Application creation method and device, equipment and readable storage medium
By configuring the processing parameters of the Q&A function, the problem of insufficient determinism of data Q&A in application creation is solved, and personalized control and optimization of the data Q&A process is realized, and the deterministic needs of enterprise-level applications are met.
Patent Information
- Application Number
- CN202411132191.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-17
- Publication Date
- 2024-11-26
AI Technical Summary
In the process of application creation, the existing technology lacks effective intervention capabilities to control the certainty of data Q&A, especially in enterprise-oriented scenarios, the certainty of data is strong, and the inference results of the generative model exist. Determinism.
By receiving and configuring the processing parameters of the Q&A function, flexibly control the rules for generating results, determine the responses to user questions from the selected data set, and realize personalized configuration and tuning of the data Q&A process.
It improves the certainty and control capabilities of data Q&A, meets the demand for data certainty in enterprise-level applications, and enhances the management and optimization capabilities of Q&A results.
Smart Images

Figure CN119025652A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to application creation methods, devices, apparatuses, and readable storage media. Background Art
[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. Terminal devices present corresponding content and interact with users through the user interface of the application to meet various needs of users. In the scenario of data question and answer, users may ask questions around data in the application. Therefore, how to determine the response to user questions to improve the quality of data question and answer is a problem of concern. Summary of the invention
[0003] In a first aspect of the present disclosure, a method for creating an application is provided. The method includes: receiving a configuration of a question-and-answer function of a target application, the question-and-answer function being configured to determine a response to a user question from at least one selected data set; in response to detecting a parameter configuration request for the question-and-answer function, receiving a configuration of at least one processing parameter for the question-and-answer function, the question-and-answer function being configured to determine a response to the user question from at least one data set using at least the configured at least one processing parameter; and creating a target application based at least on the configuration of the question-and-answer function and the configuration of the at least one processing parameter.
[0004] In a second aspect of the present disclosure, a device for application creation is provided. The device includes: a question-and-answer function configuration receiving module, configured to receive a configuration of a question-and-answer function of a target application, the question-and-answer function being configured to determine a reply to a user's question from at least one selected data set; a processing parameter configuration receiving module, configured to receive a configuration of at least one processing parameter for the question-and-answer function in response to detecting a parameter configuration request for the question-and-answer function, the question-and-answer function being configured to determine a reply to a user's question from at least one data set using at least the configured at least one processing parameter; and a target application creation module, configured to create a target application based at least on the configuration of the question-and-answer function and the configuration of at least one processing parameter.
[0005] 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, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.
[0006] 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.
[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which includes computer executable instructions, and when the instructions are executed by a processor, the method according to the first aspect of the present disclosure is implemented.
[0008] 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
[0009] The above and other features, advantages and aspects of the various 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:
[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0011] Figure 2 A block diagram illustrating a process of application creation according to some embodiments of the present disclosure;
[0012] Figure 3 A schematic diagram showing a target application creation interface according to some embodiments of the present disclosure;
[0013] Figure 4A and Figure 4B A schematic diagram of a question-and-answer parameter configuration page according to some embodiments of the present disclosure is shown;
[0014] FIG. 5A to FIG. 5D A schematic diagram of a term list configuration page according to some embodiments of the present disclosure is shown;
[0015] Figure 6 A schematic structural block diagram showing an apparatus for application creation according to some embodiments of the present disclosure; and
[0016] Figure 7 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION
[0017] The embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments described herein. On the contrary, 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 only for exemplary purposes 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, that is, "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 also be included below.
[0019] Herein, unless explicitly stated, 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 each embodiment of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained 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 software or hardware such as an 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 is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry 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 meet relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0025] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.
[0026] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 involves an application management platform 110, which can support the creation of applications and / or the running of applications. In some embodiments, the portion of the application management platform 110 that supports the creation of applications can also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that supports the running of applications can also be referred to as an application running portion.
[0027] like Figure 1 As shown, the application creation part can provide an application creation and publishing environment for user 105. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, so that developers can skip the manual coding process and speed up the application development cycle and cost. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on Application Platform as a Service (aPaaS). Such a platform can support users to efficiently develop applications and implement operations such as application creation and application function adjustment.
[0028] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part runs on the server device, the server device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application creation part can present a corresponding interface 130 to the user 105 based on the operation of the user 105, so as to output and / or receive information related to application creation to the user 105.
[0029] In some embodiments, the application creation part can be associated with a corresponding database, which stores data or information required for the application creation process supported by the application creation part. For example, the database can store the code and description information corresponding to each functional module used to constitute the application. The application creation part can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application is to be created, the application creation part can call the corresponding functional blocks from the database to build the application.
