Security quotation analysis system of mobile terminal

Abstract

The invention discloses a mobile terminal security quotation analysis system, which relates to the technical field of finance, and comprises a back-end server and a system architecture design module, and the back-end server interacts with a value-added service access module, a real-time data synchronization and updating module and a quotation analysis integrated module. According to the method, the same-screen display of time-sharing and K-line data is realized through the up-down split interface layout, the screen utilization rate is improved, the user experience is optimized, and frequent view switching is avoided; multiple functions such as market quotation, historical query and index analysis are integrated, integrated market analysis is realized, and the depth deficiency in the prior art is made up; market data are synchronized and updated in real time, it is ensured that the user follows the market dynamic state closely, and the delay problem is solved; a value-added service interface is reserved, future expansion is supported, architecture design is flexible, new function integration is facilitated, and market adaptability is enhanced; the convenience and efficiency of security quotation analysis of the mobile terminal are remarkably improved, the user experience is comprehensively improved, and the rapid change requirement of the market is met.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and particularly to a mobile securities market analysis system. Background Art

[0002] With the popularization of mobile Internet, mobile development frameworks such as ReactNative, Flutter, and Ionic have gradually emerged. ReactNative relies on the React ecosystem, uses the Flexbox layout system to efficiently handle UI layouts, and supports asynchronous communication, enabling developers to easily access device hardware and sensors. Flutter features its Widget-based system and Dart language, and has a self-drawing engine Skia, enabling direct interaction with the GPU, providing the possibility for high-performance applications. Ionic, through the combination of HTML, CSS, and JavaScript, and with the help of Capacitor or Cordova plugins, realizes access to native device functions. These frameworks provide powerful technical support and a flexible development environment for the development of mobile securities market analysis systems. In terms of front-end layout, Flexbox and Grid, as representatives of modern CSS layout technologies, greatly simplify the implementation of complex layouts. Flexbox, with its one-dimensional layout model and dynamic adjustment capabilities, has become the preferred choice for handling mobile layouts. Grid, on the other hand, arranges elements in rows and columns through a two-dimensional layout model, providing solutions for complex layout scenarios. In addition, CSS frameworks such as Bootstrap, Foundation, and Bulma provide rich predefined styles and components, realizing responsive layouts and further enhancing the adaptability and aesthetics of the user interface. In terms of data interaction, RESTful interfaces have become the standard way for the backend to provide real-time or historical stock data. It takes into account data formatting, error handling, as well as version management and compatibility issues, ensuring the efficient transmission and accurate parsing of data. At the same time, the application of dynamic data update technologies such as AJAX and WebSockets realizes data synchronization between the front-end and the backend, providing technical support for real-time market updates. In terms of user interface design, Jetpack Compose, as a modern UI toolkit for Android, uses the Kotlin language to achieve a more efficient and concise UI creation method. It avoids the traditional XML-based layout method, improving the efficiency and flexibility of UI development. The emergence of this technology provides new ideas and possibilities for the user interface design of mobile securities market analysis systems. Currently, there are already online stock analysis platforms on the market that use native JavaScript to draw stock trend charts (such as K-line charts and real-time updated line charts). These platforms usually obtain real-time or historical stock data through RESTful interfaces provided by the PHP backend, realizing the functions of data display and real-time update. However, these existing technologies have deficiencies in mobile securities market analysis systems: 1. Insufficient screen utilization: The screen size of mobile devices is limited, and the existing technologies fail to make full use of the screen space to display securities market data, resulting in users having to frequently switch between different views or pages, affecting the user experience; 2. Unreasonable interface layout: The traditional time-sharing chart and K-line chart layouts are not effectively integrated, and users cannot view time-sharing data and K-line data on the same interface at the same time, which limits the in-depth analysis of the market by users; 3. Low function integration: Existing mobile securities apps often only provide basic market viewing functions and lack integrated analysis tools such as indicator analysis, transaction distribution query, and K-line similarity prediction, which limits the comprehensive analysis of the market by users; 4. Insufficient real-time performance and synchronization: There are delays in data update and synchronization in the existing technologies, and rapid response to real-time market conditions cannot be achieved, which is particularly important for securities trading that requires quick decision-making; 5. Difficulty in accessing value-added services: The existing systems lack flexible interfaces and architecture designs, making it difficult to access value-added services, which limits the scalability of services and the development of the business; 6. Poor user experience: Due to the above limitations, users have a poor experience when analyzing the securities market on mobile devices, and it is difficult to timely and accurately grasp market information, affecting the efficiency and quality of decision-making. Summary of the Invention

[0003] The purpose of the present invention is to provide a mobile securities market analysis system to solve the technical problems raised in the above background technology.

