Distributed integrated learning method based on block chain

Abstract

The invention discloses a distributed integrated learning method based on a block chain, and the method comprises the steps: enabling miners in a network to train a base model on a training set after sampling through a consensus protocol based on a designed three-layer block chain structure composed of a mini block, an integrated block and a key block, aggregating models from other miners, and carrying out the recognition of the miners. And finally, information of the base model and the integrated model is recorded in the block chain, so that the whole process of model training, model integration and model evaluation is fused into block chain consensus, and the whole integrated learning process is automatically executed in a block chain network. Therefore, the utilization rate of a useful workload proving mechanism based on machine learning on the computing power in the block chain network can be improved, meanwhile, introduction of a center node in the model aggregation process is avoided, and the decentralization degree of the block chain is maximized.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a distributed integrated learning method based on blockchain. Background Art

[0002] Blockchain is a distributed data storage technology that ensures the consistency of data copies on all nodes in an unreliable peer-to-peer network through consensus protocols and incentive mechanisms. The consensus protocol is the cornerstone of the blockchain, and its design fundamentally determines the performance characteristics of the blockchain system, including throughput, consistency, scalability, and robustness. Currently, the Proof of Work (PoW) protocol is one of the most popular consensus protocols. In a PoW-based system, miners generate new blocks by looking for a random number that makes the hash value of the block lower than the target value. However, the mining process consumes a lot of energy, and most of this energy is wasted in meaningless hash calculations.

[0003] At present, there are two solutions to the sustainability problem of the PoW protocol: one is to reduce the amount of computation in the consensus process. The other is the Proof of Useful Work (PoUW) protocol. The latter uses practical computing tasks as proof of computation to meet the computing power needs of third parties. The existing PoUW protocol mainly uses machine learning and optimization tasks as proof of useful work. Frontier research also combines federated learning with blockchain consensus, transforming the mining pool in the PoW system into a cluster of miners competing for machine learning training rewards, and aggregating the models of each mining pool into a global model through the FedAvg algorithm.

[0004] In the above PoUW protocols using machine learning and federated learning, most machine learning-based PoUW schemes select a single model as the winning model and discard the rest, which inevitably leads to low computing power utilization. As for the existing consensus mechanisms based on federated learning, although the models are trained in a distributed manner by data holders, the robustness of these protocols is constrained by the central nodes because the models are usually aggregated by one or several central nodes. Therefore, a technology is needed to aggregate the computing power of each node in a decentralized blockchain network. Summary of the invention

[0005] Purpose of the invention: In view of the problems of low computing power utilization and insufficient decentralization in the existing PoUW protocol, the purpose of the present invention is to design a three-layer blockchain structure consisting of mini blocks, integrated blocks and key blocks, as well as a distributed integrated learning method based on blockchain, to improve the computing power utilization of the blockchain network, while avoiding the introduction of central nodes in the model aggregation process, and maximizing the decentralization of the blockchain.

[0006] Technical solution: To achieve the above-mentioned invention object, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides a three-layer blockchain structure that enables distributed ensemble learning task execution, including:

[0008] MiniBlock, each mini block corresponds to a unique base model, containing the identifier of the machine learning model parameters, the identifier of the model owner, the hash of the previous key block, the machine learning task hash, and the timestamp.

[0009] Ensemble Block, which contains the performance indicators of the ensemble model on the validation dataset, the identifier of the model integrator, the hash of the mini-block corresponding to the integrated base model, the machine learning task hash, and the timestamp.

[0010] The key block contains the hash of the previous key block, the machine learning task hash, the miner identifier, the performance index of the optimal integrated model on the test data set, the timestamp of the key block generation, the root hash of the hash tree carrying the transaction data, the random number, the task queue, the hash of each integrated block participating in the ranking, and its performance index.

