Enterprise data intelligent insight method, system and device, storage medium and product

Abstract

The invention discloses an enterprise data intelligent insight method, system and device, a storage medium and a product, and the method comprises the steps: obtaining enterprise report data from an enterprise report system, carrying out the cleaning, processing, conversion and integration, forming a report data set meeting the attribution analysis requirements, and carrying out the attribution analysis according to the input report data, data dimensions and attribution targets. Analyzing indexes, attribution dimensions and / or attribution formulas, selecting an adaptive attribution algorithm, carrying out attribution calculation in combination with a report data set, executing ad hoc processing on report data according to instant inquiry requirements of a user, forming an attribution calculation analysis result, presenting the result in a visual form, obtaining structured data and carrying out secondary analysis; and outputting an analysis result and a text insight for report data, performing semantic analysis and interpretation on the oral question of the user by using a large model, and converting the oral question into an analysis index and an attribution dimension. By adopting the technical scheme of the invention, enterprise report data analysis can be efficiently and accurately realized.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, system, device, storage medium, and product for intelligent enterprise data insight. Background Technology

[0002] As businesses expand and their operations become more complex, the volume of reported data increases dramatically, and the information reflected in these reports—such as operational status and business performance—becomes increasingly intricate. Currently, businesses primarily rely on manual analysis or simple data statistics tools for report data analysis, which has several shortcomings in attribution analysis: First, attribution analysis is inefficient; manual analysis requires significant time to process data and investigate causes, failing to meet businesses' needs for real-time data analysis. Second, attribution results are inaccurate; traditional analysis methods struggle to comprehensively consider the multi-dimensional factors influencing data changes, easily leading to attribution bias and resulting in analysis results that fail to accurately reflect the core causes of data changes. Third, there is a lack of systematic attribution algorithm support; existing tools often employ single analysis methods, unable to flexibly select appropriate attribution algorithms based on different types of report data and different business scenarios, making it difficult to address the complex needs of business report data insight analysis.

[0003] These problems prevent companies from grasping the root causes of changes in report data and business operations in a timely and accurate manner, affecting the scientific and timely nature of management decisions and hindering corporate development. Therefore, an intelligent insight solution capable of efficiently and accurately analyzing corporate report data is needed. Summary of the Invention

[0004] In view of the above, the present disclosure provides a method, system, device, storage medium and product for enterprise data intelligent insight, which can solve the problems existing in the prior art.

[0005] In a first aspect, embodiments of this disclosure provide a method for enterprise data intelligence insight, comprising the following steps:

[0006] Retrieve enterprise report data from the enterprise reporting system;

[0007] The collected enterprise report data is cleaned, processed, transformed, and integrated to form a report dataset that meets the requirements of attribution analysis;

[0008] Using a large model, semantic analysis and interpretation of users’ conversational questions are performed, and the customer’s conversational questions are transformed into analytical indicators and attribution dimensions.

[0009] Based on the input report data, data dimensions, attribution objectives, and analysis indicators, attribution dimensions, and / or attribution formulas, select an appropriate attribution algorithm, wherein the attribution algorithm includes at least one of the absolute contribution method and the chain substitution method.

[0010] Attribution calculations are performed based on the attribution algorithm and the report dataset.

[0011] Based on the user's immediate inquiry, the report data is processed ad hocly to generate attribution calculation and analysis results, which are then presented in a visual format.

[0012] Structured data is obtained from the attribution calculation and analysis results for secondary analysis, and analysis results and textual insights are output from the report data.

[0013] Furthermore, the enterprise report data includes report data collected through at least one of the following methods: importing from Excel files, manual entry, importing heterogeneous data from external systems, and reading from heterogeneous databases; the enterprise report data includes at least one of the following: financial profit report data, sales performance report data, and cost and expense report data.

