Power transaction data risk assessment method, system, device and medium

Abstract

The invention discloses a risk assessment method, system and device for power transaction data and a medium, and relates to the technical field of data risk assessment, and the method comprises the steps: predicting a target electricity price mean value in a target transaction contract period according to an electricity price influence factor; according to the target electricity price mean value and the obtained first market information, using a target credit analysis model to calculate a credit parameter of a transaction party; and evaluating the risk level of the target transaction contract according to the target electricity price mean value and the credit parameter. The method is suitable for power transaction risk assessment in a power transaction scene.

Description

Technical Field

[0001] The present application relates to the technical field of data risk assessment, and in particular to risk assessment methods, systems, equipment and media for power trading data. Background Art

[0002] Electricity trading refers to the buying and selling of electricity as a commodity in the market, which includes multiple links such as electricity production, transmission, distribution and consumption, and involves multiple market players, such as power generation companies, transmission network operators, distribution companies, retail suppliers and electricity users. In the process of electricity trading, in order to maximize their interests, both parties to the transaction generally assess the risks of the transaction before signing the transaction contract. The solution is usually to conduct a risk assessment based on the market information of the transaction parties (for example, economic conditions, operating conditions, etc.) to obtain the risk assessment results as a reference.

[0003] However, when evaluating transaction risks based only on the market information of the trading parties, there is still the problem of too few influencing factors being considered, which leads to low evaluation accuracy and cannot meet the requirements of current application scenarios for evaluation accuracy. Summary of the invention

[0004] In view of this, the present application provides a risk assessment method, system, device and medium for power trading data, the main purpose of which is to solve the technical problem in the prior art that transaction risks cannot be accurately assessed based only on the market information of the trading parties.

[0005] According to one aspect of the present application, a method for risk assessment of power transaction data is provided, the method comprising:

[0006] Predict the target average electricity price within the target transaction contract period based on the factors affecting electricity prices;

[0007] Calculating the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information;

[0008] The risk level of the target transaction contract is evaluated according to the target electricity price average and the credit parameter.

[0009] According to another aspect of the present application, a risk assessment system for power transaction data is provided, the system comprising:

[0010] A prediction module is used to predict the average target electricity price within the target transaction contract period based on factors affecting electricity prices;

[0011] A calculation module, configured to calculate the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information;

[0012] An evaluation module is used to evaluate the risk level of the target transaction contract according to the target electricity price average and the credit parameter.

[0013] According to another aspect of the present application, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the risk assessment method for power trading data described above is implemented.

[0014] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned risk assessment method for power trading data when executing the program.

[0015] By means of the above technical scheme, the risk assessment method, system, device and medium of power transaction data provided by the present application, compared with the existing technical scheme that only assesses transaction risk based on the market information of the transaction party and considers too single influencing factors, the present application predicts the target average electricity price within the target transaction contract period according to the electricity price influencing factors; calculates the credit parameter of the transaction party according to the target average electricity price and the first market information obtained using the target credit analysis model; and assesses the risk level of the target transaction contract according to the target average electricity price and the credit parameter. It can be seen that by considering the impact of electricity price changes on the transaction party and the market information of the transaction party, the risk assessment of the target transaction contract can be made more accurate.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A schematic diagram of a process for risk assessment of power transaction data provided by an embodiment of the present application is shown;

[0019] Figure 2 A schematic diagram showing a flow chart of another method for risk assessment of power trading data provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of the structure of a risk assessment system for power trading data provided by an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of the structure of another power trading data risk assessment system provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0023] In view of the technical problem that the transaction risk cannot be accurately assessed based on the market information of the transaction parties in the prior art, this embodiment provides a risk assessment method for power transaction data, which makes the risk assessment of the target transaction contract more accurate by considering the impact of electricity price changes on the transaction parties and the market information of the transaction parties. Figure 1 As shown, the above method comprises the following steps:

[0024] Step 101: predict the target electricity price average within the target transaction contract period based on electricity price influencing factors.