[0004] To achieve the above purpose, the present invention provides the following technical solution: A mobile securities market analysis system includes a backend server and a system architecture design module. The backend server interacts with a value-added service access module, a real-time data synchronization and update module, and a market analysis integration module respectively. The value-added service access module is used to reserve the ability to access value-added market analysis. The market analysis integration module is used to realize the ability of integrated mobile market analysis. The input end of the backend server is provided with a similarity prediction and application module, which is used to predict the possible subsequent trends. The input end of the similarity prediction and application module is provided with a feature extraction module, and the input end of the feature extraction module is provided with a data collection and preprocessing module, which is used to extract and process the original data; The system architecture design module adopts a layered architecture pattern and includes a data layer, a business logic layer, a user interface display layer, and a user interaction layer. The data layer interacts with the backend server to obtain various securities market data. The business logic layer is used to implement various functional modules after processing, analyzing, and integrating the data. The user interface display layer is used to present the processed data to the user in an intuitive interface form, and the user interface display layer splits the traditional time-sharing and K-line layouts on the mobile terminal vertically. The user interaction layer is used to receive the user's operation instructions and pass them to the business logic layer for processing.

[0005] Preferably, the data collection and preprocessing module includes a wide data source collection module, a data cleaning module, and a data normalization and unification module. The wide data source collection module is used to obtain long-term K-line data of multiple securities from the historical transaction data repositories of major stock exchanges and the databases of professional financial data providers.

[0006] Preferably, the data cleaning module is used to identify and remove outliers in the collected data by using data cleaning algorithms. The data normalization and unification module uses a normalization method to compare the K-line data of different securities on the same scale.

[0007] Preferably, in the normalization method, For price data, it is normalized to the interval [0, 1] by calculating (price - min_price) / (max_price - min_price), where min_price and max_price are the minimum and maximum values in the historical price data of the security, respectively; For trading volume data, it is standardized according to its distribution using Z-score standardization, i.e., (volume - mean_volume) / std_volume, where mean_volume is the average trading volume and std_volume is the standard deviation of the trading volume.

[0008] Preferably, the feature extraction module includes a basic morphological feature extraction module, a trend feature analysis module, and a trading volume and price relationship feature mining module. The trading volume and price relationship feature mining module is used to analyze the changes in trading volume during the process of price increase and decrease.

[0009] Preferably, the basic morphological feature extraction module is used to calculate the proportion of the K-line entity length in the entire K-line length and reflect the power contrast between the bulls and bears, which is obtained using the formula (close - open) / (high - low), where close is the closing price, open is the opening price, high is the highest price, and low is the lowest price. The proportions of the upper shadow line and the lower shadow line lengths to the total K-line length are calculated respectively. The upper shadow line proportion is (high - max(close, open)) / (high - low), and the lower shadow line proportion is (min(close, open) - low) / (high - low), which helps to identify the special morphology of the K-line.

[0010] Preferably, the similarity prediction and application module includes a real-time data processing and feature extraction module, a similarity calculation and result screening module, and a result presentation and decision-making assistance module.

[0011] Preferably, the value-added service access module includes an architecture reservation module. The architecture reservation module follows a standardized interface specification, namely the SOAP or RESTful extension interface, and the data layer and the backend server use the RESTful interface for data transmission.

[0012] Preferably, the integrated market analysis module includes a data integration and synchronization module and an operation process integration module. The data integration and synchronization module establishes a data caching mechanism in the business logic layer to cache and manage the market data, historical data, and analysis results obtained from the backend server. The operation process integration module designs a simple and unified operation interface in the user interaction layer for switching different function modules in one interface.

