Application management method, device and equipment and readable storage medium
By detecting the target application's Q&A pair generation request, determining and correlating the Q&A pair, the problem of insufficient update efficiency and accuracy of FAQ library in the intelligent Q&A system is solved, and the rapid and efficient response of user questions is achieved, and the efficiency of question&A pair generation is improved. accuracy.
Patent Information
- Application Number
- CN202411132206.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-18
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-18
AI Technical Summary
In the existing intelligent question and answer system, the timeliness and accuracy of the manually maintained FAQ bank is poor, resulting in insufficient efficiency and accuracy in generating FAQs, making it difficult to respond to users' online questions quickly and efficiently.
By detecting the Q&A pair generation request of the target application, the generation mode corresponding to the Q&A pair generation request is determined, multiple candidate Q&A pairs are determined based on the associated data, and at least one Q&A pair is associated with the target application to assist in the generation or automatic generation of Q&A. Yes, expand the FAQ library to improve the generation efficiency and accuracy of Q&A pairs.
It realizes quick responses to more online questions in the application, improves the efficiency and accuracy of answering high-frequency questions, assists in generating or automatically generates FAQ libraries, and improves the accuracy of responses input by users.
Smart Images

Figure CN119025653A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, apparatus, device, and readable storage medium for application management. 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 some cases, users may initiate queries within the application. Therefore, how to improve the quality of query results provided to users is a problem of concern. Summary of the invention
[0003] In a first aspect of the present disclosure, a method for application management is provided. The method includes: in response to detecting a question-answer pair generation request for a target application, determining a generation mode corresponding to the question-answer pair generation request; based on data associated with the generation mode, determining a plurality of candidate question-answer pairs, each candidate question-answer pair including a question and a corresponding answer; and in response to detecting the determination of at least one question-answer pair among the plurality of candidate question-answer pairs, associating the at least one question-answer pair to a target application, wherein the target application is configured to determine a response to a user input based on the at least one question-answer pair.
[0004] In a second aspect of the present disclosure, there is provided an application management device, the device comprising: a generation mode determination module, configured to determine a generation mode corresponding to a question and answer pair generation request for a target application in response to detecting a question and answer pair generation request; a question and answer pair determination module, configured to determine a plurality of candidate question and answer pairs based on data associated with the generation mode, each candidate question and answer pair comprising a question and a corresponding answer; and an association module, configured to associate at least one question and answer pair to a target application in response to detecting a determination of at least one question and answer pair among the plurality of candidate question and answer pairs, wherein the target application is configured to determine a response to a user input based on the at least one question and answer pair.
[0005] In a third aspect of the present disclosure, a method for application management is provided. The method includes: generating at least one candidate question based on a first question in a question-answer pair set, the question-answer pair set being associated with a target application, and the question-answer pairs in the question-answer pair set including questions and corresponding answers; and in response to detecting confirmation of one or more questions in the at least one generated candidate question, associating a question-answer pair consisting of the confirmed one or more questions, the first question, and a first answer corresponding to the first question to the target application, wherein the target application is configured to determine a response to a user input based on the associated question-answer pair.
[0006] In a fourth aspect of the present disclosure, a device for application management is provided, the device comprising: a question generation module, configured to generate at least one candidate question based on a first question in a question-answer pair set, the question-answer pair set being associated with a target application, and the question-answer pairs in the question-answer pair set comprising questions and corresponding answers; and an association module, configured to associate a question-answer pair consisting of the confirmed one or more questions, the first question and a first answer corresponding to the first question to the target application in response to detecting confirmation of one or more questions in the at least one generated candidate question, wherein the target application is configured to determine a response to a user input based on the associated question-answer pair.
[0007] In a fifth aspect of the present disclosure, a method for application management is provided. The method includes: determining at least one candidate question for the target application based on running data of the target application; generating a first answer corresponding to the first question based on a first question in the at least one candidate question; and in response to detecting confirmation of the first question and the first answer, associating a question-answer pair consisting of the first question and the first answer to the target application, wherein the target application is configured to determine a reply to a user input based on the associated question-answer pair.
[0008] In a sixth aspect of the present disclosure, there is provided an application management device, comprising: a question determination module, configured to determine at least one candidate question for a target application based on running data of the target application; an answer generation module, configured to generate a first answer corresponding to a first question based on a first question among the at least one candidate question; and an association module, configured to associate a question-answer pair consisting of the first question and the first answer to the target application in response to detecting confirmation of the first question and the first answer, wherein the target application is configured to determine a response to a user input based on the associated question-answer pair.
[0009] In a seventh 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, the method of the third aspect, and / or the method of the fifth aspect.
[0010] In an eighth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method of the first aspect, the method of the third aspect, and / or the method of the fifth aspect is implemented.
[0011] In a ninth aspect of the present disclosure, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, the method of the first aspect, the method of the third aspect, and / or the method of the fifth aspect is implemented.
