A wind power prediction method and system based on deep learning

Abstract

The present invention provides a wind power prediction method and system based on deep learning; wherein the method comprises: receiving wind data detected by each wind detector in a first area; processing the wind data to obtain a first wind matrix; inputting the wind matrix into a deep learning model, the deep learning model outputting a second wind matrix in a second area; and obtaining a wind power prediction value according to the second wind matrix. The solution of the present invention can predict the wind data in the core area of ​​a wind power generation device / equipment group based on wind data in a large range, thereby obtaining a more accurate wind power prediction value.

Description

Technical Field

[0001] The present invention relates to the field of wind power technology, and in particular to a wind power prediction method, system, electronic device and computer storage medium based on deep learning. Background Art

[0002] Under the dual carbon goals, large-scale centralized development is an important model for my country's future wind power development. However, under this model, wind resources and their power generation will present complex coupling and aggregation characteristics in time and space, exacerbating the adverse effects of their uncertainty on the safety, stability, and economic operation of the power system. How to accurately predict the spatiotemporal uncertainty of wind power has become a key issue that needs to be broken through in the new energy power system. Summary of the invention

[0003] In order to at least solve the technical problems existing in the above-mentioned background technology, the present invention provides a wind power prediction method, system, electronic device and computer storage medium based on deep learning.

[0004] A first aspect of the present invention provides a wind power prediction method based on deep learning, comprising the following steps:

[0005] Receiving wind data detected by each wind detector in the first area;

[0006] Processing the wind data to obtain a first wind matrix;

[0007] Inputting the wind matrix into a deep learning model, wherein the deep learning model outputs a second wind matrix in a second region;

[0008] A wind power prediction value is obtained according to the second wind power matrix.

[0009] Further, the processing the wind data to obtain a first wind matrix includes:

[0010] Extracting first positioning data and first wind direction data from each of the wind force data;

[0011] Filter and process each of the wind force data according to the first positioning data, the first wind direction data and the second positioning data of the second area;

[0012] Constructing the first wind matrix by using the plurality of wind data after screening according to a first preset relationship;

[0013] The first wind matrix includes first positioning data, first wind direction data, and first wind data.

[0014] Furthermore, before the wind matrix is ​​input into the deep learning model, the method further includes:

[0015] Acquire a third wind matrix and a corresponding fourth wind matrix of the historical records, and form a data pair with the third wind matrix and the fourth wind matrix; wherein the third wind matrix corresponds to the first area, and the fourth wind matrix corresponds to the second area;

[0016] A number of the data pairs are selected to form a training set, and the deep learning model is trained using the training set.

[0017] Furthermore, in the process of training the deep learning model using the training set, the following loss function is used:

[0018]

[0019] In the formula, f loss is the loss function, y represents the equivalent value of the result output by the deep learning model in the nth round of training, f(x) represents the equivalent value of each fourth wind force matrix in the data pair input into the deep learning model in the nth round of training; σ is the adjustment coefficient, which is positively correlated with the training rounds.

[0020] Further, after the deep learning model outputs the second wind matrix in the second area, the method further includes:

[0021] Calculating the similarity between the second wind matrix and the fourth wind matrix, and if the similarity is less than a threshold, correcting the second wind matrix according to the fourth wind matrix to obtain a corrected second wind matrix;

[0022] Otherwise, the second wind force matrix is ​​not corrected.

[0023] Further, obtaining a wind power prediction value according to the second wind matrix includes:

[0024] Extracting second positioning data, second wind direction data, and second wind force data corresponding to each virtual detection point from the second wind force matrix;

[0025] Determine a first weight of each virtual detection point according to each of the second positioning data and the second wind direction data, and determine equivalent wind data according to the first weight and the second wind data of each virtual detection point;

[0026] The wind power prediction value is obtained according to the equivalent wind force data and the second preset relationship.