[0030] In an embodiment of the present disclosure, the user 105 can create a target application 120 as needed on the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more end users 145. The end user 145 can be referred to as the end user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.
[0031] The digital assistant 122 may be configured to have an intelligent conversation. Figure 1In the example shown, the digital assistant 122 can be integrated into the target application 120 as a part of the target application 120 to assist in the task processing within the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users with various task processing requirements in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.
[0032] In some embodiments, the digital assistant 122 can interact with the end user 145 as a contact of the end user 145. For example, the digital assistant 122 can be implemented in an instant messaging (IM) application. The digital assistant 122 can interact with the end user 145 in a single chat session with the end user 145. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session including multiple users.
[0033] For each terminal user 145, the client of the application running part can present an interactive window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The terminal user 145 can enter a conversation message in the conversation window, and the target application 120 can determine the reply message of the digital assistant 122 based on the created configuration information and present it to the user in the interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interactive message with the target application 120 may include a message in a multimodal form, such as a text message (e.g., a natural language text), a voice message, an image message, a video message, and the like.
[0034] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each terminal user 145, and / or can be supported by a server device. For example, the terminal device of the terminal user 145 can run a client with an application running part, and the client can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the terminal user 145 can directly use the terminal device to interact with the local application running part. In the case where the application running part runs on the server device, the server device can realize the service supply to the client running in the terminal device based on the communication connection with the terminal device. The application running part can present the corresponding application interface to the terminal user 145 based on the operation of the terminal user 145, so as to output and / or receive information related to the use of the application to the terminal user 145.
[0035] In some embodiments, the implementation of at least part of the functions of the target application 120 and / or the implementation of at least part of the functions of the digital assistant 122 in the target application 120 can be implemented based on the model. During the creation or operation of the target application 120, one or more models 155 can be called, such as the capabilities of the model 155. In the target application 120, the digital assistant 122 can use the model 155 to understand the user input and provide a reply to the user based on the output of the model 155.
[0036] During the creation process, the application management platform 110 needs to use the model 155 to determine whether the operation result of the target application 120 meets expectations when testing the target application 120. During the operation process, in response to different operation requests of the user of the target application 120, the application operation part may need to use the model 155 to determine the response result to the user.
[0037] Although shown as being independent of the application management platform 110, one or more models 155 may run on the application management platform 110, or other remote servers. In some embodiments, the model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 may also be based on other appropriate models.
[0038] The application management 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 include, for example, 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 management platform 110 can be implemented based on cloud services.
[0039] 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. Figure 1 A single user interacting with the application creation portion and a single user interacting with the application running portion are shown, but in reality multiple users can access the application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.
[0040] Currently, in the process of creating applications, it is necessary to add intervention capabilities during the tuning process. Intervention capabilities include two dimensions: one is the intervention of a single use case that is hard-coded, and the other is the intervention of adding generalized rules, such as the solution of rule intervention based on the model generation process. In the scenario of data question and answer, end users can ask questions around data. By adding rules, the generation results of the model for questions can be affected, thereby assisting management users to intervene and control the effect of data question and answer more. However, there is a lack of solutions for intervention capabilities.
[0041] The question-and-answer function in the target application usually processes user input based on the inference results of a machine learning model (e.g., a language model) to determine the corresponding reply. However, considering that there is uncertainty in the inference results of generative models, especially language models, and in some application scenarios, especially in business-oriented (ToB) scenarios, there is a strong demand for data certainty. Therefore, some means are needed to increase the certainty of the model output results. In an embodiment of the present disclosure, a scheme for configuring the specific processing parameters of the question-and-answer function in an application is proposed.
[0042] In an embodiment of the present disclosure, an improved scheme for application creation is provided. The scheme can flexibly configure the rules for controlling the generation of results. In the scheme, in the creation of the target application, the configuration of the question and answer function of the target application is received. The question and answer function is configured to determine the response to the user's question from at least one selected data set. In response to detecting a parameter configuration request for the question and answer function, a question and answer parameter configuration page is presented. The configuration of at least one processing parameter for the question and answer function is received via the question and answer parameter configuration page. The question and answer function is configured to determine the response to the user's question from at least one data set using at least at least one configured processing parameter. The target application is created based on at least the configuration of the question and answer function and the configuration of at least one processing parameter. In this way, flexible and personalized configuration of the processing parameters of data question and answer can be achieved, so that the respective question and answer processes can be controlled in the creation of different applications and the effect of question and answer can be optimized.
[0043] Some example embodiments of the present disclosure will be described in detail below with reference to the examples of the accompanying drawings. It should be understood that the interfaces shown in the accompanying drawings are merely examples, and various interface designs may actually exist. The various graphical elements in the interface may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect.
