CN117422553A - Transaction processing method, device, equipment, medium and product of blockchain network - Google Patents
Transaction processing method, device, equipment, medium and product of blockchain network Download PDFInfo
- Publication number
- CN117422553A CN117422553A CN202311436637.0A CN202311436637A CN117422553A CN 117422553 A CN117422553 A CN 117422553A CN 202311436637 A CN202311436637 A CN 202311436637A CN 117422553 A CN117422553 A CN 117422553A
- Authority
- CN
- China
- Prior art keywords
- transaction
- type
- transaction data
- target
- digital resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 23
- 238000006243 chemical reaction Methods 0.000 claims abstract description 278
- 238000000034 method Methods 0.000 claims abstract description 71
- 238000012545 processing Methods 0.000 claims description 70
- 230000004927 fusion Effects 0.000 claims description 43
- 230000000977 initiatory effect Effects 0.000 claims description 40
- 230000015654 memory Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 10
- 238000012790 confirmation Methods 0.000 claims description 9
- 238000004806 packaging method and process Methods 0.000 claims description 9
- 230000007704 transition Effects 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 13
- 238000012549 training Methods 0.000 description 40
- 230000008569 process Effects 0.000 description 24
- 230000006870 function Effects 0.000 description 23
- 239000003999 initiator Substances 0.000 description 19
- 238000010586 diagram Methods 0.000 description 18
- 238000005516 engineering process Methods 0.000 description 16
- 239000013598 vector Substances 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 5
- 230000008451 emotion Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000010200 validation analysis Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000000586 desensitisation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a transaction processing method, device, equipment, medium and product of a blockchain network, which relate to the technical field of blockchains and artificial intelligence, and the method comprises the following steps: acquiring target transaction data for converting a target digital resource of a second type into a digital resource of a first type; acquiring resource circulation index information and reference transaction data associated with a second type of digital resource; the reference transaction data pertains to transaction data that converts a digital resource of a second type into a digital resource of a first type; based on the resource circulation index information and the reference transaction data, predicting the conversion quantity of the target digital resource for the first type of digital resource, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed at the blockchain network based on the predicted conversion amount. By adopting the method and the device, the conversion quantity of the target digital resource into the digital resource of the first type can be accurately predicted.
Description
Technical Field
The present disclosure relates to the field of blockchain technologies, and in particular, to a transaction processing method, apparatus, device, medium, and product for a blockchain network.
Background
In the scenario that the value evaluation is performed on the digital resource to realize the resource conversion of the digital resource, if the value of the digital resource is evaluated to be too high, the transaction of the digital resource is not facilitated; if the value of the digital resource is evaluated too low, it may be difficult to represent the value of the digital resource itself.
At present, when the value of the digital resource is evaluated, the average value or the median of the multi-transaction value of the digital resource is taken as the value obtained by the current evaluation of the digital resource, and the value evaluation mode is too simple, so that the value of the digital resource evaluation is inaccurate easily. Therefore, how to realize accurate value assessment of digital resources is a highly desirable problem.
Disclosure of Invention
The embodiment of the application provides a transaction processing method, device, equipment, medium and product of a blockchain network, which can realize accurate prediction of conversion quantity of converting target digital resources into first type digital resources.
In a first aspect, the present application provides a transaction processing method of a blockchain network, including:
acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
acquiring the resource circulation index information associated with the first type of digital resources, and acquiring the reference transaction data associated with the second type of digital resources; the reference transaction data pertains to transaction data that converts the second type of digital resource into the first type of digital resource;
based on the resource circulation index information and the reference transaction data, predicting the conversion quantity of the target digital resource for the first type of digital resource, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource;
the target transaction data is executed in the blockchain network based on the predicted conversion amount.
In a second aspect, the present application provides a transaction processing device of a blockchain network, comprising:
a transaction acquisition unit for acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
The index acquisition unit is used for acquiring the resource circulation index information associated with the first type of digital resources and acquiring the reference transaction data associated with the second type of digital resources; the reference transaction data pertains to transaction data that converts the second type of digital resource into the first type of digital resource;
the data prediction unit is used for predicting the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource;
and the transaction execution unit is used for executing the target transaction data in the blockchain network based on the predicted conversion amount.
