Data analysis method and device, computer device, storage medium and product

Abstract

The application relates to a data analysis method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: in response to a data analysis triggering operation triggered by a target identity, displaying a data analysis configuration interface; in an index selection area, displaying candidate indexes to which the target identity has access permission; acquiring a text input in a text input area, and displaying recommended indexes to which the target identity has access permission and which are filtered according to the text in a recommended index display area; in response to a recommended index selection operation, displaying the selected recommended index in the recommended index display area; in the index selection area, selecting the candidate index matched with the selected recommended index; in an analysis index display area, displaying the selected candidate index in the index selection area as a target index; and determining an analysis object, and triggering data analysis based on the target index and the analysis object. The method can improve the data analysis accuracy.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data analysis method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of computer technology, the application of data processing technology is becoming increasingly widespread. In the banking sector, the customer data, transaction records, management data, and other data accumulated by various banks are growing rapidly, with massive amounts of data emerging. Bank personnel can improve customer and bank management and enhance bank value by rationally mining and analyzing the data.

[0003] However, currently, bank staff face the problem of low accuracy in data analysis. Summary of the Invention

[0004] Therefore, it is necessary to provide a data analysis method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of data analysis in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a data analysis method, including:

[0006] In response to a data analysis trigger operation initiated by the target identity, a data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0007] In the indicator selection area, candidate indicators that the target identity has access to are displayed; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0008] The text entered in the text input area is obtained, and the recommendation index display area displays the recommendation indexes that the target identity has access rights according to the text;

[0009] In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area;

[0010] In the indicator selection area, select the candidate indicator that matches the selected recommended indicator;

[0011] In the analysis indicator display area, the candidate indicator selected in the indicator selection area is displayed as the target indicator;

[0012] Identify the object of analysis, and trigger data analysis based on the target indicators and the object of analysis.

[0013] Secondly, this application also provides a data analysis apparatus, comprising:

[0014] The interface management module is used to display the data analysis configuration interface in response to data analysis trigger operations triggered by the target identity; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0015] The indicator selection area management module is used to display candidate indicators that the target identity has access to in the indicator selection area; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0016] The recommendation indicator display area management module is used to obtain the text entered in the text input area, and display the recommendation indicators that the target identity has access rights for according to the text in the recommendation indicator display area; in response to the recommendation indicator selection operation, the selected recommendation indicator is displayed in the recommendation indicator display area.

[0017] The indicator selection area management module is also used to select candidate indicators that match the selected recommended indicator in the indicator selection area.

[0018] The analysis indicator display area management module is used to display the selected candidate indicators as target indicators in the indicator selection area;

[0019] The data analysis triggering module is used to determine the analysis object and trigger data analysis based on the target indicator and the analysis object.

[0020] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0021] In response to a data analysis trigger operation initiated by the target identity, a data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0022] In the indicator selection area, candidate indicators that the target identity has access to are displayed; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0023] The text entered in the text input area is obtained, and the recommendation index display area displays the recommendation indexes that the target identity has access rights according to the text;

[0024] In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area;

[0025] In the indicator selection area, select the candidate indicator that matches the selected recommended indicator;

[0026] In the analysis indicator display area, the candidate indicator selected in the indicator selection area is displayed as the target indicator;

[0027] Identify the object of analysis, and trigger data analysis based on the target indicators and the object of analysis.

[0028] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0029] In response to a data analysis trigger operation initiated by the target identity, a data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0030] In the indicator selection area, candidate indicators that the target identity has access to are displayed; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0031] The text entered in the text input area is obtained, and the recommendation index display area displays the recommendation indexes that the target identity has access rights according to the text;

[0032] In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area;

[0033] In the indicator selection area, select the candidate indicator that matches the selected recommended indicator;

[0034] In the analysis indicator display area, the candidate indicator selected in the indicator selection area is displayed as the target indicator;

[0035] Identify the object of analysis, and trigger data analysis based on the target indicators and the object of analysis.

[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0037] In response to a data analysis trigger operation initiated by the target identity, a data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0038] In the indicator selection area, candidate indicators that the target identity has access to are displayed; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0039] The text entered in the text input area is obtained, and the recommendation index display area displays the recommendation indexes that the target identity has access rights according to the text;

[0040] In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area;

[0041] In the indicator selection area, select the candidate indicator that matches the selected recommended indicator;

[0042] In the analysis indicator display area, the candidate indicator selected in the indicator selection area is displayed as the target indicator;

[0043] Identify the object of analysis, and trigger data analysis based on the target indicators and the object of analysis.

