CN116821169A - Financial data processing methods, devices, computer equipment and storage media - Google Patents

Abstract

This application relates to a financial data processing method, device, computer equipment, storage medium and computer program product. The method includes: collecting target financial data based on preset collection rules and actual analysis results of the target financial data; analyzing the target financial data according to an initial data mining model to obtain calculation and analysis results; according to the calculation The deviation between the analysis result and the actual analysis result is adjusted to the initial data mining model until the deviation between the calculated analysis result and the actual analysis result is less than a threshold, and a target data mining model is obtained. The target data mining model is To analyze the target financial data and obtain the target query data. This method directly obtains the target query results based on the target query data and the target data mining model without filtering financial data, reducing the process of users filtering financial data and improving query efficiency.

Description

Financial data processing methods, devices, computer equipment and storage media

Technical field

This application relates to the field of financial technology, and in particular to a financial data processing method, device, computer equipment, storage medium and computer program product.

Background technique

With the rapid development of social economy, a large amount of financial data is generated every day. Financial practitioners need to filter and analyze useful data from the massive data, which takes a lot of time.

In the existing method, by directly querying the target financial data from the server or the network, due to the wide variety of financial data categories and the large amount of data, users cannot find the target financial data in a short time, and the query efficiency is still low.

Contents of the invention

Based on this, it is necessary to address the above technical problems and provide a financial data processing method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of financial data query.

In the first aspect, this application provides a method for processing financial data. The methods include:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and a target data mining model is obtained. The data mining model is used to analyze target financial data and obtain target query data.

In one embodiment, the method further includes:

Collect target financial data at a preset collection cycle;

Call the target data mining model to analyze the target financial data and obtain calculation and analysis results;

The calculation and analysis results are filtered according to the filtering rules of the target financial data to obtain the target analysis results.

In one embodiment, in response to a query request from the user terminal, the query parameters are obtained;

Match the query parameters with the target financial data to obtain the target analysis results corresponding to the query parameters;

The target analysis results are returned to the user terminal as target query data.

In one embodiment, the collection of target financial data based on preset collection rules, and the actual analysis results of the target financial data include:

Collect data characteristics of target financial data based on preset collection rules;

Classify the target financial data based on the data characteristics of the target financial data;

Collect and test the classified target financial data;

According to the target financial data collected and tested, the actual analysis results of the target financial data are obtained.

In one embodiment, the initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, Obtain the target data mining model, including:

If the deviation between the calculated analysis result and the actual analysis result is greater than or equal to a threshold, adjust the parameters of the initial data mining model according to the value of the deviation;

Until the deviation between the calculated analysis result and the actual analysis result is less than a threshold, a target data mining model is obtained, wherein the target data mining model includes adjusted parameters.

In one embodiment, obtaining query parameters in response to a query request from a user terminal includes:

Verify the query request of the user terminal according to the user terminal identification;

The verified query request is parsed to obtain the query parameters.

In a second aspect, this application also provides a financial data processing device. The device includes:

The collection module is used to collect target financial data based on preset collection rules, as well as the actual analysis results of the target financial data;

An analysis module, used to analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

A processing module, configured to adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and the target data mining is obtained Model, the target data mining model is used to analyze the target financial data and obtain the target query data.

In a third aspect, this application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and a target data mining model is obtained. The data mining model is used to analyze target financial data and obtain target query data.

In a fourth aspect, this application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by the processor, the following steps are implemented:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and a target data mining model is obtained. The data mining model is used to analyze target financial data and obtain target query data.

In a fifth aspect, this application also provides a computer program product. The computer program product includes a computer program that implements the following steps when executed by a processor:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and a target data mining model is obtained. The data mining model is used to analyze target financial data and obtain target query data.

