Price form identification, analysis and recommendation method, device and program product

Abstract

The invention discloses a price form identification, analysis and recommendation method, device and program product, and the method comprises the steps: firstly obtaining price data, and building a price data set according to the price data; for each asset type in the price data set, obtaining a corresponding price change threshold index by using the price sequence data of the asset type; then, according to key nodes in the price sequence data, a price state sequence is constructed by using a price change threshold index; performing morphological event identification according to the price morphological characteristics of the price state sequence to obtain a price morphological event set; the monitored assets and the corresponding price form events are recommended to the user; and performing security price analysis processing by using the security price form event set to obtain a security price analysis result. According to the embodiment of the invention, the operation efficiency, controllability, interpretability and data noise resistance of price recognition analysis are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pattern recognition, and in particular to a price pattern recognition, analysis, and recommendation method, device, and program product. Background Art

[0002] As the scale of the domestic securities market continues to expand, the level of participation in securities trading continues to increase. Traditional trading methods rely on traders to manually observe price data and make subjective trading decisions. This subjective trading method has low execution efficiency, lacks stable decision-making standards, and is difficult to conduct scientific and accurate re-analysis, causing widespread economic losses to investors. Using computers to collect, analyze, assist in decision-making and conduct statistical analysis of securities data can effectively increase the accuracy and scientificity of investment strategies, improve investment returns, and accurately grasp return expectations.

[0003] Technical analysis is an important method in securities trading. Its purpose is to find the right time to invest in the asset price series and guide investors to obtain economic benefits. Common solutions on the market usually include two categories. The first category is the traditional method based on manual technical indicator analysis. This type of method relies on human subjective experience and judgment, and has low accuracy and efficiency. The second category is an interdisciplinary method that includes statistical analysis, image recognition analysis, deep neural network models and other methods. This type of method often ignores the important financial characteristics of price data, has poor controllability and interpretability, and has high requirements for the quantity and quality of data sets, making it difficult for investors to use.

[0004] Therefore, it is urgent to invent a new method for asset price pattern recognition and securities price analysis to solve the problems of low efficiency, poor controllability and interpretability, and poor resistance to data noise in existing recognition and analysis technologies. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a price pattern recognition, analysis, and recommendation method, device, and program product, which at least partially solve the problems existing in the prior art.

[0006] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0007] In order to achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] According to a first aspect of an embodiment of the present invention, a price pattern recognition method is provided, the method comprising:

[0009] Acquire price data, and establish a price data set according to the price data;

[0010] For each asset type in the price data set, using the price series data of the asset type, obtain a corresponding price change threshold indicator;

[0011] According to the key nodes in the price sequence data, the price change threshold indicator is used to construct a price state sequence;

[0012] The pattern events are identified according to the price pattern characteristics of the price state sequence to obtain a price pattern event set.

[0013] Furthermore, the price change threshold indicators include average true range (ATR) and yield standard deviation.

[0014] Furthermore, according to the key nodes in the price sequence data, the price change threshold indicator is used to construct a price state sequence, including:

[0015] Take the first price node of the price series as the initial node;

[0016] For each price node in the price sequence except the initial node, scan them one by one according to the time axis. If the closing price of the current price node is greater than the closing price of the previous price node, the current price node is taken as the first high price node.

[0017] If the closing price of the current price node is less than the closing price of the previous price node, the current price node is taken as the first low price node;

[0018] By using the first high-price node and the first low-price node, a price state sequence of second high-price nodes and second low-price nodes alternating with each other is obtained.

