “the embodiment” should be understood to mean “at least one embodiment.” The terms “several embodiments” should be understood to mean “at least several embodiments.” Other explicit and implicit definitions may be included below.

[0013] In this disclosure, unless expressly stated otherwise, performing a step “in response to A” does not mean that the step is performed immediately after “A,” and may include one or more intermediate steps.

[0014] Data related to this technical solution (including, but not limited to, the data itself, its acquisition, use, storage, and deletion) shall comply with the requirements of applicable laws and regulations.

[0015] Before using any of the technical solutions disclosed in each embodiment of this disclosure, the relevant user should be informed of the type of information relating to this disclosure, the scope of use, the usage scenarios, etc., by appropriate means in accordance with applicable laws and regulations, and should obtain permission from the relevant user, in which case the relevant user may include any type of rights holder, such as individuals, companies, and organizations.

[0016] For example, in response to receiving a spontaneous request from a user, a prompt message is sent to the relevant user, explicitly indicating to the relevant user that the operation requested to be performed by the user requires access to and use of the relevant user's information, and the relevant user is able to independently choose, based on the prompt message, whether to provide information to the electronic device, application, server, or software or hardware such as a storage medium that performs the operation of the technical solution of the disclosure.

[0017] In an optional but non-limiting embodiment, in response to receiving a voluntary request from the relevant user, prompt information is sent to the relevant user, for example, in the form of a pop-up window in which the prompt information is presented in text form. Furthermore, the pop-up window may include option controls for the user to select whether to "agree" or "disagree" to providing information to the electronic device.

[0018] The above notice and user authorization process are general in nature and do not limit the ways in which this disclosure may be implemented. Please understand that other methods that comply with applicable laws and regulations may be applied in how this disclosure may be implemented.

[0019] Application development platforms, especially low-code platforms, have a very poor ability to understand user input in specific scenarios due to their pre-configured content generation capabilities. For example, an application development platform or the model it uses can understand user input such as "move the current decision button on this page to the bottom of the page and select this button by default," or "when the user clicks this button, execute user input flow A," because these inputs clearly indicate specific tasks. However, an application development platform or the model it uses cannot understand user input that is strongly related to a specific field or scenario, such as "adjust the page recommended by this e-commerce company to better suit the e-commerce company's usage habits" or "change this page to a page style that makes ultrasound results easier to view." As a result, the application development platform cannot determine and execute tasks indicated by user input based on its own understanding capabilities or understanding capabilities learned from models.

[0020] Embodiments of this disclosure provide a proposed improvement to information processing in an application creation platform. According to this proposal, the application creation platform receives a first user input containing first descriptive information related to a task. A target prompt word input that matches the first user input is determined. The target prompt word input is provided to a model so that the model can obtain an indication regarding the execution operation of the task. In this way, the received user input is transformed into a prompt word input that is more informative and easier for the model to understand, and provided to the model so that the model can understand the task indicated by the user's needs. This helps the model understand the user input, makes model processing more efficient, makes model output more accurate, meets user expectations, and improves the user experience.

[0021] Figure 1 shows a schematic diagram of an exemplary environment 100 that can be realized herein by embodiments of the present disclosure. As shown in Figure 1, the application creation platform 110 can provide an application development and deployment environment. In some embodiments, the application creation platform 110 may be a low-code platform that provides a collection of application development tools. The application creation platform 110 can support visual development for applications, thereby allowing developers to skip the manual coding process and accelerate the application development cycle and cost. The application creation platform 110 can support any suitable platform for user-developed applications, which may include, for example, a platform based on an application platform, i.e., aPaaS (a Platform as a Service).

[0022] The application creation platform 110 can run on a suitable electronic device. The electronic device here may be any type of device with computing capabilities, including terminal devices or service-side devices. The terminal device may be any type of mobile terminal, fixed terminal, or portable terminal, such as a mobile phone, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, media computer, multimedia tablet, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA), audio / video player, digital camera / video camera, positioning device, television receiver, radio broadcast receiver, e-book device, game device, or any combination of the above, including accessories and peripheral devices of these devices or any combination thereof. The service-side device may include, for example, a computing system / server, such as a mainframe, edge computing node, computing device in a cloud environment, etc. In some embodiments, the application creation platform 110 can be realized based on cloud services.

