Data analysis method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a data analysis method and device based on artificial intelligence, computer equipment and a storage medium, and the method comprises the steps: collecting original financial data containing time information from a plurality of financial data sources; preprocessing the original financial data to obtain financial data; analyzing and processing the financial data based on a time sequence analysis model to obtain a first analysis result; analyzing and processing the financial data based on the target deep learning model to obtain a second analysis result; analyzing and processing the financial data based on the statistical model to obtain a third analysis result; integrating the first analysis result, the second analysis result and the third analysis result to obtain a target analysis result; and outputting the target analysis result. In addition, the invention also relates to a block chain technology, and the target analysis result can be stored in a block chain. According to the method, the processing efficiency and the processing accuracy of analysis and processing of the financial data are improved based on combined use of multiple models.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based data analysis methods, devices, computer equipment and storage media. Background Art

[0002] In the financial field and financial management, time variables are key factors in analyzing financial status, predicting future trends, and making reasonable decisions. Time variables are usually expressed as time series data, which is a set of data points or observations arranged in chronological order. These time series data are widely used in the financial field, including but not limited to the study of the changing patterns of financial variables such as stock prices, exchange rates, and interest rates.

[0003] At present, the analysis methods of financial data used by financial enterprises usually adopt the Wall scoring method and the DuPont analysis method. These analysis methods mainly rely on simple quantitative indicators for analysis, ignoring the in-depth analysis of time variables and the nature of the problem. When processing financial data, these methods often need to be manually performed regularly, with low processing efficiency and low accuracy. Especially in predicting future trends, traditional analysis methods have limited reference and it is difficult to accurately capture the time series characteristics of financial variables, such as seasonality, cyclicality and trend. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a data analysis method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problems that the existing financial data analysis methods need to be performed manually on a regular basis, have low processing efficiency and low accuracy.

[0005] In order to solve the above technical problems, the present application embodiment provides a data analysis method based on artificial intelligence, which adopts the following technical solutions:

[0006] Collect raw financial data including time information from various financial data sources;

[0007] Preprocessing the original financial data to obtain processed financial data;

[0008] Analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result;

[0009] Analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result;

[0010] Analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result;

[0011] Integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result;

[0012] The target analysis result is output.

[0013] Furthermore, before the step of analyzing and processing the financial data based on the preset target deep learning model to obtain the corresponding second analysis result, it also includes:

[0014] Obtain pre-built first financial sample data;

[0015] Calling an initial deep learning model and determining a model structure corresponding to the initial deep learning model;

[0016] Get the preset model building strategy;

[0017] Based on the model building strategy, the initial deep learning model is trained and evaluated using the first financial sample data to obtain a specified model that meets the preset building requirements;

[0018] Use the specified model as the target deep learning model.

[0019] Furthermore, before the step of analyzing and processing the financial data based on a preset statistical model to obtain a corresponding third analysis result, the method further includes:

[0020] Obtain pre-built second financial sample data;

[0021] Obtaining a preset analysis target, and selecting a corresponding specified Bayesian model based on the analysis target;

[0022] Get the preset model training strategy;

[0023] Based on the model training strategy, the specified Bayesian model is trained using the second financial sample data to obtain a trained target Bayesian model;

[0024] The target Bayesian model is used as the statistical model.

[0025] Furthermore, the step of preprocessing the original financial data to obtain processed financial data specifically includes:

[0026] Obtain preset data cleaning strategies and format conversion strategies;

[0027] Performing data cleaning processing on the original financial data based on the data cleaning strategy to obtain corresponding first data;

[0028] Performing format conversion processing on the first data based on the format conversion strategy to obtain corresponding second data;

[0029] The second data is used as the financial data.

[0030] Furthermore, the step of outputting the target analysis result specifically includes:

[0031] Get the preset target display format;

[0032] Call the preset target interface;

[0033] Based on the target display format, the target analysis result is displayed in the target interface.

[0034] Furthermore, after the step of outputting the target analysis result, the method further includes:

[0035] Get the preset dynamic adjustment strategy;

[0036] Calling preset financial models;

[0037] Constructing a model update rule corresponding to the financial model based on the dynamic adjustment strategy and the target analysis result;

[0038] The financial model is updated based on the model update rule.