[0011] A second aspect of the present invention provides a method for generating a three-layer blockchain structure that enables distributed ensemble learning task execution, comprising the following steps:

[0012] After the miners complete the base model training on the training data set, they generate and broadcast mini blocks; each mini block corresponds to a unique base model, containing the identifier of the machine learning model parameters, the identifier of the model owner, the hash of the previous key block, the machine learning task hash, and a timestamp;

[0013] After the miners aggregate the base models and evaluate their performance on the validation dataset, they generate and broadcast integration blocks; each integration block contains the performance indicators of the integrated model on the validation dataset, the identifier of the model integrator, the hash of the mini-block corresponding to the integrated base model, the machine learning task hash, and the timestamp;

[0014] After the miners evaluate the performance indicators of the collected integrated models on the test data set, they select the optimal integrated model, generate and broadcast the key block; the key block contains the hash of the previous key block, the machine learning task hash, the block miner identifier, the performance indicators of the optimal integrated model on the test data set, the timestamp of the key block generation, the root hash of the hash tree carrying the transaction data, the random number, the task queue, the hash of each integrated block participating in the ranking, and its performance indicators.

[0015] The third aspect of the present invention provides a distributed ensemble learning method based on blockchain, comprising the following steps:

[0016] Step 1: The task publisher prepares training, verification, and test data sets in advance, and publishes machine learning tasks through blockchain transactions. The tasks contain the hash values ​​of the three data sets and scripts for implementing base model training, model integration, and performance evaluation.

[0017] Step ②: The miner verifies the task information and forwards it to other miners.

[0018] Step 3: When the miner generates the last key block or receives a valid last key block from other miners, it downloads the training data set from the task publisher. After the download is complete, the miner starts training the base model, generates mini blocks and broadcasts them.

[0019] Step ④: The task publisher publishes the verification data set. After receiving the message, the miners start to aggregate the base model and evaluate its performance on the verification data set, generate an integrated block and broadcast it.

[0020] Step ⑤: The task publisher publishes the test data set. After receiving the message, the miners start to evaluate the performance indicators of the collected integrated models on the test data set, select the optimal integrated model, calculate the key block hash, generate the key block and broadcast it.

[0021] Step ⑥: The task publisher obtains the performance indicators of the best integrated model and the corresponding base model parameters from the key blocks, and obtains an integrated model with ideal performance by aggregating the base models.

[0022] Preferably, in one embodiment of the present invention, the machine learning task published by the user through the blockchain transaction includes a transaction used as training fee, and the transaction transfers the training fee to a virtual address.

[0023] Preferably, in one embodiment of the present invention, miners who generate key blocks and mini blocks will be rewarded, the training fees of the task publisher are evenly distributed to all miners who generate base models used by the winning integrated model, and miners who generate key blocks are rewarded through newly generated tokens.

[0024] Optionally, in one embodiment of the present invention, the miner may use local private data together with the public training data provided by the task publisher for base model training, thereby improving the quality of the base model and improving the quality of the integrated model.

[0025] Preferably, in one embodiment of the present invention, the integrated model is obtained by aggregating the base models through the Bagging algorithm.

[0026] A fourth aspect of the present invention provides a computer system, comprising a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor, wherein the computer program / instruction implements the steps of the aforementioned method when executed by the processor.

[0027] A fifth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the aforementioned method are implemented.

[0028] A sixth aspect of the present invention provides a computer program product, comprising a computer program / instructions, which implement the steps of the aforementioned method when executed by a processor.

[0029] The distributed ensemble learning method based on blockchain provided by the present invention has the following beneficial effects:

[0030] (1) The present invention designs a three-layer blockchain structure and embeds the distributed ensemble learning process into the generation, verification and propagation of three types of blocks, thereby realizing the execution of distributed ensemble learning tasks in the blockchain.

[0031] (2) Compared with the existing PoUW protocol based on machine learning, the present invention realizes the automation and distributed execution of the integrated learning process in the blockchain network, and forms an integrated model with better performance by aggregating base models trained by multiple miners; and further improves the quality of the base model and the integrated model by allowing miners to use private data.

[0032] (3) Compared with the federated learning proof mechanism, the present invention does not require the mining pool administrator to aggregate the base model, can operate on the public chain, and has a higher degree of decentralization.

[0033] (4) The present invention encourages miners to participate in maintaining blockchain, training models, integrating models and evaluating models by designing an incentive mechanism, so that the blockchain based on the present invention can operate robustly and sustainably.

