CN117114862A

CN117114862A - Financial technology morphological event identification method and system

Info

Publication number: CN117114862A
Application number: CN202310715342.0A
Authority: CN
Inventors: 阿兰·贝利叶
Original assignee: Xiangshang Shanghai Business Consulting Co ltd
Current assignee: Xiangshang Shanghai Business Consulting Co ltd
Priority date: 2023-06-15
Filing date: 2023-06-15
Publication date: 2023-11-24

Abstract

The application relates to a financial technical event identification method and a system, wherein the method comprises the following steps: identifying complex technical forms and technical events of stock market data, determining corresponding characteristics of the complex technical forms and the technical events, and storing the characteristics in a database to generate a financial event database; presetting a customer standard, and determining a subset of a financial event database according to the customer standard; receiving a data query request of a client, and identifying corresponding financial event data based on a query subset of the data query request; identifying financial event data according to a preset standard, and dynamically modifying the financial event data; and (5) overlaying the corresponding chart form of the dynamically modified financial event data and transmitting the corresponding chart form back to the client. By automatically identifying multiple technical modalities, effective information is obtained to facilitate transactions and provide investment advice and guidance.

Description

Financial technology morphological event identification method and system

Technical Field

The disclosure relates to the technical field of data processing, in particular to a method and a system for identifying morphological events of a financial technology.

Background

Technical events refer to the interaction of a stock price with an index or the confirmation of a price form, such as the breakthrough of the head and shoulder, or the breakthrough of a critical point due to a concussion, etc., within a certain period of time. The price pattern is a pattern indicating that a stock supply and demand change causes a price to rise and fall, and these changes usually form a visual pattern in a price map with the lapse of time, and a predictable price trend usually appears after the price pattern.

The price graph is used as an important tool for technical analysis and market research, and the purpose of searching price forms and technical events can be achieved by analyzing the price graph, so that potential events with possible transaction opportunities can be identified. However, in the actual analysis process, it is difficult for a technical analyst to monitor daily stock price fluctuations of all securities to identify price forms formed within minutes or hours, thereby resulting in a rapid decrease in the effectiveness of the price forms, a high cost of timely disseminating information to a large population, and a slow and expensive cost of annotating the securities forms.

Therefore, providing a method for automatically identifying the form of financial technology to improve analysis efficiency and analysis accuracy is a problem to be solved.

Disclosure of Invention

In view of the above, the present application provides a method and a system for identifying morphological events of financial technology to solve the above-mentioned problems.

In one aspect of the present application, a method for identifying morphological events of financial technology is provided, including the following steps:

identifying complex technical forms and technical events of stock market data, determining corresponding characteristics of the complex technical forms and the technical events, and storing the characteristics in a database to generate a financial event database;

presetting a customer standard, and determining a subset of the financial event database according to the customer standard;

receiving a data query request of a client, querying the subset based on the data query request, and identifying corresponding financial event data;

identifying the financial event data according to a preset standard, and dynamically modifying the financial event data;

and overlaying the corresponding chart form of the financial event data after dynamic modification and transmitting the corresponding chart form back to the client.

As an optional embodiment of the application, optionally, the technical event is located to any one of an oscillating index crossing threshold, a stock price interacting with an index, or a pre-identified morphological period.

As an optional embodiment of the application, optionally, the financial event database comprises morphological recognition derived technical events, index/oscillation index derived technical events and morphological technical events, and corresponding features.

As an alternative embodiment of the present application, optionally, customer criteria are preset to determine the customer criteria from a customer profile and a customer application.

As an optional embodiment of the present application, optionally, identifying the financial event data according to a preset standard, and dynamically modifying the financial event data includes:

identifying financial events associated with the financial event data and merging the associated financial events with the financial event data.

As an optional embodiment of the present application, optionally, the dynamically modifying the financial event data according to a preset standard identification further includes:

identifying financial events that are not related to the financial event data and excluding the financial events that are not related from the financial event data.

