Task processing method and apparatus, device, and computer-readable storage medium

Abstract

A task processing method and apparatus, a device, and a computer-readable storage medium. The method comprises: parsing a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; generating a query instruction on the basis of the parsing result; and in response to determining that a query result obtained by using the query instruction does not satisfy a specified condition, generating an analysis instruction, the analysis instruction being used for analyzing the query result obtained by using the query instruction.

Description

Task processing method, apparatus, device, and computer-readable storage medium

[0001] The present application claims priority to the Chinese patent application No. 202410851944.3, filed on June 27, 2024, entitled “Task processing method, apparatus, device, and computer-readable storage medium”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a task processing method, apparatus, device, and computer-readable storage medium. BACKGROUND

[0003] With the development of information technology, various terminal devices can provide people with various services in work and life, etc. The terminal device can be deployed with an application that provides services. The terminal device presents corresponding content through the user interface of the application and realizes interaction with the user to meet various needs of the user. In some cases, the user can initiate a task processing request in the application. Therefore, how to accurately complete the task processing request is a problem of concern. SUMMARY

[0004] In a first aspect of the present disclosure, a task processing method is provided. The method comprises: parsing a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; generating a query instruction based on the parsing result; and in response to determining that a query result obtained by using the query instruction does not satisfy a specified condition, generating an analysis instruction, the analysis instruction being used for analyzing the query result obtained by using the query instruction.

[0005] In a second aspect of the present disclosure, a task processing apparatus is provided. The apparatus comprises: a parsing module configured to parse a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; a query instruction generation module configured to generate a query instruction based on the parsing result; and an analysis instruction generation module configured to, in response to determining that a query result obtained by using the query instruction does not satisfy a specified condition, generate an analysis instruction, the analysis instruction being used for analyzing the query result obtained by using the query instruction.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device comprises at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by the at least one processor, cause the electronic device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The medium has stored thereon computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0009] It should be understood that all statements herein made regarding the exemplary embodiments of the present disclosure are intended to encompass both structural and functional equivalents thereof. Additionally, it should be understood that although the exemplary embodiments of the present disclosure have been specifically illustrated and described, various modifications and changes can be made without departing from the scope of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements, wherein:

[0011] FIG. 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG. 2 shows a block diagram of a task processing process according to some embodiments of the present disclosure;

[0013] FIG. 3 shows a schematic diagram of user input according to some embodiments of the present disclosure;

[0014] FIG. 4 shows a schematic diagram of a task processing process according to some embodiments of the present disclosure;

[0015] FIG. 5 shows a schematic diagram of a page showing data results according to some embodiments of the present disclosure;

[0016] FIG. 6 shows a schematic structural block diagram of a task processing apparatus according to some embodiments of the present disclosure;

[0017] FIG. 7 shows a block diagram of an electronic device that can implement one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described herein below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein; rather, these embodiments are provided so as to more completely and thoroughly understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are merely for illustrative purposes and are not intended to limit the scope of the present disclosure.

[0019] In the description of embodiments of the disclosure, the term "comprising" and similar terms thereof are understood to be inclusive, i.e., "including but not limited to". The term "based on" is understood to mean "based at least in part on". The term "one embodiment" or "the embodiment" is understood to mean "at least one embodiment". The term "some embodiments" is understood to mean "at least some embodiments". Other explicit and implicit definitions can also be included below.

[0020] In this article, unless specifically stated, performing a step "in response to A" does not mean performing the step immediately after "A", but can include one or more intermediate steps.

[0021] It can be understood that the data involved in the technical solutions of the present application (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0022] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means, wherein the relevant user can include any type of right subject, such as individual, enterprise, group.

[0023] For example, in response to receiving the active request of the user, the prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require the information of the relevant user to be obtained and used, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0024] As an optional but not limited implementation manner, in response to receiving the active request of the relevant user, the prompt information is sent to the relevant user, for example, in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0025] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure. The enabling of the digital assistant related functions of the embodiments of the present disclosure, the data obtained, the processing and storage manner of the data, etc. should be authorized in advance by the user and other right subjects associated with the user, and should comply with the relevant laws and regulations, the agreement rules between the right subjects.

[0026] As used herein, the term “model” can learn a relationship between a corresponding input and output from training data, so that after training is completed, a corresponding output can be generated for a given input. The generation of a model can be based on a machine learning technique. Deep learning is a machine learning algorithm that processes an input and provides a corresponding output by using multiple layers of processing units. A neural network model is one example of a model based on deep learning. In this document, a “model” can also be referred to as a “machine learning model,” a “learning model,” a “machine learning network,” or a “learning network,” which are used interchangeably herein.

[0027] FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. The environment 100 involves an application management platform 110, which can support the creation of an application and / or the running of an application. In some embodiments, the part of the application management platform 110 for supporting the creation of an application can also be referred to as an application creation part. In some embodiments, the part of the application management platform 110 for supporting the running of an application can also be referred to as an application running part.

[0028] As shown, the application creation part can provide a creation and publishing environment of an application for a user 105. The user 105 can be referred to as an application creation user, creator. In some embodiments, the application creation part can be a low-code platform, which provides a toolset for the creation of an application. The application creation part can support the visual development of various types of applications, so that a developer can skip the process of manual coding, and accelerate the development cycle and cost of an application. The application creation part can support any appropriate platform for the user to develop one or more types of applications, which can include, for example, a platform based on application platform as a service (aPaaS). Such a platform can enable the user to efficiently develop an application, implement operations such as application creation, adjustment of application functions, etc.

