Scene simulation method, device, equipment, medium and computer program product

Abstract

The invention discloses a scene simulation method, device and equipment, a medium and a computer program product, relates to the technical field of Internet, and can be applied to the field of financial science and technology. Obtaining target scene data; the target scene data comprises at least one of target cross-market data, target cross-variety data, target cross-industry data and target weather data; performing data processing on the target scene data to obtain target scene time sequence data; performing market condition reasoning simulation on the target scene time sequence data by adopting a scene simulation model to obtain a target market scene; the target market scenarios comprise an oscillation market, a fluctuation market and an extreme market. By adopting the technical scheme, the scene data is simulated through the scene simulation model, and rich and diversified market scenes are generated.

Description

Technical Field

[0001] The present invention relates to the field of Internet technologies and can be applied to the field of fintech. In particular, it relates to a scenario simulation method, device, equipment, medium, and computer program product. Background Art

[0002] In the fintech industry, a transaction evaluation strategy is to evaluate transactions to reduce transaction risks. Conducting scenario simulation on the transaction evaluation strategy is an important transaction risk assessment method, which is used to evaluate the potential performance and risks of the strategy before applying it in the real market environment. Scenario simulation helps traders understand the reactions of the strategy under different circumstances by simulating various possible market conditions, thereby optimizing the strategy and reducing risks. Therefore, how to accurately and diversely predict the corresponding market results has become an urgent problem to be solved currently.

[0003] Currently, during the process of conducting scenario simulation on the transaction evaluation strategy, the current scenario simulation model cannot predict complex market scenarios for the obtained financial scenario data; and it cannot predict the corresponding market scenarios for personalized market quotation requirements, and the scenario data corresponding to different market scenarios cannot meet the personalized needs of users. Summary of the Invention

[0004] The present invention provides a scenario simulation method, device, equipment, storage medium, and computer program product, which simulate scenario simulation data through a scenario simulation model to generate rich and diverse market scenarios.

[0005] According to one aspect of the present invention, there is provided a scenario simulation method, including:

[0006] Obtaining target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data;

[0007] Performing data processing on the target scenario data to obtain target scenario time series data;

[0008] Performing market quotation inference simulation on the target scenario time series data by using a scenario simulation model to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

[0009] According to another aspect of the present invention, there is provided a scenario simulation device, including:

[0010] A scenario data acquisition module, configured to obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data;

[0011] A scenario time-series data acquisition module, configured to process the target scenario data to obtain target scenario time-series data;

[0012] A market scenario determination module, configured to perform market condition inference simulation on the target scenario time-series data by using a scenario simulation model to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the scenario simulation method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the scenario simulation method according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, there is provided a computer program product including a computer program, and when the computer program is executed by a processor, it implements the scenario simulation method according to any embodiment of the present invention.

[0019] The technical solution of the embodiment of the present invention simulates scenario data through a scenario simulation model to obtain a corresponding market simulation result, solves the problem of scenario simulation for a trading evaluation strategy, and can generate a rich variety of market scenarios based on scenario data.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a scenario simulation method provided according to an embodiment of the present invention;

[0023] Figure 2 It is a flowchart of a scenario simulation method provided according to an embodiment of the present invention;

[0024] Figure 3 It is a flowchart of a scenario simulation method provided according to an embodiment of the present invention;

[0025] Figure 4 It is a structural block diagram of a scenario simulation device provided according to an embodiment of the present invention;

[0026] Figure 5 It is a structural block diagram of an electronic device provided for an embodiment of the present invention. Detailed implementation manners

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] In addition, it should be noted that in the technical solutions of the present invention, the collection, storage, use, processing, transmission, provision, and disclosure of scenario data and the like all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0029] Figure 1 It is a flowchart of a scenario simulation method provided according to an embodiment of the present invention. The present invention is applicable to the situation of performing scenario simulation on a trading evaluation strategy. This method can be executed by the scenario simulation device provided in the embodiment of the present invention. The scenario simulation device can be implemented in the form of hardware and / or software and can be integrated into an electronic device with scenario simulation functions, such as a server. As Figure 1 shown, the method includes:

[0030] S110. Obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data.

[0031] Among them, scenario simulation is to simulate and predict the behavior of complex systems or processes in a financial environment, especially the shocks or increases in financial transactions; while the target scenario data is the scenario data that affects the results of scenario simulation, which can include financial data or non-financial data; financial data can include cross-market data, cross-commodity data, and cross-industry data; cross-market data is to collect historical transaction data from major global financial markets, including stocks, futures, bonds, foreign exchange, etc.; cross-commodity data covers various commodity futures, such as agricultural products, energy, metals, etc.; cross-industry data includes different industry indexes, company financial reports, etc.; non-financial data is target weather data, specifically historical weather data, such as temperature, rainfall, natural disasters, etc., because these factors may affect the prices of certain industries or commodities.