[0023] The application creation platform 110 may be deployed locally on the user's terminal device and / or supported by a remote server. In some embodiments, a client of the application creation platform 110 may run on the terminal device, and this client can support the interaction between the user and the application creation platform 110. When the application creation platform 110 is running locally on the user's terminal device, the user can directly use the client to interact with the local application creation platform 110. When the application creation platform 110 is running on the service-side device, the service-side device can realize the supply of services to the client running on the terminal device based on the communication connection with the terminal device.

[0024] The application creation platform 110 may be equipped with a digital assistant 120. The user 140 can interact with the digital assistant 120 via the application creation platform 110. The digital assistant 120 is used for interaction with the user 140. The client of the application creation platform 110 can present an interaction window, such as a session window, between the user 140 and the digital assistant 120 through a client interface. The digital assistant 120, as a smart assistant, has smart interaction and information processing capabilities. The user 140 can input a session message within the session window, and the digital assistant 120 provides a reply message in response to the user's session message.

[0025] In the application creation platform 110, the digital assistant 120 can be called or woken up in an appropriate manner (e.g., shortcut key, button or voice) to present a session window with the user. In some embodiments, the digital assistant 120 may be included in the contact list in the current user's application creation platform 110 as a contact of the user, and may also be included in the information flow of the chat component. By selecting the digital assistant 120, a session window with the digital assistant 120 can be opened. In some embodiments, a session window with the digital assistant 120 can also be presented by starting the digital assistant 120 with one or more components supported by the application creation platform 110.

[0026] The application creation platform 110 can acquire interaction information (including session messages from the user and response messages from the digital assistant 120) within a session window between the user 140 and the digital assistant 120. In some embodiments, the application creation platform 110 can use model 125 to understand the user's session messages and determine the next steps to be performed. The application creation platform 110 can interact with model 125 to provide model inputs and obtain corresponding model outputs from model 125. Model 125 can run on a local or remote server of the application creation platform 110. In some embodiments, model 125 may be an instrument learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, model 125 may be based on a language model (LM). The language model can acquire question-and-answer capabilities by learning from a large vocabulary. Model 125 may be based on other suitable models.

[0027] The database 130 is used to store data or information necessary for application processing operations performed by the application creation platform 110. For example, the database 130 can store code and descriptive information corresponding to each functional block that makes up the application. The application creation platform 110 can further perform operations such as calling, adding, deleting, and updating functional blocks in the database 130. The database 130 can also store operations that can be performed on different functional blocks. For example, in a scenario where application 150 is created, the application creation platform 110 can construct application 150 by calling the corresponding functional blocks from the database 130.

[0028] It should be understood that the structure and function of Environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0029] Hereinafter, several exemplary embodiments of this disclosure will be described in detail with reference to the drawings.

[0030] Figure 2 shows a flowchart of an information processing step 200 according to some embodiments of the present disclosure. The step 200 may be implemented on an application creation platform 110. For ease of consideration, the step 200 will be described with reference to the environment 100 in Figure 1.

[0031] In block 210, the application creation platform 110 receives a first user input which includes first descriptive information related to a task on the application creation platform 110.

[0032] In some embodiments, a client corresponding to the application creation platform 110 may present a session window between the user 140 and the digital assistant 120 in the client interface. The session window may be of any shape, size, color, and position. The session window may include interface elements for information interaction, such as input blocks, message lists, message bubbles, etc. Session messages within the session window may contain content in one or more formats, such as text, images, audio, video, etc. The digital assistant 120 is used to interact with the user 140 during the application processing of the application creation platform 110. The application creation platform 110 can receive, for example, a first user input via the session window.

[0033] The first user input received by the application creation platform 110 may be a message entered by user 140 in an input block in the session window or by other means (e.g., voice input). In some embodiments, the user input may include multimodal inputs, such as text input (e.g., natural language input), voice input, image input, video input, etc.

[0034] The application creation platform 110 can determine the specific task indicated by the task through 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 particular application or part of an application. In some embodiments, the task may include a creation task for the target application (e.g., creating a new application) or an adjustment task for at least part of the target application (e.g., an adjustment task for pages, data tables, or operation controls of the target application).