Optionally, the index obtaining unit is specifically configured to:
acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
historical transaction data generated during the adjacent time period for converting the second type of digital resource to the first type of digital resource is obtained as the reference transaction data.
Optionally, the index obtaining unit is specifically configured to:
Acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
acquiring the resource circulation index information of the first type of digital resource in the adjacent time period;
wherein the resource circulation index information includes at least one of: conversion rate between the first type of digital resource and other general type of digital resource, gain rate of the first type of digital resource.
Optionally, the data prediction unit is specifically configured to:
acquiring a prediction model, and calling the prediction model to perform fusion embedding processing on the resource circulation index information and the reference transaction data to generate fusion prediction characteristics;
predicting the conversion quantity of the target digital resource aiming at the digital resource of the first type based on the fusion prediction characteristic, and generating the prediction conversion quantity; the method comprises the steps of,
and predicting transaction risk of the target digital resource based on the fusion prediction feature, and generating a predicted risk level of the target digital resource.
Optionally, the target transaction data is initiated by a transaction client; the transaction execution unit is specifically configured to:
generating transaction execution inquiry information based on the predicted conversion amount and the predicted risk level, and transmitting the transaction execution inquiry information to the transaction client;
If the confirmation information of the transaction execution inquiry information sent by the transaction client is received, packaging the predicted conversion quantity into the target transaction data to generate first packaged transaction data;
broadcasting the first packaged transaction data to the blockchain network for consensus processing;
if the first encapsulated transaction data is successfully identified in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
wherein the amount of the first type of digital resource converted by the target digital resource is the predicted conversion amount.
Optionally, the target transaction data is initiated by a transaction client; the transaction execution unit is specifically configured to:
generating a selection interval of the conversion quantity of the target digital resource for the second type of digital resource based on the predicted conversion quantity, and transmitting the selection interval and the predicted risk level to the transaction client;
receiving a target conversion amount sent by the transaction client; the target conversion amount is a conversion amount selected from the selection interval by the transaction client after performing a confirmation operation on the predicted risk level;
packaging the target conversion amount into the target transaction data, generating second packaged transaction data, and broadcasting the second packaged transaction data to the blockchain network for consensus processing;
If the target transaction data is successfully identified in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
wherein the resource amount of the first type of digital resource of the target digital resource conversion is the target conversion amount.
Optionally, the transaction processing device of the blockchain network further includes: a model training unit for:
obtaining a prediction model to be trained and sample transaction data; the sample transaction data has a first sample tag for indicating an actual conversion amount of the sample transaction data for the first type of digital resource and a second sample tag for indicating an actual transaction risk level of the sample transaction data;
acquiring sample resource circulation index information associated with the first type of digital resources, and acquiring sample reference transaction data associated with the second type of sample digital resources; the sample reference transaction data pertains to transaction data that converts the second type of sample digital resource to the first type of digital resource;
invoking the prediction model to be trained to generate a sample prediction conversion quantity of the sample digital resource for the first type of digital resource and a sample prediction risk level of the sample digital resource based on the sample resource circulation index information and the sample reference transaction data;
And correcting model parameters of the prediction model to be trained based on the sample prediction conversion quantity, the sample prediction risk level, the first sample label and the second sample label to obtain the prediction model.
Optionally, the model training unit is specifically configured to:
generating a first prediction bias of the prediction model to be trained for the sample predicted conversion amount based on a difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag;
generating a second prediction deviation of the prediction model to be trained for the sample prediction risk level based on the difference between the sample prediction risk level and the transaction risk level indicated by the second sample tag;
adding the first prediction deviation and the second prediction deviation to generate a model integral prediction deviation of the prediction model to be trained;
and correcting model parameters of the prediction model to be trained based on the overall prediction deviation to obtain the prediction model.
