Data analysis method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to the technical field of computers, and discloses a data analysis method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: displaying a data analysis page; in response to a first question input in an input control of the data analysis page, a first analysis result of the first question is displayed on the data analysis page, and an exploration control is displayed in an area, corresponding to the first analysis result, of the data analysis page; in response to an interaction operation for the exploration control, displaying a visual canvas of the first analysis result on the exploration analysis page to obtain an exploration analysis result of the first analysis result, the visual canvas being used for providing a data processing environment of the first analysis result; and in response to an interaction operation for a return control in the exploration analysis page, displaying an exploration analysis result on the data analysis page. The problem that the accuracy of a data analysis result is low can be solved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data analysis method, device, electronic device, storage medium, and program product. Background Art

[0002] At present, more and more natural language processing technologies are being integrated into data consumption tools to provide more intelligent data analysis and prediction capabilities. Some data analysis tools have begun to provide more advanced data analysis functions such as predictive modeling and natural language query. In related technologies, these data analysis tools mainly use conversational analysis. However, this conversational analysis method is often difficult to solve the problem in one go, and the accuracy of data analysis results is low. Summary of the invention

[0003] In view of this, the present disclosure provides a data analysis method, device, electronic device, storage medium and program product to solve the problem of low accuracy of data analysis results.

[0004] In a first aspect, the present disclosure provides a data analysis method, the method comprising:

[0005] Display the data analysis page;

[0006] In response to a first question input into an input control of the data analysis page, displaying a first analysis result of the first question on the data analysis page, wherein an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result;

[0007] In response to an interactive operation on the exploration control, displaying a visualization canvas of the first analysis result on an exploration analysis page to obtain an exploration analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result;

[0008] In response to an interactive operation on a return control in the exploratory analysis page, the exploratory analysis result is displayed on the data analysis page.

[0009] In a second aspect, the present disclosure provides a data analysis device, the device comprising:

[0010] A page display module, used to display a data analysis page;

[0011] a data analysis module, configured to respond to a first question input into an input control of the data analysis page and display a first analysis result of the first question on the data analysis page, wherein an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result;

[0012] an exploration and analysis module, configured to display a visualization canvas of the first analysis result on an exploration and analysis page in response to an interactive operation on the exploration control, so as to obtain an exploration and analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result;

[0013] The result display module is used to display the exploration and analysis results on the data analysis page in response to the interactive operation on the return control in the exploration and analysis page.

[0014] In a third aspect, the present disclosure provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the data analysis method of the first aspect by executing the computer instructions.

[0015] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the data analysis method of the first aspect.

[0016] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to enable a computer to execute the data analysis method of the first aspect.

[0017] The data analysis method provided by the embodiment of the present disclosure displays the first analysis result of the first question on the data analysis page in response to the first question input in the input control of the data analysis page. Therefore, a conversational interaction mode can be provided to quickly obtain the data analysis results. At the same time, the area of ​​the data analysis page corresponding to the first analysis result is displayed with an exploration control. Through the interactive operation on the exploration control, the visualization canvas of the first analysis result is displayed on the exploration analysis page to obtain the exploration analysis result of the first analysis result; wherein the visualization canvas is used to provide the data processing environment of the first analysis result. Therefore, in the case where the first analysis result does not meet the expectations, the first analysis result can be explored, analyzed and verified through the exploration control and the visualization canvas to obtain the exploration analysis result. Then, in response to the interactive operation on the return control in the exploration analysis page, the exploration analysis result is displayed on the data analysis page to achieve the synchronization of the conversational interaction model and the data analysis results in the exploration analysis mode. Therefore, the accuracy of the data analysis results can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a flow chart of a data analysis method according to an embodiment of the present disclosure;

[0020] Figure 2 is a schematic diagram of a first data analysis page according to an embodiment of the present disclosure;

[0021] Figure 3 is a schematic diagram of a first exploration and analysis page according to an embodiment of the present disclosure;

[0022] Figure 4 is a schematic diagram of a data analysis process according to an embodiment of the present disclosure;

[0023] Figure 5 is a schematic diagram of a details page according to an embodiment of the present disclosure;

[0024] Figure 6 is a schematic diagram of a second data analysis page according to an embodiment of the present disclosure;

[0025] Figure 7 is a schematic diagram of a third data analysis page according to an embodiment of the present disclosure;

[0026] Figure 8 is a schematic diagram of adding target content according to an embodiment of the present disclosure;

[0027] Fig. 9 is a schematic diagram of a second exploration and analysis page according to an embodiment of the present disclosure;

[0028] Fig.10 is a schematic diagram of a third exploration and analysis page according to an embodiment of the present disclosure;

[0029] Fig.11 is a schematic diagram of a task subscription page according to an embodiment of the present disclosure;

[0030] Fig.12 is a schematic diagram of data push according to an embodiment of the present disclosure;

[0031] Fig.13 is a schematic diagram of a data analysis framework according to an embodiment of the present disclosure;

[0032] Fig.14is a schematic diagram of another data analysis framework according to an embodiment of the present disclosure;

[0033] Fig.15 is a structural block diagram of a data analysis device according to an embodiment of the present disclosure;

[0034] Fig.16 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] At present, more and more natural language processing technologies are being integrated into data consumption tools to provide more intelligent data analysis and prediction capabilities. Some data analysis tools have begun to provide more advanced data analysis functions such as predictive modeling and natural language query. The development of natural language processing tools has led to a series of data analysis tools consuming data through natural language query.