[0013] Preferably, the real-time data synchronization and update module includes a technology selection module and an update module. The update module is used to verify and process the new data received in the business logic layer and update the corresponding cached data and interface display content in real time according to the data type and association relationship.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. Through the interface layout design of upper and lower splitting, the present invention enables the display of intraday data and K-line data on the same screen. This design improves the utilization rate of the screen space and enhances the user experience, solving the problem that the prior art often fails to make full use of the screen space of the mobile terminal, resulting in the user having to frequently switch between different views and affecting the analysis efficiency. 2. The present invention integrates various practical functions such as market quotation query, historical intraday query, historical K-line query, indicator analysis summary, transaction distribution query, and K-line similarity prediction, achieving integrated market analysis, and solving the problem that the existing technology usually only provides basic market viewing functions and lacks the integration of in-depth analysis tools; 3. The present invention can achieve real-time synchronization and update of market data, ensuring that users can obtain the latest market dynamics in a timely manner, and solving the problem that the existing technology is prone to delays in data update and synchronization and cannot meet the users' demand for real-time market conditions; 4. The present invention reserves the ability to access value-added market analysis services, providing technical support for the future expansion of services and the development of business, and solving the problem that the existing technology often lacks flexible interfaces and architecture designs and is difficult to adapt to market changes and the rapid access of new services; 5. Through the integrated market analysis ability, the present invention greatly improves the convenience and efficiency of users in conducting securities market analysis on mobile devices, improves the user experience, and solves the problem that the existing technology is prone to poor user experience due to factors such as complex interfaces and inconvenient operations; 6. The system architecture design of the present invention takes into account future expandability and can conveniently integrate new functions and services to adapt to market changes and user needs, solving the problem that the existing technology is prone to be relatively rigid in system architecture and difficult to adapt to the rapidly changing market demands; In summary, the present invention has obvious advantages over the existing technology in terms of interface layout, function integration, real-time performance, access to value-added services, user experience, and system architecture, can better meet the needs of users in conducting securities market analysis on mobile devices, and create more commercial value for enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of the main framework of the present invention; Figure 2 is a schematic diagram of the framework of the system architecture design module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Please refer to Figure 1 and Figure 2, the present invention provides a technical solution: a mobile securities market analysis system, including a backend server and a system architecture design module. The backend server interacts with a value-added service access module, a real-time data synchronization and update module, and a market analysis integration module respectively. The value-added service access module is used to reserve the ability to access value-added market analysis. The market analysis integration module is used to implement the ability of mobile market analysis integration. The input end of the backend server is provided with a similarity prediction and application module, which is used to predict the possible subsequent trends. The input end of the similarity prediction and application module is provided with a feature extraction module, and the input end of the feature extraction module is provided with a data collection and preprocessing module, which is used to extract and process the original data; Refer to Figure 2 It can be seen that the system architecture design module adopts a layered architecture mode, and it includes a data layer, a business logic layer, an interface display layer, and a user interaction layer. The data layer interacts with the backend server to obtain various securities market data. The data layer and the backend server use a RESTful interface for data transmission, following the HTTP protocol to ensure the safe and stable transmission of data. The business logic layer is used to implement various functional modules after processing, analyzing, and integrating the data. The business logic layer and the data layer and the interface display layer perform data transfer and call through a custom function interface to achieve efficient data processing and display. The user interaction layer is used to receive the user's operation instructions and pass them to the business logic layer for processing. The interface display layer is used to present the processed data to the user in an intuitive interface form. And the interface display layer splits the traditional mobile time-sharing and K-line layouts up and down. The time-sharing data is in the upper part and is displayed through a custom chart component, using simple lines and colors suitable for mobile devices to clearly present the time-sharing trend; the K-line data is in the lower part, using a mature K-line drawing library to draw according to the standard K-line form, such as using a red entity for a positive line and a green entity for a negative line, etc., to facilitate the user's intuitive comparison and analysis; in interface development, front-end layout technologies such as Flexbox are used for layout management. By setting the properties of Flexbox, such as flex-direction: column, to achieve an up-and-down arrangement layout, ensuring that the time-sharing and K-line areas can be adaptively displayed on different screen sizes, and reasonably allocating the screen space to improve the utilization rate.