[0027] Further, the correcting the second wind matrix according to the fourth wind matrix includes:

[0028] Determine the equivalent wind sub-data of each virtual detection point according to the weight and the second wind data of each virtual detection point, and calculate the fluctuation value of each equivalent wind sub-data;

[0029] determining a second weight of the second wind matrix according to the fluctuation value, and determining a third weight of the fourth wind matrix according to the second weight;

[0030] The modified second wind matrix is ​​calculated according to the fourth wind matrix and the third weight, the second wind matrix and the second weight.

[0031] A second aspect of the present invention provides a wind power prediction system based on deep learning, comprising a receiving module, a processing module, and a storage module; the processing module is connected to the receiving module and the storage module;

[0032] The storage module is used to store executable computer program code;

[0033] The receiving module is used to receive relevant data and transmit it to the processing module;

[0034] The processing module is used to execute the method as described in any of the preceding items by calling the executable computer program code in the storage module.

[0035] The third aspect of the present invention provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0036] A fourth aspect of the present invention provides a computer storage medium having a computer program stored thereon, and the computer program, when executed by a processor, executes any of the methods described above.

[0037] The solution of the present invention receives wind data detected by each wind detector in a first area; performs a first process on the wind data to obtain a first wind matrix; inputs the wind matrix into a deep learning model, and the deep learning model outputs a second wind matrix in a second area; and obtains a wind power prediction value based on the second wind matrix. The solution of the present invention can predict the wind data in the core area of ​​a wind power generation device / equipment group based on wind data in a large range, thereby obtaining a more accurate wind power prediction value. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 It is a flowchart of a wind power prediction method based on deep learning disclosed in an embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a wind power prediction system based on deep learning disclosed in an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0044] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0045] It should be understood that although the terms first, second, third, etc. may be used to describe ... in the embodiments of the present application, these ... should not be limited to these terms. These terms are only used to distinguish .... For example, without departing from the scope of the embodiments of the present application, the first ... may also be referred to as the second ..., and similarly, the second ... may also be referred to as the first ....

[0046] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0047] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a product or system. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the product or system including the elements.

[0048] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] Embodiment 1

[0050] See also Figure 1 , Figure 1 is a flow chart of a wind power prediction method based on deep learning disclosed in an embodiment of the present invention. Figure 1 As shown, a wind power prediction method based on deep learning in an embodiment of the present invention includes the following steps:

[0051] Receiving wind data detected by each wind detector in the first area;

[0052] Processing the wind data to obtain a first wind matrix;

[0053] Inputting the wind matrix into a deep learning model, wherein the deep learning model outputs a second wind matrix in a second region;

[0054] A wind power prediction value is obtained according to the second wind power matrix.

[0055] In an embodiment of the present invention, a first area is set for each wind power generation device or / equipment group, and at the same time, multiple wind detectors are arranged in the first area. After receiving the wind data detected by the distributed wind detectors, the first wind matrix is ​​obtained after the first processing. The first wind matrix reflects the real-time wind distribution in the first area; then, the first wind matrix is ​​input into the deep learning model to predict the second wind matrix of the second area, and then the wind power prediction value is obtained by analyzing and calculating the second wind matrix. Among them, the first area is a larger area outside each wind power generation device or / group, and the second area is a smaller area in the core area of ​​each wind power generation device or / equipment group, that is, the second area is the core area of ​​the first area. Therefore, the solution of the present invention can predict the wind data in the core area of ​​the wind power generation device / equipment group based on the wind data in a large range, and then can obtain a more accurate wind power prediction value.

[0056] It should be noted that the solution of the present invention is implemented in the processing center, and the processing center is connected to each wind detector in communication, so that the processing center receives the wind data detected by each wind detector and processes and predicts it. Among them, the communication link can adopt the 5th generation mobile communication point-to-point (5G Point to point) link, the second generation mobile communication (2G) point-to-point link, the 5th generation mobile communication wireless local area network (5G Wireless Local Area Networks, WLAN) link, 2G WLAN link, Ethernet (Ethernet, ETH) link, Bluetooth Low Energy (Bluetooth Low Energy, BLE) link, Wireless Fidelity (Wireless Fidelity, WIFI) link and wired connection link based on Universal Serial Bus (Universal Serial Bus, USB), etc., and the specific details are not repeated.