[0035] In some embodiments, the application creation platform 110 can understand user input through the model 125 and determine a response to the user input. In some embodiments, if a user input is directly input to the model 124, it may be difficult for the model 125 to understand it accurately, especially if the user input relates to a specific scene or specific field. For example, if the first user input received by the application creation platform 110 is "to make the pages recommended by this e-commerce vendor more compatible with the e-commerce vendor's usage habits," the model 125 may not be able to accurately determine how user 140 should specifically adjust the interface. In this case, if the descriptive information in the user input is directly input to the model 125, the resulting model output may be unsatisfactory, and the final task execution may not meet the user's needs. In embodiments of this disclosure, instead of directly providing the information in the user input directly to the model 125 for processing, the application creation platform 110 converts the user input into a more informative prompt word input that the model can better understand, provides it to the model 125 for processing, and determines the task execution operation from the output of the model 125.

[0036] In block 220, the application creation platform 110 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 descriptive information obtained after adjusting at least a portion of the first descriptive information, or an extended description of at least a portion of the first descriptive information.

[0037] In embodiments of this disclosure, first descriptive information of user input can be adjusted and / or expanded to obtain second descriptive information, thereby facilitating the model's understanding of the prompt word input containing the second descriptive information, allowing the model to provide accurate and desired model outputs. In some embodiments, adjusting some of the descriptions in the first descriptive information of user input can make the user's intent more clearly expressed. In some embodiments, some or all of the first descriptive information can be expanded. The expanded description may be an interpretation or support for the first descriptive information or the task it indicates, for example, an interpretation or definition of some words in the first descriptive information, a specific example given, and / or supplemental contextual information given. Exemplaryly, if the user input is "to make the pages recommended by this e-commerce company more aligned with the e-commerce company's usage habits," the second descriptive information of the target prompt word input may include a sample page that satisfies the e-commerce company's usage habits, and / or a detailed definition of the sample page layout that satisfies the e-commerce company's usage habits. The extended explanation in the second explanatory information allows the subsequent model 125 to better understand specific tasks in particular scenes and domains, thereby better determining the execution operations for those tasks and supporting the application creation platform 110 in executing the corresponding tasks.

[0038] 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 exemplary information processing flow 300 according to some embodiments of the present disclosure. As shown in Figure 3, the application creation platform 110 can receive user input from user 140, which is "to make the pages recommended by this e-commerce company more aligned with the e-commerce company's usage habits." The application creation platform 110 can determine from the prompt word library 320 the prompt word input 310-1 mapped by this user input. The prompt word library 320 here may be included in the database 130 in Figure 1, or it may be independent of the database 130. The prompt word library 320 contains a plurality of prompt word inputs 310 (e.g., prompt word inputs 310-1, 310-2, ..., 310-N, where N is a positive integer greater than 1).

[0039] The application creation platform 110 can determine a 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 a target prompt word input that matches the first user input from one or more prompt word inputs. The selected target prompt word input may be, for example, the prompt word input with the highest degree of match (and above a predetermined threshold) with the first user input. Here, the degree of match indicates the lexical relevance between the first user input and the prompt word input. The application creation platform 110 uses various methods to determine the lexical relevance between the user input and the prompt word input. A higher lexical relevance means that the descriptions of the first user input and the prompt word input are closer, and thus they are considered to be a match. For example, the degree of match between a prompt word input and the first user input can be determined by converting each prompt word input and the first user input into lexical vectors representing their respective vocabulary, and then calculating the distance between the lexical vector of each prompt word input and the lexical vector of the first user input. The target prompt word input may be a prompt word input that has a relatively high degree of matching with the first user input (for example, the one with the highest degree of matching and which is above a predetermined threshold).

[0040] In some embodiments, a mapping relationship can be established between user input and prompt word input, and this mapping relationship can be stored in a prompt word library accessible by the application creation platform 110. The mapping relationship may 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 prompt word input may be a one-to-one mapping relationship or a multiple-to-one mapping relationship. In the mapping relationship, the candidate user input may be in a format that the user may input, related to the prompt word input. The candidate user input included in the mapping relationship may be in a multimodal format, such as text input (e.g., natural language input), voice input, image input, video input, etc. In some embodiments, the mapping relationship may also be a mapping relationship between a natural language sequence and a prompt word input, i.e., a prompt word can be mapped to one or more natural language sequences.

[0041] In the example shown in Figure 3, the prompt word library 320 may include mapping relationships between natural language sequences and prompt word inputs. As shown in Figure 3, 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 each be mapped to one or more natural language sequences.