[0034] (5) The performance of the integrated model generated by the present invention improves as the number of miners in the blockchain that use private data to train the base model increases.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] Figure 1 A schematic diagram of a three-layer block structure for enabling distributed ensemble learning task execution according to an embodiment of the present invention;

[0038] Figure 2 A general flow chart of a distributed integrated learning method based on blockchain provided according to an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of each stage of the task execution process in the distributed ensemble learning method based on blockchain provided according to an embodiment of the present invention;

[0040] Figure 4 Schematic diagram of the performance improvement of the integrated model generated by the embodiment of the present invention relative to the base model and the model trained directly on the public data under different proportions of public data;

[0041] Figure 5 FIG. 4 is a schematic diagram showing the accuracy of the integrated model generated by an embodiment of the present invention under different network scales and network connectivity. DETAILED DESCRIPTION

[0042] The technical solution of the present invention is described in detail below in conjunction with the drawings and specific embodiments. Those skilled in the art should understand that the embodiments described below with reference to the drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0043] The following describes the distributed ensemble learning method based on blockchain in an embodiment of the present invention with reference to the accompanying drawings. In view of the problems of low computing power utilization and insufficient decentralization in the existing PoUW protocol mentioned in the above background technology center, an embodiment of the present invention provides a distributed ensemble learning method based on blockchain, which integrates models trained by multiple miners through the Bagging algorithm. The disclosed three-layer blockchain structure and distributed ensemble learning method can automatically execute model training, model integration and model evaluation processes in a fully decentralized public chain.

[0044] Specifically, Figure 1 A three-layer blockchain structure enabling the execution of distributed ensemble learning tasks is provided according to an embodiment of the present invention.

[0045] like Figure 1 As shown, the three data structures contained in the three-layer blockchain structure and the connection relationship between the three data structures are shown:

[0046] Mini-blocks (denoted as ), which is used to record the ownership of the model and the hash of the model parameters. Each mini-block corresponds to a unique base model and contains the identifier M of the model owner. i , the identifier Hash (ω) calculated by connecting the machine learning model parameters with the miner identifier i ||M i ), the hash of the previous key block (KB h-1 ), machine learning task hash (T h ) and timestamp

[0047] Integrated block (expressed as ), which is used to record the base models required for each ensemble model and the performance indicators of the ensemble model on the validation dataset. The ensemble block points to multiple mini-blocks, and an ensemble model can be obtained by aggregating the base models corresponding to the mini-blocks. The ensemble block contains the performance indicators of the ensemble model on the validation dataset D V Performance indicators on Model integrator identifier M k , a hash of the aggregated base model Machine learning task hash Hash (T h ) and timestamp

[0048] Key block (KB h ), used to store blockchain transactions, task queues, and integrated model rankings, etc., including the hash of the previous key block (KB h-1 ), machine learning task hash (T h ), block miner identifier M ξh , the optimal ensemble model is in the test data set D E Performance indicators on MTC best , the timestamp Γ(KB) of the key block generation h ), the root hash MKR of the hash tree that carries the transaction data h , random number Nonce, task queue Task Queue, hash of each integrated block participating in the ranking as well as The corresponding integrated model is in the test data set D E Performance indicators on

[0049] The embodiment of the present invention provides a three-layer blockchain structure generation method that enables the execution of distributed ensemble learning tasks, and the main steps include: after the miner completes the base model training on the training data set, it generates and broadcasts Figure 1 Mini-blocks in the structure shown; miners generate and broadcast after aggregating the base model and evaluating the performance on the validation dataset Figure 1 The integrated block in the structure shown; after the miners evaluate the performance indicators of the collected integrated models on the test data set, they select the optimal integrated model, generate it and broadcast it Figure 1 Key blocks in the structure shown.

[0050] like Figure 2 and Figure 3 As shown, Figure 2 A distributed ensemble learning method based on blockchain is provided according to an embodiment of the present invention. Figure 3 A schematic diagram of each stage of the task execution process in the blockchain-based distributed ensemble learning method is shown.