[0018] Refer to Figure 1It can be seen that the data collection and preprocessing module includes a wide data source collection module, a data cleaning module, and a data normalization and unification module. The wide data source collection module is used to obtain the long-term series K-line data of multiple securities from the historical transaction data repositories of major stock exchanges and the databases of professional financial data providers, ensuring that the data covers different market environments, industry sectors, and time periods to enhance the generalization ability of the model. For example, collect the daily K-line, weekly K-line, and monthly K-line data of the main stocks in the Shanghai and Shenzhen stock markets in the past 10 years and some representative stocks in well-known international stock markets. The data cleaning module is used to identify and remove outliers in the collected data using data cleaning algorithms. For price data, if the opening price, closing price, highest price, or lowest price at a certain moment deviates from a certain multiple of the historical average price of the security, such as 5 times the standard deviation, it is determined as an outlier and corrected or deleted. At the same time, for trading volume data, if there are extremely large or extremely small values that significantly do not conform to market rules, such as a trading volume of 0 or a value far exceeding the normal trading range, corresponding processing is also carried out. In addition, the problem of missing data needs to be addressed. For a small number of missing data points, the average value of the previous and subsequent data or linear interpolation method is used for filling; for a continuous data segment with a large number of missing data, if it cannot be effectively supplemented, the time period where this data segment is located may be excluded from the analysis sample. The data normalization and unification module uses a normalization method to compare the K-line data of different securities on the same scale. In the normalization method, for price data, it is normalized to the [0,1] interval, calculated by the formula (price - min_price) / (max_price - min_price), where min_price and max_price are the minimum and maximum values in the historical price data of the security respectively; for trading volume data, it is standardized according to its distribution, using Z-score standardization, that is, (volume - mean_volume) / std_volume, where mean_volume is the average trading volume and std_volume is the standard deviation of the trading volume.

[0019] Refer to Figure 1It can be seen that the feature extraction module includes a basic morphological feature extraction module, a trend feature analysis module, and a trading volume and price relationship feature mining module. The trend feature analysis module introduces the moving average (MA) indicator, calculates the MA values for different periods, and calculates the difference between the current price and the MA and the change rate of the difference. For example, the calculation formula for the 10-day MA value is MA10 = sum(close[i]) / 10 (i is pushed back 10 periods from the current time), the difference between the price and the MA is diff = close - MA10, and the change rate of the difference is (diff - diff_previous) / diff_previous (diff_previous is the difference in the previous period). Through these indicators, the short-term and medium-term trends of the stock price can be judged. In addition, the slope of the K-line can be calculated, and by linearly fitting the price data points within a certain time window, the slope value can be obtained. The positive or negative and magnitude of the slope reflect the upward or downward trend and speed of the price. The trading volume and price relationship feature mining module is used to analyze the changes in trading volume during the process of price increase and decrease, calculate the proportion of rising trading volume, that is, the sum of trading volume during the price increase period accounts for the proportion of the total trading volume, and the proportion of falling trading volume. At the same time, observe the relationship between the peak of trading volume and the price turning point, such as whether there is an obvious amplification of trading volume before the price rises significantly, and whether the trading volume continues to shrink when the price falls. Through these features, the distribution of buying and selling forces in the market and the sustainability of the trend can be judged.

[0020] Refer to Figure 1 It can be seen that the basic morphological feature extraction module is used to calculate the proportion of the K-line entity length in the entire K-line length and reflect the power contrast between the bulls and bears, which is obtained using the formula (close - open) / (high - low), where close is the closing price, open is the opening price, high is the highest price, and low is the lowest price. Calculate the proportions of the upper shadow line and the lower shadow line lengths in the total K-line length respectively. The proportion of the upper shadow line is (high - max(close, open)) / (high - low), and the proportion of the lower shadow line is (min(close, open) - low) / (high - low), which helps to identify the special morphology of the K-line.

[0021] Refer to Figure 1It can be seen that the similarity prediction and application module includes a real-time data processing and feature extraction module, a similarity calculation and result screening module, and a result presentation and decision-making assistance module. In the real-time data processing and feature extraction module, when the user initiates a K-line similarity prediction request, the front end quickly obtains the latest K-line data of the specified securities by the user and performs real-time processing according to the pre-designed feature extraction method to generate feature vectors. At the same time, in order to improve the timeliness and accuracy of the prediction, relevant features can also be extracted from text information such as the recent market news and industry trends of the securities through natural language processing technology and fused with the K-line feature vectors.

