WO2020124594A1 - 一种基于股票相关性算法的股市趋势分析方法和系统 - Google Patents

一种基于股票相关性算法的股市趋势分析方法和系统 Download PDF

Info

Publication number
WO2020124594A1
WO2020124594A1 PCT/CN2018/122844 CN2018122844W WO2020124594A1 WO 2020124594 A1 WO2020124594 A1 WO 2020124594A1 CN 2018122844 W CN2018122844 W CN 2018122844W WO 2020124594 A1 WO2020124594 A1 WO 2020124594A1
Authority
WO
WIPO (PCT)
Prior art keywords
stocks
core
stock
individual
correlation
Prior art date
Application number
PCT/CN2018/122844
Other languages
English (en)
French (fr)
Inventor
刘军
杨启华
Original Assignee
深圳派港投资管理有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳派港投资管理有限公司 filed Critical 深圳派港投资管理有限公司
Priority to PCT/CN2018/122844 priority Critical patent/WO2020124594A1/zh
Publication of WO2020124594A1 publication Critical patent/WO2020124594A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Definitions

  • the invention belongs to the technical field of data processing, and particularly relates to a stock market trend analysis method and system based on a stock correlation algorithm.
  • Embodiments of the present invention provide a stock market trend analysis method and system based on a stock correlation algorithm to solve the problem of insufficient accuracy when calculating stock market trends.
  • An embodiment of the present invention provides a stock market trend analysis method based on a stock correlation algorithm, including:
  • the stock market structure trend indicator within a preset period is calculated, and the stock market structure trend indicator is output in a preset form.
  • An embodiment of the present invention also provides a stock market trend analysis system based on a stock correlation algorithm, including:
  • a standardized module used to calculate the rise and fall of individual stocks on that day, and normalize the rise and fall of the individual stocks to the relative score of individual stocks;
  • the correlation calculation module is used to calculate the correlation between the individual shares according to the relative score of the individual shares;
  • the plate calculation module is used to calculate a plate composed of similar stocks according to the correlation between the stocks according to a preset algorithm
  • Core stock confirmation module used to confirm individual stocks in the sector as core stocks
  • the analysis module is used to calculate the stock market structure trend indicator within a preset period based on the confirmed core stocks, and output the stock market structure trend indicator in a preset form.
  • the price fluctuations of individual stocks on that day are normalized to the relative scores of individual stocks, and the standardized price fluctuations are used as the basis for calculating the correlation of individual stocks.
  • the actual effect is more effective than using the price fluctuations as the calculation basis directly, and Calculating the correlation between individual stocks based on the relative scores of individual stocks eliminates a large number of invalid individual stock correlations, making the characteristics of the sector composed of similar stocks obvious and meeting user needs. Recognizing all stocks composed of various sectors as core stocks, and calculating stock market structure trend indicators on this basis, has a more clear indication, and will not cause the calculated indicators to have no practical use because of the indiscriminate treatment of all stocks. This improves the accuracy of the stock market trend analysis results and provides a clear logical basis for practical applications.
  • FIG. 1 is a schematic diagram of an implementation process of a stock market trend analysis method based on a stock correlation algorithm provided by an embodiment of the present invention
  • FIG. 2 is a schematic diagram of an implementation process of a stock market trend analysis method based on a stock correlation algorithm provided by another embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a stock market trend analysis system based on a stock correlation algorithm provided by an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of a stock market trend analysis system based on a stock correlation algorithm provided by another embodiment of the present invention.
  • FIG. 1 is a schematic diagram of an implementation process of a stock market trend analysis method based on a stock correlation algorithm according to an embodiment of the present invention.
  • the method can be applied to an electronic device.
  • the electronic device may include: a smartphone, a tablet computer, etc.
  • Non-mobile electronic devices such as electronic devices that can be used on the move and personal computers (PCs).
  • the method mainly includes the following steps:
  • Standard Deviation is the most commonly used as the statistical distribution degree in statistical probability (statistical dispersion).
  • standard deviation is defined as the arithmetic square root of the variance, reflecting the degree of dispersion between individuals within the group.
  • the calculated standard deviation is multiplied by a first preset coefficient as the first normalized step size.
  • the first preset coefficient may be an integer or may not be an integer, for example, integers such as 1, 2, 3, or 0.8 , 0.9 and other non-integer numbers, preferably, the first preset coefficient is 0.8; taking the center point of the normalization as a starting point, the integer multiple of the first normalized step is taken as the relative score of each stock, that is, the The multiple is an integer, for example, from the center point, the relative score of the stock is set to 0 in the range of 1 times of the first standardized step; the relative score of the stock is set to 1 in the range of 1 to 2 times of the standardized step ; Among them, the relative score of the stock is within a preset range, such as 4 ⁇ -4, or 5 ⁇ -5, which can be customized according to the calculation.
  • the first standardized step is 1.6302.
  • the correlation coefficient Correlation between any two individual stocks
  • Correlation coefficient is a statistical index used to reflect the close degree of correlation between variables.
  • the correlation coefficient is calculated according to the product difference method, which is also based on the dispersion between the two variables and their respective averages, and the degree of correlation between the two variables is reflected by multiplying the two dispersions.
  • the correlation coefficient is between -1 and 1.
  • the first preset time period may be 20 days, or 40 days, 60 days, and so on.
  • first first preset time period may be 20 days
  • second first preset time period may be 40 days, according to the 20 days and the 40 Calculate the correlation coefficient between any two stocks based on the relative score of each day's stocks.
  • the individual shares whose correlation coefficient reaches the first preset value form a relationship pair, and the first preset value is, for example, 0.5;
  • the preset algorithm for example, the connected graph algorithm, processes all the relationship pairs through the connected graph algorithm, and treats each formed connection as a plate composed of similar stocks.
  • Each sector contains at least 2 stocks.
  • the core stocks include relatively rising core stocks and relatively falling core stocks. Among them, the relatively rising core stocks are the same day. Core stocks with a relative score greater than 0 for individual stocks, and the core stocks that are relatively down are core stocks with a relative score of less than 0 for that day.
  • the first preset time period may be multiple, and the stocks in the sector calculated according to each first preset time period are added up.
  • the core stocks entered into the sector at any first preset time period are excluded Drop out duplicate stocks and get all core stocks.
  • the stock market structure trend index refers to an index that can reflect the market structure trend of the stock market, and may include: the stock market core quantity index and the market structure index.
  • the stock market structure trend index within a preset period is calculated. Specifically, it can include: calculating the stock market core quantity index within the preset period based on the confirmed core stocks; it can also include: calculating the trend correlation of each core stock based on the confirmed core stocks, and calculating the market based on the trend correlation Structural indicators. It should be noted that after step S104, the calculation of the stock market core quantity index and the calculation of the market structure index in step S105 can be calculated separately or together, and any one of them can indicate the development trend of the stock market.
  • the calculation of the core quantity index of the stock market according to the confirmed core stocks is specifically: calculating the core stocks that repeatedly appear in the second preset time period, for example, 10 days.