[0044] The aforementioned data analysis methods, devices, computer equipment, storage media, and computer program products display candidate indicators with access permissions for the target identity in the indicator selection area of ​​the data analysis configuration interface, allowing for flexible selection of candidate indicators for data analysis. Furthermore, after entering text in the text input area of ​​the data analysis configuration interface, recommended indicators determined by the text are displayed in the recommended indicator display area of ​​the data analysis configuration interface. While flexibly configuring indicators for data analysis, users can also input analytical intent in text form to obtain recommended indicators matching the textual analytical intent, thereby determining the final target indicator for data analysis. This allows for triggering data analysis based on the target indicator and the analysis object, which can improve the accuracy of data analysis to a certain extent. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating a data analysis method in one embodiment;

[0047] Figure 2This is a flowchart illustrating the steps of obtaining text input in the text input area and displaying recommendation indicators for target identities with access rights based on the text in the recommendation indicator display area, as shown in one embodiment.

[0048] Figure 3 This is a structural block diagram of a data analysis device in one embodiment;

[0049] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] In one embodiment, such as Figure 1 As shown, a data analysis method is provided. This embodiment illustrates the method applied to a terminal, but it is understood that the method can also be applied to a system including a terminal and a server, and implemented through the interaction between the terminal and the server. The terminal can be a personal computer, laptop, smartphone, or tablet. The server can be a standalone server or a server cluster consisting of multiple servers. In this embodiment, the method includes steps 102 to 114.

[0052] Step 102: In response to the data analysis trigger operation triggered by the target identity, the data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0053] The target identity is the computer identity that triggers the data analysis trigger operation. A computer identity is information used in a computer system to distinguish different users; it can be an account, phone number, or other identifier. The data analysis trigger operation is the action that triggers the display of the data analysis configuration interface. Specifically, the data analysis trigger operation can be an action performed on a data analysis trigger button, such as a mouse click or touch operation.

[0054] The data analysis configuration interface is used to configure the information items required for data analysis. Data analysis uses appropriate statistical analysis methods to analyze collected data, extract useful information, and form conclusions. Information items include indicators, analysis objects, and may also include data time intervals or other information. The indicator selection area is the area in the data analysis configuration interface used to select candidate indicators. The text input area is the area in the data analysis configuration interface used to input text. The text input area can be used to prompt the user to input their analysis intent. The recommended indicator display area is the area in the data analysis configuration interface used to display recommended indicators. The analysis indicator display area is the area in the data analysis configuration interface used to display the candidate indicators selected in the indicator selection area.

[0055] In one embodiment, the terminal can respond to a data analysis trigger operation initiated by a target identity, obtain the display styles of the indicator selection area, text input area, recommended indicator display area, and analysis indicator display area in the data analysis configuration interface, draw the data analysis configuration interface, and draw the indicator selection area, text input area, recommended indicator display area, and analysis indicator display area in the data analysis configuration interface according to the display styles. The display styles may include area shapes, area display colors, the arrangement of areas, or other factors.

[0056] In one embodiment, the terminal may run a bank management client. Upon logging into the bank management client with the target identity, a data analysis configuration interface is displayed in response to a data analysis trigger operation initiated by the target identity within the bank management client. The bank management client is a client running on the terminal within a bank management system. The bank management system may be a bank information management system, a mobile banking back-end management system, or others.

[0057] Step 104: In the indicator selection area, display candidate indicators that the target identity has access to; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0058] In this context, an indicator is a unit of measurement used to measure a target. Indicators can be units of measurement used to represent basic information, such as name, age, gender, or others, or they can be units of measurement used to represent statistical quantities, such as delinquency rate, activity level, willingness to spend, or others.

[0059] Candidate metrics are metrics to be selected. Candidate metrics that the target identity has access to are those that the target identity is allowed to access. The candidate metric selection operation is the operation of selecting a candidate metric from the metric selection area. The candidate metric selection operation can be a click, long press, or touch operation on the trigger button corresponding to each candidate metric.

[0060] In one embodiment, after displaying the data analysis configuration interface, the terminal can determine candidate indicators that the target identity has access to from a preset indicator set, and display the determined candidate indicators in the indicator selection area of ​​the data analysis configuration interface. The preset indicator set is a pre-set set of indicators, which may be a collection of all indicators pre-configured in the bank management system for implementing data analysis.