[0019] Furthermore, it is characterized in that the price state sequence of the second high-price node and the second low-price node alternating with each other is obtained by using the first high-price node and the first low-price node, including:

[0020] For each first high-price node, determining whether the previous second price node of the current node is a high-price node, wherein the second price node includes a second high-price node and a second low-price node;

[0021] If the previous second price node of the current node is a high price node, the previous second price node of the current node is deleted, and the current node is used as the second highest price node;

[0022] If the previous second price node of the current node is not a high price node, the absolute value of the first price difference is calculated using the closing price of the previous second price node and the closing price of the current price sequence;

[0023] Determine whether the absolute value of the first price difference is greater than a price difference threshold, where the price difference threshold is calculated based on the price change threshold indicator and a preset price difference threshold multiplier;

[0024] If the absolute value of the first price difference is greater than the price difference threshold, the current node is used as the second lowest price node;

[0025] If the absolute value of the first price difference is not greater than the price difference threshold, the current node is not used as the second price node;

[0026] For each first low-price node, determine whether the previous second-price node of the current node is a low-price node;

[0027] If the previous second price node of the current node is a low price node, the previous second price node of the current node is deleted, and the current node is used as the second lowest price node;

[0028] If the previous second price node of the current node is not a low price node, the second price difference absolute value is calculated using the closing price of the previous second price node and the closing price of the current price sequence;

[0029] Determine whether the absolute value of the second price difference is greater than a price difference threshold;

[0030] If the absolute value of the second price difference is greater than the price difference threshold, the current node is taken as the second highest price node;

[0031] If the absolute value of the second price difference is not greater than the price difference threshold, the current node is not used as the second price node;

[0032] A price state sequence is obtained in which the second highest price node and the second lowest price node alternately occur.

[0033] Furthermore, according to the price pattern characteristics of the price state sequence, pattern event recognition is performed to obtain a price pattern event set, including:

[0034] For each asset class, determine the price pattern characteristics based on the current price of the asset class and the node characteristics and node relationships of the price state sequence;

[0035] Based on the preset price pattern rules, a price pattern event is obtained according to the price pattern characteristics;

[0036] Use all price pattern events to get the price pattern event set.

[0037] According to a second aspect of an embodiment of the present invention, a securities price analysis method is provided, the method comprising:

[0038] Using a price pattern recognition method as described in any one of the above items, pattern recognition is performed on securities price data to obtain a set of securities price pattern events;

[0039] The securities price pattern event set is used to perform securities price analysis and processing to obtain securities price analysis results.

[0040] Furthermore, the securities price pattern event set is used to perform securities price analysis and processing to obtain securities price analysis results, including:

[0041] For each security price pattern event in the security price pattern event set, characteristic indicators of the security price pattern event are calculated according to the opening point, opening time, closing point and closing time of the security price pattern event, and the characteristic indicators include rate of return, normalized rate of return and maximum drawdown rate;

[0042] For the set of securities price pattern events, statistically summarize the characteristic indicators according to the types of securities price pattern events to obtain the occurrence frequency indicators of securities price pattern events and profitability and risk indicators;

[0043] The occurrence frequency indicators include the number of occurrences of pattern events, the number of asset types covered by pattern events, and the distribution of pattern event occurrences;

[0044] The profitability and risk metrics include win rate, average return, average normalized return, and average maximum drawdown.

[0045] According to a third aspect of an embodiment of the present invention, a method for recommending price pattern events is provided, the method comprising:

[0046] Acquire price data in real time, and use a price pattern recognition method as described in any one of the above items to perform real-time price pattern event recognition on the monitored asset;

[0047] If a price pattern event of the monitored asset is identified, the monitored asset and the corresponding price pattern event are recommended to the investment user.

[0048] According to a fourth aspect of an embodiment of the present invention, a device is provided, the device comprising: a processor and a memory;

[0049] The memory is used to store one or more program instructions;

[0050] The processor is used to run one or more program instructions to execute the steps of a price pattern recognition method as described in any one of the above items, a securities price analysis method as described in any one of the above items, or a price pattern event recommendation method as described in any one of the above items.

[0051] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which, when executed by a computer, enable the computer to implement the steps of a price pattern recognition method as described in any one of the above items, a securities price analysis method as described in any one of the above items, or a price pattern event recommendation method as described in any one of the above items.

