Business financial data analysis method and system, electronic equipment and storage medium
By constructing a business-finance relationship network and a dynamic mapping model, the problem of weak expression of business-finance relationship and lack of causal analysis in traditional data analysis is solved, enabling accurate analysis of enterprise operation status and risk warning.
Patent Information
- Application Number
- CN202511192198.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-25
- Publication Date
- 2026-01-13
AI Technical Summary
Traditional methods of processing business and financial data are insufficient to meet the needs of modern enterprise management, especially in expressing the complex network relationships between business and finance and in conducting causal analysis, which leads to biases when quantifying the impact.
By constructing a business-finance relationship network through data mining algorithms, quantifying the impact of business on finance using causal inference algorithms, and building a dynamic business-finance mapping model, we can achieve in-depth analysis and trend prediction of business and financial data.
It improves the depth and accuracy of enterprise financial data analysis, enhances operational effectiveness, and provides scientific decision support for enterprise operations and maintenance.
Smart Images
Figure CN121329700A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of operations management technology, and in particular to a business and financial data analysis method, system, electronic device, and storage medium. Background Technology
[0002] It should be noted that the above description of the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of the present invention and facilitating understanding by those skilled in the art. It should not be assumed that the above technical solutions are known to those skilled in the art simply because they have been described in the background section of this invention.
[0003] As businesses expand and market competition intensifies, traditional business and financial data processing methods are no longer sufficient to meet the needs of modern enterprise management, and new solutions are urgently needed to improve operational efficiency and decision support capabilities.
[0004] In enterprise operations management, business systems and financial systems are interconnected but often operate independently. The basic applications of traditional data analysis techniques include: presenting data visuals through simple statistics and generating standardized reports through preset rules.
[0005] However, the relevant technologies have significant limitations: First, they are weak in expressing the relationship between business and finance, relying on traditional databases or tables to store data, making it difficult to present the complex network relationship between business and finance; second, they lack causal analysis, only able to identify the "correlation between business and financial indicators" but unable to distinguish the "causal relationship", leading to biases when quantifying the impact. Summary of the Invention
[0006] In view of the above, the purpose of one or more embodiments of this disclosure is to provide a business data analysis method, system, electronic device and storage medium to solve the problem.
[0007] To achieve the above objectives, one or more embodiments of this disclosure provide a business and financial data analysis method, characterized in that it includes:
[0008] Obtain business and financial data;
[0009] Based on the business data and the financial data, a business-finance relationship network is constructed using data mining algorithms. This network reflects the relationships between business operations and between business operations and finance.
[0010] Based on the financial data, the business data, and the business-finance relationship network, the impact of business on finance is quantified using a causal inference algorithm, and a dynamic business-finance mapping model is constructed.
[0011] Based on the business dynamic mapping model, data analysis is performed on the business data and the financial data, and the data analysis results are displayed.
[0012] Optionally, based on the business data and the financial data, a business-finance relationship network is constructed using data mining algorithms, including:
[0013] Based on the financial data, the financial indicator values of the preset financial indicators are obtained;
[0014] Based on the business data and the financial indicator values, data mining algorithms are used to obtain the correlations between the business operations and between the business operations and the financial indicators.
[0015] The business and financial indicators are used as nodes, and the relationships between the businesses and between the businesses and the financial indicators are used as edges to construct the business-finance relationship network.
[0016] Optionally, based on the financial data, the business data, and the business-finance relationship network, a dynamic business-finance mapping model is constructed by quantifying the impact of business on finance using a causal relationship algorithm, including:
[0017] Based on the financial indicator values and the business data, the impact values between the financial indicators and / or between the financial indicators and the business data are quantified using a causal inference algorithm.
[0018] Based on the influence value and the business-finance relationship network, the dynamic mapping model is constructed.
[0019] Optionally, based on the financial data, the business data, and the business-finance relationship network, a dynamic business-finance mapping model is constructed by quantifying the impact of business on finance using a causal relationship algorithm, including:
[0020] At least one data node, based on its own financial indicator values and business data, uses a causal inference algorithm to quantify the local impact values between financial indicators and / or between financial indicators and business operations.
[0021] Based on the local influence values and the business-finance relationship network, train a sub-model of the dynamic mapping model;
[0022] The parameters of the sub-models are uploaded to the federated learning server, so that the federated learning server can aggregate the parameters of all the sub-models to obtain the dynamic mapping model.
