Recommendation Method, Device, Terminal Device and Medium for Hedging Trading Products

Abstract

The present invention relates to the field of artificial intelligence, and particularly to a method, device, terminal device and medium for recommending hedging trading products. The method outputs a hedging value threshold through a threshold prediction network according to the holding details of the held products, the first price trend and the first trading volume trend, as well as the second price trend and the second trading volume trend of the products to be recommended, determines the overall hedging value according to the holding quantity of the held products and the hedging value, then outputs a recommendation index value through a recommendation index value evaluation model for the hedging value threshold and the overall hedging value, and finally determines the rise and fall type of the products to be recommended according to the hedging value of the products to be recommended, and detects whether the rise and fall type of the recommended products meets the required type corresponding to the recommendation index value to determine the target recommended products. The influence of the market conditions on the recommended hedging products is reduced, and thus the accuracy of the recommendation of hedging trading products is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and particularly to a health prediction method, device, terminal device and medium based on artificial intelligence. Background Art

[0002] In the existing hedging transaction, the overall hedging value of the held products is compared with a fixed threshold, and when the overall hedging value reaches the threshold, hedging products are recommended, and then traders or computers execute hedging transactions according to the recommended hedging products.

[0003] However, the market conditions are relatively complex. Using a fixed threshold as a reference to recommend hedging products cannot accurately recommend hedging products, resulting in additional hedging transaction costs and affecting the efficiency of hedging transactions. Therefore, how to reduce the impact of market conditions on the recommended hedging products to improve the accuracy of recommendation has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, device, terminal device and medium for recommending hedging transaction products to solve the problem of reducing the impact of market conditions on the recommended hedging products to improve the accuracy of recommendation.

[0005] In a first aspect, an embodiment of the present invention provides a method for recommending hedging transaction products, and the recommendation method includes:

[0006] Obtain the holding details, the first price trend and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended;

[0007] Input the holding details, the first price trend and the first trading volume trend of each held product, respectively, and the second price trend and the second trading volume trend of each product to be recommended into a trained threshold prediction network, and output a hedging value threshold;

[0008] Obtain the hedging value of each held product, calculate the product of the number of holdings of each held product and the corresponding hedging value, and determine the sum of all products as the overall hedging value;

[0009] Input the overall hedging value and the hedging value threshold into a preset recommended metric value evaluation model, and output a recommended metric value;

[0010] Obtain the hedging value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended metric value, and determine the product to be recommended that meets the required type as the target recommended product.

[0011] Second aspect, an embodiment of the present invention provides a recommendation device for hedging trading products, the recommendation device includes:

[0012] A product information acquisition module, configured to acquire the position details, the first price trend, and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended;

[0013] A hedging value threshold prediction module, configured to input the position details, the first price trend, and the first trading volume trend of each held product into a trained threshold prediction network respectively together with the second price trend and the second trading volume trend of each product to be recommended, and output a hedging value threshold;

[0014] An overall hedging value calculation module, configured to obtain the hedging value of each held product, calculate the product of the number of positions of each held product and the corresponding hedging value, and determine the sum of all products as the overall hedging value;

[0015] A recommended index value acquisition module, configured to input the overall hedging value and the hedging value threshold into a preset recommended index value evaluation model, and output a recommended index value;

[0016] A target recommended product determination module, configured to obtain the hedging value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value, and determine the product to be recommended that meets the required type as the target recommended product.

[0017] Third aspect, an embodiment of the present invention provides a terminal device, the terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the recommendation method described in the first aspect is implemented.

[0018] Fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the recommendation method described in the first aspect is implemented.

[0019] The beneficial effects of the embodiments of the present invention compared with the prior art are:

[0020] In the embodiments of the present invention, the holding details, the first price trend, and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended are input into a trained threshold prediction network to output a hedging value threshold. The hedging value of each held product is obtained, and the overall hedging value is calculated in combination with the number of holdings. The overall hedging value and the hedging value threshold are input into a preset recommended index value evaluation model to output a recommended index value. According to the obtained hedging value of the product to be recommended, the rise and fall type of the product to be recommended is determined, and it is detected whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value. The product to be recommended that meets the required type is determined as the target recommended product. Using the price trend and the trading volume trend to predict the hedging value threshold enables the threshold to accurately follow the market conditions, thereby making the recommendation timing more accurate. At the same time, evaluating each product with the threshold that follows the market conditions can accurately screen out the hedging products to be recommended, effectively reducing the cost of hedging transactions and improving the efficiency of hedging transactions. BRIEF 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 use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 is a schematic diagram of an application environment of a method for recommending hedging trading products provided by an embodiment of the present invention;

