Data demand analysis method and device based on index system, equipment and medium

Abstract

The invention relates to the technical field of intelligent decision making, and discloses a data demand analysis method and device based on an index system, equipment and a medium, and the data demand analysis method based on the index system comprises the steps: extracting an initial business index and initial key information of a preset business demand through a preset large model; according to the initial key information, disassembling the initial business index to generate at least one current index; and matching the current index with each preset index in a preset index library to generate a matching result, and generating a data demand analysis strategy of the preset service demand according to the matching result. Through the above mode, by analyzing the complex business demand, automatically identifying the key information, matching the current index with the indexes in the preset index library, and identifying the reusability of the existing index, repeated construction caused by artificial understanding difference is reduced, and the efficiency of business index demand analysis in the financial business field is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent decision-making technology, and in particular to a data demand analysis method, device, equipment and medium based on an indicator system. Background Art

[0002] In the financial sector, as digital transformation deepens, enterprises are facing an explosive growth in data volumes. The financial industry's data needs often involve complex business metrics. Existing technologies often lack unified standards and languages ​​for demand analysis and data processing, leading to extensive duplication of processing. This duplication not only increases hardware and computing costs but, more importantly, reduces data processing efficiency.

[0003] For example, a financial institution will have approximately 80,000 big data processing jobs by the end of 2023, consuming an average of 250,000 CPU hours per month. The financial industry faces significant cost pressures and technical challenges in data processing and analysis. Traditional data requirements analysis relies on manual interpretation of business requirements documents, which can lead to inaccurate requirements analysis and duplication due to differences in human understanding. This is especially true when complex indicators span multiple dimensions and timeframes, making manual analysis difficult to ensure efficiency and accuracy. Therefore, improving the efficiency of business indicator requirements analysis in the financial sector has become a pressing technical challenge. Summary of the Invention

[0004] This application provides a data demand analysis method, device, equipment and medium based on an indicator system to improve the efficiency of business indicator demand analysis in the financial business field.

[0005] In a first aspect, the present application provides a data demand analysis method based on an indicator system, the method comprising:

[0006] Extract the initial business indicators and initial key information of the preset business needs through the preset large model;

[0007] Decomposing the initial business indicator according to the initial key information to generate at least one current indicator;

[0008] The current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and based on the matching result, a data demand analysis strategy for the preset business demand is generated.

[0009] In a second aspect, the present application further provides a data demand analysis device based on an indicator system, the device comprising:

[0010] The business information extraction module is used to extract the initial business indicators and initial key information of the preset business requirements through the preset large model;

[0011] A current indicator generating module, configured to decompose the initial business indicator according to the initial key information to generate at least one current indicator;

[0012] The data demand analysis strategy generation module is used to match the current indicator with each preset indicator in the preset indicator library, generate a matching result, and generate a data demand analysis strategy for the preset business demand based on the matching result.

[0013] In a third aspect, the present application also provides a computer device comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the data demand analysis method based on the indicator system as described above when executing the computer program.

[0014] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the data demand analysis method based on the indicator system as described above.

[0015] The present application discloses a data demand analysis method, device, equipment and medium based on an indicator system. The data demand analysis method based on the indicator system includes extracting the initial business indicators and initial key information of the preset business needs through a preset large model; disassembling the initial business indicators according to the initial key information to generate at least one current indicator; matching the current indicators with each preset indicator in the preset indicator library to generate a matching result, and generating a data demand analysis strategy for the preset business needs based on the matching result. Through the above method, the present application automatically identifies key information by parsing complex business needs, matches the current indicators with the indicators in the preset indicator library, identifies the reusability of existing indicators, reduces duplication of construction caused by differences in human understanding, and improves the efficiency of business indicator demand analysis in the financial business field. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a schematic flow chart of a data demand analysis method based on an indicator system provided in the first embodiment of the present application;

[0018] Figure 2This is a schematic flow chart of a data demand analysis method based on an indicator system provided in the second embodiment of the present application;

[0019] Figure 3 A schematic block diagram of a data demand analysis device based on an indicator system provided in an embodiment of the present application;

[0020] Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0023] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] The embodiments of the present application provide a data demand analysis method, apparatus, device, and medium based on an indicator system. The data demand analysis method based on an indicator system can be applied to a server. By analyzing complex business requirements, it automatically identifies key information, matches current indicators with indicators in a preset indicator library, and identifies the reusability of existing indicators. This reduces duplication of work due to differences in human understanding and improves the efficiency of business indicator demand analysis in the financial business field. The server can be a standalone server or a server cluster.