[0023] Optionally, based on the business dynamic mapping model, data analysis is performed on the business data and the financial data, including:
[0024] The business data, the financial data, and the business dynamic mapping model are input into a long short-term memory neural network to obtain a predicted development trend. The predicted development trend includes the first predicted value of the financial indicators and business data, as well as the confidence interval of the first predicted value.
[0025] Optionally, data analysis of the business data and the financial data based on the business dynamic mapping model further includes:
[0026] Receive the data adjustment instruction for the aforementioned service;
[0027] Based on the adjustment data of the business and the dynamic mapping model of the business, a second predicted value of the financial indicator data is obtained;
[0028] A decision simulation report is generated based on the second predicted value.
[0029] Optionally, it also includes:
[0030] Obtain the preset risk threshold of the financial indicators;
[0031] The early warning mechanism is triggered when the first predicted value of the financial indicator exceeds the risk threshold.
[0032] Based on the same inventive concept, one or more embodiments of this disclosure also provide a business data analysis device, including:
[0033] The data acquisition layer is configured to acquire business data and financial data.
[0034] The first computing layer is configured to construct a business-finance relationship network based on the business data and the financial data using data mining algorithms. The business-finance relationship network reflects the relationships between businesses and between businesses and finance.
[0035] The second computing layer is configured to quantify the impact of business on finance using a causal inference algorithm based on the financial data, the business data, and the business-finance relationship network, and to construct a dynamic business-finance mapping model.
[0036] The data analysis layer is configured to perform data analysis on the business data and the financial data according to the business dynamic mapping model, and display the data analysis results.
[0037] Based on the same inventive concept, one or more embodiments of this disclosure also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the business data analysis method as described in any of the foregoing.
[0038] Based on the same inventive concept, one or more embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute any of the above-described business data analysis methods.
[0039] As can be seen from the above, the business and financial data analysis method provided in one or more embodiments of this disclosure constructs a business-finance relationship network through data mining algorithms to sort out the relationships between businesses and between businesses and finance; then, it quantifies the impact of business on finance through causal inference algorithms and constructs a dynamic mapping model of business and finance to achieve in-depth analysis of the causal relationships between data and accurately capture the dynamic impact of business actions on financial indicators; finally, it performs data analysis on business data and financial data based on the dynamic mapping model and displays the results to achieve trend prediction and risk warning of enterprise operation status.
[0040] The technical solution disclosed herein can effectively improve the depth of analysis of enterprise financial data, enhance enterprise operational efficiency, and provide strong technical support for scientific decision-making in enterprise operation and maintenance.
[0041] The business and financial data analysis device, electronic device, and computer-readable storage medium provided in this disclosure can all implement the steps of the above-described business and financial data analysis method, and therefore also have the beneficial effects of the above-described business and financial data analysis method. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in one or more embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only one or more embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 This is a flowchart illustrating one or more embodiments of the business data analysis method disclosed herein;
[0044] Figure 2 This is a schematic diagram of the structure of a business data analysis system according to one or more embodiments of the present disclosure;
[0045] Figure 3 This is a schematic diagram of the hardware structure of an electronic device according to one or more embodiments of this disclosure. Detailed Implementation
[0046] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.
[0047] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar words used in one or more embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0048] refer to Figure 1 The present disclosure discloses a business data analysis method according to one or more embodiments, including the following steps:
[0049] Step S101: Obtain business data and financial data;
[0050] Step S102: Based on the above business data and financial data, construct a business-finance relationship network using data mining algorithms. This business-finance relationship network reflects the relationships between businesses and between businesses and finance.
[0051] Step S103: Based on the above financial data, business data, and business-finance relationship network, quantify the impact of business on finance using a causal inference algorithm and construct a dynamic business-finance mapping model;
[0052] Step S104: Based on the above business dynamic mapping model, perform data analysis on the above business data and the above financial data, and display the data analysis results.
[0053] The financial data disclosed herein represent various types of data generated by an enterprise in the course of its business operations and related to the movement of funds and financial activities.