The above-mentioned financial data processing methods, devices, computer equipment, storage media and computer program products automatically collect target financial data and actual analysis results of the target financial data based on preset collection rules, and automatically obtain the actual analysis results of the target financial data. , analyze the target financial data according to the initial data mining model, obtain the calculated analysis results, and adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, On behalf of the iteration of the data mining model, the target data mining model obtained by the iteration is analyzed on the target financial data to obtain the target query data. This method, on the one hand, automatically analyzes the mining model based on the obtained actual analysis results and the calculated calculation analysis results. Updates are performed to realize autonomous learning of financial data. On the other hand, the target query results are directly obtained based on the target query data and the target data mining model without filtering financial data, which reduces the process of users filtering financial data and improves query efficiency. efficiency.

Description of the drawings

Figure 1 is an application environment diagram of a financial data processing method in one embodiment;

Figure 2 is a schematic flowchart of a financial data processing method in one embodiment;

Figure 3 is a structural block diagram of a financial data processing system in one embodiment;

Figure 4 is a schematic structural diagram of a query unit in an embodiment;

Figure 5 is a schematic flowchart of the operation steps of the query unit in one embodiment;

Figure 6 is a schematic diagram of a submission module in an embodiment;

Figure 7 is a schematic structural diagram of a server unit in one embodiment;

Figure 8 is a schematic structural diagram of a collection unit in an embodiment;

Figure 9 is a schematic structural diagram of the analysis system in one embodiment;

Figure 10 is an analysis method of information-based financial data in one embodiment;

Figure 11 is a structural block diagram of a financial data processing device in one embodiment;

Figure 12 is an internal structure diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

The financial data processing method provided by the embodiment of this application can be applied in the application environment as shown in Figure 1. Among them, the user terminal 102 communicates with the server 104 through the network. The data storage system may store data that server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The user terminal 102 collects target financial data based on preset collection rules, as well as actual analysis results of the target financial data. The user terminal 102 analyzes the target financial data according to the initial data mining model and obtains calculation and analysis results. The user terminal 102 adjusts the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and obtains the target data mining model. The target data mining model is used to analyze the target financial data. Perform analysis to obtain target query data.

The user terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and other terminals with certain processing capabilities. The server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in Figure 2, a financial data processing method is provided. This method is explained by taking the method applied to the user terminal in Figure 1 as an example, including:

S202: Collect target financial data based on preset collection rules, and actual analysis results of the target financial data.

Among them, the collection rules can be a unique way of collecting data in the financial field, including: collecting target financial data calculation formulas and calculation models, and then extracting parameters in the calculation formulas and calculation models to obtain target financial data. Specifically, When collecting target financial data, (1) you can first collect the calculation formulas and calculation models related to the target financial data, decompose the collected relevant calculation formulas and calculation models, collect the decomposed multiple financial data, and Multiple financial data collected and decomposed are determined as the collected target financial data. Among them, the financial data can be decomposed according to the level of the financial data. For example, according to the financial level of the institution, unit or individual where the user is located, the institutional user level, the unit user level and the individual user level, different levels of target financial data can be collected. (2) Target financial data can also be collected according to the categories of financial data, and different categories of target financial data can be collected. For example, the categories of financial data can be divided into financial category data, market data, consumer financial data, financial management data, etc. .

Among them, the triggering time of the collection action can be based on the query command issued by the user or based on the query command generated by the system. The query command includes querying the target financial data. In general, because sometimes there are multiple proper nouns corresponding to the same in the financial field, A financial concept, and sometimes a proper noun corresponds to the explanation of multiple financial concepts, resulting in an accurate correspondence between the query instructions issued by the user and the target financial data that the user actually needs to query. Therefore, before collecting the target financial data, It is necessary to perform similarity matching on the query instructions issued by the user to obtain the target financial data corresponding to the query instructions. Specifically, the query instructions issued by the user are input into the similarity matching model pre-trained with financial corpus, and the corresponding query instructions are output. Target financial data.

Generally speaking, target financial data refers to a certain financial data of a certain financial object or entity within a certain period of time. The actual analysis result of the target financial data can be the collected value of the target financial data. Specifically, the target financial data can be the numerical value of the target financial data of the target object within the target period. For example, it can be the value of the target financial data for asset i in the past. The amount of compound interest within 10 periods.