[0023] Figure 2 is a schematic flowchart of a method for recommending hedging trading products provided by an embodiment of the present invention;

[0024] Figure 3 is a schematic flowchart of a recommendation of a hedging trading product portfolio provided by an embodiment of the present invention;

[0025] Figure 4 is a schematic structural diagram of a device for recommending hedging trading products provided by an embodiment of the present invention;

[0026] Figure 5 is a schematic structural diagram of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0028] It should be understood that when used in the specification of the present invention and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0029] It should also be understood that the term "and / or" as used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification of the present invention and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0031] In addition, in the description of the specification of the present invention and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0032] The reference to "one embodiment" or "some embodiments" or the like described in the specification of the present invention means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0033] Embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0034] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0035] It should be understood that the magnitudes of the sequence numbers of the steps in the following embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0036] To illustrate the technical solution of the present invention, specific embodiments will be used for illustration below.

[0037] A recommendation method for a hedging trading product provided by Embodiment 1 of the present invention can be applied in an application environment such as Figure 1 where the client communicates with the server. Among them, the client includes but is not limited to terminal devices such as palm computers, desktop computers, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, cloud terminal devices, and personal digital assistants (PDAs). The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0038] See Figure 2 , which is a schematic flowchart of a recommendation method for a hedging trading product provided by Embodiment 1 of the present invention. The above recommendation method can be applied to the Figure 1 client in, and the terminal device corresponding to the client is connected to a corresponding database to obtain corresponding product information, transaction information, position information, etc. As Figure 2 shown, the recommendation method may include the following steps:

[0039] Step S201, obtain the position details, first price trend, and first trading volume trend of each current position product, as well as the second price trend and second trading volume trend of each product to be recommended.

[0040] Among them, the product can refer to financial products such as stock products, option products, and futures products. The held product can refer to the financial product currently held. The held details can include the number of holdings, option price, underlying type, and underlying price, etc. The product to be recommended can be the financial product pre-selected by the trader.

[0041] In one embodiment, the product to be recommended is the product selected by the terminal device according to a preset rule. For example, the preset rule can be to sort the products from high to low according to volatility and select the top K products, where K is a positive integer not less than 1.

[0042] Among them, the first price trend is the price trend of the held product within the target time period, the first trading volume is the trading volume trend of the held product within the target time period, the second price trend is the price trend of the product to be recommended within the target time period, and the second trading volume is the trading volume trend of the product to be recommended within the target time period.

[0043] In this embodiment, the above price trend and trading volume trend are represented in the form of a one-dimensional vector to quantify the price data and trading volume data for subsequent processing.

[0044] Illustrated by way of example, the one-dimensional vector form is specifically as follows: a trend vector with M columns and 1 row is constructed according to the length L of the target time period. M is set to a fixed value, which is set to 37 in this embodiment, and the length L of the target time period is set to 180 minutes. Each column of the above trend vector represents a time point, and the time interval between the time point corresponding to any column and the time point corresponding to its adjacent column on the left is set to T. Then, according to the length of the target time period and the number of columns M of the above one-dimensional vector, through the formula T can be determined to be 5 minutes, and the element value of the element in the trend vector represents the specific value of the price or trading volume at the time point corresponding to the column where the element is located.

[0045] In one embodiment, the price trend and trading volume trend can also be in the form of a curve graph, a line graph, a scatter plot, or a matrix.

[0046] Step S202: Input the held details, the first price trend, and the first trading volume trend of each held product, respectively, and the second price trend and the second trading volume trend of each product to be recommended into the trained threshold prediction network, and output the hedging value threshold.

[0047] Among them, the threshold prediction network is in the Multiple Input Single Output (MISO) mode, and its network structure is a multi-encoder - fully connected layer structure. The above-mentioned multi-encoders all use one-dimensional convolution to extract features. The corresponding input quantities are the position details of the position-held products, the first price trend of the position-held products, the first trading volume trend of the position-held products, the second price trend of the products to be recommended, and the second trading volume trend of the products to be recommended. The multiple corresponding feature tensors output by the multi-encoders are integrated through a concatenation operation, and then the integrated feature tensors are input into the fully connected layer. The fully connected layer serves to map the feature tensors to the output space, and the output quantity of the fully connected layer is the first hedging value threshold.

