Method, device, equipment, medium and product for outputting data processing results

Abstract

Disclosed are a method and apparatus, device, medium and product for outputting data processing results. The method includes receiving an input including a data processing requirement in a GUI. The method also includes determining the intent type of the user's intent by performing intent recognition on the input using a first language model. The method also includes generating a target code executable by a browser for the data processing requirement based on the intent type by using a second language model using an agent corresponding to the intent type, the second language model having a higher performance than the first language model and a lower calling speed than the first language model. The method also includes running the target code through a browser to generate a visualized processing result for predetermined data. The method also includes providing an output including the processing result in an interactive manner in a GUI. The ability to use different models to identify requirements and generate code in a targeted manner accelerates the processing process and efficiency. The processing result is visualized and interactive with the user.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of computers, and in particular, to methods and apparatuses, devices, media, and products for outputting data processing results. Background Art

[0002] In response to the user's data processing needs, corresponding data processing can be provided through a graphical user interface (GUI). Data processing often involves complex processing operations and a large amount of information display. The intuitive and easy-to-use features of GUI can greatly improve the user's work efficiency and usage experience.

[0003] GUI can be used to present abstract data in a visual way, so that users can understand the meaning and relationship of data more intuitively. For example, displaying data in the form of graphs, tables, etc. can help users find trends and outliers in the data.

[0004] In addition, GUI can provide rich interactive functions, and users can easily perform data processing and analysis operations. In addition, GUI can also be customized and expanded according to user needs to meet the diversified data processing needs of different users. For example, developers can add new functional modules and adjust the interface layout based on user feedback and needs. Summary of the invention

[0005] An embodiment of the present disclosure provides a solution for outputting visualized data processing results.

[0006] In a first aspect of the present disclosure, a method for outputting a visualized data processing result is provided, the method comprising receiving an input from a user in a graphical user interface (GUI), the input comprising a data processing requirement of the user based on a language description. The method further comprises determining the intent type of the user intent corresponding to the data processing requirement by performing intent recognition on the input using a first language model. The method further comprises generating a target code for the data processing requirement based on the determined intent type by using a second language model using an agent corresponding to the determined intent type, the target code being executable by a browser corresponding to the GUI, wherein the performance of the second language model is higher than that of the first language model, and the calling speed of the second language model is lower than the calling speed of the first language model. The method further comprises running the generated target code through a browser to generate a visualized processing result for the predetermined data to be processed. The method further comprises providing an output including the processing result in an interactive manner in the GUI.

[0007] In a second aspect of the present disclosure, a device for outputting a visualized data processing result is provided, the device comprising a demand receiving module configured to receive an input from a user in a graphical user interface (GUI), the input comprising a data processing demand of the user based on a language description. The device further comprises an intention recognition module configured to determine the intention type of the user intention corresponding to the data processing demand by performing intention recognition on the input using a first language model. The device further comprises a code generation module configured to generate a target code for the data processing demand based on the determined intention type by using a second language model using an agent corresponding to the determined intention type, the target code being executable by a browser corresponding to the GUI, wherein the performance of the second language model is higher than that of the first language model, and the calling speed of the second language model is lower than the calling speed of the first language model. The device further comprises a result generation module configured to run the generated target code through a browser to generate a visualized processing result for the predetermined data to be processed. The device further comprises a result providing module configured to provide an output including the processing result in an interactive manner in the GUI.

[0008] According to a third aspect of the present disclosure, an electronic device is provided. The computing device includes a processor and a memory, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the processor executes a method or process according to an embodiment of the present disclosure.

[0009] According to a fourth aspect of the present disclosure, a machine-readable storage medium is provided, wherein machine-executable instructions are stored on the machine-readable storage medium, and when the machine-executable instructions are executed by a processor, the processor is enabled to execute a method or process according to an embodiment of the present disclosure.

[0010] In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product is tangibly stored on a non-transitory computer-readable storage medium and includes a computer program, which, when executed by a processor of a computer, causes the processor to perform a method or process according to an embodiment of the present disclosure.