S204: Analyze the target financial data according to the initial data mining model to obtain calculation analysis results.

Among them, an initial data mining model needs to be established before analyzing the target financial data. The initial data mining model can be established based on the data flow input by the administrator to the system or terminal in advance.

Specifically, the method of establishing an initial data mining model may include: pre-collecting financial data categories according to system learning rules designed by the administrator, and obtaining initial data based on the pre-collected financial data categories and the data flow of the collected financial data. Mining model. Among them, the initial data mining model includes: target financial data, calculation formulas of the target financial data, calculation models, etc.

Among them, the target financial data, the calculation formula of the target financial data, and the calculation model can jointly constitute the framework of the target data. The target financial data is analyzed according to the framework of the target data in the initial data mining model, and the calculation and analysis results of the target financial data are obtained. Among them, the initial data mining model includes multiple target financial data and multiple target financial data frameworks. Among them, the initial data framework can also be updated based on new data to obtain a complete data framework.

S206: Adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and obtain the target data mining model. The target data mining model is used to perform the target financial data Analyze and obtain the target query data.

Among them, if the deviation between the calculated analysis results and the actual analysis results exceeds the threshold, the parameters of the initial data mining model will be fine-tuned based on the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold. Obtain the target data mining model. If the deviation between the calculated analysis results and the actual analysis results does not exceed the threshold, the initial data mining model related to the target financial data is determined as the target data mining model. By calculating the deviation between the analysis results and the actual analysis results, the initial data mining model is adjusted to obtain the target data mining model. Furthermore, new data streams can also be obtained, the data streams can be analyzed, and new target financial data can be obtained. Based on the calculation analysis results and new actual analysis results, the original target data mining model is updated to obtain a new target data mining model, and autonomous learning of data mining models and frameworks is realized.

The initial data mining model may include a first initial financial data frame and a second initial financial data frame. It should be noted that the number of financial data frames depends on the complexity of the initial data model. If the initial data mining model is more complex The more complex it is (the more financial data categories it can contain), the greater the number of frames of initial financial data.

In the existing methods, querying financial data often returns a lot of financial data with low relevance, requiring users to manually filter, which reduces the query efficiency. Therefore, a target data mining model is provided. Target data mining The model is used to analyze target financial data and obtain target query data. The target query data can be the category and value of the target financial data. Specifically, the target query data may be an estimated category of the target financial data, and the estimated category represents the category to which the predicted financial data output according to the user's query instructions belongs. The target data can be an estimated value of the target financial data. The estimated value can be obtained according to the category of the predicted financial data and the target data mining model. The estimated data can be a determined value or other data representation forms such as a numerical range.

In the above-mentioned processing method of financial data, the target financial data and the actual analysis results of the target financial data are automatically collected based on the preset collection rules, the actual analysis results of the target financial data are automatically obtained, and the target financial data is processed according to the initial data mining model. Analyze, obtain the calculated analysis results, and adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, which means the iteration of the data mining model is completed, and the iteration is completed to obtain The target data mining model analyzes the target financial data and obtains the target query data. This method, on the one hand, automatically updates the mining model based on the obtained actual analysis results and the calculated calculation analysis results, realizing autonomous learning of financial data. , On the other hand, the target query results are directly obtained based on the target query data and the target data mining model, without filtering financial data, which reduces the process of users filtering financial data and improves query efficiency.

In one embodiment, the target financial data is collected in a preset collection cycle; the target data mining model is called to analyze the target financial data to obtain the calculation and analysis results; the calculation and analysis results are filtered according to the filtering rules of the target financial data to obtain the target analysis result.

Among them, financial data are generally time-sensitive and cyclical. In addition to the category and value of financial data, the target financial data also includes time parameters such as the cycle or time range of financial data. Therefore, it is necessary to limit the financial data when collecting target financial data. belongs to the time parameter range.

The target data mining model analyzes the financial data and obtains the calculation and analysis results by analyzing and calculating the target financial data according to the framework in the target data mining model to obtain the calculation and analysis results.