[0041] In the related technologies, these data analysis tools mainly use conversational analysis. However, conversational analysis has the following shortcomings: First, end-to-end conversational analysis is difficult to solve the problem at one time, and users lack trust in the answers given by data analysis tools. Second, in conversational analysis, if you want to flexibly use natural language and accurately and completely express your demands, you need a certain degree of professionalism. Third, conversational analysis is more suitable for temporary queries, and the efficiency of each re-query is not as good as that of conventional data dashboards. Fourth, for ordinary users, it is difficult to conduct data analysis due to reasons such as lack of data set permissions, unclear data source selection logic, no answers to single questions or obvious wrong answers. Fifth, the accuracy of data analysis results of conversational analysis is low. According to incomplete statistics, the conversion rate of effective questions is about 70%, the probability of correct answers at one time is about 25.9%, and the probability of correct answers twice is about 30.2%. Sixth, some basic questions have no bottom-up logic, which makes it difficult for users to conduct data analysis in an interactive way when they first use it, for example, which data sets users have permissions for, and questions related to data sets. Seventh, in conversational analysis, the data presentation effect of one question and one answer is not good. Eighth, the entire data analysis process lacks closed-loop processing, for example, the next step is targeted and guiding questions, whether the questions have logic such as collection, sharing, and long-term memory.

[0042] Due to the above shortcomings, the accuracy of data analysis results in related technologies is low.

[0043] In view of this, according to an embodiment of the present disclosure, a data analysis method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] In this embodiment, a data analysis method is provided, which can be used in a data analysis platform. Figure 1 is a flow chart of a data analysis method according to an embodiment of the present disclosure, such as Figure 1 As shown, the process includes the following steps:

[0045] Step S101, displaying a data analysis page.

[0046] Specifically, a first analysis control corresponding to different language models is displayed on the data analysis page, and a language model suitable for the current data analysis scenario can be adopted by selecting the first analysis control to perform data analysis.

[0047] Step S102, in response to a first question input into an input control of a data analysis page, a first analysis result of the first question is displayed on the data analysis page, and an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result.

[0048] Specifically, Figure 2 As shown, an input control is displayed on the data analysis page, and the user can enter a first question through the input control. Then, in response to the input first question, a data analysis instruction is generated, and the data analysis instruction is used to determine a first analysis result of the first question. Then, the first analysis result is displayed on the data analysis page.

[0049] Specifically, Figure 2 As shown, an exploration control is displayed in the area of ​​the data analysis page corresponding to the first analysis result, and the exploration control is used to call the visualization canvas of the first analysis result to perform exploratory analysis on the first analysis result on the visualization canvas.

[0050] Step S103, in response to the interactive operation on the exploration control, displaying a visualization canvas of the first analysis result on the exploration analysis page to obtain the exploration analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result.

[0051] Specifically, in response to an interactive operation on the exploration control, an exploration analysis page is displayed, and a visualization canvas of the first analysis result is displayed on the exploration analysis page. Figure 3 As shown, different data nodes can be added or associated with the first analysis result on the visualization canvas. At the same time, it supports uploading of multiple modal contents such as pictures, notes, documents, etc. In this way, the data analysis ideas corresponding to the first question or the first analysis result can be freely organized and verified on the visualization canvas to obtain exploratory analysis results.

[0052] Step S104, in response to the interactive operation on the return control in the exploration and analysis page, the exploration and analysis results are displayed on the data analysis page.

[0053] Specifically, a return control is displayed on the exploration and analysis page, and the return control is used to return from the exploration and analysis page to the data analysis page. In response to an interactive operation on the return control, the data analysis page is displayed, and the exploration and analysis results are displayed on the data analysis page.

[0054] It should be noted that the data between the data analysis page and the exploration analysis page is synchronized.

[0055] The data analysis method provided in this embodiment displays the first analysis result of the first question on the data analysis page in response to the first question input in the input control of the data analysis page. Therefore, a conversational interaction mode can be provided to quickly obtain the data analysis results. At the same time, the area of ​​the data analysis page corresponding to the first analysis result is displayed with an exploration control. Through the interactive operation on the exploration control, the visualization canvas of the first analysis result is displayed on the exploration analysis page to obtain the exploration analysis result of the first analysis result; wherein the visualization canvas is used to provide the data processing environment of the first analysis result. Therefore, in the case where the first analysis result does not meet the expectations, the first analysis result can be explored, analyzed and verified through the exploration control and the visualization canvas to obtain the exploration analysis result. Then, in response to the interactive operation on the return control in the exploration analysis page, the exploration analysis result is displayed on the data analysis page to achieve the synchronization of the conversational interaction model and the data analysis results in the exploration analysis mode. Therefore, the accuracy of the data analysis results can be effectively improved.

[0056] In some optional implementations, the data analysis page further displays a first analysis control, and the first analysis control corresponds to at least one first language model. In response to the first question input in the input control of the data analysis page in step S102, displaying the first analysis result of the first question on the data analysis page includes:

[0057] Step a1: determining a target language model in response to a selection instruction for a first analysis control.

[0058] It is worth noting that the first analysis control corresponds to one or more first language models.

[0059] Specifically, in response to the selection instruction for the first analysis control, the first language model corresponding to the selected first analysis control is determined as the target language model. It can be understood that if the selected first analysis control corresponds to one first language model, the number of target language models is one. If the selected first analysis control corresponds to multiple first language models, the number of target language models is multiple.

[0060] Step a2: in response to a first question input into an input control of the data analysis page, displaying a first analysis result of the target language model for the first question on the data analysis page.

[0061] Specifically, in response to a first question input into an input control of a data analysis page, a data analysis instruction is generated, the data analysis instruction being used to determine a first analysis result of the target language model for the first question, wherein the first analysis result is obtained by performing data analysis based on the target language model, the target data source, and the first question.

[0062] The data analysis method provided in this embodiment can adaptively select a first language model suitable for the current data analysis scenario to perform data analysis through a first analysis control corresponding to at least one first language model, thereby effectively improving the accuracy of the data analysis result.

[0063] For example, Figure 2 As shown, the first analysis control 1 and the first analysis control 2 are provided in the data analysis page. If the user selects the first analysis control 1, the first language model corresponding to the first analysis control 1 is determined as the target language model used in this data analysis. Furthermore, the user can input questions through the input control of the data analysis page, and display the analysis results of the target language model for the input questions in the form of a dialogue. Based on this, the user can directly communicate with the language model suitable for different data analysis scenarios in a natural language manner, and display the data analysis results obtained by the language model in an intuitive and simple dialogue manner in the data analysis page, thereby realizing natural language conversational data analysis.