[0039] Furthermore, after the step of outputting the target analysis result, the method further includes:

[0040] Obtain calculation methods for preset financial ratios;

[0041] Get the preset calculation adjustment strategy;

[0042] Based on the target analysis result, the calculation method of the financial ratio is adjusted accordingly using the calculation adjustment strategy.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a data analysis device based on artificial intelligence, which adopts the following technical solution:

[0044] A collection module, used to collect raw financial data including time information from various financial data sources;

[0045] A preprocessing module, used for preprocessing the original financial data to obtain processed financial data;

[0046] A first analysis module, used to analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result;

[0047] A second analysis module is used to analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result;

[0048] A third analysis module, used to analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result;

[0049] An integration module, used to integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result;

[0050] An output module is used to output the target analysis result.

[0051] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0052] Collect raw financial data including time information from various financial data sources;

[0053] Preprocessing the original financial data to obtain processed financial data;

[0054] Analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result;

[0055] Analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result;

[0056] Analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result;

[0057] Integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result;

[0058] The target analysis result is output.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0060] Collect raw financial data including time information from various financial data sources;

[0061] Preprocessing the original financial data to obtain processed financial data;

[0062] Analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result;

[0063] Analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result;

[0064] Analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result;

[0065] Integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result;

[0066] The target analysis result is output.

[0067] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0068] The present application first collects original financial data containing time information from a variety of financial data sources; then pre-processes the original financial data to obtain processed financial data; then analyzes and processes the financial data based on a preset time series analysis model to obtain a corresponding first analysis result; and analyzes and processes the financial data based on a preset target deep learning model to obtain a corresponding second analysis result; and analyzes and processes the financial data based on a preset statistical model to obtain a corresponding third analysis result; subsequently, the first analysis result, the second analysis result, and the third analysis result are integrated and processed to obtain a corresponding target analysis result; and finally, the target analysis result is output. The present application obtains financial data by pre-processing the original financial data containing time information collected from a variety of financial data sources, and then analyzes and processes the financial data respectively by combining the use of a time series analysis model, a target deep learning model, and a statistical model, and integrates the analysis results output by each model to automatically and accurately generate a target analysis result corresponding to the financial data, effectively reducing the workload of manual processing, effectively improving the processing efficiency of the analysis and processing of financial data, and improving the accuracy of the generated target analysis results, thereby helping to improve the efficiency and accuracy of financial management. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0071] Figure 2A flowchart of an embodiment of an artificial intelligence-based data analysis method according to the present application;

[0072] Figure 3 is a schematic structural diagram of an embodiment of an artificial intelligence-based data analysis device according to the present application;

[0073] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0075] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0076] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0077] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0078] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0079] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0080] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0081] It should be noted that the artificial intelligence-based data analysis method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based data analysis device is generally set in the server / terminal device.

[0082] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0083] Continue to refer Figure 2 , showing a flow chart of an embodiment of an artificial intelligence-based data analysis method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The artificial intelligence-based data analysis method provided in the embodiment of the present application can be applied to any scenario where product recommendations are required, and the artificial intelligence-based data analysis method can be applied to products in these scenarios, for example, financial data analysis in the financial insurance field. The artificial intelligence-based data analysis method comprises the following steps:

[0084] Step S201, collecting original financial data including time information from various financial data sources.

[0085] In this embodiment, the data analysis method based on artificial intelligence is executed on the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain the original financial data through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future. The executive entity of the present application may specifically be a data analysis system, or simply referred to as a system. The above-mentioned financial data sources may include internal enterprise databases, external financial reports, market data, etc. The collected original financial data contains timestamps or time period information, which can provide a basis for subsequent time variable analysis.

[0086] Step S202, pre-processing the original financial data to obtain processed financial data.

[0087] In this embodiment, the above-mentioned preprocessing of the original financial data to obtain the specific implementation process of the processed financial data will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated in detail here.

[0088] Step S203: analyzing and processing the financial data based on a preset time series analysis model to obtain a corresponding first analysis result.

[0089] In this embodiment, the above-mentioned time series analysis model can specifically adopt an autoregressive moving average model (ARMA) or an autoregressive integrated moving average model (ARIMA). By using the time series analysis model to analyze and process the financial data, the time trend and periodicity characteristics in the financial data can be automatically and accurately analyzed and obtained as the corresponding first analysis result. Among them, according to the first analysis result output by the time series analysis model, key characteristics such as seasonal fluctuations and long-term trends in the financial data can be identified. Then, the time series analysis model is used to predict future values, and the time trend and periodicity factors behind the generated prediction results are explained.