[0012] 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
[0013] 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:
[0014] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0015] Figure 2 A block diagram illustrating a process of application management according to some embodiments of the present disclosure;
[0016] Figure 3 A schematic diagram showing a target application creation interface according to some embodiments of the present disclosure;
[0017] FIG. 4A to FIG. 4E A schematic diagram of a question-answer pair management page according to some embodiments of the present disclosure is shown;
[0018] Figure 5A and Figure 5B A schematic diagram showing a question-answer pair management page according to some other embodiments of the present disclosure;
[0019] Figure 6 A schematic structural block diagram showing an application management device according to other embodiments of the present disclosure; and
[0020] 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
[0021] 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.
[0022] 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.
[0023] 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.
[0024] 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.
[0025] 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.
[0026] 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.
[0027] 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.
[0028] 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.
[0029] 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.
[0030] 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.
[0031] like Figure 1 As shown, the application creation part can provide the user 105 with an environment for creating and publishing applications. 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.
[0032] 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.
[0033] 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 that constitutes 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.
[0034] 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 terminal users 145. The terminal user 145 can be referred to as the terminal user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.
[0035] The digital assistant 122 may be configured to have an intelligent conversation. Figure 1 In 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.
[0036] In some embodiments, digital assistant 122 can interact with end user 145 as a contact of end user 145. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.
[0037] 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.
[0038] 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.
[0039] 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, such as the capabilities of the model 155, can be called. 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.
[0040] 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.
[0041] 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.
[0042] 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.
[0043] 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.
[0044] At present, in some intelligent question-answering scenarios, terminal users' queries can be automatically answered based on the FAQ library that is manually created and managed. For example, in the scenario of data question-answering, terminal users will ask questions about data. Terminal users' questions can be quickly answered based on the question-answer pairs stored in the FAQ library or the answers automatically generated based on the model. However, the timeliness and accuracy of the manually maintained FAQ library are poor, and it is expected to improve the efficiency and accuracy of generating FAQs.
[0045] In an embodiment of the present disclosure, an improved scheme for application management is provided. In this scheme, in response to detecting a question-answer pair generation request for a target application, a generation mode corresponding to the question-answer pair generation request is determined; based on data associated with the generation mode, multiple candidate question-answer pairs are determined, each candidate question-answer pair includes a question and a corresponding answer; and in response to detecting the determination of at least one question-answer pair among the multiple candidate question-answer pairs, at least one question-answer pair is associated with a target application, wherein the target application is configured to determine a response to user input based on at least one question-answer pair. In this way, question-answer pairs used in applications can be assisted or automatically generated to expand the FAQ library. In this way, the FAQ library can be used to quickly respond to more online questions, thereby improving the efficiency and accuracy of answering high-frequency questions.
[0046] 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.
[0047] 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 a 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.
[0048] Figure 2 A block diagram of an application management process 200 according to some embodiments of the present disclosure is shown. The application management process can be implemented on the application management platform 110, and specifically can correspond to the creation process or the later maintenance process of the target application. Figure 1 To describe Figure 2 Illustrated application management process.
[0049] like Figure 2As shown, in box 210, the application management platform 110 determines the generation mode corresponding to the question-answer pair generation request in response to detecting the question-answer pair generation request for the target application 120. Examples of generation modes include, but are not limited to, various generation scenarios, such as a scenario of generating question-answer pairs based on operational data, a scenario of generating question-answer pairs based on unstructured documents, etc. Different generation modes may correspond to different question-answer pair generation methods, and / or rely on different data sources to generate question-answer pairs. The generation mode will be described in detail below in conjunction with the accompanying drawings.
[0050] At block 220 , the application management platform 110 determines a plurality of candidate question-answer pairs based on the data associated with the generation schema.
[0051] Each candidate question-answer pair includes a question and a corresponding answer. A candidate question-answer pair may include a question and an answer corresponding to it. Different candidate question-answer pairs may include different questions, but correspond to the same answer. In some embodiments, a candidate question-answer pair may also include multiple questions and an answer corresponding to them.
[0052] At block 230, the application management platform 110, in response to detecting the determination of at least one question-answer pair from the plurality of candidate question-answer pairs, associates the at least one question-answer pair to the target application 120. The target application 120 is configured to determine a reply to the user input based on the associated question-answer pair.
[0053] For example, after determining a plurality of candidate question-answer pairs, the application management platform 110 may cluster or filter based on preset rules, or the user may filter manually, thereby determining from the candidate question-answer pairs the question-answer pairs that are suitable for storage in the FAQ library of the target application 120. In this way, the question-answer pairs corresponding to the FAQ may be automatically generated, thereby improving the efficiency of generating question-answer pairs.
[0054] In some embodiments, question-answer pair generation rules may be formulated based on the adoption rates of multiple candidate question-answer pairs or the interception rates of online questions to improve the accuracy of question-answer pair generation by the application management platform 110 .