[0022] Refer to Figure 1 It can be seen that in the similarity calculation and result screening module, the back-end server inputs the extracted feature vectors into the trained model to calculate the K-line similarity scores of the securities with other securities in the database. According to the set similarity threshold, such as 0.8 - 0.95, and it can be adjusted according to market conditions and user needs, a list of securities with higher similarity is screened out. During the screening process, factors such as the correlation and liquidity of the securities can also be further considered. For securities with relatively high correlation but poor liquidity, their priority in the recommended list is appropriately reduced to ensure that the recommended securities have good trading activity and operability.

[0023] Refer to Figure 1 It can be seen that in the result presentation and decision-making assistance module, the back-end server returns the screened list of securities and the corresponding similarity scores to the front end, and the front end displays them to the user in a clear and intuitive way. For example, the securities are arranged in descending order of similarity, and their basic information (such as security code, name, industry, etc.) and key K-line feature comparison charts are displayed to help the user quickly understand the situation of similar securities. At the same time, some investment suggestions and analysis tools based on the similarity results can also be provided, such as analyzing the historical price trend correlation of similar securities and the impact of industry trends on these securities, to assist the user in making investment decisions, such as constructing an investment portfolio, discovering potential investment opportunities or risks.

[0024] Refer to Figure 1 and Figure 2 It can be seen that the value-added service access module includes an architecture reservation module. The architecture reservation module follows standardized interface specifications, namely SOAP or RESTful extension interfaces. When a new value-added service needs to be accessed, the third-party service provider develops an adaptation plug-in according to the reserved interface specifications and docks with the interface module of the system through this plug-in. After the system performs identity verification and permission management at the business logic layer, the data and functions of the value-added service can be integrated into the existing system, and new service entrances and operation options are provided for users at the interface display layer.

[0025] Refer to Figure 1 andFigure 2 It can be seen that the integrated market analysis module includes a data integration and synchronization module and an integrated operation process module. The data integration and synchronization module establishes a data caching mechanism at the business logic layer to cache and manage market data, historical data, and analysis results obtained from the backend server. Through scheduled tasks and event-driven mechanisms, it monitors data update situations in real time. Once new data is generated, it immediately updates the cache and notifies the interface display layer to refresh, ensuring that the user sees the latest integrated market analysis information. The integrated operation process module designs a simple and unified operation interface at the user interaction layer for switching different function modules in one interface, such as directly entering historical intraday query or indicator analysis summary from market quote query, without frequently switching pages or applications, improving analysis efficiency and convenience.

[0026] Refer to Figure 1 It can be seen that the real-time data synchronization and update module includes a technology selection module and an update module. The technology selection module uses WebSockets technology to achieve real-time data communication between the front end and the backend server. The front end can refer to the mobile end. When the market data changes, the backend server actively pushes data to the front end. The front end establishes a WebSockets connection listener, and once it receives a data update notification, it immediately triggers a data update operation. The update module is used to verify and process the newly received data at the business logic layer and update the corresponding cached data and interface display content in real time according to the data type and association relationship. For example, when the real-time price of a certain stock is updated, not only the market quote display area is updated, but also the indicator analysis data and historical trend charts related to the stock are synchronously updated to ensure data consistency and real-time performance.

