CN114490832A

CN114490832A - Market risk prediction method and device, electronic equipment and storage medium

Info

Publication number: CN114490832A
Application number: CN202210139789.3A
Authority: CN
Inventors: 陈若菲
Original assignee: Ping An Life Insurance Company of China Ltd
Current assignee: Ping An Life Insurance Company of China Ltd
Priority date: 2022-02-16
Filing date: 2022-02-16
Publication date: 2022-05-13

Abstract

The invention relates to the technical field of artificial intelligence, and provides a market risk prediction method, a market risk prediction device, electronic equipment and a storage medium, wherein the method comprises the following steps: obtaining a question to be inquired; searching at least one historical event similar to the question to be inquired from a preset data source; acquiring a first price change trend graph of each historical event, and analyzing the first price change trend graph of each historical event to obtain an analysis result of each historical event; analyzing a plurality of analysis results of at least one historical event to obtain a second price change trend graph of the question to be inquired; and outputting a market risk prediction result of the question to be queried based on the second price change trend graph. According to the method, the second price change trend graph is determined by analyzing a plurality of analysis results of at least one historical event, and the market risk prediction result of the question to be inquired is output according to the second price change trend graph, so that the efficiency and the accuracy of market risk prediction are improved.

Description

Market risk prediction method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a market risk prediction method and device, electronic equipment and a storage medium.

Background

With the mass increase of products in the financial investment field, market risk prediction is performed by analyzing information collected from different fields.

However, in the prior art, when performing cross-domain event analysis and information collection, an analyst needs to collect event data from various websites and databases such as hundreds of degrees, wind, and green waves, acquire quotations through SQL, perform data processing and drawing with tools such as excel, and finally perform research and writing with word. Researchers need to switch among various tools, and the efficiency is low, the time consumption is long, the fault tolerance rate is low, the time delay and the information omission are caused, so that the accuracy and the efficiency of market risk prediction are low.

Disclosure of Invention

In view of the above, it is desirable to provide a market risk prediction method, an apparatus, an electronic device, and a storage medium, which analyze a plurality of analysis results of historical events to determine a second price change trend graph, and directly output a market risk prediction result of a question to be queried according to the second price change trend graph, so as to improve efficiency and accuracy of market risk prediction.

A first aspect of the invention provides a method of market risk prediction, the method comprising:

analyzing the received market risk prediction request to obtain a question to be inquired;

searching at least one historical event similar to the question to be inquired from a preset data source;

acquiring a first price change trend graph of each historical event, and analyzing the first price change trend graph of each historical event to obtain an analysis result of each historical event;

analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired;

and outputting a market risk prediction result of the question to be inquired based on the second price change trend graph.

Optionally, the searching for at least one historical event similar to the question to be queried from a preset data source includes:

identifying key words in the question to be queried, identifying key words matched with the key words in a preset database, and determining all matched key words as preset key words;

inputting the preset keywords into a pre-trained event label model for label analysis to obtain labels of the preset keywords, and inputting the question to be inquired into a pre-trained question type identification model for type identification to obtain the type of the question to be inquired;

creating a target query strategy based on a plurality of labels of the preset keywords and the type of the question to be queried;

traversing each preset data source based on the target query strategy to obtain a preset historical event corresponding to each data source and similar to the question to be queried;

and merging at least one historical event of the preset data source to obtain at least one historical event similar to the question to be inquired.

Optionally, the creating a target query policy based on the plurality of tags of the preset keyword and the type of the question to be queried includes:

identifying a label of a preset keyword corresponding to the type of the question to be inquired;

combining the types of the question sentences to be inquired according to a preset combination mode to obtain a plurality of type combinations;

creating a corresponding query strategy according to the labels of the preset keywords in each type combination and a preset query rule;

determining a plurality of query policies of the plurality of types combinations as a target query policy.

Optionally, the analyzing the first price variation trend graph of each historical event to obtain the analysis result of each historical event includes:

performing trend division on the first price variation trend graph to obtain a plurality of trend types;

and calculating the probability of each trend type, and taking the calculated probability of each trend type as the analysis result of each historical event.