[0055] For another example, after determining multiple candidate question-answer pairs, the application management platform 110 may present them to the user 105 for further confirmation by the user 105. Furthermore, the application management platform 110 may receive the question-answer pairs determined by the user 105 and store these question-answer pairs in the FAQ library of the target application 120. In this way, the user can be assisted in generating FAQs, and the efficiency of generating question-answer pairs and the accuracy of responding to user inputs can be improved.
[0056] In some embodiments, the application management platform 110 may present multiple candidate question-answer pairs and detect edits to one or more of the multiple candidate question-answer pairs. For example, the application management platform 110 may present multiple automatically generated candidate question-answer pairs to the user 105. The user 105 may perform editing operations on some or all of these candidate question-answer pairs, such as modifying the question description, modifying the answer statement, deleting the question-answer pairs, etc. Furthermore, the application management platform 110 may receive the editing operation of the user 105 and present multiple candidate question-answer pairs including one or more edited question-answer pairs for further confirmation by the user 105. The application management platform 110 may store the confirmed question-answer pairs in the FAQ library of the target application 120. In this way, users may be assisted in generating more practical FAQs, thereby further improving the efficiency of generating question-answer pairs and the accuracy of responding to user input.
[0057] The above process can realize the scenario where a new FAQ library needs to be created during the creation of the target application, and can also realize the scenario where new or edited question and answer pairs need to be added during the maintenance of the target application. Figure 3 A schematic diagram of an interface 300 for creating / editing a target application 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 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, etc. 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.
[0058] In the configuration area 301, the application management platform 110 may present multiple functional controls related to question and answer tuning, such as control 310. Control 310 is, for example, a "fixed question and answer library (FAQ)" configuration control. The application management platform 110 may receive a trigger for the control and enter a question and answer pair management page. Question and answer pairs may be generated or edited in the question and answer pair management page.
[0059] In some embodiments, multiple generation modes are provided for automatically generating question-answer pairs. In a first generation mode indicating generation based on historical interactions, question-answer pairs can be generated based on high-frequency questions encountered during the operation of the target application, thereby assisting application creators in improving the FAQ capabilities of the target application. In a second generation mode indicating generation of similar questions, questions in entered question-answer pairs can be generalized, thereby assisting application creators in generating more questions, thereby enabling more matching of user questions. In a third generation mode based on generation of a data set, answerable questions and answers can be automatically generated from one or more selected structured or unstructured documents, thereby assisting application creators in improving the FAQ capabilities of the target application.
[0060] The following will refer to FIG. 4A to FIG. 5B Detailed description of examples of various generation modes and how to generate or edit question-answer pairs in a specific generation mode.
[0061] FIG. 4A to FIG. 4E Schematic diagrams of question-answer pair management pages 400A to 400E according to some embodiments of the present disclosure are shown. Question-answer pair management pages 400A to 400E may be provided by the application management platform 110. Figure 1 Give a description.
[0062] In the question-and-answer pair management page 400A, the application management platform 110 presents multiple controls. For example, the "Import" control 402 can be used to import question-and-answer pairs. The "Export All" control 404 can be used to export question-and-answer pairs. The "New Question-and-Answer Pair" control 406 can be used to add a new question-and-answer pair. In some embodiments, in response to triggering the "New Question-and-Answer Pair" control 406, the application management platform 110 can present an "Intelligently Generate Question-and-Answer Pair" card 408. Further, in response to triggering the "Intelligently Generate Question-and-Answer Pair" card 408, the application management platform 110 can present a pop-up window (not shown) to receive the user's 105 operation on the newly added question-and-answer pair.
[0063] Furthermore, the question-and-answer pair management page 400A also includes a search box control 410 for searching question-and-answer pairs.
[0064] In some embodiments, the question-and-answer pair management page 400A also includes a control 412 to enable / disable or disable the FAQ library. If the FAQ library is enabled, the target application is configured to match the received user questions with the question-and-answer pairs in the FAQ library first. If the user question matches the question in a certain question-and-answer pair, the answer in the question-and-answer pair can be directly output as a reply to the user question. If no matching question is retrieved from the question-and-answer pairs in the FAQ library, the target application will be configured to utilize other configured functions, such as utilizing model 155 to generate answers corresponding to the user question. It can be seen that if more and higher quality question-and-answer pairs can be maintained, the processing speed and efficiency of the target application for user questions will be significantly improved.
[0065] In some embodiments, the application management platform 110 may obtain operation data of the target application 120 in response to the generation of the generation mode indication based on the historical interaction. The operation data may be manually imported or automatically obtained (e.g., the background operation log of the application management platform 110 itself). Such operation data may include historical user input of the target application, and / or structured or unstructured operation log information. Further, the application management platform 110 may determine one or more candidate question-answer pairs based on the operation data.