[0044] The application creation process described in the embodiments of the present disclosure may be implemented on an application management platform, a terminal device installed with the application management platform, and / or a server corresponding to the application management platform. In the following examples, for the sake of discussion, the description is from the perspective of the application management platform, for example Figure 1 The application management platform 110 shown. The user interface presented by the application management platform 110 can be presented via the terminal device of the user 105, and the application management platform 110 can receive user input via the terminal device of the user 105. In some embodiments of the present disclosure, the user 105 is the creator, manager or maintainer of the target application 120. It should be understood that the user interface presented by the application management platform 110 can also be presented via the terminal device of the terminal user 145, and the application management platform 110 can also receive user input via the terminal device of the terminal user 145. In some embodiments of the present disclosure, the terminal user 145 is the terminal user of the target application 120.
[0045] Figure 2 A block diagram of a process 200 for creating an application according to some embodiments of the present disclosure is shown. The process for creating an application can be implemented on the application management platform 110, and specifically corresponds to the creation part of the application. Figure 1 To describe Figure 2 The process of application creation is shown.
[0046] like Figure 2 As shown, in box 210, the application management platform 110 receives the configuration of the question-and-answer function of the target application 120. The question-and-answer function is configured to determine a response to a user question from at least one selected data set. The question-and-answer function may also be referred to as a data question-and-answer function, a knowledge question-and-answer skill, etc. The configuration of the question-and-answer function is, for example, to enable the data question-and-answer function. For example, the terminal user 145 inputs a question through his terminal device, and the application management platform 110 may enable the question-and-answer function and respond to the question input by the user 145 based on the selected data set. The terminal user 145 may perform interactive actions in the interactive window 142, such as asking questions through text input, voice input, etc. User questions may be instructions issued in natural language received in the interactive window 142.
[0047] Figure 3 A schematic diagram of a target application creation interface 300 according to some embodiments of the present disclosure is shown. The interface 300 may include a configuration area 301 and an interaction area 302. In the configuration area 301, the application management platform 110 may present a plurality of function buttons related to question and answer tuning, such as a configuration control 310. In the configuration area 301, the application management platform 110 may also present a data management list related to a data set. The data set may include, for example, various uploaded documents, online databases, etc. The application management platform 110 may select a data set from which to determine a response to a user's question. In the interaction area 302, the application management platform 110 may provide the user 105 with debugging and preview functions to simulate the input and response preview of the terminal user 145. For example, the application management platform 110 may determine the corresponding response content from the selected data set for the user 105 input "provide a distribution map of the industry to which XX enterprise belongs", and display the distribution of the industry to which XX enterprise belongs in the form of a chart.
[0048] In block 220 , in response to detecting a parameter configuration request for the question-and-answer function, the application management platform 110 receives configuration of processing parameters for the question-and-answer function.
[0049] In some embodiments, the application management platform 110 may present a question-and-answer parameter configuration page in response to detecting a parameter configuration request for the question-and-answer function.
[0050] For example, in the interface 300, the application management platform 110 receives a trigger operation of the user 105 on the configuration control 310, and presents a question and answer parameter configuration page. Question and answer parameter configuration can also be referred to as question and answer rule setting. Question and answer parameter configuration can be used to configure terms and indicators, as well as to retrieve and generate rules. In this example, the configuration control 310 is in the style of a button and is named "Question and Answer Rules". Any suitable control style and name can be used without affecting the configuration function, and the present disclosure does not limit this.
[0051] The application management platform 110 may receive configuration of processing parameters for the question-and-answer function via the question-and-answer parameter configuration page. The processing parameters may also be referred to as question-and-answer rules. The question-and-answer function is configured to at least use the configured processing parameters to determine a response to a user's question from a selected data set. The question-and-answer parameter configuration page will be described in detail below. Figure 4A and Figure 4B Detailed description.
[0052] In block 230 , the application management platform 110 creates a target application 120 based at least on the configuration of the question-and-answer function and the configuration of the processing parameters.
[0053] The application management platform 110 can use the target application to provide answers to user questions. In order to increase control capabilities during the tuning process, during the creation of the target application, the application management platform 110 can receive instructions from the user 105 to enable the question-and-answer function and configure the processing parameters of the question-and-answer function. After the configuration is completed, the application management platform 110 can create the target application 120. In this way, the user can be supported to control the process or generated results of the data question-and-answer as needed.
[0054] In some embodiments, the Q&A parameter configuration page may include an example entry for one or more processing parameters that can be configured for the Q&A function. In response to detecting a trigger on the example entry for the processing parameter, the application management platform 110 may present a configuration example and / or a processing result preview corresponding to the processing parameter. In this way, the terminal effect of the processing parameter can be presented to assist the user in understanding.