[0057] In addition, the deep learning models involved can be constructed through CNN, RNN, LSTM and other algorithms, and the specific construction methods will not be repeated here.

[0058] Further, the processing the wind data to obtain a first wind matrix includes:

[0059] Extracting first positioning data and first wind direction data from each of the wind force data;

[0060] Screening and processing each of the wind force data according to the first positioning data, the first wind direction data and the second positioning data of the second area;

[0061] Constructing the first wind matrix by using the plurality of wind force data after screening according to a first preset relationship;

[0062] The first wind matrix includes first positioning data, first wind direction data, and first wind data.

[0063] In an embodiment of the present invention, the wind data detected by each wind detector includes at least first positioning data and first wind direction data. Meanwhile, the second positioning data of the core area where the wind power generation equipment is located, i.e., the second area, is taken into consideration. Thus, those wind data that are useless for wind power generation can be screened out. For example, the wind data located downstream of the wind power generation equipment (i.e., away from the wind power generation equipment) can be screened out.

[0064] The preset relationship may be freely set, for example, it may be determined according to the ID number of each wind detector, or it may be determined based on the location of each wind detector relative to the wind power generation equipment, and the present invention does not limit this.

[0065] Furthermore, before the wind matrix is ​​input into the deep learning model, the method further includes:

[0066] Acquire a third wind matrix and a corresponding fourth wind matrix of the historical records, and form a data pair with the third wind matrix and the fourth wind matrix; wherein the third wind matrix corresponds to the first area, and the fourth wind matrix corresponds to the second area;

[0067] A number of the data pairs are selected to form a training set, and the deep learning model is trained using the training set.

[0068] In an embodiment of the present invention, model training is a prerequisite to ensure that the deep learning model can output accurate prediction results. The present invention forms data pairs with the third wind matrix and the fourth wind matrix in the recorded historical data, and then selects an appropriate number of data pairs to form a training set to realize the training of the deep learning model.

[0069] Among them, the third wind matrix and the fourth wind matrix belong to the first area and the second area in space, and are separated by a set time in time. The set time can be determined based on the position of the corresponding third wind matrix and the second area. For example, the wind data at least includes first positioning data, first wind direction data, and first wind data. The distance difference between each wind detector and the second area can be calculated based on the first positioning data and the second positioning data, and the aforementioned set time can be predicted based on the wind direction data and the wind data. Obviously, the set time corresponding to each historical record data in the present invention is calculated separately and is different from each other.

[0070] It should be noted that, based on the relationship between the fourth wind matrix and the third wind matrix in the above training set, it can be determined that the second wind matrix in the present invention is actually the integral value of the predicted value of each wind data contained in the first wind matrix in the second area, that is, the second wind matrix is ​​used to describe the prediction of the wind transmission intensity of the first wind matrix in the second area, i.e., the core area of ​​wind power generation, within a set time period.

[0071] Furthermore, in the process of training the deep learning model using the training set, the following loss function is used:

[0072]

[0073] In the formula, f loss is the loss function, y represents the equivalent value of the result output by the deep learning model in the nth round of training, f(x) represents the equivalent value of each fourth wind force matrix in the data pair input into the deep learning model in the nth round of training; σ is the adjustment coefficient, which is positively correlated with the training rounds.

[0074] In an embodiment of the present invention, the loss function is crucial for the training of the deep learning model. The rationality of the loss function is directly related to the accuracy of the deep learning model in establishing the functional relationship between the first wind matrix and the second wind matrix, which in turn affects the accuracy of the subsequent prediction of the second wind matrix.

[0075] The present invention designs the above loss function, in the first stage of training, σ is a value less than 1, and in the second stage of training, σ is a value greater than 1, so that the training process from the first stage to the middle stage increases the deviation between the predicted value and the true value, and the training process from the middle stage to the last stage decreases the deviation between the predicted value and the true value. Therefore, the first stage focuses on the accuracy of training, and the last stage focuses on the efficiency of training.