[0014] Data cleaning further includes removing missing values ​​and outliers;

[0015] Data processing further includes generating detailed data through calculations using Excel formulas or proprietary rules in enterprise reports;

[0016] Data conversion further includes converting data in different formats and units into standard formats and units;

[0017] Data integration further includes linking and integrating scattered report data based on business logic to form a report dataset that meets the requirements of attribution analysis.

[0018] When based on attribution dimensions, the attribution algorithm employs the absolute contribution method, supporting data aggregation for different dimensions of a single indicator according to the dimension configuration relationship.

[0019] When based on the attribution formula, the attribution algorithm employs the chain substitution method, calculating according to the formula settings between indicators:

[0020] addition:

[0021] Formula characteristics: Y=A+B, Y0=A0+B0+C0, YA=A1+B0+C0, YB=A1+B1+C0, Y1=A1+B1+C1;

[0022] Factor contribution formulas: △YA=YA-Y0, △YB=YB-YA, △YC=Y1-YB;

[0023] Subtraction:

[0024] Formula characteristics: Y=AB, Y0=A0-B0, YA=A1-B0, Y1=A1-B1;

[0025] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA

[0026] multiplication:

[0027] Formula characteristics: Y=A*B, Y0=A0*B0, YA=A1*B0, Y1=A1*B1;

[0028] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA;

[0029] Division: numerator first, then denominator.

[0030] Formula characteristics: Y=A / B, Y0=A0 / B0, YA=A1 / B0, Y1=A1 / B1;

[0031] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA;

[0032] When mixing, calculate the numerator first, then the denominator:

[0033] Formula characteristics: Y=(AB) / A, Y0=(A0-B0) / A0, YA=(A1-B0) / A1, Y1=(A1-B1) / A1;

[0034] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA,

[0035] Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the change result values, and △YA and △YB represent the change process values.

[0036] Performing ad-hoc processing on the report data further includes at least one of the following: pre-setting the viewing method of the ad-hoc data, including zero value display control, sorting requirements, group subtotals and / or data ranges; setting temporary calculation members to calculate complex data from existing data, including setting month-on-month, year-on-year and / or average figures.

[0037] Secondly, this disclosure also provides an enterprise data intelligence insight system, including a data acquisition module, a data preprocessing module, an attribution algorithm module, an attribution calculation module, an ad hoc analysis module, a result visualization module, and an intelligent analysis module, wherein...

[0038] The data acquisition module is used to obtain enterprise report data from the enterprise reporting system;

[0039] The data preprocessing module is used to clean, process, transform, and integrate the collected enterprise report data to form a report dataset that meets the requirements of attribution analysis.

[0040] The attribution algorithm module is used to select an appropriate attribution algorithm based on the input report data, data dimensions, attribution objectives, as well as analysis indicators, attribution dimensions and / or attribution formulas. The attribution algorithm includes at least one of the absolute contribution method and the chain substitution method.

[0041] The attribution calculation module is used to perform attribution calculations based on the attribution algorithm and the report dataset;

[0042] The ad-hoc analysis module is used to perform ad-hoc processing on the report data based on the user's immediate inquiry requirements, and generate attribution calculation and analysis results;

[0043] The results visualization module is used to present the attribution calculation and analysis results in a visual form;

[0044] The intelligent analysis module is used to perform semantic analysis and interpretation of users' conversational questions using a large model, transforming the customer's conversational questions into analytical indicators and attribution dimensions; it is also used to obtain structured data from the attribution calculation and analysis results for secondary analysis, and output analysis results and textual insights to the report data.

[0045] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0046] At least one processor; and,

[0047] A memory communicatively connected to the at least one processor; wherein,

[0048] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the enterprise data intelligence insight method as described in the first aspect or any implementation thereof.

[0049] Fourthly, embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions that, when executed by at least one processor, cause the at least one processor to perform the enterprise data intelligence insight method in the first aspect or any implementation thereof.

[0050] Fifthly, embodiments of this disclosure also provide a computer program product, the computer program product including computer program instructions, which, when executed by a processor, implement the steps of the enterprise data intelligent insight method in the first aspect or any implementation thereof.