Specifically, taking the target financial data as the income R _t of the target asset i as an example, the dividend payment with a preset collection period of period t is D _t , and the price of the preset collection period with a collection period of t is P _t .

The revenue calculation model in the target data mining model is as follows:

Among them, analysis and calculation are performed based on the income calculation model, dividend payment D _t , and price P _t in the target data mining model, and the calculation and analysis results are obtained, that is, the target financial data is the income R _t of the target asset i.

Usually, the target data mining model is called to analyze the target financial data. Since the frameworks of the models have a nested relationship with each other, analyzing the same target financial data often results in the calculation and analysis results of multiple target financial data. Therefore, Use certain filtering rules to filter the calculation analysis results to obtain the target analysis results.

Among them, the filtering rules for target financial data may include: when analyzing the same target financial data, distinguish the framework category of the target data mining model used, match the framework of the target data mining model with the target financial data, and obtain the matching results from Select the framework of the target data mining model with the highest matching degree, and complete the filtering of other frameworks with lower matching degree. From this, the target financial data is analyzed according to the framework of the target data mining model with the highest matching degree, and the target analysis results are obtained. , which can improve the accuracy of target analysis results.

It should be noted that the filtering rules for the target financial data may also include: selecting the frame containing the fewest financial data categories from the target data mining model framework, and analyzing the target financial data according to the frame to obtain the target analysis results. The assignment range is reduced, the selection items are reduced, the amount of model calculation is reduced, and subsequent query efficiency is improved.

In this embodiment, by filtering the calculation analysis results, the accuracy of the target analysis results can be improved, the model calculation amount can also be reduced, and the model query efficiency can be improved.

In one embodiment, the query parameters are obtained in response to the query request of the user terminal; the query parameters are matched with the target financial data to obtain the target analysis results corresponding to the query parameters; and the target analysis results are returned to the user terminal as target query data.

The query request from the user terminal may be a query request triggered by the user, or a query request triggered by the user terminal according to certain rules. For example, a query request may be generated by itself every preset time period.

Among them, after obtaining the query request from the user terminal, the query instruction can be extracted from the query request of the user terminal, and the query instruction can be converted into query parameters. Specifically, the query parameter can be a system-identifiable code converted from the query instruction. The identification code can directly participate in the analysis and calculation of the model or framework.

After obtaining the query parameters, the query parameters can be matched with the target financial data. Specifically, the matching method includes: matching the query parameters with the target financial data to obtain a matching result between the query parameters and the target financial data. The matching result can be Sort the matching rate between the query parameters and the target financial data according to the degree of matching, select the target financial data with the highest matching rate, and determine the target analysis results corresponding to the target financial data as the target analysis results corresponding to the query parameters.

The target analysis results are returned to the user terminal as target query data.

In this embodiment, by matching the query parameters with the target financial data, the target analysis results suitable for the user terminal are filtered out, without the user having to manually filter the analysis results, thereby improving the accuracy of the target analysis results.

In one embodiment, collecting target financial data based on preset collection rules and actual analysis results of the target financial data include: collecting data characteristics of the target financial data based on the preset collection rules; Classify the target financial data; collect and test the classified target financial data; obtain the actual analysis results of the target financial data based on the target financial data that has passed the collection test.

Among them, the data characteristics can refer to the category to which the target financial data belongs, and the categories of the target financial data can be divided according to different dimensions. Specifically, the financial data can be divided according to the hierarchical dimension of the financial data, and can also be divided according to the category dimension of the financial data. Segment financial data.

Among them, the hierarchical dimensions of financial data include: the financial level of the user's institution, unit or individual, institutional user level, unit user level and individual user level. Target financial data at different levels can be collected. The category dimensions of financial data include: financial data category dimension, market data category dimension, consumer financial data category dimension, financial management data category dimension, etc.

Among them, classifying the target financial data based on the data characteristics of the target financial data refers to classifying multiple different categories of target financial data according to their categories.