[0064] In some optional implementations, in response to the first question input into the input control of the data analysis page in step a2, displaying a first analysis result of the target language model for the first question on the data analysis page includes:

[0065] Step a21, in response to a first question input into an input control of a data analysis page, displaying a data analysis process of the target language model for the first question on the data analysis page.

[0066] Specifically, in the process of determining the first analysis result of the target language model for the first question, the data analysis process of the target language model for the first question can be displayed. The data analysis process includes at least one level of data analysis elements. The at least one level of data analysis elements includes at least one of searching for a specified data set, searching for a specified dimension, searching for a specified indicator, and searching for a filter item. Therefore, the data analysis process can be visualized.

[0067] For example, Figure 4As shown, taking the first question as "target product sales data in March, statistical trends, and express with a line chart", and the target language model as the language model corresponding to the first analysis control 1 as an example, in the process of determining the first analysis result of the target language model for the first question, the data analysis process of the target language model for the first question is displayed. For example, the search specifies the data set as "real-time closed-loop order wide table", the search specifies the dimension as "target product", the search specifies the indicator as "month-on-month growth rate", and the search filter item as "sales time from March 1 to March 31". And the status of the data analysis link corresponding to each data analysis element is displayed. At the same time, a pause control is displayed in the area corresponding to the input control on the data analysis page. The data analysis of the target language model for the first question can be paused in response to the interactive operation of the pause control. Not only that, the modified data analysis element can also be determined in response to the modification operation on the data analysis element. Then, the data analysis is performed again according to the modified data analysis element to obtain the corresponding analysis result.

[0068] Step a22, in response to the data analysis completion instruction for the first question, displaying the first analysis result on the data analysis page.

[0069] Specifically, when the first analysis process of the target language model for the first question is determined, a data analysis completion instruction is generated. Then, in response to the data analysis completion instruction, the first analysis result is displayed on the data analysis page.

[0070] It can be understood that after the user inputs the first question, the target language model enters the data analysis process for the first question. The data analysis process of the target language model is displayed through animation on the data analysis page. Then, the data analysis process is presented in a visual way. During the data analysis process, the user can also interrupt the data analysis process and modify the data analysis elements to re-analyze the data for the first question.

[0071] The data analysis method provided in this embodiment displays the data analysis process of the target language model for the first question on the data analysis page. Therefore, the data analysis process can be visualized to improve the experience of the data analysis service. At the same time, it is easy to modify the data analysis elements with problems in the data analysis process to further improve the accuracy of the data analysis results.

[0072] In some optional embodiments, the data analysis method of the present disclosure further includes:

[0073] Step b1, in response to an instruction to view the data analysis process of the first analysis result, displaying at least one level of data analysis elements in the data analysis process on a details page.

[0074] Specifically, at least one level of data analysis elements includes asking questions, searching for specified data sets, searching for specified dimensions, searching for specified indicators, executing screening conditions, and writing structured query language databases (see Figure 5 At least one of the following (writing SQL as shown).

[0075] Specifically, the area of ​​the data analysis page corresponding to the first analysis result also displays a viewing control, which is used to view the data analysis process of the first analysis result. In response to the interactive operation on the viewing control, a viewing instruction is generated, which is used to determine and display at least one level of data analysis elements in the data analysis process.

[0076] It should be noted that the data analysis process for the first analysis result is consistent with the data analysis process for the first question.

[0077] Step b2: in response to a modification operation on at least one level of data analysis elements, determining a modified data analysis element.

[0078] Specifically, a modification control is displayed in an area corresponding to the data analysis element on the details page. In response to an interactive operation on the modification control, a modification page is displayed. In response to the modification operation on the modification page, a modification instruction of the corresponding data analysis element is generated, and the modification instruction is used to determine the modified data analysis element.

[0079] Step b3: displaying the analysis results corresponding to the modified data analysis elements on the data analysis page.

[0080] Specifically, in response to the modified data analysis element, an analysis result corresponding to the modified data analysis element is determined, and the analysis result is displayed on the data analysis page.

[0081] Specifically, the details page can be displayed on one side of the data analysis page through a drawer, pop-up window, or other display formats.

[0082] The data analysis method provided in this embodiment displays at least one level of data analysis elements in the data analysis process on the details page. Therefore, the data analysis process can be visualized and the experience of data analysis services can be improved. At the same time, it is easy to modify the data analysis elements with problems in the data analysis process to further improve the accuracy of the data analysis results.

[0083] For example, Figure 5As shown, assume that the first analysis result includes answer 1 and answer 2, and prompt "Different answers were found in multiple specified data tables, please choose the answer you think is correct". Among them, answer 1 is the detailed data of Group A's products, and answer 1 shows "The total sales volume in the past three months is 70 million. The sales volume of product 1 in January, February and March is 2367. The sales volume of product 2 in January, February and March is 325". Answer 2 is the detailed operating data of the main products, and answer 2 shows "The total sales volume in the past three months is 68 million. The sales volume of product 1 in January is 4567, and the sales volume of product 1 in February and March is 2367. The sales volume of product 2 in January, February and March is 325" ( Figure 5 The data shown is only an example. It can be seen that the two answers show different sales quantities of product 1 in January. In the area corresponding to the first analysis result on the data analysis page, a viewing control for viewing the data analysis process is displayed (see Figure 5 In response to the interactive operation on the viewing control, a viewing instruction is generated to display the detail page. The detail page displays the data analysis process of the two answers. The user can view the data analysis process of the two answers, or modify the data analysis elements in the data analysis process to adjust the first analysis result of the first question.

[0084] In some optional implementations, at least one first display control is also displayed on the details page, and the first display control is used to determine how data analysis elements of at least one level are displayed on the details page.

[0085] In some optional embodiments, such as Figure 6 As shown, the data analysis page also displays the target data source for data analysis. The data analysis method disclosed in the present invention also includes:

[0086] Step c1: in response to an interactive operation on a target data source, displaying optional data sets, the optional data sets including at least one of a public data set and other permission data sets with access rights.