In a third aspect, the present application provides a computer device comprising a processor and a memory, wherein the processor is coupled to the memory, the memory is configured to store a computer program, and the processor is configured to invoke the computer program to cause the computer program to perform the transaction processing method of the blockchain network.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored therein, the computer program being adapted to be loaded and executed by a processor to cause a computer device having the processor to perform the transaction processing method of the blockchain network described above.
In a fifth aspect, the present application provides a computer program product comprising computer programs/instructions which when executed by a processor implement the transaction processing method of a blockchain network as described above.
In the embodiment of the application, target transaction data are acquired; acquiring resource circulation index information associated with a first type of digital resource and reference transaction data associated with a second type of digital resource, and performing prediction processing on the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate a predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed in the blockchain network based on the predicted conversion amount. Since the reference transaction data refers to transaction data which belongs to the same type as the target digital resource in the target transaction data and is already transacted, the reference transaction data can be used as a reference of the conversion quantity of the target digital resource for the first type of digital resource in the target transaction data, and the resource circulation index information associated with the first type of digital resource can reflect the resource circulation condition of the first type of digital resource. Therefore, the conversion amount of the target digital resource converted into the first type of digital resource is predicted by combining the reference transaction data and the resource circulation index information associated with the first type of digital resource, and the conversion amount of the target digital resource can be predicted from different dimensions, so that the accuracy of predicting the conversion amount of the target digital resource is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a schematic diagram of a network architecture of a transaction processing system according to an embodiment of the present application;
FIG. 1b is a schematic diagram of a blockchain node system provided in an embodiment of the present application;
FIG. 1c is a schematic diagram of a blockchain composition provided in an embodiment of the present application;
fig. 2 is an application scenario schematic diagram of a transaction processing method of a blockchain network according to an embodiment of the present application;
FIG. 3 is a flow chart of a transaction processing method of a blockchain network according to an embodiment of the present disclosure;
FIG. 4 is a flow chart of another transaction processing method of a blockchain network according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a transaction processing device of a blockchain network according to an embodiment of the present disclosure;
fig. 6 is a schematic diagram of a composition structure of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.
The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions. The scheme provided by the embodiment of the application belongs to the machine learning technology in the artificial intelligence field.
Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, confidence networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like. For example, machine learning techniques may be employed in the present application to predict the conversion amount of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data, generate a predicted conversion amount of the target digital resource for the first type of digital resource, and so on.
The technical scheme of the method and the device can be suitable for predicting the value of the target digital resource (such as a digital collection) in the transaction data to obtain the predicted conversion quantity (namely the transaction price) of the target digital resource, so that the target digital resource can be transacted based on the predicted conversion quantity. Because the value of the target digital resource is difficult to evaluate before the transaction is performed, the value of the target digital resource can be reflected more reasonably by predicting the predicted conversion amount of the target digital resource, so that the transaction is performed based on the predicted value of the target digital resource. Optionally, the technical solution of the present application may also be applied to various scenarios, for example, but not limited to, cloud technology, artificial intelligence, intelligent transportation, driving assistance, and the like.
Referring to fig. 1a, fig. 1a is a network architecture diagram of a transaction processing system according to an embodiment of the present application, and as shown in fig. 1a, the network architecture diagram includes a blockchain network 10 and a transaction client 11, where the blockchain network 10 has a plurality of blockchain nodes. Wherein the transaction client 11 may be used to initiate target transaction data. The blockchain nodes in the blockchain network 10 may be configured to receive the target transaction data, call a prediction model to predict a price of the target digital resource in the target transaction data to obtain a predicted conversion amount, that is, predict a conversion amount of converting the target digital resource in the target transaction data into the digital resource of the first type to obtain the predicted conversion amount. The blockchain points in the blockchain network 10 may also be used to execute target transaction data in the blockchain network 10 based on the predicted conversion amount, and so forth.
