WO2026001059A1 - 任务处理方法、装置、设备和计算机可读存储介质 - Google Patents

任务处理方法、装置、设备和计算机可读存储介质

Info

Publication number
WO2026001059A1
WO2026001059A1 PCT/CN2025/080067 CN2025080067W WO2026001059A1 WO 2026001059 A1 WO2026001059 A1 WO 2026001059A1 CN 2025080067 W CN2025080067 W CN 2025080067W WO 2026001059 A1 WO2026001059 A1 WO 2026001059A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
subtask
request
target
user input
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/080067
Other languages
English (en)
French (fr)
Inventor
黄巍
马进
楼宇泽
王磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Publication of WO2026001059A1 publication Critical patent/WO2026001059A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/041—Abduction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the exemplary embodiments disclosed herein relate generally to the field of computers, and more particularly to task processing methods, apparatus, devices, and computer-readable storage media.
  • terminal devices can provide people with a variety of services in work and life. Applications providing these services can be deployed on these terminal devices.
  • the terminal devices present relevant content and interact with users through the application's user interface to meet various user needs. In some cases, users may initiate task processing requests within the application. Therefore, how to better achieve the goals of task processing requests is a key concern.
  • a task processing method includes: parsing received user input to obtain a parsing result, wherein the user input indicates a task execution request for a target application, and the parsing result indicates multiple subtask requests corresponding to the task execution request; determining the data requirements of each subtask request among the multiple subtask requests; and, in response to obtaining target data based on the data requirements, invoking a specified function to process the subtask request.
  • a task processing apparatus comprising: a parsing module configured to parse received user input to obtain a parsing result, wherein the user input indicates a task execution request for a target application, and the parsing result indicates multiple subtask requests corresponding to the task execution request; a query instruction generation module configured to determine the data requirements of a subtask request among the multiple subtask requests; and an analysis instruction production module configured to, in response to obtaining target data based on the data requirements, invoke a specified function to process the subtask request.
  • an electronic device in a third aspect of this disclosure, includes 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. When executed by the at least one processor, the instructions cause the electronic device to perform the method of the first aspect.
  • a computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the method of the first aspect.
  • 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.
  • Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented
  • Figure 2 shows a block diagram of a task processing procedure according to some embodiments of the present disclosure
  • Figure 3 illustrates a schematic diagram of a task processing procedure according to some embodiments of the present disclosure
  • Figure 4 shows a schematic diagram of a page displaying the results according to some embodiments of the present disclosure
  • FIGS. 5A to 5C illustrate schematic diagrams of example interfaces showing some embodiments of the present disclosure
  • Figure 6 shows a schematic structural block diagram of a task processing apparatus according to some embodiments of the present disclosure
  • Figure 7 shows a block diagram of an electronic device that can implement one or more embodiments of the present disclosure.
  • performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.
  • relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users.
  • relevant users may include any type of rights holder, such as individuals, enterprises, and groups.
  • a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.
  • a prompt message in response to a user's active request, can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format.
  • the pop-up window can also include a selection control allowing the user to choose "agree” or "disagree” to provide information to the electronic device.
  • Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented.
  • Environment 100 relates to an application management platform 110, which can support application creation and/or application execution.
  • the portion of the application management platform 110 used to support application creation may also be referred to as an application creation portion.
  • the portion of the application management platform 110 used to support application execution may also be referred to as an application execution portion.
  • the application creation section provides an environment for user 105 to create and publish applications.
  • User 105 can be referred to as the application creation user or creator.
  • the application creation section can be a low-code platform that provides a collection of tools for application creation.
  • the application creation section can support visual development of various types of applications, allowing developers to skip the manual coding process and accelerate the application development cycle and reduce costs.
  • the application creation section can support any suitable platform for users to develop one or more types of applications, such as an application platform as a service (aPaaS) based platform.
  • aPaaS application platform as a service
  • Such a platform enables users to efficiently develop applications, enabling operations such as application creation and application function adjustment.
  • the application creation component can be deployed locally on user 105's terminal device and/or supported by a server-side device.
  • user 105's terminal device can run a client with the application creation component, which can support interaction between the user and the application creation component provided by the server.
  • the application creation component runs locally on the user's terminal device
  • user 105 can directly interact with the local application creation component using the terminal device.
  • the server-side device can provide services to the client running on the terminal device based on the communication connection with the terminal device.
  • the application creation component can present a corresponding page 130 to user 105 based on user 105's actions, to output and/or receive application creation-related information from user 105.
  • the application creation section may be associated with a corresponding database, which stores the data or information required for the application creation process supported by the application creation section.
  • the database may store the code and description information corresponding to the various functional modules that make up the application.
  • the application creation section can also perform operations such as calling, adding, deleting, and updating the functional modules in the database.
  • the database may also store operations that can be performed on different functional blocks. For example, in a scenario where an application needs to be created, the application creation section can call the corresponding functional blocks from the database to build the application.
  • user 105 can create and publish target application 120 as needed in the application creation section.
  • Target application 120 can be published to any suitable application runtime section, as long as the application runtime section can support the operation of target application 120.
  • target application 120 can be operated by one or more end users 145.
  • End user 145 can operate target application 120 through an associated terminal device 146 and thereby interact with application management platform 110.
  • End user 145 can be referred to as the end user of target application 120.
  • target application 120 may include or be implemented as digital assistant 122.
  • Digital assistant 122 can be configured to have intelligent conversational capabilities.
  • digital assistant 122 can be integrated into target application 120, serving as part of target application 120 to assist in task processing within target application 120.
  • digital assistant 122 can be configured as a standalone application, such as a web application or other type of application.
  • digital assistant 122 and target application 120 can be considered as the same application.
  • Digital assistant 122 is provided to assist users with various task processing needs in different applications and scenarios.
  • the user inputs interactive messages, and digital assistant 122 responds to the user's input by providing reply messages.
  • digital assistant 122 can support users inputting questions in natural language and performs tasks and provides replies based on its understanding of natural language input and logical reasoning capabilities.
  • the digital assistant 122 can interact with the end user 145 as a contact.
  • the digital assistant 122 can be implemented in an instant messaging (IM) application.
  • IM instant messaging
  • the digital assistant 122 can interact with the end user 145 in a one-on-one chat session.
  • the digital assistant 122 can interact with multiple users in a group chat session that includes multiple users.
  • the client of the application runtime portion can present an interaction window 142 of the target application 120 or digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122.
  • the end user 145 can enter conversation messages in the conversation window, and the target application 120 can determine the response message from the digital assistant 122 based on the created configuration information and present it to the user in the interaction window 142.
  • the interaction messages with the target application 120 can include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and so on.
  • the application runtime component can be deployed locally on each end user's (145's) terminal device and/or supported by a server device.
  • the end user's (145's) terminal device can run a client with the application runtime component, which can support interaction between the user and the application runtime component provided by the server.
  • the application runtime component runs locally on the user's terminal device
  • the end user (145) can directly interact with the local application runtime component using the terminal device.
  • the server device can provide services to the client running on the terminal device based on the communication connection with the terminal device.
  • the application runtime component can present corresponding application pages to the end user (145) based on the user's (145's) actions, outputting and/or receiving application-related information from the user (145).
  • the implementation of at least some functions of the target application 120, and/or the implementation of at least some functions of the digital assistant 122 within the target application 120 may be based on models.
  • one or more models 155 may be invoked, such as the capabilities of model 155.
  • the digital assistant 122 may utilize model 155 to understand user input and provide responses to the user based on the output of model 155.
  • the application management platform 110 needs to use model 155 to test the target application 120 to determine whether the running results of the target application 120 meet expectations.
  • the application operation part may need to use model 155 to determine the response results to users.
  • model 155 may run on the application management platform 110 or other remote servers.
  • model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc.
  • the model may be based on a language model (LM).
  • LM language model
  • Model 155 may also be based on other suitable models.
  • the application management platform 110 can run on suitable electronic devices. These electronic devices can be any type of computing-capable device, including terminal devices or server devices. Terminal devices 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 system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio/video players, digital cameras/camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.
  • Server devices can include, for example, computing systems/servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on. In some embodiments, the management platform 110 can be implemented based on cloud services.
  • target applications typically receive user input, which consists of task execution requests.
  • user input which consists of task execution requests.
  • the task is usually completed well. For instance, if the user input is "use line charts and bar charts to reflect last month's sales,” it contains clear instructions for creating line and bar charts, leading to a high degree of completion.
  • the technology struggles to complete the task. For example, if the user input is "analyze last month's sales,” the technology will usually only provide sales data. In other words, the technology lacks sufficient recognition capabilities and the ability to solve problems from multiple perspectives. Therefore, for target applications, accurately understanding the user's desired outcome and providing solutions from various angles is a topic worth exploring.
  • This disclosure provides an improved task processing scheme.
  • received user input is parsed to obtain a parsing result, with the user input indicating a target application.
  • the data requirements of that subtask request are determined.
  • a specified function is invoked to process the subtask request.
  • the user input is parsed to identify multiple subtask requests, each of which can correspond to a solution for the user input.
  • personalized data requirements are determined for each subtask request; that is, the data for each subtask can be the same as or different from the data for other subtasks.
  • the solution for the first subtask might select 1000 data points, while the solution for the second subtask might involve 1000 data points.
  • the data between the two subtasks might be the same data, or they might overlap, or they might not overlap.
  • the second subtask might involve the maximum, minimum, or average value of the 1000 data points required by the first subtask.
  • the second subtask might involve data beyond the 1000 data points required by the first subtask. In other words, data acquisition is for the purpose of better solving the problem corresponding to the user input.
  • each subtask request can execute the task according to the specified function.
  • the specified function can be different functions of the target application 120, such as the function of editing data charts, generating data analysis reports, etc.
  • this embodiment can generate multiple solutions based on user input, and each solution will have corresponding data. This allows for a better solution to the problem corresponding to the user input.