[0029] The application creation part can be deployed locally at a terminal device of the user 105, and / or can be supported by a server device. For example, the terminal device of the user 105 can run a client of the application creation part, which can support the user to interact with the application creation part provided by the server. In the case where the application creation part is run locally at the terminal device of the user, the user 105 can directly interact with the local application creation part by using the terminal device. In the case where the application creation part is run at the server device, the server device can implement the service provision to the client run at the terminal device based on the communication connection between the server device and the terminal device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105, to output and / or receive information related to the creation of an application to / from the user 105.

[0030] In some embodiments, the application creation portion can be associated to a corresponding database in which data or information required by the application creation procedure supported by the application creation portion is stored. For example, the database can store code and description information corresponding to each functional module used to compose the application, etc. The application creation portion can also perform operations such as calling, adding, deleting, updating, etc. on the functional modules in the database. The database can also store operations executable on different functional blocks. Illustratively, in a scenario in which an application is to be created, the application creation portion can call corresponding functional blocks from the database to build the application.

[0031] In embodiments of the present disclosure, the user 105 can create a target application 120 on the application creation portion as needed and publish the target application 120. The target application 120 can be published to any suitable application running portion as long as the application running portion is capable of supporting the running of the target application 120. After publication, the target application 120 can be used for operation by one or more end users 145. The end users 145 can operate the target application 120 through associated terminal devices 146 and in turn interact with the application management platform 110. The end users 145 can be referred to as end users of the target application 120. In some embodiments, the target application 120 can include or be implemented as a digital assistant 122.

[0032] The digital assistant 122 can be configured to have the capability of intelligent conversation. In the example shown in the figure, the digital assistant 122 can be integrated within the target application 120 as a part of the target application 120 to assist in performing 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 type of application. In such examples, the digital assistant 122 and the target application 120 can be considered as the same application. The digital assistant 122 is provided to assist users in various task processing needs in different applications and scenarios. During interaction with the digital assistant 122, the user inputs an interaction message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 is capable of supporting the user to input a question in a natural language manner, and perform a task and provide a reply based on understanding of the natural language input and logical reasoning capability.

[0033] In some embodiments, the digital assistant 122 can interact with the end users 145 as contacts of the end users 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 users 145 in a one-on-one chat session with the end users 145. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0034] For each end user 145, the client of the application running part can present an interaction window 142 of the target application 120 or the digital assistant 122 in the client interface, for example, a conversation window with the digital assistant 122. The end user 145 can input a conversation message in the conversation window, and the target application 120 can determine a reply message of the digital assistant 122 based on the created configuration information and present the reply message to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 can include messages in multiple modalities, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0035] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each end user 145 and / or can be supported by the server device. For example, the terminal device of the end user 145 can run a client of the application running part, which can support the user's interaction with the application running part provided by the server. In the case where the application running part is run locally on the terminal device of the user, the end user 145 can directly interact with the local application running part using the terminal device. In the case where the application running part is run on the server device, the server device can implement service provision to the client running on the terminal device based on the communication connection between the terminal device. The application running part can present a corresponding application page to the end user 145 based on the operation of the end user 145 to output and / or receive information related to the use of the application to / from the end user 145.

[0036] 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 a model. During the creation or running of the target application 120, one or more models 155, for example, the capabilities of the model 155, can be invoked. In the target application 120, the digital assistant 122 can utilize the model 155 to understand the user input and provide a reply to the user based on the output of the model 155.

[0037] During the creation process, the testing of the target application 120 by the application management platform 110 needs to utilize the model 155 to determine that the running result of the target application 120 meets the expectation. During the running process, in response to different operation requests of the user of the target application 120, the application running part can need to utilize the model 155 to determine the response result to the user.

[0038] Although shown as being independent of the application management platform 110, one or more models 155 can run on the application management platform 110, or other remote servers. In some embodiments, the models 155 can be machine learning models, deep learning models, learning models, neural networks, etc. In some embodiments, the models can be based on language models (LMs). Language models can be capable of question answering by learning from a large corpus. The models 155 can also be based on other suitable models.

[0039] The application management platform 110 can run on a suitable electronic device. An electronic device here can be any type of device with computing capability, including an end device or a server device. An end device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices or any combination thereof. A 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, etc. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0040] It should be understood that the structure and functionality of the environment 100 are described for illustrative purposes only and without implying any limitation on the scope of the present disclosure. For example, although a single user is shown interacting with the application creation portion and a single user is shown interacting with the application running portion, in practice 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.

[0041] Currently, a user input from a user, i.e., a task execution request for a target application, is usually received in the target application. Taking an example where the user input contains a data analysis requirement, in the face of the user input, a structured query language (SQL) is usually used to retrieve the required information from a large amount of data. However, as the data analysis requirement becomes increasingly complex, such as the need for cross-time period comparison analysis, trend prediction, anomaly detection, and other tasks, the limitations of simply relying on SQL queries gradually emerge. For complex calculation problems such as same period and same period, if simply relying on SQL queries often cannot be completed. For an application, how to accurately understand the user's complex calculation problem and select the appropriate tool to solve the problem raised by the task execution request is worth exploring.