[0011] Please note that the summary is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary is not intended to identify key features or essential features of the disclosure, nor is it intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other purposes, features and advantages of the present disclosure will become more clearly understood by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, in which:

[0013] Figure 1is a diagram schematically illustrating an example environment in which methods and / or processes according to embodiments of the present disclosure may be implemented;

[0014] Figure 2 is a flowchart schematically illustrating a method for outputting visualized data processing results according to an embodiment of the present disclosure;

[0015] Figure 3 is a diagram schematically illustrating a process according to an embodiment of the present disclosure;

[0016] Figure 4 is a diagram schematically illustrating an example of a visualized data processing result according to an embodiment of the present disclosure;

[0017] Figure 5 is a diagram schematically illustrating an example 500 of a data processing analysis report according to an embodiment of the present disclosure;

[0018] Figure 6 is a diagram schematically illustrating an apparatus for outputting visualized data processing results according to an embodiment of the present disclosure;

[0019] Figure 7 is a schematic block diagram of an example device that may be used to implement embodiments according to the present disclosure.

[0020] Throughout the drawings, same or similar reference numbers generally refer to same or similar elements. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0022] In the description of the embodiments of the present disclosure, the term "including" and its variations should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects, unless explicitly indicated to be different.

[0023] As mentioned above, data processing based on the graphical user interface (GUI) has promoted the improvement of processing and analysis efficiency and user experience by virtue of its visualization, interactivity, and scalability. In the context of the rapid development of digitalization, users' data processing needs have shown significant diversity and complexity. Different users may come from different fields, for example, and they have obvious differences in the purpose, method, and expected results of data processing. If we only rely on a unified graphical user interface (GUI), it will be difficult to meet all these diverse and complex needs, and it will not be well covered. As a result, we may face many troubles and obstacles, which will affect work efficiency and the quality of data processing.

[0024] In related solutions, users usually need to download the data to be processed locally, and then process the data based on the data dimensions (such as merging, splitting, etc.), and finally obtain the data processing results. Such data processing results generally have poor visibility and weak interactivity, and are often difficult to cope with the user's subsequent iteration needs. In addition, this process requires a lot of manual processing, which is time-consuming and labor-intensive, and there may be a risk of processing errors. Problems or challenges such as unstable data processing goals, low efficiency in manual data processing, low efficiency in analyzing data rules, lack of unified chart processing interactions, and high costs of readjustment according to needs have seriously restricted the efficiency of processing and analysis and degraded the user experience. It is urgent to find more efficient and intelligent solutions to improve them.

[0025] In order to solve at least some of the above and other potential problems, an embodiment of the present disclosure proposes a scheme for outputting visualized data processing results. The scheme includes receiving input from a user in a graphical user interface (GUI), the input including a data processing requirement of the user based on a language description. The scheme also includes determining the intent type of the user intent corresponding to the data processing requirement by performing intent recognition on the input using a first language model. The scheme also includes generating a target code for the data processing requirement based on the determined intent type by using a second language model using an agent corresponding to the determined intent type, the target code being executable by a browser corresponding to the GUI, wherein the performance of the second language model is higher than that of the first language model, and the calling speed of the second language model is lower than the calling speed of the first language model. The scheme also includes running the generated target code through a browser to generate a visualized processing result for the predetermined data to be processed. The scheme also includes providing an output including the processing result in an interactive manner in the GUI.

[0026] In this way, real-time data processing can be achieved through language description, and different language models can be used to identify data processing requirements in a targeted manner and generate the expected operation code for the corresponding data processing operations, which accelerates the data processing process and improves processing efficiency. At the same time, the corresponding intelligent agent can be used according to the user's intention, and can respond and execute tasks accurately and quickly, greatly improving the accuracy and timeliness of data processing. In addition, users can obtain dynamically generated visualization results and interact with the results, which enhances the user experience and improves the flexibility and intuitiveness of data exploration.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] Reference below Figures 1 to 7 It should be understood that these exemplary embodiments are provided only to enable those skilled in the art to better understand and implement the embodiments of the present disclosure, and are not intended to limit the scope of the present disclosure in any way.