[0048] Optionally, the training process of the threshold prediction network includes:

[0049] Construct a threshold prediction network, which is a network representing the mapping relationship between input and output quantities. Among them, the input quantities are the position details, the first price trend, and the first trading volume trend of any position-held product, as well as the second price trend and the second trading volume trend of any product to be recommended. The output quantity is the first hedging value threshold. The threshold prediction network also includes, after outputting multiple first hedging value thresholds, calculating the ratio of the sum of all first hedging value thresholds to the number of products to be recommended, and determining this ratio as the hedging value threshold. When training the threshold prediction network, the mean squared error loss function is used as the loss function;

[0050] The training samples of the threshold prediction network are: when training, the position details, the first price trend, and the first trading volume trend of a single position-held product, as well as the second price trend and the second trading volume trend of a single product to be recommended obtained at any moment are used as training samples;

[0051] When training the threshold prediction network, the first hedging value threshold set by the trader based on experience is used as the labeled data.

[0052] Among them, the threshold prediction network can be a regression task network model such as a deep neural network, a convolutional neural network, and a multi-layer perceptron.

[0053] For example, if the number of the above-mentioned position-held products is A and the number of products to be recommended is B, then there are A * B input combinations in total. The A * B input quantities are sequentially sent into the threshold prediction network, and A * B first hedging value thresholds are output. Let the first hedging value threshold be m a, , m a,Taking the position details, the first price trend, the first trading volume trend of the a-th held product and the second price trend, the second trading volume trend of the b-th recommended product as inputs, the first hedge value threshold output by the threshold prediction network, where the value range of a is an integer in [1, A], and the value range of b is an integer in [1, B], then the hedge value threshold is expressed as

[0054] Inputting the actual obtained position details of the held products, the first price trend of the held products, the first trading volume trend of the held products, the second price trend of the products to be recommended, and the second trading volume trend of the products to be recommended into the threshold prediction network trained in the above manner, and finally outputting the hedge value threshold. Since the input of the above threshold prediction network includes position information and market information of related products, the hedge value threshold can be adjusted dynamically in real time as the market information of related products changes, avoiding the generation of additional hedge trading costs and redundant operations.

[0055] Step S203: Obtain the hedge value of each held product, calculate the product of the number of positions of each held product and the corresponding hedge value, and determine the sum of all products as the overall hedge value.

[0056] Among them, the hedge value is a concept in financial transactions and is usually referred to as "Delta value" in the financial field. The hedge value is used to measure the change range of the option price when the price of the underlying asset changes. The calculation method is the ratio of the change in the option price to the change in the price of the underlying asset. The number of positions of the held product is included in the position details of the held product. The overall hedge value is used to characterize the change degree of the prices of all held products and is used to execute hedge trading operations according to the change of the overall hedge value of the held products when hedging is needed, avoiding over-hedging or incomplete hedging.

[0057] Step S204: Input the overall hedge value and the hedge value threshold into a preset recommended metric value evaluation model, and output the recommended metric value.

[0058] Among them, the preset recommended metric value evaluation model can be a neural network, a mapping function, and a regression model, which are used to characterize the mapping relationship between the overall hedge value and the hedge value threshold and the recommended metric value.

[0059] Optionally, the preset recommended metric value evaluation model includes a recommended metric value mapping function, and the recommended metric value mapping function is:[[]]

[0060]

[0061] Among them, x is the overall hedging value, y is the hedging value threshold, the recommended index value mapping function is negatively correlated with (x - y), the value range of the recommended index value is (-1, 1), the recommended index value is used to represent the demand degree of hedging transactions for call-type products. When the recommended index value is greater than zero, the demand type for the product is call type; when the recommended index value is less than or equal to zero, the demand type for the product is put type.

[0062] Optionally, after obtaining the position details, the first price trend, and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended, it further includes:

[0063] Calculate the variance of the first price trend and the first trading volume trend of each held product, and the second price trend and the second trading volume trend of the product to be recommended, and determine the mean of all variances as the overall volatility value;

[0064] Obtain the hedging value of the product to be recommended, and determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended, including:

[0065] If the absolute value of the recommended index value is greater than the overall volatility value, obtain the hedging value of the product to be recommended, and determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended.

[0066] Among them, the calculation process of the overall volatility value is:

[0067] Calculate the variance value of the first price trend and the variance value of the first trading volume trend of a single held product respectively;

[0068] Calculate the price variance value of the second trend and the variance value of the second trading volume trend of a single product to be recommended respectively;

[0069] Perform normalization processing on the above variance values. The processing method can use the ratio of the current variance value to the historical maximum variance value of the product in the same time period as the normalized variance value;

[0070] Calculate the normalized variance values of all products one by one;

[0071] Sum up and average all the normalized variance values to determine the obtained mean as the overall volatility value.

[0072] Among them, the trigger condition for the step of obtaining the hedging value of the product to be recommended and determining the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended is that the absolute value of the recommended index value is greater than the overall volatility value, so as to ensure subsequent processing in the case of small market fluctuations of relevant hedging transaction products, and avoid generating invalid calculations or providing inaccurate recommended hedging transaction products.