[0054] In some implementations, the aforementioned financial data may include structured data that directly reflects the financial status, operating results, and cash flow, such as invoice data, cost details, and financial statements; or unstructured data that indirectly supports financial analysis and decision-making, such as financial documents and fund transfer log files. These data together constitute the record and reflection of the company's financial activities and are the core information carriers that embody the financial dimension characteristics in business and financial data analysis.
[0055] In some implementations, financial data primarily comes from the financial system.
[0056] The business data disclosed herein refers to data generated by the enterprise during the course of various specific business operations, reflecting the status and process of business execution.
[0057] In some implementations, business data can include information directly related to business activities, including multiple dimensions such as enterprise business processes, operational actions, and business results, such as material procurement volume, project progress, and sales orders.
[0058] In some implementations, business data mainly comes from various business systems such as material business control and project lifecycle management.
[0059] In some implementations, a pre-built industry health indicator library can be used to automatically benchmark enterprise data and mark deviations.
[0060] In some implementations, business data and financial data can be collected in real time through data acquisition modules set up in the business system and financial system.
[0061] In some embodiments, a RESTful API or message queue (such as Kafka) is used as the data interface standard to extract data from business and financial systems, including structured or unstructured data.
[0062] In some embodiments, real-time business and financial data can also be collected through microservices, and the scalability and fault tolerance of the system can be improved by leveraging the microservice architecture.
[0063] In some implementations, after collecting business and financial data, the data can be preprocessed.
[0064] In some implementations, the aforementioned preprocessing includes data cleaning, data transformation, data standardization, and so on. Data cleaning refers to removing noise and duplicate records from the data, using appropriate filling strategies to fill in correct data items, or correcting erroneous data; data transformation refers to converting unstructured data into structured data; and data standardization refers to standardizing or normalizing data of different magnitudes and distributions to make it conform to a unified standard.
[0065] For example, tools such as Apache Spark or Pandas can be used for data cleaning and transformation; machine learning algorithms can be used to identify outliers and fill in missing values through interpolation or mean; or natural language processing techniques can be used to parse unstructured data and then convert it into structured data.
[0066] In the design scheme disclosed herein, a dynamic mapping model of business and finance is constructed to deeply analyze the correlation and influence between business data and financial data, and this correlation and influence can be dynamically updated.
[0067] The process of constructing a dynamic mapping model between business and finance can be divided into two steps: first, mining the correlation between business data and financial data and constructing a business-finance relationship network; second, quantifying the impact of business on finance through causal inference algorithms and constructing a dynamic mapping model between business and finance.
[0068] In some implementations, the process of constructing a business-finance relationship network may include: obtaining the financial indicator values of preset financial indicators based on the aforementioned financial data; obtaining the relationships between the aforementioned businesses and between the aforementioned businesses and the aforementioned financial indicators through data mining algorithms based on the aforementioned business data and the aforementioned financial indicator values; and constructing the aforementioned business-finance relationship network by using the aforementioned businesses and the aforementioned financial indicators as nodes and the relationships between the aforementioned businesses and the aforementioned businesses and the aforementioned financial indicators as edges.
[0069] The aforementioned financial indicators refer to specific values or ratios that quantify a company's financial condition, operating results, cash flow, solvency, operational efficiency, and profitability over a certain period, derived from the processing, calculation, and analysis of financial data (such as financial statements, cost details, and cash flow). By tracking the trends in these financial indicators, companies can improve the timeliness and accuracy of their business decisions.
[0070] In some implementations, the financial indicator values of the above-mentioned financial indicators can be calculated using preset financial indicator calculation formulas.
[0071] In some embodiments, various financial indicators can be automatically calculated using Python's Pandas and NumPy libraries, combined with financial formulas.
[0072] In some embodiments, the aforementioned financial metrics may include net profit, gross profit margin, debt-to-equity ratio, and current ratio.
[0073] The aforementioned data mining algorithm is used to delve into the relationships between business activities and between business activities and financial indicators, helping to understand how business operations affect financial results.
[0074] In some implementations, data mining can be achieved using association rule algorithms such as Apriori and FP-Growth, correlation analysis algorithms such as Pearson correlation coefficient and Spearman rank correlation, decision trees, random forests, or graph neural networks (GNNs).
[0075] In some implementations, the data of the aforementioned business-finance relationship network can be stored in a graph database for easy subsequent querying and analysis. For example, the business-finance relationship network can be stored in a Neo4j database.