[0032] Figure 1 1 is a schematic diagram schematically illustrating an example environment 100 in which methods and / or processes according to embodiments of the present disclosure may be implemented. Figure 1 As shown in FIG. 1 , environment 100 includes user 101, display device 110, local computing node 120, and computing nodes 131 and 132 arranged in cloud 130. Figure 1 The implementation environment of the embodiment of the present disclosure is described by taking a mixed arrangement computing system as an example. It should be understood that this is only an exemplary and non-restrictive description, and other different types of computing systems are also feasible, such as distributed or centralized computing systems. The appropriate computing environment configuration can be selected according to actual use needs.

[0033] User 101 may be an individual or an organization (e.g., an enterprise). User 101 may provide data processing requirements through language description, such as inputting a language description of its data processing requirements via a graphical user interface (GUI) in display device 110. Other input methods may be possible, such as via an audio input device such as a microphone.

[0034] Multiple computing nodes with computing capabilities can process input from user 101. By way of example and not limitation, computing node 120 can be arranged locally at user 101, while computing nodes 131 and 132 can be arranged in cloud 130. Cloud 130 can indicate a computing and service model built based on cloud or distributed technology, in which computing resources, storage resources, etc. are coupled together through a network to form an intelligently scheduled and flexibly scalable computing resource collection. At least a portion of these resources can be dynamically accessed or allocated as needed to complete the corresponding calculation without the need to locally own or manage these physical resources.

[0035] A computing node may be a device with computing capabilities. For example, a computing node may be provided with a processor and a memory, etc., or may be equipped with a dedicated accelerator. Accelerators such as a graphics processing unit (GPU), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. can significantly accelerate specific types of computing tasks. The data and models involved in the method for outputting visualized data processing results according to an embodiment of the present disclosure (for example, the data to be processed and the language model used, etc.) may be centrally arranged on one node, or may be distributedly deployed on some of the multiple nodes.

[0036] like Figure 1 As shown in the example, the local computing node 120 and the computing nodes 131 and 132 at the cloud 130 can be interconnected to communicate with each other through a network. Figure 1 Taking the architecture in as an example, computing nodes 120, 131 and 132 can communicate via a network to achieve, for example, data synchronization or sharing between nodes. Multiple computing nodes in environment 100 can process computing tasks in parallel. In addition, multiple computing nodes in environment 100 can have redundancy and fault tolerance mechanisms to ensure reliable execution of computing tasks. When a computing node fails, the system can automatically migrate the job to other nodes that are working normally to ensure the continuity and availability of the task.

[0037] Examples of computing nodes may include supercomputers, personal computers, laptop computers, vehicle-mounted computing devices, mobile devices (such as smart phones, tablet computers, etc.), wearable electronic devices, multimedia devices, personal digital assistants (PDAs), smart home devices, consumer electronic products, or a combination of any one or more of the above devices, etc. It should be understood that the computing nodes described herein are merely exemplary and non-restrictive, and for example, other different types of computing nodes may also be used.

[0038] It should be understood that for ease of explanation and illustration purposes, Figure 1 Only limited components and exemplary connection relationships are shown. It should be understood that this is not intended to limit the scope of the present disclosure, and there may be other environments with different numbers, configurations, etc. Customized arrangements may be selected according to specific usage scenarios and needs, and the same is true in the following.

[0039] Combined with the above Figure 1 Describes an example environment in which the methods and / or processes according to embodiments of the present disclosure may be implemented. Figure 2 The method 200 for outputting visualized data processing results according to an embodiment of the present disclosure is described. Through the method 200, different models can be used to identify requirements and generate codes in a targeted manner, which accelerates the processing process and efficiency. The processing results are visualized and interactive with the user.

[0040] Figure 2 2 is a flowchart schematically illustrating a method 200 for outputting visualized data processing results according to an embodiment of the present disclosure. At 210, an input from a user is received in a graphical user interface (GUI), and the input includes a data processing requirement of the user based on a language description. According to an embodiment of the present disclosure, real-time processing of data can be achieved through language description, which not only greatly simplifies the user operation experience, but also gets rid of the tediousness of frequently building and maintaining GUIs, and can reduce resource consumption and time costs caused by frequent development.