[0032] Specifically, obtain the target scenario data and the time stamps corresponding to each scenario data, and the scenario data includes at least one of target cross-market data, target cross-commodity data, target cross-industry data, and target weather data. It should be noted that the specific acquisition method of the target scenario data can be directly input, or data can be retrieved from a database, or directly imported from an input data table. The specific acquisition method is not specifically limited in the present invention.

[0033] S120. Perform data processing on the target scenario data to obtain target scenario time series data.

[0034] The target scenario time series data is the scenario data carrying the corresponding time range; the data processing can be data cleaning of the target scenario data; specifically, by performing data cleaning on the target scenario data, removing outliers, processing duplicate data, filling in missing values, and standardizing the data format; to obtain the target scenario time series data.

[0035] It can be understood that by performing data cleaning on the target scenario data, the quality and consistency of the subsequent scenario time series data are ensured, and the accuracy of subsequent data analysis is further improved.

[0036] Optionally, performing data processing on the target scenario data to obtain target scenario time series data includes:

[0037] Integrate the target scenario data according to the time axis to obtain intermediate scenario time series data;

[0038] Extract features from the intermediate scenario time series data to obtain target scenario features;

[0039] Obtain the target scenario time series data according to the intermediate scenario time series data and the target scenario features.

[0040] Among them, the intermediate scenario time-series data is time-series data in the order of the time axis; the scenario features are the features within the time range corresponding to the scenario data, including the price change rate and volatility in financial data; and seasonal factors in non-financial data.

[0041] Specifically, sort the target cross-market data, target cross-variety data, target cross-industry data, and target weather data to be subjected to data cleaning according to the time stamp, and integrate the sorted data into a time series as the intermediate scenario time-series data; extract features from the intermediate scenario time-series data to obtain the corresponding target scenario features within each time range, including the price change rate and volatility in financial data, and seasonal factors in non-financial data; supplement the extracted target scenario features to the intermediate time-series data to obtain the target scenario time-series data. It should be noted that specific data sorting, data integration, and feature extraction can adopt existing conventional technologies, as long as the operation on the data can be realized, and the present invention does not specifically limit this.

[0042] It can be understood that by performing feature extraction on the scenario data after time series processing and splicing it with the original scenario data, the target scenario time-series data is obtained, further enriching the diversity of the target scenario time-series data.

[0043] Optionally, based on the intermediate scenario time-series data and the target scenario features, the target scenario time-series data is obtained, including:

[0044] Splice the intermediate scenario time-series data and the target scenario features to obtain candidate scenario time-series data;

[0045] Process the candidate scenario time-series data to obtain the target scenario time-series data.

[0046] Specifically, determine the common time range of the intermediate scenario time-series data and the target scenario features, and supplement the target scenario features to the corresponding intermediate scenario time-series data based on the time range to obtain candidate scenario time-series data, and perform smoothing and denoising processing on the time series in the candidate scenario time-series data to obtain the target scenario time-series data.

[0047] Among them, processing the candidate scenario time-series data specifically adopts at least one of the following implementation steps:

[0048] Optionally, introduce noise into the candidate scenario data to obtain the target scenario time-series data.

[0049] Optionally, perform time series splitting on the candidate scenario time-series data to obtain the target scenario time-series data.

[0050] Optionally, perform trend analysis on the candidate scenario time-series data to obtain the target scenario time-series data.

[0051] Specifically, when the amount of data is too small or there is only one piece of data, noise is introduced according to the time series; or the complete long time series is split into short time series; or clearer market signals are extracted from the scenario time series data; for example, the market scenario is in an upward, downward or fluctuating characteristic in the oscillating scenario, and based on different characteristics, it is supplemented into the candidate scenario time series data to obtain the target scenario time series data.

[0052] It can be understood that by increasing the amount of data, the scenario time series data input into the simulation model is further enriched, enabling the model to better adapt to various possible input situations and ensuring that the simulated market scenarios are more diverse.

[0053] Furthermore, to enhance the diversity of the amount of data, the scenario data of the split short time series can be reassembled. The split short time series are arranged, combined and assembled according to the time series to generate a new time series, which is placed in the short time series list as the target scenario time series.