[0042] In some embodiments, considering that user descriptions for different identical tasks may differ, the same prompt word input in a mapping relationship may map to multiple candidate user inputs (e.g., multiple natural language sequences), i.e., there is a multiple-to-one relationship between user input and prompt word input. For example, multiple natural language sequences such as “e-commerce recommended page layout,” “e-commerce recommended page style,” and “recommended page for e-commerce scene” may correspond to the same prompt word input, which may include specific descriptive information that adjusts the page to the e-commerce recommended page layout. It should be understood that any or all prompt word inputs in a mapping relationship may map to a single candidate user input, and the scope of embodiments of this disclosure is not limited thereto.

[0043] Figure 4 shows a schematic diagram of exemplary mapping relationships 400 between user inputs and prompt word inputs according to some embodiments of the present disclosure. As shown in Figure 4, the mapping relationships 400 may include a plurality of candidate user inputs and a plurality of prompt word inputs, each prompt word input 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.

[0044] 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 this 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 mapped by the target user input 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. Here, the degree of match indicates the degree of relevance between the first user input and the candidate user input.

[0045] In embodiments where user input is in natural language form, the degree of match can indicate the lexical relevance between the first user input and the candidate user input. The application creation platform 110 determines the lexical relevance between two natural language sequences using various methods. A higher lexical relevance means that the descriptions of the first user input and the natural language sequence are closer, and thus they are considered to be a match. For example, the degree of match between a natural language sequence and the first user input can be determined by converting each natural language sequence and the first user input in the mapping relationship into lexical vectors representing their vocabulary, and then calculating the distance between the lexical vector of each natural language sequence and the lexical vector of the first user input. The target user input may be a natural language sequence with a relatively high degree of match with the first user input (for example, the highest degree of match and above a predetermined threshold).

[0046] In some embodiments, if the first user input and / or candidate user input in the mapping relationship is of another modality, such as an image or video, the corresponding target prompt word input can be selected by determining the degree of match between the first user input and the candidate user input in the mapping relationship based on a data relevance algorithm in the corresponding modality.

[0047] In the example in Figure 3, the user input "Adjust the pages recommended by this e-commerce vendor to match the e-commerce vendor's usage habits" can match the natural language sequence "Page layout recommended by the e-commerce vendor" in the mapping relationship, and prompt word input 310-1 is mapped to this natural language sequence. Therefore, the application creation platform 110 can determine that prompt word input 310-1 is a prompt word input that matches the user input.

[0048] As mentioned above, a prompt word input in a mapping relationship can be mapped to multiple candidate user inputs (e.g., multiple natural language sequences). In this case, the application creation platform 110 can determine the degree of match between the first user input and each of the multiple candidate user inputs in the mapping relationship for this prompt word input. Based on the determined degree of match, the application creation platform 110 can select a target user input from the multiple candidate user inputs that matches the first user input. Exemplaryly, the application creation platform 110 can determine the candidate user input with the highest degree of match with the first user input as the target user input that matches the first user input. Furthermore, in response to determining that the first user input matches the target user input in the mapping relationship, the application creation platform 110 can 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 mapped by user input 21 from among the multiple prompt word inputs included in the mapping relationship 400, and set prompt word input 2 as the target prompt word input.

[0049] In some embodiments, the mapping relationships corresponding to different fields (or scenes) may differ. For example, the mapping relationships corresponding to the medical field and the gaming field may be different. In particular, different prompt word inputs can be configured in different mapping relationships. To ensure the accuracy of the ultimately determined prompt word inputs, the mapping relationships here may be specific to the target field related to the application creation platform. That is, the prompt word inputs included in the mapping relationship are prompt word inputs for the target field, which helps to improve the determination of accurate model generation by the subsequent model 125.

[0050] In some embodiments, the configured prompt word input, or the mapping relationship between user input and prompt word input, can be updated during use. The generation and updating of prompt word input or mapping relationship will be described in more detail below.

[0051] Referring to Figure 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 and obtains an indication of the task execution operation output by the model 125.

[0052] Because the target prompt word input includes more supplements and extensions to the task the user wishes to perform, Model 125 can determine indications regarding the task execution operation by more accurately understanding the user's expectations from the target prompt word input. The indications regarding the task execution operation can be provided by Model 125 to the application creation platform 110 as a model output. For example, in the example in Figure 3, prompt word input 310-1 is provided to Model 125 as a target prompt word input mapped by user input, thereby facilitating Model 125 to output indications regarding the task execution operation.