[0041] At 220, the intent type of the user intent corresponding to the data processing requirement is determined by performing intent recognition on the input using the first language model. According to an embodiment of the present disclosure, the first model may be a large language model (LLM), which, with its powerful natural language processing capability and extensive context understanding capability, can more accurately capture the user's input meaning and potential needs, thereby ensuring the accuracy and efficiency of intent recognition.

[0042] At 230, based on the determined intent type, a target code for data processing requirements is generated by utilizing a second language model using an agent corresponding to the determined intent type, the target code being executable by a browser corresponding to the GUI, wherein performance of the second language model is higher than performance of the first language model, and a calling speed of the second language model is lower than a calling speed of the first language model.

[0043] According to an embodiment of the present disclosure, the second language model can be a large language model different from the first language model. The first language model can first accurately identify the user's intent by virtue of its advantage in calling speed, and the second language model with better performance than the first language model can be configured to use a suitable agent to generate the target code for the corresponding data processing operation. The embodiment of the present disclosure will adopt targeted agents for different intent types. Different agents have different responsibilities, and can handle related processing tasks more accurately, avoiding a large agent that brings more token consumption and longer waiting time.

[0044] In addition, the generated target code is executed in the browser, ensuring the security of the data processing process and avoiding the risk of data leakage during the processing. In some embodiments, the process of generating code can be based on artificial intelligence generated content (AIGC) technology, which only needs to generate code according to instructions without the participation of data, making the prompt content concise and efficient, and accelerating the process of code generation.

[0045] At 240, the generated target code is run through the browser to generate a visual processing result for the predetermined data to be processed. According to an embodiment of the present disclosure, the time required for the final generated code to be executed in the browser is extremely short, which makes the entire processing and analysis of data faster. After the processing is completed, the results are presented in an intuitive visual form, such as a line chart, a bar chart, a pie chart, etc., so that complex structures and trends are clear at a glance. This approach not only improves the efficiency and flexibility of data processing, but also promotes users' in-depth understanding of data, such as promoting data-driven decision-making.

[0046] At 250, in the GUI, output including the processing results is provided in an interactive manner. According to an embodiment of the present disclosure, by providing interactive charts and dialog forms, the visualized data processing results can interact with the user so that the analysis can be further iterated according to the data processing requirements. This enhances the user experience while improving the flexibility and intuitiveness of data exploration.

[0047] According to the method 200 for outputting visualized data processing results of an embodiment of the present disclosure, real-time data processing can be achieved through language description, and different language models can be used to specifically identify data processing requirements and generate expected operation codes for corresponding data processing operations, thereby accelerating the process of data processing and improving processing efficiency. At the same time, the corresponding intelligent agent can be used according to the user's intention, and tasks can be responded to and executed accurately and quickly, greatly improving the accuracy and timeliness of data processing. In addition, users can obtain dynamically generated visualization results and can interact with the results, which enhances the user experience and also improves the flexibility and intuitiveness of data exploration.

[0048] Figure 3 Schematically illustrates a data processing architecture 300 according to an embodiment of the present disclosure. It should be understood that the description of the data processing architecture 300 is to facilitate the understanding of the embodiment of the present disclosure, and is not intended to limit the scope of the embodiment of the present disclosure. Other different modifications or variations are obvious to those skilled in the art.

[0049] At 310, the user may input the user's data processing requirements based on language description through the GUI, such as text, voice, etc. In some embodiments, based on the user's data processing history, etc., candidate inputs may be generated for the user. In this way, it is possible to help the user generate several questions and help the user ask inspiring questions.

[0050] At 320, the first language model performs intent recognition on the input to determine the intent type of the user intent corresponding to the user's data processing needs. In some embodiments, the intent type may include at least one of the following: invalid questions, query analysis, chart operations, or attribution insights. It should be understood that the intent type of the user intent can be customized according to specific usage scenarios and needs, etc., and is not intended to be limited to the above examples.

[0051] At 322, in response to the intent type being determined to be an invalid question, the input needs to be optimized. In some embodiments, at 330, if it is not optimized, the length of the input indicating the data processing requirement can be determined. If it is determined that the length of the input is shorter than a length threshold, an update to the input can be facilitated, such as adding an associated supplemental portion to clarify the data processing requirement. The updated input will be used again for intent recognition. Conversely, if it has been optimized, subsequent operations will be performed based on the type of intent it indicates.