[0051] The enterprise data intelligent insight method in this embodiment of the disclosure has the following technical effects:

[0052] Improve attribution analysis efficiency: By automating the enterprise data collection, preprocessing, and attribution calculation process, the traditional manual analysis method is replaced, reducing the time for enterprise report data attribution analysis from hours or even days to minutes or seconds, meeting the enterprise's need for real-time data analysis and supporting management's rapid decision-making.

[0053] Improve the accuracy of attribution results: Adopt a multi-attribution algorithm fusion application mechanism. Based on the configuration and algorithm selection function, the optimal algorithm or algorithm combination can be adapted according to different data types and business scenarios, effectively avoiding the limitations of a single algorithm, reducing attribution bias, and improving the matching degree between attribution results and the actual causes of data changes by more than 30%.

[0054] Enhance the interpretability of attribution results: Through the results visualization module, the attribution process and results are displayed in a variety of chart formats. Combined with the data drill-down function, users can clearly understand the way and extent of the influence of each factor on data changes, solving the problem of the obscure and difficult-to-understand results of traditional attribution analysis and improving the practical value of the analysis results.

[0055] It has strong adaptability to various scenarios: it supports attribution analysis of various types of enterprise report data, and can flexibly adjust the algorithm and analysis process according to user-defined attribution goals. It is suitable for the data analysis needs of enterprises of different industries and sizes, and has a wide range of applications. Attached Figure Description

[0056] The above is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Figure 1 A flowchart for enterprise data intelligent insight provided in Embodiment 1 of this disclosure; and

[0058] Figure 2 This is a schematic diagram of the structure of an enterprise data intelligent insight system provided in an embodiment of this disclosure. Detailed Implementation

[0059] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0060] The following specific examples illustrate the implementation of this disclosure. Those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0061] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0062] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The drawings only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0063] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0064] Currently, enterprises have many shortcomings in their report data analysis:

[0065] First, there are limitations to manual analysis. When processing monthly financial statements of large enterprises, manual analysis may take several days or even weeks to complete the initial attribution analysis, which is extremely inefficient when faced with massive amounts of data.

[0066] Secondly, it fails to adequately consider multi-dimensional factors. Traditional attribution analysis methods often only consider a limited number of factors, making it difficult to comprehensively cover the multi-dimensional factors that influence data changes.

[0067] Thirdly, there is the limitation of a single algorithm. Most existing tools use a single analysis method and cannot flexibly select an appropriate attribution algorithm based on different types of report data and different business scenarios.

[0068] Fourthly, large-scale model analysis suffers from a lack of focus. The data analysis capabilities of large-scale models tend to be general and differ significantly from the actual data of different industries and companies, making it impossible to conduct targeted and accurate analysis based on business needs.

[0069] Fifth, there is a lack of visualization. Effective visualization methods are lacking in presenting attribution results. The attribution process and results cannot be displayed using intuitive charts and graphs.

[0070] The technical solution of this invention is an enterprise data intelligent insight solution based on multi-algorithm fusion. It is specifically applied to scenarios such as enterprise financial data analysis, business decision-making data support, business performance evaluation data analysis, and marketing effectiveness data analysis. It is especially suitable for scenarios that require rapid and accurate attribution analysis of abnormal fluctuations in enterprise report data and changes in business indicators. The data processing and analysis results serve as the basis for intelligent analysis of large models, providing data support for enterprise management to formulate business strategies and optimize business processes.

[0071] Figure 1 This is a flowchart illustrating the enterprise data intelligent insight process provided in Embodiment 1 of this disclosure. Figure 1 As shown, the enterprise's data intelligence insight process includes the following steps:

[0072] Step 101: Obtain enterprise report data from the enterprise reporting system. Enterprise report data can be directly collected through an interface, including importing from Excel files (Excel data collection), manual entry (manual report compilation), importing heterogeneous data from external systems, and reading from heterogeneous databases (heterogeneous database integration). This ensures that the obtained enterprise report data is accurate, real-time, and complete.

[0073] Enterprise financial statement data includes financial profit statement data, sales performance statement data, and / or cost and expense statement data.

[0074] Step 102: Clean, process, transform, and integrate the collected enterprise report data to form a report dataset that meets the requirements of attribution analysis, providing a high-quality data foundation for subsequent attribution calculations.

[0075] Data cleaning further includes removing missing and outlier values; data processing further includes generating refined data through Excel formulas or enterprise report-specific rules; data transformation further includes converting data of different formats and units into standard formats and units; and data integration further includes linking and integrating scattered report data based on business logic to form a report dataset that meets the requirements of attribution analysis.

[0076] Step 103: Use a large model to perform semantic analysis and interpretation of customer questions, transforming the customer's colloquial questions into analytical indicators, attribution dimensions, etc.

[0077] Step 104: Based on the input report data, data dimensions (such as organization, period, customer, product line), user-defined attribution objectives (such as finding the reasons for abnormal data fluctuations, analyzing the reasons for revenue increase / decrease), and user-defined analysis indicators, attribution dimensions, and / or attribution formulas, select an appropriate attribution algorithm to calculate attribution data (difference value, difference rate, contribution value, contribution rate, etc.), where the attribution algorithm includes absolute contribution method and chain substitution method.

[0078] Step 105: Match the attribution algorithm according to the attribution scenario to determine whether it is dimensional attribution. If it is, proceed to step 106; otherwise, it is factor attribution and proceed to step 107.

[0079] Step 106: Use the absolute contribution method in combination with the report dataset to perform attribution calculation. The absolute contribution method is based on dimensional attribution and supports data aggregation for different dimensions of a single indicator according to the dimensional configuration relationship. Proceed to step 108.

[0080] Step 107: Attribution calculation is performed using the chain substitution method combined with the report dataset. The chain substitution method calculates according to the formula settings between indicators. The specific algorithm logic is as follows:

[0081] addition:

[0082] Formula characteristics: Y=A+B, Y0=A0+B0+C0, YA=A1+B0+C0, YB=A1+B1+C0, Y1=A1+B1+C1;

[0083] Factor contribution formulas: △YA=YA-Y0, △YB=YB-YA, △YC=Y1-YB;

[0084]

[0085] Where Y is the target indicator, and A, B, and C are all contributing indicators to Y. For example: Total expenses = financial expenses + administrative expenses + sales expenses. Y0, A0, B0, and C0 represent the base values, and YA, YB, Y1, A1, B1, and C1 represent the resulting values. For example: Total expenses increased from Y0:60 to Y1:70. YA represents the resulting value after the change in financial expenses, YB represents the resulting value after the change in financial expenses + administrative expenses, Y1 represents the final result value, and △YA and △YB represent the values ​​during the change process.

[0086] Subtraction:

[0087] Formula characteristics: Y=AB, Y0=A0-B0, YA=A1-B0, Y1=A1-B1;

[0088] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA

[0089]

[0090] Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the result values ​​of the change, and △YA and △YB represent the process values ​​of the change.

[0091] multiplication:

[0092] Formula characteristics: Y=A*B, Y0=A0*B0, YA=A1*B0, Y1=A1*B1;

[0093] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA;

[0094]

[0095] Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the result values ​​of the change, and △YA and △YB represent the process values ​​of the change.

[0096] Division: numerator first, then denominator.

[0097] Formula characteristics: Y=A / B, Y0=A0 / B0, YA=A1 / B0, Y1=A1 / B1;

[0098] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA;

[0099]

[0100] Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the change result values, and △YA and △YB represent the change process values.

[0101] When mixing, calculate the numerator first, then the denominator:

[0102] Formula characteristics: Y=(AB) / A, Y0=(A0-B0) / A0, YA=(A1-B0) / A1, Y1=(A1-B1) / A1;

[0103] Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA,

[0104]

[0105] Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the change result values, and △YA and △YB represent the change process values.

[0106] Step 108: Based on the user's immediate inquiry, perform ad-hoc processing on the report data to generate attribution calculation and analysis results, and then proceed to step 109 or step 110.

[0107] You can pre-set the viewing format of ad-hoc data, such as displaying 0 values, sorting requirements, grouping subtotals, data ranges, etc. You can also set temporary calculation members to calculate more complex data from existing data (such as setting calculation members for month-on-month, year-on-year, average, etc.). Finally, the results of ad-hoc analysis are returned to the large model for display and secondary analysis.

[0108] Step 109: Present the attribution analysis results in a visual format. Supports various chart types, including data tables (directly displaying data), bar charts (showing the contribution of each factor), and line charts (showing the correlation trend between factor changes and target variable changes). It also provides drill-down functionality for data cards, allowing users to click on data nodes in the charts to view the underlying raw data and calculation process, enhancing the readability and interpretability of the attribution results.

[0109] Step 110: Obtain structured data from the attribution calculation analysis results for secondary analysis, and output analysis results and textual insights for the report data.

[0110] To implement the above process, the embodiment also provides an enterprise data intelligence insight system.

[0111] Figure 2 This is a schematic diagram of the enterprise data intelligent insight system structure provided in an embodiment of this disclosure. Figure 2As shown, the system includes a data acquisition module 21, a data preprocessing module 22, an attribution algorithm module 23, an attribution calculation module 24, an ad hoc analysis module 25, a results visualization module 26, and an intelligent analysis module 27. Among them,

[0112] The data acquisition module obtains enterprise report data from the enterprise reporting system. It directly connects to the enterprise report data via an interface, and the data can be collected through various methods such as Excel acquisition, manual report compilation, importing heterogeneous data from external systems, and integration with heterogeneous databases, ensuring that the acquired enterprise report data is accurate, real-time, and complete.

[0113] The data preprocessing module cleans, processes, transforms, and integrates the collected enterprise report data to form a report dataset that meets the requirements of attribution analysis. The collected report data undergoes cleaning, transformation, and integration processing.

[0114] The data preprocessing module further includes a data cleaning unit 221, a data processing unit 222, and a data conversion and integration unit 223.

[0115] The data cleaning unit removes missing and outlier values ​​from the data; the data processing unit can calculate more refined data using Excel formulas and enterprise-specific report rules. The data transformation and integration unit converts data of different formats and units into a standardized format and unit, and integrates scattered report data according to business logic to form a dataset that meets the requirements of attribution analysis, providing a high-quality data foundation for subsequent attribution calculations.

[0116] The attribution algorithm module selects an appropriate attribution algorithm based on the input report data, data dimensions, attribution objectives, and analytical indicators, attribution dimensions, and / or attribution formulas. The attribution algorithm includes at least one of the absolute contribution method and the chain substitution method. The module has a built-in algorithm model that calculates attribution data (such as financial profit report data, sales performance report data, cost and expense report data), data dimensions (such as organization, period, customer, product line), and user-defined attribution objectives (such as finding the causes of abnormal data fluctuations, analyzing the reasons for revenue increases / decreases) using an appropriate aggregation algorithm based on the user-defined attribution dimensions and attribution formulas. This calculation includes attribution data (difference value, difference rate, contribution value, contribution rate, etc.).

[0117] The attribution calculation module performs attribution calculations based on attribution algorithms and the report dataset. The attribution algorithms used are the absolute contribution method and the chain substitution method. The absolute contribution method is based on dimensional attribution and supports data aggregation for different dimensions of a single indicator according to the dimensional configuration relationship; the chain substitution method calculates according to the formula settings between indicators.