[0025] In this embodiment, before step 101, historical electricity prices, factors affecting electricity prices, and first market information of the trading parties are obtained. The steps of obtaining factors affecting electricity prices include: 1) Historical electricity demand: obtaining daily electricity demand through the power supply department (e.g., power grid company), and recording it as historical electricity demand; 2) Historical fuel prices: obtaining daily fuel prices through energy producers or institutions such as commodity exchanges, and recording it as historical fuel prices; 3) Power supply capacity: obtaining the maximum power generation capacity of the power plant through the power supply department, and recording it as power supply capacity; 4) Historical weather information: obtaining daily temperature, humidity, rainfall, and sunshine duration through the Meteorological Bureau, and recording it as historical weather information.

[0026] Step 102: Calculate the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information.

[0027] In this embodiment, the market information of the historical trading parties with historical power transactions is used as the second market information and as the training sample for training the initial credit analysis model, so as to realize the training of the credit analysis model. It should be noted that the market information includes non-digital information, which is not convenient for later calculation. Therefore, the first market information and the second market information are digitized to generate the first market parameter and the second market parameter.

[0028] Step 103: Evaluate the risk level of the target transaction contract according to the target electricity price average and the credit parameter.

[0029] In this embodiment, in order to ensure the accuracy of the risk assessment of the target transaction contract, it is necessary to take into account the changes in electricity prices. Therefore, the risk value of the target transaction contract is calculated based on the historical average electricity price, the target average electricity price and the credit parameter, and then the risk level of the target transaction contract is determined based on the predetermined level rule. Among them, the risk value R of the target transaction contract is a value between 0 and 1. When the risk value R of the target transaction contract is lower than 0.35, it means that the risk level of the target transaction contract is low; when the risk value R of the target transaction contract is between 0.35 and 0.7, it means that the risk level of the target transaction contract is high; when the risk value R of the target transaction contract is higher than 0.7, it means that the risk level of the target transaction contract is very high.

[0030] For this embodiment, according to the above scheme, after predicting the average electricity price during the effective period of the target transaction contract, the credit parameters of the transaction parties are calculated, thereby realizing the risk assessment of the target transaction contract. Compared with the existing technical scheme that only assesses the transaction risk based on the market information of the transaction parties and considers too single influencing factors, this embodiment can make the risk assessment of the target transaction contract more accurate by considering the impact of electricity price changes on the market information of the transaction parties and considering the mutual influence between the various market information of the transaction parties when conducting risk assessment.

[0031] In some power transactions, the two parties will enter into a transaction contract. However, in this process, some factors may arise that make it impossible to continue to perform the contract, such as: the electricity price is in a state of change in the market, and the transaction party is unable to perform the contractual obligations due to bankruptcy, dissolution, etc. Therefore, before signing a contract with the transaction party, it is necessary to consider the above factors, namely the factors affecting the electricity price and the actual market information of the transaction party, to ensure that the risk of the transaction is accurately assessed before signing the transaction contract.

[0032] Furthermore, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another risk assessment method for power trading data is provided. This embodiment can solve the technical problem of low accuracy in the assessment of power trading risks in the existing technical solutions. This embodiment can consider the impact of changes in electricity prices on the market information of the trading parties, and consider the mutual influence between the various market information of the trading parties when conducting risk assessment, so as to ensure a more accurate risk assessment of the target trading contract. Figure 2 As shown in the figure, the risk assessment method of power transaction data based on the data open platform includes:

[0033] Step 201: construct an electricity price prediction training matrix based on electricity price influencing factors and historical electricity prices.