  • the total number of recurrences is added up, and the difference between the total number of times the core stocks that have risen relatively and the total number of times that the core stocks that have fallen relatively are total is used as the index of the number of core stocks in the stock market;
  • the total market value of individual stocks is used as a standard to distinguish core stocks into large stocks, medium stocks and small stocks.
  • the core stocks are divided into large stocks, medium stocks and small stocks based on the threshold value of the individual stock market value of the core stocks and the total stock market value of individual stocks
  • the core stocks that account for the top 30% of the total market value of the entire market are used as large stocks, and the bottom 30% are used as small stocks.
  • the core stock between the two is medium stocks.
  • the core stock quantity indexes of large stocks, medium stocks and small stocks are correspondingly divided into large stock core quantity indexes, medium stock core quantity indexes and small stock core quantity indexes.
  • the core stock When calculating the trend correlation of a core stock, according to the relative score of the core stock, calculate the correlation coefficient between the core stock and other core stocks within the preset historical date on the current day, where the preset historical date is, for example, in the past 10 days, 15 days, 20 days, etc.
  • the trend correlation can define its own range. Specifically, this embodiment In, the trend correlation is a score that is customized in the range of 0 ⁇ 4.
  • the average value of the trend correlation of all core stocks on that day is used as the market structure indicator for that day.
  • the market structure indicator finally shows a value between 0 and 4, with continuous readings every day.
  • the large stock structure index and/or the medium stock structure index are calculated based on the individual stock market value as the dividing standard, and used as a reference for investment users.
  • individual stocks' ups and downs are normalized to individual stocks' relative scores.
  • the actual effect is more effective than directly using the ups and downs as the calculation basis, and according to the relative stocks
  • the correlation between individual stocks is calculated by score, and the correlation of a large number of invalid stocks is eliminated, so that the characteristics of the plate composed of similar stocks are obvious and meet the needs of users. Recognizing all stocks composed of various sectors as core stocks, and calculating stock market structure trend indicators on this basis, has a more clear indication, and will not cause the calculated indicators to have no practical use because of the indiscriminate treatment of all stocks. This improves the accuracy of the stock market trend analysis results and provides a clear logical basis for practical applications.
  • step S104 the stocks in the sector are confirmed as core stocks, specifically: Step S204: adding up the individual stocks in each sector in the first preset time period and excluding duplicates Individual stocks get core stocks, which include relatively rising core stocks and relatively falling core stocks.
  • the passive increase and decrease of the target stock is calculated, and the passive increase and decrease points are calculated according to the passive increase and decrease of the target stock.
  • the target stocks are the stocks whose passive changes are to be calculated, and the passive changes of all stocks can be calculated.
  • the passive stock price of the target stock can be calculated according to the passive stock price.
  • the relative stock value of the stock is calculated using the same standardized method as step S101, which is the stock’s stock passive. Change points. Specifically, the passive rises and falls of all stocks are ranked from large to small, and the passive rises and falls of the median or preset percentile stocks are taken as the standardized central point to calculate the standard deviation of the passive rises and falls of all stocks , Multiply the standard deviation by the second preset coefficient as the second standardized step, then the passive stock ups and downs score is an integer multiple of the second standardized step, the second preset coefficient can be the same as the first The preset coefficients are the same or different. Among them, the passive stock ups and downs points are within the preset range, the preset range can be specifically 4 ⁇ -4 and so on.
  • step S206 may be executed separately after step S104, or may be executed together with step S105.
  • the passive stock rise and fall ranges in step S206 and the passive stock rise and fall scores in step S207 are indicative of the development trend of individual stocks.
  • the calculation of the stock market core quantity index and the calculation of the market structure index in step S105 indicate the development trend of the entire market. Individual stocks' passive ups and downs, individual stocks' passive ups and downs scores, stock market core quantity indicators and market structure indicators can jointly indicate the development trend of individual stocks and markets for users.
  • individual stocks are normalized to the relative score of individual stocks based on individual stock rises and falls, and the standardized rises and falls are used as the basis for calculating the correlation of individual stocks.
  • the actual effect is more effective than directly using the rise and fall as the calculation basis, and according to The relative score of individual stocks calculates the correlation between individual stocks, and then removes a large number of invalid individual stock correlations, making the plate characteristics of similar stocks obvious and meet user needs. Recognizing all stocks composed of various sectors as core stocks, and calculating the core number index and market structure index of the stock market on this basis, it has a more clear indication meaning, and will not cause the calculated index because of the indiscriminate treatment of all stocks.
  • FIG. 3 is a schematic structural diagram of a stock market trend analysis system based on a stock correlation algorithm provided by an embodiment of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown.
  • the stock market trend analysis system based on the stock correlation algorithm illustrated in FIG. 3 can be placed in the electronic device, and is the executive body of the stock market trend analysis method based on the stock correlation algorithm provided by the embodiment shown in FIG. 1.
  • the system mainly includes:
  • Standardization module 301 correlation calculation module 302, sector calculation module 303, core stock confirmation module 304 and analysis module 305;
  • the standardized module 301 is used to calculate the rise and fall of individual stocks on that day, and normalize the rise and fall of individual stocks to the relative score of individual stocks.
  • the correlation calculation module 302 is used to calculate the correlation between the individual shares according to the relative score of the individual shares;
  • the plate calculation module 303 is used to calculate a plate composed of similar stocks according to the correlation between the stocks according to a preset algorithm
  • the core stock confirmation module 304 is used to confirm individual stocks in the sector as core stocks
  • the analysis module 305 is used to calculate the stock market structure trend indicator within a preset period based on the confirmed core stocks, and output the stock market structure trend indicator in a preset form.
  • each functional module is only an example, and the actual application can be based on needs, such as the configuration requirements of the corresponding hardware or software
  • the above function allocation is performed by different function modules, that is, the internal structure of the electronic device is divided into different function modules to complete all or part of the functions described above.
  • the corresponding functional modules in this embodiment may be implemented by corresponding hardware, or may be completed by corresponding hardware executing corresponding software. All the embodiments provided in this specification can apply the above description principles, which will not be repeated below.
  • individual stocks' ups and downs are normalized to individual stocks' relative scores.
  • the actual effect is more effective than directly using the ups and downs as the calculation basis, and according to the relative stocks
