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, the method comprises the following steps: displaying an exploration analysis page, displaying a visual canvas on the exploration analysis page, and displaying a first analysis result aiming at a first problem on the visual canvas; in response to an interaction instruction for the visual canvas, processing the first analysis result to obtain an exploration analysis result of the first analysis result; and displaying the exploration analysis result on the exploration 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, conversational analysis is often limited by the accuracy of input questions and the language model's ability to understand input questions, resulting in low accuracy of data analysis results. 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] Displaying an exploration and analysis page, wherein a visualization canvas is displayed on the exploration and analysis page, and a first analysis result for the first question is displayed on the visualization canvas;

[0006] In response to an interactive instruction for the visualization canvas, processing the first analysis result to obtain an exploratory analysis result of the first analysis result;

[0007] The exploratory analysis results are displayed on the exploratory analysis page.

[0008] In a second aspect, the present disclosure provides a data analysis device, the device comprising:

[0009] A first display module is used to display an exploration and analysis page, wherein the exploration and analysis page displays a visualization canvas, and the visualization canvas displays a first analysis result for the first question;

[0010] an exploration and analysis module, configured to process the first analysis result in response to an interactive instruction for the visualization canvas, and obtain an exploration and analysis result of the first analysis result;

[0011] The second display module is used to display the exploration and analysis results on the exploration and analysis page.

[0012] 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.

[0013] 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.

[0014] 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.

[0015] The data analysis method provided by the embodiment of the present disclosure displays a visualization canvas on an exploration analysis page; wherein, a first analysis result for a first question is displayed on the visualization canvas. Therefore, the visualization canvas can be used to provide a data processing environment for the first analysis result. In response to an interactive instruction for the visualization canvas, the first analysis result is processed to obtain an exploration analysis result of the first analysis result. Therefore, when the first analysis result does not meet expectations, the first analysis result can be subjected to a canvas-style interactive mode through the visualization canvas to perform exploration analysis and verification on the first analysis result to obtain an exploration analysis result. The exploration analysis result is displayed on the exploration analysis page. Therefore, the accuracy of the data analysis results can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1 is a flow chart of a data analysis method according to an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of a first data analysis page according to an embodiment of the present disclosure;

[0019] Figure 3 is a schematic diagram of a first exploration and analysis page according to an embodiment of the present disclosure;

[0020] Figure 4 is a schematic diagram of uploading target content according to an embodiment of the present disclosure;

[0021] Figure 5is a schematic diagram of a second exploration and analysis page according to an embodiment of the present disclosure;

[0022] Figure 6 is a schematic diagram of a third exploration and analysis page according to an embodiment of the present disclosure;

[0023] Figure 7 is a schematic diagram of a fourth exploration and analysis page according to an embodiment of the present disclosure;

[0024] Figure 8 is a schematic diagram of a details page according to an embodiment of the present disclosure;

[0025] Fig. 9 is a schematic diagram of a summary page according to an embodiment of the present disclosure;

[0026] Fig.10 is a schematic diagram of data push according to an embodiment of the present disclosure;

[0027] Fig.11 is a schematic diagram of a second data analysis page according to an embodiment of the present disclosure;

[0028] Fig.12 is a schematic diagram of a second display area according to an embodiment of the present disclosure;

[0029] Fig.13 is a structural block diagram of a data analysis device according to an embodiment of the present disclosure;

[0030] Fig.14 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] In the related technologies, these data analysis tools mainly use conversational analysis. However, conversational analysis has the following shortcomings: Conversational analysis is often limited by the accuracy of input questions and the language model's ability to understand input questions. The accuracy of data analysis results is low. According to incomplete statistics, the conversion rate of effective questions is about 70%, the probability of a correct answer in one go is about 25.9%, and the probability of a correct answer in two tries is about 30.2%. Conversational analysis is difficult to solve the problem in one go, and users lack trust in the answers given by data analysis tools.

[0038] 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.

[0039] 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:

[0040] Step S101 : displaying an exploration and analysis page, on which a visualization canvas is displayed, and a first analysis result for a first question is displayed on the visualization canvas.

[0041] Specifically, before displaying the exploration analysis page, the data analysis method of the present disclosure further includes: displaying the data analysis page; and 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. 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.