[0053] After receiving an indication of task execution operations provided by Model 125, in some embodiments, the application creation platform 110 can present an indication including task execution operations as a response to the first user input. For example, in the example in Figure 3, when a user enters the session message "Adjust the pages recommended by this e-commerce vendor to match the e-commerce vendor's usage habits" in the session window with the digital assistant, the application creation platform 110 can present a response to this session message based on the output of Model 125. In some embodiments, the application creation platform 110 can determine a specific execution operation for the task indicated by the first user input, based on the task execution operation indication provided by Model 125. The operation performed by the application creation platform 110 may be an operation provided by Model 125, or an operation adjusted based on the provided execution operation. Of course, the application creation platform 110 can directly perform the task execution operations indicated by Model 125.

[0054] In some embodiments, the application creation platform 110 may, after obtaining an indication about a task from the model 125, present a response to a first user input via a session window between the user 140 and the digital assistant 120. This response may include at least an indication of the task's execution operation (e.g., describing how to specifically perform the task) and / or an indication of the task's execution result. In this way, the user can know in a timely manner how the task will be performed, what the result will be, and so on.

[0055] The following describes how prompt word inputs are generated and updated, and / or the mapping relationships between user inputs and prompt word inputs. In some embodiments, prompt word inputs in a prompt word library may be obtained by prompt word engineering, which involves embedding prompt words related to user inputs within the relevant field into the input template of Model 125. Here, the prompt words may be specific words predefined within the relevant field. The prompt word inputs may be in an input format that conforms to Model 125. In some embodiments, the prompt word inputs, and / or the mapping relationships between user inputs and prompt word inputs, may be predetermined by the relevant field staff and provided directly to the application creation platform 110. For example, in Figure 3, they may be provided by a prompt word engineer 330 (also called a prompt word developer). The prompt word engineer 330 may determine each prompt word input, and / or candidate user inputs mapped by the prompt word inputs, for example, through offline communication or indications within other fields.

[0056] In some embodiments, the application creation platform 110 can generate new prompt word inputs and / or candidate user inputs mapped by prompt word inputs by collecting user feedback information for tasks during the process of executing various tasks indicated by the user.

[0057] Let us take the generation of a "target prompt word input" mapped by the first user input described above as an example. The application creation platform 110 can obtain a second user input that contains descriptive information for a task of the same type as the first user input task. The application creation platform 110 can obtain user feedback information (referred to herein, for distinction purposes, as "second user feedback information"). The second user feedback information is feedback on the response to the second user input, and the second user input contains descriptive information for a task of the same type as the task. In other words, other users may want to perform a similar task on the application creation platform 110, and the application creation platform 110 can collect user feedback information after performing this task using Model 125.

[0058] In some embodiments, the application creation platform 110 can determine second user feedback information based on user actions detected after the indication or completion of the task execution operation indicated by the second user input. The user actions here may be, for example, feedback entered by user 140 within the session window, for example, the user may indicate that they approve of and like the task execution operation or the task execution result. In some embodiments, if the task is completed based on the indicated operation, the application creation platform 110 can respond by detecting a user cancel or delete action on one or more of the task execution operations and determine that the user is dissatisfied with the task execution operation provided by model 125.

[0059] The application creation platform 110 can generate a target prompt word input based on at least a second user feedback information. In some embodiments, if the second user feedback information indicates that the execution of a task does not meet a predetermined objective, the application creation platform 110 can determine that there is a need to generate a target prompt word input. If, in some cases, a prompt word input matching the second user input is not found in advance, the application creation platform 110 generates an input for model 125 based on the descriptive information in the second user input, and model 125 may not accurately understand the task that the user is to perform, thereby failing to satisfy the user with the task execution. In embodiments of this disclosure, new prompt word inputs can be created by collecting user feedback, and / or new prompt word inputs and user inputs can be added in a mapping relationship. Thus, new prompt word inputs may be used to improve the efficiency and user satisfaction of subsequent similar tasks.

[0060] In some embodiments, the prompt word engineer (e.g., prompt word engineer 330 in Figure 3) can provide a target prompt word input. For example, a second user input and / or second user feedback information can be presented to the prompt word engineer to indicate that it should generate a new prompt word input.

[0061] In some embodiments, when it is necessary to use a mapping relationship between user input and prompt word input, the application creation platform 110 can generate a target prompt word input that matches a second user input, and then generate at least one candidate user input mapped by the target prompt word input in the mapping relationship. In some embodiments, the application creation platform 110 can take multiple different second user inputs and generate a target prompt word input that matches multiple second user inputs. Based on the multiple second user inputs, the application creation platform 110 can determine multiple candidate user inputs mapped by this target prompt word input.