[0026] The present application can be applied in the financial business field. The following, in conjunction with the accompanying drawings, takes the application of the present application in the financial business field as an example to describe some embodiments of the present application in detail. The following embodiments and features of the embodiments can be combined with each other unless there is a conflict.

[0027] See also Figure 1 , Figure 1 This is a schematic flow chart of a data requirements analysis method based on an indicator system, provided in the first embodiment of this application. This data requirements analysis method based on an indicator system can be applied to a server to automatically identify key information by parsing complex business requirements, matching current indicators with indicators in a preset indicator library, and identifying the reusability of existing indicators. This reduces duplication of work caused by differences in human understanding and improves the efficiency of business indicator requirements analysis in the financial business field.

[0028] like Figure 1 As shown, the data demand analysis method based on the indicator system specifically includes steps S10 to S30.

[0029] Step S10: extracting initial business indicators and initial key information of preset business requirements through a preset large model;

[0030] Specifically, this embodiment is applied to the insurance field to illustrate the various steps of this embodiment. Initial business indicators (such as "signing premium") are extracted from the initial key information, and initial key information related to the initial business indicators (such as "signing date", "premium", "institution", etc.) are extracted. The business requirements document is parsed by the preset large model to extract the following initial key information:

[0031] Business Objective: The background or goal of the business need (e.g., "analyze the growth trend of premiums written");

[0032] Core business indicators: business indicators clearly mentioned in the requirements (such as "signed premium");

[0033] Time limit information: a field used to define the time range of the indicator (such as "signing date");

[0034] Metrics: numerical values ​​used to measure the level or status of business (e.g., “premium”);

[0035] Dimensional information: used to analyze indicators from different perspectives (such as "organization" or "product category").

[0036] Statistical period: the time range or time point for data statistics (such as "this month")

[0037] Specifically as shown in Table 1, Table 1 is the interpretation and examples of the initial business indicators and initial key information in the first embodiment of this application.

[0038] Table 1

[0039]

[0040] Step S20: Decomposing the initial business indicator according to the initial key information to generate at least one current indicator;

[0041] Specifically, based on the initial key information (such as time limit information, measurement information and dimension information), the initial business indicators are broken down into atomic indicators that cannot be further divided.

[0042] For example, decompose "signing premium" into:

[0043] Time limit: signing date;

[0044] Metrics: Premium;

[0045] Dimension: Institutional.

[0046] The preset large model automatically breaks down the business indicators in the requirements into atomic indicators, time limits, metrics, dimensions, and statistical periods. At the same time, it automatically matches the derived indicator library and atomic indicator library of the indicator cloud platform and generates a matching result report:

[0047] Successful match: Directly reference existing indicators without adding new ones;

[0048] Partial matching success: prompts the need for additional atomic indicators, dimensions, time limits or metrics;

[0049] Matching failure: Generate new indicator suggestions, including indicator definition, calculation logic, and storage method.

[0050] Step S30: Match the current indicator with each preset indicator in the preset indicator library to generate a matching result, and generate a data demand analysis strategy for the preset business demand based on the matching result.

[0051] Specifically, based on the matching results, a data demand analysis strategy is generated, including:

[0052] Recommendations for reusing existing indicators: Directly reference existing indicators that have been successfully matched.

[0053] New indicator suggestions: Provide new suggestions for indicators that failed to match.

[0054] Optimization suggestions: Optimize the calculation logic, dimension hierarchy, etc. of existing indicators.

[0055] Metadata management: Generate metadata documents to record the source, calculation logic, and usage scenarios of indicators.