[0042] Furthermore, the data analysis page also displays an analysis control, and the analysis control corresponds to at least one language model. The above-mentioned displaying 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 includes: in response to the selection instruction for the analysis control on the data analysis page, determining the language model corresponding to the selected analysis control as the target language model; in response to the first question input in the input control of the data analysis page, generating a data analysis instruction, the data analysis instruction is used to determine the 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.

[0043] It should be noted that if the analysis control corresponds to multiple language models, there are multiple target language models, and the first analysis results of each target language model for the first question are displayed in the form of a group dialogue on the data analysis page.

[0044] For example, Figure 2 As shown, analysis controls 1 and 2 are provided in the data analysis page. If the user selects analysis control 1, the language model corresponding to analysis control 1 is determined as the target language model used for this data analysis. Furthermore, the user can input questions through the input controls of the data analysis page, and the analysis results of the target language model for the input questions are displayed 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 way, and display the data analysis results obtained by the language model in an intuitive and simple dialogue way in the data analysis page, thereby realizing natural language conversational data analysis.

[0045] Furthermore, the data analysis page also displays an exploration control for the first analysis result. Then, in response to an interactive operation on the exploration control, the exploration analysis page is displayed.

[0046] Step S102: In response to an interactive instruction on the visualization canvas, the first analysis result is processed to obtain an exploratory analysis result of the first analysis result.

[0047] Specifically, 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 multimodal content, such as pictures, notes, documents, etc. The interactive instructions include instructions for uploading target content, instructions for associating target content with the first analysis result, instructions for disassembling the first analysis data in the first analysis result, 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.

[0048] Step S103: Display the exploration and analysis results on the exploration and analysis page.

[0049] It should be noted that a return control is also displayed on the exploration and analysis page. In response to an interactive operation on the return control, the user can jump from the exploration and analysis page to the data analysis page, where the exploration and analysis results are displayed. Data synchronization between the data analysis page and the exploration and analysis page.

[0050] The data analysis method provided in this embodiment displays a visualization canvas on an exploration analysis page; wherein, a first analysis result for a first question is displayed on the visualization canvas. Therefore, the visualization canvas can be used to provide a data processing environment for the first analysis result. In response to an interactive instruction for the visualization canvas, the first analysis result is processed to obtain an exploration analysis result of the first analysis result. Therefore, when the first analysis result does not meet expectations, the first analysis result can be subjected to a canvas-style interactive mode through the visualization canvas to perform exploration analysis and verification on the first analysis result to obtain an exploration analysis result. The exploration analysis result is displayed on the exploration analysis page. Therefore, the accuracy of the data analysis results can be effectively improved.

[0051] For example, Figure 2As shown, assuming that the first question for the target analysis object is "What is the main reason for the decline in sales?", if analysis control 1 is selected, the language model corresponding to analysis control 1 is used to process the first question. Assume that the first analysis result of the language model of analysis control 1 for the first question includes "City A is the main driving factor for the decline in sales" and the first analysis data of at least one hierarchical dimension. The first analysis data of at least one hierarchical dimension includes "sales are 32213.29-32143.01", and the dimensions corresponding to sales include dimensions decomposed by multiplication formulas and dimensions decomposed by city dimensions, such as "decomposed by multiplication formula, customer flow 40%, conversion rate 30%, and average customer spending 30%", "decomposed by city dimension, city A 50%, city B 30%". As Figure 2 As shown, in the data analysis page, the area for the first analysis result displays an exploration control, through which you can drill down to the canvas-style exploratory analysis. Figure 3 As shown, the exploration analysis page displays the first analysis data of at least one hierarchical dimension obtained from the data analysis page. The user can add content of different modes on the visualization canvas to help the user sort out the analysis ideas, thereby obtaining the exploration analysis results.

[0052] In some optional implementations, an upload control is displayed on the visualization canvas, and the upload control is used to upload the target content. In response to the interactive instruction for the visualization canvas in the above step S102, the first analysis result is processed to obtain an exploratory analysis result of the first analysis result, including:

[0053] Step a1: In response to an interactive operation on the upload control, the target content is displayed on a visual canvas.

[0054] Specifically, the exploration and analysis page also displays an upload control, which can be displayed in the area corresponding to the input control of the exploration and analysis page. Alternatively, the upload control is displayed in other areas of the exploration and analysis page except the input control, and the display position of the upload control is not limited here.

[0055] Specifically, the above step a1 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.