Optionally, the analyzing the analysis result of the at least one historical event to obtain a second price variation trend graph of the question to be queried includes:

calculating the probability sum of all rising trend types in the analysis result of the at least one historical event to obtain a first sum;

calculating the probability sum of all descending trend types in the analysis result of the at least one historical event to obtain a second sum;

calculating a quotient of the first sum and the second sum to obtain a first probability;

if the first probability is larger than a preset first probability threshold, determining that a second price variation trend graph of the question to be queried is an ascending trend; or

If the first probability is equal to the preset first probability threshold, determining that a second price variation trend graph of the question to be queried is a horizontal trend; or

And if the first probability is smaller than or equal to the preset first probability threshold, determining that a second price variation trend graph of the question to be queried is a descending trend.

acquiring a plurality of probabilities of a plurality of trend types of each historical event, calculating a difference value of any two probabilities of each trend type, and keeping a plurality of probabilities of which the difference values are within a preset difference value threshold range as the probabilities of each trend type;

calculating the sum of the probabilities of all rising trend types reserved in the analysis result of the at least one historical event to obtain a third sum;

calculating the probability sum of all the downward trend types reserved in the analysis result of the at least one historical event to obtain a fourth sum;

calculating the quotient of the third sum and the fourth sum to obtain a second probability;

if the second probability is larger than a preset second probability threshold, determining that a second price variation trend graph of the question to be queried is an ascending trend; or

If the second probability is equal to the preset second probability threshold, determining that a second price variation trend graph of the question to be queried is a horizontal trend; or

And if the second probability is smaller than or equal to the preset second probability threshold, determining that the second price variation trend graph of the question to be queried is a descending trend.

Optionally, the outputting the market risk prediction result of the question to be queried based on the second price change trend graph includes:

when the second price change trend graph is an ascending trend, outputting the market risk prediction result of the question to be inquired as a low risk; or

When the second price variation trend graph is a horizontal trend, outputting the market risk prediction result of the question to be inquired as the medium risk; or

And when the second price variation trend graph is a descending trend, outputting the market risk prediction result of the question to be inquired as a high risk.

A second aspect of the present invention provides a market risk prediction apparatus, the apparatus comprising:

the analysis and acquisition module is used for analyzing the received market risk prediction request to acquire a question to be inquired;

the searching module is used for searching at least one historical event similar to the question to be inquired from a preset data source;

the acquisition and analysis module is used for acquiring the first price change trend graph of each historical event and analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event;

the analysis module is used for analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired;

and the output module is used for outputting the market risk prediction result of the question to be inquired based on the second price variation trend graph.

A third aspect of the invention provides an electronic device comprising a processor and a memory, the processor being configured to implement the market risk prediction method when executing a computer program stored in the memory.

A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the market risk prediction method.

In summary, according to the market risk prediction method, the market risk prediction device, the electronic device and the storage medium of the present invention, at least one historical event similar to the query sentence is searched from a preset data source, the types of the query sentence to be queried are combined by adopting a plurality of combinations, and then, after a query policy is created based on the tags and the types in the query sentence to be queried, at least one historical event similar to the query sentence is queried, so that the similarity between the queried historical event and the query sentence to be queried is ensured, and the accuracy of subsequent market risk prediction is improved. Analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event, and subsequently, considering the overall analysis result of each historical event when market risk prediction is carried out, rather than singly considering one first price change trend graph of each historical event to carry out market risk prediction, thereby improving the accuracy of market risk prediction. Analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired, outputting a market risk prediction result of the question to be inquired based on the second price change trend graph, efficiently assisting a researcher to quickly determine the market risk prediction result of the question to be inquired, and improving the efficiency and accuracy of market risk prediction.

Drawings

Fig. 1 is a flowchart of a market risk prediction method according to an embodiment of the present invention.

Fig. 2 is a block diagram of a market risk prediction apparatus according to a second embodiment of the present invention.

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

Example one

In this embodiment, the market risk prediction method may be applied to an electronic device, and for an electronic device that needs to perform market risk prediction, the market risk prediction function provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SDK).

The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning, deep learning and the like.

As shown in fig. 1, the market risk prediction method specifically includes the following steps, and the order of the steps in the flowchart may be changed and some may be omitted according to different requirements.