[0076] Further, after the deep learning model outputs the second wind matrix in the second area, the method further includes:

[0077] Calculating the similarity between the second wind matrix and the fourth wind matrix, and if the similarity is less than a threshold, correcting the second wind matrix according to the fourth wind matrix to obtain a corrected second wind matrix;

[0078] Otherwise, the second wind force matrix is ​​not corrected.

[0079] In an embodiment of the present invention, after the deep learning model outputs the predicted second wind matrix, the present invention further analyzes whether the predicted second wind matrix has similar historical data. If so, a more accurate wind matrix, i.e., the corrected second wind matrix, is obtained based on the second wind matrix and the fourth wind matrix at the same time. Otherwise, the current prediction result shall prevail. The correction method can be implemented by taking an average value.

[0080] It should be noted that the similarity between wind matrices can be calculated using a variety of similarity calculation methods in the prior art, such as cosine similarity, Pearson correlation coefficient, Tanimoto coefficient, Hamming distance, etc., and the present invention is not limited to this.

[0081] Further, obtaining a wind power prediction value according to the second wind matrix includes:

[0082] Extracting second positioning data, second wind direction data, and second wind force data corresponding to each virtual detection point from the second wind force matrix;

[0083] Determine a first weight of each virtual detection point according to each of the second positioning data and the second wind direction data, and determine equivalent wind data according to the first weight and the second wind data of each virtual detection point;

[0084] The wind power prediction value is obtained according to the equivalent wind force data and the second preset relationship.

[0085] In an embodiment of the present invention, in order to improve the prediction accuracy, it is necessary to set the second area, i.e., the core area, as small as possible. At this time, the second area may not include wind detectors or the number of wind detectors may be insufficient. To address this problem, the present invention sets a number of virtual detection points in the second area, i.e., the core area. The second wind matrix composed of the prediction data of each virtual detection point can be predicted by the aforementioned method. At the same time, the first weight (for example, determined based on the deflection angle) of the wind force of the virtual detection point relative to the corresponding wind power generation equipment can be calculated based on the second positioning data and the second wind direction data of the virtual detection point, and then the equivalent wind force data of the overall transmission of each virtual detection point to the wind power generation equipment can be determined based on the weight and the second wind data.

[0086] After the equivalent wind power data is determined, the wind power prediction value can be calculated based on the performance parameters of the wind power generation equipment (such as rated power generation, conversion efficiency, etc.).

[0087] Further, the correcting the second wind matrix according to the fourth wind matrix includes:

[0088] Determine the equivalent wind sub-data of each virtual detection point according to the weight and the second wind data of each virtual detection point, and calculate the fluctuation value of each equivalent wind sub-data;

[0089] determining a second weight of the second wind matrix according to the fluctuation value, and determining a third weight of the fourth wind matrix according to the second weight;

[0090] The modified second wind matrix is ​​calculated according to the fourth wind matrix and the third weight, the second wind matrix and the second weight.

[0091] The embodiment of the present invention is an improvement on the aforementioned embodiment, and the fluctuation value (variance or square difference) of the second wind matrix obtained by calculation and prediction is obtained. The higher the fluctuation value is, the more complex the wind source in the area is. At this time, the weight of the second wind matrix can be appropriately increased according to the fluctuation value, that is, the weight of the fourth wind matrix can be lowered (the sum of the two matrices is 1), and then a more accurate second wind matrix can be obtained by weighted averaging.

[0092] Embodiment 2

[0093] See also Figure 2 , Figure 2 Schematic diagram of a wind power prediction system based on deep learning disclosed in an embodiment of the present invention. Figure 2 As shown, a wind power prediction system based on deep learning according to an embodiment of the present invention comprises a receiving module (101), a processing module (102), and a storage module (103); the processing module (101) is connected to the receiving module (101) and the storage module (103);

[0094] The storage module (103) is used to store executable computer program code;

[0095] The receiving module (101) is used to receive relevant data and transmit it to the processing module (102);

[0096] The processing module (102) is used to execute the method described in the first embodiment by calling the executable computer program code in the storage module (103).

[0097] The specific functions of a wind power prediction system based on deep learning in this embodiment refer to the above-mentioned embodiment 1. Since the system in this embodiment adopts all the technical solutions of the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be described one by one here.