  • the correlation between individual stocks is calculated by score, and the correlation of a large number of invalid stocks is eliminated, so that the characteristics of the plate composed of similar stocks are obvious and meet the needs of users. Recognizing all stocks composed of various sectors as core stocks, and calculating stock market structure trend indicators on this basis, has a more clear indication, and will not cause the calculated indicators to have no practical use because of the indiscriminate treatment of all stocks. This improves the accuracy of the stock market trend analysis results and provides a clear logical basis for practical applications.
  • FIG. 4 is a schematic structural diagram of a stock market trend analysis system based on a stock correlation algorithm provided by another embodiment of the present invention.
  • the stock market trend analysis system exemplified in FIG. 4 is built into the electronic device and is the main body of the stock market trend analysis method based on the stock correlation algorithm provided by the embodiments shown in FIGS. 1 to 2.
  • the stock market trend analysis system based on the stock correlation algorithm in this embodiment is different from the stock market trend analysis system based on the stock correlation algorithm in the embodiment shown in FIG. 3 mainly in:
  • the standardization module 301 is also used to sort the rise and fall of all stocks from large to small, taking the median or preset percentile of individual stocks as the center point of standardization; calculate the rise and fall of all stocks The standard deviation of the amplitude; and, multiplying the standard deviation by the first preset coefficient as the first standardized step size, then the relative score of each individual stock is an integer multiple of the first standardized step size, where The value is within the preset range.
  • the correlation calculation module 302 is further used to calculate the correlation coefficient between any two stocks according to the relative score of the stocks in the first preset time period.
  • the plate calculation module 303 is further configured to form a relationship pair of the stocks whose correlation coefficient reaches the first preset value; process all the relationship pairs through a connected graph algorithm, and use each connection formed after the processing as the plate.
  • the core stock confirmation module 304 is also used to add up individual stocks in each sector in the first preset time period and remove duplicate stocks to obtain core stocks, which include relatively rising core stocks and relatively falling core stocks;
  • the relatively rising core stocks are the core stocks whose relative score is greater than 0 on that day
  • the relatively falling core stocks are the core stocks whose relative score is less than 0 on that day.
  • the analysis module 305 also includes an indicator analysis module 3051 and a passive rise and fall analysis module 3052.
  • the index analysis module 3051 is used to calculate the stock market core quantity index within the preset period based on the confirmed core stocks
  • the index analysis module 3051 is also used to calculate the trend correlation of each core stock based on the confirmed core stocks, and calculate the market structure index according to the trend correlation;
  • Passive change analysis module 3052 used to calculate the passive change of target stocks
  • the passive ups and downs analysis module 3052 is also used to calculate the passive ups and downs scores of target stocks.
  • the indicator analysis module 3051 is also used to calculate the recurring core stocks within the second preset time period; add up the number of recurrences, and add up the total number of times that the core stocks that have risen relatively to the relative decline The difference in the total number of times the core stocks are added is used as an indicator of the number of core stocks in the stock market; and, based on the threshold value of the core stock's individual stock market value and the individual stock's total market value, the core stock is divided into large stocks, medium stocks, and small stocks, and the The stock market core quantity indexes of the large stock, the medium stock and the small stock are correspondingly divided into a large stock core quantity index, a medium stock core quantity index and a small stock core quantity index.
  • the index analysis module 3051 is also used to calculate the correlation coefficient of the core shares of the day and each other core stock within the preset historical date according to the relative score of the individual shares of the core shares; the average of all correlation coefficients is taken as the average correlation Coefficient, the average correlation coefficient is compared with the second preset value to obtain the trend correlation of the core stocks; and, the average value of the trend correlation of all core stocks on the day is used as the market structure index for the day.
  • the passive ups and downs analysis module 3052 is also used to calculate the correlation coefficient of the target individual stock and the large stock, and calculate the product of the correlation coefficient and the increase and decrease of the large stock on the day to obtain the passive increase and decrease of the target stock.
  • the big stock refers to the big stock in the core stock.
  • the passive ups and downs analysis module 3052 is also used to sort the passive ups and downs of all stocks from large to small, and take the passive ups and downs of the median or preset percentile stocks as the standardized central point to calculate The standard deviation of the passive rise and fall of all stocks, the standard deviation is multiplied by the second preset coefficient as the second standardized step, then the passive rise and fall score of the individual stock is an integer multiple of the second standardized step, where, The passive stock ups and downs points are within the preset range.
  • individual stocks' ups and downs are normalized to individual stocks' relative scores.
  • the actual effect is more effective than directly using the ups and downs as the calculation basis, and according to the relative stocks
  • the correlation between individual stocks is calculated by score, and the correlation of a large number of invalid stocks is eliminated, so that the characteristics of the plate composed of similar stocks are obvious and meet the needs of users. Recognizing all stocks composed of various sectors as core stocks, and calculating stock market structure trend indicators on this basis, has a more clear indication, and will not cause the calculated indicators to have no practical use because of the indiscriminate treatment of all stocks.
  • this embodiment also provides an electronic device, including:
  • Memory, processor, and computer program stored on the memory and executable on the processor, when the processor executes the computer program, the stock market trend based on the stock correlation algorithm described in the embodiments shown in FIG. 1 and FIG. 2 is realized Analytical method.
  • the electronic device further includes:
  • At least one input device and at least one output device are At least one input device and at least one output device.
  • the above-mentioned memory, processor, input device and output device are connected via a bus.
  • the input device may specifically be a camera, a touch panel, a physical button, a mouse, or the like.
  • the output device may be a display screen.
  • Memory can be high-speed random access memory (RAM, Random Access Memory) can also be non-volatile memory (non-volatile memory), such as disk storage.
  • RAM Random Access Memory
  • non-volatile memory such as disk storage.
  • the memory is used to store a set of executable program code, and the processor is coupled to the memory.
  • an embodiment of the present invention further provides a computer-readable storage medium
  • the computer-readable storage medium may be the memory in the foregoing embodiments.
  • a computer program is stored on the computer-readable storage medium. When the program is executed by the processor, the stock market trend analysis method based on the stock correlation algorithm described in the foregoing embodiments shown in FIGS. 1 and 2 is implemented.
  • the computer-storable medium may also be various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk, or an optical disk.
  • the disclosed method and system may be implemented in other ways.
  • the above-described embodiments are only schematic.
  • the division of the modules is only a division of logical functions.
  • there may be other divisions for example, multiple modules or components may be combined or may Integration into another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication link may be through some interfaces, and the indirect coupling or communication link of the module may be in electrical, mechanical, or other forms.
  • modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or software function modules.