[0054] It can be understood that by enhancing the amount of data and the diversity of the processed data, the amount of input data is expanded, and the diversity of the time series data is further increased, enriching the scenario time series data.

[0055] S130. Use the scenario simulation model to conduct market condition inference and simulation on the target scenario time series data to obtain the target market scenario; the target market scenario includes an oscillating market, a fluctuating market and an extreme market.

[0056] Among them, the scenario simulation model is a pre-trained model. Through the input target scenario time series data, it outputs the corresponding future prediction scenario; the target market scenario is used to test the effect of the current trading strategy; in an oscillating market, the market price fluctuates repeatedly within a certain period, and the investment risk is relatively high at this time; a fluctuating market refers to the fluctuations of the prices of various financial assets in the financial market; an extreme market is characterized by violent fluctuations in asset prices, exceeding the normal state of the market.

[0057] Specifically, the target scenario time series data is input into the pre-trained scenario simulation model, and the corresponding future prediction market scenario is output, including an oscillating market, a fluctuating market and an extreme market, etc.

[0058] It can be understood that through the market simulation of the future market scenario by the scenario simulation model, the market scenario of the current trading strategy is predicted, providing a basis and direction for investment risk.

[0059] Furthermore, by adjusting the temperature parameter of the scenario simulation model, the randomness and diversity of the generated data can be controlled to simulate different market sentiments and uncertainties, which can improve the stability of the output while maintaining the model performance and enhance the diversity of the predicted market scenario.

[0060] Optionally, after obtaining the target market scenario, the strategy corresponding to the input target scenario data can be evaluated through the target market scenario; the trading evaluation strategy designed in advance based on market theory and experience performs market scenario simulation on a large amount of scenario time series data of the current trading strategy through a scenario simulation model, and evaluates the trading strategy from the market conditions of the target market scenario to reduce trading risks.

[0061] In the embodiment of the present invention, target scenario data is obtained; the target scenario data is processed to obtain target scenario time series data; a scenario simulation model is used to perform market condition inference simulation on the target scenario time series data to obtain a target market scenario. The above technical solution solves the problem of performing market scenario simulation on the trading evaluation strategy. By simulating the scenario data through the scenario simulation model, a rich variety of market scenarios can be generated, and further provide a better and more convenient scenario simulation service for quantitatively evaluating the trading strategy.

[0062] Figure 2 It is a flowchart of a scenario simulation method provided by an embodiment of the present invention. On the basis of the above embodiment, the scenario simulation model may include a first scenario simulation model and / or a second scenario simulation model; based on this, the specific market condition inference simulation method for performing market condition inference simulation on the target scenario time series data by using the scenario simulation model is supplemented. It should be noted that for the parts not detailed in the embodiment of the present invention, reference may be made to the relevant descriptions of other embodiments. As Figure 2 shown, the method includes:

[0063] S210. Obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data.

[0064] S220. Process the target scenario data to obtain target scenario time series data.

[0065] S230. Use the first scenario simulation model to perform market condition inference simulation on the target scenario time series data to obtain a first simulated market scenario.

[0066] Among them, the first scenario simulation model is a time series model, preferably a generative model in the present invention, which can generate new data sequences based on the learned data sequences, not only tries to extract features from the input data to distinguish different categories, but also can simulate the process of data generation; the first simulated market scenario is the scenario time series data corresponding to the target scenario time series data in a future period of time.

[0067] Specifically, based on the generative model, future market scenario prediction is performed on the input target scenario time series data to obtain the corresponding market scenario sequence. For example: input the scenario time series data, and the time series data for a period of time in the future is output through the first scenario simulation model. Based on the first simulated market scenario, the current trading strategy can be analyzed in the market scenario for a period of time in the future.

[0068] S240. Perform image conversion on the target scenario time series data to obtain the target scenario time series diagram.

[0069] Among them, the image conversion is to generate the corresponding market condition picture for a single short time series through the Transform model; the target scenario time series diagram is a market condition picture that can represent the characteristics of the target scenario time series data. For example, when the market data is in a unilateral upward process, the corresponding market condition picture is an oscillating diagram, and the characteristics corresponding to this oscillating diagram are large-scale upward or small-scale upward.

[0070] Specifically, after obtaining the list of short time series in the target scenario time series data, for each short time series in the list of short time series, the corresponding market condition picture is generated through the Transform model as the target scenario time series diagram.

[0071] S250. Use the second scenario simulation model to perform market condition reasoning simulation on the target scenario time series diagram to obtain the second simulated market scenario.