[0066] As an example, the application management platform 110 may respond to Figure 4A The triggering of the "intelligently generated question and answer pairs" card 408 in the display is as follows Figure 4B Pop-up window 422 is shown. Pop-up window 422 includes a scenario selection control 424, which can indicate a generation mode for generating question-answer pairs based on running data.
[0067] If the scenario selection control 424 is selected, the application management platform 110 can generate a question-answer pair based on the high-frequency question file. Furthermore, the application management platform 110 can receive a file uploaded by the user 105 in the control 428. The uploaded file is, for example, a file related to operation data. Such a file includes historical user input. The application management platform 110 can analyze these historical user inputs using the model 155 to discover high-frequency questions.
[0068] In some embodiments, the application management platform 110 can determine multiple historical user inputs that appear in the operation of the target application from the operation data. Based on the frequency of occurrence of multiple historical user inputs, at least one candidate question is determined. In this way, high-frequency problems that appear during the operation of the target application can be identified from the operation data. In some embodiments, the application management platform 110 can determine at least one candidate question by clustering high-frequency historical user inputs (also called questions) in the operation of the application. For example, the application management platform 110 identifies high-frequency questions and similar questions based on the heat of the questions, and then clusters these questions as candidate questions. For another example, the application management platform 110 derives questions based on document slicing information of unstructured data, slicing information of structured data, table metadata, metadata of fields corresponding to the table, table and field annotations, terminology rules and other information, and then clusters these questions.
[0069] In some embodiments, the application management platform 110 can dynamically generate multiple questions based on the number of online operation logs, document length, and slice information, and rank these questions by score. The application management platform 110 can determine and present questions that exceed a threshold score, or can sort the questions by score and present them to the user for selection.
[0070] Continue to refer Figure 4B , the application management platform 110 may present the following in response to triggering the control 430: Figure 4D The pop-up window 442 is shown. The application management platform 110 can generate high-frequency recommendation questions based on the uploaded files and present them in the pop-up window 442.
[0071] In some embodiments, the application management platform 110 may generate answers to the questions based on the confirmed questions in response to detecting confirmation of one or more of the presented candidate questions, so as to obtain one or more candidate question-answer pairs. In some embodiments, the application management platform 110 may generate answers corresponding to each candidate question after determining the candidate questions, and then present the candidate questions and the corresponding answers to the user for selection.
[0072] For example, the application management platform 110 presents the generated high-frequency recommended questions in a pop-up window 442. The user 105 can select a portion of these questions to achieve secondary confirmation, thereby improving the accuracy of the generated question-answer pairs. In response to the triggering of the control 444, the application management platform 110 can generate answers for the selected questions and present them in a pop-up window such as Figure 4EIn the pop-up window 452 shown. In the pop-up window 452, the application management platform 110 presents the question and the answer in pairs. After receiving the user's confirmation, the application management platform 110 can associate the user-confirmed question and answer pair with the target application. In some embodiments, the application management platform 110 can support the user to modify the question and answer and confirm to add it to the FAQ library.
[0073] In some embodiments, the application management platform 110 can support an offline generation and operation mechanism of FAQ. For example, the application management platform 110 can run the process of generating questions or answers in the background. The application management platform 110 can remind the user in the interface that the operation takes a certain amount of time, and can refresh the FAQ interface after successful execution. If the operation fails, the application management platform 110 can present an error prompt to support the user to initiate a retry.
[0074] In some embodiments, the generation of answers can be implemented using a machine learning model. In some embodiments, the machine learning model can generate answers corresponding to candidate questions based on a data set (also referred to as a knowledge base) associated with the target application. In some embodiments, the machine learning model can also generate answers corresponding to candidate questions based on the operating data of the target application, because the answer to the candidate question may be determined and presented to the user during the operation of the target application. In some embodiments, when generating answers corresponding to candidate questions as candidate question-answer pairs, feedback information of one or more historical answers corresponding to questions that are the same or similar to the candidate question can also be determined from the operating data. If the feedback information indicates that a certain historical answer is of higher quality, the machine learning model can refer more to the historical answer to generate answers corresponding to the candidate question.
[0075] In summary, the application management platform 110 can present a question-and-answer pair management page and an intelligently generated question-and-answer pair pop-up window in response to a question-and-answer pair generation request. In the intelligently generated question-and-answer pair pop-up window in the question-and-answer pair management page 400B, the application management platform 110 supports users to select a generation mode (i.e., scenario selection) and import operating data. In the intelligently generated question-and-answer pair pop-up window in the question-and-answer pair management page 400D, the application management platform 110 supports summarizing and extracting high-frequency questions. In the intelligently generated question-and-answer pair pop-up window in the question-and-answer pair management page 400E, the application management platform 110 can generate question-and-answer pairs. In this way, the ability to discover high-frequency questions online for data question answering can be provided, online questions can be clustered, missing FAQ libraries can be discovered, and FAQs can be assisted in generation or supplementation, thereby improving the accuracy of answers to high-frequency questions.