[0042] In embodiments of the present disclosure, an improved solution for task processing is provided. In the solution, a received user input is parsed to obtain a parsing result, the user input indicating a task execution request for a target application. A query instruction is generated based on the parsing result. In response to determining that a query result obtained by using the query instruction does not satisfy a specified condition, an analysis instruction is generated, the analysis instruction being used for analyzing the query result obtained by using the query instruction. In this way, first, a suitable query instruction is selected according to the parsing result of the user input, and the user's input corresponds to the task execution request sent by the user to the target application. In the case where it is determined that the query instruction cannot satisfy the specified condition, that is, in the case where it is determined that relying only on the query instruction is not the optimal solution, the analysis instruction can also be combined. The query result obtained by using the query instruction is analyzed, calculated, etc. by using the analysis instruction, so as to solve the problem raised by the task execution request in multiple ways.

[0043] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and various page designs can actually exist. Various graphical elements in the pages can have different arrangements and different visual representations, one or more of which can be omitted or replaced, and one or more other elements can also exist. Embodiments of the present disclosure are not limited in this respect.

[0044] The task management process described in embodiments of the present disclosure can be implemented in 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 examples below, for the sake of discussion, the application management platform is described from the perspective of the application management platform 110 shown in FIG. 1. The user interface presented by the application management platform 110 can be presented via the terminal device of the end user 145, and the application management platform 110 can receive user input via the terminal device of the end user 145. In some embodiments of the present disclosure, the end user 145 is an end user 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 user 105, and the application management platform 110 can also 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.

[0045] FIG. 2 shows a block diagram of a task processing process 200 according to some embodiments of the present disclosure. The task processing process can be implemented in the application management platform 110. The task processing process shown in FIG. 2 is described below in conjunction with FIG. 1.

[0046] As shown in FIG. 2, at block 201, the application management platform 110 parses the received user input to obtain a parsing result, the user input indicating a task execution request for the target application 120.

[0047] The user input can be natural language received in a session between the end user and the digital assistant. The user input is the task execution request for the target application 120. For example, the user input can be “a list of students who scored full marks in the math exam of the current class”, “the monthly sales proportion change of the A product last year”, etc. In addition, the session between the end user and the digital assistant usually includes explanations or exemplary descriptions of terms that can be involved in the task to be executed.

[0048] After the application management platform 110 receives the user input, the application management platform 110 can parse the user input. For example, the parsing can be completed by the application management platform 110 invoking the model 155 with the natural language processing capability of the model 155. The model 155 is also a target model. The model 155 can also be referred to as a machine learning model. By parsing the user input, a parsing result can be obtained. For example, the parsing can at least include completing a question raised by the task execution request and data required to solve the question.

[0049] Taking the user input “a list of students who scored full marks in the math exam of the current class” as an example, the application management platform 110 can determine that the question raised by the task execution request is to obtain a list of personnel. The required data is to obtain the math scores of all students in the current class in the final exam.

[0050] Taking the user input “the monthly sales proportion change of the A product last year” as an example, the application management platform 110 can determine that the question raised by the task execution request is sales comparison. The required data is to obtain the sales data of the A product in each month of last year, the sales data of all products in each month of last year, etc.

[0051] Referring to FIG. 3, FIG. 3 shows an example of an acquisition page 300 of data information according to some embodiments of the present disclosure. The page 300 includes a query content input area 301, a term set area 302, a dialogue record area 303, a reference prompt word area 304, and the like. Among them, the query content input area 301 can be used to receive user input of the end user 145. The term set area 302 can be used to receive terms. The terms include explanations or give examples of terms used by the user group of the target application. The dialogue record area 303 can be used to record the dialogue process between the end user 145 and the digital assistant, including query instructions and / or analysis instructions generated by the digital assistant 122, and the like. The reference prompt word area 304 can be used to receive reference prompt content. Through the reference prompt word, the digital assistant 122 can be provided with better guidance to help the digital assistant 122 better complete the user's task. That is, the content of the reference prompt word area 304 is that the model 155 can receive the role description of the end user 145 to the digital assistant 122, thereby completing the guidance to the digital assistant 122.

[0052] As shown in FIG. 2, at block 202, the application management platform 110 can generate a query instruction based on the parsing result.

[0053] The application management platform 110 can generate a query instruction corresponding to the parsing result according to the parsing result. For example, the parsing result is to obtain the mathematics scores of all students in the class for the final exam, and the application management platform 110 can generate a query instruction to obtain the mathematics scores of all students in the class for the final exam according to the known database, the table in the known database, and the column in the table, and the like. Similarly, for the parsing result of needing to obtain the sales data of A product in each month from January to December last year and the sales data of all products in each month from January to December last year, the application management platform 110 can generate a query instruction to obtain the sales of A product and the sales of all products according to the known database, the table in the known database, and the column in the table, and the like.

[0054] The management platform 110 can combine the user input as a token of the query instruction to be generated by means of the code compilation instruction of the model 155. In addition, the management platform 110 can input the parsing result and the interaction content with the user to the model 155 as context information. Finally, the management platform 110 can also input the database information such as the database name, the database access address, and the like to the model 155. Thus, the query instruction can be generated by means of the model 155. Exemplarily, the query instruction can be a SQL query statement.