[0073] Optionally, after determining that the mean of all variances is the overall volatility value, it further includes:

[0074] If the absolute value of the recommended index value is less than or equal to the overall volatility value, after waiting for a preset time, perform the steps of obtaining the position details, the first price trend, and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended.

[0075] Among them, the preset time is set by the trader. For example, the preset time is set to 30 minutes.

[0076] When the condition that the absolute value of the recommended index value is less than or equal to the overall volatility value is met, after waiting for the preset time, execute:

[0077] Obtain the position details, the first price trend, and the first trading volume trend of each current held product, as well as the second price trend and the second trading volume trend of each product to be recommended;

[0078] Input the position details, the first price trend, and the first trading volume trend of each held product, respectively, and the second price trend and the second trading volume trend of each product to be recommended into the trained threshold prediction network, and output the hedge value threshold;

[0079] Obtain the hedge value of each held product, calculate the product of the number of positions of each held product and the corresponding hedge value, and determine that the sum of all products is the overall hedge value;

[0080] Input the overall hedge value and the hedge value threshold into the preset recommended index value evaluation model, and output the recommended index value;

[0081] Obtain the hedge value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedge value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value, and determine that the product to be recommended that meets the required type is the target recommended product.

[0082] When the absolute value of the recommended index value is less than or equal to the overall volatility value, it indicates that the market of the relevant hedging trading products fluctuates greatly. At this time, to avoid incorrect transactions and improve the hedging trading efficiency, after waiting for the preset time, re-recommend the hedging trading products.

[0083] Step S205: Obtain the hedge value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedge value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value, and determine that the product to be recommended that meets the required type is the target recommended product.

[0084] Among them, the rise and fall types include the bullish type and the bearish type. If the hedge value of the product to be recommended is greater than 0, determine that the rise and fall type of the product to be recommended is the bullish type; if the hedge value of the product to be recommended is less than or equal to 0, determine that the rise and fall type of the product to be recommended is the bearish type.

[0085] Detecting whether the rise and fall type of the product to be recommended meets the demand type corresponding to the recommended index value means detecting whether the rise and fall type of the product to be recommended is consistent with the demand type corresponding to the recommended index value. If they are consistent, it means that the rise and fall type of the product to be recommended meets the demand type corresponding to the recommended index value; if they are inconsistent, it means that the rise and fall type of the product to be recommended does not meet the demand type corresponding to the recommended index value.

[0086] Determining the product to be recommended that meets the demand type as the target recommended product is a screening process, that is, retaining the product to be recommended that meets the demand type as the target recommended product and screening out the product to be recommended that does not meet the demand type, so as to provide traders with a rich selection of target recommended products.

[0087] In this embodiment, the price trend and trading volume trend are used to predict the hedge value threshold, so that the threshold can accurately follow the market conditions, thereby making the recommendation timing more accurate. At the same time, using the threshold that follows the market conditions to evaluate each product can accurately screen out the hedge products to be recommended, effectively reducing the cost of hedge trading and improving the efficiency of hedge trading.

[0088] See Figure 3 , which is a schematic flowchart of a method for recommending hedge trading products provided in the second embodiment of the present invention. The recommendation method includes the following steps:

[0089] Step S301, obtain the position details, the first price trend, and the first trading volume trend of each current position product, as well as the second price trend and the second trading volume trend of each product to be recommended.

[0090] Step S302, input the position details, the first price trend, and the first trading volume trend of each position product, respectively, and the second price trend and the second trading volume trend of each product to be recommended into the trained threshold prediction network, and output the hedge value threshold.

[0091] Step S303, obtain the hedge value of each position product, calculate the product of the position number of each position product and the corresponding hedge value, and determine the sum of all products as the overall hedge value.

[0092] Step S304, input the overall hedge value and the hedge value threshold into the preset recommended index value evaluation model, and output the recommended index value.

[0093] Step S305: Obtain the hedge value of the product to be recommended. Based on the hedge value of the product to be recommended, determine the rising or falling type of the product to be recommended, and detect whether the rising or falling type of the product to be recommended meets the required type corresponding to the recommended index value. Determine the product to be recommended that meets the required type as the target recommended product.

[0094] Among them, the content of steps S301 to S305 is the same as that of the above steps S201 to S205. For specific reference, please refer to the above steps S201 to S205 and will not be elaborated here.

[0095] Step S306: After determining that the product to be recommended that meets the required type is the target recommended product, if there are at least three target recommended products, screen out at least two hedge trading product combinations according to the preset rules, and recommend the hedge trading product combinations.

[0096] The preset rule is to set the limit value of the number of products in the hedge trading product combination as N. Under the condition that the number of products in the hedge trading product combination meets the condition of being less than or equal to N, randomly select and combine from the target recommended products, where N is an integer greater than zero.