[0056] It is worth noting that the target content includes content of at least one modality, and the at least one modality includes at least one of a table, a picture, a document, and other modalities, thereby supporting multiple content uploads in the visualization canvas.

[0057] 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.

[0058] For example, Figure 4 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.

[0059] Step a2: in response to an instruction to associate the target content with the first analysis result, the target content is associated with the first analysis result to obtain an exploration analysis result.

[0060] 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 language model linked to the visualization canvas associates the first analysis result with the target content to obtain an exploratory analysis result.

[0061] 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.

[0062] 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 files at any position of the visualization canvas to help them sort out their analysis ideas. Figure 5 As shown, the visualization canvas supports uploading of multiple modal contents such as tables, pictures, documents, etc. After uploading the target content, the user can associate the target content with the first analysis result according to his own ideas, or the language model can summarize or suggest at least one of the target content and the first analysis result.

[0063] In some optional implementations, the first analysis result includes first analysis data of at least one hierarchical dimension. In the above step S102, in response to the interactive instruction for the visualization canvas, the first analysis result is processed to obtain an exploratory analysis result of the first analysis result, including: in response to the decomposition instruction for the first analysis data in the visualization canvas, second analysis data decomposed from the first analysis data is obtained to obtain an exploratory analysis result, and the exploratory analysis result is obtained based on the first analysis data and the second analysis data.

[0064] Specifically, for each first analysis data, the first analysis data can be disassembled using the selected optional disassembly type to obtain the second analysis data. Further, the optional disassembly type corresponds to at least one recommended disassembly dimension, and the first analysis data can be disassembled using the selected recommended disassembly dimension to obtain the second analysis data.

[0065] In other optional embodiments, such as Figure 5 As shown, the exploration and analysis page also displays an analysis control, which corresponds to a language model linked to the visualization canvas, and the analysis control is used to call a dialogue page corresponding to the language model. In response to the interactive operation of the analysis control in the exploration and analysis page, a dialogue page corresponding to the 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 obtain the second analysis data. Alternatively, in response to the question input into 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 obtain the second analysis data.

[0066] 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, the first analysis data can be analyzed in more detail to improve the accuracy of the data analysis result.

[0067] In some optional implementations, in response to the decomposition instruction for the first analysis data in the visualization canvas, obtaining the second analysis data decomposed from the first analysis data includes:

[0068] Step b1: in response to a disassembly instruction for the first analysis data, display corresponding optional disassembly types.

[0069] Specifically, the optional decomposition type includes at least one of dimensional decomposition and formula decomposition.

[0070] For example, Figure 6 As shown, in response to the interactive operation on the first analysis data corresponding to city A, a disassembly instruction is generated. In response to the disassembly instruction, the disassembly types are displayed in the visualization canvas, for example, dimension disassembly and formula disassembly.

[0071] Step b2, in response to a selection instruction for an optional disassembly type, obtaining second analysis data obtained by disassembling the first analysis data, wherein the second analysis data is obtained by disassembling the first analysis data based on the selected optional disassembly type.

[0072] Exemplarily, if the selected decomposable type is dimensional decomposition, the first analysis data is decomposed by dimensional decomposition to obtain the second analysis data. If the selected decomposable type is formula decomposition, the first analysis data is decomposed by formula decomposition to obtain the second analysis data.

[0073] The data analysis method provided in this embodiment displays the optional disassembly type corresponding to the first analysis data. The first analysis data is disassembled based on the selected optional disassembly type to obtain the second analysis data. Therefore, the first analysis data can be analyzed in a more detailed manner to further improve the accuracy of the data analysis results.

[0074] In some optional implementations, in response to the selection instruction for the optional decomposition type in step b2, obtaining the second analysis data decomposed from the first analysis data includes:

[0075] Step b21: in response to a selection instruction for an optional disassembly type, display a corresponding recommended disassembly dimension.

[0076] For example, Figure 7 As shown, if the selected decomposable type is dimensional decomposition, the recommended decomposition dimensions corresponding to the dimensional decomposition are displayed, for example, recommended decomposition dimension 1 and recommended decomposition dimension 2.

[0077] Step b22, in response to a selection instruction for a recommended decomposition dimension, obtain second analysis data decomposing the first analysis result, wherein the second analysis data is obtained by decomposing the first analysis data based on the selected recommended decomposition dimension.