[0052] In response to the intent type being determined as query analysis (at 324), the second language model uses an agent for query analysis (hereinafter, also referred to as a first agent) to generate codes for one or more operations corresponding to the user's data processing needs (hereinafter, also referred to as a first operation code) (at 370). According to an embodiment of the present disclosure, targeted agents are designed for different types of user intents, and each agent is assigned specific responsibilities, aiming to handle their respective tasks more efficiently and accurately. This effectively avoids the problems of excessive resource consumption and prolonged user waiting time that may be caused by a single general agent when handling multiple needs.

[0053] The agent may indicate one or more target roles (e.g., code engineer, data analyst, etc.), the code type of the target code to be generated (e.g., Javascript, etc.), and one or more operations corresponding to the user's data processing requirements, etc. According to an embodiment of the present disclosure, for query analysis, the first agent may indicate at least one of the following: aggregate analysis, filter query, conditional sorting, etc.

[0054] In an exemplary but non-limiting manner, aggregate analysis can be configured to divide the predetermined data to be processed into multiple sub-data sets based on one or more predetermined data dimensions (such as time, etc.), wherein each sub-data set corresponds to a corresponding feature. Aggregate analysis allows data to be automatically aggregated and calculated according to one or more data dimensions in the predetermined data dimensions to reduce the need for manual data merging. One or more of these sub-data sets can be visually presented to the user differently in response to a selection operation from the user, and all data in each sub-data set can be uniformly renamed in response to a renaming operation from the user (e.g., via a user instruction) or a predetermined rule, which eliminates data inconsistencies and facilitates comparison and analysis across data sets. In addition, the filter query can be configured to filter out matching data sets from the predetermined data to be processed based on the filter target, and the conditional sorting can be configured to sort the predetermined data to be processed based on a predetermined field and order (e.g., ascending or descending, etc.).

[0055] In response to the intention type being determined as a chart operation (at 326), the second language model uses an agent for chart operations (hereinafter, also referred to as a second agent) to generate a code for a predetermined operation in an operation library corresponding to the user's data processing needs (hereinafter, also referred to as a second operation code) (at 370). According to an embodiment of the present disclosure, an operation library for chart data can be predefined, and the operation library includes at least one predetermined operation for chart data, and these predetermined operations can be represented via Javascript, etc. For chart operations, the operation library for predefined chart operations avoids redundant coding and resource waste of repeatedly generating the same functional code, and can directly call functions or methods in the operation library to quickly realize the processing, display, analysis, etc. of chart data. The second agent can indicate predefined chart operations, and these predefined chart operations include at least one of the following: switching chart types, restoring charts, adjusting chart sizes, adding or deleting chart elements, changing chart color themes, etc.

[0056] In response to the intent type being determined as attribution insight (at 328), the second language model generates codes (hereinafter, also referred to as third operation codes) of insight operation 3281 and attribution operation 3282 corresponding to the data processing requirements of the user using an agent for attribution insight (hereinafter, also referred to as a third agent) (at 370). In some embodiments, before the insight operation 3281 and the attribution operation 3282 are executed, data reduction may be performed on the predetermined data to be processed to generate simplified data to achieve redundancy removal, which is not only feasible for the attribution insight type, but also for the above or other types.

[0057] According to an embodiment of the present disclosure, before the insight operation 3281 and the attribution operation 3282 are performed, it can be determined whether the security level of the predetermined data to be processed reaches a security threshold. For data with security considerations (for example, reaching the above-mentioned security threshold), the security measures of the data processing environment will be enabled. In an example implementation, in response to determining that the security level of the predetermined data to be processed has reached the security threshold, a second security language model can be used to generate a third operation code (at 350). The second security language model has the same or similar performance as the second language model, but has an authentication mechanism in terms of security. Only after the individual and organization are verified can the second security language model be enabled to perform the insight operation 3281 and the attribution operation 3282.