[0052] The embodiments of the present invention have the following advantages:

[0053] A price pattern recognition method provided by an embodiment of the present invention classifies the price status at each time point into rising and falling, and analyzes the price historical oscillation status, so as to assist users in interpreting the price trend of assets. A securities price analysis method provided by an embodiment of the present invention performs statistical analysis on securities price pattern events and uses historical data to analyze the frequency of occurrence, profitability, and risk level of price patterns, so as to assist users in discovering and selecting price patterns suitable for investment. A price pattern event recommendation method provided by an embodiment of the present invention can realize real-time monitoring of assets, timely recommend price pattern events, and assist users in making decisions on transaction timing, asset type screening, and major asset allocation.

[0054] The embodiments of the present invention effectively improve the recognition and analysis operation efficiency, controllability, interpretability and resistance to data noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0056] Figure 1 A schematic diagram of a flow chart of a price pattern recognition method provided by an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of a flow chart of a securities price analysis method provided by an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of a flow chart of a price pattern event recommendation method provided by an embodiment of the present invention;

[0059] Figure 4 A schematic diagram of the effect of price pattern recognition provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0062] In order to solve the defects of the prior art, the present invention provides an accurate and efficient method for price pattern recognition, securities price analysis and price pattern event recommendation. By adjusting the indicators and parameters of pattern recognition, investors can match price fluctuations under various scales and risk preferences, and perform price analysis for various trading scenarios. By specifying the characteristic parameters of price pattern rules, users can historically evaluate and recommend various patterns in real time, identify investment opportunities such as transaction timing, asset type configuration, and market timing of major asset classes that match their trading style, and effectively improve the efficiency of recognition and analysis, controllability and explainability, and resistance to data noise.

[0063] Figure 1 The figure shows a flow chart of a price pattern recognition method according to an embodiment of the present invention.

[0064] like Figure 1 As shown, the price pattern recognition method according to the embodiment of the present invention may include step S100, step S200, step S300 and step S400.

[0065] In step S100, price data is acquired, and a price data set is established according to the price data.

[0066] Specifically, the above steps include: obtaining and collating the price data of the target object through the Internet to establish a price data set.

[0067] Next, in step S200, for each asset type in the price data set, the corresponding price change threshold index is obtained using the price series data of the asset type.

[0068] Among them, the above-mentioned price change threshold indicators include the average true range ATR and the standard deviation of yield.

[0069] In step S300, the key nodes in the price sequence data are captured, and a price state sequence is constructed based on the key nodes in the price sequence data and using a price change threshold indicator.

[0070] The above steps specifically include: taking the first price node of the price sequence as the initial node init; scanning each price node in the price sequence except the initial node init one by one according to the time axis, if the closing price of the current price node is greater than the closing price of the previous price node, taking the current price node as the first high price node candidate_high; if the closing price of the current price node is less than the closing price of the previous price node, taking the current price node as the first low price node candidate_low.

[0071] Then, by using the first high-price node candidate_high and the first low-price node candidate_low, a price state sequence of the second high-price node and the second low-price node alternating is obtained, including:

[0072] For each first high-price node, determine whether the previous second price node of the current node is a high-price node, and the second price nodes include the second high-price node and the second low-price node; if the previous second price node of the current node is a high-price node, delete the previous second price node of the current node, and use the current node as the second high-price node; if the previous second price node of the current node is not a high-price node, use the closing price of the previous second price node and the closing price of the current price sequence to calculate the absolute value of the first price difference; determine whether the absolute value of the first price difference is greater than the price difference threshold, and the price difference threshold is calculated based on the price change threshold indicator and the preset price difference threshold multiplier; if the absolute value of the first price difference is greater than the price difference threshold, use the current node as the second low-price node; if the absolute value of the first price difference is not greater than the price difference threshold, do not use the current node as the second price node.

[0073] For each first low price node, determine whether the previous second price node of the current node is a low price node; if the previous second price node of the current node is a low price node, delete the previous second price node of the current node and use the current node as the second low price node; if the previous second price node of the current node is not a low price node, use the closing price of the previous second price node and the closing price of the current price sequence to calculate the absolute value of the second price difference; determine whether the absolute value of the second price difference is greater than the price difference threshold; if the absolute value of the second price difference is greater than the price difference threshold, use the current node as the second high price node; if the absolute value of the second price difference is not greater than the price difference threshold, do not use the current node as the second price node.

[0074] Finally, a price state sequence of the second highest price node and the second lowest price node alternating is obtained.

[0075] The embodiment of the present invention uses the above method to abstract the price time series into a price trend curve starting from the initial node init, with the second high price node high and the second low price node low alternating; the subsequence starting from the second high price node high and reaching the next node can be considered as a price trend descending interval; the subsequence starting from the second low price node low and reaching the next node can be considered as a trend rising interval.

[0076] In step S400, pattern events are identified based on the price pattern characteristics of the price state sequence to obtain a price pattern event set.

[0077] The above steps specifically include:

[0078] For each asset type, the price shape characteristics are determined based on the current price end of the asset type and the specific node characteristics of the N nodes before the current price end in the price state sequence and the relationship between the nodes.

[0079] Based on the price pattern rules pre-set by the user, price pattern events are identified according to the price pattern characteristics. Among them, common price patterns include double bottom pattern, double top pattern, head and shoulders top pattern, etc.

[0080] For example, the double bottom price pattern rule is defined as follows: the four nodes before the end of the current price line are A, B, C, and D; among them, node A is a high node, node B is a low node, node C is a high node, and the closing price is lower than node A, node D is a low node, and the closing price is higher than node B, and the price of the current price line end is higher than node C.

[0081] refer to Figure 4 , using the above double bottom price pattern rules, identify the end price line triggering the double bottom price pattern, record end as the pattern end price line, D as the pattern end node, record the sequence

[0082] [A,B,C,D,end] is a double bottom price pattern event. In addition, for price pattern events with the same termination node but different end times of the pattern termination price line, the one with the earliest end time of the pattern termination price line is taken.

[0083] Finally, all the identified price pattern events are used to obtain the price pattern event set.

[0084] In addition, the embodiment of the present invention also provides a securities price analysis method, referring to Figure 2 , the above method specifically includes:

[0085] First, a price pattern recognition method as described above is used to perform pattern recognition on securities price data to obtain a set of securities price pattern events.

[0086] The securities price pattern event set is then used to perform securities price analysis and processing to obtain securities price analysis results.

[0087] The above steps specifically include:

[0088] For each asset type in the securities price data set, the average price volatility within the data set interval is counted, and the k-day average return rate with normalized volatility is taken as the baseline return rate. For each securities price pattern event in the securities price pattern event set, the end price line is used as the opening point, the end price is used as the opening price, and the k-th price line after the end price line is counted, and its time is recorded as the closing point, and the end price is used as the closing price.

[0089] According to the opening point, opening time, closing point and closing time of the securities price pattern event, the characteristic indicators of the securities price pattern event are calculated. The characteristic indicators include yield, normalized yield and maximum drawdown rate. Among them, the yield is the rate of change of the closing price relative to the opening price, the normalized yield is the yield divided by the volatility of the current asset type, and the maximum drawdown rate is the yield of the lowest price between the opening point and the closing point and the opening price.

[0090] For the set of securities price pattern events, the characteristic indicators are statistically summarized according to the types of securities price pattern events to obtain the occurrence frequency indicators of securities price pattern events as well as profitability and risk indicators. Among them, the occurrence frequency indicators include the number of occurrences of pattern events, the number of asset types covered by pattern events, and the distribution of occurrences of pattern events; the profitability and risk indicators include winning rate, average return, average standardized return and average maximum drawdown rate.