  • the task management process described in the embodiments of this disclosure can be implemented on an application management platform, a terminal device with the application management platform installed, and/or a server corresponding to the application management platform.
  • the description is from the perspective of the application management platform, such as the application management platform 110 shown in FIG1.
  • the user interface presented by the application management platform 110 can be presented via the terminal device of end user 145, and the application management platform 110 can receive user input via the terminal device of end user 145.
  • end user 145 is the end user of the target application 120.
  • the user interface presented by the application management platform 110 can also be presented via the terminal device of user 105, and the application management platform 110 can also receive user input via the terminal device of user 105.
  • user 105 is the creator, manager, or maintainer of the target application 120.
  • FIG. 2 shows a block diagram of a task processing procedure 200 according to some embodiments of the present disclosure. This task processing procedure can be implemented on an application management platform 110. The task processing procedure shown in Figure 2 will be described below with reference to Figure 1.
  • the application management platform 110 parses the received user input and obtains the parsing result.
  • the user input indicates a task execution request for the target application, and the parsing result indicates multiple sub-task requests corresponding to the task execution request.
  • End user 145 can perform interactive actions in the interaction window 142, such as text input and voice input.
  • User input can be natural language received in the interaction window 142.
  • User input is a task execution request for the target application 120. For example, user input could be "analyze the sales performance of product A in the last quarter", “predict the market performance of product B", and so on.
  • Figure 3 illustrates a schematic diagram of a task processing procedure 300 according to some embodiments of the present disclosure.
  • the application management platform 110 can parse the user input. Exemplarily, parsing can be accomplished by the application management platform 110 calling model 155, leveraging the natural language processing capabilities of model 155.
  • model 155 obtains a parsing result by parsing the user input. The parsing result can be used to indicate multiple subtask requests corresponding to the task execution request.
  • the parsed results can include presenting sales data in the form of a bar chart, presenting sales percentage in the form of a pie chart, and displaying month-on-month sales changes in the form of a bar chart combined with a line chart.
  • Different formats correspond to sub-task requests. That is, in this example, the parsed results can determine the goal of analyzing the sales performance of product A in the previous quarter in three ways. These three methods can be independent of each other; that is, each method can independently address the goal of analyzing the sales performance of product A in the previous quarter from its own problem-solving perspective.
  • the parsed results indicate that the task execution request corresponds to three sub-task requests.
  • the above user input and parsed results are for illustrative purposes only, and the actual situation is not limited to this.
  • the application management platform 110 determines the data requirements of a subtask request among multiple subtask requests.
  • the data requirements can typically be different; these will be referred to as subtasks below.
  • the application management platform 110 can determine that the data requirement for the first subtask is the sales data of product A over several past quarters.
  • the application management platform 110 can determine that the data requirement for the second subtask is the sales data of product A in the previous quarter, as well as the sales data of several other products (from the same manufacturer) in the previous quarter.
  • the application management platform 110 can determine that the data requirement for the third subtask is the sales data of product A over several past quarters, as well as the sales data of several other products (from the same manufacturer) over several past quarters.
  • the application management platform 110 can use the code compilation instructions of model 155 to combine user input as tokens for the generated query instructions. Furthermore, the management platform 110 can input parsing results and user interaction content as context information into model 155. Finally, the management platform 110 can also input database information, such as database name and database access address, into model 155.
  • the query instructions for retrieving target data can be generated using model 155.
  • the query instructions can be Structured Query Language (SQL) query statements.
  • the application management platform 110 responds to the acquisition of target data based on data requirements by calling the specified function to process the subtask request.
  • the application management platform 110 can obtain three sets of target data for the three sub-task requests. After obtaining the three sets of target data, the application management platform 110 can invoke the specified functions to process each sub-task request.
  • the three sub-task requests in the aforementioned example are requests to generate charts based on user input. Therefore, when the application management platform 110 calls the specified function, it can correspondingly call the function to generate editable data charts.
  • the function to generate editable data charts can include functions such as generating pie charts, bar charts, line charts, or combination charts. It is easy to understand that the above charts are merely illustrative and do not limit the actual situation.
  • the application management platform 110 can call various functions related to user input based on user input. For example, if the user input is "predict the market performance of product B", then, for example, the specified function determined by the application management platform 110 could be the function of generating editable data charts, or it could be a digital human broadcast function, an editable text report generation function, etc.
  • This application's embodiments overcome the limitation of interpreting user input from a single dimension by parsing it to determine multiple sub-task requests corresponding to the task execution request. For different sub-task requests, suitable target data can be selected. Finally, a specified function is invoked to complete the execution of multiple sub-tasks. Therefore, diverse problem-solving approaches can be provided, and each approach uses more suitable data. This solution better addresses problems related to user input.
  • the application management platform 110 parses the received user input, including: determining multiple solutions to the task execution request based on the user input; adding a reasoning identifier to each solution, the reasoning identifier being used to indicate the reason for determining the solution; and generating a subtask request corresponding to each solution.
  • the application management platform 110 calls the model 155 to complete the understanding of the text input by the user, it can generate multiple solutions for the task execution request based on the task execution request of the target application.
  • the application management platform 110 can add an inference identifier, thereby using the inference identifier to explain why the application management platform 110 selected that solution approach.
  • the inference label added by the application management platform 110 can be "compare the sales of the previous quarter with the sales of the two previous quarters to show the changes in sales".
  • the inference label added by the application management platform 110 can be "Compare the sales of similar products B and C, etc., and show the market share of product A".
  • the inference label added by the application management platform 110 can be "on the one hand, to intuitively compare the sales of the previous quarter, and on the other hand, to introduce the sales change trend for dynamic comparison".
  • the application management platform 110 can also add a character limit to the inference identifier. If the number of characters in the generated inference identifier exceeds the preset character threshold, the application management platform 110 can also summarize the generated inference identifier to complete the character compression.
  • the application management platform 110 can generate subtask requests based on the solution approach with added inference identifiers. In other words, it breaks down the single task execution request corresponding to the user input into multiple subtask execution requests.
  • the application management platform 110 can also display the solutions with added inference tags in a designated display area; and in response to a received adjustment instruction, perform an adjustment action corresponding to the adjustment instruction, wherein the adjustment instruction is for at least one solution with added inference tags.
  • FIG4 illustrates an example of a page 400 displaying data information according to some embodiments of the present disclosure.
  • User input can be displayed in the query content interaction area 411.
  • the solution interaction area 412 multiple solution paths determined based on user input and their reasoning identifiers can be displayed.
  • the solution interaction area 412 can also serve as an interaction window to receive adjustment instructions from the end user 145 regarding the solution paths.
  • the adjustment command may include a deletion command.
  • end user 145 determines that the solution corresponding to recommended chart 1 is inappropriate and there is no way to modify the foreground, they can directly issue an adjustment command to "delete recommended chart 1".
  • the application management platform 110 can directly delete the solution based on the deletion command.
  • adjustment instructions may include modification instructions.
  • the reasoning label in Recommendation Chart 3 states, "Compare the sales volume of similar products B and C to analyze the market share of product A.”
  • Modification instructions could include, “Comparison of product B is unnecessary,” “Add the product with the highest current market sales for comparison,” or "Besides market share, can we add new comparison dimensions?”
  • the application management platform 110 can update the solutions corresponding to Recommendation Chart 3 based on the modification instructions.
  • adjustment instructions may also include addition instructions. For instance, if end user 145 has devised a better solution than the existing one, they can directly issue instructions such as, "Can we combine recommended chart 1 and recommended chart 2?" or "Add another deviation chart, including the growth amount and growth rate.” Thus, application management platform 110 can expand the solution based on addition instructions.
  • the application management platform 110 can generate corresponding adjustment actions for adjustment commands. Finally, it determines the target of the adjustment action and applies the action to the target, thus optimizing the solution.
  • the solution can be improved by interacting with end user 145 to optimize the execution effect of task execution requests.
  • the method by which the application management platform 110 determines the data requirements of a subtask request includes: determining data filtering conditions based on the target of the obtained subtask request; generating a data query instruction based on the data filtering conditions; and using the result obtained by executing the data query instruction as the target data.
  • Each subtask request has a corresponding objective.
  • the objective is to display the sales data of the previous quarter. Therefore, the application management platform 110 can determine that the corresponding filter condition is to query the sales data of product A in the previous quarter from the database. Based on this, the application management platform 110 generates a query instruction to retrieve the sales data of product A in the previous quarter, according to the known database, the tables in the known database, and the columns in the tables.
  • the goal is to show the sales percentage of product A.
  • the application management platform 110 can then determine that the corresponding filtering condition is to query the database for the sales data of product A, as well as the sales data of other products (similar or competing products).
  • the sales data for other products besides product A can be the total (e.g., the sum of sales of products B, C, and D), or it can be retrieved sequentially based on product category (e.g., sequentially retrieving sales data for products B, C, and D).
  • the result obtained from executing the query command can be used as the target data obtained in response to the data requirements.
  • the application management platform 110 may determine the data requirements of a subtask request in the following ways: in response to the fact that the result obtained from the data query instruction cannot complete the target, a data analysis instruction is generated, which is configured to perform data analysis processing on the result obtained from the execution of the data query instruction to obtain the analysis processing result; and the analysis processing result is used as the target data.
  • the goal is to display sales data from the previous quarter.
  • the application management platform 110 can determine that the data query command corresponding to the goal will retrieve the sales data for product A from the database for the previous quarter. After obtaining this result, the application management platform 110 can determine whether the retrieved target data can fulfill the goal of displaying the previous quarter's sales data. If the goal can be fulfilled, then the sales data for product A from the database for the previous quarter can be used as the target data. Conversely, if the goal cannot be fulfilled, the application management platform 110 can generate an analysis command. This analysis command processes the data obtained from the data query command, producing an analysis result, which is then used as the target data.
  • the goal is to display the sales percentage of product A.
  • the application management platform 110 can determine that the filtering condition corresponding to the goal is to query the sales data of product A from the database, along with the sales data of other products besides product A. After obtaining this result, the application management platform 110 can determine whether the obtained data can achieve the goal of displaying the sales percentage of product A.
  • displaying sales percentage requires not only sales data but also percentage calculation. Therefore, the application management platform 110 can determine that the result obtained from the data query instruction cannot achieve the goal of displaying the sales percentage of product A.