[0072] Among them, the second scenario simulation model is an image model, preferably a diffusion model in the embodiments of the present invention, and the second simulated market scenario is a market scenario prediction diagram corresponding to the target scenario time series data.

[0073] Specifically, through the input target scenario time series diagram, the corresponding market scenario prediction diagram is output based on the diffusion model. For example: input the target scenario time series diagram into the second scenario simulation model, and the second simulated market scenario for a period of time in the future can be output. Based on the second simulated market scenario, it can be analyzed that the current trading strategy has a 30% return in a period of time in the future.

[0074] S260. Determine the target market scenario according to the first simulated market scenario and the second simulated market scenario.

[0075] Specifically, based on the predicted scenario time series data of the first simulated market scenario and the predicted scenario diagram of the second simulated market scenario, the predicted market scenario result is determined. The market scenario is predicted in two ways: vector text and image, and the predicted scenario sequence effect and picture effect are obtained, making the prediction result richer, more vivid and observable.

[0076] Optionally, in the embodiments of the present invention, the target market scenario may include a first simulated market scenario or a second simulated market scenario; based on specific application requirements, it may be represented separately by market scenario data or separately by a market scenario graph, or represented in combination according to market scenario data and a market scenario graph; the specific display method of the target market scenario is not specifically limited in the present invention, and the scenario time series data and / or the scenario graph can represent the prediction result.

[0077] In the embodiments of the present invention, the scenario time series data is predicted through different simulated scenario models, ensuring that the market scenario prediction results corresponding to multiple market scenarios are more abundant, vivid and observable, capable of simulating different market sentiments and uncertainties, and improving the diversity of the generated market scenarios.

[0078] Optionally, the method for determining the target market scenario further includes: in response to a market profile graph drawn by a user; performing sequence conversion on the market profile graph using a second scenario simulation model to obtain a market time series.

[0079] Wherein, the market profile graph is a scenario prediction graph drawn by the user, and there is no target scenario time series data corresponding to the current scenario prediction graph in the current scenario time series data.

[0080] Specifically, obtain the personalized market profile graph drawn by the user, and use the diffusion model of the second scenario simulation model to perform sequence conversion on the market profile graph to convert it into corresponding market time series data.

[0081] It can be understood that based on the user's hand-drawn profile graph, market time series conversion is performed; specific scenarios can be generated to meet the scenario time series data of personalized needs. It can also be in the case where the amount of input target scenario time series data is small, and the corresponding market time series is obtained through the personalized market profile graph drawn by the user and supplemented into the target scenario time series data to further increase the amount of input data.

[0082] In the embodiments of the present invention, by introducing the time series conversion of the personalized market profile graph, the detection of the second scenario simulation model is realized, and at the same time, the required specific market scenarios can be generated to meet the personalized needs of various users.

[0083] Figure 3 It is a flowchart of a scenario simulation method provided according to the embodiments of the present invention. On the basis of the above embodiments, the training method of the scenario simulation model is supplemented in the embodiments of the present invention. It should be noted that for the parts not detailed in the embodiments of the present invention, reference can be made to the relevant descriptions of other embodiments. As Figure 3 shown, the method includes:

[0084] S310. Obtain sample scenario time series data, and perform picture conversion on the sample scenario time series data to obtain a sample scenario time series graph.

[0085] Among them, the sample scenario time-series data is the processed sample scenario data; the sample scenario time-series data is a short time-series segment; the sample scenario time-series graph is the market graph corresponding to the sample scenario time-series data.

[0086] Specifically, obtain the processed sample scenario time-series data, and perform image conversion through the Transformer model to obtain the sample scenario time-series graph corresponding to the sample scenario time-series data.

[0087] Optionally, before obtaining the sample scenario time-series data, process the sample scenario data, including: obtaining historical scenario data, arranging it according to the time axis of the historical scenario data to obtain the corresponding historical scenario time-series data, extracting the scenario features within the corresponding time range, splicing the scenario features within the corresponding time range with the time-series data, and processing the spliced data to obtain the corresponding sample scenario time-series data.

[0088] Optionally, when the sample scenario time-series data is too scarce, or a specific market scenario is required to train the scenario simulation model, in response to the market graph outline drawn by the user, use the second scenario simulation model to perform sequence conversion on the market graph outline to obtain the market time series; perform processing based on the current market time series to obtain the corresponding sample scenario time-series data. By introducing the personalized drawn market graph, the corresponding sample scenario time-series data is obtained, further enriching the diversity of the sample scenario time-series data.