[0076] In some embodiments, the application management platform 110 may present a data set configuration portal in response to the generation mode indicating generation based on the data set. The application management platform 110 may receive at least one data set through the data set configuration portal, and then generate one or more candidate question-answer pairs based on the at least one data set.
[0077] As an example, the application management platform 110 may respond to Figure 4A The triggering of the "intelligently generated question and answer pairs" card 408 in the display is as follows Figure 4B The pop-up window 422 shown. The pop-up window 422 includes a scenario selection control 426, which can indicate a generation mode of generating question-answer pairs based on knowledge. In other words, the application management platform 110 can automatically mine keywords in the data from the selected knowledge and generate questions and answers.
[0078] If the scene selection control 426 is selected, the application management platform 110 may present the following Figure 4C The pop-up window 432 is shown. Furthermore, the application management platform 110 can receive data resources for generating question-answer pairs in the data set configuration entry control 434.
[0079] In some embodiments, the application management platform 110 can extract keywords from a given data set. In response to detecting confirmation of the keywords, the application management platform 110 can generate one or more candidate questions based on the confirmed keywords, and generate answers for each candidate question from one or more data sets to obtain candidate question-answer pairs. In some embodiments, when generating answers, the application management platform 110 can use a machine learning model to determine the answers corresponding to the candidate questions based on one or more data sets associated with the target application. The machine learning model can be a model configured to the target application to support the question-answering function.
[0080] In this way, when accessing unstructured documents, you can choose to automatically generate answerable questions and answers based on the document content, and add them to the FAQ library after user confirmation, to assist in completing the generation of the FAQ.
[0081] For example, the application management platform 110 may generate candidate questions based on the data resources received for generating question-answer pairs. The received data resources may be all data resources by default, or data resources specified by the user. The application management platform 110 may present the generated candidate questions to the user 105, and generate answers based on the candidate questions screened by the user 105, thereby forming question-answer pairs that can be presented to the user 105. For another example, the application management platform 110 may mine and derive keywords based on the data resources received for generating question-answer pairs. The application management platform 110 may present the automatically generated keywords to the user 105. The user 105 may select and edit these keywords. The application management platform 110 may generate questions and answers based on the keywords edited by the user 105, thereby forming question-answer pairs that can be presented to the user 105. In some embodiments, the application management platform 110 may support users to modify questions and answers and confirm that they are added to the FAQ library.
[0082] Generating question-answer pairs based on corpus is suitable for FAQ generation in the cold start phase. The application management platform 110 can choose to automatically generate answerable questions and answers based on document content, and add them to the FAQ library after user confirmation, thereby assisting in the completion of FAQ generation.
[0083] As an example, refer to Figure 4E , the application management platform 110 presents multiple question-answer pairs in a pop-up window 452. In response to the user's selection operation on a certain question-answer pair, the application management platform 110 may present multiple controls. For example, control 454 is used to support the operation of deleting the question-answer pair, control 456 is used to support editing the question-answer pair, and control 458 is used to support adding the question-answer pair to the FAQ library.
[0084] References FIG. 4A to FIG. 4E Describes the generation mode of question-answer pairs based on given data. Figure 5A and Figure 5B An example of another generation mode is described, which indicates that generalized questions can be generated based on an existing FAQ library, thereby enriching the diversity of question-answer pairs.
[0085] Figure 5A and Figure 5B Schematic diagrams of question-answer pair management pages 500A and 500B according to other embodiments of the present disclosure are shown. Question-answer pair management pages 500A and 500B may be provided by the application management platform 110. Figure 1 Give a description.
[0086] In some embodiments, the application management platform 110 may generate similar questions in response to the generation mode indicating the generation of similar questions, and present one or more question-answer pairs associated with the target application 120 (which may be a set of question-answer pairs or a list of question-answer pairs). The application management platform 110 may generate at least one candidate question based on the question in response to detecting the selection of a question in these question-answer pairs. The question may also be referred to as the first question or the initial question. It is expected that at least one candidate question generated is a variation of the initial question, so the candidate question and the initial question are usually similar and semantically matched, but different in language expression. This can cover all kinds of user questioning methods that may be received during the actual application operation. The at least one candidate question generated and the answer corresponding to the question constitute at least one candidate question-answer pair. In this way, the data entered into the FAQ library can be generalized to obtain question-answer pairs with multiple questions corresponding to one answer, thereby improving the online question interception rate.