[0062] In some embodiments, one or more prompt word inputs and / or mapped candidate user inputs (in examples using mapping relationships) can be continuously added, deleted, or updated while the application creation platform 110 is running.

[0063] Taking the first user input described above as an example, the first user input indicates a task on the application creation platform 110. As previously stated, the first user input is converted into a target prompt word input and provided to the model 125, from which an indication for the task execution operation is obtained. Then, in some embodiments, the application creation platform 110 can obtain first user feedback information for the task. In some embodiments, the application creation platform 110 can receive a session message from the session window regarding a response from the user 140 and use this as first user feedback information for the task. In some embodiments, the application creation platform 110 can further determine the first user feedback information based on the indication for the task execution operation or a user action detected after completion. The user action here may be, for example, feedback entered by the user 140 in the session window, for example, the user may indicate that they approve of and like the task execution operation or the task execution result. In some embodiments, if a task is completed based on an indicated operation, the application creation platform 110 may, in response to detecting a user's cancel or delete action on one or more execution operations of the task, determine that the user is dissatisfied with the task execution operations provided by Model 125.

[0064] The application creation platform 110 can further determine adjustments to the target prompt word input based on at least first user feedback information. In some embodiments, the application creation platform 110 may determine that the target prompt word input should be adjusted if the first user feedback information indicates that the task execution does not meet a predetermined objective. In this case, if the first user feedback information can indicate an adjustment method, the application creation platform 110 may 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 may provide clear guidance to the user to help them determine the desired adjustment method.

[0065] In some embodiments, when it is determined that a target prompt word input needs to be adjusted, the application creation platform 110 can present a prompt word adjustment indication to the prompt word engineer (prompt word engineer 330 in Figure 3) to show 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 further help the prompt word engineer know how to adjust the target prompt word input by presenting user feedback information to the prompt word engineer. The target prompt word input after adjustment by the prompt word engineer can be stored in the prompt word library.

[0066] In some embodiments, when using a mapping relationship between user input and prompt word input, in addition to updating the prompt word input, or as an alternative, user inputs mapped by one or more prompt word inputs can also be updated based on user feedback. For example, for a given prompt word input, one or more user inputs mapped by that prompt word input can be added, deleted, or modified.

[0067] By updating the prompt word inputs in the prompt word library and / or the mapping relationships between user input and prompt word inputs based on user feedback during operation, Model 125 can maintain an accurate understanding of user input at all times by synchronizing in real time the user's expectations and the way user input is expressed in specific fields and scenes.

[0068] According to embodiments of this disclosure, received user input is provided to the model by converting it into more easily understandable prompt word input, allowing the model to understand the task indicated by the user's needs. Because user input is converted into more informative and more easily understandable prompt word input, the model processing becomes more efficient and the model output becomes more accurate, thereby improving the task processing efficiency and accuracy of the application creation platform.

[0069] Figure 5 shows an exemplary structural block diagram of an information processing apparatus 500 according to several embodiments of the present disclosure. The apparatus 500 may be implemented, for example, as an application creation platform 110, or included as part thereof. Each module / component of the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0070] As shown in the figure, the device 500 includes an input receiving module 510 configured to receive a first user input containing first descriptive information relating to a task on an application creation platform. The device 500 further includes a prompt word determination module 520 configured to determine a target prompt word input that matches the first user input, wherein the target prompt word input contains second descriptive information relating to the task, and the second descriptive information contains at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information, and an extended description for at least a portion of the first descriptive information. The device 500 also includes a prompt word providing module 530 configured to provide the target prompt word input to a model to obtain an indication of the task execution operation output by the model.

[0071] In some embodiments, the prompt word determination module 520 includes a sequence determination module configured to determine that a first user input matches a target user input in a mapping relationship between a user input and a prompt word input, and a target prompt word input determination module configured to determine that a prompt word input mapped from the mapping relationship to a target user input is the target prompt word input.

[0072] In some embodiments, the mapping relationship includes a mapping relationship between a natural language sequence and a prompt word input.

[0073] In some embodiments, a target prompt word input is mapped to a plurality of candidate user inputs in a mapping relationship, and the sequence determination module comprises a degree of match determination module configured to determine the degree of match between a first user input and each of the plurality of candidate user inputs, and a sequence selection module configured to select a target user input that matches the first user input from the plurality of candidate user inputs based on the determined degree of match.