[0051] Figure 2 In step ① “Task Release”, the task publisher prepares training, verification, and test data sets in advance, and releases machine learning tasks through blockchain transactions. The task contains the hash values ​​of the three data sets and scripts for implementing base model training, model integration, and performance evaluation, and also includes a transaction for paying the training fee, which transfers the training fee to a virtual address.

[0052] Figure 2 In step ② "Task verification and chaining", miners verify the task information and forward it to other miners. The task will eventually enter the task queue of the key block.

[0053] Figure 2 Steps ③ to ⑤ are the task execution process. Figure 3 Phase 1 (Base Model Training) corresponds to Figure 2 Step ③ "Base model training", Figure 3 The second phase (Phase 2, Ensemble Block Generation) corresponds to Figure 2 Step ④ "Generate integrated block" Figure 3 The third phase (Phase 3, Key Model Generation) corresponds to Figure 2 Step ⑤ "Generate key blocks".

[0054] The task execution process in the embodiment of the present invention includes the following three stages:

[0055] When the block height is h-1, the key block KB h-1 After being generated by a miner, it triggers the first stage of the task execution process. i KB received h-1 After that, if KB h-1 After verification, miner M i The base model will start training. If miner M i Receive one or more valid forks, select the longest fork (i.e. the one with the largest terminal key block height), if the terminal key blocks of these forks have the same height, select the one with the best MTC best The fork where the key block is located is used as the main chain and the tasks at the current height are performed on the main chain. Once the miner M i Confirm KB h-1 , it will choose in KB h-1 The first task in the task queue is to download the public training dataset D T , D T With private datasets Merge into local dataset Then, miner M i In local dataset Execute the training script and generate the parameters ω of the base model i Once the base model is ready, miner M i Timestamp The miner's identifier M i 、Task Hash(T h ), model parameter identifier Hash(ω i ||M i ) and Hash(KB h-1 ) packaged in and broadcast it to the blockchain network All miners receive mini-blocks before the second phase and broadcast them to neighboring miners, but do not transmit the base model to the outside to avoid model theft.

[0056] The task publisher can publicly verify the dataset D at t1 V To trigger the second stage of the task execution process. Once the honest miner M i After receiving the verification dataset, it will refuse to receive new mini-blocks and perform the following steps: (1) Download the verification dataset D V And according to The identifier Hash(ω j ||M j ) Get the model parameters ω j ; (2) Miner M i Verify all collected mini-blocks, if the key block pointed to by the mini-block is invalid, or the model parameters ω downloaded are j With the identifier Hash(ω j ||M j ) does not match, or the performance index of the base model corresponding to the mini-block on the verification data set is lower than the minimum tolerance value given by the task publisher, then the mini-block is considered invalid, and the miner M i All invalid mini-blocks will be discarded; (3) Miner M i Using the validation dataset D V Evaluate the performance index of the ensemble model formed by aggregating the base models corresponding to all valid mini-blocks (4) Timestamp encapsulated in Miner Identifier M i 、Task Hash(T h ), the performance indicators obtained by evaluation A hash of the mini-blocks corresponding to all the aggregated base models and broadcast it to the blockchain network. Before the third phase begins, if miner M i Receive any integrated blocks from other miners Miner M i verify And broadcast the integrated block to neighboring miners.

[0057] The task publisher can publish the test dataset D at t2 E To trigger the third stage of the task execution process. i Receive the test data set D E After that, we will use the test data set D E Evaluate all verified integrated blocks and then try to generate a new key block. Assume that miner M i Already verified and point to and Contains Hash(ω j,l ||M l ), where η j yes The number of mini-blocks pointed to, l is no greater than η j A positive integer, ω j,l By miner M l Then miner M i Calculate K performance indicators and from a series of Find the optimal performance indicator MTC best Assumptions is the best performance indicator. Then the miner M i Load all key block components into candidate blocks By changing the random number and calculating the hash value of the candidate block, the miner will eventually find a block that satisfies Valid key blocks And after receiving a valid key block KB from other miners h Former Broadcaster If a valid key block is found and broadcast Received valid key block KB from other miners before h , then the miners abandon And enter the machine learning task T at block height h+1 h+1 The first stage of the execution process. Here, Target is a static threshold that controls the difficulty of generating key blocks, which is equivalent to the target value in the PoW consensus.