Abstract

一种基于股票相关性算法的股市趋势分析方法和系统，属于数据处理技术领域。其中，该方法包括：计算当日个股涨跌幅，并将个股涨跌幅标准化为个股相对分值，根据个股相对分值计算个股之间的相关性，根据个股之间的相关性，按照预设算法计算相似个股组成的板块，将板块中的个股确认为核心股，根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出该股市结构趋势指标。上述基于股票相关性算法的股市趋势分析方法和系统，可提高股市发展趋势分析的准确性。

Description

一种基于股票相关性算法的股市趋势分析方法和系统 技术领域
本发明属于数据处理技术领域，尤其涉及一种基于股票相关性算法的股市趋势分析方法和系统。
 背景技术
个股的发展趋势是证券投资的重要研究目标，通过股票分析软件，可以提供股市相关指数和个股的发展趋势，目前有很多种算法可以得出股票类数据的发展趋势，一般都是通过个股的涨跌幅的规律进行分析，但是基于个股的涨跌幅得到的分析结果会因为偶然性而不够准确。
 技术问题
本发明实施例提供一种基于股票相关性算法的股市趋势分析方法和系统，以解决计算股市趋势时结果不够准确的问题。
 技术解决方案
本发明实施例提供了一种基于股票相关性算法的股市趋势分析方法，包括：
计算当日个股涨跌幅，并将所述个股涨跌幅标准化为个股相对分值；
根据所述个股相对分值计算个股之间的相关性；
根据所述个股之间的相关性，按照预设算法计算相似个股组成的板块；
将所述板块中的个股确认为核心股；
根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出所述股市结构趋势指标。
本发明实施例还提供了一种基于股票相关性算法的股市趋势分析系统，包括：
标准化模块，用于计算当日个股涨跌幅，并将所述个股涨跌幅标准化为个股相对分值；
相关性计算模块，用于根据所述个股相对分值计算个股之间的相关性；
板块计算模块，用于根据所述个股之间的相关性，按照预设算法计算相似个股组成的板块；
核心股确认模块，用于将所述板块中的个股确认为核心股；
分析模块，用于根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出所述股市结构趋势指标。
 有益效果
本发明实施例中，将当日的个股涨跌幅标准化为个股相对分值，使用标准化后的涨跌幅作为个股相关性的计算基础，实际效果比直接使用涨跌幅作为计算基础更有效，并且根据个股相对分值计算个股之间的相关性，则剔除了大量无效的个股相关性，使得相似个股组成的板块特征明显，并符合用户需求。将各板块构成的所有个股确认为核心股，并在此基础上计算出股市结构趋势指标，则有着更明确的指示意义，不会因为无差别对待所有个股而导致所计算的指标没有实际用途，从而提高股市趋势分析结果的准确性，并且为实际应用提供了明确的逻辑基础。
 附图说明
图1是本发明一实施例提供的基于股票相关性算法的股市趋势分析方法的实现流程示意图；
图2是本发明另一实施例提供的基于股票相关性算法的股市趋势分析方法的实现流程示意图；
图3是本发明一实施例提供的基于股票相关性算法的股市趋势分析系统的结构示意图；
图4是本发明另一实施例提供的基于股票相关性算法的股市趋势分析系统的结构示意图。
 本发明的实施方式
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而非全部实施例。基于本发明中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
请参阅图1，图1为本发明一实施例提供的基于股票相关性算法的股市趋势分析方法的实现流程示意图，该方法可应用于电子装置中，电子装置可包括：智能手机、平板电脑等可在移动中使用的电子装置以及PC（personal computer）机等非移动中使用的电子装置。如图1所示，该方法主要包括以下步骤：
S101、计算当日个股涨跌幅，并将个股涨跌幅标准化为个股相对分值；
具体地，计算当日的每个个股的涨跌幅，将所有个股的涨跌幅从大到小排序，取中位数或者预置百分位个股的涨跌幅作为标准化的中心点。
计算所有个股的涨跌幅的标准差（Standard Deviation），标准差是在概率统计中最常使用作为统计分布程度（statistical dispersion）上的测量。标准差定义为方差的算术平方根，反映组内个体间的离散程度。
将计算出的标准差乘以第一预设系数作为第一标准化步长，该第一预设系数可以是整数，也可以不是整数，例如可以取1、2、3等整数，亦可以取0.8、0.9等非整数，优选地，该第一预设系数为0.8；以该标准化的中心点为起点，将该第一标准化步长的整数倍数作为每个个股的该个股相对分值，即该倍数为整数，例如，从中心点出发，该第一标准化步长1倍范围内该个股相对分值设定为0；该标准化步长1~2倍范围内该个股相对分值设定为1；其中，该个股相对分值在一个预设范围之内，具体如4~-4，或者，5~-5，可根据计算自定义。
个股相对分值的计算实例如下：
例如2018年11月26日，经过计算全市场中心点为0.45，标准差为2.0378，取标准差的0.8倍作为第一标准化步长，则第一标准化步长为1.6302。
1、个股A涨跌幅为-10%，则其个股相对分值为：
（-10-0.45）/1.6302=-6.41
系统规定个股相对分值的范围为-4到4之间的情况下，则个股A的个股相对分值取值为-4。
2、个股B涨跌幅为6.03%，则其个股相对分值为：
（6.03-0.45）/1.6302=3.42
则个股B的个股相对分值取值为3。
S102、根据个股相对分值计算个股之间的相关性；
具体地，根据在第一预设时间段中的个股相对分值，计算任意两个个股之间的相关系数（Correlation coefficient）。
相关系数是用以反映变量之间相关关系密切程度的统计指标。相关系数是按积差方法计算，同样以两变量与各自平均值的离差为基础，通过两个离差相乘来反映两变量之间相关程度。相关系数的大小在-1~1之间。
该第一预设时间段可以是20天，或者40天、60天等。
该第一预设时间段可以有多个，例如，第一个第一预设时间段可以是20天，第二个第一预设时间段可以是40天，则根据该20天和该40天的个股相对分值，计算任意两个个股之间的相关系数。
S103、根据个股之间的相关性，按照预设算法计算相似个股组成的板块；
具体地，将相关系数达到第一预设值的个股构成关系对，该第一预设值例如为0.5；
该预设算法例如连通图算法，通过连通图算法处理所有的关系对，将处理后形成的各个连通作为相似个股组成的板块。
每个板块至少包含2支个股。
相似个股构成的板块的计算是动态的，只与个股的实际涨跌和K线运行有关，而与个股的实际基本面、主营业务没有关系。
S104、将板块中的个股确认为核心股；
以基于该第一预设时间段中的板块运算结果作为基准，把所有进入到各板块内的个股作为核心股。没有进入板块的个股则剔除。
将第一预设时间段的各板块中的个股加总并剔除重复个股，得到核心股，该核心股包括相对上涨的核心股和相对下跌的核心股，其中，该相对上涨的核心股为当日个股相对分值大于0的核心股，该相对下跌的核心股为当日个股相对分值小于0的核心股。