[0055] Figure 4A FIG. 4 is a schematic diagram of a question and answer parameter configuration page 400A according to some embodiments of the present disclosure. The question and answer parameter configuration page 400A may be provided by the application management platform 110. Figure 1 In the question and answer parameter configuration page 400A, the application management platform 110 presents an example entry 402 and an example entry 404 .
[0056] The example entry 402 is displayed in a hyperlink style and is named “Configuration Example Preview”. The application management platform 110 may, for example, receive a click operation of the user 105 on the example entry 402 and present a floating card (not shown). In the floating card, the application management platform 110 may present a configuration example corresponding to the “Generation Result Custom Prompt Word” for the user 105 to preview.
[0057] The example entry 404 is displayed in a hyperlink style and is named “result preview”. The application management platform 110 may, for example, receive a click operation of the user 105 on the example entry 404 and present a floating card (not shown). In the floating card, the application management platform 110 may present the processing result corresponding to the “result display reference source” for the user 105 to preview.
[0058] In some embodiments, the question and answer parameter configuration page 400A may include at least one configuration control for a first machine learning model (e.g., model 155). For example, the question and answer parameter configuration page 400A includes a "global configuration" area 410. Configuration controls 406 and 408 are presented in area 410. Configuration control 406 is, for example, a "generate result custom prompt word" input control. The application management platform 110 can receive prompt words for model 155 via configuration control 406. Model 155 can be configured to generate model outputs from a selected data set based on at least the input prompt words and user questions. The response to the user's question is determined based on the output of model 155. In this way, the model question and answer results can be constrained, and the model output can be tuned.
[0059] The control style of the configuration control 406 is a text box and the name is "Generate Result Custom Prompt Words". Any suitable control style and name can be used without affecting the function of the control, and the present disclosure does not limit this. Further, the application management platform 110 can receive the prompt word input by the user 105 via the configuration control 406, and present a preview of the configuration in response to the user 105 triggering the example entry 402.
[0060] exist Figure 4A In the example, the configuration control 406 supports the user to input a prompt word within 500 characters, and does not limit the format characters. Examples of prompt words may include, but are not limited to, rule constraints for generating charts, rule constraints for generating text results, rule constraints for source filtering (e.g., not displaying certain data assets to protect sensitive data), etc. Rule instructions for generating results include, for example, reply tone, reply language, etc. Table 1 shows examples of prompt words for generating results.
[0061] Table 1
[0062]
[0063] Additionally and / or alternatively, the configuration control 408 is, for example, a context enable / disable control. The application management platform 110 may receive an enable configuration or a disable configuration for the context reference of the model 155 via the configuration control 408. In this way, the model may generate model outputs with reference to the previous conversation context in each new conversation, thereby achieving tuning of the model outputs.
[0064] The control style of configuration control 408 is a check box and the name is "Start multiple rounds of dialogue based on context". Any suitable control style and name can be used without affecting the function of the control, and the present disclosure does not limit this.
[0065] If an enabling configuration for context reference is received, for example, the configuration control 408 is selected, the model 155 is further configured to generate a model output by referring to the context information associated with the user question. For example, if the configuration control 408 is selected during the creation of the target application, the application management platform 110 can use the model 155 to provide a response to the user question based on the context information associated with the user question and the selected data set.
[0066] If a disabling configuration for context reference is received, for example, the configuration control 408 is unchecked, the model 155 is also configured to disable reference to context information associated with the user question when generating the model output. For example, if the configuration control 408 is not checked during the creation of the target application, the application management platform 110 will not consider the context information when providing a response to the user question using the model 155.
[0067] In some embodiments, the Q&A parameter configuration page 400A may include a data retrieval configuration area for the Q&A function, such as a "knowledge Q&A configuration" area 420. The application management platform 110 may receive a configuration of the number of matching data fragments retrieved from the selected data set via area 420. Data fragments may also be referred to as knowledge slices. The retrieval of data fragments may also be referred to as knowledge slice retrieval. For example, the application management platform 110 may receive settings regarding the number of recalls via a control 422 in area 420.
[0068] Additionally and / or alternatively, the application management platform 110 may receive configuration of a matching threshold between the data segments retrieved from the selected data set and the user question via area 420. For example, the application management platform 110 may receive settings regarding the matching threshold via a control 424 in area 420. Optionally, the application management platform 110 may also receive configuration of the number of documents retrieved from the selected data set via a control (not shown) in area 420.
[0069] The control styles of control 422 and control 424 are sliding number selectors and are named "recall quantity" and "matching threshold" respectively. Any suitable control style and name can be used without affecting the function of the control, and the present disclosure does not limit this.