[0058] Figure 2 In step ⑥ "Task End", the task publisher can use the key block KB at block height h h After downloading the base model parameters from the blockchain network and aggregating the base models, the task publisher will obtain an integrated model with ideal performance.

[0059] refer to Figure 4 and Figure 5 In order to reveal the performance of the present invention in actual work, actual tests and data recording were carried out for typical embodiments of the present invention, and the analysis results are as follows.

[0060] Figure 4 It reflects the performance improvement of the integrated model (BagChain) generated by the present invention relative to the base model (Base) and the model (Public) trained simply on public data under different public data ratios. It can be seen that the accuracy (Accuracy) of the integrated model on the test data set is better than any of their base models. When the public data set ratio (PublicDataset Ratio) κ is less than 0.3, the model trained on the public data set performs worse than the base model trained with both private and public data. This can demonstrate the value of the present invention, because when all miners have private data sets that can be used for machine learning tasks, task publishers can obtain high-quality machine learning models from the present invention. It can also be observed that with the increase of the public data set ratio κ, the accuracy of the base model and the integrated model in the present invention are improved, because the increase of the public data set ratio κ leads to an increase in the data samples in the miner's local training data set, thereby generating more accurate base models and integrated models. In addition, the difference between the ensemble models obtained after training the base model for 20 and 30 epochs is negligible, indicating that 20 epochs are sufficient to generate a sufficiently good base model, and the aggregated model has ideal performance, thus illustrating that training the base model in the present invention is lightweight. Therefore, more resource-constrained nodes can participate in model training without fine-tuning the machine learning model, and their models can be aggregated to improve the performance of the ensemble model in the present invention.

[0061] Figure 5 It reflects the accuracy of the integrated model generated by the present invention under different network scales and network connectivity. The sparse network in the figure is a network model with worse connectivity than the fully connected synchronous network. It can be seen that with the increase in the number of miners, the average accuracy on the test data set increases, because as the network scale expands, more private data and computing power are invested in the training of the base model. In addition, the higher private data set ratio significantly improves the accuracy of the integrated model generated in the present invention, indicating that under higher levels of miner participation and private data abundance, the performance of the integrated model in the present invention is improved. In addition, comparing the accuracy under the two network models shows that in the sparse network model, the performance of the present invention is basically unaffected, which highlights the robustness of the present invention in a more severe network environment.

[0062] The present invention discloses a distributed ensemble learning method based on blockchain, designs a three-layer blockchain structure consisting of mini-blocks, integrated blocks and key blocks, and designs a consensus protocol so that miners in the network train a base model on a training set after replacement sampling and aggregate models from other miners, and finally record the information of the base model and the integrated model on the blockchain, thereby integrating the entire process of model training, model integration and model evaluation into the blockchain consensus mechanism. This method can realize the automation and distributed execution of the entire ensemble learning process in the blockchain network, improve the computing power utilization rate of the useful workload proof mechanism based on machine learning in the blockchain network, and avoid introducing central nodes in the model aggregation process, thereby maximizing the degree of decentralization of the blockchain.

[0063] An embodiment of the present invention provides a computer system, including a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor, wherein the steps of the aforementioned method are implemented when the computer program / instruction is executed by the processor.

[0064] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the aforementioned method are implemented.

[0065] An embodiment of the present invention provides a computer program product, including a computer program / instruction, which implements the steps of the above method when executed by a processor.

Claims

1. A three-layer blockchain structure that enables distributed ensemble learning task execution, It is characterized in that include: Mini-blocks, each mini-block corresponds to a unique base model and contains the identifier of the machine learning model parameters, the identifier of the model owner, the hash of the previous key block, the machine learning task hash, and a timestamp; The integration block contains the performance indicators of the integrated model on the validation dataset, the identifier of the model integrator, the hash of the mini-block corresponding to the integrated base model, the machine learning task hash and the timestamp; The key block includes the hash of the previous key block, the machine learning task hash, the block miner identifier, the performance indicators of the optimal integrated model on the test data set, the timestamp of the key block generation, the root hash of the hash tree carrying the transaction data, the random number, the task queue, the hash of each integrated block participating in the ranking, and its performance indicators.