As an optional embodiment of the present application, optionally, after identifying the financial event data according to a preset standard and dynamically modifying the financial event data, the method further includes:

and formatting the modified financial event data according to a preset format standard.

As an alternative embodiment of the present application, the format standard may optionally include any one of HTML, XML, or SOAP.

As an alternative embodiment of the application, the identification is optionally performed by means of a loosely defined algorithm when identifying the technical morphology and technical events of the stock market data.

In another aspect of the present application, a system for implementing the financial technical form event recognition method described in any one of the above is provided, including:

the database construction module is configured to identify complex technical forms and technical events of stock market data, determine corresponding characteristics of the complex technical forms and the technical events, and store the characteristics in the database to generate a financial event database;

a subset determining module configured to preset customer criteria and determine a subset of the financial event database according to the customer criteria;

a data query module configured to receive a data query request from a client and to query the subset based on the data query request, identifying corresponding financial event data;

the data modification module is configured to identify the financial event data according to a preset standard and dynamically modify the financial event data;

and the data return module is configured to return the dynamic modified financial event data to the client by overlaying corresponding chart forms.

The application has the technical effects that:

the financial technical event identification method provided by the application can automatically identify various technical forms, and effectively improves analysis efficiency and analysis accuracy. Specifically, complex technical forms and technical events of stock market data are identified, corresponding characteristics of the complex technical forms and the technical events are determined and then stored in a database, and a financial event database is generated; presetting a customer standard, and determining a subset of a financial event database according to the customer standard; receiving a data query request of a client, and identifying corresponding financial event data based on a query subset of the data query request; identifying financial event data according to a preset standard, and dynamically modifying the financial event data; and (5) overlaying the corresponding chart form of the dynamically modified financial event data and transmitting the corresponding chart form back to the client. The application utilizes automatic chart form recognition to obtain effective information, which is convenient for promoting transactions and providing investment advice and guidance.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a flow chart of a method for identifying morphological events of a financial technology according to the present application;

FIG. 2 is a schematic diagram of a financial event database construction process for a financial technology morphological event identification method of the present application;

FIG. 3 is a schematic diagram of a data query request implementation flow for a financial technology modality event identification method of the present application;

FIG. 4 is a flow chart of another embodiment of a data query request for the financial technology modality event recognition method of the present application;

FIG. 5 is a flow chart of another embodiment of a data query request for the financial technology modality event recognition method of the present application;

FIG. 6 is a schematic view of the head and shoulder aspects of the present application and related art events;

FIG. 7 is a schematic diagram of a moving average technical event in the present application;

FIG. 8 is a schematic diagram of a downward skip technology event in the present application;

FIG. 9 is a schematic diagram illustrating the simultaneous occurrence of the technical events of FIGS. 6, 7 and 8 in the present application;

FIG. 10 is a detailed schematic of FIG. 11 in accordance with the present application;

FIG. 11 is a schematic diagram illustrating the implementation flow of the method for identifying morphological events of financial technology according to the present application;

FIG. 12 is a flow chart illustrating another embodiment of the method for identifying morphological events of financial technology according to the present application.

Detailed Description

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

Example 1

As shown in fig. 1, the present application provides a method for identifying morphological events of a financial technology, which includes the following steps:

s100, identifying complex technical forms and technical events of stock market data, determining corresponding features of the complex technical forms and the technical events, and storing the features in a database to generate a financial event database;

s200, presetting a customer standard, and determining a subset of the financial event database according to the customer standard;

s300, receiving a data query request of a client, querying the subset based on the data query request, and identifying corresponding financial event data;

s400, identifying the financial event data according to a preset standard, and dynamically modifying the financial event data;

s500, the dynamic modified financial event data are overlapped with corresponding chart forms and are transmitted back to the client.