[0087] Optionally, the optional data set may also include other data sets that do not have access rights, and the area corresponding to the other data sets on the data analysis page displays a permission application control, which is used to apply for access rights to the corresponding other data sets. Alternatively, in response to an interactive operation on other data sets, an application instruction is generated, which is used to apply for access rights to other data sets.

[0088] Step c2: in response to a selection instruction for an optional data set, updating the target data source with the selected optional data set.

[0089] Specifically, in response to a selection operation on an optional data set, a selection instruction is generated, the selection instruction is used to determine the selected optional data set, and the target data source is updated to the selected optional data set.

[0090] The data analysis method provided in this embodiment displays an optional data set of at least one of the public data sets and other permission data sets with access rights. The target data source is updated using the selected optional data set. Therefore, on the one hand, the public data set can be provided as a backup data for data analysis to avoid the situation where the analysis results of the problem cannot be generated, thereby improving the data analysis effect. On the other hand, providing an optional data set for switching the target data source can explore data from different sources, adapt to changes in data analysis needs, and improve the generalization ability of data analysis.

[0091] It is worth noting that in order to ensure the security of the data, the permissions of the data set need to be opened before use, which makes it difficult for some users to quickly conduct data analysis. Therefore, in the data analysis method disclosed in the present invention, a public data set is provided for users to choose from, so as to guide users to conduct data analysis. At the same time, a permission data set with access rights is prepared for user roles or permission information, so as to select the target data source required for this data analysis from the public data set and the permission data set.

[0092] For example, Figure 6 As shown in the figure, it is assumed that the optional datasets include public datasets, permission dataset 1, and other datasets without access permissions. The prompt words "The following are datasets that you may be interested in but do not have access permissions for" and "Based on your role, the system has preset the following datasets for you" can be used to distinguish other datasets without access permissions, as well as accessible public datasets and permission datasets. Figure 6 As shown, assuming that the selected optional data set is a public data set, the public data set is displayed in the area corresponding to the target data source to prompt the user of the data set currently used.

[0093] For example, Figure 7 As shown, when the number of optional data sets selected is greater than 1, the area corresponding to the target data source on the data analysis page displays the number of selected data sets. For example, if the public data set and permission data set 1 are selected as the target data source, 2 data sets are displayed. At the same time, when the target data source switches data sets, an explicit prompt is given in the dialogue flow. Specifically, a prompt word is displayed on the data analysis page to indicate that the target data source has been successfully updated, for example: "The target data source has switched to all 2 specified data sets."

[0094] In some optional implementations, the data analysis page also displays a newly added theme control (see Figure 7The new theme control is used to add a new data analysis theme.

[0095] In some optional implementations, an upload control is displayed on the exploration and analysis page, and the upload control is used to upload the target content. The data analysis method of the present disclosure also includes:

[0096] Step d1, in response to an interactive operation on the upload control, displaying target content on a visualization canvas.

[0097] Specifically, an input control is also displayed on the exploration and analysis page, and the upload control can be displayed in an area corresponding to the input control on the exploration and analysis page.

[0098] Specifically, the above step d1 includes: generating an upload instruction in response to an interactive operation on the upload control, where the upload instruction is used to determine the target content to be uploaded so as to display the target content on the visualization canvas.

[0099] Optionally, in response to an interactive operation on an upload control, an upload page is displayed. In response to an upload operation of target content in the upload page, an upload instruction is generated to determine the target content. The target content is displayed on a visual canvas.

[0100] For example, Figure 8 As shown, the upload page displays a prompt "Add any content", and the user can add any content such as pictures, documents, files, etc. to the corresponding area of ​​the upload page to determine the target content.

[0101] Step d2, in response to the association operation on the first analysis result and the target content, the first analysis result and the target content are associated to obtain an exploration analysis result.

[0102] Specifically, the user can selectively connect the first analysis result with the target content according to his own ideas to associate the first analysis result with the target content. Alternatively, the second language model linked to the visualization canvas associates the first analysis result with the target content.

[0103] The data analysis method provided in this embodiment displays the target content on the visualization canvas in response to the interactive operation on the upload control. The first analysis result is associated with the target content to obtain the exploration analysis result. Therefore, the target content can be uploaded in the visualization canvas to perform exploration analysis and verification on the first analysis result, thereby improving the flexibility of the exploration analysis and improving the accuracy of the data analysis result.

[0104] It can be understood that the data analysis method of the present disclosure supports drilling down to canvas-style exploratory analysis, and users can add different data sources or file formats at any location of the visualization canvas to help them sort out their analysis ideas. Among them, the visualization canvas supports uploading of multiple modal contents such as tables, pictures, and documents. After uploading the target content, the user can associate the target content with the first analysis result according to his own ideas, or the second language model can summarize or suggest at least one of the target content and the first analysis result.

[0105] In some optional embodiments, the first analysis result includes first analysis data of at least one hierarchical dimension. The data analysis method of the present disclosure also includes: in response to a decomposition instruction for the first analysis data in the visualization canvas, obtaining second analysis data decomposed from the first analysis data to obtain an exploratory analysis result, wherein the exploratory analysis result is obtained based on the first analysis data and the second analysis data.

[0106] Specifically, in response to an interactive operation on the first analysis data in the visualization canvas, a decomposable type is displayed; in response to a selection instruction on the decomposable type, second analysis data is decomposed to obtain the second analysis data, and the second analysis data is obtained by decomposing the first analysis data based on the selected decomposable type.

[0107] Further, in response to a selection instruction for a decomposable type, second analysis data is obtained by decomposing, including: in response to a selection instruction for a decomposable type, a decomposable dimension corresponding to the selected decomposable type is displayed; in response to a selection instruction for a decomposable dimension, second analysis data is obtained by decomposing the first analysis data based on the selected decomposable dimension.