[0091] Through the data obtained from the above analysis, investors can analyze the effectiveness of the pattern in the current market, thereby assisting in determining whether to use the specified pattern to guide investment.

[0092] In addition, the embodiment of the present invention also provides a price pattern event recommendation method, referring to Figure 3 , the above method specifically includes:

[0093] The price data is updated by acquiring price data in real time through the Internet, and the price pattern event recognition method as described above is used to recognize the price pattern events of the monitored assets in real time.

[0094] When the above-mentioned monitored assets trigger a price pattern event and the price pattern event of the monitored assets is identified, the monitored assets and the corresponding price pattern events are recommended to investment users to assist investment users in making decisions.

[0095] In addition, an embodiment of the present invention also provides a device, which includes: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a price pattern recognition method as described above, a securities price analysis method as described above, or a price pattern event recommendation method as described above.

[0096] In addition, an embodiment of the present invention also provides a computer program product, which includes computer program instructions, which, when executed by a processor, implement the steps of a price pattern recognition method as described above, a securities price analysis method as described above, or a price pattern event recommendation method as described above.

[0097] A price pattern recognition method provided by an embodiment of the present invention classifies the price status at each time point into rising and falling, and analyzes the historical price shock status to assist users in interpreting the price trend of assets. A securities price analysis method provided by an embodiment of the present invention performs statistical analysis on securities price pattern events and uses historical data to analyze the frequency of occurrence, profitability, and risk level of price patterns to assist users in discovering and selecting price patterns suitable for investment. A price pattern event recommendation method provided by an embodiment of the present invention can achieve real-time monitoring of assets, timely recommend price pattern events, and assist users in making decisions on transaction timing, asset type screening, and major asset allocation.

[0098] The embodiments of the present invention effectively improve the efficiency, controllability and interpretability of recognition and analysis operations, as well as the ability to resist data noise.

[0099] In addition, the embodiment of the present invention can match price changes of various scales and amplitudes by specifying different price difference indicator types and multipliers to adapt to the user's investment cycle and risk preference.

[0100] In the embodiment of the present invention, the processor may be an integrated circuit chip with signal processing capability. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware. The storage medium may be a memory, for example, a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM).The storage medium described in the embodiment of the present invention is intended to include but is not limited to these and any other suitable types of memory. Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by a combination of hardware and software. When the software is applied, the corresponding function can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access. Although the present invention has been described in detail above with general descriptions and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to it on the basis of the present invention. Therefore, these modifications or improvements made on the basis of not departing from the spirit of the present invention all belong to the scope of protection claimed in the present invention.

Claims

1. A price pattern recognition method, characterized in that: The method comprises: Acquire price data, and establish a price data set according to the price data; For each asset type in the price data set, using the price series data of the asset type, obtain a corresponding price change threshold indicator; According to the key nodes in the price sequence data, the price change threshold indicator is used to construct a price state sequence; The pattern events are identified according to the price pattern characteristics of the price state sequence to obtain a price pattern event set.

2. A price pattern recognition method as claimed in claim 1, characterized in that: The price change threshold indicators include the average true range (ATR) and the standard deviation of yield.

3. A price pattern recognition method as claimed in claim 1, characterized in that: According to the key nodes in the price sequence data, the price change threshold indicator is used to construct a price state sequence, including: Take the first price node of the price series as the initial node; For each price node in the price sequence except the initial node, scan them one by one according to the time axis. If the closing price of the current price node is greater than the closing price of the previous price node, the current price node is taken as the first high price node. If the closing price of the current price node is less than the closing price of the previous price node, the current price node is taken as the first low price node; By using the first high-price node and the first low-price node, a price state sequence of second high-price nodes and second low-price nodes alternating with each other is obtained.