In the embodiment, investors are helped to judge market trends by automatically identifying classical multiple technical forms, analysis accuracy is improved, and judgment errors caused by manual identification are avoided. Table 1 shows 28 classical technical forms, including rising continuous triangle, triangle base, continuous diamond (see expansion), continuous wedge (see expansion) diamond base, double base, flag arrangement (see expansion), head shoulder base, horn base, triangular flag arrangement (see expansion), circular arc base, symmetrical continuous triangle (see expansion), triple base, upward breakthrough, and continuous diamond (see drop), continuous wedge (see drop), falling continuous triangle, diamond top, double top, downward breakthrough, flag arrangement (see drop), head shoulder top, horn top, triangular flag arrangement (see drop), circular arc top, symmetrical continuous triangle (see drop), triangle top, triple top.

TABLE 1 morphology table of 28 classical techniques

Specifically, through step S100, the technical form and the technical event of the stock market data are identified, and the features corresponding to the technical form and the technical event are determined and then stored in a database, so as to generate a financial event database. Here, the stock market data includes daily stock market information, such as high price, low price, open price, closing price, volume of delivery, holding amount, and the value of the stock's tick data, and the market data includes not only real-time data but also historical data, and by inputting the market data into the loosely defined algorithm LSAs, candidate forms with different window sizes are identified, and the identified candidate forms are written into the database for facilitating subsequent further analysis. The complex form in the present application is an inverted form, and the inverted form includes a double top, a head and shoulder top, a double bottom or a head and shoulder bottom inverted form, and the complex form is an asymmetric complex form.

As an optional embodiment of the application, optionally, the technical event is located to any one of an oscillating index crossing threshold, a stock price interacting with an index, or a pre-identified morphological period. Wherein, the oscillation index is the relative intensity index RSI, and the index is the moving average line. As an optional embodiment of the application, optionally, the financial event database comprises morphological recognition derived technical events, index/oscillation index derived technical events and morphological technical events, and corresponding features. Further, chart marks and notes are generated through LSAs, so that investors are helped to analyze market trends, and accurate judgment is made. Meanwhile, market data is also input into an index and oscillation index calculation engine, and the neural network is embedded into a price prediction unit and a characterization engine, so that a constructed metal event database comprises morphological recognition derived technical events, index/oscillation index derived technical events and simple morphological technical events, and features or attributes corresponding to the technical events.

It should also be noted that event sequences, such as simple moving average and relative intensity index (RSI) oscillation indices, are calculated by an index and oscillation index calculation engine and written into a database. Meanwhile, a neural network embedded price prediction module is utilized to obtain a characteristic of a certain form, and the price prediction shows the expected price in a future time interval. The embedded price predictions are also written into a database, which generates future price predictions by embedding the price predictions, it being noted that the price predictions are statistically independent of morphology and technical events.

Further, as an alternative embodiment of the present application, as shown in fig. 2, optionally, in identifying the technical morphology and technical event of the stock market data, the identification is performed by a loosely defined algorithm. The LSAs algorithm is tuned by a parametric tuning genetic algorithm, which is to be interpreted as a periodic training activity. Genetic algorithms are used to select and weight various parameters and rules for LSAs to facilitate finding candidate morphologies. At the same time, the candidate morphology of LSAs is also used for manual ranking, which is a periodic training activity. The candidate morphologies are displayed to human experts and then ranked according to their experience. This information is stored in training module 406. The information in the training module 406 is used by the bayesian regularizer 412. Bayesian regularizer 412 is a training file that is used to update RBF neural network 414 on a regular basis. Where RBF neural network 414 receives candidate morphologies from LSAs and calculates an empirical rating for past performance or consensus of each candidate morphology. That is, experience ratings are equivalent to ratings given by human experts to candidate modalities.