[0070] exist Figure 4A In the example, the parameters of the knowledge question and answer include document retrieval and knowledge slice retrieval. The number of document retrievals is the top N (top N, where N is, for example, 7 by default), the number of knowledge slice retrievals is the top M (top M, where M is, for example, 7 by default), and the matching threshold is, for example, 0.5 by default. In this way, the application management platform 110 can retrieve knowledge related to user questions from unstructured knowledge, and then use the model 155 to generate responses to user questions based on this knowledge. In this way, content related to the question can be retrieved based on vectorization, and the relevance of the recalled knowledge fragments and the number of fragments can be controlled by the matching threshold.
[0071] Additionally and / or alternatively, the application management platform 110 may receive, via region 420, an enabling configuration or a disabling configuration for displaying a used data set in a reply to a user question. The used data set may also be referred to as a reference source. For example, region 420 includes a control 426, and if control 426 is selected, the reference source is displayed in the generated reply to the user question. In this way, the reference source information may be displayed in the generated result from the perspective of the end user.
[0072] Based on the above configuration regarding data retrieval, the question-answering function may be configured to determine a response to a user's question based on matching data segments retrieved from a selected data set.
[0073] In some embodiments, the Q&A parameter configuration page 400A may include a data analysis configuration area for the Q&A function, such as a "data analysis configuration" area 430. The application management platform 110 may receive an enable configuration or disable configuration for the data analysis capability in the Q&A function via area 430. For example, the application management platform 110 may support enabling or disabling the data analysis function through a control 432 in area 430. In this way, the answers to the data-related conclusions may be automatically analyzed to present data details, data insights, and other information to the end user. For example, in Figure 4A In the example of , control 432 is checked, and the data analysis function is enabled. Figure 4B In the example of , control 432 is not checked, and the data analysis function is disabled.
[0074] The data analysis function is, for example, set to on by default. In some embodiments, if the model 155 does not support the data analysis function, the data analysis function is set to off by default. For example, the application management platform 110 may enable or disable the data analysis function by default based on the function or type of the model 155. In the case of disabling the data analysis function, the application management platform 110 may prompt the user 105 that the model it has set does not support the data analysis function.
[0075] Additionally and / or alternatively, the application management platform 110 may receive an enabling configuration or disabling configuration for data insight results when the data analysis capability is enabled via area 430. For example, the application management platform 110 may support enabling or disabling the data insight function through a control 434 in area 430, thereby automatically generating data insights on the user side based on the model 155.
[0076] Additionally and / or alternatively, the application management platform 110 may receive, via area 430, a configuration of whether non-questioning users are allowed to view the data analysis results when the data analysis capability is enabled. For example, the application management platform 110 may support setting whether non-questioning users are allowed to view the details page through the control 436 in area 430. In some embodiments, if non-questioning users are allowed to view the data analysis results, all users with corresponding permissions can view the data details. The range of data that non-questioning users can view is the same as the range of data that questioning users can view, but non-questioning users can only view and cannot edit, save, or perform other operations. If non-questioning users are not allowed to view the data analysis results, the application management platform 110 may, for example, present a prompt message that "the application developer has set it so that only questioners can view it."
[0077] Additionally and / or alternatively, the application management platform 110 may receive a configuration of whether the data analysis results are allowed to be exported when the data analysis capability is enabled via area 430. For example, the application management platform 110 may support setting whether the data analysis results are allowed to be exported through a control 438 in area 430. In this way, users may be supported to export data analysis results by themselves.
[0078] Based on the above configuration regarding data analysis, the question-and-answer function may be configured to utilize the data analysis capability to determine responses to user questions when the data analysis capability is enabled.
[0079] In some embodiments, the data analysis configuration area may also include a second prompt word input control for a second machine learning model (e.g., another model 155). For example, area 430 includes control 442. Control 442 is, for example, an input control for a "custom prompt word for SQL generation phase." The application management platform 110 may receive a second prompt word for the second machine learning model via control 442. When the data analysis capability is enabled, the second machine learning model is configured to retrieve from a selected data set based at least on the second prompt word. In this way, the prompt words that the model acts on in the data retrieval and processing phases of data question and answer can be constrained, thereby fine-tuning the model output.
[0080] exist Figure 4A In the example, the style of control 442 is a text box. For example, it supports users to enter prompt words within 500 characters, and does not limit format characters. Examples of prompt words may include but are not limited to SQL variable usage constraints (for example, the available variable $current_user_id, which can represent the ID of the current user, corresponding to the employee ID (employee_id)), SQL query result format constraints (for example, the number of decimal places displayed when querying data, for example, the default is 2 digits), SQL query return result constraints (for example, querying employee information must include the column `employee_id` to ensure that the data corresponds accurately), etc. Table 2 shows an example of SQL generating custom prompt words.