And S11, analyzing the received market risk prediction request to obtain a question to be inquired.

In this embodiment, for the financial investment field, when a user purchases an investment product, the user may initiate a market risk prediction request to a server through a client, where the client may specifically be a smart phone, an IPAD, or other existing smart device, the server may be a market risk prediction subsystem, and the market risk prediction subsystem is configured to receive the market risk prediction request sent by the client, and analyze the market risk prediction request to obtain a question to be queried input by the user, where the question to be queried may be "stock market historical performance after mid-autumn festival", for example.

S12, searching at least one historical event similar to the question to be inquired from a preset data source.

In this embodiment, in the process of predicting the market risk, the server needs to collect a large number of historical events similar to the question to be queried in the market risk prediction request sent by the client, where the historical events may be from a historical event library, and the historical event library may be a plurality of preset data sources such as a market quotation library, a macro database, a factor library, and a calendar event library.

In this embodiment, each preset data source may include at least one historical event similar to the question to be queried.

In an optional embodiment, the searching for at least one historical event similar to the question to be queried from a preset data source includes:

traversing each preset data source based on the target query strategy to obtain a historical event which corresponds to each preset data source and is similar to the question to be queried;

In this embodiment, preset keywords are pre-stored in a database, the question to be queried is analyzed, and the question to be queried is matched with the keywords pre-stored in the database to obtain the preset keywords.

Specifically, the type of the question to be queried may include: event, event target, date target, modality target, macro base surface target.

In this embodiment, an event tag model and a question type identification model may be trained in advance, where the training process of the event tag model and the question type identification model is the prior art, and details are not described here in this embodiment.

Illustratively, the accuracy of identifying the event type of a question to be queried reaches 97%, the event mainly comprises a date event, a target event and a macro news event, the accuracy of identifying the type of the date and the target reaches 100%, the macro basic plane refers to the analysis of the basic conditions of macro economy, industry and companies, the macro basic plane is calculated according to the peak value of news and is influenced by noise, and the accuracy of identifying can reach 97%, for example, the peak value judgment of the macro event, the judgment of the hot event trend similar to a search engine needs to comprehensively consider a plurality of disturbance factors, such as the data relation with a time sequence and a lot of noise contained in news, but the accuracy of identifying can also reach 97%.

Further, the creating of the target query policy based on the plurality of labels of the preset keyword and the type of the question to be queried includes:

In this embodiment, the preset query rule is determined according to the historical data based on the types of the preset keywords and the corresponding tags, for example: the question to be inquired is 'stock market historical expression after mid-autumn festival', and the type of the question to be inquired is as follows: the date and event label, wherein, the label that the date corresponds to is: after mid-autumn festival, the corresponding labels of the event labels are: the stock market, stock market trends and American stock market trends, the query strategy corresponding to the corresponding query strategy is created according to the preset query rule, namely, the stock market trends of Shanghai Shenshen 300 of 5 days after the mid-autumn festival of the last 10 years and the American stock market trend of 500 years after the last 10 years are queried, namely: the at least one historical event obtained by searching is: the market trend of Shanghai Shen 300 is A after T +5 days in mid-autumn; the American stock standard market trend is 500 after T +5 days in mid-autumn.

In this embodiment, after the types of the question sentences to be queried are combined by adopting multiple combinations, a query strategy is created based on the tags and the types in the question sentences to be queried, and then at least one historical event similar to the question sentences to be queried is queried, so that the similarity between the queried historical events and the question sentences to be queried is ensured, and the accuracy of subsequent market risk prediction is further improved.

S13, obtaining the first price change trend graph of each historical event, and analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event.

Illustratively, for the stock market, the price movement trend graph refers to the market trend graph of each historical event at a specific time.

In an optional embodiment, the analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event includes:

Illustratively, 5 market trends of the shanghai depth 300 of a stock 5 days after the mid-autumn festival in the last 10 years are upward trends and 5 downward trends, and the upward trends are calculated, so that the probability of the upward trend type is 5/10-0.5, the probability of the downward trend type is 5/10-0.5, and the probability of the upward trend type is 0.5 and the probability of the downward trend type is 0.5 as the analysis results of corresponding events.