[0089] It can be understood that by processing the scenario data, the diversity of the time-series data is enriched; and image conversion is performed on the time-series data to obtain the corresponding scenario time-series graph, providing data support for subsequent training of the second scenario simulation model; and further ensuring that the subsequent simulation model can learn richer features.

[0090] S320. Use the sample scenario time-series data to train the first scenario simulation model in the scenario simulation model.

[0091] The first scenario simulation model is trained on time-series data and can be a generative model. Specifically, input the sample scenario time-series data into the first scenario simulation model in the scenario simulation model to obtain the predicted market scenario time series for a future period.

[0092] S330. Use the sample scenario time-series graph to train the second scenario simulation model in the scenario simulation model.

[0093] The second scenario simulation model is trained on the sample scenario time-series graph to predict the market scenario graph for a future period and can be a diffusion model. Specifically, input the sample scenario time-series graph into the second scenario simulation model in the scenario simulation model, and output the corresponding sample market scenario graph.

[0094] Optionally, the trained scenario simulation model is optimized. The performance of the model can be optimized by adjusting parameters, using regularization techniques, etc.; the corresponding parameters are adjusted according to specific usage requirements to optimize the model performance and improve the accuracy and efficiency of the scenario simulation model in simulating market scenarios. It should be noted that the specific model optimization method in the embodiments of the present invention is not specifically limited.

[0095] In the embodiments of the present invention, the processed short-time series segments and historical market condition pictures are used to train the generative model and the diffusion model respectively to learn the dynamic behavior of the market; and the historical market condition data and features used to train the scenario simulation model can be expanded and adjusted according to actual needs; further, by adjusting parameters, it is ensured that the generative model and the diffusion model used in the scenario simulation model can be replaced and adjusted according to actual needs.

[0096] S340. Obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data.

[0097] S350. Process the target scenario data to obtain target scenario time series data.

[0098] S360. Use the scenario simulation model to perform market condition inference and simulation on the target scenario time series data to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

[0099] In the embodiments of the present invention, the scenario simulation model is pre-trained, and the historical sample scenario data corresponding to the training simulation model can be adjusted according to actual needs to improve the scalability of the scenario simulation model, learn the behavior of the market from the historical scenario data, so as to use the scenario simulation model to generate a large number of simulation scenarios to ensure the quantitative evaluation of trading strategies.

[0100] Figure 4 It is a structural block diagram of a scenario simulation device provided according to an embodiment of the present invention. It is applicable to the situation of scenario simulation for trading evaluation strategies. The scenario simulation device can be implemented in the form of hardware and / or software and can be integrated into an electronic device with scenario simulation functions, such as a server. As Figure 4 shown, the scenario device 400 includes a scenario data acquisition module 410, a scenario time series data acquisition module 420, and a market scenario determination module 430.

[0101] The scenario data acquisition module 410 is used to obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data;

[0102] A scenario time series data acquisition module 420 is configured to process target scenario data to obtain target scenario time series data;

[0103] A market scenario determination module 430 is configured to perform market condition inference simulation on the target scenario time series data by using a scenario simulation model to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

[0104] In an embodiment of the present invention, target scenario data is acquired; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data; the target scenario data is processed to obtain target scenario time series data; a scenario simulation model is used to perform market condition inference simulation on the target scenario time series data to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market. The above technical solution solves the problem of performing scenario simulation on a trading evaluation strategy. By simulating scenario data through a scenario simulation model, market simulation result scenario simulation data can be obtained, and a rich variety of market scenarios can be generated, and further provide a higher-quality and more convenient scenario simulation service for quantitatively evaluating trading strategies.

[0105] Optionally, the scenario time series data acquisition module 420 includes: an intermediate scenario time series data acquisition unit, a target scenario feature determination unit, and a target scenario time series data determination unit;

[0106] The intermediate scenario time series data acquisition unit is configured to integrate the target scenario data according to a time axis to obtain intermediate scenario time series data;

[0107] The target scenario feature determination unit is configured to extract features from the intermediate scenario time series data to obtain target scenario features;

[0108] The target scenario time series data determination unit is configured to obtain target scenario time series data according to the intermediate scenario time series data and the target scenario features.

[0109] Optionally, the target scenario time series data determination unit is specifically configured to splice the intermediate scenario time series data and the target scenario features to obtain candidate scenario time series data; and perform processing on the candidate scenario time series data to obtain target scenario time series data.