[0076] In some implementations, the process of constructing the business-finance dynamic mapping model may include: quantifying the impact values between the aforementioned financial indicators and / or between the aforementioned financial indicators and the aforementioned business data using a causal inference algorithm; and constructing the aforementioned dynamic mapping model based on the aforementioned impact values and the aforementioned business-finance relationship network.
[0077] Causal inference algorithms can specifically employ classical causal inference methods based on statistical models, causal inference methods based on potential outcome frameworks, or causal inference based on machine learning.
[0078] In some embodiments, the Do-Calculus algorithm can be used to quantify the impact of business activities on financial metrics. For example, the Do-Calculus algorithm can be used to quantify the impact of promotional spending on net profit.
[0079] In some embodiments, a causal inference engine can be developed based on the CausalNLP library to perform causal inference calculations on influence relationships.
[0080] In some implementations, a sand table simulation interface can also be set up to support the adjustment of business parameters according to user instructions and generate a forecast report on the adjustment of financial indicators based on those business parameters.
[0081] In some embodiments, the latest forecast report can be displayed in real time by dynamically refreshing the chart using React+D3.js.
[0082] As mentioned above, machine learning techniques may be used in the construction of business-finance relationship networks and dynamic business-finance mapping models. Machine learning models can be used to explore the correlation between business and financial indicators and the impact of business on financial indicators.
[0083] When using machine learning models to uncover the relationships between business and / or financial metrics and the impact of business on financial metrics, the aforementioned machine learning models can be trained using a federated learning framework.
[0084] Federated learning enables enterprises to achieve cross-entity collaborative data modeling without disclosing sensitive business and financial data. This protects privacy and security while improving the comprehensiveness and accuracy of the model's analysis of business and financial relationships.
[0085] In some implementations, the construction of the dynamic mapping model using federated learning may include: at least one data node quantifies the local impact values between the aforementioned financial indicators and / or between the aforementioned financial indicators and the aforementioned business data using a causal inference algorithm; trains a sub-model of the dynamic mapping model based on the aforementioned local impact values and the aforementioned business-finance relationship network; and uploads the parameters of the aforementioned sub-models to a federated learning server so that the federated learning server can aggregate the parameters of all the aforementioned sub-models to obtain the aforementioned dynamic mapping model.
[0086] In this context, the business-finance relationship network used by each data node can be the same network that reflects the relationship between all business and finance, or it can be a partial business-finance relationship network that is only related to the corresponding data node.
[0087] In some implementations, the model parameters of each data node are encrypted before being uploaded to the central server.
[0088] In some implementations, data fingerprints and other evidence related to key training steps can also be stored on the blockchain to ensure that the process is auditable.
[0089] In some embodiments, the Secure Multi-Party Computation (SMPC) method can be used to fuse multi-source model parameters to obtain a trained machine learning model, which can then be used to generate a dynamic mapping model.
[0090] In some embodiments, federated learning can be implemented based on the PySyft framework.
[0091] In some embodiments, Hyperledger Fabric can also be integrated to record training logs.
[0092] For each data node, training the deep learning model can be achieved using either unsupervised learning methods or other methods.
[0093] In some implementations, data analysis is performed on the aforementioned business data and financial data based on the aforementioned business dynamic mapping model, including: inputting the aforementioned business data, financial data, and the aforementioned business dynamic mapping model into a long short-term memory neural network to obtain a predicted development trend, wherein the predicted development trend includes the first predicted value of the financial indicators and business data and the confidence interval of the first predicted value.
[0094] In some implementations, data analysis of the aforementioned business data and financial data based on the aforementioned business dynamic mapping model further includes: receiving data adjustment instructions for the aforementioned business; obtaining a second predicted value for the aforementioned financial indicator data based on the adjusted data of the aforementioned business and the aforementioned business dynamic mapping model; and generating a decision simulation report based on the aforementioned second predicted value.
[0095] In some implementations, when performing data analysis on the business data and the financial data based on the business dynamic mapping model, resource scheduling can be adaptively adjusted according to resource availability.
[0096] For example, before performing data analysis, peak computing demands over a future period can be predicted, and capacity can be automatically increased during peak periods while existing capacity is used during off-peak periods. By allocating GPU resources in advance, response time can be reduced.
[0097] When conducting data analysis, you can also prioritize low-latency tasks such as risk scanning, depending on the actual situation.