该第一预设时间段可以为多个，按照每个第一预设时间段计算的板块中的个股加总处理，在任一个第一预设时间段进入到板块中的都是核心股，剔除掉重复的个股，得到所有核心股。
S105、根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出该股市结构趋势指标。
股市结构趋势指标是指能够反映股市的市场结构趋势的指标，可包括：股市核心数量指标和市场结构指标。
具体地，根据确认的核心股，计算在预设周期内的股市结构趋势指标。具体可以包括：根据确认的核心股，计算在该预设周期内的股市核心数量指标；还可以包括：根据确认的核心股，计算各核心股的趋势相关度，并根据该趋势相关度计算市场结构指标。需要说明的是，在步骤S104之后，步骤S105中的计算股市核心数量指标和计算市场结构指标，可以单独或共同计算，它们中的任意一个均可以指示股市的发展趋势。
其中，根据确认的核心股，计算股市核心数量指标具体是：计算第二预设时间段内重复出现的核心股，该第二预设时间段例如10天。
将重复出现的次数加总，并将相对上涨的核心股加总得到的次数总和与相对下跌的核心股加总得到的次数总和的差值作为股市核心数量指标；
个股总市值作为将核心股区分为大股票、中股票和小股票的标准，具体地，根据核心股的个股市值与个股总市值的界定阈值，将核心股划分为大股票、中股票和小股票，例如，占全市场总市值前30%的核心股作为大股票，后30%作为小股票，二者之间的核心股则为中股票。
并将大股票、中股票和小股票的股市核心数量指标对应划分为大股票核心数量指标、中股票核心数量指标和小股票核心数量指标。
根据确认的核心股，计算各核心股的趋势相关度，并根据趋势相关度计算市场结构指标具体为：
在计算一个核心股的趋势相关度时，根据该核心股的个股相对分值，计算当日的该核心股与预设历史日期内的各其他核心股的相关系数，其中，预设历史日期例如过去的10天，15天，20天等。
取全部相关系数的平均值作为平均相关系数，将该平均相关系数与第二预设值进行比较，得到该核心股的趋势相关度，该趋势相关度可以自行定义范围，具体地，本实施例中，该趋势相关度是被自定义在0~4范围内的分值。
当日所有核心股的趋势相关度的平均值，则作为当日市场结构指标。市场结构指标最终表现为0~4之间的数值，每日连续读数。
进一步地，使用与上述区分大股票、中股票和小股票的方式相同，以个股总市值为划分标准，计算出大股票结构指标和/或中股票结构指标，作为投资用户的参考。
本实施例中，将个股涨跌幅标准化为个股相对分值，使用标准化后的涨跌幅作为个股相关性的计算基础，实际效果比直接使用涨跌幅作为计算基础更有效，并且根据个股相对分值计算个股之间的相关性，则剔除了大量无效的个股相关性，使得相似个股组成的板块特征明显，并符合用户需求。将各板块构成的所有个股确认为核心股，并在此基础上计算出股市结构趋势指标，则有着更明确的指示意义，不会因为无差别对待所有个股而导致所计算的指标没有实际用途，从而提高股市趋势分析结果的准确性，并且为实际应用提供了明确的逻辑基础。
进一步地，在另一个实施例中，步骤S104中，将板块中的个股确认为核心股，具体为：步骤S204：将该第一预设时间段中的各板块中的个股加总并剔除重复个股，得到核心股，该核心股包括相对上涨的核心股和相对下跌的核心股。
进一步地，计算目标个股的被动涨跌幅，以及，根据目标个股的被动涨跌幅计算被动涨跌分值。
S206、计算目标个股的被动涨跌幅；
将目标个股与上述得出的大股票核心股计算相关性，计算相关性即为计算二者的相关系数，方法参见前述步骤S102的相关描述，并以相关系数乘以大股票核心股当日的涨跌幅，即为该目标个股当日的被动涨跌幅。目标个股即为要计算被动涨跌幅的个股，可以计算出所有个股的被动涨跌幅。
S207、计算目标个股的被动涨跌分值；
进一步地，还可以根据该被动涨跌幅计算目标个股的被动涨跌分值，具体地，将被动涨跌幅以与步骤S101相同的标准化方法，计算出个股相对分值，即为个股的被动涨跌分值。具体地，将所有个股的被动涨跌幅从大到小排序，取中位数或者预置百分位个股的被动涨跌幅作为标准化的中心点，计算所有个股的被动涨跌幅的标准差，将该标准差乘以第二预设系数作为第二标准化步长，则个股的被动涨跌分值为该第二标准化步长的整数倍数，该第二预设系数可以与前述该第一预设系数相同，也可以不同。其中，个股的被动涨跌分值在该预设范围之内，该预设范围可以具体为4~-4等。
需要说明的是，步骤S206可以在步骤S104之后单独执行，也可以与步骤S105共同执行，步骤S206中的个股被动涨跌幅和步骤S207中的个股被动涨跌分值是指示个股的发展趋势。步骤S105中的计算股市核心数量指标和计算市场结构指标，是指示全市场的发展趋势。个股被动涨跌幅、个股的被动涨跌分值、股市核心数量指标和市场结构指标可以共同为用户指示个股和市场的发展趋势。
本实施例中，根据个股涨跌幅将个股标准化为个股相对分值，使用标准化后的涨跌幅作为个股相关性的计算基础，实际效果比直接使用涨跌幅作为计算基础更有效，并且根据个股相对分值计算个股之间的相关性，则剔除了大量无效的个股相关性，使得相似个股组成的板块特征明显，并符合用户需求。将各板块构成的所有个股确认为核心股，并在此基础上计算出股市核心数量指标和市场结构指标，则有着更明确的指示意义，不会因为无差别对待所有个股而导致所计算的指标没有实际用途，从而提高股市趋势分析结果的准确性，也为实际应用提供了明确的逻辑基础。并且，计算的个股被动涨跌幅以及被动涨跌分值，对于判定个股实际涨跌幅的性质、未来走向的估计有重要意义，可提高个股趋势数据分析的准确性。
请参阅图3，图3是本发明一实施例提供的基于股票相关性算法的股市趋势分析系统的结构示意图，为了便于说明，仅示出了与本发明实施例相关的部分。图3示例的基于股票相关性算法的股市趋势分析系统可置于该电子装置中，是前述图1所示实施例提供的基于股票相关性算法的股市趋势分析方法的执行主体。该系统主要包括：
标准化模块301、相关性计算模块302、板块计算模块303、核心股确认模块304和分析模块305；
其中，标准化模块301，用于计算当日个股涨跌幅，并将个股涨跌幅标准化为个股相对分值。
相关性计算模块302，用于根据该个股相对分值计算个股之间的相关性；
板块计算模块303，用于根据个股之间的相关性，按照预设算法计算相似个股组成的板块；
核心股确认模块304，用于将板块中的个股确认为核心股；
分析模块305，用于根据确认的核心股，计算在预设周期内股市结构趋势指标，并以预设形式输出该股市结构趋势指标。
本实施例未尽之细节，请参阅前述图1所示实施例的描述，此处不再赘述。
需要说明的是，以上图3示例的基于股票相关性算法的股市趋势分析系统的实施方式中，各功能模块的划分仅是举例说明，实际应用中可以根据需要，例如相应硬件的配置要求或者软件的实现的便利考虑，而将上述功能分配由不同的功能模块完成，即将电子装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。而且，实际应用中，本实施例中的相应的功能模块可以是由相应的硬件实现，也可以由相应的硬件执行相应的软件完成。本说明书提供的各个实施例都可应用上述描述原则，以下不再赘述。