[0078] For example, if the recommended decomposition dimension 1 is selected, the first analysis data is decomposed using the recommended decomposition dimension 1 to obtain the second analysis data. If the recommended decomposition dimension 2 is selected, the first analysis data is decomposed using the recommended decomposition dimension 2 to obtain the second analysis data.

[0079] The data analysis method provided in this embodiment displays the recommended disassembly dimensions of the selected optional disassembly type, and disassembles the first analysis data based on the selected recommended disassembly dimensions to obtain the second analysis data. Therefore, the analysis ideas can be expanded in the form of a mind map, which better maps the data analysis ideas and improves the exploration and analysis effect.

[0080] 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.

[0081] 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.

[0082] Specifically, the data analysis details include anomaly detection results for the first analysis data.

[0083] For example, Figure 8 As shown in the figure, if you need to view the data analysis details of the city dimension disassembly, you can click the data analysis node corresponding to the city dimension disassembly to display the details page, and the data analysis details corresponding to the city dimension disassembly will be displayed on the details page. For example, the contribution rate, change rate, change value, baseline period value, observation period value, lead rate, lead rate change trend, anomaly detection results, etc. corresponding to each city dimension under the city dimension disassembly.

[0084] The data analysis method provided in this embodiment displays the data analysis details of the first analysis data on the details page in response to the detail viewing instruction for the first analysis data. Therefore, the data situation represented by the first analysis data can be understood through the data analysis details, so as to find and correct potential problems.

[0085] In some optional implementations, a summary generation control is displayed in the exploration analysis page. The data analysis method of the present disclosure also includes:

[0086] Step c1, in response to a selection instruction for the first analysis data and / or the second analysis data decomposed from the first analysis data, determining a target summary object.

[0087] Specifically, the user may select at least one first analysis data as the target summary object, or select at least one second analysis data as the target summary object, or select at least one first analysis data and second analysis data as the target summary objects.

[0088] Step c2, in response to the interactive operation on the summary generation control, summarize the target summary object to obtain the exploration analysis result.

[0089] Specifically, in response to an interactive operation on a summary generation control, a summary generation instruction is generated, and the summary generation instruction is used to summarize the target summary object, obtain the summary content of the target summary object, and obtain the exploration analysis result. The exploration analysis result includes the summary content of the target summary object.

[0090] For example, Fig. 9 As shown, the user can click the summary generation control in the exploration and analysis page to generate a summary generation instruction to obtain the summary content of the selected target summary object. In addition, the target summary object can be summarized in a natural language interactive mode through the input control in the exploration and analysis page or the dialogue page to obtain the summary content. Furthermore, the summary page is displayed, and the summary content is displayed on the summary page.

[0091] The data analysis method provided in this embodiment selects the first analysis data and / or the second analysis data as the target summary object. Then, in response to the interactive operation of the summary generation control, the target summary object is summarized to obtain the exploration analysis result. Therefore, it is possible to summarize and analyze more fine-grained data, extract key information of the target summary object, verify the correctness of the target summary object or the first analysis result, and thus improve the accuracy of the data analysis result.

[0092] In some optional implementations, an analysis control is displayed in the exploration analysis page, and the analysis control is used to call a dialog page corresponding to the language model. In response to the interactive instruction for the visualization canvas in the above step S102, the first analysis result is processed to obtain an exploration analysis result of the first analysis result, including:

[0093] Step d1, in response to an interactive operation on the analysis control, displaying a dialog page.

[0094] Specifically, the conversation page may be displayed through a floating layer, a drawer, a pop-up window, or the like.

[0095] Step d2, in response to the second question input in the input control of the dialogue page, generating an interaction instruction, wherein the interaction instruction is generated based on the language model and the second question.

[0096] Specifically, the second question includes at least one of a question for 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 questions for operating 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.

[0097] Step d3, in response to the interactive instruction, processing the first analysis result to obtain an exploration analysis result.

[0098] It can be understood that the interactive instruction is used to perform target processing on the first analysis result, and the target processing 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, the target processing also includes operations on the first analysis result, target content, first analysis data, or second analysis data in the visualization canvas, which are not limited here. Therefore, the linkage between the language model and the visualization canvas can be achieved.

[0099] It should be noted that the analysis controls in the exploration and analysis page can be the same as the analysis controls in the data analysis page. That is, the language model linked to the visualization canvas can be the same as the language model linked to the data analysis page, or other language models can be used, which are not limited here.