[0034] During implementation, historical electricity prices, factors affecting electricity prices and first-hand market information of trading parties are obtained. Specifically, in the process of an electricity transaction, the risks include not only natural disasters, human operational errors, policy changes and other unpredictable factors, but also changes in electricity prices and the credit risk of Party B. For example, if during the execution of the contract, the market electricity price gradually increases, the seller will sell electricity at a price lower than the market price, resulting in the risk of reduced revenue. The trading party (Party B) may encounter operational problems during the execution of the electricity trading contract and be unable to continue to execute the contract. Therefore, this embodiment comprehensively considers the above two factors and analyzes and evaluates the possible electricity trading risks.

[0035] Among them, factors affecting electricity prices include: historical electricity demand, historical fuel prices, electricity supply capacity and historical weather information; specifically, electricity demand, fuel prices and weather information are always changing, and electricity supply capacity depends on the specific equipment power of the power supply department. Analysis is conducted based on the above information to achieve a forecast of the average electricity price during the electricity trading contract period.

[0036] The calculation formula for historical weather information is as follows:

[0037] WI i =w 1 ×T i +w 2 ×H i +w 3 ×R i +w 4 ×S i

[0038] Where WI i represents the historical weather information of the i-th day; T i represents the average temperature of the i-th day; H i represents the average humidity on the i-th day; R i represents the rainfall on the i-th day; S i represents the sunshine duration of the i-th day; w 1 、w 2 、w 3 and w 4 represent the first, second, third and fourth weight parameters of historical weather information respectively; according to the needs of actual application scenarios, w 1 、w 2 、w 3 and w 4 Set to 0.2, 0.3, 0.4 and 0.1 respectively.

[0039] The first market information includes: industry information, historical financial status information, technology research and development information, market position information and historical transaction information; it should be noted that the credit risk in electricity trading mainly comes from the operating conditions of the trading parties. If the trading parties go bankrupt, they will not be able to continue to perform the electricity trading contract, so it is necessary to obtain the above information.

[0040] Step 202: construct an initial electricity price mean prediction model, and obtain a target electricity price mean prediction model based on the electricity price prediction training matrix.

[0041] In order to illustrate the specific implementation of step 202, as a preferred embodiment, step 202 includes: setting a sliding window based on the electricity price prediction training matrix and obtaining training samples; setting the average electricity price within a second preset time period as a sample label; according to the initial electricity price mean prediction model, using the training samples and the sample labels to train to obtain a target electricity price mean prediction model.

[0042] Step 203: using the target electricity price average prediction model, predict the target electricity price average within the target transaction contract period.

[0043] In order to illustrate the specific implementation method of step 203, as a preferred embodiment, step 203 includes: obtaining prediction samples according to the electricity price prediction training matrix; based on the prediction samples, using the target electricity price average prediction model to predict the target electricity price average within the target transaction contract period.

[0044] In implementation, the electricity price prediction training matrix is ​​constructed by electricity price influencing factors and historical electricity prices within a first preset time period. In order to predict the risk of the target transaction contract, the impact of electricity price risk needs to be considered. Steps 202 and 203 specifically include the following steps:

[0045] S1. Construct the electricity price prediction training matrix A based on the factors affecting electricity prices and historical electricity prices. in, Indicates the electricity demand, fuel price, electricity supply capacity, weather information and historical electricity price on the first day; This is analogous to the electricity demand from day 1 to day n. Indicates the historical electricity price from day 1 to day n;

[0046] S2. Set a sliding window with a length of k, a width of 5, and a step length of 1. The sliding window obtains a training sample each time it slides in the electricity price prediction training matrix A. According to the requirements of the actual application scenario, k is set to 30.