[0110] Optionally, the scenario simulation model includes a first scenario simulation model and / or a second scenario simulation model;

[0111] Correspondingly, the market scenario determination module 430 is specifically configured to perform market condition inference simulation on the target scenario time series data by using the first scenario simulation model to obtain a first simulated market scenario;

[0112] Perform image conversion on the time-series data of the target scenario to obtain the time-series diagram of the target scenario;

[0113] Use the second scenario simulation model to perform market condition inference simulation on the time-series diagram of the target scenario to obtain the second simulated market scenario;

[0114] Determine the target market scenario based on the first simulated market scenario and the second simulated market scenario.

[0115] Optionally, the scenario device 400 further includes a simulation model training module, configured to obtain sample scenario time-series data, and perform image conversion on the sample scenario time-series data to obtain a sample scenario time-series diagram;

[0116] Use the sample scenario time-series data to train the first scenario simulation model in the scenario simulation model;

[0117] Use the sample scenario time-series diagram to train the second scenario simulation model in the scenario simulation model.

[0118] Optionally, the market scenario determination module 430 is specifically configured to respond to the market condition contour diagram drawn by the user; use the second scenario simulation model to perform sequence conversion on the market condition contour diagram to obtain a market condition time series.

[0119] The scenario simulation device provided by the embodiments of the present invention can execute the scenario simulation method provided by any embodiment of the present invention, and has the corresponding function modules and beneficial effects for executing the method.

[0120] According to the embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0121] Figure 5 It is a structural block diagram of an electronic device provided by an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0122] Such as Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0123] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the scenario simulation method.

[0125] In some embodiments, the scenario simulation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the scenario simulation method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the scenario simulation method in any other appropriate manner (e.g., by means of firmware).

[0126] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0127] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0128] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0131] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0132] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0133] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A scenario simulation method, characterized in that, Including: Obtain target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data; Perform data processing on the target scenario data to obtain target scenario time series data; Use a scenario simulation model to perform market condition inference simulation on the target scenario time series data to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

2. The method according to claim 1, wherein Performing data processing on the target scenario data to obtain target scenario time series data includes: Integrate the target scenario data according to the time axis to obtain intermediate scenario time series data; Extract features from the intermediate scenario time series data to obtain target scenario features; Obtain target scenario time series data based on the intermediate scenario time series data and the target scenario features.

3. The method according to claim 2, wherein Obtaining target scenario time series data based on the intermediate scenario time series data and the target scenario features includes: Concatenate the intermediate scenario time series data and the target scenario features to obtain candidate scenario time series data; Perform processing on the candidate scenario time series data to obtain target scenario time series data.

4. The method according to claim 1, characterized in that The scenario simulation model includes a first scenario simulation model and / or a second scenario simulation model; correspondingly, using the scenario simulation model to perform market condition inference simulation on the target scenario time series data to obtain a target market scenario includes: Use the first scenario simulation model to perform market condition inference simulation on the target scenario time series data to obtain a first simulated market scenario; Perform image conversion on the target scenario time series data to obtain a target scenario time series diagram; Use the second scenario simulation model to perform market condition inference simulation on the target scenario time series diagram to obtain a second simulated market scenario; Determine the target market scenario based on the first simulated market scenario and the second simulated market scenario.

5. The method according to claim 1, wherein The training process of the scenario simulation model is as follows: Obtain sample scenario time series data and perform image conversion on the sample scenario time series data to obtain a sample scenario time series diagram; Use the sample scenario time series data to train the first scenario simulation model in the scenario simulation model; Use the sample scenario time series diagram to train the second scenario simulation model in the scenario simulation model.

6. The method according to claim 4, characterized in that, It also includes: Respond to the market condition profile diagram drawn by the user; Use the second scenario simulation model to perform sequence conversion on the market condition profile diagram to obtain a market condition time series.

7. A scenario simulation device, characterized in that, Including: A scenario data acquisition module for acquiring target scenario data; wherein, the target scenario data includes at least one of target cross-market data, target cross-variety data, target cross-industry data, and target weather data; A scenario time series data acquisition module for performing data processing on the target scenario data to obtain target scenario time series data; A market scenario determination module for using a scenario simulation model to perform market condition inference simulation on the target scenario time series data to obtain a target market scenario; the target market scenario includes a volatile market, a fluctuating market, and an extreme market.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the scenario simulation method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the scenario simulation method according to any one of claims 1-6 when the computer instructions are executed by a processor.

10. A computer program product, characterized in that, The computer program product includes a computer program which, when executed by a processor, implements the scenario simulation method according to any one of claims 1-6.

Images