[0087] For example, in the question-answer pair management page 500A, the application management platform 110 presents the associated question-answer pairs. The user 105 can select a question-answer pair from these question-answer pairs. The application management platform 110 can use the question in the selected question-answer pair as the initial question to perform the generalization function. The generalization function performs one or more of the following operations on the question selected by the user to obtain more candidate difficult questions. Possible operations include, but are not limited to, rewriting the user's question (for example, colloquial rewriting), modifying the sentence structure of the user's question, replacing synonyms of the user's question, deleting at least part of the content of the user's question (for example, deleting irrelevant sentence components that do not affect the answer), and the like. In some embodiments, the application management platform 110 can use a machine learning model to generate one or more candidate questions that semantically match the initial question. The machine learning model can be trained to be able to perform various changes to the initial question to obtain additional candidate questions that semantically match.
[0088] Further, in the question-answer pair management page 500A, the application management platform 110 presents an "intelligently generate questions" control 502. In response to the control 502 being triggered, the application management platform 110 presents a pop-up window 504 in the question-answer pair management page 500B. In the pop-up window 504, the application management platform 110 presents a question-answer pair generalized based on the initial question.
[0089] In some embodiments, in response to detecting confirmation of one or more questions among the generated candidate questions, the application management platform 110 may associate the question-answer pair consisting of the confirmed one or more questions, the initial question, and the initial answer to the target application 120. In this way, the user 105 may be supported to further filter the generalized questions, thereby improving the recall rate and interception rate of the question-answer pair.
[0090] For example, the user 105 may select a question-answer pair that he / she wishes to adopt from the question-answer pairs presented in the pop-up window 504, and then trigger the control 506. In response to the triggering of the control 506, the application management platform 110 may add the selected question-answer pair to the FAQ library. The application management platform 110 may support the adoption of a single question-answer pair or the batch adoption of multiple question-answer pairs.
[0091] In summary, according to the embodiments of the present disclosure, a question-answer pair generation scheme based on multiple generation modes can be provided. Generation modes include, for example, maintaining the FAQs accumulated by users into the platform through the entry or import function, generalizing a batch of FAQs based on existing FAQs, assisting in the generation of FAQs based on summarized and extracted high-frequency questions, or assisting in the batch generation of FAQs during initialization. Thus, on the basis of supporting FAQ management entry, the ability to use models to assist in the generation of FAQs is added, assisting users in constructing questions and answers generated based on data resources, which can be added to the FAQ library after being adopted.
[0092] In some embodiments, the application management platform 110 can support viewing and operating the generated question-answer pairs. For example, the generation of the question-answer pairs is the result of asynchronous operation. After the user submits the task and the operation is successfully executed, the application management platform 110 can support the user to view the results of the question-answer pairs, and perform secondary editing on the results of the question-answer pairs and adopt them into the online FAQ library for use. When viewing the question-answer pairs, the associated question-answer pairs can be presented. In some embodiments, these question-answer pairs can include questions, answers, and can also include the knowledge source referenced by the answer, the knowledge fragment referenced by the answer, and / or the generation time of the question-answer pair of the answer.
[0093] When viewing question-answer pairs, various operations on the question-answer pairs can be supported, including detail viewing operations and editing operations (editing questions and / or answers). In some embodiments, the question-answer pairs adopted and associated with the target application in the generated question-answer pairs can also be adopted individually or in batches. In some embodiments, the question-answer pairs adopted and associated with the target application in the generated question-answer pairs can also be deleted individually or in batches. In some embodiments, users can also be supported to choose to add one or more question-answer pairs to the corpus for use by the machine learning model when generating answers to user questions.
[0094] Figure 6 A schematic structural block diagram of an application management apparatus 600 according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented in or included in the application management platform 110. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware or any combination thereof.
[0095] As shown in the figure, the device 600 includes a generation mode determination module 610, which is configured to determine the generation mode corresponding to the question and answer pair generation request in response to detecting a question and answer pair generation request for a target application. The device 600 also includes a question and answer pair determination module 620, which is configured to determine a plurality of candidate question and answer pairs based on data associated with the generation mode, each candidate question and answer pair including a question and a corresponding answer. The device 600 also includes an association module 630, which is configured to associate at least one question and answer pair to a target application in response to detecting the determination of at least one question and answer pair among the plurality of candidate question and answer pairs, wherein the target application is configured to determine a response to a user input based on the at least one question and answer pair.
[0096] In some embodiments, the device 600 also includes: a first presentation module configured to present multiple candidate question-answer pairs; a detection module configured to detect edits to one or more question-answer pairs among the multiple candidate question-answer pairs; and a second presentation module configured to present multiple candidate question-answer pairs including the edited one or more question-answer pairs for confirmation.
[0097] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: in response to the generation mode indicating generation based on historical interactions, obtain operation data in the target application, the operation data at least including historical user input; and determine one or more candidate question-answer pairs based on the operation data.
[0098] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: determine at least one candidate question by clustering historical user inputs in the operation data; and in response to detecting confirmation of one or more questions in the at least one candidate question, generate answers to the confirmed one or more questions to obtain one or more candidate question-answer pairs.