[0108] In some other optional embodiments, the exploration and analysis page also displays a second analysis control corresponding to the second language model. In response to the interactive operation on the second analysis control, a dialogue page corresponding to the second language model is displayed, and the dialogue page displays processing suggestions for the first analysis result or the first analysis data. In response to the question input based on the processing suggestion in the dialogue page, a disassembly instruction is generated, and the disassembly instruction is used to disassemble the selected first analysis data to disassemble the second analysis data. Alternatively, in response to the question input in the input control of the exploration and analysis page, a disassembly instruction is generated, and the disassembly instruction is used to disassemble the selected first analysis data to disassemble the second analysis data.

[0109] The data analysis method provided in this embodiment disassembles the first analysis data on a visualization canvas and displays the disassembled second analysis data to obtain an exploratory analysis result. Therefore, a more detailed analysis can be performed on the first analysis data to improve the accuracy of the data analysis result.

[0110] For example, Fig. 9 As shown, the first analysis data of at least one hierarchical dimension includes "sales volume is 32213.29-32143.01", and the sales volume includes dimensions decomposed by multiplication formula and dimensions decomposed by city dimension, such as "decomposed by multiplication formula, customer flow 40%, conversion rate 30%, customer unit price 30%", "decomposed by city dimension, city A 50%, city B 30%". Fig. 9 As shown in the figure, if the user clicks on the first analysis data corresponding to city A, the decomposable types of city A are displayed on the visualization canvas, such as dimension decomposition and formula decomposition. If dimension decomposition is selected, the decomposable dimensions are further displayed, such as decomposable dimension 1 and decomposable dimension 2. Then, the first analysis data is decomposed according to the selected decomposable dimension to obtain the corresponding second analysis data to determine the exploration analysis results.

[0111] For example, Fig.10 As shown, in response to the interactive operation of the second analysis control, a dialogue page corresponding to the second language model can be displayed, and processing suggestions are displayed on the dialogue page, for example, "If the decomposition is carried out according to the city dimension, city A is the dimension with the greatest influencing factor, and it is recommended to further decompose city A." Then, the user can perform natural language operations through the input controls of the dialogue page to generate decomposition instructions for the first analysis data to decompose and obtain the second analysis data. Alternatively, the user performs global natural language operations through the input controls of the exploration analysis page to generate decomposition instructions for the first analysis data to decompose and obtain the second analysis data.

[0112] In some optional implementations, a second analysis control is also displayed in the exploration analysis page, and the second analysis control is used to call a dialogue page corresponding to the second language model. The data analysis method of the present disclosure also includes:

[0113] Step e1, in response to an interactive operation on the second analysis control, displaying a dialog page.

[0114] Specifically, the dialog page corresponding to the second analysis control may be displayed through a floating layer, a drawer, a pop-up window, or other display methods.

[0115] Step e2: generating an operation instruction in response to a second question input on the dialogue page, wherein the operation instruction is generated based on the second language model and the second question, and the operation instruction is used to perform a target operation on the first analysis result in the visualization canvas.

[0116] Specifically, the target operation includes at least one of adding a data node of the first analysis result, explaining the first analysis result or the first analysis data, disassembling the first analysis data, and summarizing the content in the visualization canvas. In addition, other operations on the first analysis result, target content, first analysis data, or second analysis data in the visualization canvas are also included, which are not limited here. Therefore, the linkage between the second language model and the visualization canvas can be achieved.

[0117] It should be noted that the second analysis control may be the first analysis control or other analysis control except the first analysis control, that is, the second language model may be the same as the first language model or other language models may be used, which is not limited here.

[0118] The data analysis method provided in this embodiment displays a dialog page corresponding to the second analysis control. Then, in response to the second question input on the dialog page, an operation instruction is generated to perform a target operation on the first analysis result in the visualization canvas. Therefore, the second language model can be linked with the visualization canvas, thereby improving the efficiency and operability of data analysis.

[0119] In some optional implementations, the data analysis method of the present disclosure further includes: in response to a detail viewing instruction for the first analysis data, displaying data analysis details of the first analysis data on a detail page.

[0120] Specifically, in response to an interactive operation on the first analysis data, a detail viewing instruction is generated, where the detail viewing instruction is used to display data analysis details of the first analysis data on a detail page.

[0121] Specifically, the data analysis details include anomaly detection results for the first analysis data.

[0122] In some optional implementations, a save control is displayed in an area of ​​the data analysis page corresponding to the first analysis result, and the save control is used to store the first question and / or the first analysis result.

[0123] Specifically, the user can use the save control to store the first question alone, or store the first question and the first analysis result at the same time. In addition, the first analysis result can also be stored alone according to actual needs.

[0124] The data analysis method provided in this embodiment displays a save control to store the first question and / or the first analysis result, thereby facilitating subsequent query of the data analysis results and further data analysis.

[0125] In some optional embodiments, the data analysis method of the present disclosure further includes:

[0126] Step f1, in response to an interactive operation on a save control, displaying a task subscription page, where the task subscription page is used to store the first question to obtain a target subscription task corresponding to the first question.

[0127] Specifically, Fig.11 As shown, the task subscription page can be displayed in a floating layer, a pop-up window, or other display modes. The task subscription page displays at least one configuration item of the subscription question (the first question that can be stored in a configurable manner), the update rule, and the deadline of the subscribed task. In response to the configuration operation for the configuration item in the task subscription page, the target subscription task corresponding to the first question is determined. The user can save the target subscription task, or skip and directly save the first question.

[0128] Step f2: generating push content in response to the second analysis result fed back to the target subscription task.

[0129] Specifically, assuming that the update rule of the target subscription task is monthly update and the deadline is never deadline, the second analysis result of the target subscription task is obtained every month, and the push content is generated based on the second analysis result.

[0130] Step f3: Push the push content to the target push object.

[0131] Specifically, the corresponding push content can be pushed to the target push object in the form of email, document, message card, etc.

[0132] For example, Fig.12 As shown, the corresponding push content can be pushed to the target push object in the form of a message card.