[0081] Table 2
[0082]
[0083] In some embodiments, the application management platform 110 can support SQL generation restriction rules (for example, default field selection order, default sort field order by, etc.) and field link display rules (for example, when the query returns a table, the data field displays link information and can click on the corresponding link).
[0084] The above describes the configuration of the supported question-and-answer functions and the configuration of the processing parameters in the process of creating the target application. In particular, according to the embodiments of the present disclosure, adding the setting of constraint rule prompt words in the data retrieval and processing stages, as well as the generation of results stages, can support users to have more control over the effect of data question-and-answer. Furthermore, the embodiments of the present disclosure also support the setting of semantic rules for increasing the corpus so that the model can better understand and identify user needs. The following will refer to FIG. 5A to FIG. 5D Give a description.
[0085] In some embodiments, the application management platform 110 may receive an edit operation on a term list associated with the question-and-answer function. The term list may include the name and definition of at least one term. A term may include semantic rules for specific business logic, such as to supplement the lack of business support for the model in a specific field, to assist the model in understanding the business, etc. The definition structure of a term is, for example, a KV (Key-Value) data structure, which includes structural information of fields such as term name, term meaning, and term status (enabled / disabled).
[0086] Furthermore, the above-mentioned editing operation may include adding, deleting or modifying the terms in the term list. The question-answering function may also be configured to determine the answer to the user's question based on the term list. Furthermore, the application management platform 110 may create the target application 120 based on the edited term list.
[0087] FIG. 5A to FIG. 5D Schematic diagrams of term list configuration pages 500A to 500D according to some embodiments of the present disclosure are shown. The term list configuration pages 500A to 500D may be provided by the application management platform 110. Figure 1 Give a description.
[0088] The term list configuration page 500A provides a term entry function, for example, a "new term" control 502 supports entering a new term. For example, in response to the "new term" control 502 being triggered, the application management platform 110 may present a pop-up window 512, such as Figure 5B The "Add a new term" pop-up window 512 presented in the term list configuration page 500B includes an editable text box to support the user to enter the term name and term meaning. In some embodiments, when adding a new term, the default term status is not enabled.
[0089] Return to reference Figure 5A The term list in the term list configuration page 500A includes the term name, term meaning, enabled status, and available operations (such as editing, deleting, etc.) of each term. A term may include short text or keywords in terms of business dictionaries and business rules to supplement the business knowledge of the model in the business field, thereby achieving better data question-answering effects. In some embodiments, a term may be globally available by default.
[0090] In some embodiments, terms can include terms edited using semantic descriptions and terms using formula expression tables. In specific applications, terms edited using only semantic descriptions are equivalent to adding an alias and annotation description, and the effect depends on the clarity of the annotation description and the semantic reasoning and understanding ability of the model. Terms described using reference fields or expressions are strong rule terms, and the accuracy of expression writing will affect the model's reasoning and understanding ability.
[0091] In some implementations, the application management platform 110 may receive a configuration of a search strategy for a term list. The question-answering function may also be configured to retrieve terms from the term list based on the configured search strategy to determine a response to a user's question.
[0092] For example, the term list configuration page 500A also provides a search box control 504 to support searching for terms by name. In some embodiments, the application management platform 110 may support vector recall semantic retrieval. For example, the number of retrievals for term recall is the top L (top L, where L is, for example, 5 by default), and the matching threshold is, for example, 0.8 by default. In other embodiments, the application management platform 110 may support ES (Elasticsearch) word segmentation retrieval (ES keyword matching). In some embodiments, the application management platform 110 may support fuzzy retrieval of keywords, such as regular matching based on term keywords, configuring which fields in existing fields need to generate like%% queries using like syntax, and implementing fuzzy matching in in. Through the above embodiments, the accuracy of term retrieval can be improved.
[0093] In some embodiments, the application management platform 110 may also support a terminology batch management function, such as the “manage terminology status” control 506 , the “batch delete” control 508 , and the “batch import” control 510 shown on the terminology list configuration page 500A.
[0094] For example, in response to the “manage term status” control 506 being triggered, the application management platform 110 may present a floating card 514, such as Figure 5C The floating card 514 presented in the term list configuration page 500C supports batch management of the status of the selected terms, such as enabling the currently selected terms or disabling the currently selected terms.
[0095] For another example, when the “batch import” control 510 is triggered, the application management platform 110 may present a pop-up window 516, such as Figure 5D As shown. The pop-up window 516 presented in the term list configuration page 500D supports batch import of terms. The importable files support file formats such as csv, xlsx, and xls. In some embodiments, the size of the importable file and the number of terms recorded can be set. The term name is a required item, and the term description can be empty.