[0099] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: in response to the generation mode indicating similar question generation, present a set of question-answer pairs associated with the target application; and in response to detecting a selection of a first question in the question-answer pair set, generate at least one candidate question based on the first question, the generated at least one candidate question and the answer corresponding to the first question forming at least one candidate question-answer pair.
[0100] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: in response to detecting confirmation of one or more questions among at least one generated candidate question, associate the question-answer pair consisting of the confirmed one or more questions, the first question and the first answer to the target application.
[0101] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: present a data set configuration entry in response to the generation mode indicating generation based on a data set; receive at least one data set via the data set configuration entry; and generate one or more candidate question-answer pairs based on at least one data set.
[0102] In some embodiments, the question-answer pair determination module 620 can also be specifically configured to: extract at least one keyword from at least one data set; and in response to detecting confirmation of one or more keywords in the at least one keyword, generate one or more candidate questions based on the confirmed one or more keywords; and generate answers corresponding to each of the one or more candidate questions from at least one data set to obtain one or more candidate question-answer pairs.
[0103] In some embodiments, an application management device includes: a question generation module, configured to generate at least one candidate question based on a first question in a question-answer pair set, the question-answer pair set being associated with a target application, and the question-answer pairs in the question-answer pair set including questions and corresponding answers; and an association module, configured to associate a question-answer pair consisting of the confirmed one or more questions, the first question and a first answer corresponding to the first question to a target application in response to detecting confirmation of one or more questions in the at least one generated candidate question, wherein the target application is configured to determine a response to a user input based on the associated question-answer pair.
[0104] In some embodiments, the question generation module is further configured to generate at least one candidate question by executing at least one item on the first question: rewriting the first question, modifying the sentence structure of the first question, replacing a synonymous expression of the first question, and deleting at least part of the content of the first question.
[0105] In some embodiments, the question generation module is further configured to: utilize a machine learning model to generate at least one candidate question that semantically matches the first question.
[0106] In some embodiments, an application management device includes: a question determination module, configured to determine at least one candidate question for a target application based on running data in the target application; an answer generation module, configured to generate a first answer corresponding to the first question based on a first question among the at least one candidate question; and an association module, configured to associate a question-answer pair consisting of the first question and the first answer to the target application in response to detecting confirmation of the first question and the first answer, wherein the target application is configured to determine a response to a user input based on the associated question-answer pair.
[0107] In some embodiments, the operation data includes at least one of the following: historical user input for the target application, and operation log information of the target application.
[0108] In some embodiments, the answer generation module is further configured to: in response to detecting confirmation of a first question among the at least one candidate question, generate a first answer corresponding to the first question based on the first question.
[0109] In some embodiments, the problem determination module is further configured to: determine from the operation data a plurality of historical user inputs occurring during the operation of the target application; and determine at least one candidate problem based on the occurrence frequencies of the plurality of historical user inputs.
[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 generating 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 application management, comprising: In response to detecting a question-answer pair generation request for a target application, determining a generation mode corresponding to the question-answer pair generation request; determining, based on data associated with the generated pattern, a plurality of candidate question-answer pairs, each candidate question-answer pair comprising a question and a corresponding answer; as well as In response to detecting a determination of at least one question-answer pair from the plurality of candidate question-answer pairs, the at least one question-answer pair is associated with the target application, wherein the target application is configured to determine a response to a user input based on the at least one question-answer pair.
2. The method according to claim 1, further comprising: presenting the plurality of candidate question-answer pairs; detecting edits to one or more question-answer pairs from among the plurality of candidate question-answer pairs; as well as The plurality of candidate question-answer pairs including the edited one or more question-answer pairs are presented for confirmation.
3. The method according to claim 1, wherein determining a plurality of candidate question-answer pairs comprises: In response to the generation mode indicating generation based on historical interactions, acquiring operation data of the target application; as well as One or more candidate question-answer pairs are determined based on the operational data.
4. The method of claim 3, wherein determining one or more candidate question-answer pairs based on the operational data comprises: determining at least one candidate question by clustering historical user inputs in the operational data; as well as In response to detecting confirmation of one or more questions in the at least one candidate question, answers to the confirmed one or more questions are generated to obtain one or more candidate question-answer pairs.
5. The method of claim 1, wherein determining a plurality of candidate question-answer pairs comprises: In response to the generation pattern indicating similar question generation, presenting a set of question-answer pairs associated with the target application; as well as In response to detecting a selection of a first question in the question-answer pair set, at least one candidate question is generated based on the first question, and the generated at least one candidate question and an answer corresponding to the first question constitute at least one candidate question-answer pair.
6. The method of claim 5, wherein associating the at least one question-answer pair to the target application comprises: In response to detecting confirmation of one or more questions among the generated at least one candidate question, a question-answer pair consisting of the confirmed one or more questions, the first question, and the first answer is associated with the target application.