[0098] Embodiment 3

[0099] See also Figure 3, Figure 3 An electronic device disclosed in an embodiment of the present invention comprises: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in the first embodiment.

[0100] Embodiment 4

[0101] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first embodiment is executed.

[0102] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0103] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0104] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0105] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0106] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present invention, all of which belong to the scope of protection of the present invention.

Claims

1. A wind power prediction method based on deep learning, characterized in that: The steps include: Receiving wind data detected by each wind detector in the first area; Processing the wind data to obtain a first wind matrix; The wind matrix is ​​input into a deep learning model, and the deep learning model outputs a second wind matrix in a second area; wherein the first area is an area outside each wind power generation device or / group, and the second area is an area of ​​a core area of ​​each wind power generation device or / group, that is, the second area is an inner core area of ​​the first area; deriving a wind power prediction value according to the second wind matrix; Before inputting the wind matrix into the deep learning model, it also includes: Acquire a third wind matrix and a corresponding fourth wind matrix of the historical records, and form a data pair with the third wind matrix and the fourth wind matrix; wherein the third wind matrix corresponds to the first area, and the fourth wind matrix corresponds to the second area; Selecting a number of the data pairs to form a training set, and using the training set to train the deep learning model; In the process of training the deep learning model using the training set, the following loss function is used: In the formula, f loss is the loss function, y represents the equivalent value of the result output by the deep learning model in the nth round of training, f(x) represents the equivalent value of each fourth wind matrix in the data pair input into the deep learning model in the nth round of training; σ is the adjustment coefficient, which is positively correlated with the training rounds. In the early stage of training, σ is a value less than 1, and in the latter stage of training, σ is a value greater than 1.

2. The wind power prediction method based on deep learning according to claim 1, characterized in that: The step of processing the wind data to obtain a first wind matrix comprises: Extracting first positioning data and first wind direction data from each of the wind force data; Screening and processing each of the wind force data according to the first positioning data, the first wind direction data and the second positioning data of the second area; Constructing the first wind matrix by using the plurality of wind force data after screening according to a first preset relationship; The first wind matrix includes first positioning data, first wind direction data, and first wind data.

3. The wind power prediction method based on deep learning according to claim 1, characterized in that: After the deep learning model outputs the second wind matrix in the second area, the method further includes: Calculating the similarity between the second wind matrix and the fourth wind matrix, and if the similarity is less than a threshold, correcting the second wind matrix according to the fourth wind matrix to obtain a corrected second wind matrix; Otherwise, the second wind force matrix is ​​not corrected.

4. The method for wind power prediction based on deep learning according to claim 3, characterized in that: The step of obtaining a wind power prediction value according to the second wind matrix includes: Extracting second positioning data, second wind direction data, and second wind force data corresponding to each virtual detection point from the second wind force matrix; wherein each of the virtual detection points is set in the second area, i.e., the core area; Determine a first weight of each virtual detection point according to each of the second positioning data and the second wind direction data, and determine equivalent wind data according to the first weight and the second wind data of each virtual detection point; The wind power prediction value is obtained according to the equivalent wind force data and the second preset relationship.

5. The method for wind power prediction based on deep learning according to claim 4, characterized in that: The correcting the second wind matrix according to the fourth wind matrix includes: Determine the equivalent wind sub-data of each virtual detection point according to the weight and the second wind data of each virtual detection point, and calculate the fluctuation value of each equivalent wind sub-data; determining a second weight of the second wind matrix according to the fluctuation value, and determining a third weight of the fourth wind matrix according to the second weight; The modified second wind matrix is ​​calculated according to the fourth wind matrix and the third weight, the second wind matrix and the second weight.

6. A wind power prediction system based on deep learning, comprising a receiving module, a processing module, and a storage module; the processing module is connected to the receiving module and the storage module; The storage module is used to store executable computer program code; The receiving module is used to receive relevant data and transmit it to the processing module; Features: The processing module is used to execute the method according to any one of claims 1 to 5 by calling the executable computer program code in the storage module.

7. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-5.

8. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images