[0055] As shown in FIG. 2, at block 203, the application management platform 110 generates an analysis instruction for analyzing the query result obtained by the query instruction in response to determining that the query result obtained by the query instruction does not satisfy the specified condition.

[0056] After generating the query instruction, the application management platform 110 can send the query instruction to the target application 120 to make the target application 120 execute the query instruction to obtain a query result. The application management platform 110 can determine whether the query result can solve the problem raised by the task execution request. The determination of the query result includes that the query result can solve the problem or the query result cannot solve the problem.

[0057] In combination with the aforementioned example that the user input is “a list of students who get full marks in the math exam of the current class”, the application management platform 110 can obtain the math scores of all students in the current class according to the obtained data. Then, the application management platform 110 determines that the query result cannot solve the problem. Further, if the application management platform 110 determines that the query result can be optimized by combining other query statements to obtain a list of students who get full marks in the math exam, it can be determined that the query result can solve the problem. For example, the query instruction can be used to filter out students who get full marks in math, and a list of students who get full marks in math can be obtained.

[0058] In combination with the aforementioned example that the user input is “the change of the sales proportion of product A in each month of last year”, if the sales data of product A in each month of the past 12 months and the sales data of all products in each month of the past 12 months are obtained, the application management platform 110 can determine that only the sales data cannot solve the problem of determining the change of the sales proportion. For example, if the application management platform 110 determines that no other query instruction can obtain the result of the change of the sales proportion, it can be determined that the query result cannot solve the problem.

[0059] If the application management platform 110 determines that the query result obtained by using the query instruction does not meet the specified condition, it means that the problem raised by the task execution request cannot be solved only by using the query instruction. In this case, the application management platform 110 can introduce an analysis instruction. If the advantage of the query instruction is to quickly obtain data, the advantage of the analysis instruction is to perform complex calculations on the data. For example, the problems of proportion, same period comparison, and period comparison, as well as data analysis problems, can all correspond to complex calculations. In the current embodiment, the code compilation of the query instruction and the analysis instruction can be completed by the application management platform 110 calling the model 155. The code compilation capability of the model 155 is used to save the process of manual code compilation.

[0060] In combination with the aforementioned example that the user input is “the change of the sales proportion of product A in each month of last year”, the analysis instruction can be configured by the application management platform 110 to calculate the sales proportion of product A in each month. In addition, the analysis instruction can also be configured by the application management platform 110 to obtain the change of the sales proportion of product A in each month according to the sales proportion in the past 12 months.

[0061] Through the analysis of the user input, first, the query instruction corresponding to the analysis result is matched. Secondly, the analysis instruction is introduced when it is determined that the query instruction does not meet the specified condition, and the analysis instruction and the query instruction are combined, on the one hand, the advantages of the query instruction in the data query efficiency are exerted, and on the other hand, the advantages of the analysis instruction in the data analysis aspect in coping with complex problems are exerted, so that the task execution request can be completed in combination with different schemes. In this way, the respective advantages of the query instruction and the analysis instruction can be fully exerted, so that the task processing is completed.

[0062] In some embodiments, the application management platform 110 can determine that the task execution request needs multiple execution steps based on the user input by using the target model. In response to the determination that the task execution request needs multiple execution steps, the task execution request is split into multiple sub-task requests as the analysis result.

[0063] As mentioned earlier, the application management platform 110 can call the model 155 to analyze the user input by using the natural language processing capability of the model 155. In combination with the aforementioned example that the user input is "the monthly sales proportion change of A product last year", the analysis result of the application management platform 110 is to obtain the monthly sales of A product from January to December last year, and to obtain the monthly sales of all products from January to December last year. Therefore, the application management platform 110 can determine that the task execution request needs multiple execution steps. For example, the first step is to obtain the monthly sales of A product from January to December last year. The second step is to obtain the monthly sales of all products from January to December last year. If further subdivided, the application management platform 110 can further subdivide the first step into 12 sub-steps, that is, each sub-step corresponds to obtaining the sales of A product in January last year. Similarly, the application management platform 110 can also subdivide the second step into 12 sub-steps, that is, each sub-step corresponds to obtaining the sales of all products in January last year.

[0064] For the sub-steps of the first step, the application management platform 110 can correspondingly generate 12 query instructions, each of which is configured to obtain the sales data of A product in one month. For the sub-steps of the second step, the application management platform 110 can also generate 12 query instructions, each of which is configured to obtain the sales data of all products in one month. Through the splitting of the task execution request, the complex problem can be split into multiple simple problems.

[0065] In some embodiments, the application management platform 110 can determine the data description of the data to be obtained based on the analysis result, the data description being used to indicate at least one of the terms and examples of the data to be obtained, and generate the query instruction based on the data description by using the target model.

[0066] As mentioned above, the resolution can be completed by the application management platform 110 invoking the model 155, and the resolution result is obtained by means of the natural language processing capability of the model 155. In one aspect, the resolution result is completed based on the user input and the natural language processing capability of the model 155, and thus the resolution result is usually unstructured. In another aspect, the query instruction represented by the SQL query statement is structured, and thus there can be a difference between the resolution result and the query instruction. Based on this, after obtaining the resolution result, the application management platform 110 can match the resolution result with the term examples received by the term set display area 302 by means of the natural language processing capability of the model 155, so as to take the matched terms as the data description of the data to be obtained.