[0058] According to an embodiment of the present disclosure, it may be determined whether the model output of the second security language model for the predetermined data to be processed is structured data (at 360). In response to determining that its model output is structured data, a third operation code may be generated based on the model output (at 370). In response to determining that its model output is not structured data, insight information or attribution information presented to a user may be generated based on the model output, and the insight information or attribution information may indicate a pattern, a specific value, etc. of the predetermined data in the form of a language description, so as to be used to form a data processing report.

[0059] The data processing results are obtained by running the generated target code in a browser, and based on the indicated data patterns in the form of language descriptions, insight information of specific values, attribution information, etc., a visualized data processing result (at 380 ) such as a processing analysis report can be output to the user.

[0060] Figure 4 4 is a diagram schematically illustrating an example 400 of a visualized data processing result according to an embodiment of the present disclosure. Figure 4 As shown in , multiple lines in the line graph can indicate the trend, highest value and lowest value of the data, etc. It should be understood that the line graph is one of the multiple implementations of the embodiments of the present disclosure, and the data processing results can also be presented through, for example, pie charts, bar charts, etc.

[0061] exist Figure 4 In the example, each of the multiple broken lines corresponds to a corresponding data item, such as a product name, etc., wherein the horizontal axis indicates time, for example, and the vertical axis indicates a metric value corresponding to the time (such as product sales, product price, etc.). In some embodiments, a real-time data monitoring function can be provided, and users can view data insight results in real time. The processing and analysis component 410 in the GUI can perform data processing on predetermined data, or further iterate the data processing results to interact with the results. Item 1 and Item 2 and their corresponding broken lines will be described below as examples.

[0062] Through the multiple subcomponents in the analysis component 410, such as aggregation, filtering, renaming, sorting, insight, etc., data processing can be performed on the predetermined data. By way of example, project 1 and project 2 can be merged via the aggregation subcomponent, and the merged project is called a merged project, wherein the broken line 406 corresponding to the merged project can indicate the merger of the broken line 402 corresponding to project 1 and the broken line corresponding to project 2. For another example, the project with the highest average value can be determined via the insight subcomponent. In addition, the user can input data processing requirements in the form of language description through the input subcomponent 415.

[0063] Figure 55 is a diagram schematically illustrating an example 500 of a data processing analysis report according to an embodiment of the present disclosure. By executing an operation code corresponding to an insight operation for user needs by a browser, a user can obtain Figure 5 Process analysis reports such as "Which data item has the highest average value and what is the difference analysis with the highest and lowest points?" as shown in to provide business decision support.

[0064] Figure 6 Schematically illustrates an apparatus 600 for outputting visualized data processing results according to an embodiment of the present disclosure. The apparatus 600 may include multiple units or modules for performing the steps or actions in the method or process discussed above. Figure 6 As shown in , the device 600 includes a demand receiving module 610, which is configured to receive input from a user in a graphical user interface GUI, wherein the input includes a user data processing demand based on a language description. The device 600 also includes an intention recognition module 620, which is configured to determine the intention type of the user intention corresponding to the data processing demand by performing intention recognition on the input using a first language model.

[0065] The device 600 also includes a code generation module 630, which is configured to generate a target code for the data processing requirement based on the determined intent type by using a second language model using an agent corresponding to the determined intent type, wherein the target code is executable by a browser corresponding to the GUI, wherein the performance of the second language model is higher than the performance of the first language model, and the calling speed of the second language model is lower than the calling speed of the first language model. The device 600 also includes a result generation module 640, which is configured to run the generated target code through the browser to generate a visualized processing result for the predetermined data to be processed. The device 600 also includes a result providing module 650, which is configured to provide an output including the processing result in an interactive manner in the GUI.

[0066] In some embodiments, the intent type of the user intent may include at least one of the following: invalid question; query analysis; chart operation; or attribution insight.

[0067] In some embodiments, the device 600 also includes an input optimization module, which is configured to determine the length of the input indicating the data processing requirement in response to determining that the intent type of the user intention is the invalid question; in response to determining that the length of the input is shorter than a length threshold, promote updating the input; and re-perform intent recognition on the updated input using the first language model.

[0068] In some embodiments, the generation of the target code for the data processing requirement may include: in response to determining that the intent type of the user intention is the query analysis, using the second language model to use the first agent corresponding to the query analysis to generate a first operation code for one or more operations corresponding to the data processing requirement, wherein the first agent indicates at least one of the following for the predetermined data: aggregation analysis, filtering query, and conditional sorting.