[0097] Among them, the preset rule can be a quantity limit rule. In the embodiment of the present invention, the preset rule is to set the limit value of the number of products in the hedge trading product combination as N. Under the condition that the number of products in the hedge trading product combination meets the condition of being less than or equal to N, randomly select and combine from the target recommended products, where N is an integer greater than zero.

[0098] For example, assume there are K target recommended products. If K≥N, there are a total of combination methods, where represents the permutation and combination of randomly selecting n options from K options; if K<N, there are a total of combination methods. The purpose of setting the quantity limit rule is to avoid excessive computational complexity, resulting in long time consumption and delaying the timing of hedge trading.

[0099] The above recommendation in the form of hedge trading product combinations is beneficial to saving the time of manual calculation by traders, improving the richness of recommended trading products, and facilitating traders to make appropriate adjustments and optimizations based on their own trading experience.

[0100] Optionally, after screening out at least two hedge trading product combinations according to the preset rules, it further includes:

[0101] Determine the price volatility evaluation value of the hedge trading product combination according to the second price trend of the target recommended products included in the hedge trading product combination.

[0102] Determine the real-time cost evaluation value of the hedging trading product portfolio according to the second price trend of the target recommended products included in the hedging trading product portfolio;

[0103] Compare the hedging value corresponding to the target recommended products included in the hedging trading product portfolio with the recommended index value to determine the matching evaluation value of the recommended index value of the hedging trading product portfolio.

[0104] Perform a weighted sum of the price volatility degree evaluation value, the real-time cost evaluation value, and the recommended index value matching evaluation value to determine that the result of the weighted sum is the final evaluation value of the hedging trading product portfolio;

[0105] Take the hedging trading product portfolio with the highest final evaluation value as the recommended hedging trading product portfolio.

[0106] Among them, the specific calculation process of the price volatility degree evaluation value is as follows:

[0107] For each target recommended product in the hedging trading product portfolio, perform variance calculation based on all elements in its second price trend vector;

[0108] Normalize the variance result. The normalization method can be that the current variance value is used as the normalization value by the ratio of the historical maximum variance value calculated based on the historical price trend of the target recommended product under the same time length;

[0109] Perform mean calculation on the normalized variance values of all target recommended products in the hedging trading product portfolio, and subtract the calculated mean from 1 to obtain the price volatility degree evaluation value of the hedging trading product portfolio.

[0110] Among them, the specific calculation process of the real-time cost evaluation value is as follows:

[0111] For each target recommended product in the hedging trading product portfolio, use the element value in the last column of the second price trend vector as the real-time price value;

[0112] Normalize the real-time price value. The normalization method can be that the current real-time price value is used as the normalization value by the ratio of the maximum current real-time price value of all target recommended products;

[0113] Perform mean calculation on the normalized real-time price values of all target recommended products in the hedging trading product portfolio, and subtract the calculated mean from 1 to obtain the real-time cost evaluation value of the hedging trading product portfolio.

[0114] Among them, the specific calculation process of the recommended index value matching evaluation value is as follows:

[0115] Calculate the sum of the hedging values corresponding to all target recommended products within the hedging trading product portfolio;

[0116] Take the absolute value after subtracting the sum of the hedge values from the recommended index value, and use 1 minus half of this absolute value as the matching evaluation value of the recommended index value.

[0117] The value ranges of the above price fluctuation degree evaluation value, real-time cost evaluation value, and recommended index value matching evaluation value are all [0, 1], and the closer the value is to 1, the more beneficial it is for this index to improve the hedge trading efficiency.

[0118] Among them, the weight values for weighted summation of the price fluctuation degree evaluation value, real-time cost evaluation value, and recommended index value matching evaluation value are set as w1, w2, and w3 respectively. Each weight value satisfies w ∈ [0, 1], and the weight values are set as w1 = w2 = w3 = 1. Implementers can also adjust the weight values according to the actual situation, or adjust the items participating in the calculation of the final evaluation value. For example, if the weight value w1 of the price fluctuation degree evaluation value is set to 0, then only the real-time cost evaluation value and the recommended index value matching evaluation value participate in the calculation of the final evaluation value.

[0119] Using the above final evaluation value to screen the hedge trading product portfolio improves the accuracy of the recommended hedge trading product portfolio. At the same time, it is convenient for traders to select appropriate weights for evaluation according to their own trading experience, which conforms to the trading habits of traders, thereby improving the work efficiency of traders.

[0120] In one implementation, sort the final evaluation values and select the top Q hedge trading product portfolios as the recommended hedge trading product portfolios, where Q is a positive integer.