本实施例中，将个股涨跌幅标准化为个股相对分值，使用标准化后的涨跌幅作为个股相关性的计算基础，实际效果比直接使用涨跌幅作为计算基础更有效，并且根据个股相对分值计算个股之间的相关性，则剔除了大量无效的个股相关性，使得相似个股组成的板块特征明显，并符合用户需求。将各板块构成的所有个股确认为核心股，并在此基础上计算出股市结构趋势指标，则有着更明确的指示意义，不会因为无差别对待所有个股而导致所计算的指标没有实际用途，从而提高股市趋势分析结果的准确性，并且为实际应用提供了明确的逻辑基础。
请参阅图4，本发明另一实施例提供的基于股票相关性算法的股市趋势分析系统的结构示意图，为了便于说明，仅示出了与本发明实施例相关的部分。图4示例的股市趋势分析系统内置于该电子装置中，是前述图1~图2所示实施例提供的基于股票相关性算法的股市趋势分析方法的执行主体。本实施例中的基于股票相关性算法的股市趋势分析系统，与图3所示实施例中的基于股票相关性算法的股市趋势分析系统的不同之处主要在于：
进一步地，标准化模块301，还用于将所有个股的涨跌幅从大到小排序，取中位数或者预置百分位个股的涨跌幅作为标准化的中心点；计算所有个股的涨跌幅的标准差；以及，将该标准差乘以第一预设系数作为第一标准化步长，则每个个股的个股相对分值为该第一标准化步长的整数倍数，其中，个股相对分值在预设范围之内。
相关性计算模块302，还用于根据在第一预设时间段中的该个股相对分值，计算任意两个个股之间的相关系数。
板块计算模块303，还用于将该相关系数达到第一预设值的个股构成关系对；通过连通图算法处理所有该关系对，将处理后形成的各个连通作为该板块。
核心股确认模块304，还用于将第一预设时间段中的各板块中的个股加总并剔除重复个股，得到核心股，该核心股包括相对上涨的核心股和相对下跌的核心股；
其中，相对上涨的核心股为当日该个股相对分值大于0的核心股，相对下跌的核心股为当日该个股相对分值小于0的核心股。
分析模块305还包括：指标分析模块3051和被动涨跌分析模块3052。
指标分析模块3051，用于根据确认的核心股，计算在所述预设周期内的股市核心数量指标；
指标分析模块3051，还用于根据确认的核心股，计算各核心股的趋势相关度，并根据趋势相关度计算市场结构指标；
被动涨跌分析模块3052，用于计算目标个股的被动涨跌幅；
被动涨跌分析模块3052，还用于计算目标个股的被动涨跌分值。
进一步地，指标分析模块3051，还用于计算第二预设时间段内重复出现的核心股；将重复出现的次数加总，并将相对上涨的核心股加总得到的次数总和与相对下跌的核心股加总得到的次数总和的差值作为股市核心数量指标；以及，根据核心股的个股市值与个股总市值的界定阈值，将核心股划分为大股票、中股票和小股票，并将所述大股票、所述中股票和所述小股票的股市核心数量指标对应划分为大股票核心数量指标、中股票核心数量指标和小股票核心数量指标。
进一步的，指标分析模块3051，还用于根据核心股的个股相对分值，计算当日的核心股与预设历史日期内的各其他核心股的相关系数；取全部相关系数的平均值作为平均相关系数，将该平均相关系数与第二预设值进行比较，得到核心股的趋势相关度；以及，将当日的所有核心股的趋势相关度的平均值，作为当日市场结构指标。
被动涨跌分析模块3052，还用于计算目标个股与大股票的相关系数，并计算该相关系数与该大股票当日的涨跌幅的乘积，得到该目标个股当日的被动涨跌幅。该大股票是指核心股中的大股票。
进一步地，被动涨跌分析模块3052，还用于将所有个股的被动涨跌幅从大到小排序，取中位数或者预置百分位个股的被动涨跌幅作为标准化的中心点，计算所有个股的被动涨跌幅的标准差，将该标准差乘以第二预设系数作为第二标准化步长，则个股的被动涨跌分值为该第二标准化步长的整数倍数，其中，个股的被动涨跌分值在该预设范围之内。
本实施例未尽之细节，请参阅前述图1~图3所示实施例的描述，此处不再赘述。
本实施例中，将个股涨跌幅标准化为个股相对分值，使用标准化后的涨跌幅作为个股相关性的计算基础，实际效果比直接使用涨跌幅作为计算基础更有效，并且根据个股相对分值计算个股之间的相关性，则剔除了大量无效的个股相关性，使得相似个股组成的板块特征明显，并符合用户需求。将各板块构成的所有个股确认为核心股，并在此基础上计算出股市结构趋势指标，则有着更明确的指示意义，不会因为无差别对待所有个股而导致所计算的指标没有实际用途，从而提高股市趋势分析结果的准确性，并且为实际应用提供了明确的逻辑基础。并且，计算的个股被动涨跌幅以及被动涨跌分值，对于判定个股实际涨跌幅的性质、未来走向的估计有重要意义，可提高个股趋势数据分析的准确性。
进一步地，本实施例还提供了一种电子装置，包括：
存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行该计算机程序时，实现前述图1和图2所示实施例中描述的基于股票相关性算法的股市趋势分析方法。
进一步的，该电子装置还包括：
至少一个输入设备以及至少一个输出设备。
上述存储器、处理器、输入设备以及输出设备，通过总线连接。
其中，输入设备具体可为摄像头、触控面板、物理按键或者鼠标等等。输出设备具体可为显示屏。
存储器可以是高速随机存取记忆体（RAM，Random Access Memory）存储器，也可为非不稳定的存储器（non-volatile memory），例如磁盘存储器。存储器用于存储一组可执行程序代码，处理器与存储器耦合。
进一步的，本发明实施例还提供了一种计算机可读存储介质，该计算机可读存储介质可以是前述实施例中的存储器。该计算机可读存储介质上存储有计算机程序，该程序被处理器执行时实现前述图1和图2所示实施例中描述的基于股票相关性算法的股市趋势分析方法。进一步的，该计算机可存储介质还可以是U盘、移动硬盘、只读存储器（ROM，Read-Only Memory）、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
Figure 381523dest_path_image001
在本申请所提供的多个实施例中，应该理解到，所揭露的方法和系统，可以通过其它的方式实现。例如，以上所描述的实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信链接可以是通过一些接口，模块的间接耦合或通信链接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
需要说明的是，对于前述的各方法实施例，为了简便描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其它顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定都是本发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其它实施例的相关描述。
以上为对本发明所提供的基于股票相关性算法的股市趋势分析方法和基于股票相关性算法的股市趋势分析系统的描述，对于本领域的技术人员，依据本发明实施例的思想，在具体实施方式及应用范围上均会有改变之处，综上，本说明书内容不应理解为对本发明的限制。