[0098] In some embodiments, long short-term memory networks can be used to predict peak computation times in the future, and the proximal policy optimization (PPO) algorithm can be used to dynamically allocate container resources.
[0099] In some implementations, the data analysis results can be displayed as charts such as bar charts, line charts, and pie charts, or as text reports.
[0100] In some implementations, data from different dimensions can be displayed based on user-defined filtering criteria.
[0101] Some implementations also support simulated decision-making operations by users to evaluate the impact of different decision-making options on business and financial indicators.
[0102] For example, you can use front-end frameworks such as React.js or Vue.js to develop user-friendly interfaces, and use Node.js or Flask on the back-end to provide API interfaces to connect the front-end and back-end services. You can use ECharts or D3.js to draw charts and dynamically update them.
[0103] The following description uses a specific embodiment of this disclosure as an example.
[0104] In this embodiment, raw data is first extracted from the business system and financial system through a RESTful API or a Kafka message queue. The extracted data includes structured data such as sales orders and invoices, as well as unstructured data such as log documents.
[0105] The extracted data is preprocessed. Preprocessing operations include data deduplication, data format conversion, and data standardization. Data deduplication includes removing duplicate records (e.g., multiple entries of the same order number), data format conversion includes standardizing date formats and currency units, and data standardization includes normalizing numeric fields.
[0106] The preprocessed data is stored in a distributed data warehouse (such as an HBase cluster) to provide a data foundation for subsequent operations.
[0107] Before constructing the business-finance dynamic mapping model, the financial indicator values are obtained based on the original financial data and the preset financial indicator calculation formula.
[0108] Based on business data and financial indicator values, a business-finance relationship network is constructed. In this network, nodes represent business entities and financial indicators, and edges represent the relationships between businesses or between businesses and financial indicators.
[0109] Based on business data, financial indicators, and the aforementioned business-finance relationship network, the PageRank algorithm is used to identify key business drivers and quantify the impact of business on finance, thus constructing a dynamic business-finance mapping model.
[0110] In situations where privacy and security requirements are high, each data node trains a lightweight model on a private server, then uses the Paillier homomorphic encryption algorithm to encrypt the model parameters, generating an encrypted parameter package containing a weight matrix and a bias vector. This encrypted parameter package is then encrypted and uploaded to the central server using a secure multi-party algorithm to update the global model.
[0111] To ensure the authenticity, integrity, and traceability of key information, this embodiment uses blockchain technology to synchronously store information such as digital fingerprints (SHA-256), parameter update logs, and timestamps during the evidence aggregation process.
[0112] Based on the dynamic mapping model of business and finance, risk prediction or trend prediction can be carried out.
[0113] Risk prediction includes assessing cyclical risks based on ensemble time series models and calculating the probability of sudden risks using logistic regression models.
[0114] Trend forecasting involves using an LSTM neural network to predict data change trends over the next 12 weeks and analyzing the forecast results with confidence intervals between 80% and 95%.
[0115] In addition to risk and trend forecasting, decision-making simulations can also be performed. Specifically, user-defined business parameters can be input into the causal inference engine via a web page slider or API. For example, operational parameters such as inventory levels and promotional efforts, and market parameters such as competitor pricing and raw material price fluctuations can be input into the causal inference engine.
[0116] Based on the aforementioned business parameters and the business-finance dynamic mapping model, the causal inference engine generates a decision simulation report.
[0117] The decision simulation report can include three types: a baseline report, an optimistic report, and a pessimistic report. The baseline report is based on the current parameters provided by the user, the optimistic report is based on the optimized parameters after optimizing the current parameters by 20%, and the pessimistic report is based on the deteriorated parameters after deteriorating the current parameters by 20%.
[0118] The aforementioned risk predictions, trend predictions, and simulated decision reports are displayed on a visual interface.
[0119] In this embodiment, the visualization interface comprises three areas: a control panel area, a core display area, and a decision simulation area. The control panel area includes a time range selector, a business dimension filter, and a slider for adjusting parameters in the sandbox simulation. The core display area includes a financial indicator dashboard, a business correlation heatmap, and a risk warning timeline. The decision simulation area includes a comparison view of multiple versions of decision simulation reports and a panel for quantifying the impact of decisions.