[0121] In this embodiment, by evaluating the hedge trading product portfolio from multiple dimensions of the price fluctuation degree evaluation value, real-time cost evaluation value, and recommended index value matching evaluation value, the hedge product portfolio to be recommended can be accurately screened out, and the recommended hedge product portfolio contains multiple products, which can support traders to flexibly perform hedge trading operations, thereby effectively reducing the cost of hedge trading and improving the efficiency of hedge trading.

[0122] Corresponding to the above-described recommended method for hedge trading products in the embodiment, Figure 4 The structural block diagram of a recommended device for a hedge trading product provided in the third embodiment of the present invention is given. For the sake of convenience of description, only the parts related to the embodiment of the present invention are shown.

[0123] See Figure 4 and this recommended device includes:

[0124] A product information acquisition module 41, configured to acquire the position details, first price trend, and first trading volume trend of each current held product, as well as the second price trend and second trading volume trend of each product to be recommended;

[0125] A hedging value threshold prediction module 42, configured to input the position details, the first price trend, and the first trading volume trend of each position-holding product, and the second price trend and the second trading volume trend of each product to be recommended into a trained threshold prediction network, and output a hedging value threshold;

[0126] An overall hedging value calculation module 43, configured to obtain the hedging value of each position-holding product, calculate the product of the number of positions of each position-holding product and the corresponding hedging value, and determine the sum of all products as the overall hedging value;

[0127] A recommended index value acquisition module 44, configured to input the overall hedging value and the hedging value threshold into a preset recommended index value evaluation model, and output a recommended index value;

[0128] A target recommended product determination module 45, configured to obtain the hedging value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value, and determine the product to be recommended that meets the required type as the target recommended product.

[0129] Optionally, the above hedging value threshold prediction module 42 includes:

[0130] A threshold prediction network construction sub-module, configured to construct a threshold prediction network, where the threshold prediction network is a mapping relationship network representing the input quantity and the output quantity. The input quantity is the position details, the first price trend, and the first trading volume trend of any position-holding product, and the second price trend and the second trading volume trend of any product to be recommended. The output quantity is the first hedging value threshold. The threshold prediction network further includes, after outputting a plurality of first hedging value thresholds, calculating the ratio of the sum of all first hedging value thresholds to the number of products to be recommended, and determining this ratio as the hedging value threshold. The loss function of the threshold prediction network adopts the mean square error loss function during training;

[0131] The training sample of the threshold prediction network is: during training, the position details, the first price trend, and the first trading volume trend of a single position-holding product obtained at any moment, and the second price trend and the second trading volume trend of a single product to be recommended are used as training samples;

[0132] The threshold prediction network uses the first hedging value threshold set by the trader according to experience as the label data during training.

[0133] Optionally, the above recommended index value acquisition module 44 includes:

[0134] The preset recommended index value evaluation model includes a recommended index value mapping function, and the recommended index value mapping function is:

[0135]

[0136] Among them, x is the overall hedging value, y is the hedging value threshold, the recommended index value mapping function is negatively correlated with (x - y), the value range of the recommended index value is (-1, 1), and the recommended index value is used to represent the demand degree of hedging transactions for call-type products. When the recommended index value is greater than zero, the demand type for the product is call type; when the recommended index value is less than or equal to zero, the demand type for the product is put type.

[0137] Optionally, the above-mentioned recommended index value acquisition module 44 includes:

[0138] An overall volatility degree value calculation sub-module, which is used to calculate the variance of the first price trend and the first trading volume trend of each held product and the second price trend and the second trading volume trend of each product to be recommended after obtaining the holding details, the first price trend, and the first trading volume trend of each currently held product, as well as the second price trend and the second trading volume trend of each product to be recommended, and determine the mean of all variances as the overall volatility degree value;

[0139] A product type determination trigger sub-module, which is used to trigger the target recommended product determination module 45 to execute the operation of determining the rise and fall type of the product to be recommended according to the obtained hedging value of the product to be recommended when the absolute value of the recommended index value is greater than the overall volatility degree value.

[0140] Optionally, the above-mentioned recommended index value acquisition module 44 includes:

[0141] A product information re-acquisition trigger sub-module, which is used to trigger the product information acquisition module 41 to execute the operation of obtaining the holding details, the first price trend, and the first trading volume trend of each currently held product, as well as the second price trend and the second trading volume trend of each product to be recommended after waiting for a preset time when the absolute value of the recommended index value is less than or equal to the overall volatility degree value.

[0142] Optionally, the recommendation device further includes:

[0143] After determining that the product to be recommended that meets the demand type is the target recommended product, if there are at least three target recommended products, at least two hedging transaction product combinations are screened out according to a preset rule, and the hedging transaction product combinations are recommended;

[0144] The preset rule is to set the limit value of the number of products in the hedging transaction product combination to N, and randomly select and combine from the target recommended products under the condition that the number of products in the hedging transaction product combination meets less than or equal to N, where N is an integer greater than zero.