Claims (11)

  1. 一种基于股票相关性算法的股市趋势分析方法，其特征在于，所述方法包括：
    计算当日个股涨跌幅，并将所述个股涨跌幅标准化为个股相对分值；
    根据所述个股相对分值计算个股之间的相关性；
    根据所述个股之间的相关性，按照预设算法计算相似个股组成的板块；
    将所述板块中的个股确认为核心股；
    根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出所述股市结构趋势指标。
  2. 如权利要求1所述的方法，其特征在于，所述将所述个股涨跌幅标准化为个股相对分值包括：
    将所有个股的涨跌幅从大到小排序，取中位数或者预置百分位个股的涨跌幅作为标准化的中心点；
    计算所有个股的涨跌幅的标准差；
    将所述标准差乘以第一预设系数作为第一标准化步长，则每个个股的所述个股相对分值为所述第一标准化步长的整数倍数，其中，所述个股相对分值在预设范围之内。
  3. 如权利要求2所述的方法，其特征在于，所述根据所述个股相对分值计算个股之间的相关性包括：
    根据在第一预设时间段中的所述个股相对分值，计算任意两个个股之间的相关系数。
  4. 如权利要求3所述的方法，其特征在于，所述根据所述个股之间的相关性，按照预设算法计算相似个股组成的板块包括：
    将所述相关系数达到第一预设值的个股构成关系对；
    通过连通图算法处理所有所述关系对，将处理后形成的各个连通作为所述板块。
  5. 如权利要求4所述的方法，其特征在于，所述将所述板块中的个股确认为核心股包括：
    将所述第一预设时间段中的各所述板块中的个股加总并剔除重复个股，得到所述核心股，所述核心股包括相对上涨的核心股和相对下跌的核心股；
    其中，所述相对上涨的核心股为当日所述个股相对分值大于0的核心股，所述相对下跌的核心股为当日所述个股相对分值小于0的核心股。
  6. 如权利要求5所述的方法，其特征在于，所述计算在预设周期内的股市结构趋势指标，并以预设形式输出所述股市结构趋势指标包括：
    根据确认的核心股，计算在所述预设周期内的股市核心数量指标；
    和/或，
    根据确认的核心股，计算各核心股的趋势相关度，并根据所述趋势相关度计算市场结构指标。
  7. 如权利要求6所述的方法，其特征在于，所述根据确认的核心股，计算在所述预设周期内的股市核心数量指标包括：
    计算第二预设时间段内重复出现的核心股；
    将重复出现的次数加总，并将相对上涨的核心股加总得到的次数总和与相对下跌的核心股加总得到的次数总和的差值作为所述股市核心数量指标；
    根据核心股的个股市值与个股总市值的界定阈值，将核心股划分为大股票、中股票和小股票，并将所述大股票、所述中股票和所述小股票的股市核心数量指标对应划分为大股票核心数量指标、中股票核心数量指标和小股票核心数量指标。
  8. 如权利要求7所述的方法，其特征在于，所述根据确认的核心股，计算各核心股的趋势相关度，并根据所述趋势相关度计算市场结构指标包括：
    根据所述核心股的个股相对分值，计算当日的所述核心股与预设历史日期内的各其他核心股的相关系数；
    取全部相关系数的平均值作为平均相关系数，将所述平均相关系数与第二预设值进行比较，得到所述核心股的趋势相关度；
    将当日的所有核心股的趋势相关度的平均值，作为当日市场结构指标。
  9. 如权利要求8所述的方法，其特征在于，所述将相对上涨的核心股加总得到的次数总和与相对下跌的核心股加总得到的次数总和的差值作为所述股市核心数量指标之后包括：
    计算目标个股与所述大股票的相关系数，并计算所述相关系数与所述大股票当日的涨跌幅的乘积，得到所述目标个股当日的被动涨跌幅。
  10. 如权利要求9所述的方法，其特征在于，计算所述相关系数与所述大股票当日的涨跌幅的乘积，得到所述目标个股当日的被动涨跌幅之后包括：
    将所有个股的被动涨跌幅从大到小排序；
    取中位数或者预置百分位个股的被动涨跌幅作为标准化的中心点，计算所有个股的被动涨跌幅的标准差；
    将所述被动涨跌幅的标准差乘以第二预设系数作为第二标准化步长，则个股的被动涨跌分值为所述第二标准化步长的整数倍数。
  11. 一种基于股票相关性算法的股市趋势分析系统，应用于电子装置中，其特征在于，包括：
    标准化模块，用于计算当日个股涨跌幅，并将所述个股涨跌幅标准化为个股相对分值；
    相关性计算模块，用于根据所述个股相对分值计算个股之间的相关性；
    板块计算模块，用于根据所述个股之间的相关性，按照预设算法计算相似个股组成的板块；
    核心股确认模块，用于将所述板块中的个股确认为核心股；
    分析模块，用于根据确认的核心股，计算在预设周期内的股市结构趋势指标，并以预设形式输出所述股市结构趋势指标。
     