[0067] In addition, after obtaining the resolution result, the application management platform 110 can also declare the examples of the data to be obtained based on the resolution result. The examples of the data to be obtained can be used to indicate the data format, data content, etc. of the data to be obtained. The examples of the data to be obtained can also be used as the data description of the data to be obtained.

[0068] After determining the data description of the data to be obtained, the model 155 can generate the query instruction in combination with the data description of the data to be obtained, so as to make the query instruction better fit the data obtaining requirement of the resolution result.

[0069] In some embodiments, after obtaining the query result obtained by the query instruction, the application management platform 110 can also add a data source identifier to the query result obtained by the query instruction, and the data source identifier is used to indicate the provenance of the query result in the source data.

[0070] After obtaining the query result obtained by the query instruction, the application management platform 110 can also add a data source identifier to the query result obtained by the query instruction. The data source identifier is used to indicate the provenance of the query result in the source data. Exemplarily, the data source identifier can be used to indicate the database name of the database, the table in the database, the column in the table, etc. information of the query result obtained by the query instruction.

[0071] The significance of adding the data source identifier is that the data authenticity can be annotated, and thus the false data without provenance can be avoided.

[0072] In some embodiments, determining that the query result obtained by the query instruction does not satisfy the specified condition comprises: in response to the query result obtained by the query instruction being unable to solve the problem raised by the task execution request, determining a reason, the reason being that the query instruction is incorrect in instruction category; in response to the reason indicating that the instruction category of the query instruction is correct, adjusting the query instruction to obtain an adjusted query instruction, the adjusting comprising one of replacing the query instruction and adding a new query instruction; and in response to the adjusting satisfying a preset adjustment procedure and the query result obtained by the adjusted query instruction still being unable to solve the problem raised by the task execution request, determining that the reason indicates that the instruction category of the query instruction is incorrect.

[0073] FIG. 4 shows a schematic diagram of a flow 400 of a task processing method. In combination with FIG. 4, after the query instruction is generated in block 401, the application management platform 110 needs to determine whether the query result obtained by the query instruction can solve the problem raised by the task execution request, that is, to perform the problem solving judgment. The query result judgment can include can solve or cannot solve.

[0074] If the query result is determined to be able to solve, it means that the generated query instruction is correct and does not need to be adjusted. Thus, in block 403, feedback can be performed to the terminal user 145, that is, to perform the feedback query instruction in the interaction window 142. Conversely, if the query result is determined to be unable to solve, the application management platform 110 needs to further determine the reason why the problem cannot be solved in block 404, that is, to perform the reason judgment whether the instruction category of the query instruction is incorrect. Generally, the reason why the problem cannot be solved can be classified as indicating that the instruction category of the query instruction is correct, but the query instruction needs to be adjusted; or the reason why the problem cannot be solved can be classified as the instruction category of the query instruction being incorrect. If it is determined that the reason why the problem cannot be solved is that the instruction category of the query instruction is correct, it means that the current query instruction needs to be adjusted, that is, to return to block 401. The adjustment can include replacing or adding a new query instruction.

[0075] Taking replacement as an example, if the result obtained by the query instruction generated based on the analysis result cannot solve the problem raised by the task execution request, the application management platform 110 can generate a new query instruction according to the actual situation. The new query instruction is used to replace the original query instruction to perform data query. The so-called actual situation can be the result analyzed according to the model 155, or can be an indication obtained after interaction with the terminal user 145. The specific process of obtaining the actual situation is not described here.

[0076] Taking adding a new query instruction as an example, in combination with the foregoing example of the user input being "a list of students in the class who scored full marks in the math final exam", the application management platform 110 can obtain the math scores of all students in the class for the math final exam. If the application management platform 110 determines that the query result obtained by using the query instruction cannot solve the problem raised by the task execution request, and the reason indicates that the instruction category of the query instruction is correct, a new query instruction can be added. The new query instruction can be to query the students who scored full marks in the math scores of all students in the class for the math final exam.

[0077] The preset adjustment process can be used to indicate the adjustment capability of the application management platform 110. For example, the adjustment capability can indicate the capability of the application management platform 110 to generate a new query instruction. If the capability of generating a new query instruction is to generate m (m is a positive integer) new query instructions, but the query result obtained by the newly generated m query instructions still cannot solve the problem raised by the task execution request, it can be determined that the reason indicating the instruction category of the query instruction is incorrect. Alternatively, the adjustment capability can indicate the number of adjustments. For example, after adjusting n times (n is a positive integer), the query result obtained by the query instruction still cannot solve the problem raised by the task execution request, and it can also be determined that the reason for being unable to solve the problem raised by the task execution request is that the instruction category of the query instruction is incorrect.

[0078] In the scenario where it is determined that the query result obtained by using the query instruction cannot solve the problem raised by the task execution request, and the reason is that the query instruction is not accurate or there is an omission, the query instruction can be adjusted to select a more suitable query instruction. Conversely, if the problem raised by the task execution request still cannot be solved after adjusting the query instruction, it can be determined that the problem cannot be solved by relying on the query instruction alone. Thus, the introduction of an analysis instruction can be triggered, so that the task execution request can be better completed.

[0079] In some embodiments, the application management platform 110 determining that the query result obtained by using the query instruction does not satisfy the specified condition further includes: in response to the reason indicating that the instruction category of the query instruction is incorrect, determining that the query result obtained by using the query instruction does not satisfy the specified condition.