[0090] Step S204: Analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result.

[0091] In this embodiment, by inputting financial data into the target deep learning model, the nonlinear relationship and long-term dependency in the financial data are captured based on the target deep learning model, and the characteristics of the time series data in the financial data are automatically learned, and the corresponding predicted future values ​​are accurately output as the above-mentioned second analysis result. Among them, the model construction process of the above-mentioned target deep learning model will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0092] Step S205: analyzing and processing the financial data based on a preset statistical model to obtain a corresponding third analysis result.

[0093] In this embodiment, the financial data is input into the statistical model, and then the financial data is predicted based on the statistical model to evaluate the financial risk and profit potential in different time periods, which is used as the third analysis result. The model construction process of the above statistical model will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated here.

[0094] Step S206: Integrate the first analysis result, the second analysis result, and the third analysis result to obtain a corresponding target analysis result.

[0095] In this embodiment, integrated data may be obtained by integrating the generated first analysis result, the second analysis result, and the third analysis result, and the obtained integrated data may be used as the target analysis result.

[0096] Step S207: output the target analysis result.

[0097] In this embodiment, the specific implementation process of outputting the target analysis results will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0098] The present application first collects original financial data containing time information from a variety of financial data sources; then pre-processes the original financial data to obtain processed financial data; then analyzes and processes the financial data based on a preset time series analysis model to obtain a corresponding first analysis result; and analyzes and processes the financial data based on a preset target deep learning model to obtain a corresponding second analysis result; and analyzes and processes the financial data based on a preset statistical model to obtain a corresponding third analysis result; subsequently, the first analysis result, the second analysis result, and the third analysis result are integrated and processed to obtain a corresponding target analysis result; and finally, the target analysis result is output. The present application obtains financial data by pre-processing the original financial data containing time information collected from a variety of financial data sources, and then analyzes and processes the financial data respectively by combining the use of a time series analysis model, a target deep learning model, and a statistical model, and integrates the analysis results output by each model to automatically and accurately generate a target analysis result corresponding to the financial data, effectively reducing the workload of manual processing, effectively improving the processing efficiency of the analysis and processing of financial data, and improving the accuracy of the generated target analysis results, thereby helping to improve the efficiency and accuracy of financial management.

[0099] In some optional implementations, before step S204, the electronic device may further perform the following steps:

[0100] Get the pre-built First Finance sample data.

[0101] In this embodiment, the first financial data containing time information within a preset time period can be collected from the above-mentioned multiple financial data sources. And the obtained first financial data is subjected to sample construction processing to obtain the above-mentioned first financial sample data. Among them, the sample construction processing includes: data cleaning processing: processing missing values ​​and outliers to ensure the integrity and accuracy of the data. Feature engineering processing: extracting or constructing features according to the needs of the prediction or classification task. For time series data, it is necessary to calculate statistics such as moving average, standard deviation, volatility, etc. Data partitioning processing: dividing the obtained first financial sample data into a training set, a validation set, and a test set for model training, verification, and evaluation. In addition, there is no specific limitation on the time value of the above-mentioned preset time period, for example, it can be within nearly 1 year from the current time.

[0102] An initial deep learning model is called, and a model structure corresponding to the initial deep learning model is determined.

[0103] In this embodiment, there is no specific limitation on the model selection of the above-mentioned initial deep learning model, for example, RNN or LSTM can be selected. The model structure corresponding to the above-mentioned initial deep learning model includes an input layer, a hidden layer and an output layer. Input layer: accepts the input of time series data, and usually needs to convert the data into a format suitable for model processing, such as converting one-dimensional time series data into a two-dimensional matrix (number of samples, time step, number of features). Hidden layer: composed of multiple LSTM units, used to capture the time dependency in the time series. Output layer: select the appropriate output layer structure according to the task type (prediction or classification). For prediction tasks, the output layer may be one or more neurons for outputting predicted values; for classification tasks, the output layer is usually a softmax layer for outputting category probabilities.

[0104] Get a preset model building strategy.