The candidate technology modalities are written to the financial event database 420 and these patterns are also stored for later feature extraction, retrieval and analysis. The RBF neural network 414 is tuned by a feature selection genetic algorithm 416, which is also a periodic training activity. The metrics and oscillation time series and events are written into database 420 for technical analysis calculations identifying technical events. It should be noted that technical events such as the closing price rising above the 200 day movement average line or RSI falling below 70. The RBF neural network ratings are also written to database 420, which is a number that indicates how the human expert would evaluate the candidate morphology. Feature extraction engine 422 calculates various features for each candidate modality found by the LSAs while using feature extraction engine 422 to read candidate modalities, metrics, and oscillation metrics from database 420, calculate modality and event features, and write the results back to database 420. For example, features are symmetry numbers, which are indicators of how similar two halves of a pattern are. Specifically, in the head-shoulder-bottom mode, the symmetry number indicates how balanced the head is and how similar the left and right shoulders are.

It should be noted that, in the technical form, a simple form is identified by a simple standard machine, such as a notch, and in the technical form, a complex form is identified by a form identification technology, such as the identification of the top of the head. It should also be noted that the corresponding features or attributes of the technical events in the database include primary features, such as the length and height of the complex morphology, and turning points for creating morphology candidates, and secondary features derived from the primary features, such as symmetry and experience ratings.

After the database is generated, customer criteria are preset as shown in step S200, and a subset of the financial event database is determined according to the customer criteria. Wherein, as an optional embodiment of the present application, optionally, the client standard is preset to determine the client standard according to the client configuration file and the client application program. Here, it should be noted that, as shown in fig. 5, in the client profile database, the client 1 includes one profile, where the specified number X and y must satisfy: x >7 and y <5. Likewise, client 2 has a profile in which x <6 and Z >9 are specified. At the client application level, for example, user 712 makes a request for data satisfying conditions a >10 and c <5. In the segmentation engine 504 or module, this will translate into a request from the database 420 for data that satisfies the condition: criteria for a >10, c <5 and X >7, y <5. Also, the user 722 request, requiring data satisfying b <7 and c >2, the segmentation engine queries the database 420 to satisfy the criteria: b <7, c >2 and x <6, Z >9, thereby determining a subset of the financial database.

Further, through step S300, a data query request of the client is received, and the subset is queried based on the data query request, so as to identify corresponding financial event data. Wherein, as an optional implementation manner of the present application, optionally, the dynamic modification of the financial event data according to the preset standard identification includes: identifying financial events associated with the financial event data and merging the associated financial events with the financial event data. Further, as an optional embodiment of the present application, optionally, the dynamically modifying the financial event data according to the preset standard identification further includes: identifying financial events that are not related to the financial event data and excluding the financial events that are not related from the financial event data.

Here, it should be noted that, after providing the subset of the financial event data to the client according to the client configuration file, the subset is queried in combination with a query request of the client for acquiring the data of the financial event, so as to obtain the result of the financial event data. Wherein the customer may be a financial service provider or an end customer. In particular, the system of databases is maintained by financial content providers. The customers of the financial content provider can be directly consumers of their services, such as dealer or retail investors. It should also be noted that the customer may be a financial service provider or other intermediary that receives data and related information from the financial service provider and provides this information, either directly or after modification, to the customer, typically a consumer or end user. Financial content providers can access historical and real-time market data, including, for example, intra-day, end-of-day, weekly, and monthly data, through the databases of the present application, for analysis to identify chart morphology and other technical events. The corresponding results are provided to the financial content recipient, e.g., the financial service provider, for modification and re-tagging to enable the user of the financial service provider to find useful information. The financial content provider and the financial service provider may also respond to downstream requests and preferences and modify the transmitted information accordingly. Within the scope of the present application, the wireless market is also considered to be targeted. The task of implementing and promoting wireless services again falls on the customer's premises, i.e. the financial content provider only provides material that helps to attract users to their web sites.

Still further, as shown in fig. 11 and 12, the financial content provider maintains a database 420. Clients, such as financial service providers 1306, 1308, 1310 may access databases using client applications over a network 1304, such as the Internet and I/O server 1302. The client 1308 has a database or data source 1312 and presentation templates 1314, and the user 1320 may access the client system via a network 1318, such as a wireless network and an I/O server 1316.