[0047] S3. The average electricity price h days after each training sample is used as the sample label of the training sample; according to the requirements of the actual application scenario, h is the execution period (validity period) of the target transaction contract;

[0048] S4. construct an initial electricity price mean prediction model, and obtain a target electricity price mean prediction model by training with training samples and sample labels; specifically, since the influence of electricity price influencing factors on electricity price is extremely complex, the relationship is not linear, and the same electricity price influencing factors may have different influences on electricity price under different circumstances, therefore, the electricity price mean prediction model includes a first hidden layer, a second hidden layer and a classifier;

[0049] Among them, the first hidden layer includes k hidden units, each hidden unit inputs the corresponding electricity demand, fuel price, electricity supply capacity, weather information and historical electricity price in the training sample, and outputs the first updated feature; the first updated feature output by the k hidden units is input into the second hidden layer, and the second updated feature is output; the second updated feature is input into the classifier, and the average electricity price h days after the training sample is output.

[0050] S5. When the training samples selected by the sliding window include When the training sample is used as the prediction set, it is input into the target electricity price average prediction model, and the average electricity price within the target transaction contract period is output. Specifically, the first hidden layer and the second hidden layer of the electricity price average prediction model are constructed based on a multi-layer perceptron and a long short-term memory network, respectively.

[0051] It can be seen that compared with the existing electricity price forecasting method, this embodiment comprehensively considers the impact of electricity price influencing factors on electricity prices, and considers the different impacts of different electricity price influencing factors on electricity prices under different circumstances, effectively improving the accuracy of predicting electricity prices within the contract period.

[0052] Step 204: Acquire second market information, wherein the second market information is market information of historical trading parties with historical power transactions.

[0053] Step 205: construct an initial credit analysis model and obtain a target credit analysis model through training based on the second market information.

[0054] Step 206: Calculate the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information.

[0055] In order to illustrate the specific implementation method of step 206, as a preferred embodiment, step 206 includes: preprocessing the acquired first market information to obtain the first market parameter; calculating the credit parameter of the transaction party using the target credit analysis model according to the target electricity price average and the first market parameter.

[0056] In the implementation, the credit parameters of the transaction parties are calculated using the target credit analysis model according to the average electricity price and the first market information; specifically, since the credit risk of the transaction parties is also directly related to whether the target transaction contract can be successfully completed, steps 204-206 specifically include the following steps:

[0057] S1. Obtain the second market information of m enterprises that have conducted electricity transactions; specifically, the second market information includes: industry information, historical financial status information, technology research and development information, market position information and historical transaction information; it should be noted that the first market information includes the industry information, historical financial status information, technology research and development information, market position information and historical transaction information of the transaction parties, and the information contained in the two is the same.

[0058] S2, digitizing the first market information and the second market information to generate the first market parameter and the second market parameter, specifically comprising the following steps;

[0059] S21. The steps of digitizing the first market information and the second market information are as follows:

[0060] 1) Calculate the industry information parameter S through the industry information h The specific calculation formula is:

[0061] S h =W profit R profit +W risk (1-R risk )

[0062] In the formula, R profit The weighted average of the average net profit of the industry to which the transaction parties belong; R risk The weighted average of the debt-to-asset ratio and current ratio of the industry to which the transaction parties belong; W profit ,

[0063] W risk They represent the corresponding weight parameters respectively.

[0064] 2) The formula for calculating the financial status parameter C based on historical financial status information is as follows:

[0065]

[0066] In the formula, Z c Indicates the debt-to-asset ratio of the transaction party in the previous quarter; L z Indicates the current liquid assets of the transaction party; L f Indicates the current current liabilities of the transaction party; X zIndicates the current inventory value of the trading party; J l Indicates the net profit of the trading party in the previous quarter; J z Indicates the current net assets of the transaction party; W 1 , W 2 , W 3 and W 4 Respectively represent the first, second, third and fourth weight parameters of the debt-to-asset ratio; specifically, according to the needs of the actual application scenario, W 1 , W 2 , W 3 and W 4 They are set to 0.4, 0.2, 0.2 and 0.2 respectively;

[0067] 3) Calculate the R&D investment parameter Y based on the technology R&D information z The specific calculation formula is:

[0068]