[0105] In this embodiment, the above-mentioned model construction strategy includes model training processing and model evaluation processing. The model training process includes: selecting a suitable loss function according to the task type, such as mean square error (MSE) for regression tasks and cross entropy loss (Cross-Entropy Loss) for classification tasks. Then select an appropriate optimization algorithm, such as Adam, SGD, etc., to update the model parameters. Then, by iterating the training data, minimize the loss function and update the model parameters. The model evaluation process includes: during the training process, use the validation set to monitor the model performance to prevent overfitting. After the training is completed, use the test set to evaluate the model performance to ensure the generalization ability of the model.

[0106] Based on the model building strategy, the initial deep learning model is trained and evaluated using the first financial sample data to obtain a specified model that meets the preset building requirements. The obtained specified model is a model that can automatically learn the characteristics of time series data and build a model that can accurately predict future values.

[0107] In this embodiment, the initial deep learning model can be trained and evaluated using the first financial sample data according to the policy content of the model building strategy, so as to obtain a specified model that meets the building requirements.

[0108] Use the specified model as the target deep learning model.

[0109] This application obtains a pre-constructed first financial sample data; then calls an initial deep learning model and determines a model structure corresponding to the initial deep learning model; then obtains a preset model building strategy; subsequently, based on the model building strategy, uses the first financial sample data to train and evaluate the initial deep learning model to obtain a specified model that meets the preset construction requirements; finally, uses the specified model as the target deep learning model. This application obtains a pre-constructed first financial sample data, and then, based on the use of a model building strategy, uses the first financial sample data to train and evaluate the initial deep learning model, so that a target deep learning model that meets the requirements can be quickly and accurately constructed, thereby improving the construction efficiency of the target deep learning model and ensuring the model effect of the obtained target deep learning model.

[0110] In some optional implementations of this embodiment, before step S205, the electronic device may further perform the following steps:

[0111] Get the pre-built Second Finance sample data.

[0112] In this embodiment, the construction process of the second financial sample data may refer to the construction process of the second financial sample data, and will not be described in detail here.

[0113] A preset analysis target is obtained, and a corresponding specified Bayesian model is selected based on the analysis target.

[0114] In this embodiment, the specific goal of analyzing the financial data, i.e., the above-mentioned analysis goal, can be determined according to actual business needs, for example, it can be to evaluate the financial risk and profit potential of different time periods. In addition, a suitable Bayesian model can be selected as the above-mentioned designated Bayesian model according to the data characteristics and analysis goals of the financial data, for example, Bayesian linear regression, Bayesian time series model, etc. can be selected.

[0115] Get the preset model training strategy.

[0116] In this embodiment, the above-mentioned model training strategy includes: setting priors, constructing likelihood functions, and calculating and processing posterior distributions. Among them, setting priors includes: setting prior distributions of model parameters based on historical data or expert knowledge. Likelihood function construction includes: constructing likelihood functions based on data characteristics and model assumptions to describe the probability distribution of observed data under given parameters. Posterior distribution calculation includes: applying Bayes' theorem to calculate the posterior distribution of model parameters, that is, combining priors and likelihoods to obtain a new distribution of parameters. And use sampling methods such as Markov Chain Monte Carlo (MCMC) to extract samples from the posterior distribution. Then estimate the mean, median, confidence interval, etc. of the model parameters based on the posterior samples.

[0117] Based on the model training strategy, the designated Bayesian model is trained using the second financial sample data to obtain a trained target Bayesian model.

[0118] In this embodiment, according to the policy content of the above-mentioned model training policy, the second financial sample data can be used to train the specified Bayesian model, thereby obtaining a trained target Bayesian model. By using the trained target Bayesian model to predict financial data, the financial risk and profit potential of different time periods can be evaluated.

[0119] The target Bayesian model is used as the statistical model.

[0120] The present application obtains a pre-constructed second financial sample data; then obtains a preset analysis target, and selects a corresponding designated Bayesian model based on the analysis target; then obtains a preset model training strategy; subsequently, based on the model training strategy, the designated Bayesian model is trained using the second financial sample data to obtain a trained target Bayesian model; finally, the target Bayesian model is used as the statistical model. The present application obtains a pre-constructed second financial sample data, and then, based on the use of a model training strategy, the designated Bayesian model is trained using the second financial sample data, so that a statistical model that meets the requirements can be constructed quickly and accurately, thereby improving the efficiency of building the statistical model and ensuring the model effect of the obtained statistical model.

[0121] In some optional implementations, step S202 includes the following steps:

[0122] Get the preset data cleaning strategy and format conversion strategy.