  • the application management platform 110 needs to generate a data analysis instruction.
  • the data analysis instruction is configured to calculate the ratio between the sales of product A and the total sales of other products, including product A. If the result of the ratio calculation can achieve the goal of displaying the sales percentage of product A, then the result of the ratio calculation can be used as the target data. Conversely, if the ratio calculation still fails to achieve the goal of displaying the sales percentage of product A, the application management platform 110 can adjust the analysis instructions or add new ones so that the analysis results obtained from executing the adjusted instructions can achieve the sub-task request's goal. In other words, if the ratio calculation still fails to achieve the goal of displaying the sales percentage of product A, the application management platform 110 can set up multiple rounds of analysis instructions. Each round can refer to the results of previous rounds and the identified reasons for failing to achieve the goal, thereby ultimately achieving the sub-task request's goal through multiple rounds of analysis instructions.
  • the application management platform 110 can simultaneously utilize analysis commands and query commands to achieve the goals of subtask requests. If the advantage of query commands is rapid data retrieval, then the advantage of analysis commands lies in their ability to perform complex calculations on the data. For example, percentage-based, year-on-year, and month-on-month comparisons can all be addressed with complex calculations. Analysis commands can be compiled using a suitable programming language. The basic statements of programming languages include arithmetic and logical operators, thus easily handling complex problems such as year-on-year comparisons, month-on-month comparisons, and percentage-based calculations. In this current embodiment, the compilation of query and analysis commands can be completed by the application management platform 110 calling model 155. Utilizing the code compilation capabilities of model 155 saves the manual code compilation process.
  • the application management platform 110 may also perform data optimization processing on the results obtained from executing data query instructions, including at least one of data cleaning and data bit adjustment.
  • Data optimization processing may include at least one of data cleaning and data bit adjustment.
  • meaningless data can be cleaned.
  • meaningless data can be unidentifiable data, null data, or data with a value of 0, etc.
  • the application management platform 110 can adjust the decimal place value based on the results obtained from a data query command.
  • the adjustment can include rounding the data to the nearest whole number, retaining one decimal place.
  • the application management platform 110 may also add a data source identifier to the target data, which is used to indicate the source of the target data.
  • the application management platform 110 can also add a data source identifier to the result.
  • the data source identifier is used to indicate the origin of the result.
  • the data source identifier can be used to indicate information such as the database name, the table in the database, and the columns in the table from which the result of the query originates.
  • the application management platform 110 can also use the data source identifier of the object being analyzed and calculated as the data source identifier corresponding to the result of the analysis and calculation.
  • the significance of adding data source identifiers is that it allows for the labeling of data authenticity, thereby avoiding false data without a source.
  • the application management platform 110 may call a specified function to process each subtask request, specifically by calling a data chart generation function to generate a data chart based on each subtask request and the target data corresponding to that subtask request.
  • the presentation style of the data chart is editable.
  • the function to be called is the function to generate editable data charts, as an example.
  • the application management platform 110 can generate editable data charts based on subtask requests and the target data corresponding to the subtask requests by calling the editable data chart function supported by the target application 120.
  • the function of editing data charts can be implemented based on a domain-specific language (DSL).
  • DSL can be a scripting language specifically for chart generation, which can complete the generation and rendering of the chart corresponding to the subtask according to the target of the subtask and the target data of the subtask.
  • FIG5A shows an example of page 500 of the bar chart results corresponding to the subtask request processed by calling the specified function according to some embodiments of the present disclosure.
  • FIG5A sales data of product A in the past three quarters are shown in the form of a bar chart.
  • FIG5B shows an example of page 510 of the pie chart results corresponding to the subtask request processed by calling the specified function according to some embodiments of the present disclosure.
  • the sales percentage of product A in the previous quarter is shown in the form of a pie chart.
  • Figure 5C illustrates an example of page 520 showing the bar chart combined with a line chart result corresponding to a request to invoke a specified function processing subtask according to some embodiments of this disclosure.
  • Figure 5C shows the month-on-month change in sales volume of product A compared to the sales volume of other products, displayed in the form of a bar chart combined with a line chart.
  • the data chart presentation style in page 520 is editable; for example, the font, font size, color, and other presentation styles in the data charts are all editable.
  • the application management platform 110 may also store the target data in a designated storage area. Furthermore, invoking a designated function to process the subtask request includes providing the address of the designated storage area to the designated function.
  • the application management platform 110 can store the results in a designated storage area.
  • This designated area can be a cache area within a programming language sandbox.
  • the application management platform 110 can generate a storage identifier based on the address where the query results are stored. This storage identifier can be used to represent the data. Therefore, when the application management platform 110 calls a subtask request to generate a new query command or when a generated analysis command requires data access, it can first generate a storage address identifier and then use the storage identifier to read the query results stored in the designated storage area.
  • the results obtained from executing analysis commands can also be stored in a designated storage area, and a storage identifier can be generated based on the address where the analysis command results are stored.
  • Figure 6 shows a schematic structural block diagram of a task processing apparatus 600 according to some embodiments of the present disclosure.
  • the apparatus 600 may be implemented in or included in an application management platform 110, for example.
  • the various modules/components in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.
  • device 600 includes a parsing module 601, configured to parse received user input to obtain a parsing result.
  • the user input indicates a task execution request for a target application, and the parsing result indicates multiple sub-task requests corresponding to the task execution request.
  • a data requirement determination module 602 is configured to determine the data requirements of a sub-task request among the multiple sub-task requests.
  • a sub-task request processing module 603 is configured to, in response to obtaining target data based on the data requirements, call a specified function to process the sub-task request.
  • the parsing module 601 is further configured to include a solution path determination submodule, which is configured to determine multiple solutions to a task execution request based on user input; an identifier addition submodule, which is configured to add a reasoning identifier to each solution path, the reasoning identifier indicating the reason for determining the solution path; and a subtask request generation module, which is configured to generate a subtask request corresponding to each solution path.
  • a solution path determination submodule which is configured to determine multiple solutions to a task execution request based on user input
  • an identifier addition submodule which is configured to add a reasoning identifier to each solution path, the reasoning identifier indicating the reason for determining the solution path
  • a subtask request generation module which is configured to generate a subtask request corresponding to each solution path.
  • the device 600 is further configured to include a solution path display module, which is configured to display solutions with added inference tags in a designated display area; and a solution path adjustment module, which is configured to perform an adjustment action corresponding to a received adjustment instruction, the adjustment instruction being for at least one solution path with added inference tags.
  • a solution path display module which is configured to display solutions with added inference tags in a designated display area
  • a solution path adjustment module which is configured to perform an adjustment action corresponding to a received adjustment instruction, the adjustment instruction being for at least one solution path with added inference tags.
  • the data requirement determination module 602 is configured to include a filtering condition determination submodule, which is configured to determine data filtering conditions based on the target of the obtained subtask request; a data query instruction generation submodule, which is configured to generate a data query instruction based on the data filtering conditions; and to use the result obtained by executing the data query instruction as the target data.
  • a filtering condition determination submodule which is configured to determine data filtering conditions based on the target of the obtained subtask request
  • a data query instruction generation submodule which is configured to generate a data query instruction based on the data filtering conditions; and to use the result obtained by executing the data query instruction as the target data.
  • the data requirement determination module 602 is configured to further include an analysis instruction generation submodule, which is configured to generate a data analysis instruction in response to the result obtained from the data query instruction being unable to achieve the target.
  • the data analysis instruction is configured to perform data analysis processing on the result obtained from executing the data query instruction to obtain the analysis processing result; and use the analysis processing result as the target data.
  • the data requirement determination module 602 is configured to perform data optimization processing on the results obtained from executing a data query instruction, the data optimization processing including at least one of data cleaning and data bit adjustment.
  • the apparatus 600 further includes a data source identifier adding module, which is configured to add a data source identifier to the target data, the data source identifier being used to indicate the origin of the target data.
  • the subtask request processing module 603 is specifically configured to invoke the data chart generation function to generate a data chart based on each subtask request and the target data corresponding to that subtask request.
  • the presentation style of the data chart is editable.
  • the apparatus 600 further includes a target data characterization module configured to store target data in a designated storage area. Invoking a designated function to process the subtask request includes providing the address of the designated storage area to the designated function.
  • Figure 7 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 the electronic device 700 shown in Figure 7 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein.
  • the electronic device 700 shown in Figure 7 may include or be implemented as the application management platform 110 of Figure 1, or the device 600 of Figure 6.
  • the electronic device 700 is in the form of a general-purpose electronic device.
  • Components of the electronic device 700 may 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 may be a physical or virtual processor and is capable of performing various processes according to programs stored in the memory 720. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 700.
  • Electronic device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media.
  • Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof.
  • Storage device 730 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and/or data and can be accessed within electronic device 700.
  • Electronic device 700 may further include additional removable/non-removable, volatile/non-volatile storage media.
  • disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided.
  • each drive may be connected to a bus (not shown) via one or more data media interfaces.
  • Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.
  • the communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, 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 node.
  • PCs network personal computers
  • Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc.
  • Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc.
  • Electronic device 700 can also communicate with one or more external devices (not shown) via communication unit 740 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 700, or with any device that enables electronic device 700 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input/output (I/O) interface (not shown).
  • I/O input/output
  • a computer-readable storage medium that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above.
  • a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.
  • These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions/actions specified in one or more blocks of the flowchart and/or block diagram.
  • These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and/or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions/actions specified in one or more blocks of the flowchart and/or block diagram.
  • Computer-readable program instructions can 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 data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions/actions specified in one or more boxes of a flowchart and/or block diagram.
  • each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function.
  • the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Stored Programmes (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开的实施例提供了任务处理方法、装置、设备和计算机可读存储介质。该方法包括：对接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用的任务执行请求，解析结果指示任务执行请求对应的多个子任务请求。针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。

Description

任务处理方法、装置、设备和计算机可读存储介质
本申请要求2024年6月27日递交的、标题为“任务处理方法、装置、设备和计算机可读存储介质”、申请号为202410853011.8的中国发明专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开的示例实施例总体涉及计算机领域，特别地涉及任务处理方法、装置、设备和计算机可读存储介质。
背景技术
随着信息技术的发展，各种终端设备可以在工作和生活等方面向人们提供各种服务。终端设备中可以部署有提供服务的应用。终端设备通过应用的用户界面呈现相应的内容并实现与用户之间的交互，满足用户的各类需求。在一些情况下，用户可能在应用内发起任务处理请求。因此，如何更好的达成任务处理请求的目标是所关注的问题。
发明内容
在本公开的第一方面，提供了一种任务处理方法。该方法包括：对接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用的任务执行请求，解析结果指示任务执行请求对应的多个子任务请求。针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。
在本公开的第二方面，提供了一种任务处理装置，包括：解析模块，被配置为对接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用的任务执行请求，解析结果指示任务执行请求对应的多个子任务请求。查询指令生成模块，被配置为针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。分析指令生产模块，被配置为响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。
在本公开的第三方面，提供了一种电子设备。该设备包括至少一个处理器；以及至少一个存储器，至少一个存储器被耦合到至少一个处理器并且存储用于由至少一个处理器执行的指令。指令在由至少一个处理器执行时使电子设备执行第一方面的方法。
在本公开的第四方面，提供了一种计算机可读存储介质。介质上存储有计算机可执行指令，计算机可执行指令被处理器执行时实现第一方面的方法。
在本公开的第五方面，提供了一种计算机程序产品。该计算机程序产品被有形地存储在计算机存储介质中并且包括计算机可执行指令,该计算机可执行指令在由设备执行时使设备执行第一方面的方法。
应当理解，该部分中所描述的内容并非旨在限定本公开的实施例的关键特征或重要特征，也不用于限制本公开的范围。本公开的其他特征将通过以下的描述而变得容易理解。
附图说明
结合附图并参考以下详细说明，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。在附图中，相同或相似的附图标记表示相同或相似的元素，其中：
图1示出了能够在其中实现本公开的实施例的示例环境的示意图；
图2示出了根据本公开的一些实施例的任务处理过程的框图；
图3示出了根据本公开的一些实施例的任务处理过程的示意图；
图4示出了根据本公开的一些实施例的展示结果的页面的示意图；
图5A至图5C示出了根据本公开的一些实施例的图表展示示例界面的示意图；
图6示出了根据本公开的一些实施例的任务处理装置的示意性结构框图；
图7示出了可以实现本公开的一个或多个实施例的电子设备的框图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中示出了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
在本公开的实施例的描述中，术语“包括”及其类似用语应当理解为开放性包含，即“包括但不限于”。术语“基于”应当理解为“至少部分地基于”。术语“一个实施例”或“该实施例”应当理解为“至少一个实施例”。术语“一些实施例”应当理解为“至少一些实施例”。下文还可能包括其他明确的和隐含的定义。
在本文中，除非明确说明，“响应于A”执行一个步骤并不意味着在“A”之后立即执行该步骤，而是可以包括一个或多个中间步骤。
可以理解的是，本技术方案所涉及的数据(包括但不限于数据本身、数据的获得、使用、存储或删除)应当遵循相应法律法规及相关规定的要求。
可以理解的是，在使用本公开各实施例公开的技术方案之前，均应当根据相关法律法规通过适当的方式对本公开所涉及信息的类型、使用范围、使用场景等告知相关用户并获得相关用户的授权，其中，相关用户可以包括任何类型的权利主体，例如个人、企业、团体。
例如，在响应于接收到用户的主动请求时，向相关用户发送提示信息，以明确地提示相关用户，其请求执行的操作将需要获得和使用到相关用户的信息，从而使得相关用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供信息。
作为一种可选的但非限制性的实现方式，响应于接收到相关用户的主动请求，向相关用户发送提示信息的方式，例如可以是弹窗的方式，弹窗中可以以文字的方式呈现提示信息。此外，弹窗中还可以承载供用户选择“同意”或“不同意”向电子设备提供信息的选择控件。
可以理解的是，上述通知和获得用户授权过程仅是示意性的，不对本公开的实现方式构成限定，其他满足相关法律法规的方式也可应用于本公开的实现方式中。本公开实施例数字助手相关功能的启用、获取的数据、数据的处理和存储方式等，均应获得用户、以及与用户关联的其他权利主体的提前授权，并应符合相关法律法规、权利主体间协议规则的约定。
如本文中所使用的，术语“模型”可以从训练数据中学习到相应的输入与输出之间的关联关系，从而在训练完成后可以针对给定的输入，生成对应的输出。模型的生成可以基于机器学习技术。深度学习是一种机器学习算法，通过使用多层处理器来处理输入和提供相应输出。神经网络模型是基于深度学习的模型的一个示例。在本文中，“模型”也可以被称为“机器学习模型”、“学习模型”、“机器学习网络”或“学习网络”，这些术语在本文中可互换地使用。
图1示出了本公开的实施例能够在其中实现的示例环境100的示意图。环境100涉及应用管理平台110，其可以支持应用的创建和/或应用的运行。在一些实施例中，应用管理平台110中用于支持应用创建的部分也可以称为应用创建部分。在一些实施例中，应用管理平台110中用于支持应用运行的部分也可以称为应用运行部分。
如图所示，应用创建部分可以为用户105提供应用的创建和发布环境。用户105可以被称为应用创建用户、创建者。在一些实施例中，应用创建部分可以是低代码平台，其提供应用创建的工具合集。应用创建部分可以支持对各类应用的可视化开发，从而使开发人员可以跳过手工编码的过程，加快应用的开发周期和成本。应用创建部分可以支持用户开发一个或多个类型的应用的任何适当平台，例如可以包括基于应用平台即服务(aPaaS)的平台。这样的平台能够支持用户对应用进行高效开发，实现应用创建、应用功能调整等操作。
应用创建部分可以被部署在用户105的终端设备本地，和/或可以由服务端设备来支持。例如，用户105的终端设备可以运行有应用创建部分的客户端，该客户端可以支持用户与服务端所提供的应用创建部分的交互。在应用创建部分运行在用户的终端设备本地的情况下，用户105可以直接利用终端设备与本地的应用创建部分进行交互。在应用创建部分运行在服务端设备的情况下，服务端设备可以基于与终端设备之间的通信连接，实现对终端设备中运行的客户端的服务供应。应用创建部分可以基于用户105的操作而向用户105呈现相应的页面130，以向用户105输出和/或从用户105接收与应用创建相关的信息。
在一些实施例中，应用创建部分可以关联到相应的数据库，其中存储应用创建部分所支持的应用创建过程所需的数据或信息。例如，数据库可以存储用于组成应用的各个功能模块对应的代码和描述信息等。应用创建部分还可以对数据库中的功能模块执行调用、增加、删除、更新等操作。数据库还可以存储对不同功能块可执行的操作。示例性的，在要创建应用的场景，应用创建部分可以从数据库中调用相应的功能块来搭建应用。
在本公开的实施例中，用户105可以在应用创建部分上根据需要创建目标应用120，并发布目标应用120。目标应用120可被发布到任一适当的应用运行部分，只要应用运行部分能够支持目标应用120的运行。在发布后，目标应用120可以用于由一个或多个终端用户145进行操作。终端用户145可以通过相关联的终端设备146来操作目标应用120，并进而与应用管理平台110进行交互。终端用户145可以被称目标应用120的终端用户。在一些实施例中，目标应用120可以包括或者被实现为数字助手122。
数字助手122可以被配置为具有智能对话的能力。在图所示的示例中，数字助手122可以被集成在目标应用120内，作为目标应用120的一部分来协助执行目标应用120内的任务处理。在其他示例中，数字助手122可以被配置为独立运行的应用，例如网页应用或其他类型的应用。在这样的示例中，数字助手122与目标应用120可以被视为同一应用。数字助手122被提供用于协助用户在不同应用、场景下的各类任务处理需求。在与数字助手122的交互过程中，用户输入交互消息，并且数字助手122响应于用户输入来提供回复消息。通常，数字助手122能够支持用户以自然语言方式输入提问，并基于对自然语言输入的理解和逻辑推理能力来执行任务和提供回复。
在一些实施例中，数字助手122可以作为终端用户145的联系人与之交互。例如，数字助手122可以被实现在即时消息(IM)应用中。数字助手122可以在与终端用户145的单聊会话中与终端用户145交互。在一些实施例中，数字助手122可以在包括多个用户的群聊会话中与多个用户交互。
对于每个终端用户145，应用运行部分的客户端可以在客户端界面中呈现目标应用120或数字助手122的交互窗口142，例如与数字助手122的会话窗口。终端用户145可以在会话窗口中输入会话消息，目标应用120可以基于所创建的配置信息，来确定数字助手122的回复消息并在交互窗口142中呈现给用户。在一些实施例中，取决于目标应用120的配置，与目标应用120的交互消息可以包括多模态形式的消息，诸如文本消息(例如，自然语言文本)、语音消息、图像消息、视频消息，等等。
与应用创建部分类似，应用运行部分可以被部署在每个终端用户145的终端设备本地，和/或可以由服务端设备来支持。例如，终端用户145的终端设备可以运行有应用运行部分的客户端，该客户端可以支持用户与服务端所提供的应用运行部分的交互。在应用运行部分运行在用户的终端设备本地的情况下，终端用户145可以直接利用终端设备与本地的应用运行部分进行交互。在应用运行部分运行在服务端设备的情况下，服务端设备可以基于与终端设备之间的通信连接，实现对终端设备中运行的客户端的服务供应。应用运行部分可以基于终端用户145的操作而向终端用户145呈现相应的应用页面，以向终端用户145输出和/或从终端用户145接收与应用使用相关的信息。
在一些实施例中，目标应用120的至少部分功能的实现，和/或目标应用120中的数字助手122的至少部分功能的实现可以基于模型来实现。在目标应用120的创建或运行过程中，可以调用一个或多个模型155，例如模型155的能力。在目标应用120中，数字助手122可以利用模型155来理解用户输入，并基于模型155的输出来提供对用户的回复。
在创建过程中，应用管理平台110对目标应用120的测试需要利用模型155来确定目标应用120的运行结果符合预期。在运行过程中，响应于目标应用120的用户的不同操作请求，应用运行部分可能需要利用模型155来确定对用户的响应结果。
虽然被示出为独立于应用管理平台110，但一个或多个模型155可以运行在应用管理平台110上，或者其他远端服务器。在一些实施例中，模型155可以是机器学习模型、深度学习模型、学习模型、神经网络等。在一些实施例中，模型可以基于语言模型(LM)。语言模型通过从大量语料中学习，能够具备问答能力。模型155也可以基于其他适当的模型。
应用管理平台110可以运行在适当的电子设备。这里的电子设备可以是任何类型的具有计算能力的设备，包括终端设备或服务端设备。终端设备可以是任何类型的移动终端、固定终端或便携式终端，包括移动手机、台式计算机、膝上型计算机、笔记本计算机、上网本计算机、平板计算机、媒体计算机、多媒体平板、个人通信系统(PCS)设备、个人导航设备、个人数字助理(PDA)、音频/视频播放器、数码相机/摄像机、定位设备、电视接收器、无线电广播接收器、电子书设备、游戏设备或者前述各项的任何组合，包括这些设备的配件和外设或者其任何组合。服务端设备例如可以包括计算系统/服务器，诸如大型机、边缘计算节点、云环境中的计算设备，等等。在一些实施例中，管理平台110可以基于云服务来实现。
应当理解，仅出于示例性的目的描述环境100的结构和功能，而不暗示对于本公开的范围的任何限制。例如，虽然图示出了与应用创建部分交互的单个用户和与应用运行部分交互的单个用户，但实际上可以多个用户访问应用管理平台110来各自创建数字助手，并且每个数字助手可以被用于与多个用户进行交互。
目前，在目标应用中通常会接收到用户的用户输入，也就是针对目标应用的任务执行请求。以用户输入包含数据分析需求为示例，面对用户输入是有明确指令的情况，通常可以较好的完成。例如用户输入是“利用折线图和柱状图反应上个月的销量”，包含明确的折线图和柱状图指令，由此在执行时会有较好的完成度。但如果用户输入是比较模糊的情况，相关技术便比较难完成。例如，如果用户输入是“分析一下上个月的销量情况”，那么相关技术通常只会得到一个销量数据。也就是说，相关技术缺乏足够的识别能力以及多维度的解决问题的能力。对于目标应用120而言，如何能够准确理解用户期望的目标，并且从不为角度给出解决方案，是值得探讨的。
在本公开实施例中，提供了一种任务处理的改进方案。在该方案中，对接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用。针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。通过此种方式，首先对用户输入进行解析，以确定出多个子任务请求，每个子任务请求便可以对应一种应对用户输入的解决方案。其次，对每子任务请求确定出个性化的数据需求，也就是说每个子任务的数据可以是和其他子任务相同，也可以是不相同的。例如一共有5000条数据，第一个子任务对应的解决方案可能会选择其中的1000条数据，而第二个子任务对应的解决方案可能涉及到其中的1000条数据。两个子任务之间的数据可能是同一份数据，或者可能会存在交集，也可能不存在交集。例如，第二个子任务可能涉及到第一个子任务所需1000条数据中的最大值、最小值或者平均值等数据。也可能第二个子任务涉及到的数据是第一个子任务所需的1000条数据以外的其他数据等。也就是说，数据的获取是为了子任务更好的解决用户输入所对应的问题的。每个子任务请求在获取到目标数据以后，便可以根据调用的指定功能进行任务执行。指定功能可以是目标应用120所具有的不同功能，例如可以是编辑数据图表的功能，生成数据分析播报的功能等。最终，本申请实施例可以根据用户输入生成多种解决方案，并且每种解决方案都会有适配的数据。从而可以更好的解决用户输入所对应的问题。
以下将参考附图的示例来详细描述本公开的一些示例实施例。应当理解，附图中示出的页面仅仅是示例，实际可以存在各种页面设计。页面中的各个图形元素可以具有不同的布置和不同的视觉表示，其中的一个或多个元素可以省略或被替换，并且还可以存在一个或多个其他元素。本公开的实施例在此方面不受限制。
本公开的实施例所描述的任务管理过程可以被实现在应用管理平台，安装有应用管理平台的终端设备和/或应用管理平台对应的服务端。在下文的示例中，出于讨论的需要，从应用管理平台的角度来描述，例如图1所示的应用管理平台110。应用管理平台110所呈现的用户界面，可以经由终端用户145的终端设备被呈现，并且应用管理平台110可以经由终端用户145的终端设备来接收用户输入。在本公开的一些实施例中，终端用户145为目标应用120的终端用户。应当理解，应用管理平台110所呈现的用户界面，也可以经由用户105的终端设备被呈现，并且应用管理平台110也可以经由用户105的终端设备来接收用户输入。在本公开的一些实施例中，用户105为目标应用120的创建者、管理者或维护者。
图2示出了根据本公开的一些实施例的任务处理过程200的框图。该任务处理过程可以在应用管理平台110被实施。以下结合图1来描述图2示出的任务处理过程。
如图2所示，在框201，应用管理平台110对接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用的任务执行请求，解析结果指示任务执行请求对应的多个子任务请求。
终端用户145可以在交互窗口142进行交互动作，例如可以包括文字输入、语音输入等。用户输入可以是在交互窗口142接收到的自然语言。用户输入为针对目标应用120的任务执行请求。例如，用户输入可以是“分析A款商品上个季度的销量情况”、“预测B款商品的市场表现”，等等。
图3示出了根据本公开的一些实施例的任务处理过程300的示意图，结合图3所示，在框301，应用管理平台110接收到用户输入301后，可以对用户输入进行解析。示例性地，解析可以通过应用管理平台110调用模型155，借助模型155的自然语言处理能力完成。在框302，模型155通过对用户输入进行解析，可以得到解析结果。解析结果可以用于指示任务执行请求对应的多个子任务请求。
以用户输入301是“分析A款商品上个季度的销量情况”为示例，解析结果可以包括采用柱状图的形式呈现销量数据，采用饼状图的形式呈现销量占比，采用柱状图结合折线图的形式展示销量环比变化数据等。不同的形式即可对应子任务请求。也就是说，当前示例中，解析结果可以得出以3种方式完成A款商品上个季度的销量情况的分析这个目标。3种方式可以是彼此独立的，也就是说，3种方式均可以以各自独立的解决问题的角度完成A款商品上个季度的销量情况的分析这个目标。以解析结果为3种方式完成A款商品上个季度的销量情况的分析这个目标为示例，则解析结果指示任务执行请求对应的子任务请求便是3个。以上用户输入和解析结果仅为示例性说明，实际情况并不限于此。
如图2所示，在框202，应用管理平台110针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。
对于多个子任务请求中的每个子任务请求而言，数据需求通常可以是不同的，后文简称为子任务。仍然以前述用户输入是“分析A款商品上个季度的销量情况”的解析结果为示例。对于柱状图的形式所对应的第一个子任务，结合图3所示，在框303，应用管理平台110可以确定第一个子任务的数据需求是过往多个季度A款商品的销售数据。对于饼状图的形式所对应的第二个子任务，应用管理平台110可以确定第二个子任务的数据需求是上个季度A款商品的销售数据，以及(同厂家的)其它几款商品在上个季度的销量数据。对于柱状图叠加折线图的形式所对应的第三个子任务，应用管理平台110可以确定第三个子任务的数据需求是过往多个季度A款商品的销售数据，以及过往多个季度(同厂家的)其它几款商品的销量数据。
应用管理平台110可以借助模型155的代码编译指令，将结合用户输入作为待生成的查询指令的词元(token)。此外，管理平台110可以向模型155输入解析结果以及与用户的交互内容等作为上下文信息。最终，管理平台110还可以向模型155输入数据库信息，例如数据库名称、数据库访问地址等。由此，可以借助模型155生成获取目标数据的查询指令。示例性地，查询指令可以是结构化查询语言(Structured Query Language，SQL)查询语句。
通过上述过程不难发现，即便是同一个数据库，不同子任务请求的数据需求可能也是不同的。子任务请求的数据需求和子任务的目标具有较强的关联性。由此可知，在当前实施例中，即便源数据是同一个数据库，也可以基于源数据的不同切片达成不同子任务请求对应的目标。
如图2所示，在框203，应用管理平台110响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。
仍然以前述用户输入是“分析A款商品上个季度的销量情况”的示例，针对3个子任务请求，应用管理平台110可以获取到3份目标数据。得到3份目标数据之后，应用管理平台110即可调用指定功能，对每个子任务请求进行处理。
前述示例中的3个子任务请求为根据用户输入得出可以生成图表的请求，因此应用管理平台110在调用指定功能时便可对应调用生成可编辑数据图表的功能。仍然结合图3所示，在框304，生成可编辑数据图表的功能可以包括如生成饼图、柱状图、折线图或者是组合图等功能。不难理解，以上图表只是示例性说明，并不对实际情况进行限定。