PCT/CN2018/122844 2018-12-21 2018-12-21 一种基于股票相关性算法的股市趋势分析方法和系统 WO2020124594A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/122844 WO2020124594A1 (zh) 2018-12-21 2018-12-21 一种基于股票相关性算法的股市趋势分析方法和系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/122844 WO2020124594A1 (zh) 2018-12-21 2018-12-21 一种基于股票相关性算法的股市趋势分析方法和系统

Publications (1)

Publication Number Publication Date
WO2020124594A1 true WO2020124594A1 (zh) 2020-06-25

Family

ID=71099999

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/122844 WO2020124594A1 (zh) 2018-12-21 2018-12-21 一种基于股票相关性算法的股市趋势分析方法和系统

Country Status (1)

Country Link
WO (1) WO2020124594A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110320383A1 (en) * 2010-06-24 2011-12-29 Cherng Chang Stock market filters
CN105956703A (zh) * 2016-05-05 2016-09-21 南京邮电大学 一种基于马尔科夫的股价走势预测方法和系统
CN107918813A (zh) * 2017-12-14 2018-04-17 上海宽全智能科技有限公司 趋势预测分析方法、设备及存储介质
CN108536748A (zh) * 2018-03-12 2018-09-14 上海宽全智能科技有限公司 板块相关性地图显示方法、设备及存储装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110320383A1 (en) * 2010-06-24 2011-12-29 Cherng Chang Stock market filters
CN105956703A (zh) * 2016-05-05 2016-09-21 南京邮电大学 一种基于马尔科夫的股价走势预测方法和系统
CN107918813A (zh) * 2017-12-14 2018-04-17 上海宽全智能科技有限公司 趋势预测分析方法、设备及存储介质
CN108536748A (zh) * 2018-03-12 2018-09-14 上海宽全智能科技有限公司 板块相关性地图显示方法、设备及存储装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHANG, LAIJUN ET AL.: "Empirical Analysis of Relevance of Stock Indicators Based on Complex Network Theory", CHINESE JOURNAL OF MANAGEMENT SCIENCE, vol. 22, no. 12, 31 December 2014 (2014-12-31), XP055715607, ISSN: 1003-207X *

Similar Documents

Publication Publication Date Title
CN107679946B (zh) 基金产品推荐方法、装置、终端设备及存储介质
Azizi et al. Slacks-based measures of efficiency in imprecise data envelopment analysis: An approach based on data envelopment analysis with double frontiers
CN110751326B (zh) 一种光伏日前功率预测方法、装置以及存储介质
TW202004636A (zh) 保險服務優化方法、系統及電腦程式產品
WO2023103527A1 (zh) 一种访问频次的预测方法及装置
CN115358866A (zh) 一种投资风险预估系统
Hwang et al. A logistic regression point of view toward loss given default distribution estimation
CN108596493A (zh) 拆单式交易方法及装置
CN110033165A (zh) 逾期借款催收方式的推荐方法、装置、介质、电子设备
WO2020124594A1 (zh) 一种基于股票相关性算法的股市趋势分析方法和系统
Huang et al. The strategy of investment in the stock market using modified support vector regression model
WO2020199483A1 (zh) 金融数据的图像处理方法、装置、设备及计算机可读存储介质
Xu et al. Web mining for financial market prediction based on online sentiments
Boccanfuso et al. Parametric and nonparametric income distribution estimators in CGE micro-simulation modeling
CN114723481A (zh) 数据处理方法、装置、电子设备和存储介质
CN114240599A (zh) 贷款测算方法、装置、计算机设备和存储介质
CN114385460A (zh) 数据稳定性的检测方法及装置、存储介质
US11010368B1 (en) Writing incoming items to a database based on location of similar items in a database
WO2020037922A1 (zh) 股指预测方法、装置及存储介质
CN110852392A (zh) 一种用户分群方法、装置、设备和介质
Das et al. A semi-parametric Bayesian dynamic hurdle model with an application to the health and retirement study
CN112070593B (zh) 数据处理方法、装置、设备以及存储介质
CN114240653A (zh) 一种贵金属配对交易方法、装置、设备及可读存储介质
WO2022176281A1 (ja) 情報提供サーバ、データ処理装置、情報提供方法及びプログラム
Aggarwal et al. Distribution of extreme changes in Asian currencies: tail index estimates and value-at-risk calculations

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18943868

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18943868

Country of ref document: EP

Kind code of ref document: A1