[0100] The data analysis method provided in this embodiment displays a dialog page in response to an interactive operation on an analysis control in an exploration analysis page. In response to a second question input in the dialog page, an interactive instruction is generated to perform corresponding processing on the first analysis result in the visualization canvas. Therefore, the language model and the visualization canvas can be linked, thereby improving the efficiency and operability of data analysis.

[0101] In some optional embodiments, the data analysis method of the present disclosure further includes: generating an interactive instruction in response to a third question input into an input control in the exploration analysis page, wherein the interactive instruction is used to perform target processing on the first analysis result in the visualization canvas.

[0102] It can be understood that users can directly perform global natural language operations through the input controls in the exploration and analysis page, or call up the dialogue page corresponding to the analysis controls in the exploration and analysis page to perform global natural language operations, thereby realizing the linkage between the language model and the visualization canvas, and improving the efficiency of data analysis for the content in the visualization canvas.

[0103] 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.

[0104] In some optional embodiments, a save control is displayed in an area of ​​the data analysis page corresponding to the target analysis result, and the save control is used to store the first question and / or the target analysis result, where the target analysis result includes the first analysis result or the exploratory analysis result corresponding to the first question.

[0105] Specifically, the first question may be stored separately through the save control, or the first question and the target analysis result may be stored simultaneously. In addition, the target analysis result may be stored separately according to actual needs.

[0106] The data analysis method provided in this embodiment stores the first question and / or target analysis result by saving the control, thereby facilitating subsequent query of the data analysis result and further data analysis.

[0107] In some optional embodiments, the data analysis method of the present disclosure further includes:

[0108] Step e1, in response to an interactive operation on a save control, a task subscription page is displayed, where the task subscription page is used to store the first question to obtain a target subscription task corresponding to the first question.

[0109] Specifically, Fig.10 As shown, the task subscription page can be displayed by a floating layer, a pop-up window, or the like. The task subscription page displays at least one configuration item of the subscription question, update rule, and deadline of the subscribed task. The subscription question can be configured as the first question of the target storage. 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.

[0110] Step e2: generating push content in response to the second analysis result fed back to the target subscription task.

[0111] 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.

[0112] Step e3: Push the push content to the target push object.

[0113] Specifically, the corresponding push content can be pushed to the target push object in the form of email, document, message card, etc.

[0114] For example, Fig.10 As shown, the corresponding push content can be pushed to the target push object in the form of a message card.

[0115] 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 target analysis result can be pre-configured to support subscription to the first question and the target analysis result according to the configuration items.

[0116] 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 target analysis results can also be stored for a long time.

[0117] It is worth mentioning that the content generated in the exploration and analysis page can be synchronized to the conversation flow of the data analysis page, or shared and exported.

[0118] In some optional implementations, the data analysis page includes a first display area for displaying the first question and the target analysis result, and a second display area for displaying the storage result corresponding to the save control.

[0119] Specifically, the first question and the target 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 (if the target data source is a public data set), 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, and the "My Space" section in the attached figure can be seen. At the same time, the second display area also displays analysis controls corresponding to different language models.

[0120] 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 target 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.

[0121] 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.

[0122] Specifically, Fig.11 As shown, the user can select the storage results displayed in the second display area, and display the summary content of the selected storage results in the first display area, to perform data analysis of the collected questions and analysis results to improve the query efficiency of the collected query questions and analysis results.

[0123] The data analysis method provided in this embodiment, when selecting a storage result, displays the summary content of the selected storage result in the first display area, thereby improving the query efficiency of the collected query questions and analysis results.

[0124] In some optional implementations, the second display area displays at least one display control, and the display control is used to determine the display mode of the storage result in the second display area.

[0125] Specifically, each display control corresponds to a display mode, such as a form, a slide, a video, etc. The user can switch the display mode of the storage result through the display control. Fig.12 As shown, each stored result can be displayed in a slide show manner.

[0126] 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.

[0127] The data analysis method provided in this embodiment displays at least one display control in the second display area, so it is possible to flexibly adjust the display mode of the storage results and improve the display effect of the data analysis results.

[0128] In some optional implementations, the second display area corresponds to an area for storing results, and also displays a download control for downloading the stored results.

[0129] In some optional implementations, the second display area corresponds to an area for storing results, and also displays a sharing control for sharing the stored results.

[0130] In some optional implementations, the data analysis page corresponds to an area of ​​the target analysis result and further displays a download control for downloading the first question and the target analysis result.