[0061] In one embodiment, the terminal may respond to a data analysis triggering operation triggered by the target identity, display the data analysis configuration interface, determine candidate indicators that the target identity has access to from a preset set of indicators, and display the determined candidate indicators in the indicator selection area of ​​the data analysis configuration interface.

[0062] Step 106: Obtain the text entered in the text input area, and display the recommendation indicators that the target identity has access rights according to the text in the recommendation indicator display area.

[0063] The text entered in the text input area can be a continuous sentence, a single keyword, or multiple non-contiguous keywords. For example, the text could be "assess customer credit risk" or "customer credit risk assessment." Recommended metrics are selected from candidate metrics that the target user has access to based on the text.

[0064] In one embodiment, the terminal can respond to a text submission operation triggered in the data analysis configuration interface, obtain the text entered in the text input area, and display recommended indicators that the target identity has access rights for, filtered according to the obtained text, in the recommendation indicator display area. The text submission operation is a trigger operation of the text submission function key.

[0065] In one embodiment, after detecting text input in the text input area, the terminal can retrieve the currently input text at preset intervals. If the currently retrieved text differs from the text retrieved at the previous time point, the terminal will display recommendation indicators in the recommendation indicator display area indicating that the target identity has access rights based on the retrieved text. The preset interval is a pre-set duration, such as 30 seconds, 1 minute, 2 minutes, or others. The previous time point is a time interval preceding the current time point; for example, if the current time point is 12:00 and the preset interval is 1 minute, the previous time point could be 11:59.

[0066] In one embodiment, the terminal can input the acquired text and candidate indicators of the target identity's access permissions into the indicator prediction model to obtain the predicted recommended indicators.

[0067] Step 108: In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area.

[0068] The "Recommended Metric Selection" operation involves selecting a recommended metric displayed in the recommended metric display area. Recommended metrics can be displayed as labels. The recommended metric selection operation can be triggered by the corresponding label of a recommended metric.

[0069] In one embodiment, the terminal can display unselected recommended indicators in the recommended indicator display area, and in response to the recommended indicator selection operation, determine the recommended indicator selected by the recommended indicator selection operation, and switch the unselected recommended indicator to the selected state.

[0070] Step 110: In the indicator selection area, select the candidate indicators that match the selected recommended indicator.

[0071] In one embodiment, whenever a recommended indicator is selected in the recommended indicator display area, the terminal can determine a candidate indicator in the indicator selection area that matches the selected recommended indicator, and select the determined candidate indicator.

[0072] Step 112: In the analysis indicator display area, display the candidate indicator selected in the indicator selection area as the target indicator.

[0073] The target indicator is the indicator displayed in the analysis indicator display area.

[0074] In one embodiment, whenever a candidate indicator is selected in the indicator selection area, the terminal can display the selected candidate indicator as the target indicator in the analysis indicator display area.

[0075] In one embodiment, the target indicator can be displayed as a label, and the display area of ​​the label corresponding to the target indicator has a close button. In this embodiment, the terminal can respond to the triggering operation of the close button in the label corresponding to any target indicator in the analysis indicator display area, de-display the corresponding target indicator in the analysis indicator display area, and deselect the candidate indicators in the indicator selection area that match the de-displayed target indicator.

[0076] Step 114: Determine the analysis object and trigger data analysis based on the target indicators and the analysis object.

[0077] The analysis object is the target of the data analysis. The analysis object can be a customer object, such as an individual customer or a corporate customer, or an internal object of the bank, such as a bank employee or a bank department.

[0078] In one embodiment, the terminal can respond to an indicator submission event by displaying an object configuration interface within the data analysis configuration interface, retrieving the analysis objects configured in the object configuration interface, and triggering data analysis based on the target indicator and the analysis objects. The object configuration interface is used to configure analysis objects. It can display objects that the target identity has access permissions to; when a displayed object is selected, the selected object can be identified as the analysis object configured in the object configuration interface.

[0079] In the aforementioned data analysis method, the indicator selection area of ​​the data analysis configuration interface displays candidate indicators that the target identity has access to, allowing for flexible selection of candidate indicators for data analysis. Furthermore, after entering text in the text input area of ​​the data analysis configuration interface, recommended indicators determined by the text can be displayed in the recommended indicator display area of ​​the data analysis configuration interface. While flexibly configuring indicators for data analysis, one can also input analysis intent in text form to obtain recommended indicators that match the analysis intent in text form, thereby determining the final target indicator for data analysis. Then, data analysis can be triggered based on the target indicator and the analysis object, which can improve the accuracy of data analysis to a certain extent.