[0133] It can be understood that in the data analysis method of the present disclosure, the configuration items required for the subscription task corresponding to the first question and the first analysis result can be pre-configured to support subscription to the first question and the first analysis result according to the configuration items.

[0134] The data analysis method provided in this embodiment displays a task subscription page to store the first question and obtains the target subscription task corresponding to the first question through interactive operations on the save control. Then, the push content corresponding to the target subscription task is pushed to the target push object. Therefore, temporary query questions can be converted into routine query needs, improving the data query efficiency of historical query questions. At the same time, the first question and the first analysis result can also be stored for a long time to achieve closed-loop processing.

[0135] In some optional implementations, the data analysis page includes a first display area for displaying the first question and the first analysis result, and a second display area for displaying the storage result corresponding to the save control.

[0136] Specifically, the first question and the first analysis result are displayed in the form of a dialogue in the first display area. At the same time, the first display area also displays the data analysis topic, target data source, data analysis process and other contents of the data analysis page. The stored questions, analysis results and other stored results are displayed in the second display area, as shown in the "My Space" section in the attached figure. At the same time, the second display area also displays the first analysis control.

[0137] The data analysis method provided in this embodiment divides the data analysis page into a first display area for displaying the first question and the first analysis result, and a second display area for displaying the storage result corresponding to the save control. Therefore, the display effect of the data analysis can be improved, and the storage result can be linked to perform data analysis.

[0138] In some optional implementations, the second display area further displays at least one second display control, and the second display control is used to determine the display mode of the storage result in the second display area.

[0139] Specifically, each second display control corresponds to a display mode, for example, a form, a slide, a video, etc. The user can switch the display mode of the storage result through the second display control.

[0140] It should be noted that the video display method can generate a video of the storage result in the form of an automatic slide show to automatically play the storage result.

[0141] In some optional implementations, the data analysis method of the present disclosure further includes: in response to a selection instruction for a storage result, displaying a summary content of the selected storage result in the first display area.

[0142] In some optional implementations, a sharing control is also displayed in the area of ​​the data analysis page corresponding to the first analysis result, and the sharing control is used to share the corresponding first question and / or first analysis result.

[0143] In some optional implementations, the data analysis page also displays a history record control, which is used to display historical questions and corresponding historical analysis results.

[0144] In some optional implementations, a summary generation control is also displayed in the exploration analysis page. The data analysis method disclosed herein also includes: determining a target summary object in response to a selection instruction for the first analysis data and / or the second analysis data disassembled from the first analysis data; generating a summary generation instruction in response to an interactive operation on the summary generation control, the summary generation instruction is used to summarize the target summary object to obtain an exploration analysis result, and the exploration analysis result includes the summary content of the target summary object.

[0145] In some optional implementations, an execution control is also displayed in the exploration and analysis page, and the execution control is used to perform data analysis on the content in the visualization canvas to obtain exploration and analysis results.

[0146] For example, Fig.13 As shown, in the data analysis method of the present disclosure, a multi-dialogue architecture divided for different language models is provided, and users can select the required language model in the language model warehouse through the required data analysis function to display the analysis controls corresponding to different language models, thereby creating a data analysis platform including language models for at least one function of registration, rapid query, attribution, detailed query, chart generation, indicator creation, query structured query language (Structured Query Language, referred to as SQL) database, dashboard analysis, and report generation. Among them, conversational guidance assistance can be provided for language models with different functions. And knowledge management, problem handling strategy, semantic governance, data set settings, abnormal diagnosis, scheduled tasks and other settings are provided in the data analysis platform.

[0147] In addition, it also provides the function of conversation query analysis, which can query the conversation records of different language models, for example, the conversation records of language model 2. In each conversation record, it provides the ability to ask questions, query the data analysis process, and analyze the results under different conversation identifiers (i.e., data analysis topics). At the same time, the conversation content can be explored and analyzed through information visualization, and the data analysis results can be modified and then generated, stored, subscribed, and shared. Not only that, questions, analysis results, etc. can also be stored in "My Space" (i.e., the area where the user's data analysis data is stored) and displayed. At the same time, conversation groups can be created for different language models, such as Fig.13 As shown, a conversation group is created for language model 3 and language model 4 to obtain the conversation record of the conversation group.

[0148] In addition, in the data analysis platform built based on the data analysis method disclosed in the present invention, you can also subscribe, share, report, etc. based on the questions, analysis results or conversation records stored in "My Space".

[0149] As a specific application example, Fig.14As shown, the data analysis platform using the data analysis method disclosed in the present invention mainly includes three modules: data source, language model, and processing of data analysis results. Among them, the module corresponding to the data source provides the capabilities of knowledge management, semantic governance, and data source management. The data source management includes the management of public data sets and permission data sets in local data files, for example, the management of public data sets, permission data sets 1, permission data sets 2, and other data sets in local data files such as local data files 1 and local data files 2. The module corresponding to the language model includes three parts: conversation records, process details of the data analysis process, and exploration and analysis. Conversation records include questions, analysis, and answers. The process details include process display, adjustment clarification, and adjustment of ideas. Exploration and analysis include autonomous exploration. The three parts work together. The module corresponding to the processing of data analysis results provides the ability to display the stored results of the data analysis process in "My Space", as well as share, subscribe, and push the target push objects.

[0150] As a specific application example, a target program is installed on a data analysis platform, and the target program is used to perform data analysis using the data analysis method disclosed in the present invention. In the data analysis platform, a dialogue interaction mode can be used to conduct dialogues with different language models to quickly obtain data analysis results (such as the first analysis results). If the data analysis results obtained through the dialogue do not meet expectations, you can drill down to the exploration and analysis page, use the canvas interaction mode, and analyze and verify the analysis hypothesis for the first question or the first analysis result on the visual canvas displayed on the exploration and analysis page, and form an analysis idea and exploration analysis result dominated by the operation object through repeated interactions.