2. A three-layer blockchain structure generation method that enables distributed ensemble learning task execution, It is characterized in that The following steps are involved: After the miners complete the base model training on the training data set, they generate and broadcast mini blocks; each mini block corresponds to a unique base model, containing the identifier of the machine learning model parameters, the identifier of the model owner, the hash of the previous key block, the machine learning task hash, and a timestamp; After the miners aggregate the base models and evaluate their performance on the validation dataset, they generate and broadcast integration blocks; each integration block contains the performance indicators of the integrated model on the validation dataset, the identifier of the model integrator, the hash of the mini-block corresponding to the integrated base model, the machine learning task hash, and the timestamp; After the miners evaluate the performance indicators of the collected integrated models on the test data set, they select the optimal integrated model, generate and broadcast the key block; the key block contains the hash of the previous key block, the machine learning task hash, the block miner identifier, the performance indicators of the optimal integrated model on the test data set, the timestamp of the key block generation, the root hash of the hash tree carrying the transaction data, the random number, the task queue, the hash of each integrated block participating in the ranking, and its performance indicators.

3. A distributed ensemble learning method based on blockchain, It is characterized in that The following steps are involved: The task publisher prepares training, validation, and test data sets in advance, and publishes machine learning tasks through blockchain transactions. The tasks contain the hash values ​​of the three data sets and scripts for implementing base model training, model integration, and performance evaluation. The miner verifies the task information and forwards it to other miners. When the miner generates the last key block or receives a valid last key block from other miners, it downloads the training data set from the task publisher. After the download is complete, the miner starts training the base model, generates a mini block and broadcasts it. The mini block contains the identifier of the machine learning model parameters, the identifier of the model owner, the hash of the last key block, the machine learning task hash and a timestamp. The task publisher publishes the verification data set. After receiving the message, the miners start to aggregate the base model and evaluate its performance on the verification data set, generate integrated blocks and broadcast them; The integrated block includes the performance index of the integrated model on the validation data set, the identifier of the model integrator, the hash of the mini-block corresponding to the integrated base model, the machine learning task hash and the timestamp; The task publisher publishes the test data set. After receiving the message, the miners start to evaluate the performance indicators of the collected ensemble models on the test data set, select the optimal ensemble model, calculate the key block hash, generate the key block and broadcast it; The key block includes the hash of the previous key block, the machine learning task hash, the block miner identifier, the performance index of the optimal integrated model on the test data set, the timestamp of the key block generation, the root hash of the hash tree carrying the transaction data, the random number, the task queue, the hash of each integrated block participating in the ranking, and its performance index; The task publisher obtains the performance indicators of the best integrated model and the corresponding base model parameters from the key blocks, and obtains an integrated model with ideal performance by aggregating the base models.

4. According to the distributed ensemble learning method based on blockchain according to claim 3, It is characterized in that The machine learning task published by the user through the blockchain transaction includes a transaction used as training fee, which transfers the training fee to a virtual address.

5. According to the distributed ensemble learning method based on blockchain in claim 3, It is characterized in that Miners who generate key blocks and mini blocks will be rewarded, and the training costs of the task publisher are evenly distributed to all miners who generate base models used by the winning integrated model. At the same time, miners who generate key blocks are rewarded through newly generated tokens.

6. The distributed ensemble learning method based on blockchain according to claim 3, It is characterized in that Miners use local private data together with the public training data provided by the task publisher for base model training.

7. The distributed ensemble learning method based on blockchain according to claim 3, It is characterized in that The integrated model is obtained by aggregating the base models through the Bagging algorithm.

8. A computer system comprising a memory, a processor and a computer program / instructions stored in the memory and executable on the processor, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 2 to 7 are implemented.

9. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 2 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 2 to 7 are implemented.

Images