[0131] In some optional implementations, the data analysis page corresponds to an area of ​​the target analysis result and also displays a sharing control for sharing the first question and the target analysis result.

[0132] As a specific application example, a target program is installed on the data analysis platform, and the target program is used to perform data analysis using the data analysis method disclosed in the present invention. Users can perform data analysis through the data analysis platform to obtain analysis results of input questions. If the obtained analysis results do not meet expectations, the canvas-style interactive mode is used to explore and analyze the analysis results to verify the correctness of the analysis results.

[0133] It is worth noting that, in the case where the data analysis results do not meet expectations, the data analysis method disclosed in the present invention can drill down to the exploration analysis page through the exploration control in the data analysis page, freely verify the analysis hypothesis on the visual canvas displayed on the exploration analysis page, and form user-led analysis ideas and results through repeated interactions, thus realizing user-led graphical user interface (GUI) canvas-style interaction. Therefore, it can meet different data analysis needs.

[0134] 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.

[0135] This embodiment provides a data analysis device, such as Fig.13 As shown, including:

[0136] A first display module 1301 is used to display an exploration and analysis page, where a visualization canvas is displayed on the exploration and analysis page, and a first analysis result for a first question is displayed on the visualization canvas;

[0137] An exploration and analysis module 1302 is used to process the first analysis result in response to an interactive instruction on the visualization canvas to obtain an exploration and analysis result of the first analysis result;

[0138] The second display module 1303 is used to display the exploration and analysis results on the exploration and analysis page.

[0139] In some optional implementations, an upload control is displayed on the visualization canvas, and the upload control is used to upload the target content. The exploration and analysis module 1302 includes:

[0140] A data uploading unit, configured to display target content on a visualization canvas in response to an interactive operation on the upload control;

[0141] The data association unit is used to associate the target content with the first analysis result in response to an association instruction for the target content and the first analysis result, so as to obtain an exploration analysis result.

[0142] In some optional implementations, the first analysis result includes first analysis data of at least one hierarchical dimension. The exploration analysis module 1302 includes:

[0143] The data decomposition unit 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.

[0144] In some optional implementations, the data disassembly unit includes:

[0145] a type selection subunit, configured to display corresponding optional disassembly types in response to a disassembly instruction for the first analysis data;

[0146] The data disassembly subunit is used to obtain second analysis data disassembled from the first analysis data in response to a selection instruction for an optional disassembly type, wherein the second analysis data is obtained by disassembling the first analysis data based on the selected optional disassembly type.

[0147] In some optional embodiments, the data disassembly subunit is specifically used to: in response to a selection instruction for an optional disassembly type, display the corresponding recommended disassembly dimension; in response to a selection instruction for the recommended disassembly dimension, obtain second analysis data disassembled from the first analysis result, and the second analysis data is obtained by disassembling the first analysis data based on the selected recommended disassembly dimension.

[0148] In some optional embodiments, the data analysis device of the present disclosure further includes:

[0149] The detail viewing module is used to display data analysis details of the first analysis data on a detail page in response to a detail viewing instruction for the first analysis data.

[0150] In some optional implementations, a summary generation control is displayed in the exploration analysis page. The data analysis device of the present disclosure also includes:

[0151] An object selection module, configured to determine a target summary object in response to a selection instruction for the first analysis data and / or second analysis data decomposed from the first analysis data;

[0152] The data summarizing module is used to summarize the target summary object in response to the interactive operation on the summary generation control to obtain the exploration analysis result.

[0153] In some optional implementations, an analysis control is displayed in the exploration and analysis page, and the analysis control is used to call a dialog page corresponding to the language model. The exploration and analysis module 1302 includes:

[0154] A page calling unit, configured to display a dialog page in response to an interactive operation on the analysis control;

[0155] an instruction generating unit, configured to generate an interactive instruction in response to a second question input into an input control of the dialogue page, wherein the interactive instruction is generated based on the language model and the second question;

[0156] The data processing unit is used to process the first analysis result in response to the interactive instruction to obtain the exploration analysis result.

[0157] 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.

[0158] 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.

[0159] The present disclosure also provides an electronic device having the above Fig.13 The data analysis device shown.

[0160] See also Fig.14 , Fig.14 is a structural block diagram of an electronic device provided by an optional embodiment of the present disclosure, such as Fig.14 As shown, the electronic device includes: one or more processors 1401, memory 1402, 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 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.14 A processor 1401 is taken as an example.