[0080] In one embodiment, step 114 includes: identifying the analysis object and displaying a verification interface; obtaining the verification information entered in the verification interface; and when the target identity is verified based on the verification information, initiating a data analysis request to the data analysis platform that indicates the target metric, the analysis object, and the target identity; wherein the data analysis request is used to instruct the data analysis platform to determine the database where the data of the analysis object under the target metric is located, and, if the target identity has access to the database, to obtain the data from the database and perform data analysis based on the data and the target metric.

[0081] The verification interface is used to verify the target's identity. Verification information is the information entered into the verification interface to verify the target's identity. Verification information can be a password, a dynamic verification code, or biometric information. Biometric information includes facial images, fingerprints, or other biometric data. The data analysis platform is the platform for performing data analysis. The data analysis platform can run on a server.

[0082] In this embodiment, the target identity is authenticated. After successful authentication, a data analysis request is initiated. The data analysis platform then retrieves data from the database containing the target metrics. Data is only retrieved from the database if the target identity has access to the database, thus ensuring data security.

[0083] In one embodiment, the data analysis configuration interface can also be used to configure a data time interval. After determining the analysis object, the terminal determines the target time interval configured in the data analysis configuration interface, displays a verification interface, and obtains the verification information entered in the verification interface. When the target identity is verified based on the verification information, a data analysis request is sent to the data analysis platform, specifying the target indicator, analysis object, target time interval, and target identity. Here, the data time interval is the time range within which data is generated. The target time interval is the configured data time interval, such as August 1, 2023 to September 1, 2023.

[0084] In one embodiment, the data analysis platform can obtain the database containing the data of the analysis object under the target indicator from the database. If the target identity has access to the database, the platform can obtain the target data of the analysis object under the target indicator and within the target time range from the database. If there is a pre-configured analysis algorithm for the target indicator, the platform can determine the indicator result of the analysis object under the target indicator based on the target data and according to the pre-configured analysis algorithm.

[0085] For target metrics that do not have pre-configured analysis algorithms, the data of the analysis object under the target metric can be used as the metric result. An analysis algorithm is an algorithm that analyzes data under the target metric. Analysis algorithms may include statistical algorithms and evaluation algorithms for the data.

[0086] A statistical algorithm is an algorithm that performs statistical analysis on data to obtain statistical results. For example, when the target metric is the activity level in a mobile banking app, and the target time period is from August 1, 2023 to September 1, 2023, the statistical algorithm could be to statistically analyze the number of times the target user accesses the mobile banking app during that period. The number of accesses can be considered a statistical result.

[0087] An evaluation algorithm is an algorithm that evaluates statistical results to obtain evaluation results. For example, an evaluation algorithm might determine that a target is active if the number of visits to a mobile banking app is no less than 10; moderately active if the number of visits is more than 2 but less than 10; and inactive if the number of visits is no more than 2. Here, active, moderately active, and inactive can be evaluation results. When a pre-configured analysis algorithm exists for the target indicator, the indicator results can include both statistical results and evaluation results.

[0088] In one embodiment, the recommendation indicator display area includes a first-level recommendation indicator display area and a second-level recommendation indicator display area, such as... Figure 2 As shown, step 106 includes steps 202 to 210. Wherein:

[0089] Step 202: Obtain the text entered in the text input area.

[0090] Step 204: Based on the text and candidate indicators that the target identity has access to, determine the first-level recommended indicators; the first-level recommended indicators belong to the candidate indicators that the target identity has access to.

[0091] The first-level recommendation metrics are selected directly from candidate metrics that the target identity has access to based on the text.

[0092] Step 206: Display the first-level recommendation indicators in the first-level recommendation indicator display area.

[0093] The first-level recommendation indicator display area is the area in the recommendation indicator display area used to display the first-level recommendation indicators.

[0094] Step 208: From the candidate indicators that the target identity has access to, determine the candidate indicators that are associated with the first-level recommended indicators, and use them as the second-level recommended indicators.

[0095] In one embodiment, the terminal can determine related indicators that are associated with each recommended indicator in the first-level recommended indicators from the indicator association library, and determine candidate indicators that match the related indicators from the candidate indicators that the target identity has access to, as the second-level recommended indicators. The indicator association library is a database that stores the association relationships between different indicators. The association relationships between indicators can be pre-set. Developers can perform multiple historical data analyses and count the number of times data analysis is performed based on indicator pairs. When this number exceeds a preset number, an association relationship is established for the indicator pair. Here, an indicator pair refers to a pair of indicators. The preset number of times can be 10, 20, or other values.