4. A price pattern recognition method as claimed in claim 3, characterized in that: Using the first high-price node and the first low-price node, a price state sequence of a second high-price node and a second low-price node alternating is obtained, including: For each first high-price node, determining whether the previous second price node of the current node is a high-price node, wherein the second price node includes a second high-price node and a second low-price node; If the previous second price node of the current node is a high price node, the previous second price node of the current node is deleted, and the current node is used as the second highest price node; If the previous second price node of the current node is not a high price node, the absolute value of the first price difference is calculated using the closing price of the previous second price node and the closing price of the current price sequence; Determine whether the absolute value of the first price difference is greater than a price difference threshold, where the price difference threshold is calculated based on the price change threshold indicator and a preset price difference threshold multiplier; If the absolute value of the first price difference is greater than the price difference threshold, the current node is used as the second lowest price node; If the absolute value of the first price difference is not greater than the price difference threshold, the current node is not used as the second price node; For each first low-price node, determine whether the previous second-price node of the current node is a low-price node; If the previous second price node of the current node is a low price node, the previous second price node of the current node is deleted, and the current node is used as the second lowest price node; If the previous second price node of the current node is not a low price node, the second price difference absolute value is calculated using the closing price of the previous second price node and the closing price of the current price sequence; Determine whether the absolute value of the second price difference is greater than a price difference threshold; If the absolute value of the second price difference is greater than the price difference threshold, the current node is taken as the second highest price node; If the absolute value of the second price difference is not greater than the price difference threshold, the current node is not used as the second price node; A price state sequence is obtained in which the second highest price node and the second lowest price node alternately occur.

5. A price pattern recognition method as claimed in claim 1, characterized in that: The pattern event recognition is performed according to the price pattern characteristics of the price state sequence to obtain a price pattern event set, including: For each asset class, determine the price pattern characteristics based on the current price of the asset class and the node characteristics and node relationships of the price state sequence; Based on the preset price pattern rules, a price pattern event is obtained according to the price pattern characteristics; Use all price pattern events to get the price pattern event set.

6. A method for analyzing securities prices, characterized in that: The method comprises: Using a price pattern recognition method as claimed in any one of claims 1 to 5, pattern recognition is performed on securities price data to obtain a set of securities price pattern events; The securities price pattern event set is used to perform securities price analysis and processing to obtain securities price analysis results.

7. A securities price analysis method as claimed in claim 6, characterized in that: The securities price pattern event set is used to perform securities price analysis and processing to obtain securities price analysis results, including: For each security price pattern event in the security price pattern event set, characteristic indicators of the security price pattern event are calculated according to the opening point, opening time, closing point and closing time of the security price pattern event, and the characteristic indicators include rate of return, normalized rate of return and maximum drawdown rate; For the set of securities price pattern events, statistically summarize the characteristic indicators according to the types of securities price pattern events to obtain the occurrence frequency indicators of securities price pattern events and profitability and risk indicators; The occurrence frequency indicators include the number of occurrences of pattern events, the number of asset types covered by pattern events, and the distribution of pattern event occurrences; The profitability and risk metrics include win rate, average return, average normalized return, and average maximum drawdown.

8. A price pattern event recommendation method, characterized in that: The method comprises: Acquire price data in real time, and use a price pattern recognition method as described in any one of claims 1 to 5 to perform real-time price pattern event recognition on the monitored assets; If a price pattern event of the monitored asset is identified, the monitored asset and the corresponding price pattern event are recommended to the investment user.

9. A device, characterized in that: The device comprises: a processor and a memory; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute the steps of a price pattern recognition method as described in any one of claims 1 to 5, a securities price analysis method as described in claims 6 to 7, or a price pattern event recommendation method as described in claim 8.

10. A computer program product, characterized in that The computer program product includes computer program instructions, which, when executed by a processor, implement the steps of a price pattern recognition method as described in any one of claims 1 to 5, a securities price analysis method as described in claims 6 to 7, or a price pattern event recommendation method as described in claim 8.

Images