[0069] In the formula, F y represents the R&D expenses of the transaction party in the previous quarter; X s Indicates the sales revenue of the trading party in the previous quarter;

[0070] 4) Calculate the market position parameter D based on the market position information s The specific calculation formula is:

[0071]

[0072] In the formula, X l Indicates the sales volume of the trading party in the previous quarter; X Z It indicates the total sales volume of similar products in the entire market in the previous quarter;

[0073] 5) Calculate historical transaction parameter L based on historical transaction information ly The specific calculation formula is:

[0074]

[0075] Where, L s Indicates the actual number of historical fulfillment orders of the trading party; X d Indicates the total number of orders of the trading party;

[0076] S22, the industry information parameter S h , financial status parameter C, R&D investment parameter Y z , Market position parameter D s and historical trading parameters L ly Recorded as the first market parameter.

[0077] S3. Construct an initial credit analysis model. Specifically, since the relationship between all factors in the first market information and credit is relatively complex, the expression of the credit analysis model is:

[0078]

[0079] Where D xy represents the output of the initial credit analysis model; X i and X j All belong to

[0080] {S h , C, Y z , D s , L ly , P pred};P pred represents the mean electricity price; i≠j; β 0 represents the intercept term; β i represents the coefficient of the first-order term; β ii represents the coefficient of the quadratic term; β ij represents the interaction coefficient; n=6.

[0081] S4. The initial credit analysis model is trained using the second market parameter to obtain a target credit analysis model. Specifically, before the target credit analysis model is put into use, it needs to be trained to ensure its accuracy. Therefore, in step S34, the following steps are specifically included:

[0082] S41. Relevant technical experts label the credit parameters of the training samples according to the second market parameters and historical transaction data (average electricity price, credit parameters, etc.) of each enterprise;

[0083] S42, setting β 0 , β i , β ii and β ij The initial value of

[0084] S43. Define the loss function MSE of the credit analysis model. The calculation formula is as follows:

[0085]

[0086] In the formula, y (i) represents the training credit parameter of the i-th enterprise; It represents the output of the second market parameter of the i-th enterprise in the credit analysis model;

[0087] S44. Update β using the gradient descent algorithm 0 , β i , β ii and βij ;

[0088] S45. Repeat steps S43 and S44 until the credit analysis model converges.

[0089] S5. Input the first market parameter into the target credit analysis model, and output the credit parameter of the transaction party.

[0090] It can be seen that by analyzing the first market information through the target credit analysis model and obtaining the credit parameters of the transaction parties, not only the impact of each factor in the first market information on the credit parameters of the transaction parties is taken into account, but also the mutual influence of each factor in the first market factors under different conditions is taken into account, thereby effectively improving the accuracy of calculating the credit parameters of the transaction parties, and then improving the accuracy of the subsequent calculation of the risk of the target transaction contract.

[0091] Step 207: Calculate the average historical electricity price of the trading parties in the previous time period.

[0092] Step 208: Calculate the risk value of the target transaction contract based on the historical average electricity price, the target average electricity price and the credit parameter.

[0093] Step 209: Determine the risk level of the target transaction contract according to the risk value and a predetermined level rule.

[0094] During implementation, the risk value of the target transaction contract is calculated based on the historical average electricity price, the average electricity price and the credit parameter; specifically, the calculation formula for calculating the risk value R of the target transaction contract is as follows:

[0095]

[0096] In the formula, represents the average electricity price in the previous quarter; w α and w β They represent the first and second weight parameters of the risk of the target transaction contract respectively; according to the requirements of the actual application scenario, w α and w β Set them to 0.25 and 0.75 respectively.