[0027] Working principle: When using this mobile securities market analysis system, a wide range of data sources collection module obtains the long-term series K-line data of multiple securities from the historical transaction data repositories of major stock exchanges and the databases of professional financial data providers, ensuring that the data covers different market environments, industry sectors, and time periods to enhance the generalization ability of the model. And through the data cleaning module, for the collected data, data cleaning algorithms are used to identify and eliminate outliers. For price data, if the opening price, closing price, highest price, or lowest price at a certain moment deviates from the historical average price of the security by a certain multiple, such as 5 times the standard deviation, it is determined as an outlier and corrected or deleted. At the same time, for trading volume data, if there are extremely large or extremely small values that significantly do not conform to market rules, such as a trading volume of 0 or a value far exceeding the normal trading range, corresponding processing is also carried out. In addition, the problem of missing data needs to be addressed. For a small number of missing data points, the average value of the previous and subsequent data or linear interpolation method is used for filling; for a continuous data segment with a large number of missing data, if it cannot be effectively supplemented, the time period where this data segment is located is excluded from the analysis sample. After that, through the data normalization and unified standard module, the K-line data of different securities can be compared on the same scale; Then, through the basic morphological feature extraction module, calculate the proportion of the K-line entity length to the entire K-line length, which reflects the power contrast between the bulls and bears. At the same time, calculate the proportions of the upper shadow line length and the lower shadow line length to the total K-line length respectively. These proportion features help to identify special K-line patterns. For example, a long upper shadow line may indicate strong selling pressure above, and a long lower shadow line may imply strong support below. Then, through the trend feature analysis module, introduce the moving average (MA) indicator, calculate the MA values of different periods, and calculate the difference between the current price and the MA and the change rate of the difference. Through these indicators, the short-term and medium-term trends of the stock price can be judged. In addition, the slope of the K-line can also be calculated. By linearly fitting the price data points within a certain time window, the slope value is obtained. The positive or negative and magnitude of the slope reflect the upward or downward trend and speed of the price. And through the trading volume and price relationship feature mining module, analyze the changes in trading volume during the price increase and decrease processes, calculate the rising trading volume ratio, that is, the sum of the trading volumes during the price increase period accounts for the proportion of the total trading volume, and the falling trading volume ratio. At the same time, observe the relationship between the peak of the trading volume and the price turning point, such as whether there is a significant increase in trading volume before the price rises sharply, and whether the trading volume continues to shrink when the price falls. Through these features, the distribution of buying and selling forces in the market and the sustainability of the trend can be judged; In the real-time data processing and feature extraction module, when the user initiates a K-line similarity prediction request, the front-end quickly obtains the latest K-line data of the specified securities by the user and performs real-time processing according to the pre-designed feature extraction method to generate feature vectors. At the same time, in order to improve the timeliness and accuracy of the prediction, relevant text information such as the recent market news and industry trends of the securities can also be combined, and relevant features are extracted through natural language processing technology and fused with the K-line feature vectors. In the similarity calculation and result screening module, the back-end inputs the extracted feature vectors into the trained model, calculates the K-line similarity scores of the securities with other securities in the database, and screens out a list of securities with relatively high similarity according to the set similarity threshold. During the screening process, factors such as the relevance and liquidity of the securities can be further considered. For securities with relatively high relevance but poor liquidity, their priority in the recommendation list can be appropriately reduced to ensure that the recommended securities have good trading activity and operability. In the result presentation and decision-making assistance module, the back-end returns the screened list of securities and the corresponding similarity scores to the front-end, and the front-end displays them to the user in a clear and intuitive manner. At the same time, some investment suggestions and analysis tools based on the similarity results can also be provided to assist the user in making investment decisions; When designing the system architecture, a dedicated interface module is reserved, which follows standardized interface specifications such as SOAP or RESTful extension interfaces. This interface module defines clear data formats and call methods, facilitating the future access to various value-added market analysis services. When a new value-added service needs to be accessed, the third-party service provider develops an adaptation plug-in according to the reserved interface specifications and docks it with the interface module of the system. After the system performs identity verification and permission management at the business logic layer, the data and functions of the value-added service can be integrated into the existing system, and new service entrances and operation options are provided for users at the interface display layer; The data integration and synchronization module establishes a data caching mechanism at the business logic layer to cache and manage the market data, historical data, and analysis results obtained from the back-end. Through the timed task and event-driven mechanism, it monitors the data update situation in real time. Once new data is generated, the cache is immediately updated, and the interface display layer is notified to refresh, ensuring that the user sees the latest integrated market analysis information. The operation process integration module designs a simple and unified operation interface at the user interaction layer, where the user can conveniently switch between different function modules in one interface without frequently switching pages or applications, improving the analysis efficiency and convenience; The technology selection module uses WebSockets technology to achieve real-time data communication between the front end and the back end. When the market data changes, the back-end server actively pushes the data to the front end. The front end establishes a WebSockets connection listener. Once it receives a data update notification, it immediately triggers a data update operation. The update module validates and processes the new data received at the business logic layer, and updates the corresponding cached data and interface display content according to the data type and association relationship. The content not described in detail in this specification belongs to the prior art well known to those skilled in the art.