[0161] The processor 1401 may be a central processing unit, a network processor or a combination thereof. The processor 1401 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.

[0162] The memory 1402 stores instructions executable by at least one processor 1401 , so that the at least one processor 1401 executes the method shown in the above embodiment.

[0163] The memory 1402 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 1402 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 1402 may optionally include a memory remotely arranged relative to the processor 1401, 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.

[0164] The memory 1402 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 1402 may also include a combination of the above types of memory.

[0165] The electronic device also includes an input device 1403 and an output device 1404. The processor 1401, the memory 1402, the input device 1403 and the output device 1404 may be connected via a bus or other means. Fig.14 The example of connecting through bus is taken in the following.

[0166] The input device 1403 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 1404 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.

[0167] 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.

[0168] 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.

[0169] 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: Displaying an exploration and analysis page, wherein a visualization canvas is displayed on the exploration and analysis page, and a first analysis result for the first question is displayed on the visualization canvas; In response to an interactive instruction for the visualization canvas, processing the first analysis result to obtain an exploratory analysis result of the first analysis result; The exploratory analysis results are displayed on the exploratory analysis page.

2. The method according to claim 1, characterized in that An upload control is displayed on the visualization canvas, and the upload control is used to upload target content; The step of processing the first analysis result in response to the interactive instruction for the visualization canvas to obtain an exploratory analysis result of the first analysis result includes: In response to an interactive operation on the upload control, displaying the target content on the visualization canvas; In response to an instruction to associate the target content with the first analysis result, the target content is associated with the first analysis result to obtain the exploration analysis result.

3. The method according to claim 1, characterized in that The first analysis result includes first analysis data of at least one hierarchical dimension; The step of processing the first analysis result in response to the interactive instruction for the visualization canvas to obtain an exploratory analysis result of the first analysis result 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.

4. The method according to claim 3, characterized in that The step of obtaining second analysis data decomposed from the first analysis data in response to the decomposition instruction for the first analysis data in the visualization canvas includes: In response to the disassembly instruction for the first analysis data, displaying a corresponding optional disassembly type; In response to a selection instruction for the optional disassembly type, the second analysis data obtained by disassembling the first analysis data is obtained, where the second analysis data is obtained by disassembling the first analysis data based on the selected optional disassembly type.

5. The method according to claim 4, characterized in that The step of obtaining the second analysis data obtained by decomposing the first analysis data in response to the selection instruction for the optional decomposition type includes: In response to a selection instruction for the optional disassembly type, displaying a corresponding recommended disassembly dimension; In response to a selection instruction for the recommended decomposition dimension, the second analysis data decomposed from the first analysis result is obtained, where the second analysis data is obtained by decomposing the first analysis data based on the selected recommended decomposition dimension.

6. The method according to claim 3, characterized in that The method further comprises: In response to a detail viewing instruction for the first analysis data, data analysis details of the first analysis data are displayed on a detail page.

7. The method according to claim 3, characterized in that The exploration analysis page displays a summary generation control; the method further includes: In response to a selection instruction for the first analysis data and / or second analysis data decomposed from the first analysis data, determining a target summary object; In response to the interactive operation on the summary generation control, the target summary object is summarized to obtain the exploration analysis result.

8. The method according to claim 1, characterized in that An analysis control is displayed in the exploration and analysis page, and the analysis control is used to call a dialogue page corresponding to a language model; The step of processing the first analysis result in response to the interactive instruction for the visualization canvas to obtain an exploratory analysis result of the first analysis result includes: In response to an interactive operation on the analysis control, displaying the dialog page; In response to a second question input in an input control of the dialog page, generating the interaction instruction, wherein the interaction instruction is generated based on the language model and the second question; In response to the interactive instruction, the first analysis result is processed to obtain the exploration analysis result.

9. A data analysis device, characterized in that: The device comprises: A first display module is used to display an exploration and analysis page, wherein the exploration and analysis page displays a visualization canvas, and the visualization canvas displays a first analysis result for the first question; an exploration and analysis module, configured to process the first analysis result in response to an interactive instruction for the visualization canvas, and obtain an exploration and analysis result of the first analysis result; The second display module is used to display the exploration and analysis results on the exploration and analysis page.

10. 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 8 by executing the computer instructions.

11. 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 8.

12. 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 8.

Images