[0056] In one embodiment, detailed information of the current indicator, such as indicator name, definition, calculation logic, storage method, etc., is input, and the detailed information of the current indicator is organized into a structured data format, such as JSON (JavaScript Object Notation) or XML (Extensible Markup Language), ensuring that the preset indicator information in the preset indicator library is also stored in the same structured format to finally output the structured current indicator data and preset indicator library data.

[0057] Input structured current indicator data and preset indicator library data, and match them according to the following dimensions:

[0058] Indicator name: compare the current indicator name with the preset indicator name;

[0059] Indicator definition: compare the current indicator definition with the preset indicator definition;

[0060] Calculation logic: compare the current indicator calculation logic with the preset indicator calculation logic;

[0061] Storage method: compare the current indicator storage method with the preset indicator storage method;

[0062] Dimension information: compare the current indicator dimension information with the preset indicator dimension information;

[0063] Matching algorithm: Use text similarity algorithm (such as cosine similarity, Jaccard similarity) or rule matching algorithm for matching;

[0064] The final output is the matching results, which include a list of indicators of successful, partially successful, or failed matches.

[0065] If the final match is successful, the information that the current indicator completely matches the preset indicator is recorded;

[0066] If the final partial match is successful, the information that the current indicator partially matches the preset indicator is recorded, and the unmatched dimensions are pointed out;

[0067] If the final matching fails, the information that the current indicator does not match the preset indicator at all is recorded.

[0068] For indicators that are successfully matched, the indicators in the preset indicator library are directly referenced. For indicators that are partially matched, the corresponding atomic indicators, dimensions, time limits or measurements are supplemented according to the unmatched dimensions. For indicators that fail to match, new indicator suggestions are generated, including indicator definitions, calculation logic and storage methods.

[0069] The present embodiment discloses a data demand analysis method, device, equipment and medium based on an indicator system, wherein the data demand analysis method based on the indicator system includes extracting the initial business indicators and initial key information of the preset business needs through a preset large model; decomposing the initial business indicators according to the initial key information to generate at least one current indicator; matching the current indicators with each preset indicator in the preset indicator library to generate a matching result, and generating a data demand analysis strategy for the preset business needs based on the matching result. Through the above method, the present application automatically identifies key information by parsing complex business needs, matches the current indicators with the indicators in the preset indicator library, identifies the reusability of existing indicators, reduces duplication of construction caused by differences in human understanding, and improves the efficiency of business indicator demand analysis in the financial business field.

[0070] See also Figure 2 , Figure 2 This is a schematic flow chart of a data demand analysis method based on an indicator system provided in the second embodiment of the present application. This data demand analysis method based on an indicator system can be applied to a server and is used to match based on a preset business indicator library and a preset key information library, thereby ensuring the consistency and accuracy of business indicators and key information, avoiding errors caused by differences in human understanding, and significantly improving the efficiency of data demand analysis. By matching the current indicators with the preset indicator library, existing indicators are identified. By reusing existing indicators and optimizing calculation logic, repeated development is avoided, resources and time are saved, and the efficiency of business indicator demand analysis in the financial business field is improved.

[0071] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S10 includes steps S101 to S104.

[0072] Step S101: Acquire a preset business indicator database and a preset key information database;

[0073] Specifically, a preset business indicator library is obtained from the enterprise's data warehouse, data mart or indicator management system. The preset business indicator library contains all defined business indicators and their detailed information, such as indicator name, definition, calculation logic, storage location, etc.

[0074] Obtain the preset key information database from the enterprise's metadata management system or key information database. The preset key information database contains all defined key information, such as statistical period information, time limit information, measurement information, etc.

[0075] Step S102: extracting various business keywords and various information keywords in the preset business requirements through the preset large model;

[0076] Specifically, the pre-set business requirements document is parsed using a pre-set large model to extract business keywords and information keywords. Business keywords are keywords related to business indicators (such as "signed premium" and "number of Yilan users"), while information keywords are keywords related to key information (such as "signed date", "current month", and "premium").

[0077] Step S103: determining the preset business indicators in the preset business indicator library that match the business keywords as the initial business indicators;

[0078] Specifically, the preset business indicator library is traversed to find the preset business indicators that match the business keywords.