[0096] In some embodiments, the application management platform 110 may support the import process shown in Table 3.
[0097] Table 3
[0098]
[0099] In some embodiments, the application management platform 110 may support duplicate checking during the import process. For example, if the term names are completely matched, these terms are determined to be duplicates and the duplicate terms are deleted. The application management platform 110 may present a prompt message such as "There are XX terms in the file, YY terms were successfully imported, and ZZ of them are duplicates."
[0100] In summary, according to the embodiments of the present disclosure, in the creation of the target application, the application management platform 110 can configure the processing parameters of the question-and-answer function. Furthermore, the application management platform 110 can also edit the term list associated with the question-and-answer function. Through these embodiments, the processing parameters of the data question-and-answer can be personalized, so as to control the question-and-answer process in the creation of different applications and optimize the effect of the question-and-answer.
[0101] Figure 6 A schematic structural block diagram of a data processing device 600 according to some embodiments of the present disclosure is shown. The device 600 may be implemented in or included in the application management platform 110. Each module / component in the device 600 may be implemented by hardware, software, firmware or any combination thereof.
[0102] As shown in the figure, the device 600 includes a question-and-answer function configuration receiving module 610, which is configured to receive the configuration of the question-and-answer function of the target application. The question-and-answer function is configured to determine the response to the user's question from at least one selected data set. The device 600 also includes a processing parameter configuration receiving module 620, which is configured to receive the configuration of at least one processing parameter for the question-and-answer function in response to detecting a parameter configuration request for the question-and-answer function. The question-and-answer function is configured to determine the response to the user's question from at least one data set using at least the configured at least one processing parameter. The device 600 also includes a target application creation module 630, which is configured to create a target application based on at least the configuration of the question-and-answer function and the configuration of at least one processing parameter.
[0103] In some embodiments, the device 600 also includes: a presentation module, configured to present a configuration example and / or a processing result preview corresponding to the first processing parameter in response to detecting a trigger of an example entry of a first processing parameter among one or more processing parameters configurable for the question and answer function.
[0104] In some embodiments, the processing parameter configuration receiving module 620 can also be specifically configured to: receive a first prompt word for a first machine learning model, the first machine learning model is configured to generate a model output from at least one data set based on at least the first prompt word and a user question, wherein a response to the user question is determined based on the model output; and / or receive an enable configuration or a disable configuration for a context reference of the first machine learning model via a context enable / disable control in at least one configuration control, wherein if an enable configuration for the context reference is received, the first machine learning model is also configured to generate a model output by referring to context information associated with the user question, and wherein if a disable configuration for the context reference is received, the first machine learning model is also configured to disable reference to context information associated with the user question when generating the model output.
[0105] In some embodiments, the processing parameter configuration receiving module 620 can also be specifically configured to: receive at least one of the following configurations: a configuration for the number of matching data fragments retrieved from at least one data set, a configuration for a matching degree threshold between the data fragments retrieved from at least one data set and the user question, or an enable configuration or a disable configuration for displaying the data set used in the reply to the user question, wherein the question-and-answer function is configured to determine the reply to the user question based on the matching data fragments retrieved from at least one data set.
[0106] In some embodiments, the processing parameter configuration receiving module 620 can also be specifically configured to: receive at least one of the following configurations: an enable configuration or a disable configuration for the data analysis capability in the question and answer function, an enable configuration or a disable configuration for the data insight results when the data analysis capability is enabled, a configuration for whether the data analysis results are allowed to be viewed by non-questioning users when the data analysis capability is enabled, or a configuration for whether the data analysis results are allowed to be exported when the data analysis capability is enabled, wherein the question and answer function is configured to utilize the data analysis capability to determine responses to user questions when the data analysis capability is enabled.
[0107] In some embodiments, the processing parameter configuration receiving module 620 can also be specifically configured to: receive a second prompt word for a second machine learning model, wherein when the data analysis capability is enabled, the second machine learning model is configured to retrieve from at least one data set based at least on the second prompt word.
[0108] In some embodiments, the device 600 also includes an editing operation receiving module, which is configured to receive an editing operation on a term list associated with the question and answer function, the term list including the name and definition of at least one term, wherein the question and answer function is also configured to determine a response to a user question based on the term list, and wherein the editing operation includes adding, deleting or modifying a term in the term list, and wherein creating a target application also includes: creating the target application based on the edited term list.
[0109] In some embodiments, the processing parameter configuration receiving module 620 can also be specifically configured to: receive the configuration of at least one retrieval strategy for the term list, wherein the question and answer function is also configured to retrieve terms from the term list based on the configured at least one retrieval strategy to determine the answer to the user's question.