In this embodiment, the first price variation trend graph of each historical event is analyzed to obtain an analysis result of each historical event, and the overall analysis result of each historical event is considered in the subsequent market risk prediction, rather than singly considering one first price variation trend graph of each historical event to predict the market risk, so that the accuracy of the market risk prediction is improved.

And S14, analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired.

In this embodiment, since one question to be queried corresponds to a plurality of similar historical events, a plurality of analysis results of at least one historical event need to be summarized and counted, and based on the price change trends in the plurality of similar historical events under similar situations, a second price change trend graph of the question to be queried is further obtained, so that the second price change trend graph obtained through analysis is more accurate, and the accuracy of market risk prediction is further improved.

In an optional embodiment, the analyzing the analysis result of the at least one historical event to obtain the second price variation trend graph of the question to be queried includes:

If the first probability is equal to the preset first probability threshold, determining a second price variation trend graph of the question to be inquired as a horizontal trend; or

In this embodiment, a first probability threshold may be preset, for example, the first probability threshold may be set to 1.

And if the second probability is smaller than or equal to the preset second probability threshold, determining that the second price variation trend graph of the question to be inquired is a descending trend.

In this embodiment, a second probability threshold may be preset, for example, the second probability threshold may be set to 1.

In this embodiment, a preset difference threshold range may be preset, and when the second price variation trend graph of the question to be queried is determined, the accuracy of the second price variation trend graph is further improved by screening out the probability of the trend type with a larger deviation in each historical event.

And S15, outputting the market risk prediction result of the question to be inquired based on the second price change trend graph.

In this embodiment, the market risk prediction result refers to a result predicted by analyzing a price change trend graph of similar historical events of the question to be queried.

In an optional embodiment, the outputting the market risk prediction result of the question to be queried based on the second price change trend graph includes:

In the embodiment, by predicting the second price variation trend chart of the question to be queried, a researcher is efficiently assisted to quickly determine the market risk prediction result of the question to be queried, and the efficiency and the accuracy of market risk prediction are improved.

In the embodiment, at least one historical event similar to the question to be queried is obtained from a preset data source by adopting a created query strategy, and based on a price change trend chart of the at least one historical event under similar situations, namely the performance of historical investment products, generalizing the price change trend chart rule of the statistical target to predict the market risk without the need that a researcher firstly searches information from a plurality of preset data sources, and then acquiring quotations through SQL, performing data processing and drawing by using excel and other tools, and finally writing a market risk prediction report by using word, wherein researchers need to switch back and forth among various tools, so that the efficiency and the accuracy of market risk prediction are low, the time consumption is long, the fault tolerance rate is low, time delay and information omission are caused, the preemptive opportunity of investment is easily lost, and the efficiency and the accuracy of market risk prediction are improved.

In summary, according to the market risk prediction method provided by this embodiment, at least one historical event similar to the question to be queried is searched from a preset data source, the types of the question to be queried are combined by adopting multiple combinations, a query policy is created based on the tags and types in the question to be queried, and then at least one historical event similar to the question to be queried is queried, so that the similarity between the queried historical event and the question to be queried is ensured, and the accuracy of subsequent market risk prediction is further improved. Analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event, and subsequently, considering the overall analysis result of each historical event when market risk prediction is carried out, rather than singly considering one first price change trend graph of each historical event to carry out market risk prediction, thereby improving the accuracy of market risk prediction. Analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired, outputting a market risk prediction result of the question to be inquired based on the second price change trend graph, efficiently assisting a researcher to quickly determine the market risk prediction result of the question to be inquired, and improving the efficiency and accuracy of market risk prediction.

Example two

In some embodiments, the market risk prediction apparatus 20 may include a plurality of functional modules composed of program code segments. The program code of the various program segments in the market risk prediction unit 20 may be stored in a memory of the electronic device and executed by the at least one processor to perform the functions of market risk prediction (described in detail with reference to fig. 1).

In this embodiment, the market risk prediction unit 20 may be divided into a plurality of functional modules according to the functions performed by the market risk prediction unit. The functional module may include: a parsing and acquisition module 201, a lookup module 202, an acquisition and analysis module 203, an analysis module 204, and an output module 205. The module referred to herein is a series of computer readable instruction segments stored in a memory that can be executed by at least one processor and that can perform a fixed function. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

And the analyzing and acquiring module 201 is used for analyzing the received market risk prediction request to acquire the question to be queried.