[0079] Matching dimensions include indicator name, indicator definition, calculation logic, etc., that is, whether the indicator name contains business keywords, whether the indicator definition contains business keywords, and whether the calculation logic contains business keywords, and finally generate an initial business indicator list.

[0080] Step S104: Determine the preset key information in the preset key information database that matches each of the information keywords as the initial key information, wherein the initial key information includes statistical period information, time limit information, and measurement information.

[0081] Specifically, the preset key information database is traversed to search for preset key information that matches the information keyword.

[0082] Matching dimensions include statistical period information, time limit information, and measurement information. Determine whether the statistical period information contains information keywords (such as "current month"), whether the time limit information contains information keywords (such as "order date"), and whether the measurement information contains information keywords (such as "premium").

[0083] The present embodiment discloses a data demand analysis method, apparatus, equipment and medium based on an indicator system. The data demand analysis method based on the indicator system includes obtaining a preset business indicator library and a preset key information library; extracting each business keyword and each information keyword in the preset business demand through the preset large model; determining the preset business indicator that matches each business keyword in the preset business indicator library as the initial business indicator; determining the preset key information that matches each information keyword in the preset key information library as the initial key information, wherein the initial key information includes statistical period information, time limit information and measurement information; disassembling the initial business indicator according to the initial key information to generate at least one current indicator; matching the current indicator with each preset indicator in the preset indicator library to generate a matching result, and generating a data demand analysis strategy for the preset business demand based on the matching result. Through the above method, this application is based on matching the preset business indicator library and the preset key information library, ensuring the consistency and accuracy of business indicators and key information, avoiding errors caused by differences in human understanding, and significantly improving the efficiency of data demand analysis. By matching the current indicators with the preset indicator library, existing indicators are identified. By reusing existing indicators and optimizing calculation logic, repeated development is avoided, resources and time are saved, and the efficiency of business indicator demand analysis in the financial business field is improved.

[0084] based on Figure 2 In the embodiment shown, in this embodiment, step S20 includes:

[0085] Decomposing the initial business indicator according to the time limit information and the measurement information by the preset large model to generate at least one current atomic indicator;

[0086] Matching the current atomic index with each preset atomic index in a preset atomic index library;

[0087] If there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, the current derived indicator is generated according to the statistical period information and the current atomic indicator.

[0088] Specifically, obtain a preset business indicator library and a preset key information library, parse the preset business requirements through a preset large model, extract business keywords and information keywords, match the business keywords in the preset business indicator library, and determine the initial business indicators.

[0089] Match information keywords in the preset key information database to determine the initial key information, which can be statistical period, time and measurement.

[0090] Based on the time and measurement details in the initial key information, the initial business indicators are decomposed into current atomic indicators, and the current atomic indicators are matched with the preset atomic indicators in the preset atomic indicator library to check whether there are the same indicators.

[0091] If the match is successful, the preset atomic indicators are directly reused to ensure efficient resource utilization;

[0092] If the match fails, the current derivative indicator is generated based on the statistical period information and the current atomic indicator to meet the new business needs.

[0093] The present embodiment discloses a data demand analysis method, apparatus, equipment and medium based on an indicator system. The data demand analysis method based on the indicator system includes extracting initial business indicators and initial key information of preset business needs through a preset large model; decomposing the initial business indicators according to the time limit information and the measurement information through the preset large model to generate at least one current atomic indicator; matching the current atomic indicator with each preset atomic indicator in a preset atomic indicator library; if there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, generating the current derived indicator according to the statistical period information and the current atomic indicator; matching the current indicator with each preset indicator in the preset indicator library to generate a matching result, and generating a data demand analysis strategy for the preset business needs based on the matching result. Through the above method, this application is based on matching of preset large models and preset libraries, ensuring the consistency and accuracy of business indicators and key information, avoiding errors and duplication of work caused by differences in human understanding, and over-matching current atomic indicators with preset atomic indicator libraries to identify existing indicators, avoiding repeated development, saving resources and time, and improving resource utilization efficiency, thereby improving the efficiency of business indicator demand analysis in the financial business field.