[0145] Optionally, the recommendation device further includes:

[0146] A price fluctuation degree evaluation value acquisition sub-module, configured to determine a price fluctuation degree evaluation value of the hedging trading product portfolio according to the second price trend of the target recommended products included in the hedging trading product portfolio;

[0147] A real-time cost evaluation value calculation sub-module, configured to determine a real-time cost evaluation value of the hedging trading product portfolio according to the second price trend of the target recommended products included in the hedging trading product portfolio;

[0148] A recommended index value matching evaluation value calculation sub-module, configured to compare the hedging value corresponding to the target recommended products included in the hedging trading product portfolio with the recommended index value, and determine a recommended index value matching evaluation value of the hedging trading product portfolio;

[0149] A final evaluation value acquisition sub-module, configured to perform a weighted sum on the price fluctuation degree evaluation value, the real-time cost evaluation value, and the recommended index value matching evaluation value, and determine that the result of the weighted sum is the final evaluation value of the hedging trading product portfolio;

[0150] A hedging trading product portfolio recommendation sub-module, configured to use the hedging trading product portfolio with the highest final evaluation value as the recommended hedging trading product portfolio.

[0151] It should be noted that for the information interaction, execution process, etc. between the above modules, since they are based on the same concept as the method embodiment of the present invention, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0152] Figure 5 This is a schematic structural diagram of a terminal device provided in Embodiment 4 of the present invention. As Figure 5 shown, the terminal device of this embodiment includes: at least one processor ( Figure 5 only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, the steps in any of the above-mentioned recommended method embodiments are implemented.

[0153] The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 5 this is only an example of the terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include a network interface, a display screen, and an input device, etc.

[0154] The so-called processor may be a CPU, and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0155] The memory includes a readable storage medium, internal memory, etc. Among them, the internal memory may be the memory of the terminal device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the terminal device, and in some other embodiments, it may also be an external storage device of the terminal device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device. Further, the memory may also include both the internal storage unit of the terminal device and the external storage device. The memory is used to store the operating system, application programs, boot loaders, data, and other programs, etc. The other programs such as the program code of the computer program. The memory may also be used to temporarily store the data that has been output or will be output.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working processes of the units and modules in the above device can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0157] All or part of the processes in the above method embodiments of the present invention can also be completed by a computer program product. When the computer program product runs on a terminal device, the terminal device can be made to execute the steps in the above method embodiments when executed.

[0158] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0160] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the device or unit can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A recommendation method for a hedging trading product, characterized in that, Including: Obtain the position details, first price trend, and first trading volume trend of each current held product, as well as the second price trend and second trading volume trend of each product to be recommended; Input the position details, first price trend, and first trading volume trend of each held product, respectively, and the second price trend and second trading volume trend of each product to be recommended into the trained threshold prediction network, and output the hedge value threshold; Obtain the hedge value of each held product, calculate the product of the position quantity of each held product and the corresponding hedge value, and determine the sum of all products as the overall hedge value; Input the overall hedge value and the hedge value threshold into the preset recommended index value evaluation model, and output the recommended index value; Obtain the hedge value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedge value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the required type corresponding to the recommended index value, and determine the product to be recommended that meets the required type as the target recommended product; The training process of the threshold prediction network includes: Construct a threshold prediction network, which is a mapping relationship network representing the input quantity and the output quantity. Among them, the input quantity is the position details, first price trend, and first trading volume trend of any held product, as well as the second price trend and second trading volume trend of any product to be recommended, and the output quantity is the first hedge value threshold. The threshold prediction network also includes that after outputting multiple first hedge value thresholds, calculate the ratio of the sum of all first hedge value thresholds to the number of products to be recommended, and determine this ratio as the hedge value threshold. The loss function of the threshold prediction network adopts the mean square error loss function during training; The training samples of the threshold prediction network are: when training, the position details, first price trend, and first trading volume trend of a single held product, as well as the second price trend and second trading volume trend of a single product to be recommended obtained at any moment are used as training samples; The threshold prediction network uses the first hedge value threshold set by the trader according to experience as the label data during training.

2. The recommended method according to claim 1, characterized in that The preset recommended index value evaluation model includes a recommended index value mapping function, and the recommended index value mapping function is: Wherein, is the overall hedging value, is the hedging value threshold, and the recommended index value mapping function is negatively correlated. The value range of the recommended index value is . The recommended index value is used to represent the demand degree of hedging transactions for call-type products. When the recommended index value is greater than zero, the demand type for the product is call type. When the recommended index value is less than or equal to zero, the demand type for the product is put type.