Among them, the collection test is to test the legality, logic and other contents of the target financial data. Specifically, taking the test content as a logical test as an example, input the classified target financial data into the corresponding financial data mining model. If the before and after values of the classified target financial data change, that is, the test results and collection Inconsistent results mean that the target financial data has failed the collection test and needs to be collected again until the target financial data that passes the collection test is obtained.

The target financial data that has passed the collection test can be determined as the actual analysis result of the target financial data.

In this embodiment, by collecting and testing the target financial data, target financial data that does not correspond logically are filtered out, thereby providing a basis for further analysis of the subsequent target financial data, thus improving the accuracy of the query.

In some cases, the data mining model lacks effective verification during construction, resulting in low accuracy during the use of the data mining model. Therefore, a verification mechanism can be introduced when using the data mining model. Thus, in one embodiment, , adjust the initial data mining model based on the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and obtain the target data mining model, including: If the deviation between the calculated analysis results and the actual analysis results is greater than or equal to the threshold, adjust the parameters of the initial data mining model according to the value of the deviation; until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, the target data mining model is obtained, where the target data mining model includes the adjusted parameters.

Among them, if the deviation between the calculated analysis results and the actual analysis results is greater than or equal to the threshold, the parameters of the initial data mining model can be adjusted according to the size of the deviation. Specifically, if the deviation is larger, the amplitude of the adjustment of the parameters of the initial data mining model will be greater, and the size of the deviation is positively correlated with the extent of adjustment of the parameters of the initial data mining model.

In this embodiment, query accuracy can be improved by calibrating the initial data mining model according to the size of the deviation.

In one embodiment, in response to the query request of the user terminal, obtaining the query parameters includes: verifying the query request of the user terminal according to the user terminal identifier; parsing the verified query request to obtain the query parameters.

Among them, the user terminal identifier is the unique identifier of the user terminal. Before obtaining the query request of the user terminal, the user's identity information needs to be verified. After obtaining the query request of the user terminal, the query request of the user terminal is verified and the verification is obtained. test results. And based on the verification results, the verified query request is parsed to obtain the query parameters.

Among them, after obtaining the query request from the user terminal, the query instruction can be extracted from the query request of the user terminal, and the query instruction can be converted into query parameters. Specifically, the query parameter can be a system-identifiable code converted from the query instruction. The identification code can directly participate in the analysis and calculation of the model or framework.

In this embodiment, by verifying the user terminal identifier for the query request of the user terminal, the query accuracy of the mining model and the accuracy of the query results can be improved.

In one embodiment, as shown in Figure 3, a financial data processing system is provided, including: a query unit, a collection unit and a server unit. The query unit is connected to the server unit, and the collection unit is connected to the server unit respectively.

Among them, the query unit is used for users to input query instructions, send the instruction code to the server unit, and find the corresponding financial data from inside the server unit; the server unit is used to save, analyze, display and manage financial data and system permissions; the collection unit By manually setting collection rules, the control system automatically performs deep learning, and the system analyzes and collects the learned data.

As shown in Figure 4, the structural diagram of the query unit is shown. The query unit includes a login module and a submission module. The login module is used to log in user information. After the user inputs the user name and password, the operating system will display it to the user after the system query is qualified. ; When using it, the user enters the query interface by entering the user name and password. When the query result is No, it prompts that the user name or password is entered incorrectly, and the user re-enters it until the two are entered correctly, the system query result is Yes, and the user enters the system interface. A single user corresponds to a username and password, as shown in Figure 5, a flowchart of the query unit operation steps. Among them, the operation steps include:

Step 1: The current user opens the system login interface, fills in the user name and password information, and clicks the "Login" button.

Step 2: The system queries and determines whether the user name and password are correct in the server database based on the filled in user name. If the query fails, the system will pop up a dialog box with "Incorrect user name or password" and then return to step one. If the query is successful, proceed to step three.

Step 3: Log in to the main interface of the financial data analysis system.