The searching module 202 is configured to search at least one historical event similar to the question to be queried from a preset data source.

In an optional embodiment, the searching module 202 searches for at least one historical event similar to the question to be queried from a preset data source, including:

identifying key words in the question to be queried, identifying key words matched with the key words in the preset database, and determining all matched key words as preset key words;

In this embodiment, preset keywords are pre-stored in a database, the question to be queried is analyzed, and the question to be queried is matched with the preset keywords pre-stored in the database to obtain the preset keywords.

In this embodiment, the event tag model and the question type identification model may be trained in advance, where the training process of the event tag model and the question type identification model is the prior art, and details are not described here in this embodiment.

Illustratively, the accuracy of identifying the event type of a question to be queried reaches 97%, the event mainly comprises a date type event, a target event and a macro news event, the accuracy of identifying the type of the date and the target date reaches 100%, the macro basic plane refers to the analysis of basic conditions of macro economy, industry and companies, the macro basic plane is calculated according to a news peak value and is influenced by noise, and the accuracy of identifying can reach 97%, for example, the peak judgment of the macro event, the judgment of the hot event trend similar to a search engine needs to comprehensively consider a plurality of disturbance factors, such as data relation with a time sequence and a lot of noise contained in news, but the accuracy of identifying can also reach 97%.

In this embodiment, the preset query rule is determined according to the historical data based on the types of the preset keywords and the corresponding tags, for example: the question to be inquired is 'stock market historical expression after mid-autumn festival', and the type of the question to be inquired is as follows: the date and event label, wherein the label corresponding to the date is: after mid-autumn festival, the corresponding labels of the event labels are: the stock market, stock A and American stock market trend, creates a corresponding query strategy according to a preset query rule, and queries the stock market of stock Shanghai Shenshen 300 of 5 days after the mid-autumn festival of the past 10 years and the American stock standard 500 market trend of the past 10 years, namely: the at least one historical event obtained by searching is: the market trend of Shanghai Shen 300 is A after T +5 days in mid-autumn; the American stock standard 500 market trend is about T +5 days after mid-autumn festival.

In the embodiment, after the types of the question to be queried are combined by adopting multiple combinations, a query strategy is created based on the tags and the types in the question to be queried, and at least one historical event similar to the question to be queried is queried, so that the similarity between the queried historical event and the question to be queried is ensured, and the accuracy of subsequent market risk prediction is improved.

The obtaining and analyzing module 203 is configured to obtain a first price change trend graph of each historical event, and analyze the first price change trend graph of each historical event to obtain an analysis result of each historical event.

In an alternative embodiment, the obtaining and analyzing module 203 analyzes the first price variation trend graph of each historical event, and obtaining the analysis result of each historical event includes:

For example, if 5 market trends of a shanghai depth 300 are an upward trend and 5 downward trends after 5 days of mid-autumn in the last 10 years, the upward trend is calculated, and then the probability of the upward trend type is 5/10-0.5, the probability of the downward trend type is 5/10-0.5, and the probability of the upward trend type is 0.5 and the probability of the downward trend type is 0.5, as the analysis results of the corresponding events.

The analysis module 204 is configured to analyze an analysis result of the at least one historical event to obtain a second price variation trend graph of the question to be queried.

In an optional embodiment, the analyzing module 204 analyzes the analysis result of the at least one historical event, and obtaining the second price variation trend graph of the question to be queried includes:

obtaining a plurality of probabilities of a plurality of trend types of each historical event, calculating a difference value of any two probabilities of each trend type, and keeping a plurality of probabilities of the difference value within a preset difference value threshold range as the probability of each trend type;

And the output module 205 is configured to output a market risk prediction result of the question to be queried based on the second price variation trend graph.

In an optional embodiment, the outputting module 205 outputs the market risk prediction result of the question to be queried based on the second price change trend graph includes:

when the second price variation trend graph is in an ascending trend, outputting a market risk prediction result of the question to be inquired as a low risk; or

In the embodiment, by predicting the second price variation trend chart of the question to be queried, an efficient auxiliary researcher can quickly determine the market risk prediction result of the question to be queried, and the efficiency and the accuracy of market risk prediction are improved.