[0118] The ad-hoc analysis module performs ad-hoc processing on report data based on users' immediate inquiries, generating attribution analysis results. This module can present collected report data according to customers' immediate questions and requirements. The viewing format of ad-hoc data can be pre-set, such as displaying zero values, sorting requirements, grouping subtotals, and data ranges. Temporary calculation members can also be set to derive more complex data from existing data (such as setting calculation members for month-on-month, year-on-year, and average figures). Finally, the ad-hoc analysis results are returned to the larger model for display and secondary analysis.

[0119] The results visualization module presents the attribution analysis results in a visual format. It supports various chart types, including data tables (directly displaying data), bar charts (showing the contribution of each factor), and line charts (showing the correlation between changes in factors and the target variable). It also provides drill-down functionality for data cards, allowing users to click on data nodes in the charts to view the underlying raw data and calculation process, enhancing the readability and interpretability of the attribution results.

[0120] The intelligent analysis module uses a large model to perform semantic analysis and interpretation of users' conversational questions, transforming them into analytical indicators and attribution dimensions. It also obtains structured data from the attribution calculation and analysis results for secondary analysis, and outputs analysis results and textual insights to the report data.

[0121] This disclosure also provides an electronic device, which includes:

[0122] At least one processor; and,

[0123] The memory is communicatively connected to the at least one processor; wherein,

[0124] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the enterprise data intelligence insight method in the foregoing method embodiments.

[0125] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the enterprise data intelligent insight method described in the foregoing method embodiments.

[0126] This disclosure also provides a computer program product, which includes computer program instructions that, when executed by a processor, implement the steps of the enterprise data intelligent insight method in the first aspect or any implementation thereof.

[0127] The above-mentioned technical solution of the present invention, through automated data collection, preprocessing, and attribution calculation, reduces the enterprise report analysis time from several hours / days to minutes / seconds, supporting real-time decision-making; it adopts a multi-algorithm fusion mechanism to adapt the optimal combination according to the business scenario, improving the accuracy of the results by more than 30%; it enhances the interpretability of the results with the help of visual charts and data drill-down functions, making the influencing factors easy to understand; at the same time, it supports multiple report types and custom adjustments to meet the needs of enterprises of different industries and sizes.

[0128] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0129] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0130] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire at least two Internet Protocol (IP) addresses; send a node evaluation request including the at least two IP addresses to a node evaluation device, wherein the node evaluation device selects an IP address from the at least two IP addresses and returns it; and receive the IP address returned by the node evaluation device; wherein the acquired IP address indicates an edge node in a content delivery network.

[0131] Alternatively, the aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet Protocol (IP) addresses; select an IP address from the at least two IP addresses; and return the selected IP address; wherein the received IP address indicates an edge node in the content delivery network.

[0132] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0135] It should be understood that the various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof.

[0136] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for intelligent enterprise data insights, characterized in that, Includes the following steps: Obtain enterprise report data from the enterprise reporting system; The collected enterprise report data is cleaned, processed, transformed, and integrated to form a report dataset that meets the requirements of attribution analysis; Using a large model, semantic analysis and interpretation of users’ conversational questions are performed, and the customer’s conversational questions are transformed into analytical indicators and attribution dimensions. Based on the input report data, data dimensions, attribution objectives, and analysis indicators, attribution dimensions, and / or attribution formulas, select an appropriate attribution algorithm, which includes at least one of the absolute contribution method and the chain substitution method. Attribution calculations are performed based on the attribution algorithm and the report dataset. Based on the user's immediate inquiry, the report data is processed ad hocly to generate attribution calculation and analysis results, which are then presented in a visual format. Structured data is obtained from the attribution calculation and analysis results for secondary analysis, and analysis results and textual insights are output from the report data.

2. The enterprise data intelligent insight method according to claim 1, characterized in that, The enterprise report data includes report data collected through at least one of the following methods: importing from Excel files, manual entry, importing heterogeneous data from external systems, and reading from heterogeneous databases; the enterprise report data includes at least one of the following: financial profit report data, sales performance report data, and cost and expense report data.