3. The recommended method according to claim 1, characterized in that, After obtaining the position details, first price trend, and first trading volume trend of each current held product, as well as the second price trend and second trading volume trend of each product to be recommended, it also includes: Calculate the variance between the first price trend and the first trading volume trend of each held product and the second price trend and the second trading volume trend of the product to be recommended, and determine the mean of all variances as the overall volatility degree value; Obtain the hedge value of the product to be recommended, and determining the rise and fall type of the product to be recommended according to the hedge value of the product to be recommended includes: If the absolute value of the recommended index value is greater than the overall volatility degree value, obtain the hedge value of the product to be recommended, and determine the rise and fall type of the product to be recommended according to the hedge value of the product to be recommended.

4. The recommendation method according to claim 3, wherein After determining the mean of all variances as the overall volatility degree value, it also includes: If the absolute value of the recommended index value is less than or equal to the overall fluctuation degree value, after waiting for a preset time, perform the steps of obtaining the holding details, the first price trend, and the first trading volume trend of each current holding product, as well as the second price trend and the second trading volume trend of each product to be recommended.

5. The recommendation method according to any one of claims 1 to 4, characterized in that, After determining that the product to be recommended that meets the demand type is the target recommended product, it further includes: If there are at least three target recommended products, screen out at least two hedging trading product combinations according to a preset rule, and recommend the hedging trading product combinations; The preset rule is to set the limit value of the number of products in the hedging trading product combination to N, and randomly select and combine from the target recommended products under the condition that the number of products in the hedging trading product combination meets the condition of being less than or equal to N, where N is an integer greater than zero.

6. The recommendation method according to claim 5, characterized in that After screening out at least two hedging trading product combinations according to the preset rule, it further includes: Determine the price fluctuation degree evaluation value of the hedging trading product combination according to the second price trend of the target recommended products included in the hedging trading product combination; Determine the real-time cost evaluation value of the hedging trading product combination according to the second price trend of the target recommended products included in the hedging trading product combination; Compare the hedging value corresponding to the target recommended products included in the hedging trading product combination with the recommended index value to determine the recommended index value matching evaluation value of the hedging trading product combination; Perform a weighted sum of the price fluctuation degree evaluation value, the real-time cost evaluation value, and the recommended index value matching evaluation value to determine that the result of the weighted sum is the final evaluation value of the hedging trading product combination; Take the hedging trading product combination with the highest final evaluation value as the recommended hedging trading product combination.

7. A recommendation device for a hedging trading product, characterized in that, The recommended device for the hedging trading product includes: A product information acquisition module, configured to acquire the holding details, the first price trend, and the first trading volume trend of each current holding product, as well as the second price trend and the second trading volume trend of each product to be recommended; A hedging value threshold prediction module, configured to input the holding details, the first price trend, and the first trading volume trend of each holding product, respectively, and the second price trend and the second trading volume trend of each product to be recommended into a trained threshold prediction network, and output a hedging value threshold; An overall hedging value calculation module, configured to acquire the hedging value of each holding product, calculate the product of the number of holdings of each holding product and the corresponding hedging value, and determine that the sum of all products is the overall hedging value; A recommended index value acquisition module, configured to input the overall hedging value and the hedging value threshold into a preset recommended index value evaluation model, and output a recommended index value; A target recommended product determination module, configured to acquire the hedging value of the product to be recommended, determine the rise and fall type of the product to be recommended according to the hedging value of the product to be recommended, and detect whether the rise and fall type of the product to be recommended meets the demand type corresponding to the recommended index value, and determine that the product to be recommended that meets the demand type is the target recommended product; The training process of the threshold prediction network includes: Construct a threshold prediction network, which is a mapping relationship network representing the input quantity and the output quantity. Among them, the input quantity is the position details, the first price trend, and the first trading volume trend of any held product, as well as the second price trend and the second trading volume trend of any product to be recommended. The output quantity is the first hedging value threshold. The threshold prediction network further includes, after outputting multiple first hedging value thresholds, calculating the ratio of the sum of all first hedging value thresholds to the number of products to be recommended, and determining this ratio as the hedging value threshold. When training the threshold prediction network, the mean square error loss function is used as the loss function; The training samples of the threshold prediction network are: when training, the position details, the first price trend, and the first trading volume trend of a single held product obtained at any moment, as well as the second price trend and the second trading volume trend of a single product to be recommended are used as training samples; When training the threshold prediction network, the first hedging value threshold set by the trader based on experience is used as the labeled data.

8. A terminal device, characterized in that, The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the recommendation method described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the recommendation method described in any one of claims 1 to 6 is implemented.

Images