[0151] It can be understood that in the data analysis method of the present invention, users are divided into two roles, one is ordinary users and the other is professional data analysts. The data analysis platform using the data analysis method of the present invention is compatible with these two types of users. For ordinary users or simple data analysis scenarios, a relatively simple dialogue interaction mode is provided, and users can have conversations with different language models to quickly obtain the desired data analysis results. If the dialogue interaction mode does not meet expectations, the user can manually click the exploration control to drill down to the exploration analysis page, which displays a visual canvas. The visual canvas is a tool for free exploration ideas based on a canvas. Users can freely analyze and verify their own analysis hypotheses on the visual canvas, and form user-led analysis ideas and exploration analysis results through repeated interactions, and synchronize the data of the canvas interaction mode and the dialogue interaction mode.

[0152] It is worth noting that in the data analysis method disclosed in the present invention, the data analysis platform integrates different language models for data analysis, which can simplify and democratize data analysis and gain insight into data consumption, and accelerate the transformation of data value by combining the language model capabilities, providing intelligent, personalized and situational solutions for ordinary users. In the data analysis method disclosed in the present invention, the interactive architecture of the entire data analysis has the following advantages: First, a public data set is preset or problems related to the data set are solved through targeted operational means. Second, the overall question-and-answer experience is simplified and optimized, the data analysis process is queried, and the data analysis elements in the data analysis process are externally displayed, the overall data analysis process is visualized, and the user has a sense of control, which can optimize the collection and sharing experience of the overall data analysis. Third, the concept of collaborative operation of multiple language models is exposed, which is a data development platform. Fourth, by corresponding to the analysis space of different language models, the concept of dialogue identification is hidden or removed, and all dialogues are divided according to the analysis control or language model. Different dialogue topics or contexts can be divided in the dialogue flow to simulate the real communication experience between people. Fifth, for professional consumers, we provide high-level autonomous exploration and analysis. When the answers provided by the language model are not satisfactory or the user has the ability to explore independently, high-level autonomous analysis can be performed through exploration controls and visualization canvases. Sixth, we create a personalized data analysis platform by continuously asking questions and collecting (i.e. saving questions and analysis results), and provide reporting, sharing and other functions on the data consumption side.

[0153] In this embodiment, a data analysis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0154] This embodiment provides a data analysis device, such as Fig.15 As shown, including:

[0155] The page display module 1501 is used to display the data analysis page;

[0156] A data analysis module 1502, configured to respond to a first question input in an input control of a data analysis page, and display a first analysis result of the first question on the data analysis page, wherein an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result;

[0157] An exploration and analysis module 1503 is used to display a visualization canvas of the first analysis result on the exploration and analysis page in response to an interactive operation on the exploration control, so as to obtain an exploration and analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result;

[0158] The result display module 1504 is used to display the exploration and analysis results on the data analysis page in response to the interactive operation on the return control in the exploration and analysis page.

[0159] In some optional implementations, the data analysis page further displays a first analysis control, and the first analysis control corresponds to at least one first language model. The data analysis module 1502 includes:

[0160] A language model selection unit, configured to determine a target language model in response to a selection instruction for the first analysis control;

[0161] The analysis result display unit is used to display a first analysis result of the target language model for the first question on the data analysis page in response to a first question input into an input control of the data analysis page.

[0162] In some optional embodiments, the analysis result display unit includes:

[0163] An analysis process display subunit, configured to display, on the data analysis page, a data analysis process of the target language model for the first question in response to the first question input into the input control of the data analysis page;

[0164] The analysis result display subunit is used to display the first analysis result on the data analysis page in response to the data analysis completion instruction for the first question.

[0165] In some optional embodiments, the data analysis device of the present disclosure further includes:

[0166] an analysis element display module, configured to display at least one level of data analysis elements in the data analysis process on a detail page in response to a viewing instruction for the data analysis process of the first analysis result;

[0167] An analysis element modification module, configured to determine a modified data analysis element in response to a modification operation on at least one level of data analysis elements;

[0168] The modified content display module is used to display the analysis results corresponding to the modified data analysis elements on the data analysis page.

[0169] In some optional implementations, the data analysis page also displays a target data source for data analysis. The data analysis device of the present disclosure also includes:

[0170] A data set display module, configured to display an optional data set in response to an interactive operation on a target data source, wherein the optional data set includes at least one of a public data set and other permission data sets with access rights;

[0171] The data set selection module is used to respond to a selection instruction for an optional data set and update the target data source with the selected optional data set.

[0172] In some optional implementations, an upload control is displayed on the exploration and analysis page, and the upload control is used to upload the target content. The data analysis device of the present disclosure also includes:

[0173] An upload content display module, used to display target content on a visual canvas in response to an interactive operation on the upload control;

[0174] The upload content association module is used to associate the first analysis result with the target content in response to an association operation on the first analysis result and the target content, so as to obtain an exploration analysis result.

[0175] In some optional implementations, the first analysis result includes first analysis data of at least one hierarchical dimension. The data analysis device of the present disclosure also includes:

[0176] The analysis data decomposition module is used to obtain second analysis data decomposed from the first analysis data in response to a decomposition instruction for the first analysis data in the visualization canvas, so as to obtain an exploration analysis result, wherein the exploration analysis result is obtained based on the first analysis data and the second analysis data.

[0177] In some optional implementations, a second analysis control is also displayed in the exploration analysis page, and the second analysis control is used to call a dialogue page corresponding to the second language model. The data analysis device of the present disclosure also includes:

[0178] A dialog page calling module, configured to display a dialog page in response to an interactive operation on the second analysis control;

[0179] An operation instruction generation module is used to generate an operation instruction in response to a second question input on the dialogue page, wherein the operation instruction is generated based on the second language model and the second question, and the operation instruction is used to perform a target operation on the first analysis result in the visualization canvas.

[0180] In some optional implementations, a save control is displayed in an area of ​​the data analysis page corresponding to the first analysis result, and the save control is used to store the first question and / or the first analysis result.