3. The enterprise data intelligent insight method according to claim 1, characterized in that, Data cleaning further includes removing missing values ​​and outliers; Data processing further includes generating detailed data through calculations using Excel formulas or proprietary rules in enterprise reports; Data conversion further includes converting data in different formats and units into standard formats and units; Data integration further includes linking and integrating scattered report data based on business logic to form a report dataset that meets the requirements of attribution analysis.

4. The enterprise data intelligent insight method according to claim 1, characterized in that, When based on attribution dimensions, the attribution algorithm employs the absolute contribution method, supporting data aggregation for different dimensions of a single indicator according to the dimension configuration relationship.

5. The enterprise data intelligent insight method according to claim 1, characterized in that, When based on the attribution formula, the attribution algorithm employs the chain substitution method, calculating according to the formula settings between indicators: addition: Formula characteristics: Y=A+B, Y0=A0+B0+C0, YA=A1+B0+C0, YB=A1+B1+C0, Y1=A1+B1+C1; Factor contribution formulas: △YA=YA-Y0, △YB=YB-YA, △YC=Y1-YB; Subtraction: Formula characteristics: Y=AB, Y0=A0-B0, YA=A1-B0, Y1=A1-B1; Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA multiplication: Formula characteristics: Y=A*B, Y0=A0*B0, YA=A1*B0, Y1=A1*B1; Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA; Division: numerator first, then denominator. Formula characteristics: Y=A / B, Y0=A0 / B0, YA=A1 / B0, Y1=A1 / B1; Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA; When mixing, calculate the numerator first, then the denominator: Formula characteristics: Y=(AB) / A, Y0=(A0-B0) / A0, YA=(A1-B0) / A1, Y1=(A1-B1) / A1; Factor contribution formulas: △YA=YA-Y0, △YB=Y1-YA, Where Y is the target indicator, A, B and C are all contribution indicators of Y, Y0, A0, B0 and C0 represent the base values, YA, YB, Y1, A1, B1 and C1 represent the change result values, and △YA and △YB represent the change process values.

6. The enterprise data intelligent insight method according to claim 1, characterized in that, Performing ad-hoc processing on the report data further includes at least one of the following: pre-setting the viewing method of the ad-hoc data, including zero value display control, sorting requirements, group subtotals and / or data ranges; setting temporary calculation members to calculate complex data from existing data, including setting month-on-month, year-on-year and / or average figures.

7. An enterprise data intelligence insight system, characterized in that, It includes a data acquisition module, a data preprocessing module, an attribution algorithm module, an attribution calculation module, an ad hoc analysis module, a results visualization module, and an intelligent analysis module. The data acquisition module is used to obtain enterprise report data from the enterprise reporting system; The data preprocessing module is used to clean, process, transform, and integrate the collected enterprise report data to form a report dataset that meets the requirements of attribution analysis. The attribution algorithm module is used to select an appropriate attribution algorithm based on the input report data, data dimensions, attribution objectives, as well as analysis indicators, attribution dimensions and / or attribution formulas. The attribution algorithm includes at least one of the absolute contribution method and the chain substitution method. The attribution calculation module is used to perform attribution calculations based on the attribution algorithm and the report dataset; The ad-hoc analysis module is used to perform ad-hoc processing on the report data based on the user's immediate inquiry requirements, and generate attribution calculation and analysis results; The results visualization module is used to present the attribution calculation and analysis results in a visual form; The intelligent analysis module is used to perform semantic analysis and interpretation of users' conversational questions using a large model, transforming the customer's conversational questions into analytical indicators and attribution dimensions; it is also used to obtain structured data from the attribution calculation and analysis results for secondary analysis, and output analysis results and textual insights to the report data.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, cause the at least one processor to perform the enterprise data intelligence insight method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that, when executed by at least one processor, cause the at least one processor to perform the enterprise data intelligence insight method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes computer program instructions that, when executed by a processor, implement the steps of enterprise data intelligence insights as described in any one of claims 1 to 6.

Images