利用生成可编辑数据图表的功能对子任务请求进行处理。最终，结合图3所示，在框305，通过执行可编辑数据图表的渲染，生成最终的可编辑数据图表。不难理解，虽然当前实施例中指定功能是与图表生成相关的生成可编辑数据图表的功能。在实际场景中应用管理平台110可以基于用户输入，调用与用户输入相关的各类功能。例如，用户输入是“预测B款商品的市场表现”，那么示例性地，应用管理平台110确定的指定功能可以是可编辑数据图表的功能，也可以是数字人播报功能、可编辑文字报告生成功能等。
通过本申请实施例，可以克服对用户输入的单一维度解读，通过解析用户输入以确定出任务执行请求对应的多个子任务请求。针对不同子任务请求，可以选择适合该子任务请求的目标数据。最终调用指定功能完成多个子任务的执行。由此，可以提供多元化的解决问题的途径，并且每个解决问题的途径所采用的数据是更适合的。通过上述方案，可以更好的解决用户输入所对应的问题。
在一些实施例中，应用管理平台110对接收到的用户输入进行解析包括：基于用户输入，确定任务执行请求的多个解决途径；为每个解决途径添加推理标识，推理标识用于指示确定该解决途径的原因；分别生成与每个解决途径对应的子任务请求。
应用管理平台110在调用模型155完成对用户输入的文字理解后，可以基于对目标应用的任务执行请求，生成任务执行请求的多个解决途径。
仍然以前述用户输入是“分析A款商品上个季度的销量情况”的解析结果为示例，解析结果得出以3种方式完成A款商品上个季度的销量情况的分析这个目标。3种方式也就对应着3个解决途径。
对于每种解决途径，应用管理平台110可以添加推理标识，从而利用推理标识解释说明应用管理平台110选择该解决途径的原因。
以采用柱状图的形式呈现销量数据为示例，应用管理平台110添加的推理标识可以是“将上季度销量和此前两个季度的销量放在一起比较，显示销量变化”。
以采用饼状图的形式呈现销量占比为示例，应用管理平台110添加的推理标识可以是“对比同类型的B款商品和C款商品等的销量，显示A款商品的市场占比”。
以采用柱状图结合折线图的形式展示销量环比变化数据为示例，应用管理平台110添加的推理标识可以是“一方面直观比较上季度销量，另一方面引入销量变化趋势，进行动态比较”。
更进一步的，应用管理平台110还可以对推理标识增加字数限制。如果生成的推理标识的字数超过预设的字数阈值，应用管理平台110还可以对生成的推理标识进行概况总结，从而完成推理标识的字数压缩。
最终，应用管理平台110可以基于添加推理标识后的解决途径，生成子任务请求。也就是完成将用户输入所对应的单一任务执行请求拆分成多个子任务执行请求。
在一些实施例中，应用管理平台110还可以执行在指定展示区域展示已添加推理标识的解决途径；响应于接收到的调整指令，执行与调整指令对应的调整动作，调整指令是针对至少一个已添加推理标识的解决途径的。
参考图4，图4示出了根据本公开的一些实施例的展示数据信息的页面400的示例。在查询内容交互区域411可以显示出用户输入。在解决途径交互区域412，一方面可以显示出根据用户输入确定出的多个解决途径，以及该途径的推理标识。另一方面，解决途径交互区域412可以作为交互窗口，接收终端用户145对解决途径的调整指令。
示例性地，调整指令可以包括删除指令。例如，终端用户145确定推荐图表1对应的解决途径是不合适的，没有修改前景的，可以直接下达“删除推荐图表1”的调整指令。由此，应用管理平台110可以根据删除指令直接将该解决途径删除。
示例性地，调整指令可以包括修改指令。例如，在推荐图表3的推理标识记载有“对比同类型的B款商品和C款商品的销量，分析A款商品的市场占比”。修改指令可以是“不需要比较B款商品”、“增加目前市场销量最高的商品进行比对”、“除了市场占比，能不能再增加新的对比维度”等。由此，应用管理平台110可以根据修改指令对推荐图表3对应的解决途径进行更新。
示例性地，调整指令还可以包括增加指令。例如，终端用户145针对现有的解决途径想到了更优的解决途径，可以直接下达如：“能不能将推荐图表1和推荐图表2结合”，或者“再增加一个偏差图，把增长额和增长率也加进来”。由此，应用管理平台110可以根据增加指令进行解决途径的扩充。
应用管理平台110针对调整指令，可以生成与调整指令对应的调整动作。最终，确定调整动作的调整对象，从而将调整动作作用到对应的调整对象上，也就将调整动作作用于与其匹配的解决途径上，对该解决途径进行优化调整。
通过上述过程，可以通过与终端用户145进行交互的方式对解决途径进行完善，以优化对于任务执行请求的执行效果。
在一些实施例中，应用管理平台110对于子任务请求的数据需求的确定方式包括：基于获取到的子任务请求的目标，确定数据筛选条件；基于数据筛选条件，生成数据查询指令；将执行数据查询指令得到的结果作为目标数据。
每一个子任务请求，都有其对应的目标。以采用柱状图的形式呈现销量数据为示例，其目标是展示上一季度的销量数据。那么应用管理平台110可以确定与目标对应的筛选条件便是从数据库中查询A款商品在上季度的销量数据。基于此，应用管理平台110则根据已知数据库、已知数据库中的表以及表中的列等信息，生成获取A商品在上季度的销量数据的查询指令。
同理，以采用饼状图的形式呈现销量占比为示例，其目标是展示A款商品的销量占比。那么应用管理平台110可以确定与目标对应的筛选条件便是从数据库中查询A款商品的销量数据，以及除A款商品外的其他(同类型或竞品)商品的销量数据。除A款商品外的其他商品的销量数据可以是总数(例如B款商品、C款商品和D款商品的销量总和)，也可以是根据商品的类别，依次获取其它款商品的销量数据(例如依次获取B款商品的销量数据、C款商品的销量数据和D款商品的销量数据)。
在生成查询指令后，根据执行查询指令得到的结果即可作为响应于基于数据需求所获取到的目标数据。
通过上述过程，即可完成针对不同子任务请求的个性化数据获取。最终目的是使得每个子任务请求都可以完成对应的目标。
在一些实施例中，应用管理平台110对于子任务请求的数据需求的确定方式还可以是：响应于数据查询指令得到的结果无法完成目标，生成数据分析指令，数据分析指令被配置为对执行数据查询指令得到的结果进行数据分析处理，得到分析处理结果；将分析处理结果作为目标数据。
仍然以采用柱状图的形式呈现销量数据为示例，其目标是展示上一季度的销量数据。那么应用管理平台110可以确定与目标对应的数据查询指令得到的结果是从数据库中查询A款商品在上季度的销量数据。获取到该结果后，应用管理平台110可以对获取到的目标数据能否完成展示上一季度的销量数据的目标进行判断。如果判断可以完成目标，那么从数据库中查询A款商品在上季度的销量数据便可以作为目标数据。反之，如果判断结果为不能完成目标，那么应用管理平台110可以生成分析指令。通过分析指令对执行数据查询指令得到的结果进行数据分析处理，得到分析处理结果，并以分析处理结果作为目标数据。
以采用饼状图的形式呈现销量占比为示例，其目标是展示A款商品的销量占比。那么应用管理平台110可以确定与目标对应的筛选条件是从数据库中查询A款商品的销量数据，除A款商品外的其他商品的销量数据。获取到该结果后，应用管理平台110可以对获取到的数据能否完成展示A款商品的销量占比的目标进行判断。显然，展示销量占比不仅需要销量数据，还需要进行占比计算。因此，应用管理平台110可以确定数据查询指令得到的结果无法完成展示A款商品的销量占比的目标。响应于数据查询指令得到的结果无法完成目标，应用管理平台110需要生成数据分析指令。在当前实施例中，数据分析指令被配置为将A款商品的销量与包含A款商品在内的其他商品的总销量进行比值运算。如果比值运算的结果可以完成展示A款商品的销量占比的目标，那么可以将比值运算的结果作为目标数据。反之，如果比值运算的结果依然不能完成展示A款商品的销量占比的目标，那么应用管理平台110可以调整分析指令，或者增加新的分析指令，以使得执行调整后的分析指令得到的分析处理结果可以完成子任务请求的目标。也就是说，如果比值运算的结果依然不能完成展示A款商品的销量占比的目标，那么应用管理平台110可以设定多轮分析指令，每一个轮次都可以参照之前轮次的结果以及确定出的无法完成目标的原因等信息，由此通过多轮分析指令最终完成子任务请求的目标。
通过上述过程，应用管理平台110可以同时利用分析指令和查询指令完成子任务请求的目标。如果说查询指令的优势是快速获取数据，那么分析指令的优势则在于可以对数据进行复杂的计算。示例性地，占比问题、同比问题、环比问题等，均可以对应复杂的计算。分析指令可以采用适合的编程语言进行代码编译。编程语言的基本语句中包含算术运算符、逻辑运算符等，因而面对如同比、环比、占比等复杂问题可以轻松应对。在当前实施例中，对于查询指令和分析指令的代码编译可以由应用管理平台110调用模型155完成。利用模型155的代码编译能力，可以节省人工进行代码编译的过程。
在一些实施例中，应用管理平台110还可以对执行数据查询指令得到的结果进行数据优化处理，数据优化处理包括数据清洗和数据位数调整的至少一项。
在执行数据查询指令得到查询结果后，应用管理平台110还可以对查询结果进行数据优化处理。数据优化处理可以包括数据清洗以及数据位数调整中的至少一项。
以数据清洗为示例，如果应用管理平台110确定出查询结果中存在无意义的数据，那么可以将无意义的数据进行清洗。示例性地，无意义的数据可以是无法识别的数据、空值数据或者数值为0的数据等。
再以数据位数调整为示例，应用管理平台110可以通过对数据查询指令得到的结果进行位数调整。例如，调整可以包括数据取整，数据保留小数点后保留一位等整。
通过上述过程，可以完成对查询指令得到结果的优化处理。不难理解对于分析指令得到的结果，也可以进行如数据位数调整，由此在后续生成可编辑图表或者执行数据播报等功能时，可以使得数据更为简化。
在一些实施例中，应用管理平台110还可以向目标数据添加数据来源标识，数据来源标识用于指示目标数据的出处。
以查询指令得到的结果作为目标数据为示例，在获取到查询指令得到的结果后，应用管理平台110还可以对查询指令得到的结果添加数据来源标识。数据来源标识用于指示结果的出处。示例性地，数据来源标识可以用于指示查询指令得到的结果源自数据库的数据库名、数据库中的表、表中的列等信息。