[0069] In some embodiments, the device 600 also includes a division module, which is configured to divide the predetermined data into multiple sub-data sets based on a predetermined data dimension, wherein the predetermined data dimension includes a channel source, and wherein at least one of the multiple sub-data sets is visually differently provided to the user in response to a selection operation from the user, and all data in each of the multiple sub-data sets is uniformly renamed in response to a renaming operation from the user.

[0070] In some embodiments, the generation of the target code for the data analysis and data processing requirements may include: in response to determining that the intention type of the user intention is the chart operation, using the second language model to use the second agent corresponding to the chart operation to generate a second operation code for a predetermined operation in an operation library corresponding to the data analysis and data processing requirements, wherein the predetermined data includes chart data, and the second agent indicates at least one of the following for the chart data: switching chart type, chart restoration.

[0071] In some embodiments, the generation of the target code for the data analysis data processing requirements may include: in response to determining that the intent type of the user intent is the attribution insight, using the second language model to use a third agent corresponding to the attribution insight to generate a third operation code for insight operations and attribution operations for the predetermined data, wherein before the insight operation and the attribution operation are executed, the predetermined data is de-redundant by performing data simplification.

[0072] In some embodiments, wherein the second language model includes a second security language model, the apparatus 600 may further include a security module configured to: determine whether the security level of the predetermined data reaches a security threshold before the insight operation and the attribution operation are performed; and in response to determining that the security level of the predetermined data has reached the security threshold, generate the third operation code using the second security language model, the second security language model being enabled based on authentication of the user.

[0073] In some embodiments, the device 600 also includes a structuring module configured to: determine whether the model output of the second security language model for the predetermined data is structured data; in response to determining that the model output is the structured data, generate the third operation code based on the model output; and in response to determining that the model output is not the structured data, generate insight information or attribution information presented to the user based on the model output.

[0074] In some embodiments, the device 600 further includes a candidate generation module configured to generate candidate inputs for the user based on the data processing history of the user. In addition, different analysis scenarios corresponding to different screening conditions are different, so different first questions can be preset in advance for different configuration conditions to facilitate quick questioning and improve user dialogue efficiency.

[0075] Figure 7 FIG. 1 is a block diagram of an electronic device 700 according to some embodiments of the present disclosure. The device 700 may be a device or apparatus described in an embodiment of the present disclosure. Figure 7 As shown, the device 700 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 701, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 702 or loaded from a storage unit 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The CPU / GPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704. Although not shown in FIG. Figure 7 As shown in FIG. 7 , device 700 may further include a co-processor.

[0076] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0077] The various methods or processes described above may be performed by the CPU / GPU 701. For example, in some embodiments, the methods may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the CPU / GPU 701, one or more steps or actions in the methods or processes described above may be performed.

[0078] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0079] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0080] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0081] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, and conventional procedural programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0082] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0083] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0084] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the equipment, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous frames can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the functions involved. It should also be noted that each frame in the block diagram and / or flow chart, and the combination of frames in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0085] Various embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the various embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various embodiments disclosed herein.

Claims

1. A method for outputting a visualized data processing result, comprising: Receiving input from a user in a graphical user interface GUI, wherein the input includes a data processing requirement of the user based on a language description; Determining an intent type of a user intent corresponding to the data processing requirement by performing intent recognition on the input using a first language model, wherein the intent type of the user intent includes at least one of the following: invalid question, query analysis, chart operation, or attribution insight; Based on the determined intent type, generating a target code for the data processing requirement by using an agent corresponding to the determined intent type by using a second language model, the target code being executable by a browser corresponding to the GUI, wherein performance of the second language model is higher than performance of the first language model, and a calling speed of the second language model is lower than a calling speed of the first language model; Running the generated target code through the browser to generate a visualized processing result for predetermined data to be processed; and providing, in the GUI, an output including the processing result in an interactive manner, The generation of the target code for the data processing requirement includes: In response to determining that the intent type of the user intent is the attribution insight, generating operation codes for insight operations and attribution operations for the predetermined data using the second language model using an agent corresponding to the attribution insight, the second language model including a second security language model used for authentication, The method further comprises: determining whether a model output of the second security language model for the predetermined data is structured data; In response to determining that the model output is the structured data, generating the operation code based on the model output; and In response to determining that the model output is not the structured data, generating insight information or attribution information for presentation to the user based on the model output.