[0097] By applying the technical solution of this embodiment, the target electricity price average within the target transaction contract period is predicted based on the electricity price influencing factors; the target credit analysis model is used to calculate the credit parameters of the trading parties based on the target electricity price average and the first market information obtained; and the risk level of the target transaction contract is evaluated based on the target electricity price average and the credit parameters. Compared with the existing technical solution that only evaluates transaction risks based on the market information of the trading parties and considers too single influencing factors, by considering the market information of the trading parties and the impact of electricity price changes on the market information of the trading parties, and considering the mutual influence between the various market information of the trading parties when conducting risk assessment, the risk assessment of the target transaction contract is more accurate than the risk calculation method of the target transaction contract in the existing technology.

[0098] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a risk assessment system for power trading data, such as Figure 3 As shown, the system includes: a prediction module 31 , a calculation module 33 , and an evaluation module 34 .

[0099] The prediction module 31 is used to predict the target electricity price average within the target transaction contract period according to the factors affecting the electricity price.

[0100] The calculation module 33 is used to calculate the credit parameters of the transaction parties using the target credit analysis model according to the target electricity price average and the acquired first market information.

[0101] The evaluation module 34 is used to evaluate the risk level of the target transaction contract according to the target electricity price average and the credit parameter.

[0102] In specific application scenarios, such as Figure 4 As shown, the factors affecting electricity prices include historical electricity demand, historical fuel prices, electricity supply capacity and historical weather information; the prediction module 31 includes: a construction submodule 311, a training submodule 312 and a prediction submodule 313.

[0103] The construction submodule 311 is used to construct an electricity price prediction training matrix according to electricity price influencing factors and historical electricity prices.

[0104] The training submodule 312 is used to construct an initial electricity price mean prediction model and obtain a target electricity price mean prediction model based on the electricity price prediction training matrix.

[0105] The prediction submodule 313 is used to predict the target electricity price average within the target transaction contract period by using the target electricity price average prediction model.

[0106] In a specific application scenario, the training submodule 312 is specifically used to set a sliding window based on the electricity price prediction training matrix and obtain training samples; and, set the average electricity price within a second preset time period as a sample label; and, based on the initial electricity price mean prediction model, use the training samples and the sample labels to train to obtain a target electricity price mean prediction model.

[0107] In a specific application scenario, the prediction submodule 313 is specifically used to obtain prediction samples according to the electricity price prediction training matrix; and, based on the prediction samples, use the target electricity price average prediction model to predict the target electricity price average within the target transaction contract period.

[0108] In a specific application scenario, the risk assessment system for power trading data further includes: a training module 32 .

[0109] The training module 32 is used to obtain the second market information; and to construct an initial credit analysis model and obtain a target credit analysis model based on the training of the second market information; wherein the second market information is the market information of the historical trading parties with historical electricity transactions.

[0110] In a specific application scenario, the first market information includes the industry information, historical financial status information, technology research and development information, market position information and historical transaction information of the transaction parties, and the calculation module 33 includes: a preprocessing submodule 331 and a calculation submodule 332.

[0111] The preprocessing submodule 331 is used to preprocess the acquired first market information to obtain the first market parameter.

[0112] The calculation submodule 332 is used to calculate the credit parameters of the trading parties according to the target electricity price average and the first market parameter using a target credit analysis model.

[0113] In a specific application scenario, the evaluation module 34 is specifically used to calculate the average historical electricity price of the transaction parties in the previous time period; and, based on the average historical electricity price, the target electricity price average and the credit parameter, calculate the risk value of the target transaction contract; and, based on the risk value, determine the risk level of the target transaction contract according to predetermined level rules.

[0114] It should be noted that for other corresponding descriptions of the functional units involved in the risk assessment system for power trading data provided in the embodiment of the present application, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0115] Based on the above Figure 1 and Figure 2 The method shown in the embodiment of the present application accordingly provides a computer storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The risk assessment method for electricity trading data is shown.

[0116] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0117] Based on the above Figure 1 , Figure 2 The method shown, and Figure 3 , Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The physical device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The risk assessment method for electricity trading data is shown.