[0123] In this embodiment, the strategy content of the above data cleaning strategy includes: missing value processing, abnormal value processing, duplicate value processing, data deduplication, and data consistency check. Among them, missing value processing includes: taking appropriate processing measures according to the number and distribution of missing values, such as deleting records containing missing values, filling missing values ​​with mean / median / mode, using interpolation or model prediction of missing values, etc. Abnormal value processing includes: identifying abnormal values ​​in data through statistical methods (such as box plots, Z scores, etc.) or business logic, and taking appropriate processing measures according to the nature of abnormal values, such as deleting abnormal values, replacing abnormal values ​​with reasonable values, or smoothing abnormal values. Duplicate value processing includes: identifying duplicate records in a data set by comparing key fields in data records. And according to business needs, delete duplicate records or retain one of the records. Data deduplication processing includes: for possible duplicate data, deduplication processing is performed by comparing key fields (such as date, transaction ID, etc.). Data consistency check processing includes: checking whether the field values ​​in the data set conform to business logic and expectations, such as whether the date format is unified and whether the value range is reasonable. Correct or delete data that does not meet the consistency requirements.

[0124] The above-mentioned format conversion strategy includes: data type conversion, data format unification, data standardization, and data discretization. Data type conversion includes: converting the fields in the data set to appropriate data types according to the needs of data analysis and modeling, such as converting string type dates to date types, converting numeric strings to numeric types, etc. Data format unification includes: ensuring that the field formats in the data set are unified, such as date format, time format, numeric format, etc. Convert or correct inconsistent formats. Data standardization includes: standardizing numeric data, such as scaling data to a specific range (such as 0-1) or normalizing it. Standardization helps eliminate the impact of data of different dimensions on the model. Data discretization includes: discretizing continuous data, such as dividing age into different age groups, dividing income into different income levels, etc.

[0125] The original financial data is cleansed based on the data cleaning strategy to obtain corresponding first data.

[0126] In this embodiment, data cleaning processing may be performed on the original financial data according to the policy content of the data cleaning policy, so as to obtain corresponding first data.

[0127] The first data is format converted based on the format conversion strategy to obtain corresponding second data.

[0128] In this embodiment, the first data may be format converted according to the policy content of the format conversion policy, thereby obtaining corresponding second data.

[0129] The second data is used as the financial data.

[0130] The present application obtains a preset data cleaning strategy and format conversion strategy; then performs data cleaning processing on the original financial data based on the data cleaning strategy to obtain corresponding first data; then performs format conversion processing on the first data based on the format conversion strategy to obtain corresponding second data; and subsequently uses the second data as the financial data. The present application performs data cleaning processing and format conversion processing on the original financial data based on the use of data cleaning strategy and format conversion strategy, thereby achieving intelligent and accurate preprocessing of the original financial data, effectively improving the accuracy and consistency of the generated financial data. This is conducive to ensuring the accuracy and effectiveness of subsequent model-based analysis work.

[0131] In some optional implementations, step S207 includes the following steps:

[0132] Get the preset target display format.

[0133] In this embodiment, there is no specific limitation on the selection of the above-mentioned target display form, for example, charts, reports, etc. can be used.

[0134] Call the preset target interface.

[0135] In this embodiment, the target interface is a pre-built front-end page for presenting the analysis status of financial data.

[0136] Based on the target display format, the target analysis result is displayed in the target interface.

[0137] In this embodiment, the generated target analysis results can be visualized in the target interface in the form of target presentation, such as charts, reports, etc.

[0138] This application obtains a preset target display format; then calls a preset target interface; and subsequently displays the target analysis results in the target interface based on the target display format. This application displays the target analysis results of financial data in the target interface based on the target display format, so as to intuitively present the changing trend of financial status over time, facilitate user understanding and analysis, effectively improve the output intelligence of the target analysis results, and improve the user experience.

[0139] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0140] Get the preset dynamic adjustment strategy.

[0141] In this embodiment, a dynamic adjustment strategy is pre-designed and implemented according to actual business needs to automatically update the financial model over time. The dynamic adjustment strategy can automatically adjust the parameters and structure of the financial model based on the analysis results of the financial data to adapt to market changes. At the same time, the dynamic adjustment strategy can also monitor the changes in financial data, and when the data exceeds a preset threshold, the financial model update process is triggered.