再以分析指令得到的结果作为目标数据为示例，由于分析指令是对查询指令得到的结果进行分析计算所得到的结果。因此，对于通过分析指令得到的结果而言，应用管理平台110也可以将其分析计算的对象的数据来源标识作为分析计算的结果所对应的数据来源标识。
添加数据来源标识的意义在于，可以实现对于数据真实性进行标注，由此可以规避掉没有出处的虚假数据。
在一些实施例中，应用管理平台110调用指定功能处理每个子任务请求具体可以是：调用数据图表生成功能，基于每个子任务请求以及与该子任务请求对应的目标数据，生成数据图表，数据图表的呈现样式是可编辑的。
在当前实施例中，以调用的指定功能为生成可编辑数据图表的功能为示例。应用管理平台110可以通过调用目标应用120所支持的可编辑数据图表的功能，基于子任务请求以及与该子任务请求对应的目标数据，生成可编辑数据图表。可编辑数据图表的功能可以基于领域特定语言(Domain-Specific Language，DSL)实现。DSL可以作为一种专用于图表生成的脚本语言，可以根据子任务的目标以及子任务的目标数据，完成子任务对应的图表的生成和渲染。参考图5A，图5A示出了根据本公开的一些实施例的调用指定功能处理子任务请求对应的柱状图结果的页面500的示例。在图5A中，示出了以柱状图的形式展示A款商品在过往三个季度的销量数据。参考图5B，图5B示出了根据本公开的一些实施例的调用指定功能处理子任务请求对应的饼状图结果的页面510的示例。在图5B中，示出了以饼状图的形式展示A款商品在上一季度的销量占比。参考图5C，图5C示出了根据本公开的一些实施例的调用指定功能处理子任务请求对应的柱状图结合折线图结果的页面520的示例。在图5C中，示出了以柱状图结合折线图的形式展示A款商品销量与其他商品销量相比的环比变化情况。示例性地，页面520中的数据图表呈现样式是可编辑的，例如，所述数据图表中的字体、字号、颜色等呈现样式均为可编辑的状态。
在一些实施例中，应用管理平台110还可以将目标数据存储于指定存储区域。并且其中调用指定功能处理该子任务请求包括：将指定存储区域的地址提供给指定功能。
应用管理平台110在利用查询指令进行数据查询获取到查询结果后，可以将查询指令得到的结果存储于指定的存储区域。指定区域可以是编程语言沙箱中的缓存区域。在存储完毕后，应用管理平台110可以根据查询指令得到的结果所存储的地址生成存储标识。存储标识可以用于表征数据。由此，应用管理平台110在调用指定功能处理子任务请求生成新的查询指令或者生成的分析指令需要进行数据访问时，可以先生成存储地址标识读取指令，从而利用存储标识读取指定存储区域中存储的查询结果。同理，执行分析指令获得的结果也可以存储于指定存储区域，并且根据分析指令的结果所存储的地址生成存储标识。
通过上述过程，数据之间的访问仅通过存储标识进行表示，由此可以完成对应用管理平台110在模型调用时编译token的数据量降维。也就是说，在编译token时，无需罗列所有待获取数据，而只需生成对存储区域地址的读取指令即可。在面对模型上下文窗口数据量接收能力有限的情况下，可以大幅度降低模型的资源开销。
图6示出了根据本公开的一些实施例的任务处理装置600的示意性结构框图。装置600例如可以被实现在或被包括在应用管理平台110中。装置600中的各个模块/组件可以由硬件、软件、固件或者它们的任何组合来实现。
如图所示，装置600包括解析模块601，被配置为接收到的用户输入进行解析，得到解析结果，用户输入指示针对目标应用的任务执行请求，解析结果指示任务执行请求对应的多个子任务请求。数据需求确定模块602，被配置为针对多个子任务请求中的子任务请求，确定该子任务请求的数据需求。子任务请求处理模块603，被配置为响应于基于数据需求获取到目标数据，调用指定功能处理该子任务请求。
在一些实施例中，解析模块601还被配置为可以包括解决途径确定子模块，该模块被配置为基于用户输入，确定任务执行请求的多个解决途径。标识添加子模块，该模块被配置为为每个解决途径添加推理标识，推理标识用于指示确定该解决途径的原因。子任务请求生成模块，该模块被配置为分别生成与每个解决途径对应的子任务请求。
在一些实施例中，装置600还被配置为包括解决途径展示模块，该模块被配置为在指定展示区域展示已添加推理标识的解决途径；解决途径调整模块，该模块被配置为响应于接收到的调整指令，执行与调整指令对应的调整动作，调整指令是针对至少一个已添加推理标识的解决途径的。
在一些实施例中，数据需求确定模块602被配置为可以包括筛选条件确定子模块，该模块被配置为基于获取到的子任务请求的目标，确定数据筛选条件；数据查询指令生成子模块，该模块被配置为基于数据筛选条件，生成数据查询指令；以及将执行数据查询指令得到的结果作为目标数据。
在一些实施例中，数据需求确定模块602被配置为还可以包括分析指令生成子模块，该模块被配置为响应于数据查询指令得到的结果无法完成目标，生成数据分析指令，数据分析指令被配置为对执行数据查询指令得到的结果进行数据分析处理，得到分析处理结果；将分析处理结果作为目标数据。
在一些实施例中，数据需求确定模块602被配置为对执行数据查询指令得到的结果进行数据优化处理，数据优化处理包括数据清洗和数据位数调整的至少一项。
在一些实施例中，装置600还包括数据来源标识添加模块，该模块被配置为向目标数据添加数据来源标识，数据来源标识用于指示目标数据的出处。
在一些实施例中，子任务请求处理模块603具体被配置为调用数据图表生成功能，基于每个子任务请求以及与该子任务请求对应的目标数据，生成数据图表，数据图表的呈现样式是可编辑的。
在一些实施例中，装置600还包括目标数据表征模块，该模块被配置为将目标数据存储于指定存储区域。并且调用指定功能处理该子任务请求包括：将指定存储区域的地址提供给指定功能。
图7示出了其中可以实现本公开的一个或多个实施例的电子设备700的框图。应当理解，图7所示出的电子设备700仅仅是示例性的，而不应当构成对本文所描述的实施例的功能和范围的任何限制。图7所示出的电子设备700可以包括或被实现为图1的应用管理平台110，或图6的装置600。
如图7所示，电子设备700是通用电子设备的形式。电子设备700的组件可以包括但不限于一个或多个处理器710或处理单元、存储器720、存储设备730、一个或多个通信单元740、一个或多个输入设备750以及一个或多个输出设备760。处理器710可以是实际或虚拟处理器并且能够根据存储器720中存储的程序来执行各种处理。在多处理器系统中，多个处理器并行执行计算机可执行指令，以提高电子设备700的并行处理能力。
电子设备700通常包括多个计算机存储介质。这样的介质可以是电子设备700可访问的任何可以获取的介质，包括但不限于易失性和非易失性介质、可拆卸和不可拆卸介质。存储器720可以是易失性存储器(例如寄存器、高速缓存、随机访问存储器(RAM))、非易失性存储器(例如，只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、闪存)或它们的某种组合。存储设备730可以是可拆卸或不可拆卸的介质，并且可以包括机器可读介质，诸如闪存驱动、磁盘或者任何其他介质，其可以能够用于存储信息和/或数据并且可以在电子设备700内被访问。
电子设备700可以进一步包括另外的可拆卸/不可拆卸、易失性/非易失性存储介质。尽管未在图7中示出，可以提供用于从可拆卸、非易失性磁盘(例如“软盘”)进行读取或写入的磁盘驱动和用于从可拆卸、非易失性光盘进行读取或写入的光盘驱动。在这些情况中，每个驱动可以由一个或多个数据介质接口被连接至总线(未示出)。存储器720可以包括计算机程序产品725，其具有一个或多个程序模块，这些程序模块被配置为执行本公开的各种实施例的各种方法或动作。
通信单元740实现通过通信介质与其他电子设备进行通信。附加地，电子设备700的组件的功能可以以单个计算集群或多个计算机器来实现，这些计算机器能够通过通信连接进行通信。因此，电子设备700可以使用与一个或多个其他服务器、网络个人计算机(PC)或者另一个网络节点的逻辑连接来在联网环境中进行操作。
输入设备750可以是一个或多个输入设备，例如鼠标、键盘、追踪球等。输出设备760可以是一个或多个输出设备，例如显示器、扬声器、打印机等。电子设备700还可以根据需要通过通信单元740与一个或多个外部设备(未示出)进行通信，外部设备诸如存储设备、显示设备等，与一个或多个使得用户与电子设备700交互的设备进行通信，或者与使得电子设备700与一个或多个其他电子设备通信的任何设备(例如，网卡、调制解调器等)进行通信。这样的通信可以经由输入/输出(I/O)接口(未示出)来执行。
根据本公开的示例性实现方式，提供了一种计算机可读存储介质，其上存储有计算机可执行指令，其中计算机可执行指令被处理器执行以实现上文描述的方法。根据本公开的示例性实现方式，还提供了一种计算机程序产品，计算机程序产品被有形地存储在非瞬态计算机可读介质上并且包括计算机可执行指令，而计算机可执行指令被处理器执行以实现上文描述的方法。
这里参照根据本公开实现的方法、装置、设备和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其他可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
可以把计算机可读程序指令加载到计算机、其他可编程数据处理装置、或其他设备上，使得在计算机、其他可编程数据处理装置或其他设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其他可编程数据处理装置、或其他设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实现的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实现，上述说明是示例性的，并非穷尽性的，并且也不限于所公开的各实现。在不偏离所说明的各实现的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实现的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其他普通技术人员能理解本文公开的各个实现方式。

