Big data index query and analysis method based on large model

Abstract

The invention provides a big data index query and analysis method based on a big model, and the method comprises the steps: accessing a data source; after a data source is accessed, establishing a data index based on a service demand; based on the dialogue form, querying the data index through a large model to obtain a query result and an analysis result; and carrying out visual display on the query result and the analysis result. According to the big data index query and analysis method based on the big model, multiple data sources are accessed, and corresponding data indexes are established according to service requirements; introducing an AI dialogue form, determining a query condition of the data index according to dialogue information of a dialogue person, and obtaining a query result; and the query result and the analysis result are visually displayed according to the personalized chart analysis form selection result of the dialogue personnel, so that the readability of the data is improved, and the method is more convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a big data indicator query and analysis method based on a big model. Background Art

[0002] Data indicators are specific numerical values ​​used in data analysis and business management. They segment and quantify business units, making business goals describable, measurable, and decomposable, in order to measure and evaluate business operations, performance, efficiency, and other aspects. Data indicators are usually obtained through calculation, aggregation, or analysis based on raw data. They can provide insights into business conditions and help make data-based decisions. In addition, the data indicator system is an important part of building a data middle platform. It helps operations and product personnel intuitively see changes in basic indicators, allowing data analysts to conduct data analysis more conveniently.

[0003] The invention patent with application number: CN202311465846.8 discloses a financial big data storage query method based on artificial intelligence, wherein the method includes: obtaining different types of financial transaction data in different transaction data tables of an enterprise to construct long strings of different transaction data tables; adding a check code to each substring according to the data type of each substring; reorganizing the substrings in each long string according to the check code and length of each substring in each long string to obtain a reorganized string; processing the reorganized string to obtain the encoding data of each reorganized string, and obtaining the importance index of each encoding data according to the distribution of encoding data of different lengths in the encoding data of each reorganized string; processing each reorganized string into blocks to obtain data blocks, and marking and storing all data blocks according to the check code of the substring corresponding to the data block. The above invention makes data storage query more efficient.

[0004] However, the above indicator data is presented to users in the form of data tables or strings, which cannot be viewed intuitively by users and have poor readability. In addition, when querying the stored data, users need to follow the set query path to perform the corresponding query, which is not convenient enough.

[0005] In view of this, there is an urgent need for a big data indicator query and analysis method based on a big model to at least solve the above-mentioned shortcomings. Summary of the invention

[0006] One of the purposes of the present invention is to provide a big data indicator query and analysis method based on a big model, access a variety of data sources, and establish corresponding data indicators according to business needs; introduce the form of AI dialogue, determine the query conditions of data indicators and obtain query results based on the dialogue information of the dialogue personnel; select the results in the form of personalized chart analysis according to the dialogue personnel to visualize the query results and analysis results, which improves the readability of the data and is more convenient.

[0007] The embodiment of the present invention provides a big data index query and analysis method based on a big model, including:

[0008] Access data sources;

[0009] After accessing the data source, establish data indicators based on business needs;

[0010] Based on the dialogue form, query data indicators through the big model to obtain query results and analysis results;

[0011] Visualize the query and analysis results.

[0012] Preferably, accessing a data source includes:

[0013] Determine the type of data source required;

[0014] Fill in the connection information according to the preset connection information template of the required data source type;

[0015] After completing the connection information, test the connection status until the connection is successful.

[0016] Preferably, accessing a data source further includes:

[0017] Obtain the target access network docking node;

[0018] Connect to the target access network and the data source;

[0019] Wherein, obtaining the target access network connection node includes:

[0020] Acquire first data evaluation information of a pre-access network docking node;

[0021] Determining a plurality of evaluation parties and evaluation values ​​according to the first data evaluation information;

[0022] Obtaining a first access data credibility value according to the evaluation weight and the evaluation value of the evaluation party;

[0023] Obtain the historical access response rate of the pre-access network connection node;

[0024] Normalizing and summing the first access data credibility value and the historical access response rate to obtain a first target value;