Among them, the schematic diagram of the submission module is shown in Figure 6. The submission module is used to submit query instructions issued by users who have completed identity verification, and convert the input instructions into codes that can be recognized by the system. After the user's ID information is recognized, the query command can be sent to the system through the computer. After code conversion, the command to be queried is given an exclusive shortcut key. This shortcut key is automatically backed up within the system. The next time the user queries, click directly Shortcut keys can be used to complete the corresponding operations, simplify the query process, and improve the system's processing and response speed.

As shown in Figure 7, the structural diagram of the server unit is shown. The server unit includes a financial data display module, a report module and a management module, among which:

The financial data display module is used to display the analyzed and collected financial data to the outside world. The system automatically filters out key data through independent learning; the report module is used to display data reports to the outside world and uniformly classify the analyzed and collected data. Users can quickly retrieve the required data; the management module is used to control users' access rights and manage data within the system, which can be freely controlled by the backend administrator.

Among them, the key data may refer to the target financial data of the framework of the financial data mining model.

Among them, the structural diagram of the collection unit is shown in Figure 8. The collection unit includes a rule design module, a rule learning module, an automatic collection module, a filtering module and a manual intervention module, where:

The rule design module uses the administrator to design the learning rules of the system. The administrator first inputs the data flow into the system to form a preliminary framework. The system will continue to improve on this framework.

The rule learning module control system analyzes and learns data through pre-designed analysis rules to prepare for subsequent independent data collection.

Based on the rule learning module, the automatic collection module independently collects external data flows according to the learning rules within the system and continuously improves the database. When the system collects data and learns independently, the system first accesses the target address of the collection rule learning, selects the collection items, then studies the data characteristics of the collection items, and categorizes the corresponding data. After the classification is completed, the data items are collected and tested. Verify whether the data is accurate. If yes, continue to collect the next data item. If not, select the collection item again.

The filtering module is used to filter the data that is not required by the query unit, and only displays the required data to the user; when the data is undergoing intelligent mining and learning, the data starts to be intelligently collected, and then the collection items are set to detect whether the collected data is accurate, and inaccurate data is reprocessed. Classification calculations are performed until accurate, and then all data with correct detections are classified and filtered.

The manual intervention module modifies and monitors the operation of the system through the active intervention of external administrators. Administrator users can manage the mined financial data after data mining, and use system and manual review to manage the mined data. Administrators can add, delete and modify stock data. It is likely that some new data will appear on the Financial Securities website.

Specifically, automatic learning is as follows:

Set mining rules: Administrator users can add, modify, delete, query various data mining rules, and manage financial data mining rules.

Web page parsing: parse the web page through the set mining rules and analyze its source files.

Data filtering: Use regular expressions to filter useless data.

Obtain data: After the data is filtered, the required financial data is finally obtained and stored in the database.

Manage data: Administrators review and manage the acquired data.

Among them, the structural diagram of the analysis system shown in Figure 9 includes: front-end user, analysis system, data collector and back-end administrator.

As shown in Figure 10, the analysis system is used to perform an information-based financial data analysis method, where the steps of the method include:

S1002: Collect data characteristics of target financial data based on preset collection rules.

S1004. Classify the target financial data based on the data characteristics of the target financial data.

S1006: Collect and test the classified target financial data.

S1008: Obtain the actual analysis results of the target financial data based on the target financial data that has passed the collection test.

S1010: Analyze the target financial data according to the initial data mining model and obtain calculation analysis results.

S1012: Adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and obtain the target data mining model. The target data mining model is used to perform target financial data analysis. Analyze and obtain the target query data.

Among them, if the deviation between the calculated analysis result and the actual analysis result is greater than or equal to the threshold, the parameters of the initial data mining model are adjusted according to the value of the deviation. Until the deviation between the calculated analysis result and the actual analysis result is less than the threshold, the target data mining model is obtained, where the target data mining model includes the adjusted parameters.

Among them, the target data mining model can include:

The random walk model of single financial asset price P _t =μ+P _t-1 +σε _t ; the random walk model of single financial asset return rate r _t =μ+r _t-1 +σε _t .