[0142] Call a preset financial model.

[0143] In this embodiment, the financial model is a data model pre-built in a financial enterprise for financial management.

[0144] A model updating rule corresponding to the financial model is constructed based on the dynamic adjustment strategy and the target analysis result.

[0145] In this embodiment, a model update rule corresponding to the financial model can be formulated based on the target analysis results corresponding to the above financial data and the above financial model. The generated model update model is used to clarify which data changes will trigger the financial model update, as well as the specific content and method of the update.

[0146] The financial model is updated based on the model update rule.

[0147] In this embodiment, an automated script corresponding to the model update rule can be developed to automatically run the model update process when the financial model update is triggered. The model update process may include steps such as data preprocessing, model parameter adjustment, and model retraining to ensure the stability and reliability of the automated update process.

[0148] By updating the financial model using the model update rules, it can be ensured that the financial model can accurately reflect the financial status and risk level of different time periods and dynamically adjust according to market changes. This will help enterprises better cope with the impact of market fluctuations and economic cycles and improve the effectiveness and accuracy of financial decision-making.

[0149] The present application obtains a preset dynamic adjustment strategy; then calls a preset financial model; then constructs a model update rule corresponding to the financial model based on the dynamic adjustment strategy and the target analysis result; and subsequently updates the financial model based on the model update rule. The present application obtains a preset dynamic adjustment strategy, and then intelligently constructs a model update rule corresponding to the preset financial model based on the dynamic adjustment strategy and the generated target analysis result. Subsequently, the financial model is updated based on the use of automatic model update rules, which improves the intelligence of the update of the financial model and helps to ensure that the financial model can accurately reflect the financial status and risk level of different time periods.

[0150] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0151] Gets the calculation method for a preset financial ratio.

[0152] In this embodiment, the above-mentioned method for calculating the financial ratio is a method pre-constructed in a financial enterprise for calculating the financial ratio.

[0153] Get the preset calculation adjustment strategy.

[0154] In this embodiment, the calculation adjustment strategy includes: adjusting the calculation method of the financial ratio according to the time trend and periodic characteristics to make it more reflective of the actual situation. For example, for financial ratios affected by the economic cycle, a periodic adjustment factor can be introduced.

[0155] Based on the target analysis result, the calculation method of the financial ratio is adjusted accordingly using the calculation adjustment strategy.

[0156] In this embodiment, the time trend and periodicity characteristics can be extracted from the target analysis results, and then the parameters in the calculation formula of the financial ratio can be modified according to the obtained time trend and periodicity characteristics, so that the calculation formula of the financial ratio can better reflect the actual situation. In addition, the adjusted financial ratio can also be used to verify the new data set to ensure that its performance in different time periods is more accurate. And the calculation method can be further fine-tuned according to the obtained verification results.

[0157] The present application obtains a preset calculation method for financial ratios; then obtains a preset calculation adjustment strategy; and subsequently, based on the target analysis results, uses the calculation adjustment strategy to make corresponding adjustments to the calculation method for the financial ratios. The present application obtains a calculation adjustment strategy, and then, based on the generated target analysis results for financial data, uses the calculation adjustment strategy to make corresponding adjustments to the calculation method for the financial ratios, which can help ensure that the adjusted financial ratios are more accurate in different time periods.

[0158] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0159] In addition, the non-Company software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0160] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0161] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target analysis results, the above-mentioned target analysis results can also be stored in a node of a blockchain.

[0162] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0163] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0164] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0165] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0166] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0167] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a data analysis device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0168] like Figure 3As shown, the artificial intelligence-based data analysis device 300 described in this embodiment includes: a collection module 301, a preprocessing module 302, a first analysis module 303, a second analysis module 304, a third analysis module 305, an integration module 306 and an output module 307.

[0169] in:

[0170] A collection module 301 is used to collect original financial data including time information from various financial data sources;

[0171] A preprocessing module 302 is used to preprocess the original financial data to obtain processed financial data;

[0172] A first analysis module 303, used to analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result;

[0173] A second analysis module 304 is used to analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result;

[0174] The third analysis module 305 is used to analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result;

[0175] An integration module 306, configured to integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result;

[0176] The output module 307 is used to output the target analysis result.