[0028] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A mobile securities market analysis system, including a backend server and a system architecture design module, characterized in that: The back-end server interacts with the value-added service access module, the real-time data synchronization and update module and the market analysis integration module respectively. The value-added service access module is used to reserve the ability to access the value-added market analysis. The market analysis integration module is used to realize the ability of mobile terminal market analysis integration. The input end of the back-end server is provided with a similarity prediction and application module. The similarity prediction and application module is used to predict the possible subsequent trend. The input end of the similarity prediction and application module is provided with a feature extraction module. The input end of the feature extraction module is provided with a data collection and preprocessing module. The data collection and preprocessing module is used to extract and process the original data. The system architecture design module adopts a layered architecture model, and includes a data layer, a business logic layer, an interface display layer and a user interaction layer. The data layer interacts with the back-end server to obtain various types of securities market data. The business logic layer is used to implement various functional modules after data processing, analysis and integration. The interface display layer is used to present the processed data to the user in an intuitive interface form, and the interface display layer splits the traditional time-sharing and K-line layout of the mobile terminal into upper and lower parts. The user interaction layer is used to receive the user's operation instructions and pass them to the business logic layer for processing.

2. A mobile securities market analysis system according to claim 1, characterized in that: The data collection and preprocessing module includes a data source wide collection module, a data cleaning module and a data normalization and unification module. The data source wide collection module is used to obtain long-term series K-line data of multiple securities from the historical transaction data repositories of major stock exchanges and the databases of professional financial data providers.

3. A mobile securities market analysis system according to claim 2, characterized in that: The data cleaning module is used to use a data cleaning algorithm to identify and remove abnormal values ​​in the collected data, and the data normalization and unification module uses a normalization method to compare the K-line data of different securities on the same scale.

4. A mobile securities market analysis system according to claim 3, characterized in that: In the normalization method, For price data, normalize it to the interval [0,1] and calculate it using the formula (price-min_price) / (max_price-min_price), where min_price and max_price are the minimum and maximum values ​​in the historical price data of the security respectively; For trading volume data, it is standardized according to its distribution, and Z-score standardization is used, that is, (volume-mean_volume) / std_volume, where mean_volume is the average trading volume and std_volume is the standard deviation of the trading volume.

5. A mobile securities market analysis system according to claim 1, characterized in that: The feature extraction module includes a basic morphological feature extraction module, a trend feature analysis module and a trading volume and price relationship feature mining module. The trading volume and price relationship feature mining module is used to analyze the changes in trading volume during price increases and decreases.

6. A mobile securities market analysis system according to claim 5, characterized in that: The basic morphological feature extraction module is used to calculate the proportion of the K-line entity length to the entire K-line length and reflect the power comparison between the long and short sides. It is obtained using the formula (close-open) / (high-low), where close is the closing price, open is the opening price, high is the highest price, and low is the lowest price. The ratio of the upper shadow line and the lower shadow line length to the total length of the K-line is calculated respectively. The upper shadow line ratio is (high-max (close, open)) / (high-low), and the lower shadow line ratio is (min (close, open)-low) / (high-low), which helps to identify the special shape of the K-line.

7. A mobile securities market analysis system according to claim 1, characterized in that: The similarity prediction and application module includes a real-time data processing and feature extraction module, a similarity calculation and result screening module, and a result presentation and decision-making assistance module.

8. A mobile securities market analysis system according to claim 1, characterized in that: The value-added service access module includes an architecture reservation module, which complies with a standardized interface specification, namely, a SOAP or RESTful extension interface, and the data layer and the back-end server use a RESTful interface for data transmission.

9. A mobile securities market analysis system according to claim 1, characterized in that: The market analysis integration module includes a data integration and synchronization module and an operation process integration module. The data integration and synchronization module establishes a data caching mechanism at the business logic layer to cache and manage the market data, historical data and analysis results obtained from the back-end server. The operation process integration module designs a simple and unified operation interface at the user interaction layer to switch between different functional modules in one interface.

10. A mobile securities market analysis system according to claim 1, characterized in that: The real-time data synchronization and update module includes a technology selection module and an update module. The update module is used to verify and process the received new data at the business logic layer, and update the corresponding cache data and interface display content in real time according to the data type and association relationship.

Images