[0025] Acquire second data evaluation information of the current access network docking node;

[0026] Determining a second access data credibility value according to the second data evaluation information;

[0027] Obtain the local access response rate of the current access network docking node;

[0028] Normalizing and summing the second access data credibility value and the local access response rate to obtain a second target value;

[0029] When the second target value is greater than or equal to each first target value, the current access network connection node corresponding to the corresponding second target value is used as the first node to be reorganized;

[0030] When there is a second target value that is smaller than the first target value, obtaining the target number of the second target values ​​that are smaller than the first target value;

[0031] Taking a second target value which is smaller than the first target value and the corresponding first target value together as a third target value;

[0032] Sort the third target values ​​from large to small, select the third target value of the previous target number, and use it as the fourth target value;

[0033] Acquire a current access network docking node and / or a pre-access network docking node corresponding to the fourth target value and use them as a second node to be reorganized;

[0034] The first node to be reorganized and the second node to be reorganized are used together as target access network docking nodes.

[0035] Preferably, after accessing the data source, data indicators are established based on business needs, including:

[0036] According to business needs, obtain indicator establishment information, which includes: indicator name, indicator type, indicator source and calculation logic;

[0037] Establish information based on indicators and establish data indicators.

[0038] Preferably, based on the dialogue form, querying data indicators through a large model to obtain query results and analysis results includes:

[0039] Acquire first dialogue information generated based on the dialogue form;

[0040] Extracting a template based on a preset query condition, and determining a first query condition according to the first conversation information;

[0041] The data index is queried according to the first query condition through the large model to obtain the query results and analysis results.

[0042] Preferably, extracting a template based on a preset query condition and determining the first query condition according to the first conversation information includes:

[0043] Based on the preset query condition extraction template, obtaining the extraction result of the first query condition according to the first conversation information;

[0044] If the extraction result is successful, determine the corresponding first query condition;

[0045] If the extraction result is extraction failure, extract the template and the first dialogue information according to the query condition to determine the missing dialogue information;

[0046] Generate supplementary dialogue reminder information based on missing dialogue information;

[0047] Displaying supplementary conversation reminder information to conversation users;

[0048] Obtain the supplementary conversation information after the conversation user views the supplementary conversation reminder information;

[0049] The template, the first dialogue information and the supplementary dialogue information are extracted according to the query condition to determine the first query condition.

[0050] The embodiment of the present invention provides a big data index query and analysis method based on a big model, which also includes:

[0051] Before querying the data indicator according to the first query condition through the big model, determine whether to trigger multiple rounds of dialogue;

[0052] If multiple rounds of dialogue are triggered, a second query condition for obtaining the second dialogue information that has been triggered;

[0053] According to the first query condition and the second query condition, the data indicators are queried through the large model to obtain query results and analysis results.

[0054] Preferably, according to the first query condition and the second query condition, querying the data index through the large model to obtain the query result and the analysis result includes:

[0055] Obtain the verification result of the query result by the dialog user;

[0056] If the verification result is that the verification is unsuccessful, the third query condition is displayed to the dialog user, and a modified query condition after the dialog user modifies the third query condition is obtained;

[0057] Re-obtain query results based on the revised query conditions.

[0058] Preferably, presenting the third query condition to the dialog user, and obtaining a modified query condition after the dialog user modifies the third query condition, includes:

[0059] Parsing the third query condition to determine at least one unit condition;

[0060] Obtaining a deletion path of the unit condition, and associating the deletion path with an operation position preset by a visual icon of the unit condition;

[0061] Get the condition constraint type of the unit condition, which includes necessary constraint and non-necessary constraint;

[0062] If the conditional constraint type is a necessary constraint, when the number of unit conditions of any conditional constraint type is identified to be 1 and the deletion path of the corresponding unit condition is triggered, the corresponding unit condition is used as the target unit condition;

[0063] Obtaining a unit condition candidate list preset for the target unit condition; the unit condition candidate list includes multiple candidate unit conditions, and the candidate unit conditions are sorted from large to small according to the correlation with the remaining unit conditions;

[0064] Displaying the candidate list of unit conditions to the dialog user, and reminding the dialog user to keep at least one unit condition whose condition constraint type is a necessary constraint;

[0065] Determine the selection result of the dialog user and obtain the modified query conditions.