[0177] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0178] In some optional implementations of this embodiment, the artificial intelligence-based data analysis device further includes:

[0179] A first acquisition module, used to acquire pre-built first financial sample data;

[0180] A first calling module, for a submodule, for calling an initial deep learning model and determining a model structure corresponding to the initial deep learning model;

[0181] A second acquisition module is used to acquire a preset model building strategy;

[0182] A processing module, configured to train and evaluate the initial deep learning model using the first financial sample data based on the model building strategy to obtain a specified model that meets the preset building requirements;

[0183] The first determination module is used to use a specified model as the target deep learning model.

[0184] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0185] In some optional implementations of this embodiment, the data analysis device based on artificial intelligence also includes:

[0186] A third acquisition module is used to acquire pre-built second financial sample data;

[0187] A selection module, used to obtain a preset analysis target and select a corresponding specified Bayesian model based on the analysis target;

[0188] The fourth acquisition module is used to obtain a preset model training strategy;

[0189] A training module, configured to train the specified Bayesian model using the second financial sample data based on the model training strategy to obtain a trained target Bayesian model;

[0190] The second determination module is used to use the target Bayesian model as the statistical model.

[0191] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0192] In some optional implementations of this embodiment, the preprocessing module 302 includes:

[0193] The first acquisition submodule is used to acquire a preset data cleaning strategy and format conversion strategy;

[0194] A cleaning submodule, configured to perform data cleaning processing on the original financial data based on the data cleaning strategy to obtain corresponding first data;

[0195] a conversion submodule, configured to perform format conversion processing on the first data based on the format conversion strategy to obtain corresponding second data;

[0196] A determination submodule is configured to use the second data as the financial data.

[0197] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0198] In some optional implementations of this embodiment, the output module 307 includes:

[0199] The second acquisition submodule is used to acquire a preset target display form;

[0200] The calling submodule is used to call the preset target interface;

[0201] The display submodule is used to display the target analysis result in the target interface based on the target display form.

[0202] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0203] In some optional implementations of this embodiment, the artificial intelligence-based data analysis device further includes:

[0204] A fifth acquisition module, used to acquire a preset dynamic adjustment strategy;

[0205] The second calling module is used to call a preset financial model;

[0206] A construction module, used to construct a model update rule corresponding to the financial model based on the dynamic adjustment strategy and the target analysis result;

[0207] An updating module is used to update the financial model based on the model updating rule.

[0208] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0209] In some optional implementations of this embodiment, the artificial intelligence-based data analysis device further includes:

[0210] A sixth acquisition module, used to acquire a calculation method of a preset financial ratio;

[0211] A seventh acquisition module, used to acquire a preset calculation adjustment strategy;

[0212] An adjustment module is used to adjust the calculation method of the financial ratio accordingly using the calculation adjustment strategy based on the target analysis result.

[0213] In this embodiment, the operations performed by the above modules or units respectively correspond one-to-one to the steps of the artificial intelligence-based data analysis method in the aforementioned implementation mode, and will not be repeated here.

[0214] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0215] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0216] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0217] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of data analysis methods based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0218] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based data analysis method.

[0219] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0220] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0221] In an embodiment of the present application, first, original financial data containing time information is collected from a variety of financial data sources; then, the original financial data is preprocessed to obtain processed financial data; then, the financial data is analyzed and processed based on a preset time series analysis model to obtain a corresponding first analysis result; and the financial data is analyzed and processed based on a preset target deep learning model to obtain a corresponding second analysis result; and the financial data is analyzed and processed based on a preset statistical model to obtain a corresponding third analysis result; subsequently, the first analysis result, the second analysis result, and the third analysis result are integrated and processed to obtain a corresponding target analysis result; and finally, the target analysis result is output. The present application obtains financial data by preprocessing the original financial data containing time information collected from a variety of financial data sources, and then analyzes and processes the financial data respectively by combining the use of a time series analysis model, a target deep learning model, and a statistical model, and integrates the analysis results output by each model to automatically and accurately generate a target analysis result corresponding to the financial data, effectively reducing the workload of manual processing, effectively improving the processing efficiency of the analysis and processing of financial data, and improving the accuracy of the generated target analysis results, thereby helping to improve the efficiency and accuracy of financial management.

[0222] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the artificial intelligence-based data analysis method as described above.