According to the application, the client application can be deployed via the Internet into financial oriented websites and Internet dealer and transaction facilities. The user 1320 increases the content value of the website with minimal cost and effort by interacting the website with personal applications operated by the financial content provider.

The clients access data from the database through the Internet, on the clients, each client configures a client application program, extracts data through the Internet and server application programming interface API, or queries the database through the segmentation engine. Wherein the segmentation engine dynamically identifies other relevant financial events or eliminates irrelevant financial events, or otherwise modifies the query results, using a client profile database and a data fusion algorithm, presenting the appropriate data to each client. That is, the present application identifies financial event data by the segmentation engine and dynamically modifies it. When a financial event associated with the financial event data is identified, the associated financial event is merged with the financial event data; when a financial event is identified that is not related to the financial event data, the unrelated financial event is excluded from the financial event data.

And (3) dynamically modifying the financial event data according to the preset standard identification in the step S400, and overlapping the financial event data subjected to dynamic modification in the step S500 to the corresponding chart form and transmitting the chart form back to the client. Wherein, as an optional implementation manner of the present application, optionally, after identifying the financial event data according to a preset standard and dynamically modifying the financial event data, the method further comprises: and formatting the modified financial event data according to a preset format standard. Further, as an optional embodiment of the present application, optionally, the format standard includes any one of HTML, XML, or SOAP.

Specifically, the client application receives the user request and converts the request to a database query through the API. The client application then receives the results and formats them, which are then transmitted to the user. The format of the response is formatted, for example, into hypertext markup language (HTML), so that the user's graphical user interface can be interpreted. In this way, the user can query the database and access rich data sources to confidently identify potentially tradable information. Applications and databases can be accessed using complex Web-based XML APIs, with very varying and complex calls. The API may return data in XML formats (including, for example, RSS, ICE, and SOAP) and HTML formats. These formats provide flexibility and allow for multiple uses.

Since it is necessary to provide appropriate information for different customers, professional traders may be more likely not to want to receive obvious trivial data or be willing to choose to mask information that does not fit their investment style. For example, if a transactant is focusing on transactions in a short period of time, a long transaction opportunity is unsuitable. In contrast, a bulk home may prefer to invest in a longer time frame and may prefer to trade based on a clearer modality. For example, a scattered user may only be willing to rely on a relatively flat profile of the neck line in a highly symmetrical or head-shoulder profile. Another important aspect is that regulatory requirements do not provide trade signals to a spammer, and professional traders may be very interested in strong trade signals, including stock, price changes, and confidence ratings. To this end, clients may use different client applications depending on the functions and information they wish to use. As shown in fig. 3 and 4, four different clients are shown, each having a different client application 520, 530, 540, 550.

The subset of data used to selectively make each client application available is responsive to a user request by a segmentation engine. For example, specialized application 520 sees only a subset of data 522, data 524. Thus, all requests will be based on this subset. For example, if a professional trader is only interested in asymmetric complex forms, not all other complex forms will be present. Similarly, the scatter application 530 will manipulate or analyze a different subset of the data 522, namely data 534. Where there is no predetermined relationship between data 524 and data 534. They may overlap, i.e. have some common data, may be disjoint, or one may be a subset of the other.

It should be noted that, as shown in fig. 4, the API may also interact with the virtual data structure of the client for each client of the present application, because, as shown in fig. 6, there is a head-shoulder configuration, having a configuration neck line 804, and the price receiving price is lower than the neck line, and the head-shoulder configuration is confirmed. In conventional systems, only the chart is displayed, but the identification of the critical technical event 810 cannot be performed. Fig. 7 is a graph showing a 200 day movement average line 902. 904 also shows standard high, low, open, and receipt bars. A technical event 910 occurs when the price drops by 200 days moving the average line. Fig. 8 illustrates a series of price bars forming a gap morphology, technical event 1010 occurring when a price jumps down. While investors may be interested in both these basic and technical events, it is particularly valuable to identify these moments that occur concurrently with financial events. The present system is capable of identifying and presenting such events, for example, by a chart overlay as shown in fig. 9. The detailed information of region 1100 is illustrated in fig. 10, where it is clearly seen that technical events 810, 910 and 1010 occur in the vicinity of the right shoulder edge 503 meeting the pattern neck line 804.