[0080] For the case where the reason indicates that the instruction category of the query instruction is incorrect, it can be directly determined that the query result obtained by using the query instruction does not satisfy the specified condition. The determination of the application management platform 110 on the incorrect instruction category can be completed with the analysis capability of the model 155. For example, the analysis result and the query result obtained by the query instruction can be input to the model 155, and the model 155 can obtain the reason for being unable to solve the problem raised by the task execution request as the instruction category being incorrect.

[0081] In some embodiments, the application management platform 110 generates the analysis instruction, which can include: obtaining context information, the context information including at least one of the user input, the parsing result, the query instruction, the query result obtained by using the query instruction, and the reason why the query result fails to meet the specified condition, and generating the analysis instruction based on the context information.

[0082] Still referring to FIG. 4, at block 405, the application management platform 110 can generate the analysis instruction by using the model 155 to reference the context information. Illustratively, the application management platform 110 can obtain the context information, that is, obtain at least one of the user input, the parsing result of the user input, all the query instructions that have been selected, the query result corresponding to each query instruction, and the reason why the query result fails to meet the specified condition.

[0083] After obtaining the context information, the model 155 can determine the analysis instruction based on the context information. In combination with the aforementioned example that the user input is “the monthly sales proportion change of the A product last year”, after obtaining the user input, the parsing result, the query instruction, and the reason why the query instruction fails to solve the problem proposed in the task execution request, the application management platform 110 can perform analysis by using the model 155, so as to determine that the analysis instruction is needed to solve the problem. In addition, it can be determined that the analysis instruction can be configured to perform the proportion operation and configured to analyze the result of the proportion operation.

[0084] It is not difficult to understand that if the generated analysis instruction still cannot solve the problem proposed in the task execution request, the application management platform 110 can perform analysis by using the model 155, so as to adjust the analysis instruction. The adjustment target is that the adjusted analysis instruction can solve the problem proposed in the task execution request. For example, for the case of the sales proportion change, the first round of analysis instruction can determine the proportion data, but the proportion data cannot be equivalent to the proportion change. Therefore, the generation of the second round of analysis instruction can be performed, that is, according to the proportion of multiple statistical periods, the final analysis result of the proportion change is obtained.

[0085] Therefore, the problem can be solved through multiple rounds of analysis instructions. Still in combination with FIG. 4, at block 406, after determining the analysis instruction, the analysis instruction can be executed.

[0086] The analysis instruction can be compiled in any programming language that can complete the analysis task. The basic statements of the programming language include arithmetic operators, logical operators, etc., so it can easily handle complex problems such as comparison, cycle, and proportion. The code compilation process of the programming language can be completed with the code compilation capability of the model 155. FIG. 5 shows an example of a page 500 showing data results according to some embodiments of the present disclosure. In the query content display area 511, the user input can be displayed. In the data result display area 512, the data source involved in obtaining the final data result, the query instruction generated or used in the process of obtaining the final data result (query instruction generation), the analysis instruction generated or used in the process of obtaining the final data result (analysis instruction generation), and the final analysis result can be displayed.

[0087] In the embodiments of the present application, in the case that the data obtained only by the query instruction cannot solve the problem raised by the user, the analysis instruction can be introduced according to the communication with the user and the factual judgment conclusion in the communication process. The user's problem is solved by combining the analysis instruction with the query instruction.

[0088] In some embodiments, the prompt information is determined based on the context information, and the analysis instruction is generated based on the prompt information using the target model.

[0089] After obtaining the context information, the prompt information can be generated based on the context information. For example, the context information can be subjected to structured processing to obtain the prompt information. The structured processing can first determine the key fields, such as user input, parsing result, etc. Thereafter, corresponding contents are added to different key fields to obtain the prompt information. In the process of determining the key fields and / or adding the corresponding contents, text deduplication, simplified expression, etc. can also be included. After obtaining the prompt information, the model 155 can determine the analysis instruction based on the prompt information. That is, the model 155 performs natural language code compilation based on the prompt information to obtain the code of the corresponding analysis instruction.

[0090] In some embodiments, the application management platform 110 can further perform the following steps: storing the data result in a designated storage area, the data result including at least one of the query result obtained by the query instruction and the analysis result obtained by the analysis instruction; and representing the data result by the address of the storage area.

[0091] After the application management platform 110 obtains the data result by using the query instruction or the analysis instruction to process data, the application management platform 110 can store the data result in a specified storage area. For example, the specified area can be a cache area in a sandbox that executes the analysis instruction. After the data result is stored, the application management platform 110 can generate a storage identifier according to the address where the data result is stored. The storage identifier can be used to represent the data. Thus, when the application management platform 110 generates a new query instruction or an analysis instruction that needs to access data, the application management platform 110 can generate a storage identifier reading instruction, so as to read the data result stored in the specified storage area by using the storage identifier reading instruction.

[0092] Through the above process, the data access between different instructions is only through the storage identifier, so that the data amount of the token involved in the code compilation of the model 155 when the application management platform 110 calls the model 155 to compile the query instruction and the analysis instruction can be reduced. That is, when the code is compiled, all the data to be obtained does not need to be listed by the token, but only the data to be read can be represented by the address of the storage area. In the case where the context window data amount of the model 155 is limited, the resource consumption of the model can be greatly reduced.