Claims (13)

  1. 一种任务处理方法，包括：
    对接收到的用户输入进行解析，得到解析结果，所述用户输入指示针对目标应用的任务执行请求，所述解析结果指示所述任务执行请求对应的多个子任务请求；
    针对所述多个子任务请求中的子任务请求，确定该子任务请求的数据需求；以及
    响应于基于所述数据需求获取到目标数据，调用指定功能处理该子任务请求。
  2. 根据权利要求1所述的方法，其中对接收到的用户输入进行解析包括：
    基于所述用户输入，确定所述任务执行请求的多个解决途径；
    为每个所述解决途径添加推理标识，所述推理标识用于指示确定该解决途径的原因；以及
    分别生成与每个所述解决途径对应的子任务请求。
  3. 根据权利要求2所述的方法，还包括：
    在指定展示区域展示已添加推理标识的解决途径；以及
    响应于接收到的调整指令，执行与所述调整指令对应的调整动作，所述调整指令是针对至少一个所述已添加推理标识的解决途径的。
  4. 根据权利要求1所述的方法，其中所述确定该子任务请求的数据需求包括：
    基于获取到的所述子任务请求的目标，确定数据筛选条件；
    基于所述数据筛选条件，生成数据查询指令；以及
    将执行所述数据查询指令得到的结果作为所述目标数据。
  5. 根据权利要求4所述的方法，其中所述确定该子任务请求的数据需求还包括：
    响应于所述数据查询指令得到的结果无法完成所述目标，生成数据分析指令，所述数据分析指令被配置为对执行所述数据查询指令得到的结果进行数据分析处理，得到分析处理结果；以及
    将所述分析处理结果作为所述目标数据。
  6. 根据权利要求4所述的方法，还包括：
    对执行所述数据查询指令得到的结果进行数据优化处理，所述数据优化处理包括数据清洗和数据位数调整的至少一项。
  7. 根据权利要求1、4或5所述的方法，还包括：
    向所述目标数据添加数据来源标识，所述数据来源标识用于指示所述目标数据的出处。
  8. 根据权利要求1所述的方法，其中调用指定功能处理每个所述子任务请求，包括：
    调用数据图表生成功能，基于每个所述子任务请求以及与该子任务请求对应的目标数据，生成数据图表，所述数据图表的呈现样式是可编辑的。
  9. 根据权利要求1所述的方法，还包括：
    将所述目标数据存储于指定存储区域，并且
    其中调用指定功能处理该子任务请求包括：以及
    将所述指定存储区域的地址提供给所述指定功能。
  10. 一种任务处理装置，包括：
    解析模块，被配置为接收到的用户输入进行解析，得到解析结果，所述用户输入指示针对目标应用的任务执行请求，所述解析结果指示所述任务执行请求对应的多个子任务请求；
    数据需求确定模块，被配置为针对所述多个子任务请求中的子任务请求，确定该子任务请求的数据需求；以及
    子任务请求处理模块，被配置为响应于基于所述数据需求获取到目标数据，调用指定功能处理该子任务请求。
  11. 一种电子设备，包括：
    至少一个处理器；以及
    至少一个存储器，至少一个存储器被耦合到至少一个处理器并且存储用于由至少一个处理器执行的指令，指令在由至少一个处理器执行时使电子设备执行根据权利要求1至9中任一项的方法。
  12. 一种计算机可读存储介质，其上存储有计算机可执行指令，计算机可执行指令可由处理器执行以实现根据权利要求1至9中任一项的方法。
  13. 一种计算机程序产品，所述计算机程序产品被有形地存储在计算机存储介质中并且包括计算机可执行指令,所述计算机可执行指令在由设备执行时使所述设备执行根据权利要求1至9中任一项所述的方法。
PCT/CN2025/080067 2024-06-27 2025-02-28 任务处理方法、装置、设备和计算机可读存储介质 Pending WO2026001059A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410853011.8A CN118839769B (zh) 2024-06-27 2024-06-27 任务处理方法、装置、设备和计算机可读存储介质
CN202410853011.8 2024-06-27

Publications (1)

Publication Number Publication Date
WO2026001059A1 true WO2026001059A1 (zh) 2026-01-02

Family

ID=93147615

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/080067 Pending WO2026001059A1 (zh) 2024-06-27 2025-02-28 任务处理方法、装置、设备和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN118839769B (zh)
WO (1) WO2026001059A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118839769B (zh) * 2024-06-27 2025-08-29 北京字跳网络技术有限公司 任务处理方法、装置、设备和计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117033540A (zh) * 2023-09-01 2023-11-10 中国工商银行股份有限公司 报表生成方法、装置、电子设备和介质
CN117787415A (zh) * 2023-12-29 2024-03-29 新奥新智科技有限公司 一种智能问答方法、装置、设备及介质
WO2024082754A1 (zh) * 2022-10-18 2024-04-25 华为云计算技术有限公司 见解数据生成的方法和装置
CN118035387A (zh) * 2024-04-03 2024-05-14 浙江口碑网络技术有限公司 一种基于大语言模型的数据选取、输出方法和装置
CN118839769A (zh) * 2024-06-27 2024-10-25 北京字跳网络技术有限公司 任务处理方法、装置、设备和计算机可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114090620B (zh) * 2022-01-19 2022-09-27 支付宝(杭州)信息技术有限公司 查询请求的处理方法及装置
CN115687672A (zh) * 2022-10-26 2023-02-03 中网华信科技股份有限公司 图表可视化智能推荐方法、装置、设备及可读存储介质
CN118093851A (zh) * 2024-02-02 2024-05-28 阿里巴巴（中国）有限公司 任务处理方法、自动问答方法以及法律任务处理方法
CN118229310A (zh) * 2024-03-23 2024-06-21 深圳市喂车科技有限公司 一种基于大模型的加油站经营咨询方法和服务器

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024082754A1 (zh) * 2022-10-18 2024-04-25 华为云计算技术有限公司 见解数据生成的方法和装置
CN117033540A (zh) * 2023-09-01 2023-11-10 中国工商银行股份有限公司 报表生成方法、装置、电子设备和介质
CN117787415A (zh) * 2023-12-29 2024-03-29 新奥新智科技有限公司 一种智能问答方法、装置、设备及介质
CN118035387A (zh) * 2024-04-03 2024-05-14 浙江口碑网络技术有限公司 一种基于大语言模型的数据选取、输出方法和装置
CN118839769A (zh) * 2024-06-27 2024-10-25 北京字跳网络技术有限公司 任务处理方法、装置、设备和计算机可读存储介质

Also Published As

Publication number Publication date
CN118839769B (zh) 2025-08-29
CN118839769A (zh) 2024-10-25

Similar Documents

Publication Publication Date Title
JP2025540746A (ja) 大規模言語モデルに基づくタスク生成方法、システム、デバイス及びコンピュータプログラム
US20260100193A1 (en) Document creation and editing via automated assistant interactions
US12333341B2 (en) Managing a digital assistant workflow
WO2026001052A1 (zh) 任务处理方法、装置、设备和计算机可读存储介质
US20250138993A1 (en) Debugging a digital assistant
WO2026001059A1 (zh) 任务处理方法、装置、设备和计算机可读存储介质
WO2026040475A1 (zh) 数据处理方法、装置、设备和可读存储介质
WO2026001042A1 (zh) 信息处理方法、装置、设备和存储介质
WO2026001060A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025223030A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025223031A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025246492A1 (zh) 信息处理方法、装置、设备和存储介质
JP2026512322A (ja) アプリケーション作成のための方法、装置、機器及び記憶媒体
US20250086405A1 (en) Prompt complexity for large language models
US11328018B2 (en) System and method for state dependency based task execution and natural language response generation
CN113094191A (zh) 业务规则处理方法、装置、服务器及存储介质
US20260050437A1 (en) Application creation
US20250147735A1 (en) Method, apparatus, device and storage medium for message processing
US20250165166A1 (en) Storing data in a digital assistant
US20260093702A1 (en) Method for data processing, apparatus, device, storage medium and program product
CN116663515B (zh) 一种动态申报表单的生成方法和装置
US20250150417A1 (en) Method, apparatus, device and storage medium for session interaction
CN119292707A (zh) 信息处理方法、装置、设备、存储介质和程序产品
WO2026040535A1 (zh) 用于应用创建的方法、装置、设备、介质和程序产品
WO2026091768A1 (zh) 用于文档生成的方法、装置、设备、存储介质和程序产品

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25824454

Country of ref document: EP

Kind code of ref document: A1