[0223] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0224] In an embodiment of the present application, first, original financial data containing time information is collected from a variety of financial data sources; then, the original financial data is preprocessed to obtain processed financial data; then, the financial data is analyzed and processed based on a preset time series analysis model to obtain a corresponding first analysis result; and the financial data is analyzed and processed based on a preset target deep learning model to obtain a corresponding second analysis result; and the financial data is analyzed and processed based on a preset statistical model to obtain a corresponding third analysis result; subsequently, the first analysis result, the second analysis result, and the third analysis result are integrated and processed to obtain a corresponding target analysis result; and finally, the target analysis result is output. The present application obtains financial data by preprocessing the original financial data containing time information collected from a variety of financial data sources, and then analyzes and processes the financial data respectively by combining the use of a time series analysis model, a target deep learning model, and a statistical model, and integrates the analysis results output by each model to automatically and accurately generate a target analysis result corresponding to the financial data, effectively reducing the workload of manual processing, effectively improving the processing efficiency of the analysis and processing of financial data, and improving the accuracy of the generated target analysis results, thereby helping to improve the efficiency and accuracy of financial management.

[0225] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0226] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data analysis method based on artificial intelligence, characterized in that: The steps include: Collect raw financial data including time information from various financial data sources; Preprocessing the original financial data to obtain processed financial data; Analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result; Analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result; Analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result; Integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result; The target analysis result is output.

2. The artificial intelligence-based data analysis method according to claim 1, characterized in that: Before the step of analyzing and processing the financial data based on the preset target deep learning model to obtain the corresponding second analysis result, the method further includes: Obtain pre-built first financial sample data; Calling an initial deep learning model and determining a model structure corresponding to the initial deep learning model; Get the preset model building strategy; Based on the model building strategy, the initial deep learning model is trained and evaluated using the first financial sample data to obtain a specified model that meets the preset building requirements; Use the specified model as the target deep learning model.

3. The data analysis method based on artificial intelligence according to claim 1, characterized in that: Before the step of analyzing and processing the financial data based on the preset statistical model to obtain the corresponding third analysis result, the method further includes: Obtain pre-built second financial sample data; Obtaining a preset analysis target, and selecting a corresponding specified Bayesian model based on the analysis target; Get the preset model training strategy; Based on the model training strategy, the specified Bayesian model is trained using the second financial sample data to obtain a trained target Bayesian model; The target Bayesian model is used as the statistical model.

4. The artificial intelligence-based data analysis method according to claim 1, characterized in that: The step of preprocessing the original financial data to obtain processed financial data specifically includes: Obtain preset data cleaning strategies and format conversion strategies; Performing data cleaning processing on the original financial data based on the data cleaning strategy to obtain corresponding first data; Performing format conversion processing on the first data based on the format conversion strategy to obtain corresponding second data; The second data is used as the financial data.

5. The artificial intelligence-based data analysis method according to claim 1, characterized in that: The step of outputting the target analysis result specifically includes: Get the preset target display format; Call the preset target interface; Based on the target display format, the target analysis result is displayed in the target interface.

6. The artificial intelligence-based data analysis method according to claim 1, characterized in that: After the step of outputting the target analysis result, the method further includes: Get the preset dynamic adjustment strategy; Calling preset financial models; Constructing a model update rule corresponding to the financial model based on the dynamic adjustment strategy and the target analysis result; The financial model is updated based on the model update rule.

7. The artificial intelligence-based data analysis method according to claim 1, characterized in that: After the step of outputting the target analysis result, the method further includes: Obtain calculation methods for preset financial ratios; Get the preset calculation adjustment strategy; Based on the target analysis result, the calculation method of the financial ratio is adjusted accordingly using the calculation adjustment strategy.

8. A data analysis device based on artificial intelligence, characterized in that: include: A collection module, used to collect raw financial data including time information from various financial data sources; A preprocessing module, used for preprocessing the original financial data to obtain processed financial data; A first analysis module, used to analyze and process the financial data based on a preset time series analysis model to obtain a corresponding first analysis result; A second analysis module is used to analyze and process the financial data based on a preset target deep learning model to obtain a corresponding second analysis result; A third analysis module, used to analyze and process the financial data based on a preset statistical model to obtain a corresponding third analysis result; An integration module, used to integrate the first analysis result, the second analysis result and the third analysis result to obtain a corresponding target analysis result; An output module is used to output the target analysis result.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the artificial intelligence-based data analysis method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based data analysis method as described in any one of claims 1 to 7.

Images