[0118] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0119] Those skilled in the art will appreciate that the computer device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0120] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of a computer device and supports the operation of information processing programs and other software and / or programs. The network communication module is used to achieve communication between components within the storage medium and with other hardware and software in the physical device.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware. By applying the technical solution of the present application, compared with the existing technical solution that only evaluates transaction risks based on the market information of the transaction parties and considers too single influencing factors, this embodiment considers the market information of the transaction parties, the impact of changes in electricity prices on the market information of the transaction parties, and the mutual influence between the various market information of the transaction parties when conducting risk assessment. Compared with the risk calculation method of the target transaction contract in the prior art, the risk assessment of the target transaction contract is more accurate.

[0122] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more systems different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0123] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A risk assessment method for power trading data, characterized in that: include: Predict the target average electricity price within the target transaction contract period based on the factors affecting electricity prices; Calculating the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information; The risk level of the target transaction contract is evaluated according to the target electricity price average and the credit parameter.

2. The method according to claim 1, characterized in that The electricity price influencing factors include historical electricity demand, historical fuel prices, electricity supply capacity and historical weather information; the step of predicting the target electricity price average within the target transaction contract period based on the electricity price influencing factors includes: Construct an electricity price prediction training matrix based on electricity price influencing factors and historical electricity prices; By constructing an initial electricity price mean prediction model, a target electricity price mean prediction model is obtained based on the electricity price prediction training matrix; The target electricity price average prediction model is used to predict the target electricity price average within the target transaction contract period.

3. The method according to claim 1 or 2, characterized in that: The step of constructing an initial electricity price mean prediction model and obtaining a target electricity price mean prediction model based on the electricity price prediction training matrix includes: Setting a sliding window based on the electricity price prediction training matrix and obtaining training samples; Setting the average electricity price within the second preset time period as a sample label; According to the initial electricity price mean prediction model, a target electricity price mean prediction model is obtained by training using the training samples and the sample labels.

4. The method according to claim 1 or 2, characterized in that: The step of using the target electricity price average prediction model to predict the target electricity price average within the target transaction contract period includes: Acquire prediction samples according to the electricity price prediction training matrix; According to the prediction samples, the target electricity price average prediction model is used to predict the target electricity price average within the target transaction contract period.

5. The method according to claim 1, characterized in that: Before the step of calculating the credit parameters of the trading parties using the target credit analysis model according to the target electricity price average and the acquired first market information, the step further includes: Obtain secondary market information; By constructing an initial credit analysis model, a target credit analysis model is obtained by training according to the second market information; The second market information is market information of historical trading parties with historical electricity transactions.

6. The method according to claim 1 or 4, characterized in that: The first market information includes industry information, historical financial status information, technology research and development information, market position information and historical transaction information of the transaction party. The step of calculating the credit parameters of the transaction party using the target credit analysis model according to the target electricity price average and the acquired first market information includes: Preprocessing the acquired first market information to obtain first market parameters; According to the target electricity price average and the first market parameter, the credit parameter of the trading party is calculated using a target credit analysis model.

7. The method according to claim 1, characterized in that The step of evaluating the risk level of the target transaction contract according to the target electricity price average and the credit parameter comprises: Calculate the average historical electricity price of the trading party in the previous time period; Calculating the risk value of the target transaction contract based on the historical average electricity price, the target average electricity price and the credit parameter; According to the risk value, the risk level of the target transaction contract is determined according to a predetermined level rule.

8. A risk assessment system for power trading data, characterized in that: include: A prediction module is used to predict the average target electricity price within the target transaction contract period based on factors affecting electricity prices; A calculation module, configured to calculate the credit parameters of the transaction parties using a target credit analysis model according to the target electricity price average and the acquired first market information; An evaluation module is used to evaluate the risk level of the target transaction contract according to the target electricity price average and the credit parameter.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the risk assessment method for power transaction data described in any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the program, the risk assessment method for power transaction data according to any one of claims 1 to 7 is implemented.

Images