[0120] Users can select to view quarterly or annual data through a visual interface, choose product categories or regions in terms of business dimensions, and set business parameters in the sand table simulation parameter adjustment slider.
[0121] The core display area will display financial indicators, such as budget completion rate, through a pie chart based on the user's settings; use red and blue spectra to indicate the intensity of the business's impact on financial indicators; and mark high-risk events.
[0122] The decision simulation area will display the projected cash flows from the baseline / optimistic / pessimistic reports side by side; and show the changes in net profit resulting from parameter adjustments.
[0123] It is understandable that this method can be executed by any device, equipment, platform, or cluster of devices with computing and processing capabilities.
[0124] It should be noted that the methods of one or more embodiments of this disclosure can be executed by a single device, such as a computer or server. The methods of this embodiment can also be applied in a distributed scenario, where multiple devices cooperate to complete the process. In such a distributed scenario, one of these devices may execute only one or more steps of the methods of one or more embodiments of this disclosure, and the multiple devices will interact with each other to complete the method described.
[0125] It should be noted that the above description pertains to specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0126] Based on the same inventive concept, and corresponding to any of the methods in the above embodiments, this disclosure also provides a business and financial data analysis system. For example... Figure 2 As shown, the system includes:
[0127] Data acquisition layer 11 is configured to acquire business data and financial data;
[0128] The first computing layer 12 is configured to construct a business-finance relationship network based on the aforementioned business data and financial data through data mining algorithms. The aforementioned business-finance relationship network reflects the relationships between businesses and between businesses and finance.
[0129] The second computing layer 13 is configured to quantify the impact of business on finance through a causal inference algorithm based on the above-mentioned financial data, business data and business-finance relationship network, and to construct a dynamic business-finance mapping model.
[0130] The data analysis layer 14 is configured to perform data analysis on the aforementioned business data and financial data based on the aforementioned business dynamic mapping model, and to display the data analysis results.
[0131] Optionally, the first computing layer 12 is specifically configured as follows:
[0132] Based on the above financial data, the financial indicator values of the preset financial indicators are obtained;
[0133] Based on the above business data and the above financial indicator values, data mining algorithms are used to obtain the correlation between the above businesses and between the above businesses and the above financial indicators.
[0134] By using the aforementioned business operations and financial indicators as nodes, and the relationships between the aforementioned business operations and between the aforementioned business operations and financial indicators as edges, the aforementioned business-finance relationship network is constructed.
[0135] Optionally, the second computing layer 13 is specifically configured as follows:
[0136] Based on the above financial indicators and business data, the impact between the above financial indicators and / or between the above financial indicators and the above business data is quantified using a causal inference algorithm.
[0137] Based on the aforementioned impact values and the aforementioned business-finance relationship network, the aforementioned dynamic mapping model is constructed.
[0138] Optionally, the second computing layer 13 is specifically configured as follows:
[0139] At least one data node, based on its own aforementioned financial indicator values and business data, uses a causal inference algorithm to quantify the local impact values between the aforementioned financial indicators and / or between the aforementioned financial indicators and the aforementioned business data.
[0140] Based on the aforementioned local influence values and the aforementioned business-finance relationship network, train the sub-model of the aforementioned dynamic mapping model;
[0141] The parameters of the above sub-models are uploaded to the federated learning server, so that the federated learning server can aggregate the parameters of all the above sub-models to obtain the above dynamic mapping model.
[0142] Optionally, the 14th layer of data analysis is specifically configured as follows:
[0143] The aforementioned business data, financial data, and business dynamic mapping model are input into a long short-term memory neural network to obtain a predicted development trend. The predicted development trend includes the first predicted values of the financial indicators and business data, as well as the confidence intervals of the first predicted values.
[0144] Optionally, the 14th layer of data analysis is specifically configured as follows:
[0145] Receive data adjustment instructions for the aforementioned services;
[0146] Based on the adjustment data of the above business and the above business dynamic mapping model, the second predicted value of the above financial indicator data is obtained.
[0147] Based on the second predicted value mentioned above, a decision simulation report is generated.
[0148] Optionally, the 14th layer of data analysis is specifically configured as follows:
[0149] Obtain the preset risk thresholds for the above financial indicators;
[0150] If the first predicted value of the above financial indicators exceeds the above risk threshold, an early warning mechanism will be triggered.