[0094] In a specific embodiment, the initial business indicator is decomposed and processed by the preset large model according to the time limit information and the measurement information to generate at least one current atomic indicator, including:

[0095] Decomposing the initial business indicator into initial sub-indicators corresponding to each of the information keywords through the preset large model;

[0096] Determining a time-limited keyword from the initial service indicator based on the time-limited information, and determining a measurement keyword from the initial service indicator based on the measurement information;

[0097] The initial sub-index corresponding to the time-limited keyword and the initial sub-index corresponding to the measurement keyword are respectively determined as the current atomic index.

[0098] Specifically, a preset business indicator library and a preset key information library are obtained from the enterprise's data warehouse or indicator management system.

[0099] The preset business requirement document is parsed through the preset large model to extract the following content:

[0100] Initial business indicators: indicators related to business (such as "signed premium");

[0101] Initial key information: Keywords related to business indicators (such as "signing date", "premium", "current month", etc.), and the following information is extracted from the initial key information:

[0102] Time limit information: a field used to define the time range of the indicator (such as "signing date");

[0103] Metric information: A numerical value used to measure business level or status (such as "premium"). By presetting a large model, the initial business indicator is broken down into multiple initial sub-indicators based on the time limit information and metric information in the initial key information. For example, "signing premium" is broken down into "premium on the signing date" and "premium for the current month."

[0104] Keywords related to time-limited information (such as "signing date") and keywords related to measurement information (such as "premium") are extracted from the initial business indicators.

[0105] The initial sub-indicator corresponding to the time-limited keyword is determined as the current atomic indicator (such as "premium on the signing date") and the initial sub-indicator corresponding to the measurement keyword is determined as the current atomic indicator (such as "premium for the current month").

[0106] Match the current atomic indicator with the preset atomic indicator in the preset atomic indicator library. If the match is successful, directly reference the existing atomic indicator. If the match fails, generate a derived indicator. If there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, generate the current derived indicator based on the statistical period information and the current atomic indicator.

[0107] In a specific embodiment, if there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, generating the current derived indicator according to the statistical period information and the current atomic indicator includes:

[0108] The statistical period information and the current atomic indicator are aggregated to generate the current derived indicator.

[0109] Specifically, the aggregation dimension is determined according to business needs, such as by time, by organization, by product category, etc., to aggregate the current atomic indicators. The forms of aggregation include:

[0110] Aggregation by time: Aggregate the current atomic indicators by statistical period. For example, aggregate the daily "premium on the signing date" by month. In addition, aggregation can also be performed by other dimensions (such as institution, product category).

[0111] In a specific embodiment, the current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and a data demand analysis strategy for the preset business demand is generated based on the matching result, including:

[0112] Matching each of the current atomic indicators with each of the preset atomic indicators in the preset atomic indicator library;

[0113] If the preset atomic indicator library contains the preset atomic indicator that matches the current atomic indicator, the data demand analysis strategy is generated according to the current atomic indicator.

[0114] Specifically, the preset atomic index library is traversed to find the preset atomic index that matches the current atomic index, where the matching dimensions include:

[0115] Indicator name: whether the current atomic indicator name is consistent with the preset atomic indicator name;

[0116] Indicator definition: whether the current atomic indicator definition is consistent with the preset atomic indicator definition;

[0117] Calculation logic: whether the current atomic indicator calculation logic is consistent with the preset atomic indicator calculation logic;

[0118] Storage method: Whether the current atomic indicator storage method is consistent with the preset atomic indicator storage method.

[0119] For the current atomic indicator that matches successfully, directly reference the preset atomic indicator;

[0120] For current atomic indicators that fail to match, new indicator suggestions are provided. The atomic indicator suggestions include indicator definition, calculation logic, and storage method.

[0121] In a specific embodiment, the current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and a data demand analysis strategy for the preset business demand is generated based on the matching result, including:

[0122] Matching the current derivative indicator with each preset derivative indicator in the preset derivative indicator library;

[0123] If the preset derivative indicator library contains the preset derivative indicator that matches the current derivative indicator, generating the data demand analysis strategy according to the current derivative indicator;

[0124] If the preset derivative indicator library does not contain the preset derivative indicator that matches the current derivative indicator, then decomposing each preset business indicator in the preset business indicator library according to the dimension information to generate a decomposed derivative indicator;

[0125] The data demand analysis strategy is generated based on the disassembly-derived indicators.

[0126] Specifically, the current derivative indicator and the preset derivative indicator are matched through the following dimensions, including:

[0127] Whether the current derived indicator name is consistent with the preset derived indicator name;

[0128] Whether the current derivative indicator definition is consistent with the preset derivative indicator definition;

[0129] Whether the current derivative indicator calculation logic is consistent with the preset derivative indicator calculation logic;

[0130] Whether the current derived indicator storage method is consistent with the preset derived indicator storage method.

[0131] If the match is successful, the preset derivative indicator of the successful match is directly referenced;

[0132] If the match fails, the preset business indicators in the preset business indicator library are disassembled through dimension information. According to the dimension information (such as "organization" and "product category"), the preset business indicators in the preset business indicator library are disassembled to generate disassembled derivative indicators.

[0133] See also Figure 3 , Figure 3 The embodiment of the present application provides a schematic block diagram of a data demand analysis device based on an indicator system, wherein the data demand analysis device based on an indicator system is used to execute the aforementioned data demand analysis method based on an indicator system. The data demand analysis device based on an indicator system can be configured on a server.

[0134] like Figure 3 As shown, the data demand analysis device 400 based on the indicator system includes:

[0135] The business information extraction module 410 is used to extract initial business indicators and initial key information of preset business requirements through a preset large model;

[0136] A current indicator generating module 420 is configured to decompose the initial business indicator according to the initial key information to generate at least one current indicator;

[0137] The data demand analysis strategy generation module 430 is used to match the current indicator with each preset indicator in the preset indicator library to generate a matching result, and generate a data demand analysis strategy for the preset business demand based on the matching result.

[0138] Furthermore, the business information extraction module 410 includes:

[0139] The database acquisition submodule is used to obtain the preset business indicator database and the preset key information database;

[0140] A keyword extraction submodule, configured to extract various business keywords and information keywords in the preset business requirements through the preset large model;

[0141] An initial business indicator determination submodule, configured to determine a preset business indicator in the preset business indicator library that matches each of the business keywords as the initial business indicator;

[0142] The initial key information determination submodule is used to determine the preset key information matching each of the information keywords in the preset key information database as the initial key information, wherein the initial key information includes statistical period information, time limit information and measurement information.

[0143] Furthermore, the current indicator generation module 420 includes:

[0144] a current atomic indicator generating submodule, configured to decompose the initial business indicator according to the time limit information and the measurement information using the preset large model to generate at least one current atomic indicator;

[0145] An atomic index matching submodule, configured to match the current atomic index with each preset atomic index in a preset atomic index library;

[0146] The current derived indicator generating submodule is configured to generate the current derived indicator according to the statistical period information and the current atomic indicator if there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library.

[0147] Furthermore, the current atomic index generation submodule includes:

[0148] An initial sub-indicator generating unit, configured to decompose the initial business indicator into initial sub-indicators corresponding to each of the information keywords using the preset large model;

[0149] a metric keyword determining unit, configured to determine a time-limited keyword from the initial business indicator according to the time-limited information, and to determine a metric keyword from the initial business indicator according to the metric information;

[0150] The current atomic indicator determination unit is configured to respectively determine the initial sub-indicator corresponding to the time-limited keyword and the initial sub-indicator corresponding to the measurement keyword as the current atomic indicator.

[0151] Furthermore, the current derived indicator generation submodule includes:

[0152] The current derived indicator generating unit is used to aggregate the statistical period information and the current atomic indicator to generate the current derived indicator.

[0153] Furthermore, the data demand analysis strategy generation module 430 includes:

[0154] an atomic index matching unit, configured to match each of the current atomic indexes with each of the preset atomic indexes in the preset atomic index library;

[0155] The first data demand analysis strategy generating unit is configured to generate the data demand analysis strategy according to the current atomic indicator if the preset atomic indicator library contains the preset atomic indicator that matches the current atomic indicator.

[0156] Furthermore, the data demand analysis strategy generation module 430 includes:

[0157] A derivative indicator matching unit, configured to match the current derivative indicator with each preset derivative indicator in the preset derivative indicator library;

[0158] a second data demand analysis strategy generating unit, configured to generate the data demand analysis strategy according to the current derived indicator if the preset derived indicator library contains the preset derived indicator that matches the current derived indicator;

[0159] a disassembly derivative indicator generating unit, configured to, if the preset derivative indicator library does not contain the preset derivative indicator matching the current derivative indicator, disassemble each preset business indicator in the preset business indicator library using the dimension information to generate a disassembly derivative indicator;

[0160] The third data demand analysis strategy generating unit is configured to generate the data demand analysis strategy according to the disassembly derived indicators.

[0161] It should be noted that those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] The above-mentioned device can be realized in the form of a computer program. The computer program can be used in Figure 4Runs on the computer device shown.

[0163] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0164] See Figure 4 The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0165] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause a processor to execute any data demand analysis method based on an indicator system.

[0166] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0167] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any data demand analysis method based on the indicator system.

[0168] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0169] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0170] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0171] Extract the initial business indicators and initial key information of the preset business needs through the preset large model;

[0172] Decomposing the initial business indicator according to the initial key information to generate at least one current indicator;

[0173] The current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and based on the matching result, a data demand analysis strategy for the preset business demand is generated.

[0174] In one embodiment, initial business indicators and initial key information of preset business requirements are extracted through a preset large model to achieve:

[0175] Obtain the preset business indicator database and preset key information database;

[0176] Extracting each business keyword and each information keyword in the preset business requirement through the preset large model;

[0177] Determining the preset business indicators that match the business keywords in the preset business indicator library as the initial business indicators;

[0178] The preset key information in the preset key information database that matches each of the information keywords is determined as the initial key information, wherein the initial key information includes statistical period information, time limit information and measurement information.

[0179] In one embodiment, the initial business indicator is decomposed based on the initial key information to generate at least one current indicator for achieving:

[0180] Decomposing the initial business indicator according to the time limit information and the measurement information by the preset large model to generate at least one current atomic indicator;

[0181] Matching the current atomic index with each preset atomic index in a preset atomic index library;

[0182] If there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, the current derived indicator is generated according to the statistical period information and the current atomic indicator.

[0183] In one embodiment, the preset large model decomposes the initial business indicator according to the time limit information and the measurement information to generate at least one current atomic indicator for achieving:

[0184] Decomposing the initial business indicator into initial sub-indicators corresponding to each of the information keywords through the preset large model;

[0185] Determining a time-limited keyword from the initial service indicator based on the time-limited information, and determining a measurement keyword from the initial service indicator based on the measurement information;

[0186] The initial sub-index corresponding to the time-limited keyword and the initial sub-index corresponding to the measurement keyword are respectively determined as the current atomic index.

[0187] In one embodiment, if there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, the current derived indicator is generated according to the statistical period information and the current atomic indicator, so as to achieve:

[0188] The statistical period information and the current atomic indicator are aggregated to generate the current derived indicator.

[0189] In one embodiment, the current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and based on the matching result, a data demand analysis strategy for the preset business demand is generated to achieve:

[0190] Matching each of the current atomic indicators with each of the preset atomic indicators in the preset atomic indicator library;

[0191] If the preset atomic indicator library contains the preset atomic indicator that matches the current atomic indicator, the data demand analysis strategy is generated according to the current atomic indicator.

[0192] In one embodiment, the current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and based on the matching result, a data demand analysis strategy for the preset business demand is generated to achieve:

[0193] Matching the current derivative indicator with each preset derivative indicator in the preset derivative indicator library;

[0194] If the preset derivative indicator library contains the preset derivative indicator that matches the current derivative indicator, generating the data demand analysis strategy according to the current derivative indicator;

[0195] If the preset derivative indicator library does not contain the preset derivative indicator that matches the current derivative indicator, then decomposing each preset business indicator in the preset business indicator library according to the dimension information to generate a decomposed derivative indicator;

[0196] The data demand analysis strategy is generated based on the disassembly-derived indicators.

[0197] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the data demand analysis methods based on the indicator system provided in the embodiment of the present application.

[0198] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0199] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A data demand analysis method based on an indicator system, characterized in that: include: Extract the initial business indicators and initial key information of the preset business needs through the preset large model; Decomposing the initial business indicator according to the initial key information to generate at least one current indicator; The current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and based on the matching result, a data demand analysis strategy for the preset business demand is generated.

2. The data demand analysis method based on the indicator system according to claim 1 is characterized in that: The extraction of initial business indicators and initial key information of preset business requirements through the preset large model includes: Obtain the preset business indicator database and preset key information database; Extracting each business keyword and each information keyword in the preset business requirement through the preset large model; Determining the preset business indicators that match the business keywords in the preset business indicator library as the initial business indicators; The preset key information in the preset key information database that matches each of the information keywords is determined as the initial key information, wherein the initial key information includes statistical period information, time limit information and measurement information.

3. The data demand analysis method based on the indicator system according to claim 2 is characterized in that: The current indicator includes a current atomic indicator and a current derived indicator. The initial business indicator is decomposed according to the initial key information to generate at least one current indicator, including: Decomposing the initial business indicator according to the time limit information and the measurement information by the preset large model to generate at least one current atomic indicator; Matching the current atomic index with each preset atomic index in a preset atomic index library; If there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, the current derived indicator is generated according to the statistical period information and the current atomic indicator.

4. The data demand analysis method based on the indicator system according to claim 3 is characterized in that: The step of decomposing the initial business indicator according to the time limit information and the measurement information by the preset large model to generate at least one current atomic indicator includes: Decomposing the initial business indicator into initial sub-indicators corresponding to each of the information keywords through the preset large model; Determining a time-limited keyword from the initial service indicator based on the time-limited information, and determining a measurement keyword from the initial service indicator based on the measurement information; The initial sub-index corresponding to the time-limited keyword and the initial sub-index corresponding to the measurement keyword are respectively determined as the current atomic index.

5. The data demand analysis method based on the indicator system according to claim 3 is characterized in that: If there is no preset atomic indicator matching the current atomic indicator in the preset atomic indicator library, generating the current derived indicator according to the statistical period information and the current atomic indicator, including: The statistical period information and the current atomic indicator are aggregated to generate the current derived indicator.

6. The data demand analysis method based on the indicator system according to claim 3 is characterized in that: The preset indicator is the current atomic indicator, the preset indicator library is the preset atomic indicator library, the current indicator is matched with each preset indicator in the preset indicator library to generate a matching result, and a data demand analysis strategy for the preset business demand is generated based on the matching result, including: Matching each of the current atomic indicators with each of the preset atomic indicators in the preset atomic indicator library; If the preset atomic indicator library contains the preset atomic indicator that matches the current atomic indicator, the data demand analysis strategy is generated according to the current atomic indicator.

7. The data demand analysis method based on the indicator system according to claim 3 is characterized in that: The initial key information also includes dimension information, the preset indicator is the current derived indicator, the preset indicator library includes the preset business indicator library and the preset derived indicator library, matching the current indicator with each preset indicator in the preset indicator library to generate a matching result, and generating a data demand analysis strategy for the preset business demand based on the matching result, including: Matching the current derivative indicator with each preset derivative indicator in the preset derivative indicator library; If the preset derivative indicator library contains the preset derivative indicator that matches the current derivative indicator, generating the data demand analysis strategy according to the current derivative indicator; If the preset derivative indicator library does not contain the preset derivative indicator that matches the current derivative indicator, then decomposing each preset business indicator in the preset business indicator library according to the dimension information to generate a decomposed derivative indicator; The data demand analysis strategy is generated based on the disassembly-derived indicators.

8. A data demand analysis device based on an indicator system, characterized in that: include: The business information extraction module is used to extract the initial business indicators and initial key information of the preset business requirements through the preset large model; A current indicator generating module, configured to decompose the initial business indicator according to the initial key information to generate at least one current indicator; The data demand analysis strategy generation module is used to match the current indicator with each preset indicator in the preset indicator library, generate a matching result, and generate a data demand analysis strategy for the preset business demand based on the matching result.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the data requirement analysis method based on the indicator system according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the data demand analysis method based on the indicator system according to any one of claims 1 to 7.

Images