7. The method of claim 1, wherein determining a plurality of candidate question-answer pairs comprises: In response to the generation mode indicating generation based on the data set, presenting a data set configuration entry; receiving at least one data set via the data set configuration portal; as well as One or more candidate question-answer pairs are generated based on the at least one data set.
8. The method of claim 7, wherein generating one or more candidate question-answer pairs based on the at least one data set comprises: extracting at least one keyword from the at least one data set; as well as In response to detecting confirmation of one or more of the at least one keyword, generating one or more candidate questions based on the confirmed one or more keywords; as well as Generate answers corresponding to each of the one or more candidate questions from the at least one data set to obtain the one or more candidate question-answer pairs.
9. A method for application management, comprising: generating at least one candidate question based on a first question in a set of question-answer pairs, the set of question-answer pairs being associated with a target application, and the question-answer pairs in the set of question-answer pairs comprising a question and a corresponding answer; as well as In response to detecting confirmation of one or more questions among at least one generated candidate question, a question-answer pair consisting of the confirmed one or more questions, the first question and a first answer corresponding to the first question is associated with the target application, wherein the target application is configured to determine a response to the user input based on the associated question-answer pair.
10. The method of claim 9, wherein generating at least one candidate question based on the first question comprises: At least one candidate question is generated by executing at least one item on the first question: A rephrasing of the first question: The modification of the sentence structure of the first question, A synonymous replacement for the first question, A deletion of at least part of the first question.
11. The method of claim 9, wherein generating at least one candidate question based on the first question comprises: Using a machine learning model, generate at least one candidate question that semantically matches the first question.
12. A method for application management, comprising: Determining at least one candidate problem for the target application based on the operation data of the target application; Based on a first question among at least one candidate question, generating a first answer corresponding to the first question; as well as In response to detecting confirmation of the first question and the first answer, a question-answer pair consisting of the first question and the first answer is associated with the target application, wherein the target application is configured to determine a reply to the user input based on the associated question-answer pair.
13. The method according to claim 12, wherein the operating data comprises at least one of the following: historical user input for the target application, The target application's running log information.
14. The method according to claim 12, wherein generating a first answer corresponding to the first question comprises: In response to detecting confirmation of a first question among the at least one candidate question, a first answer corresponding to the first question is generated based on the first question.
15. The method of claim 12, wherein determining at least one candidate question for the target application comprises: determining, from the operation data, a plurality of historical user inputs occurring during the operation of the target application; as well as At least one candidate question is determined based on the occurrence frequencies of the plurality of historical user inputs.
16. An application management device, comprising: A generation mode determination module, configured to, in response to detecting a question-answer pair generation request for a target application, determine a generation mode corresponding to the question-answer pair generation request; a question-answer pair determination module configured to determine a plurality of candidate question-answer pairs based on data associated with the generation pattern, each candidate question-answer pair comprising a question and a corresponding answer; as well as An association module is configured to associate at least one question-answer pair with the target application in response to detecting a determination of at least one question-answer pair among the multiple candidate question-answer pairs, wherein the target application is configured to determine a response to a user input based on the at least one question-answer pair.
17. An application management device, comprising: a question generation module configured to generate at least one candidate question based on a first question in a question-answer pair set, wherein the question-answer pair set is associated with a target application, and the question-answer pairs in the question-answer pair set include questions and corresponding answers; as well as An association module is configured to associate a question-answer pair consisting of the confirmed one or more questions, the first question and a first answer corresponding to the first question to the target application in response to detecting confirmation of one or more questions among at least one generated candidate question, wherein the target application is configured to determine a response to the user input based on the associated question-answer pair.
18. An application management device, comprising: A problem determination module, configured to determine at least one candidate problem for the target application based on the operation data of the target application; An answer generation module, configured to generate a first answer corresponding to a first question among at least one candidate question based on the first question; as well as An associating module is configured to associate a question-answer pair consisting of the first question and the first answer to the target application in response to detecting confirmation of the first question and the first answer, wherein the target application is configured to determine a reply to the user input based on the associated question-answer pair.
19. 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, cause the electronic device to perform a method according to any one of claims 1 to 8, a method according to any one of claims 9 to 11, and / or a method according to any one of claims 12 to 15.
20. 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, the method according to any one of claims 9 to 11, and / or the method according to any one of claims 12 to 15.
21. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8, the method according to any one of claims 9 to 11, and / or the method according to any one of claims 12 to 15.
Citation Information
Patent Citations
Answer matching method and device, electronic equipment and storage medium
CN110837548A
Keyword-based long text question and answer pair generation system
CN111914062A
Information pushing method, device, electronic equipment and storage medium
CN113505293A
Question and answer pair generation method and device thereof, equipment and storage medium
CN113515601A
Processing method for intelligent customer service dialogue and related product
CN117312521A