[0151] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, when implementing one or more embodiments of this disclosure, the functions of each module can be implemented in one or more software and / or hardware.
[0152] The apparatus described above is used to implement the corresponding methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0153] Figure 3 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.
[0154] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure.
[0155] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this disclosure are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.
[0156] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.
[0157] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0158] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.
[0159] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this disclosure, and not necessarily all the components shown in the figures.
[0160] The electronic devices described above are used to implement the corresponding methods in the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0161] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0162] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.
[0163] Additionally, to simplify the description and discussion, and to avoid obscuring one or more embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring one or more embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which one or more embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuitry) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that one or more embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0164] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0165] This disclosure includes one or more embodiments intended to cover all such substitutions, modifications, and variations falling within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A business and financial data analysis method, characterized in that, include: Obtain business and financial data; Based on the business data and the financial data, a business-finance relationship network is constructed using data mining algorithms. This network reflects the relationships between business operations and between business operations and finance. Based on the financial data, the business data, and the business-finance relationship network, the impact of business on finance is quantified using a causal inference algorithm, and a dynamic business-finance mapping model is constructed. Based on the business dynamic mapping model, data analysis is performed on the business data and the financial data, and the data analysis results are displayed.
2. The method according to claim 1, characterized in that, Based on the business data and the financial data, a business-finance relationship network is constructed using data mining algorithms, including: Based on the financial data, the financial indicator values of the preset financial indicators are obtained; Based on the business data and the financial indicator values, data mining algorithms are used to obtain the correlations between the business operations and between the business operations and the financial indicators. The business and financial indicators are used as nodes, and the relationships between the businesses and between the businesses and the financial indicators are used as edges to construct the business-finance relationship network.
3. The method according to claim 2, characterized in that, Based on the financial data, the business data, and the business-finance relationship network, a dynamic business-finance mapping model is constructed by quantifying the impact of business on finance using a causal relationship algorithm, including: Based on the financial indicator values and the business data, the impact values between the financial indicators and / or between the financial indicators and the business data are quantified using a causal inference algorithm. Based on the influence value and the business-finance relationship network, the dynamic mapping model is constructed.
4. The method according to claim 2, characterized in that, Based on the financial data, the business data, and the business-finance relationship network, a dynamic business-finance mapping model is constructed by quantifying the impact of business on finance using a causal relationship algorithm, including: At least one data node, based on its own financial indicator values and business data, uses a causal inference algorithm to quantify the local impact values between financial indicators and / or between financial indicators and business operations. Based on the local influence values and the business-finance relationship network, train a sub-model of the dynamic mapping model; The parameters of the sub-models are uploaded to the federated learning server, so that the federated learning server can aggregate the parameters of all the sub-models to obtain the dynamic mapping model.
5. The method according to claim 1, characterized in that, Based on the aforementioned business dynamic mapping model, data analysis is performed on the business data and the financial data, including: The business data, the financial data, and the business dynamic mapping model are input into a long short-term memory neural network to obtain a predicted development trend. The predicted development trend includes the first predicted value of the financial indicators and business data, as well as the confidence interval of the first predicted value.
6. The method according to claim 5, characterized in that, Based on the aforementioned business dynamic mapping model, data analysis of the business data and the financial data further includes: Receive the data adjustment instruction for the aforementioned service; Based on the adjustment data of the business and the dynamic mapping model of the business, a second predicted value of the financial indicator data is obtained; A decision simulation report is generated based on the second predicted value.
7. The method according to claim 5, characterized in that, Also includes: Obtain the preset risk threshold of the financial indicators; The early warning mechanism is triggered when the first predicted value of the financial indicator exceeds the risk threshold.
8. A business and financial data analysis system, characterized in that, include: The data acquisition layer is configured to acquire business data and financial data. The first computing layer is configured to construct a business-finance relationship network based on the business data and the financial data using data mining algorithms. The business-finance relationship network reflects the relationships between businesses and between businesses and finance. The second computing layer is configured to quantify the impact of business on finance using a causal inference algorithm based on the financial data, the business data, and the business-finance relationship network, and to construct a dynamic business-finance mapping model. The data analysis layer is configured to perform data analysis on the business data and the financial data according to the business dynamic mapping model, and display the data analysis results.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executed by the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.