Specifically, assuming that the price of asset i at time t is P _t , and there is no dividend, the single-period net income R _t of asset i from t-1 to period t is defined as:

Gross income is defined as 1+R _t , and the gross income from period t-k+1 to t is defined as:

Among them, R _t (k) is compound interest income.

The arithmetic mean and geometric mean of multiple single-period returns are calculated as follows:

Continuous compound interest income:

S1014, collect target financial data in a preset collection cycle.

S1016: Call the target data mining model to analyze the target financial data and obtain the calculation analysis results.

S1018: Filter the calculation analysis results according to the filtering rules of the target financial data to obtain the target analysis results.

S1020: Verify the query request of the user terminal according to the user terminal identifier.

S1022: Parse the verified query request to obtain query parameters.

S1024: Match the query parameters with the target financial data to obtain the target analysis results corresponding to the query parameters.

S1026: Return the target analysis result to the user terminal as target query data.

In this embodiment, the target financial data and the actual analysis results of the target financial data are automatically collected based on the preset collection rules, and the actual analysis results of the target financial data are automatically obtained. The target financial data is analyzed according to the initial data mining model to obtain Calculated analysis results, the initial data mining model is adjusted based on the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, which represents the completion of the iteration of the data mining model, and the target data obtained after the iteration is completed The mining model analyzes the target financial data and obtains the target query data. On the one hand, this method automatically updates the mining model based on the obtained actual analysis results and the calculated calculation analysis results, realizing autonomous learning of financial data. On the other hand, On the other hand, the target query results are directly obtained based on the target query data and the target data mining model, without filtering financial data, which reduces the process of users filtering financial data and improves query efficiency. When using this method, the system has a high safety factor. After many verifications, the system enters the system. After the initial establishment of the model framework, the system is gradually learned and improved. The system has its own set of learning logic and algorithms, and the system directly communicates with the outside world. Internet interoperability, through the learning of massive data, the system can learn and mine data independently, and classify and filter the received data, reducing the impact of redundant and single data on the system, reducing the work pressure of practitioners, and improving work efficiency.

It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or stages. These steps or stages are not necessarily executed at the same time, but may be completed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

Based on the same inventive concept, embodiments of the present application also provide a financial data processing device for implementing the above-mentioned financial data processing method. The solution to the problem provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in the embodiments of one or more financial data processing devices provided below can be found in the above description of the processing of financial data. The limitations of the method will not be repeated here.

In one embodiment, as shown in Figure 11, a financial data processing device is provided, including: a collection module 1102, an analysis module 1104 and a processing module 1106, wherein:

The collection module 1102 is used to collect target financial data based on preset collection rules, and the actual analysis results of the target financial data;

The analysis module 1104 is used to analyze the target financial data according to the initial data mining model and obtain calculation and analysis results;

The processing module 1106 is used to adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and obtain the target data mining model. The target data mining model is used to The target financial data is analyzed to obtain the target query data.

In one embodiment, the financial data processing device also includes: a pre-collection module, used to collect target financial data in a preset collection cycle; call the target data mining model to analyze the target financial data to obtain calculation and analysis results; according to the target The filtering rules of financial data filter the calculation analysis results to obtain the target analysis results.

In one embodiment, the pre-acquisition module is also used to obtain query parameters in response to a query request from the user terminal; match the query parameters with the target financial data to obtain the target analysis results corresponding to the query parameters; and use the target analysis results as The target query data is returned to the user terminal.

In one embodiment, the collection module 1102 is also used to collect data characteristics of the target financial data based on preset collection rules; classify the target financial data based on the data characteristics of the target financial data; classify the classified target financial data. The data is collected and tested; based on the target financial data that has passed the collection test, the actual analysis results of the target financial data are obtained.

In one embodiment, the processing module 1106 is also configured to adjust the parameters of the initial data mining model according to the value of the deviation if the deviation between the calculated analysis result and the actual analysis result is greater than or equal to the threshold; until the deviation between the calculated analysis result and the actual analysis result is If the deviation is less than the threshold, a target mining model is obtained, where the target mining model includes the adjusted parameters.