[0093] In some embodiments, the application management platform 110 can also execute the analysis instruction to obtain an analysis result. Executing the analysis instruction includes: sending the analysis instruction and information related to the query result to an instruction execution environment, and obtaining the analysis result output by the instruction execution environment, the analysis result being obtained by processing the query result based on the analysis instruction.

[0094] The analysis instruction can be run in an instruction execution environment. For example, the instruction execution environment can be a sandbox environment, a sandbox environment, and the like. That is, the application management platform 110 can send the code corresponding to the analysis instruction and the query result required by the analysis instruction to the instruction execution environment. In combination with the previous example, for the query result required by the analysis instruction, the address of the storage area corresponding to the query result can be sent to the instruction execution environment. Thus, in the instruction execution environment, the corresponding query result is obtained based on the address of the storage area.

[0095] The analysis instruction is run in the instruction execution environment to process the query result, so as to obtain the analysis result. The analysis result can be sent by the instruction execution environment to a specified storage area. The analysis result stored in the specified storage area can be a final analysis result. Alternatively, the analysis result can be directly displayed on the user interface of the application management platform 110.

[0096] FIG. 6 illustrates a schematic structural block diagram of a task processing apparatus 600 according to some embodiments of the present disclosure. The apparatus 600 may, for example, be implemented in or included in the application management platform 110. Various modules / components in the apparatus 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0097] As shown, the apparatus 600 includes a parsing module 601 configured to parse a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; a query instruction generation module 602 configured to generate a query instruction based on the parsing result; and an analysis instruction generation module 603 configured to generate an analysis instruction for analyzing a query result obtained by the query instruction, in response to determining that the query result obtained by the query instruction does not satisfy a specified condition.

[0098] In some embodiments, the parsing module 601 is further configured to include: an execution step identification submodule configured to determine, based on the user input, that the task execution request requires a plurality of execution steps, by using a target model; and a splitting submodule configured to split, as the parsing result, the task execution request into a plurality of subtask requests, in response to determining that the task execution request requires the plurality of execution steps.

[0099] In some embodiments, the query instruction generation module 602 is further configured to determine, based on the parsing result, a data specification of data to be obtained, the data specification being used to indicate at least one of a term and an example of the data to be obtained; and generate the query instruction based on the data specification, by using the target model.

[0100] In some embodiments, the apparatus 600 further includes a data source identification adding module configured to add a data source identification to the query result obtained by the query instruction, the data source identification being used to indicate a provenance of the query result in source data.

[0101] In some embodiments, the analysis instruction generation module 603 is further configured to include: a cause determination submodule configured to determine a cause, in response to the query result obtained by the query instruction being unable to solve a problem raised by the task execution request, the cause being a reason why the query result is unable to solve the problem raised by the task execution request; a query instruction adjustment submodule configured to adjust the query instruction to obtain an adjusted query instruction, in response to the cause indicating that an instruction category of the query instruction is correct, the adjustment including one of replacing the query instruction and adding a new query instruction; and an instruction category error determination submodule configured to determine that the instruction category of the query instruction is incorrect, in response to the adjustment satisfying a preset adjustment procedure and the query result obtained by the adjusted query instruction still being unable to solve the problem raised by the task execution request.

[0102] In some embodiments, the instruction category error determination submodule is further configured to, in response to the reason indicating that the instruction category of the query instruction is erroneous, determine that the query result obtained by using the query instruction does not satisfy the specified condition.

[0103] In some embodiments, the analysis instruction generation module 603 is further configured to obtain context information, the context information comprising at least one of the user input, the parsing result, the query instruction, the query result obtained by using the query instruction, and the reason why the query result does not satisfy the specified condition; and generate the analysis instruction based on the context information.

[0104] In some embodiments, the analysis instruction generation module 603 is further configured to determine the prompt information based on the context information, and generate the analysis instruction based on the prompt information by using the target model.

[0105] In some embodiments, the apparatus 600 further comprises a data representation module configured to store the data result in a specified storage area, the data result comprising at least one of the query result obtained by using the query instruction and the analysis result obtained by using the analysis instruction; and represent the data result by using the stored address.

[0106] In some embodiments, the apparatus 600 further comprises an analysis instruction running module configured to: send the analysis instruction and the information related to the query result to an instruction execution environment; and obtain the analysis result output by the instruction execution environment, the analysis result being obtained by processing the query result based on the analysis instruction.

[0107] FIG. 7 illustrates a block diagram of an electronic device 700 in which one or more embodiments of the disclosure can be implemented. It should be understood that the electronic device 700 illustrated in FIG. 7 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 700 illustrated in FIG. 7 can include or be implemented as the application management platform 110 of FIG. 1, or the apparatus 600 of FIG. 6.

[0108] As shown in FIG. 7, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 can include, but are not limited to, one or more processors 710 or processing units, 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 processor 710 can be an actual or virtual processor and is capable of performing various processing according to programs stored in the memory 720. In a multi-processor system, multiple processors perform computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 700.

[0109] The electronic device 700 typically includes a plurality of computer storage media. Such media can be volatile and / or nonvolatile, removable and / or non-removable, and can be implemented in any method or technology for storage of information and / or data. The memory 720 can be volatile (such as random access memory (RAM)), non-volatile (such as read-only memory (ROM), flash memory, or any other memory technology), or some combination of the multiple memory types. The storage device 730 can be a removable storage medium or a non-removable storage medium implemented in any method or technology for storage of information and / or data.