[0074] In some embodiments, the tasks include a creation task for the target application, or a rework task for at least a portion of the target application.

[0075] In some embodiments, the mapping relationship is specific to the target domain related to the application creation platform.

[0076] In some embodiments, the device 500 further comprises a presentation module configured to present a response to a first user input, the response including an indication of an operation to perform a task, or an indication of the result of performing a task.

[0077] In some embodiments, the device 500 further comprises a feedback information acquisition module configured to acquire first user feedback information for a task, and an adjustment determination module configured to determine adjustments to target prompt word input based on at least the first user feedback information.

[0078] In some embodiments, the feedback information acquisition module includes a feedback information determination module configured to determine first user feedback information based on user actions detected after the indication or completion of a task execution operation.

[0079] In some embodiments, the adjustment decision module includes a decision module configured to determine that the target prompt word input is adjusted if first user feedback information indicates that the task execution does not meet a predetermined objective.

[0080] In some embodiments, the device 500 further comprises a second user feedback information acquisition module configured to acquire second user feedback information which is feedback to a response to a second user input, including descriptive information for a task of the same type as the task, and a prompt word input generation module configured to generate a target prompt word input based on at least the second user feedback information.

[0081] The modules included in the device 500 can be implemented using a variety of means, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to, or instead of, machine-executable instructions, some or all of the modules of the device 500 can be implemented at least partially by one or more hardware logic components. Exemplary types of hardware logic components that may be used include, but are not limited to, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), and composite programmable logic devices (CPLDs).

[0082] Figure 6 shows a block diagram of an electronic device 600 that can carry out one or more embodiments of the present disclosure. It should be understood that the electronic device 600 shown in Figure 6 is merely an example and does not limit the functionality and scope of the embodiments described herein. The electronic device 600 shown in Figure 6 can be used to implement the application creation platform 110 shown in Figure 1.

[0083] As shown in Figure 6, the electronic device 600 is in the form of a general-purpose electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage devices 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and can perform various processes based on a program stored in memory 620. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0084] The electronic device 600 generally includes multiple computer storage media. Such media may be any obtainable media accessible to the electronic device 600, and may include, but are not limited to, volatile and non-volatile media, and removable and non-removable media. Memory 620 may be volatile memory (e.g., registers, fast 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 may be removable or non-removable media, and may include machine-readable media, such as flash memory drives, magnetic disks, or any other media, which can be used to store information and / or data and can be accessed within the electronic device 600.

[0085] The electronic device 600 may further include other removable / non-removable, volatile / non-volatile storage media. Not shown in Figure 6, a magnetic disk drive for reading from or writing to removable, non-volatile magnetic disks (e.g., "floppy disks") and a disk drive for reading from or writing to removable, non-volatile disks can be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data medium interfaces. The memory 620 may include a computer program product 625 having one or more program modules, which are configured to perform various methods or operations of various embodiments of the present disclosure.

[0086] 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 by a single computing cluster or multiple computing devices, which can communicate via a communication connection. Therefore, the electronic device 600 can operate in a network environment using logical connections with one or more other servers, network personal computers (PCs), or other network nodes.

[0087] 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, speaker, or printer. The electronic device 600 may further communicate with one or more external devices (not shown), such as storage devices or display devices, via the communication unit 640 as needed, communicate with one or more devices for user-to-electronic device 600 interaction, or communicate with any device (e.g., a network card or modem) for communication between electronic device 600 and one or more other electronic devices. Such communication may be performed via an input / output (I / O) interface (not shown).

[0088] An exemplary embodiment of the present disclosure provides a computer-readable storage medium in which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to realize the method described above. An exemplary embodiment of the present disclosure further provides a computer program product, which is tangibly stored in a non-transient computer-readable medium and includes computer-executable instructions, wherein the computer-executable instructions are executed by a processor to realize the method described above.

[0089] Aspects of this disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus, devices, and computer program products implemented in accordance with this disclosure. It should be understood that every block in a flowchart and / or block diagram, and every combination of blocks in a flowchart and / or block diagram, can be implemented by computer-readable program instructions.

[0090] These computer-readable program instructions are provided to a processing unit of a general-purpose computer, a computer for specific purposes, or other programmable data processing device to create a device that, when executed by the processing unit of the computer or other programmable data processing device, produces a device that performs one or more functions / operations defined in a flowchart and / or block diagram. These computer-readable program instructions may be stored in a computer-readable storage medium, and by operating the computer, programmable data processing device, and / or other device in a specific manner using these instructions, the computer-readable medium on which the instructions are stored includes a product containing instructions in each mode that perform one or more functions / operations defined in a flowchart and / or block diagram.