[0096] In one embodiment, the terminal can determine the combination of recommendation indicators consisting of the first-level recommendation indicators, obtain the indicators pre-associated with the recommendation indicator combination, and take the candidate indicators that match the obtained pre-associated indicators from the candidate indicators that the target identity has access to as the second-level recommendation indicators.

[0097] Step 210: Display the second-level recommendation indicators in the second-level recommendation indicator display area.

[0098] The second recommendation indicator display area is used to display the second-level recommendation indicators. The first-level recommendation indicators, compared to the second-level indicators, can be displayed with a more prominent format, such as larger font size and more prominent color.

[0099] In this embodiment, the first-level recommendation indicator display area can display first-level recommendation indicators directly related to the text entered by the user, providing indicators that meet the user's data analysis needs. The second-level recommendation indicator display area displays second-level recommendation indicators related to the first-level recommendation indicators, providing the user with more indicators that may meet the data analysis needs to choose from, thereby improving the accuracy of data analysis.

[0100] In one embodiment, step 204 includes: inputting text into a pre-trained intent recognition model to obtain the predicted analysis intent; and selecting candidate indicators associated with the predicted analysis intent from among the candidate indicators of the target identity having access rights, as the first-level recommended indicators.

[0101] The intent recognition model is used to predict the analytical intent of the input text. Analytical intent refers to the intention to perform data analysis. Examples of analytical intent include credit risk assessment, user profiling analysis, or other purposes.

[0102] In this embodiment, the intent recognition model can conveniently and accurately determine the user's intent to perform data analysis. Candidate indicators associated with the predicted analysis intent can be used as first-level recommended indicators, which can recommend indicators that match the user's analysis intent and improve the accuracy of subsequent data analysis.

[0103] In one embodiment, the terminal can segment multiple sample texts and input them into a word vector model to obtain word vectors corresponding to each sample text. Using these word vectors as input and the labeled analysis intents for each sample text as annotations, the terminal trains the intent recognition model to obtain a trained intent recognition model. Here, the sample texts are the texts used as samples, and the word vector model is a model that converts words into vectors. The word vector model can be a Word2Vec (Word to Vector) model or GloVe (Global Vectors for Word Representation, a word matrix generation model proposed by Stanford University that comprehensively utilizes global and local statistical information of words to generate language models and vectorized representations of words). The intent recognition model to be trained can be a logistic regression model.

[0104] In one embodiment, the terminal can acquire indicators that are related to the predictive analysis intent, and determine candidate indicators that match the predictive analysis intent from among the candidate indicators that the target identity has access to, as the first-level recommended indicators.

[0105] In one embodiment, step 204 further includes: obtaining the number of indicators contained in a preset indicator set; the preset indicator set includes candidate indicators that the target identity has access to; constructing a feature vector template according to the number of indicators, the feature vector template including elements that correspond one-to-one with the indicators in the indicator set; marking the candidate indicators that the target identity has access to in the feature vector template to obtain indicator feature vectors; constructing combined features based on the text and indicator feature vectors; and predicting the first-level recommendation indicators based on the combined features.

[0106] The feature vector template is a template used to generate feature vectors from the indicators in the indicator set. Marking candidate indicators that the target identity has access rights to means marking the elements corresponding to the candidate indicators in the feature vector template with preset values, so that the obtained indicator feature vector represents the candidate indicators that the target identity has access rights to. For example, the preset indicator set may include 5 indicators, a, b, c, d, and e. The feature vector template can be [a, b, c, d, e]. The candidate indicators that the target identity has access rights to can be b, d, and e. Marking the elements corresponding to the candidate indicators with 1 results in an indicator feature vector of [0, 1, 0, 1, 1].

[0107] Combined features are features formed by combining text and indicator feature vectors. Specifically, combined features can be features formed by concatenating the word vectors corresponding to the text with the indicator feature vectors.

[0108] In this embodiment, elements corresponding one-to-one with indicators in the indicator set are constructed, and then candidate indicators with access permissions for the target identity are marked in the feature vector template to obtain indicator feature vectors. This allows for convenient feature processing of candidate indicators with access permissions for the target identity. Then, the first-level recommended indicators are predicted based on the combined features constructed from the text and indicator feature vectors. This can quickly predict recommended indicators and improve data processing efficiency.