[0110] The electronic device 700 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 7, a disk drive or other computer-readable media drive can be provided for reading from or writing to a removable, non-removable, volatile, or non-volatile computer-readable medium. In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 720 can include a computer program product 725 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0111] The communication unit 740 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating with one another over a communication connection. As such, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes.

[0112] The input device 750 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 760 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 740, as needed, one or more devices that enable a user to interact with the electronic device 700, or any device (e.g., a network card, a modem, etc.) that enables the electronic device 700 to communicate with one or more other electronic devices. Such communication can be enabled by an input / output (I / O) interface (not shown).

[0113] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0114] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0115] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium. The instructions stored on the computer readable storage medium can be used to program a computer, a programmable data processing apparatus, and / or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0116] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0117] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray Disc, hard disk, or memory stick, can also be used to implement the present disclosure. The computer program product of the present disclosure can also be provided as a service to download and use the computer program over a network, such as the Internet.

[0118] Having described several implementations of the present disclosure, it will be clear to those skilled in the art that many modifications, additions, and substitutions are possible without departing from the scope and spirit of the described implementations. Many modifications and variations of the present disclosure are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims, the present disclosure can be practiced otherwise than as specifically described. While the present disclosure has been described with reference to the implementation figures, it will be understood by those skilled in the art that various changes can be made and equivalents can be substituted for elements thereof without departing from the scope of the present disclosure. In addition, many modifications can be made to adapt a particular situation or material to the teachings of the disclosure without departing from its scope. Therefore, it is contemplated to cover any and all adaptations and modifications falling within the scope of the appended claims. It should also be noted that, in this document, the term "can" is used to mean various possible constructions, for example, a structure, device, or apparatus can be configured to perform one or more functions.

Claims

1.A task processing method, comprising: parsing a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; generating a query instruction based on the parsing result; and in response to determining that a query result obtained by using the query instruction does not satisfy a specified condition, generating an analysis instruction for analyzing the query result obtained by using the query instruction. 2.The method of claim 1, wherein the parsing the received user input comprises: determining, by using a target model, that the task execution request requires a plurality of execution steps based on the user input; and in response to determining that the task execution request requires the plurality of execution steps, splitting the task execution request into a plurality of sub-task requests as the parsing result. 3.The method of claim 1, wherein the generating the query instruction based on the parsing result comprises: determining, based on the parsing result, a data specification of to-be-acquired data, the data specification being used to indicate at least one of a term and an example of the to-be-acquired data; and generating, by using a target model, the query instruction based on the data specification. 4.The method of claim 1, further comprising: adding a data source identifier to the query result obtained by using the query instruction, the data source identifier being used to indicate a provenance of the query result in source data. 5.The method of claim 1, wherein the determining that the query result obtained by using the query instruction does not satisfy the specified condition comprises: in response to the query result obtained by using the query instruction being unable to solve a problem raised by the task execution request, determining a reason for being unable to solve the problem raised by the task execution request; in response to the reason indicating that an instruction category of the query instruction is correct, adjusting the query instruction to obtain an adjusted query instruction, the adjusting comprising one of replacing the query instruction and adding a new query instruction; and in response to the adjustment satisfying a preset adjustment procedure and the query result obtained by using the adjusted query instruction still being unable to solve the problem raised by the task execution request, determining that the reason indicates that the instruction category of the query instruction is incorrect. 6.The method of claim 5, wherein the determining that the query result obtained by using the query instruction does not satisfy the specified condition further comprises: in response to the reason indicating that the instruction category of the query instruction is incorrect, determining that the query result obtained by using the query instruction does not satisfy the specified condition. 7.The method of any one of claims 1 to 6, wherein the generating the analysis instruction comprises: obtaining context information, the context information comprising at least one of the user input, the parsing result, the query instruction, the query result obtained by using the query instruction, and the reason for the query result not satisfying the specified condition; and generating the analysis instruction based on the context information. 8.The method of claim 7, wherein the generating the analysis instruction based on the context information comprises: determining prompt information based on the context information; and ​ ​ ​ ​ ​ ​ The analysis instruction is generated based on the prompt information using a target model. 9.The method of any one of claims 1-6, further comprising: storing a data result in a designated storage area, the data result comprising at least one of a query result obtained by the query instruction and an analysis result obtained by the analysis instruction; and characterizing the data result using the stored address. 10.The method of claim 1, further comprising: sending information related to the analysis instruction and the query result to an instruction execution environment; and obtaining an analysis result output by the instruction execution environment, the analysis result being obtained based on processing the query result by the analysis instruction. 11.A task processing apparatus, comprising: a parsing module configured to parse a received user input to obtain a parsing result, the user input indicating a task execution request for a target application; a query instruction generation module configured to generate a query instruction based on the parsing result; and an analysis instruction generation module configured to generate an analysis instruction in response to determining that a query result obtained by the query instruction does not satisfy a specified condition, the analysis instruction being used to analyze the query result obtained by the query instruction. 12.An electronic device, comprising: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, causing the electronic device to perform the method of any one of claims 1-10. 13.A computer-readable storage medium having stored thereon computer-executable instructions that are executable by a processor to implement the method of any one of claims 1-10. 14.A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method of any one of claims 1-10.

Images