Such coincidences or correspondences can be found by a request issued to database 420 specifying that a technical event occur at the same time T. Different technical events also improve the quality of the search for useful or "tradable information", especially when the search and technical analysis can be automated. For example, if a complex morphology takes 60 days to form, it is more appropriate to examine a 100-day moving average than to examine a 5-day moving average. The client application of the present application may suggest and implement the appropriate companion graph and search for confirmatory technical events. In addition, the geometry of the form indicates the price target and also affects the choice of technical events derived from the index and the oscillation index. The application can be customized by modifying the application program corresponding to the requirements of different client application programs.

In summary, the application can automatically identify the chart form, namely more widely identify the form and technical event, and can be deployed on any financial website on the Internet, meanwhile, the database in the application enables researchers and investors to study the chart behaviors in a brand new way, and can also provide historical data, thereby improving the chart form identification and obtaining useful information. Specifically, by accessing historical data and real-time data, analyzing the historical data and real-time data to identify chart morphology, analyzing the historical market data and current market data to determine technical events, parsing the identified chart morphology to determine technical events, and providing financial events to financial content recipients for customization and private tagging. Further, analysis of the morphology in the database by the present application shows that in selecting a profit trade opportunity, the flexible search and order delivery mechanism allows the user to search and select a morphology based on important criteria.

It should be noted that although the above has been described as an example, those skilled in the art will appreciate that the present disclosure should not be limited thereto. In fact, the user can flexibly set the device according to the actual application scene, so long as the technical function of the application can be realized according to the technical method.

It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiment methods may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the embodiment flow of each control method as described above when executed. The storage medium may be a magnetic disk, an optical disc, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a flash memory (flash memory), a hard disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.

Example 2

In another aspect of the present application, based on the implementation principles of embodiment 1, a system for implementing the financial technology morphological event recognition method described in any one of the above is provided, including:

the database construction module is configured to identify the technical form and the technical event of the stock market data, determine the corresponding characteristics of the technical form and the technical event, store the characteristics in the database and generate a financial event database; the data construction module comprises a module for identifying complex forms in stock market data and a module for generating a financial event database.

a data query module configured to receive a data query request from a client and to query the subset based on the data query request, identifying corresponding financial event data; including a module for receiving a target modality from a client and requesting financial event data associated therewith, and a module for querying a subset to identify financial event data associated with the target modality.

the data return module is configured to return the dynamic modified financial event data to the client in a corresponding chart form in a superposition mode, and comprises a target form module for superposing the modified financial event data and a client module for returning the financial event data in the superposition form.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. The financial technology morphological event identification method is characterized by comprising the following steps:

2. The method of claim 1, wherein the technical event is located at any one of an oscillating index crossing threshold, a stock price interacting with an index, or a pre-identified morphological time period.

3. The method of claim 1, wherein the financial event database includes morphological recognition derived technical events, index/oscillation index derived technical events and morphological technical events, and corresponding features.

4. The method of claim 1, wherein the customer criteria is preset to determine the customer criteria based on a customer profile and a customer application.

5. The method of claim 1, wherein dynamically modifying the financial event data according to a predetermined criteria identification comprises:

6. The method of claim 5, wherein dynamically modifying the financial event data according to a predetermined criteria identification, further comprises:

7. The method for identifying a financial technical form event according to claim 1, wherein after dynamically modifying the financial event data according to a predetermined standard identification, further comprising:

8. The method of claim 7, wherein the format standard comprises any one of HTML, XML, or SOAP.

9. The method of claim 1, wherein the identifying is performed by a loosely defined algorithm when identifying the technical morphology and the technical event of the stock market data.

10. A system for implementing a financial technology morphological event recognition method according to any one of claims 1-9, comprising: