Technical status and development analysis method and device based on deep neural network

Abstract

The embodiment of the invention provides a technology status and development analysis method and device based on a deep neural network, and the method comprises the steps: receiving technology development data which is used for indicating the technology status and / or development trend; extracting technology development characteristics from the technology development data based on a self-attention mechanism; according to a preset dimension label, classifying the technology development characteristics; respectively carrying out convolution on each type of technology development features to obtain corresponding convolution features; fusing the convolution features to obtain a keyword set; and according to the keyword set, generating a knowledge graph of the current technical situation and development. The technical scheme provided by the invention is used for solving the problem of data loss in the data mining and analysis process in the prior art, so that the data loss probability is reduced.

Description

Technical Field

[0001] This document relates to the field of knowledge prediction, and in particular to a method and apparatus for analyzing the current status and development of deep neural network technology. Background Technology

[0002] In the era of data explosion, how to extract valuable data on the current status and development of new energy storage technologies from massive amounts of data is a concern for enterprises and a hot topic for researchers.

[0003] Traditional data mining and analysis methods can extract relevant information about new energy storage technologies from data.

[0004] However, existing technologies suffer from data loss during data mining and analysis. Furthermore, results presented in tables and reports are not intuitive and have limited dimensions of presentation. Summary of the Invention

[0005] In view of the above-mentioned technical problems, this application aims to propose a method and apparatus for analyzing the current status and development of deep neural networks, so as to solve at least one of the above-mentioned technical problems.

[0006] Firstly, one or more embodiments of this specification provide a method for analyzing the current state and development of technologies based on deep neural networks, including:

[0007] Receive technology development data, which is used to indicate the current state and / or development trend of technology;

[0008] Based on the self-attention mechanism, technological development features are extracted from the technological development data;

[0009] The technological development characteristics are classified according to preset dimension labels;

[0010] Convolution is performed on each type of technological development characteristic to obtain the corresponding convolutional features;

[0011] The convolutional features are fused to obtain a keyword set; and

[0012] Based on the set of keywords, a knowledge graph of the current state and development of technology is generated.

[0013] Furthermore, before receiving technology development data, the method further includes:

[0014] Retrieve technical literature data from a pre-set database;

[0015] Based on a pre-defined dual-tower recall model, the technical literature data is recalled to obtain first-ranked data; and

[0016] The first sorted data is used as the technology development data.

[0017] Furthermore, after obtaining the first sorted data, the method further includes:

[0018] Based on a preset deep semantic matching model, the first sorted data is sorted to obtain the second sorted data; and

[0019] The second sorted data is used as the technology development data.

[0020] Furthermore, after obtaining a knowledge graph of the current state and development of technology, the method also includes:

[0021] Based on the knowledge graph, extract indicators for scientific papers; and

[0022] Using the aforementioned scientific and technological paper indicators as training samples, a preset deep neural network is trained. The deep neural network is used to identify academic papers and patents in the field of new energy storage technologies with potential development value.

[0023] Furthermore, the dimension labels include the frequency of keyword occurrences in the literature.

[0024] Secondly, one or more embodiments of this specification provide a device for analyzing the current state and development of deep neural networks, including:

[0025] A receiving module is used to receive technology development data, which is used to indicate the current state of technology and / or development trends.

[0026] An extraction module is used to extract technological development features from the technological development data based on a self-attention mechanism.

[0027] The classification module is used to classify the technological development characteristics according to preset dimension labels;

[0028] The convolution module is used to perform convolutions on each type of technological development feature to obtain the corresponding convolutional features.

[0029] The feature fusion module is used to fuse the convolutional features to obtain a keyword set; and

[0030] The generation module is used to generate a knowledge graph of the current state and development of technology based on the set of keywords.

[0031] Furthermore, it also includes:

[0032] The acquisition module is used to retrieve technical literature data from a preset database;

[0033] The recall module is used to recall the technical literature data based on a preset dual-tower recall model to obtain first-ranked data; and

[0034] The first sorted data is used as the technology development data.

[0035] Furthermore, it also includes:

[0036] The sorting module is used to sort the first sorted data based on a preset deep semantic matching model to obtain the second sorted data; and

[0037] The second sorted data is used as the technology development data.

[0038] Furthermore, it also includes:

[0039] The extraction module is used to extract scientific paper indicators based on the knowledge graph; and

[0040] The training module is used to train a preset deep neural network using the scientific and technological paper indicators as training samples. The deep neural network is used to identify academic papers and patents in the field of new energy storage technologies with potential development value.

[0041] Thirdly, one or more embodiments of this specification provide a storage medium, including:

[0042] Used to store computer-executable instructions, which, when executed, implement the method described in any of the first aspects.

[0043] Compared with the prior art, this application can achieve at least the following technical effects:

[0044] To address the issue of data loss, this application introduces a self-attention mechanism into a graph deep neural network to ensure that as many features as possible are extracted. Then, based on preset dimensional labels, the technological development features are classified, and convolution is performed on each category of technological development features to reduce the probability of data loss for each category, thereby reducing the overall data loss probability in the analysis process. Finally, the analysis results are presented intuitively using a knowledge graph. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1A flowchart illustrating a method for analyzing the current state and development of deep neural network technology, provided for one or more embodiments of this specification;

[0047] Figure 2 This is a schematic diagram of the structure of a device for analyzing the current status and development of deep neural networks, provided for one or more embodiments of this specification. Detailed Implementation

[0048] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0049] This application provides a method for analyzing the current state and development of deep neural network technology, such as... Figure 1 As shown, it includes the following steps:

[0050] Step 1: Receive technology development data.

[0051] In this application embodiment, technology development data is used to indicate the current state and / or development trend of technology, and is derived from government reports, patent documents, the internet, academic journals, etc. This data can be obtained directly from the aforementioned sources or can be processed data.

[0052] Step 2: Extract technological development characteristics from technological development data based on the self-attention mechanism.

[0053] In this embodiment, the knowledge graph essentially constitutes a semantic link, storing various entities and their interrelationships to map various things in the objective world and their relationships. Considering the aforementioned characteristics of the knowledge graph, this application uses a graph neural network as the deep neural network. Furthermore, to reduce the probability of data loss, a self-attention mechanism is embedded in the graph neural network. This self-attention mechanism is a special type of attention mechanism that allows the model to consider the relationship between each element in a sequence and all other elements when processing a sequence. This mechanism helps the model better understand the contextual information in the sequence by calculating the correlation (or weight) between each element and other elements, thereby processing the sequence data more accurately.

[0054] Step 3: Classify the characteristics of technological development according to the preset dimension labels.

[0055] In this embodiment, nodes in the knowledge graph can be considered keywords. These keywords are distributed across various types of literature. The frequency of keyword occurrence and the weight of keywords in related literature differ. For example, in literature specifically researching a particular technology, keyword A will inevitably appear frequently. However, in another article, where the technology is not the focus, the frequency of keyword A will decrease. In top-tier journals, government reports, and other literature, because the technologies mentioned are usually forward-looking, the weight of keywords in these documents is typically greater than in other documents.

[0056] In response to the fact that the frequency of keyword occurrence and the weight of keywords in related literature are different, this application uses dimension labels to classify the extracted features so that convolution can be performed on each category separately, which can reduce the probability of data loss.

[0057] For example, keyword A appears frequently in file 1 but infrequently in file 2. If the two are convolved together, the features of keyword A in file 2 are easily lost. However, if they are convolved separately, the features from both files will be extracted.

[0058] Step 4: Perform convolution on each type of technological development feature to obtain the corresponding convolutional features.

[0059] In this embodiment of the application, the convolution process involves three neural network layers, each consisting of a convolutional layer and a pooling layer.

[0060] Step 5: Fuse convolutional features to obtain a keyword set.

[0061] In this embodiment, the neural network involved in feature fusion has only one layer, which is a fully connected layer. That is, the fully connected layer is used to concatenate the features obtained from convolution to obtain the nodes in the knowledge graph, i.e., the keyword set.

[0062] Step 6: Generate a knowledge graph of the current state and development of technology based on the keyword set.

[0063] In this application embodiment, a knowledge graph is generated based on triples using keywords from a keyword set. In the knowledge graph, the larger the node, the more important and potentially valuable the corresponding technical field. Thicker lines between nodes indicate a stronger connection between them. Stronger connections suggest that the related technology may become key to future technological development. Therefore, the knowledge graph provided in this application can intuitively display the current state and development of technology.

[0064] Therefore, this application reduces the probability of data loss based on self-attention mechanisms and feature classification. Furthermore, it utilizes knowledge graphs to intuitively demonstrate the current state and development of the technology.

[0065] In this embodiment of the application, in order to further prevent data loss, technical literature data is obtained from a preset database; based on a preset dual-tower recall model, the technical literature data is recalled to obtain first sorted data; the first sorted data is used as the technology development data.

[0066] Recall algorithms can be roughly divided into two main categories:

[0067] Statistical recall: Based on mining user's historical interaction data with items, without involving model training.

[0068] Model-based recall updates model parameters through a loss function and requires model training. This often involves vectorizing users and items separately, and then calculating the relationship between them based on their respective vectors.

[0069] The dual-tower recall model is a model-based recall method. As the name suggests, it requires that items and users be mapped to a deep neural network tower respectively. After the inputs of each tower pass through the first few hidden layers, the last hidden layer is the user vector representation and the item vector representation. The output prediction value is obtained by the normalized inner product of the two. The loss between the prediction value and the true value is calculated, and then the parameters are updated by backpropagation to achieve the purpose of model learning.

[0070] The dual-tower recall model adopted in this application is CCKG (compressed collaborative knowledge graph). This model can effectively fuse recommended content and knowledge graph at the implicit semantic level, so as to obtain more accurate nodes in the knowledge graph.

[0071] Preferably, in order to obtain nodes in the knowledge graph more accurately, in this embodiment of the application, after obtaining the first sorted data, the first sorted data is sorted based on a preset deep semantic matching model to obtain the second sorted data; the second sorted data is used as the technology development data.

[0072] The Deep Semantic Matching Model (DSSM) demonstrates superior performance in latent semantic mining and representation. It effectively constructs representation vectors that conform to the latent semantic characteristics of each data point, and then uses a cosine similarity algorithm to rank the latent semantic feature representation vectors to derive the similarity order of the technology development data. This lays the foundation for the subsequent construction of knowledge graphs.

[0073] Because knowledge graphs can intuitively display the current state and development of technology, this application proposes a method for evaluating whether technical solutions in literature have development potential, utilizing knowledge graphs. Specifically,

[0074] Based on the knowledge graph, scientific paper indicators are extracted. Using these indicators as training samples, a pre-defined deep neural network (DNN) is trained. This DNN identifies academic papers and patents in the field of new energy storage technologies with potential development value. The DNN is equipped with four hidden layers consisting of 5, 10, 10, and 5 neurons. This network can perform classification operations on two different types of objects: academic papers and patents in the field of new energy storage technologies with high or low potential development value. The DNN's input can process data with ten-dimensional feature indicators. First, these hidden layers are initialized with random values ​​following a normal distribution. The output layer is responsible for comparing and verifying the prediction results of each training sample with its actual development prospects. The model adjusts its internal parameters by continuously iteratively optimizing the loss function. When the loss function stabilizes and converges to a predetermined limit, the model's parameters are finally optimized, and further training terminates.

[0075] Therefore, knowledge graphs represent the current state and development of technology from the perspective of volume and surface, while evaluating whether a technical solution in a document has development potential represents the current state and development of technology from the perspective of points. The combination of the two can help users gain a more comprehensive and objective understanding of the current state and development of technology.

[0076] In this embodiment, the dimension label includes the frequency of keyword occurrences in the literature. Specifically, the frequency of keyword occurrences in the literature and the weight of keywords in related literature are different. For example, in literature specifically researching a certain technology, keyword A will inevitably appear frequently. However, in another article, the technology is not the focus of the description, and the frequency of keyword A will decrease accordingly. Grouping based on the frequency of keyword occurrences in the literature can better avoid data loss. For example, keyword A appears frequently in document 1, infrequently in document 2, and at a medium frequency in document 3. In this case, the corresponding features can be divided into three categories according to the frequency of keyword occurrences in the literature: high frequency, medium frequency, and low frequency. Then, convolution is performed separately, and the features from all three documents will be extracted.

[0077] This application provides a device for analyzing the current state and development of deep neural networks, such as... Figure 2 As shown, it includes:

[0078] Receiving module 201 is used to receive technology development data, which is used to indicate the current state of technology and / or development trends;

[0079] Extraction module 202 is used to extract technological development features from the technological development data based on a self-attention mechanism;

[0080] The classification module 203 is used to classify the technological development characteristics according to preset dimension labels;

[0081] Convolution module 204 is used to perform convolution on each type of technological development feature to obtain the corresponding convolution features;

[0082] Feature fusion module 205 is used to fuse the convolutional features to obtain a keyword set; and

[0083] The generation module 206 is used to generate a knowledge graph of the current status and development of technology based on the set of keywords.

[0084] In this embodiment of the application, the device further includes:

[0085] The acquisition module is used to retrieve technical literature data from a preset database;

[0086] The recall module is used to recall the technical literature data based on a preset dual-tower recall model to obtain first-ranked data; and

[0087] The first sorted data is used as the technology development data.

[0088] In this embodiment of the application, the device further includes:

[0089] The sorting module is used to sort the first sorted data based on a preset deep semantic matching model to obtain the second sorted data; and

[0090] The second sorted data is used as the technology development data.

[0091] In this embodiment of the application, the device further includes:

[0092] The extraction module is used to extract scientific paper indicators based on the knowledge graph; and

[0093] The training module is used to train a preset deep neural network using the scientific and technological paper indicators as training samples. The deep neural network is used to identify academic papers and patents in the field of new energy storage technologies with potential development value.

[0094] This application provides a storage medium, including:

[0095] Used to store computer-executable instructions, which, when executed, implement the method described in any of the above embodiments.

[0096] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0097] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using a hardware physical module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital methodology "integrated" onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0098] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0099] The methods, apparatus, modules, or units described in the above embodiments can be implemented by a computer chip or entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0100] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0101] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, method, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (methods), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0107] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0109] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0110] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the method embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0111] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A method for analyzing the current status and development of technology based on deep neural networks, characterized in that The method comprises: Receiving technology development data, wherein the technology development data is used to indicate the technology status and / or development trend; Extracting technology development features from the technology development data based on a self-attention mechanism; Classify the technical development characteristics according to preset dimension labels; Convolution is performed on each category of technological development features to obtain corresponding convolution features; fusing the convolutional features to obtain a keyword set; and Based on the keyword set, a knowledge graph of technology status and development is generated.

2. The method according to claim 1, characterized in that Before receiving the technology development data, the method further includes: Obtain technical literature data from a preset database; Based on a preset double-tower recall model, the technical document data is recalled to obtain first ranking data; and The first sorting data is used as the technology development data.

3. The method according to claim 2, characterized in that After obtaining the first sorting data, the method further includes: sorting the first sorting data based on a preset deep semantic matching model to obtain second sorting data; and The second sorting data is used as the technology development data.

4. The method according to claim 1, characterized in that After obtaining the knowledge graph of the current status and development of the technology, the method further includes: Extracting scientific paper indicators according to the knowledge graph; and The scientific and technological paper indicators are used as training samples to train a preset deep neural network, which is used to determine academic papers and patents in the field of new energy storage technologies with potential development value.

5. The method according to claim 1, characterized in that The dimension tags include: the frequency of occurrence of keywords in the document.

6. A technology status and development analysis device based on deep neural network, characterized in that include: A receiving module, used to receive technology development data, where the technology development data is used to indicate the technology status and / or development trend; An extraction module, for extracting technology development features from the technology development data based on a self-attention mechanism; A classification module, used for classifying the technical development characteristics according to preset dimension labels; The convolution module is used to perform convolution on each type of technology development features to obtain corresponding convolution features; A feature fusion module, used to fuse the convolution features to obtain a keyword set; as well as A generation module is used to generate a knowledge graph of technology status and development based on the keyword set.

7. The device according to claim 6, characterized in that Also includes: An acquisition module is used to acquire technical literature data from a preset database; A recall module, used for recalling the technical document data based on a preset double-tower recall model to obtain first sorted data; as well as The first sorting data is used as the technology development data.

8. The device according to claim 7, characterized in that Also includes: A sorting module, used to sort the first sorting data based on a preset deep semantic matching model to obtain second sorting data; as well as The second sorting data is used as the technology development data.

9. The device according to claim 8, characterized in that Also includes: An extraction module, used for extracting scientific paper indicators according to the knowledge graph; as well as The training module is used to train a preset deep neural network using the scientific paper indicators as training samples, and the deep neural network is used to determine academic papers and patents in the field of new energy storage technologies with potential development value.

10. A storage medium for storing computer executable instructions, characterized in that: When the computer executable instructions are executed, the method according to any one of claims 1 to 5 is implemented.

Images