[0110] Figure 7 1 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown may include or be implemented as Figure 1 Application management platform 110 or Figure 6 Device 600.
[0111] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.
[0112] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 700.
[0113] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , 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 the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0114] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 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.
[0115] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 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).
[0116] 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.
[0117] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0118] 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, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0119] 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, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0120] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square 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 includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.
[0121] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.
Claims
1. A method for creating an application, comprising: receiving a configuration of a question-and-answer function of a target application, the question-and-answer function being configured to determine a response to a user question from the selected at least one data set; In response to detecting a parameter configuration request for the question-and-answer function, receiving a configuration of at least one processing parameter for the question-and-answer function, the question-and-answer function being configured to determine a response to a user question from the at least one data set using at least the configured at least one processing parameter; as well as The target application is created based at least on the configuration of the question-and-answer function and the configuration of the at least one processing parameter.
2. The method according to claim 1, further comprising: In response to detecting a triggering of an example entry of a first processing parameter among one or more processing parameters configurable by the question-and-answer function, a configuration example and / or a processing result preview corresponding to the first processing parameter is presented.
3. The method according to claim 1, wherein receiving a configuration of at least one processing parameter for the question-and-answer function comprises: receiving a first prompt word for a first machine learning model, the first machine learning model being configured to generate a model output from the at least one data set based at least on the first prompt word and a user question, wherein a response to the user question is determined based on the model output; and / or receiving, via a context enable / disable control in the at least one configuration control, an enable configuration or a disable configuration for a context reference of the first machine learning model, wherein if the enable configuration for the context reference is received, the first machine learning model is further configured to generate the model output by referencing context information associated with the user question, and Wherein, if the disabling configuration for context reference is received, the first machine learning model is also configured to disable reference to context information associated with the user question when generating the model output.
4. The method according to claim 1, wherein receiving a configuration of at least one processing parameter for the question-and-answer function comprises: Receive at least one of the following configurations: configuring the number of matching data segments retrieved from the at least one data set, configuring a matching threshold between the data segments retrieved from the at least one data set and the user question, or In the response to the user's question, show the enabled or disabled configuration of the dataset used, The question-and-answer function is configured to determine a response to a user question based on matching data segments retrieved from the at least one data set.
5. The method according to claim 1, wherein receiving a configuration of at least one processing parameter for the question-and-answer function comprises: Receive at least one of the following configurations: the configuration of enabling or disabling the data analysis capability in the question-and-answer function, and the configuration of enabling or disabling the data insight results when the data analysis capability is enabled, When the data analysis capability is enabled, whether the data analysis results are allowed to be viewed by non-questioning users, or Configuration of whether data analysis results are allowed to be exported when the data analysis capability is enabled, The question-and-answer function is configured to utilize the data analysis capability to determine responses to user questions when the data analysis capability is enabled.
6. The method according to claim 5, wherein receiving a configuration of at least one processing parameter for the question-and-answer function comprises: Receiving a second cue word for a second machine learning model, wherein when the data analysis capability is enabled, the second machine learning model is configured to retrieve from the at least one data set based at least on the second cue word.
7. The method according to claim 1, further comprising: receiving an edit operation on a term list associated with the question-and-answer function, the term list including a name and a definition of at least one term, wherein the question-answering function is further configured to determine a response to a user's question based on the list of terms, and wherein the editing operation includes adding, deleting or modifying terms in the term list, and The creating the target application further includes: creating the target application based on the edited term list.
8. The method according to claim 7, wherein receiving a configuration of at least one processing parameter for the question-and-answer function comprises: A configuration of at least one search strategy for the term list is received, wherein the question-answering function is further configured to retrieve terms from the term list to determine a response to a user question based on the configured at least one search strategy.
9. A device for creating an application, comprising: A question-and-answer function configuration receiving module, configured to receive a configuration of a question-and-answer function of a target application, wherein the question-and-answer function is configured to determine a response to a user's question from at least one selected data set; a processing parameter configuration receiving module, configured to receive a configuration of at least one processing parameter for the question-and-answer function in response to detecting a parameter configuration request for the question-and-answer function, wherein the question-and-answer function is configured to determine a response to a user question from the at least one data set using at least the configured at least one processing parameter; as well as The target application creation module is configured to create the target application based at least on the configuration of the question-and-answer function and the configuration of the at least one processing parameter.
10. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 8.
11. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.
12. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Intelligent data analysis processing method, device, equipment and medium
CN117785920A
Cited By
Application creation method and apparatus, device, and readable storage medium
WO2026040536A1