[0109] In one embodiment, the terminal can input combined features into a pre-trained machine learning model to obtain predicted first-level recommendation metrics. The pre-trained machine learning model can be trained by taking multiple sample combined features as input and recommendation metrics labeled for each of the sample combined features as annotations. Sample combined features are the combined features formed by the word vectors corresponding to the sample text and the sample metric feature vectors. Sample metric feature vectors are the metric feature vectors corresponding to candidate metrics for which the sample identity has access permissions.

[0110] In one embodiment, the first-level recommendation indicators are the recommended indicators in the pre-generated combination of recommendation indicators; the above data analysis also includes the following steps: when there are unselected recommendation indicators in the first-level recommendation indicators, determine the combination of recommendation indicators composed of the first-level recommendation indicators; update the unselected statistics corresponding to the unselected recommendation indicators in the combination of recommendation indicators; when the unselected statistics reach a preset threshold, filter out the unselected recommendation indicators from the combination of recommendation indicators; configure the filtered recommendation indicators as the recommendation indicators associated with the combination of recommendation indicators.

[0111] The recommended indicator combination consists of at least two recommended indicators. The unselected statistic is the number of times the unselected recommended indicator in the recommended indicator combination has not been selected. The preset threshold is a pre-set threshold. The preset threshold can be 10 times, 15 times, or other values. When the recommended indicator combination is used as the first-level recommended indicator, the recommended indicators associated with the recommended indicator combination can be used as the second-level recommended indicators.

[0112] In this embodiment, if the unselected statistics of an unselected recommended indicator in the recommended indicator combination corresponding to the first-level recommended indicator reach a preset threshold, it indicates that the unselected recommended indicator may not meet the user's analysis intent. The unselected recommended indicator is filtered out from the recommended indicator combination, and the filtered recommended indicator is configured as an associated recommended indicator, which can improve the accuracy of indicator recommendation.

[0113] In one embodiment, whenever a combination of recommended indicators is used as the first-level recommended indicator and the first-level recommended indicator is updated in the recommended indicator display area, if there are unselected recommended indicators in the combination of recommended indicators, the terminal can accumulate the number of unselected indicators by one to update the unselected statistics corresponding to the unselected recommended indicators in the combination of recommended indicators.

[0114] In one embodiment, the above data analysis specifically includes the following steps.

[0115] The terminal can respond to data analysis trigger operations initiated by the target identity and display the data analysis configuration interface; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area; the recommended indicator display area includes a first-level recommended indicator display area and a second-level recommended indicator display area.

[0116] In the indicator selection area, the terminal displays candidate indicators that the target identity has access to; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0117] The terminal can acquire the text entered in the text input area, input the text into a pre-trained intent recognition model, obtain the predicted and analyzed intent, filter candidate indicators associated with the predicted and analyzed intent from the candidate indicators that the target identity has access to, and use them as first-level recommended indicators; display the first-level recommended indicators in the first-level recommended indicator display area; determine the candidate indicators associated with the first-level recommended indicators from the candidate indicators that the target identity has access to, and use them as second-level recommended indicators; display the second-level recommended indicators in the second-level recommended indicator display area.

[0118] The terminal can respond to the recommended indicator selection operation by displaying the selected recommended indicator in the recommended indicator display area; selecting candidate indicators that match the selected recommended indicator in the indicator selection area; and displaying the candidate indicators selected in the indicator selection area as the target indicator in the analysis indicator display area.

[0119] The terminal can identify the object of analysis and display the verification interface; obtain the verification information entered in the verification interface; when the target identity is verified based on the verification information, it sends a data analysis request to the data analysis platform running on the server, indicating the target indicator, the object of analysis, and the target identity.

[0120] The data analysis platform can determine the database where the data of the analysis object is located under the target indicators. If the target identity has access to the database, it can retrieve the data from the database and perform data analysis based on the data and the target indicators.

[0121] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0122] Based on the same inventive concept, this application also provides a data analysis apparatus for implementing the data analysis method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data analysis apparatus embodiments provided below can be found in the limitations of the data analysis method described above, and will not be repeated here.

[0123] In one embodiment, such as Figure 3 As shown, a data analysis device 300 is provided, including: an interface management module 310, an indicator selection area management module 320, a recommended indicator display area management module 330, an analysis indicator display area management module 340, and a data analysis triggering module 350, wherein:

[0124] The interface management module 310 is used to display the data analysis configuration interface in response to a data analysis trigger operation triggered by the target identity. The data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area.

[0125] The indicator selection area management module 320 is used to display candidate indicators that the target identity has access to in the indicator selection area; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator.