[0181] In some optional embodiments, the data analysis device of the present disclosure further includes:

[0182] A subscription task generation module, used for displaying a task subscription page in response to an interactive operation on a save control, where the task subscription page is used to store the first question to obtain a target subscription task corresponding to the first question;

[0183] A push content generation module, configured to generate push content in response to a second analysis result fed back on the target subscription task;

[0184] The analysis result push module is used to push the push content to the target push object.

[0185] In some optional implementations, the data analysis page includes a first display area for displaying the first question and the first analysis result, and a second display area for displaying the storage result corresponding to the save control.

[0186] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0187] The data analysis device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0188] The present disclosure also provides an electronic device having the above Fig.15 The data analysis device shown.

[0189] See also Fig.16 , Fig.16 is a structural block diagram of an electronic device provided by an optional embodiment of the present disclosure, such as Fig.16 As shown, the electronic device includes: one or more processors 1601, memory 1602, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.16 A processor 1601 is taken as an example.

[0190] The processor 1601 may be a central processing unit, a network processor or a combination thereof. The processor 1601 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.

[0191] The memory 1602 stores instructions executable by at least one processor 1601, so that the at least one processor 1601 executes the method shown in the above embodiment.

[0192] The memory 1602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1602 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 1602 may optionally include a memory remotely arranged relative to the processor 1601, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0193] The memory 1602 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 1602 may also include a combination of the above types of memory.

[0194] The electronic device also includes an input device 1603 and an output device 1604. The processor 1601, the memory 1602, the input device 1603 and the output device 1604 may be connected via a bus or other means. Fig.16 The example of connecting through bus is taken in the following.

[0195] The input device 1603 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 1604 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0196] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0197] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0198] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A data analysis method, characterized in that: The method comprises: Display the data analysis page; In response to a first question input into an input control of the data analysis page, displaying a first analysis result of the first question on the data analysis page, wherein an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result; In response to an interactive operation on the exploration control, displaying a visualization canvas of the first analysis result on an exploration analysis page to obtain an exploration analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result; In response to an interactive operation on a return control in the exploratory analysis page, the exploratory analysis result is displayed on the data analysis page.

2. The method according to claim 1, characterized in that The data analysis page further displays a first analysis control, the first analysis control corresponding to at least one first language model; in response to a first question input into the input control of the data analysis page, displaying a first analysis result of the first question on the data analysis page includes: In response to a selection instruction for the first analysis control, determining a target language model; In response to a first question input into an input control of the data analysis page, a first analysis result of the target language model for the first question is displayed on the data analysis page.

3. The method according to claim 2, characterized in that In response to the first question input into the input control of the data analysis page, displaying on the data analysis page a first analysis result of the target language model for the first question, comprises: In response to a first question input into an input control of the data analysis page, displaying on the data analysis page a data analysis process of the target language model for the first question; In response to a data analysis completion instruction for the first question, the first analysis result is displayed on the data analysis page.

4. The method according to claim 1, characterized in that The method further comprises: In response to a viewing instruction for the data analysis process of the first analysis result, displaying data analysis elements of at least one level in the data analysis process on a detail page; In response to a modification operation on the data analysis element of the at least one level, determining a modified data analysis element; The analysis results corresponding to the modified data analysis elements are displayed on the data analysis page.

5. The method according to claim 1, characterized in that: The data analysis page also displays a target data source for data analysis; the method further includes: In response to an interactive operation on the target data source, displaying an optional data set, the optional data set comprising at least one of a public data set and other permission data sets with access rights; In response to a selection instruction for the selectable data set, the target data source is updated with the selected selectable data set.

6. The method according to claim 1, characterized in that An upload control is displayed on the exploration and analysis page, and the upload control is used to upload target content; the method further includes: In response to an interactive operation on the upload control, displaying the target content on the visualization canvas; In response to an association operation on the first analysis result and the target content, the first analysis result and the target content are associated to obtain the exploration analysis result.

7. The method according to claim 1, characterized in that The first analysis result includes first analysis data of at least one hierarchical dimension; the method further includes: In response to a decomposition instruction for the first analysis data in the visualization canvas, second analysis data decomposed from the first analysis data is obtained to obtain the exploration analysis result, where the exploration analysis result is obtained based on the first analysis data and the second analysis data.

8. The method according to claim 1, characterized in that: The exploration and analysis page also displays a second analysis control, and the second analysis control is used to call a dialogue page corresponding to the second language model; the method also includes: In response to an interactive operation on the second analysis control, displaying the dialog page; In response to a second question input on the dialogue page, an operation instruction is generated, where the operation instruction is generated based on the second language model and the second question, and the operation instruction is used to perform a target operation on the first analysis result in the visualization canvas.

9. The method according to claim 1, characterized in that: A save control is displayed in an area of ​​the data analysis page corresponding to the first analysis result, and the save control is used to store the first question and / or the first analysis result.

10. The method according to claim 9, characterized in that The method further comprises: In response to an interactive operation on the save control, displaying a task subscription page, the task subscription page being used to store the first question to obtain a target subscription task corresponding to the first question; In response to a second analysis result fed back to the target subscription task, generating push content; The push content is pushed to the target push object.

11. The method according to claim 9, characterized in that The data analysis page includes a first display area for displaying the first question and the first analysis result, and a second display area for displaying the storage result corresponding to the save control.

12. A data analysis device, characterized in that: The device comprises: A page display module, used to display a data analysis page; a data analysis module, configured to respond to a first question input into an input control of the data analysis page and display a first analysis result of the first question on the data analysis page, wherein an exploration control is displayed in an area of ​​the data analysis page corresponding to the first analysis result; an exploration and analysis module, configured to display a visualization canvas of the first analysis result on an exploration and analysis page in response to an interactive operation on the exploration control, so as to obtain an exploration and analysis result of the first analysis result, wherein the visualization canvas is used to provide a data processing environment for the first analysis result; The result display module is used to display the exploration and analysis results on the data analysis page in response to the interactive operation on the return control in the exploration and analysis page.

13. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the data analysis method according to any one of claims 1 to 11 by executing the computer instructions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the data analysis method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the data analysis method according to any one of claims 1 to 11.

Images