2. The method according to claim 1, wherein the generation of the target code for the data processing requirement further comprises: In response to determining that the intent type of the user's intent is the invalid question, determining a length of the input indicative of the data processing requirement; responsive to determining that the length of the input is shorter than a length threshold, facilitating updating the input; as well as Re-perform intent recognition on the updated input using the first language model.

3. The method according to claim 1, wherein the generation of the target code for the data processing requirement further comprises: In response to determining that the intent type of the user intent is the query analysis, generating a first operation code of one or more operations corresponding to the data processing requirement by using the second language model and the first agent corresponding to the query analysis, The first agent indicates at least one of the following items for the predetermined data: aggregate analysis, filter query, and conditional sorting.

4. The method according to claim 3, further comprising: Based on a predetermined data dimension, the predetermined data is divided into a plurality of sub-data sets, The predetermined data dimensions include channel sources, and wherein at least one of the plurality of sub-data sets is visually differently provided to the user in response to a selection operation from the user, and All data in each of the plurality of sub-data sets are uniformly renamed in response to a renaming operation from the user.

5. The method according to claim 1, wherein the generation of the target code for the data processing requirement further comprises: In response to determining that the intention type of the user intention is the chart operation, generating a second operation code for a predetermined operation in an operation library corresponding to the data processing requirement by using the second language model and a second agent corresponding to the chart operation, The predetermined data includes chart data, and the second agent instructs at least one of the following for the chart data: switching chart type, chart restoration.

6. The method according to claim 1, wherein: Before the insight operation and the attribution operation are performed, the predetermined data is de-redundant by performing data reduction.

7. The method according to claim 6, further comprising: Before the insight operation and the attribution operation are performed, determining whether the security level of the predetermined data reaches a security threshold; as well as In response to determining that the security level of the predetermined data has reached the security threshold, the operation code is generated using the second security language model, the second security language model being enabled based on authentication of the user.

8. The method according to claim 1, further comprising: Based on the data processing history of the user, candidate inputs are generated for the user.

9. A device for outputting visualized data processing results, comprising: A demand receiving module, configured to receive input from a user in a graphical user interface GUI, wherein the input includes a user data processing demand based on a language description; an intent recognition module configured to determine an intent type of a user intent corresponding to the data processing requirement by performing intent recognition on the input using a first language model, wherein the intent type of the user intent includes at least one of the following: invalid question, query analysis, chart operation, or attribution insight; a code generation module configured to generate, based on the determined intent type, a target code for the data processing requirement by using an agent corresponding to the determined intent type by utilizing a second language model, wherein the target code is executable by a browser corresponding to the GUI, wherein performance of the second language model is higher than performance of the first language model, and a calling speed of the second language model is lower than a calling speed of the first language model; a result generating module configured to generate a visualized processing result for predetermined data to be processed by running the generated target code through the browser; and A result providing module is configured to provide an output including the processing result in an interactive manner in the GUI, The code generation module is further configured as follows: In response to determining that the intent type of the user intent is the attribution insight, generating operation codes for insight operations and attribution operations for the predetermined data using the second language model using an agent corresponding to the attribution insight, the second language model including a second security language model used for authentication, The apparatus further comprises a structural module configured to: determining whether a model output of the second security language model for the predetermined data is structured data; In response to determining that the model output is the structured data, generating the operation code based on the model output; and In response to determining that the model output is not the structured data, generating insight information or attribution information for presentation to the user based on the model output.

10. An electronic device comprising: processor; as well as A memory coupled to the processor, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the processor is caused to perform the method according to any one of claims 1 to 8.

11. A machine-readable storage medium having machine-executable instructions stored thereon, wherein the machine-executable instructions, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program which, when executed by a processor of a computer, causes the processor to perform the method according to any one of claims 1 to 8.

Images