[0126] The recommendation indicator display area management module 330 is used to obtain the text entered in the text input area and display the recommendation indicators that the target identity has access rights according to the text in the recommendation indicator display area; in response to the recommendation indicator selection operation, the selected recommendation indicator is displayed in the recommendation indicator display area.

[0127] The indicator selection area management module 320 is also used to select candidate indicators that match the selected recommended indicator in the indicator selection area;

[0128] The analysis indicator display area management module 340 is used to display the selected candidate indicators as target indicators in the indicator selection area;

[0129] The data analysis trigger module 350 is used to determine the analysis object and trigger data analysis based on the target indicators and the analysis object.

[0130] In one embodiment, the data analysis triggering module 350 is further configured to determine the analysis object, display a verification interface, obtain the verification information entered in the verification interface, and when the target identity is verified based on the verification information, initiate a data analysis request to the data analysis platform indicating the target indicator, the analysis object, and the target identity. The data analysis request is configured to instruct the data analysis platform to determine the database where the data of the analysis object under the target indicator is located, and, if the target identity has access to the database, to obtain the data from the database and perform data analysis based on the data and the target indicator.

[0131] In one embodiment, the recommendation indicator display area includes a first-level recommendation indicator display area and a second-level recommendation indicator display area; the recommendation indicator display area management module 330 is further configured to acquire the text input in the text input area; determine the first-level recommendation indicator based on the text and candidate indicators that the target identity has access to; the first-level recommendation indicator belongs to the candidate indicators that the target identity has access to; display the first-level recommendation indicator in the first-level recommendation indicator display area; determine the candidate indicator associated with the first-level recommendation indicator from the candidate indicators that the target identity has access to, and use it as the second-level recommendation indicator; display the second-level recommendation indicator in the second-level recommendation indicator display area.

[0132] In one embodiment, the recommendation metric display area management module 330 is further configured to input text into a pre-trained intent recognition model to obtain predictive analysis intent; and to filter candidate metrics associated with predictive analysis intent from candidate metrics for which the target identity has access rights, as first-level recommendation metrics.

[0133] In one embodiment, the recommendation indicator display area management module 330 is further configured to obtain the number of indicators contained in a preset indicator set; the preset indicator set includes candidate indicators that the target identity has access to; construct a feature vector template according to the number of indicators, the feature vector template including elements that correspond one-to-one with the indicators in the indicator set; mark the candidate indicators that the target identity has access to in the feature vector template to obtain indicator feature vectors; construct combined features based on the text and indicator feature vectors; and predict the first-level recommendation indicators based on the combined features.

[0134] In one embodiment, the first-level recommendation indicators are the recommended indicators in the pre-generated combination of recommendation indicators. The recommendation indicator display area management module 330 is also used to determine the combination of recommendation indicators composed of the first-level recommendation indicators when there are unselected recommendation indicators in the first-level recommendation indicators; update the unselected statistics corresponding to the unselected recommendation indicators in the combination of recommendation indicators; filter out the unselected recommendation indicators from the combination of recommendation indicators when the unselected statistics reach a preset threshold; and configure the filtered recommendation indicators as the recommendation indicators associated with the combination of recommendation indicators.

[0135] Each module in the aforementioned data analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0136] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a data analysis method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0137] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0139] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0140] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0142] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data analysis method, characterized by, The method includes: In response to a data analysis trigger operation initiated by the target identity, a data analysis configuration interface is displayed; the data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area; the recommended indicator display area includes a first-level recommended indicator display area and a second-level recommended indicator display area. Get the text entered in the text input area; Based on the text and the candidate indicators that the target identity has access rights as filtered according to the text, a first-level recommendation indicator is determined; the first-level recommendation indicator belongs to the candidate indicators that the target identity has access rights. The first-level recommendation indicators are displayed in the first-level recommendation indicator display area. From the candidate indicators that the target identity has access to, determine the candidate indicators that are associated with the first-level recommended indicators, and use them as the second-level recommended indicators. The second-level recommendation indicator display area displays the second-level recommendation indicators; In response to the recommended indicator selection operation, the selected recommended indicator is displayed in the recommended indicator display area; In the indicator selection area, select the candidate indicator that matches the selected recommended indicator; In the analysis indicator display area, the candidate indicator selected in the indicator selection area is displayed as the target indicator; Identify the analysis object and display the verification interface; Obtain the verification information entered in the verification interface; Once the target identity is verified based on the verification information, a data analysis request is sent to the data analysis platform, indicating the target metric, the analysis object, and the target identity. The data analysis request is used to instruct the data analysis platform to determine the database where the data of the analysis object under the target indicator is located, and, if the target identity has access to the database, to obtain the data from the database and perform data analysis based on the data and the target indicator.

2. The method according to claim 1, characterized in that, The determination of first-level recommendation metrics based on the text and candidate metrics indicating access rights for the target identity includes: The text is input into a pre-trained intent recognition model to obtain a predicted and analyzed intent; From the candidate indicators that the target identity has access to, candidate indicators that are associated with the predictive analysis intent are selected as the first-level recommended indicators.

3. The method according to claim 1, characterized in that, The determination of first-level recommendation metrics based on the text and candidate metrics indicating access rights for the target identity includes: Obtain the number of indicators contained in a preset indicator set; the preset indicator set includes candidate indicators that the target identity has access to. A feature vector template is constructed according to the number of indicators, and the feature vector template includes elements that correspond one-to-one with the indicators in the indicator set. In the feature vector template, candidate indicators for which the target identity has access rights are marked to obtain indicator feature vectors; Construct combined features based on the text and the indicator feature vector; The first-level recommendation index is predicted based on the combined features.

4. The method according to any one of claims 1 to 3, characterized in that, The first-level recommendation index is the recommendation index in the pre-generated combination of recommendation indices; the method further includes: If there are unselected recommended indicators among the recommended indicators of the first level, determine the recommended indicator combination composed of the recommended indicators of the first level. Update the unselected statistics corresponding to the unselected recommended indicators in the recommended indicator combination; When the unselected statistics reach a preset threshold, the unselected recommended indicators are filtered out from the recommended indicator combination; The filtered recommendation metrics are configured as recommendation metrics associated with the combination of recommendation metrics.

5. A data analysis device, characterized in that, The device includes: The interface management module is used to display the data analysis configuration interface in response to data analysis trigger operations initiated by the target identity. The data analysis configuration interface includes an indicator selection area, a text input area, a recommended indicator display area, and an analysis indicator display area. The recommended indicator display area includes a first-level recommended indicator display area and a second-level recommended indicator display area. The indicator selection area management module is used to display candidate indicators that the target identity has access to in the indicator selection area; the indicator selection area is used to respond to the candidate indicator selection operation to display the selected candidate indicator. The recommendation indicator display area management module is used to obtain the text entered in the text input area, and display the recommendation indicators that the target identity has access rights for according to the text in the recommendation indicator display area; in response to the recommendation indicator selection operation, the selected recommendation indicator is displayed in the recommendation indicator display area. The indicator selection area management module is also used to select candidate indicators that match the selected recommended indicator in the indicator selection area. The analysis indicator display area management module is used to display the selected candidate indicators as target indicators in the indicator selection area; A data analysis triggering module is used to identify the analysis object and display a verification interface; obtain the verification information entered in the verification interface; when the target identity is verified based on the verification information, a data analysis request is initiated to the data analysis platform, indicating the target indicator, the analysis object, and the target identity; wherein, the data analysis request is used to instruct the data analysis platform to determine the database where the data of the analysis object under the target indicator is located, and if the target identity has access to the database, to obtain the data from the database and perform data analysis based on the data and the target indicator; The recommendation indicator display area management module is further configured to: acquire the text input in the text input area; determine a first-level recommendation indicator based on the text and candidate indicators that the target identity has access to; the first-level recommendation indicator belongs to the candidate indicators that the target identity has access to; display the first-level recommendation indicator in the first-level recommendation indicator display area; determine candidate indicators associated with the first-level recommendation indicator from the candidate indicators that the target identity has access to, as second-level recommendation indicators; and display the second-level recommendation indicator in the second-level recommendation indicator display area.

6. The apparatus according to claim 5, characterized in that, The recommendation indicator display area management module is also used to input the text into a pre-trained intent recognition model to obtain the predicted analysis intent; and to select candidate indicators associated with the predicted analysis intent from the candidate indicators that the target identity has access to, as the first-level recommendation indicators.

7. The apparatus according to claim 5, characterized in that, The recommendation indicator display area management module is further configured to obtain the number of indicators contained in a preset indicator set; the preset indicator set includes candidate indicators that the target identity has access to; construct a feature vector template according to the number of indicators, the feature vector template including elements that correspond one-to-one with the indicators in the indicator set; mark the candidate indicators that the target identity has access to in the feature vector template to obtain indicator feature vectors; construct combined features based on the text and the indicator feature vectors; and predict the first-level recommendation indicators based on the combined features.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images