In one embodiment, the pre-collection module is also used to verify the query request of the user terminal according to the user terminal identifier; parse the verified query request to obtain the query parameters.

Each module in the above-mentioned financial data processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in Figure 12. The computer device includes a processor, a memory, an input/output interface (Input/Output, referred to as I/O), and a communication interface. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The computer device's database is used to store target financial data. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a method of processing financial data.

Those skilled in the art can understand that the structure shown in Figure 12 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.

In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the following steps:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data based on the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and the target data mining model is obtained. The target data mining model is used to analyze the target financial data. Get target query data.

In one embodiment, a computer-readable storage medium is provided with a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data based on the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and the target data mining model is obtained. The target data mining model is used to analyze the target financial data. Get target query data.

A computer program performs the following steps when executed by a processor:

Collect target financial data based on preset collection rules, and actual analysis results of the target financial data;

Analyze the target financial data based on the initial data mining model and obtain calculation and analysis results;

The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than the threshold, and the target data mining model is obtained. The target data mining model is used to analyze the target financial data. Get target query data.

It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all It is information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random) Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (10)

1. A method for processing financial data, characterized in that the method includes: Collect target financial data based on preset collection rules, and actual analysis results of the target financial data; Analyze the target financial data according to the initial data mining model and obtain calculation and analysis results; The initial data mining model is adjusted according to the deviation between the calculated analysis results and the actual analysis results until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and a target data mining model is obtained. The data mining model is used to analyze target financial data and obtain target query data. 2. The method according to claim 1, characterized in that, the method further comprises: Collect target financial data at a preset collection cycle; Call the target data mining model to analyze the target financial data and obtain calculation and analysis results; The calculation and analysis results are filtered according to the filtering rules of the target financial data to obtain the target analysis results. 3. The method according to claim 2, characterized in that, the method further comprises: In response to the query request from the user terminal, obtain the query parameters; Match the query parameters with the target financial data to obtain the target analysis results corresponding to the query parameters; The target analysis results are returned to the user terminal as target query data. 4. The method according to claim 1, characterized in that the collection of target financial data based on preset collection rules and the actual analysis results of the target financial data include: Collect data characteristics of target financial data based on preset collection rules; Classify the target financial data based on the data characteristics of the target financial data; Collect and test the classified target financial data; According to the target financial data collected and tested, the actual analysis results of the target financial data are obtained. 5. The method according to claim 1, characterized in that the initial data mining model is adjusted according to the deviation between the calculated analysis result and the actual analysis result, until the calculated analysis result and the actual analysis result are adjusted. The deviation of the actual analysis results is less than the threshold, and the target data mining model is obtained, including: If the deviation between the calculated analysis result and the actual analysis result is greater than or equal to a threshold, adjust the parameters of the initial data mining model according to the value of the deviation; Until the deviation between the calculated analysis result and the actual analysis result is less than a threshold, a target data mining model is obtained, wherein the target data mining model includes adjusted parameters. 6. The method according to claim 3, characterized in that, in response to a query request from a user terminal, obtaining query parameters includes: Verify the query request of the user terminal according to the user terminal identification; The verified query request is parsed to obtain the query parameters. 7. A financial data processing device, characterized in that the device includes: The collection module is used to collect target financial data based on preset collection rules, as well as the actual analysis results of the target financial data; An analysis module, used to analyze the target financial data according to the initial data mining model and obtain calculation and analysis results; A processing module, configured to adjust the initial data mining model according to the deviation between the calculated analysis results and the actual analysis results, until the deviation between the calculated analysis results and the actual analysis results is less than a threshold, and the target data mining is obtained Model, the target data mining model is used to analyze the target financial data and obtain the target query data. 8. A computer device, comprising a memory and a processor, the memory stores a computer program, wherein the method of any one of claims 1 to 6 is implemented when the processor executes the computer program. step. 9. A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented. 10. A computer program product, comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.