[0091] By loading computer-readable program instructions into a computer, other programmable data processing device, or other device, and by executing a series of operational steps on the computer, other programmable data processing device, or other device, the instructions executed on the computer, other programmable data processing device, or other device can realize the functions / operations defined in one or more blocks in a flowchart and / or block diagram.

[0092] The flowcharts and block diagrams in the drawings illustrate the implementable system architectures, functions, and operations of the systems, methods, and computer program products of the multiple implementations of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and a module, program segment, or part of an instruction may contain one or more executable instructions for implementing a defined logical function. In some alternative implementations, the functions represented in the blocks may occur in an order different from the order shown in the drawings. For example, two consecutive blocks may actually be executed almost in parallel, or in reverse order depending on the related functions. Note that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented in a dedicated, hardware-based system that performs the function or operation defined, or in a combination of dedicated hardware and computer instructions.

[0093] The above descriptions illustrate various implementations of this disclosure; however, these descriptions are illustrative, not exhaustive, and are not limited to any of the disclosed implementations. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein has been selected to best describe the various embodiments disclosed herein, the principles of the embodiments, the practical application or improvement of the technology in the market, or to be understood by those skilled in the art.

Claims

1. Receiving a first user input containing first descriptive information related to a task in the application creation platform, Determining 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, and the second descriptive information includes at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information, and an extended description of at least a portion of the first descriptive information. This includes providing the target prompt word input to the model and obtaining an indication of the task execution operation output by the model, Information processing methods.

2. Determining the target prompt word input means that In the mapping relationship between user input and prompt word input, it is determined that the first user input matches the target user input in the mapping relationship, This includes determining the prompt word input to which the target user input is mapped from the mapping relationship as the target prompt word input. The method according to claim 1.

3. The aforementioned mapping relationship includes a mapping relationship between a natural language sequence and a prompt word input. The method according to claim 2.

4. In the aforementioned mapping relationship, the target prompt word input is mapped to multiple candidate user inputs. Determining the target user input means that The degree of agreement between the first user input and the plurality of candidate user inputs is determined, This includes selecting the target user input that matches the first user input from the plurality of candidate user inputs based on the determined degree of match, The method according to claim 2.

5. The aforementioned tasks include creation tasks for the target application, or adjustment tasks for at least a portion of the target application. The method according to claim 1.

6. The aforementioned mapping relationship is specific to the target domain related to the application creation platform. The method according to claim 2.

7. Further including providing a response to the first user input, the response including an indication of the execution operation of the task, or an indication of the task execution result of the task. The method according to claim 1.

8. To obtain first user feedback information for the aforementioned task, The further includes determining adjustments to the target prompt word input based on at least the first user feedback information, The method according to claim 1.

9. Obtaining the first user feedback information mentioned above means The process includes determining the first user feedback information based on user actions detected after the indication or completion of the execution operation of the task, The method according to claim 8.

10. Determining adjustments to the input of the target prompt word means that If the first user feedback information indicates that the execution of the task does not meet a predetermined objective, the system includes determining that the target prompt word input is adjusted. The method according to claim 8.

11. To obtain second user feedback information, which is feedback to the response of the second user input, including descriptive information for a task of the same type as the aforementioned task, The further includes generating the target prompt word input based on at least the second user feedback information, The method according to claim 1.

12. A device for information processing, An input receiving module configured to receive a first user input containing first descriptive information related to a task in an application creation platform, A prompt word determination module 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, and the second descriptive information includes at least one of descriptive information obtained after adjusting at least a portion of the first descriptive information, and an extended descriptive for at least a portion of the first descriptive information. An apparatus comprising: a prompt word providing module configured to provide the target prompt word input to a model and to obtain an indication of the execution operation of the task output by the model.

13. At least one processing unit, An electronic device comprising at least one processing unit and at least one memory in which instructions executed by the at least one processing unit are stored, When the instruction is executed by the at least one processing unit, it causes the electronic device to perform the method according to any one of claims 1 to 11. electronic equipment.

14. When executed on a processor, a computer program that implements the method described in any one of claims 1 to 11 is stored. Computer-readable storage medium.

Images