In the embodiment, at least one historical event similar to the question to be queried is obtained from a preset data source by adopting a created query strategy, and based on a price change trend chart of the at least one historical event under similar situations, namely the performance of historical investment products, generalizing the price change trend chart rule of the statistical target to predict the market risk without the need that a researcher firstly searches information from a plurality of preset data sources, then, the market information is obtained through SQL, tools such as excel and the like are used for data processing and drawing, finally, word is used for writing a market risk prediction report, researchers need to switch among various tools, the efficiency is low, the time consumption is long, the fault tolerance rate is low, time delay and information omission are caused, the efficiency and the accuracy of market risk prediction are low, the investment is prone to be lost, and the efficiency and the accuracy of market risk prediction are improved.

In summary, in the market risk prediction apparatus according to this embodiment, at least one historical event similar to the question to be queried is searched from a preset data source, after the types of the question to be queried are combined by using multiple combinations, a query policy is created based on the tags and the types in the question to be queried, and then at least one historical event similar to the question to be queried is queried, so that the similarity between the queried historical event and the question to be queried is ensured, and further, the accuracy of subsequent market risk prediction is improved. Analyzing the first price change trend graph of each historical event to obtain the analysis result of each historical event, and subsequently, considering the overall analysis result of each historical event when market risk prediction is carried out, rather than singly considering one first price change trend graph of each historical event to carry out market risk prediction, thereby improving the accuracy of market risk prediction. Analyzing the analysis result of the at least one historical event to obtain a second price change trend graph of the question to be inquired, outputting a market risk prediction result of the question to be inquired based on the second price change trend graph, efficiently assisting a researcher to quickly determine the market risk prediction result of the question to be inquired, and improving the efficiency and accuracy of market risk prediction.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.

It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiment of the present invention, and may be a bus-type configuration or a star-type configuration, and the electronic device 3 may include more or less other hardware or software than those shown, or a different arrangement of components.

In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.

It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.

In some embodiments, the memory 31 is used for storing program codes and various data, such as the market risk prediction unit 20 installed in the electronic device 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic device 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the whole electronic device 3 by using various interfaces and lines, and executes various functions of the electronic device 3 and processes data by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.

In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and installed various types of application programs (such as the market risk prediction apparatus 20), program code, and the like, such as the various modules described above.

The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the modules illustrated in fig. 2 are program code stored in the memory 31 and executed by the at least one processor 32, so as to implement the functions of the modules for the purpose of market risk prediction.

Illustratively, the program code may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to accomplish the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing certain functions, which are used for describing the execution process of the program code in the electronic device 3. For example, the program code may be partitioned into a parsing and acquisition module 201, a lookup module 202, an acquisition and analysis module 203, an analysis module 204, and an output module 205.

In one embodiment of the present invention, the memory 31 stores a plurality of computer readable instructions that are executed by the at least one processor 32 to implement the functions of market risk prediction.

Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present invention may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims

1. A method for market risk prediction, the method comprising:

and outputting a market risk prediction result of the question to be queried based on the second price change trend graph.

2. The market risk prediction method of claim 1, wherein the searching for at least one historical event similar to the question to be queried from a preset data source comprises:

3. The market risk prediction method of claim 2, wherein the creating a target query policy based on the plurality of labels of the preset keyword and the type of the question to be queried comprises:

4. The method of market risk prediction according to claim 1, wherein the analyzing the first price change trend graph for each of the historical events to obtain the analysis result for each of the historical events comprises:

5. The method for predicting market risk according to claim 1, wherein the analyzing the analysis result of the at least one historical event to obtain the second price change trend graph of the question to be queried comprises:

6. The method for predicting market risk according to claim 1, wherein the analyzing the analysis result of the at least one historical event to obtain the second price change trend graph of the question to be queried comprises:

7. The market risk prediction method of claim 1, wherein outputting the market risk prediction result of the question to be queried based on the second price change trend graph comprises:

8. A market risk prediction apparatus, characterized in that the apparatus comprises:

9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the market risk prediction method according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the market risk prediction method according to any one of claims 1 to 7.