[0066] The embodiment of the present invention provides a big data index query and analysis method based on a big model, which also includes:

[0067] Label development is performed according to data indicators to obtain label development results; label development results include: original labels, combined labels and external labels.

[0068] The embodiment of the present invention provides a big data index query and analysis method based on a big model, which also includes:

[0069] According to the label development results, obtain the label task list;

[0070] Determine the execution result according to the list operation of the tag task list;

[0071] Get the index link of the task instance display interface in the tag task list;

[0072] Get the task instance running status according to the index link.

[0073] The embodiment of the present invention provides a big data index query and analysis method based on a big model, which also includes:

[0074] Based on the label development results, single-object panoramic profiling and group analysis are performed;

[0075] Based on the label development results, share the label API;

[0076] When sharing the label API, the API call statistics are performed;

[0077] When sharing a tag API, obtain an application list of the tag API, the application list includes: application information and associated API information;

[0078] Parse the associated API information and obtain the associated API operation; wherein the operation types of the associated API operation include: generating an interface document and removing.

[0079] The beneficial effects of the present invention are:

[0080] The present invention accesses multiple data sources and establishes corresponding data indicators according to business needs; introduces the form of AI dialogue, determines the query conditions of data indicators and obtains query results according to the dialogue information of the dialogue personnel; selects results in the form of personalized chart analysis by the dialogue personnel to visualize the query results and analysis results, which improves the readability of the data and is more convenient.

[0081] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the present application documents.

[0082] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0084] Figure 1 It is a schematic diagram of a big data indicator query and analysis method based on a big model in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0086] The embodiment of the present invention provides a big data index query and analysis method based on a big model, such as Figure 1 As shown, including:

[0087] Step 1: Access the data source; the data source is: a network connection node that provides query data;

[0088] Step 2: After accessing the data source, establish data indicators based on business needs; business needs include: indicator query needs, such as: elderly information management query; data indicators include: data related to business needs, such as: the number of elderly people in each region, age and home address, etc.;

[0089] Step 3: Based on the dialogue form, query the data indicators through the big model to obtain the query results and analysis results; where, based on the dialogue form refers to the form based on the dialogue with AI; the big model is: according to the query conditions, the AI ​​model of the data that meets the query conditions is retrieved from the database, and the acquisition records of the data obtained by manually inputting the query conditions are used for machine learning acquisition; the query result is: the result obtained by parsing the dialogue input by the dialogue personnel, determining the query conditions for the query data indicators and performing the corresponding query; the analysis result is: the result obtained by analyzing the query results according to the chart analysis form selected by the dialogue personnel;

[0090] Step 4: Visualize the query results and analysis results.

[0091] The working principle and beneficial effects of the above technical solution are:

[0092] The present invention accesses multiple data sources and establishes corresponding data indicators according to business needs; introduces the form of AI dialogue, determines the query conditions of data indicators and obtains query results according to the dialogue information of the dialogue personnel; selects results in the form of personalized chart analysis by the dialogue personnel to visualize the query results and analysis results, which improves the readability of the data and is more convenient.

[0093] In one embodiment, accessing a data source includes:

[0094] Determine the required data source type; the required data source type is: the type of data source to be connected, such as: relational database, NoSQL database;

[0095] Fill in the connection information according to the connection information filling template preset for the required data source type; the connection information filling template is an information framework for the information that needs to be filled in when accessing the data source of the required data source type, such as database address, port, user name, password, etc.;

[0096] After completing the connection information, test the connection status until the connection is successful.

[0097] The working principle and beneficial effects of the above technical solution are:

[0098] To access a data source, first log in to the system and enter the data source access page. Select the required data source type (such as relational database, NoSQL database, etc.) and fill in the relevant connection information, such as database address, port, user name, password, etc. After completing the filling, test the connection to ensure that the connection is successful. After the test connection is successful, confirm the access.

[0099] The present invention introduces a connection information filling template to guide the filling of connection information, thereby improving the standardization and success rate of data source connection.

[0100] In one embodiment, accessing a data source further includes:

[0101] Obtaining a target access network docking node; wherein the target access network docking node is: a data source access network node that is allowed to access;

[0102] Connect to the target access network and the data source;

[0103] Wherein, obtaining the target access network connection node includes:

[0104] Acquire first data evaluation information of a pre-access network docking node; wherein the pre-access network docking node is: all data source access network nodes acquired by big data; the first data evaluation information is: an evaluation value of data shared by a data sharing party corresponding to the pre-access network docking node on a data sharing platform;

[0105] Determining a plurality of evaluation parties and evaluation values ​​according to the first data evaluation information;

[0106] According to the evaluation weight and evaluation value of the evaluation party, the first access data credibility value is obtained; wherein the evaluation weight is determined according to the historical evaluation credit of the evaluation party, the lower the historical evaluation credit, the smaller the weight is given, and the sum of the evaluation weights of the evaluation party corresponding to the same pre-access network docking node is 1; the first access data credibility value is the evaluation weight multiplied by the evaluation value and then summed;

[0107] Obtaining a historical access response rate of a pre-access network connection node; wherein the historical access response rate is: a historical data sharing response speed of the pre-access network connection node;

[0108] Normalizing and summing the first access data credibility value and the historical access response rate to obtain a first target value;

[0109] Acquire second data evaluation information of the current access network docking node; wherein the second data evaluation information is: evaluation information of the current access network docking node by the local information management personnel;

[0110] Determine the second access data trust value according to the second data evaluation information; wherein the second access data trust value is: the evaluation value of the local information management personnel on the current access network docking node;

[0111] Obtaining the local access response rate of the current access network docking node; wherein the local access response rate is: the response speed of the current access network docking node in the local history of data sharing;

[0112] Normalizing and summing the second access data credibility value and the local access response rate to obtain a second target value;

[0113] When the second target value is greater than or equal to each first target value, the current access network connection node corresponding to the corresponding second target value is used as the first node to be reorganized;

[0114] When there is a second target value that is less than the first target value, obtain the target number of the second target value that is less than the first target value; for example: there is a second target value of 85 that is less than the first target value of 90, and there is a second target value of 75 that is less than the first target values ​​of 90 and 80;

[0115] The second target value which is smaller than the first target value and the corresponding first target value are taken together as the third target value; wherein the third target value is, for example: 90, 85, 80, 75;

[0116] Sort the third target values ​​from large to small, select the third target value of the previous target number, and use it as the fourth target value; the third target value is, for example: 90, 85;

[0117] Acquire a current access network docking node and / or a pre-access network docking node corresponding to the fourth target value and use them as a second node to be reorganized;

[0118] The first node to be reorganized and the second node to be reorganized are used together as target access network docking nodes.

[0119] The working principle and beneficial effects of the above technical solution are:

[0120] The present invention screens a target access network docking node for accessing a data source. Specifically, first data evaluation information of a pre-access network docking node obtained by big data is obtained, and a first access data credibility value is calculated according to evaluation values ​​and evaluation weights of different evaluation parties; a historical access response rate of the pre-access network docking node is obtained, and the first access data credibility value and the historical access response rate are normalized and summed to obtain a first target value; evaluation information of a local information management personnel on a current access network docking node is obtained to determine a second access data credibility value, and in addition, a local access response rate of the current access network docking node is obtained, and the second access data credibility value and the local access response rate are normalized and summed to obtain a second target value.

[0121] Compare the second target value with the first target value. If the second target value is greater than or equal to each first target value, the current access network docking node corresponding to the second target value does not need to be eliminated and is directly used as the first node to be reorganized; if there is a second target value less than the first target value, the current access network docking node corresponding to the second target value is at risk of being eliminated, and the target number of second target values ​​less than the first target value is obtained. At the same time, the second target value less than the first target value and the corresponding first target value are used together as the third target value; sort the third target values ​​from large to small, and select the current access network docking node and / or pre-access network docking node corresponding to the fourth target value of the former target number as the second node to be reorganized;

[0122] It is more appropriate to reintegrate the first node to be reorganized and the second node to be reorganized as the target access network docking node, dynamically determine the reliable network docking node in real time and obtain data from it.

[0123] In one embodiment, after accessing the data source, data indicators are established based on business needs, including:

[0124] According to business needs, obtain indicator establishment information, which includes: indicator name, indicator type, indicator source and calculation logic;

[0125] Establish information based on indicators and establish data indicators.

[0126] The working principle and beneficial effects of the above technical solution are:

[0127] The present invention customizes indicator names, indicator types (such as counting, summing, average, etc.), indicator sources (i.e., connected data sources), calculation logic, etc. according to business needs, making the formulation of data indicators more flexible.

[0128] In one embodiment, based on the dialogue form, the data indicators are queried through the big model to obtain the query results and analysis results, including:

[0129] Acquire first dialogue information generated based on the dialogue form; wherein the first dialogue information is: dialogue semantics generated in real time by the dialogue user in the AI ​​dialogue interface;

[0130] Based on the preset query condition extraction template, according to the first conversation information, a first query condition is determined; wherein the preset query condition extraction template is formulated according to the historical record of manually formulating query conditions according to query requirements; the first query condition is: the query condition of the data indicator obtained by comparing the first conversation information with the query condition extraction template;

[0131] The data index is queried according to the first query condition through the large model to obtain the query results and analysis results.

[0132] The working principle and beneficial effects of the above technical solution are:

[0133] The present invention extracts a template based on the first dialogue information extracted from the AI ​​dialogue and the introduced query condition, determines the query condition of the data indicator, and improves the efficiency of determining the first query condition.

[0134] In one embodiment, extracting a template based on a preset query condition and determining a first query condition according to the first conversation information includes:

[0135] Based on the preset query condition extraction template, obtaining the extraction result of the first query condition according to the first conversation information;

[0136] If the extraction result is successful, determine the corresponding first query condition; if the description factor (e.g., indicator name, application subject) in the first dialogue information matches the condition determination factor (e.g., indicator name, application subject, and query time) corresponding to any pre-selected query condition in the query condition extraction template, then use the corresponding pre-selected query condition as the first query condition;

[0137] If the extraction result is extraction failure, determine the missing dialogue information according to the query condition extraction template and the first dialogue information; wherein the missing dialogue information is: when the description factor in the first dialogue information has the highest matching degree with the corresponding condition determination factor in the query condition extraction template, the description information of the condition determination factor missing from the determined description factors;

[0138] Generate supplementary dialogue reminder information based on missing dialogue information;

[0139] Displaying supplementary conversation reminder information to conversation users;

[0140] Obtain the supplementary conversation information after the conversation user views the supplementary conversation reminder information;

[0141] The template, the first dialogue information and the supplementary dialogue information are extracted according to the query condition to determine the first query condition.

[0142] The working principle and beneficial effects of the above technical solution are:

[0143] When the query condition extraction template is used to extract the first query condition in the first dialogue information, there is a situation where the descriptive factor in the first dialogue information does not meet the condition determination factor of any of the first query condition determination situations. Therefore, before determining the first query condition, the extraction result of the first query condition is obtained; if the extraction is successful, it can be directly extracted; if the extraction is unsuccessful, the descriptive factor in the first dialogue information and the corresponding condition determination factor in the query condition extraction template are obtained. When the matching degree is the highest, the corresponding missing condition determination factor that does not match is obtained, and the missing dialogue information is obtained according to the missing condition determination factor; based on the missing dialogue information, supplementary dialogue reminder information is generated and the dialogue user is reminded to supplement the dialogue information; after the supplement, the first query condition is extracted based on the query condition extraction template, thereby improving the rationality of the first query condition determination process.

[0144] In one embodiment, before querying the data index according to the first query condition through the large model, the method further includes:

[0145] Determine whether to trigger a multi-round dialogue; wherein, when determining whether to trigger a multi-round dialogue, if the user clicks a preset "continue to ask" button on the dialogue interface, the multi-round dialogue state is entered, and the query condition is automatically determined by connecting the context content;

[0146] If multiple rounds of dialogue are triggered, a second query condition for the triggered second dialogue information is obtained; wherein the second query condition is: after the multiple rounds of dialogue are triggered, the data indicator query condition determined above;

[0147] According to the first query condition and the second query condition, the data indicators are queried through the large model to obtain query results and analysis results.

[0148] The working principle and beneficial effects of the above technical solution are:

[0149] The present invention introduces a question-and-answer format of multiple rounds of dialogue. According to the first query condition and the second query condition, data indicators are queried through a large model to obtain query results and analysis results. Through multiple rounds of dialogue, the system can more accurately capture and understand the user's query intentions and needs, thereby providing more accurate query results.

[0150] In one embodiment, according to the first query condition and the second query condition, the data index is queried through the large model to obtain the query result and the analysis result, including:

[0151] Obtain the verification result of the query result by the dialog user; wherein the verification result is: the result of verifying whether the query result meets the query intention of the dialog user. During the verification, the dialog user is asked through a pop-up window on the dialog interface and the feedback information of the dialog user is obtained;

[0152] If the verification result is that the verification fails, the third query condition is displayed to the dialog user, and a modified query condition after the dialog user modifies the third query condition is obtained; wherein the third query condition is: the first query condition that fails the verification and the second query condition; when obtaining the modified query condition, the dialog user can add or delete the third query condition on his own to obtain the modified query condition;

[0153] Re-obtain query results based on the revised query conditions.

[0154] The working principle and beneficial effects of the above technical solution are:

[0155] The present invention introduces a verification procedure for query results by the dialog user. When the verification fails, the third query condition is displayed to the dialog user, and the revised query condition modified by the dialog user is obtained; the query result is re-obtained based on the revised query condition, thereby improving the accuracy of the query.

[0156] In one embodiment, presenting the third query condition to the dialog user, and obtaining the modified query condition after the dialog user modifies the third query condition, includes:

[0157] Parse the third query condition to determine at least one unit condition; wherein the unit condition is: a basic unit constituting the third query condition;

[0158] Obtain a deletion path of the unit condition, and associate the deletion path with a preset operation position of a visual icon of the unit condition; wherein the deletion path is: a program in the system for executing the deletion of the unit condition; the visual icon is: a visual element of the unit condition; the preset operation position is: a position preset by the visual icon for indicating a deletion operation, such as: an "x" symbol in the upper right corner of the icon;

[0159] Obtain the condition constraint type of the unit condition. The condition constraint types include necessary constraints and non-necessary constraints. Among them, necessary constraints are conditions that must be met to execute data indicator queries; non-necessary constraints are conditions that do not have to be met to execute data indicator queries. For example, to count the birth population in the past 10 years, necessary constraints are time, date of birth, etc., and non-necessary constraints are gender, etc.

[0160] If the conditional constraint type is a necessary constraint, when the number of unit conditions of any conditional constraint type is identified to be 1 and the deletion path of the corresponding unit condition is triggered, the corresponding unit condition is used as the target unit condition;

[0161] Obtain a candidate list of unit conditions preset for the target unit condition; the candidate list of unit conditions includes multiple candidate unit conditions, and the candidate unit conditions are sorted from large to small according to the correlation with the remaining unit conditions. Among them, the condition description content of the candidate unit condition is consistent with the condition description content type of the target unit condition, for example: when the target unit condition is 2022, the candidate unit condition can be: 2023, 2021, etc.; the remaining unit conditions are: the remaining conditions in the unit condition except the target unit condition; the correlation is: the quantitative value of the degree of association;

[0162] Displaying the candidate list of unit conditions to the dialog user, and reminding the dialog user to keep at least one unit condition whose condition constraint type is a necessary constraint;

[0163] Determine the selection result of the dialog user and obtain the modified query condition, wherein the selection result is: the cancel deletion operation or the candidate unit condition selected by the dialog user.

[0164] The working principle and beneficial effects of the above technical solution are:

[0165] The present invention splits the third query condition to obtain unit conditions; introduces an operation position for a deletion path of the unit conditions, so that when the corresponding unit conditions are not needed, the dialog user can directly delete the corresponding unit conditions based on the query logic, which is more convenient; in addition, the condition constraint type of the unit condition is introduced, and when the condition constraint type is a necessary constraint, when it is recognized that the number of unit conditions of any condition constraint type is 1 and the deletion path of the corresponding unit condition is triggered, the corresponding unit condition is used as the target unit condition, and a unit condition candidate list of the target unit condition is obtained; the unit condition candidate list is displayed to the dialog user, and the candidate unit conditions in the unit condition candidate list are sorted from large to small according to the correlation with the remaining unit conditions, and the candidate unit conditions that are more likely to be selected are presented more preferentially, constraining the dialog user to retain at least one unit condition whose condition constraint type is a necessary constraint, and obtaining a modified query condition, thereby improving the standardization of the query condition modification.

[0166] In one embodiment, a big data index query and analysis method based on a big model further includes:

[0167] Label development is performed based on data indicators to obtain label development results; label development results include: original labels, combined labels, and external labels. Label development is: creating labels for classifying and identifying user groups or data points based on data indicators and user behaviors; original labels are calculated and judged based on different data sources; combined labels are calculated and combined based on different labels; and external labels are defined based on external label data.

[0168] The working principle and beneficial effects of the above technical solution are:

[0169] The present invention develops labels for data indicators, provides more detailed screening conditions, and has higher reusability.

[0170] In one embodiment, a big data index query and analysis method based on a big model further includes:

[0171] According to the label development results, obtain the label task list; wherein the label task list: a list storing the label online status;

[0172] Determine the execution result according to the list operation of the tag task list; wherein the list operation is: an operation to control the online and offline status of the tags in the tag task list;

[0173] Get the index link of the task instance display interface in the tag task list; wherein the index link is: the preset viewing link of the task instance display interface;

[0174] Get the task instance running status according to the index link. The task instance running status includes: running time, creation time, and update time.

[0175] The working principle and beneficial effects of the above technical solution are:

[0176] This application obtains the label task list according to the label development results; introduces the list operation of the label task list, determines the execution results, reasonably sets the online and offline cycles, and reduces the occupation of system resources; constructs a viewing index for the running status of the task instance, and the user can directly click the index link to view the running status of the task instance, which is more convenient.

[0177] In one embodiment, a big data index query and analysis method based on a big model further includes:

[0178] Based on the label development results, single-object panoramic profiling and group analysis are performed; single-object panoramic profiling refers to a comprehensive analysis of a single object (such as a single user or a single product), including all relevant data and labels of the object, forming a 360-degree complete view; group analysis refers to the statistics and analysis of a group of objects (such as a user group or a product collection) to identify the characteristics, behavior patterns or trends of the group;

[0179] Sharing the tag API according to the tag development results; wherein the tag API is: an application programming interface that provides tag data or tag generation capabilities to other systems or services in the form of an API;

[0180] When sharing the tag API, the API call statistics are performed; wherein the API call statistics are: the process of recording and analyzing the usage of the tag API, including the number of calls, call time, call source and other information;

[0181] When sharing a tag API, obtain the application list of the tag API, which includes: application information and associated API information; wherein the application information includes: application ID, application name, etc.; the associated API information includes: API name, status, creator, authorization validity period, and associated API operation, etc.;

[0182] Parse the associated API information and obtain the associated API operation; wherein the operation types of the associated API operation include: generating an interface document and removing.

[0183] The working principle and beneficial effects of the above technical solution are:

[0184] The present invention performs single-object panoramic profiling and group analysis based on the label development results, and generates a shared label API for external services. In addition, the application list of the label API is introduced to obtain application information, and the detailed information of the API associated with the application is obtained according to the application information. The interface document is directly generated or removed for its operation, which improves the data sharing efficiency and the convenience of calling.

[0185] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A big data index query and analysis method based on a big model, characterized in that: include: Access data sources; After accessing the data source, establish data indicators based on business needs; Based on the dialogue form, query data indicators through the big model to obtain query results and analysis results; Visualize the query and analysis results.

2. A big data index query and analysis method based on a big model as claimed in claim 1, characterized in that: Access data sources, including: Determine the type of data source required; Fill in the connection information according to the preset connection information template of the required data source type; After completing the connection information, test the connection status until the connection is successful.

3. A big data index query and analysis method based on a big model as claimed in claim 1, characterized in that: After accessing the data source, establish data indicators based on business needs, including: According to business needs, obtain indicator establishment information, which includes: indicator name, indicator type, indicator source and calculation logic; Establish information based on indicators and establish data indicators.

4. A method for querying and analyzing big data indicators based on a big model as claimed in claim 1, characterized in that: Based on the dialogue form, query data indicators through the big model to obtain query results and analysis results, including: Acquire first dialogue information generated based on the dialogue form; Extracting a template based on a preset query condition, and determining a first query condition according to the first conversation information; The data index is queried according to the first query condition through the large model to obtain the query results and analysis results.

5. A method for querying and analyzing big data indicators based on a big model as claimed in claim 4, characterized in that: Extracting a template based on a preset query condition and determining a first query condition according to the first conversation information includes: Based on the preset query condition extraction template, obtaining the extraction result of the first query condition according to the first conversation information; If the extraction result is successful, determine the corresponding first query condition; If the extraction result is extraction failure, extract the template and the first dialogue information according to the query condition to determine the missing dialogue information; Generate supplementary dialogue reminder information based on missing dialogue information; Displaying supplementary conversation reminder information to conversation users; Obtain the supplementary conversation information after the conversation user views the supplementary conversation reminder information; The template, the first dialogue information and the supplementary dialogue information are extracted according to the query condition to determine the first query condition.

6. A method for querying and analyzing big data indicators based on a big model as claimed in claim 4, characterized in that: Also includes: Before querying the data indicator according to the first query condition through the big model, determine whether to trigger multiple rounds of dialogue; If multiple rounds of dialogue are triggered, a second query condition for obtaining the second dialogue information that has been triggered; According to the first query condition and the second query condition, the data indicators are queried through the large model to obtain query results and analysis results.

7. A method for querying and analyzing big data indicators based on a big model as claimed in claim 6, characterized in that: According to the first query condition and the second query condition, the data indicators are queried through the large model to obtain query results and analysis results, including: Obtain the verification result of the query result by the dialog user; If the verification result is that the verification is unsuccessful, the third query condition is displayed to the dialog user, and a modified query condition after the dialog user modifies the third query condition is obtained; Re-obtain query results based on the revised query conditions.

8. A method for querying and analyzing big data indicators based on a big model as claimed in claim 3, characterized in that: Also includes: Develop labels based on data indicators and obtain label development results; The label development results include: original labels, combined labels and external labels.

9. A method for querying and analyzing big data indicators based on a big model as claimed in claim 8, characterized in that: Also includes: According to the label development results, obtain the label task list; Determine the execution result according to the list operation of the tag task list; Get the index link of the task instance display interface in the tag task list; Get the task instance running status according to the index link.

10. A method for querying and analyzing big data indicators based on a big model as claimed in claim 8, characterized in that: Also includes: Based on the label development results, single-object panoramic profiling and group analysis are performed; Based on the tag development results, share the tag API; When sharing tag API, collect API call statistics; When sharing a tag API, obtain the tag API application list, which includes: application information and associated API information; Parse the associated API information and obtain the associated API operations; wherein the operation types of the associated API operations include: generating an interface document and removing.

Images