It is to be understood that the blockchain nodes in the blockchain network mentioned in the embodiments of the present application may include, but are not limited to, a terminal device or a server, and may also be a system composed of a server and a terminal device. The above-mentioned terminal device may be an electronic device, including, but not limited to, a mobile phone, a tablet computer, a desktop computer, a notebook computer, a palm computer, a vehicle-mounted device, an intelligent voice interaction device, an augmented Reality (AR/VR) device, a head mounted display, a wearable device, a smart speaker, a smart home appliance, an aircraft, a digital camera, a camera, and other mobile internet devices (mobile internet device, MID) with network access capability, etc. The server mentioned above may be a separate physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, vehicle-road collaboration, content distribution network (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
It should be specifically noted that, in the embodiment of the present application, the collection and processing of related data (such as data of target transaction data, resource circulation index information, reference transaction data, etc.) should be strictly according to requirements of laws and regulations of related regions when the application is implemented, so as to obtain informed consent or independent consent of the personal information body, and develop subsequent data use and processing behaviors within the authorized range of laws and regulations and the personal information body. For example, an object may refer to a user of a terminal device or a computer device.
In addition, referring to fig. 1b, fig. 1b is a schematic diagram of a blockchain node system provided in an embodiment of the present application, where the blockchain node system is a system composed of blockchain link points in a blockchain network, and the blockchain node system shown in fig. 1b is a system for transaction processing, and each node in the blockchain node system can receive input information during normal operation and maintain shared data in the blockchain node system based on the received input information. In order to ensure the information intercommunication in the block chain node system, information connection can exist between each node in the block chain node system, and the nodes can transmit information through the information connection. For example, when any node in the blockchain node system receives input information, other nodes in the blockchain node system acquire the input information according to a consensus algorithm, and store the input information as data in shared data, so that the data stored on all nodes in the blockchain node system are consistent.
For each node in the blockchain node system, the node identification corresponding to the node is provided, and each node in the blockchain node system can store the node identifications of other nodes in the blockchain node system so as to broadcast the generated blocks to other nodes in the blockchain node system according to the node identifications of other nodes. Each node can maintain a node identification list shown in the following table, and the node names and the node identifications are correspondingly stored in the node identification list. The node identifier may be an IP (Internet Protocol, protocol of interconnection between networks) address, and any other information that can be used to identify the node, and the IP address is only illustrated in table 1.
TABLE 1
| Node name | Node identification |
| Node 1 | 117.114.151.174 |
| Node 2 | 117.116.189.145 |
| … | … |
| Node N | 119.123.789.258 |
Each node in the blockchain node system stores one and the same blockchain. Referring to fig. 1c, fig. 1c is a schematic diagram of a block chain composition provided in an embodiment of the present application, where the block chain is composed of a plurality of blocks, and an initiation block includes a block header and a block body, where the block header stores an input information feature value, a version number, a timestamp and a difficulty value, and the block body stores input information; the next block of the starting block takes the starting block as a father block, the next block also comprises a block head and a block main body, the block head stores the input information characteristic value of the current block, the block head characteristic value of the father block, the version number, the timestamp and the difficulty value, and the like, so that the block data stored in each block in the block chain are associated with the block data stored in the father block, and the safety of the input information in the block is ensured.
The embodiment of the application utilizes the intelligent contract in the blockchain technology and the characteristic that the blockchain is not tamperable to process transaction data, namely provides a transaction processing method of a blockchain network. Wherein the smart contract, i.e. the computerized agreement, may execute the terms of a certain contract, implemented by code deployed on the shared ledger for execution upon satisfaction of certain conditions, for completing automated transactions according to actual business demand code, of course, the smart contract is not limited to executing contracts for transactions, but may also execute contracts that process received information. The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like, and is essentially a decentralised database; the blockchain may be composed of a plurality of serial transaction records (also known as blocks) that are cryptographically concatenated and protected from content, and the distributed ledgers concatenated by the blockchain enable multiple parties to effectively record transactions and permanently verify the transactions (non-tamperable). The consensus mechanism is a mathematical algorithm for realizing trust establishment and rights acquisition among different nodes in the blockchain network; that is, the consensus mechanism is a mathematical algorithm commonly recognized by the network nodes of the blockchain.
Further, referring to fig. 2, fig. 2 is a schematic application scenario diagram of a transaction processing method of a blockchain network according to an embodiment of the present application; as shown in fig. 2, the transaction client 20 may initiate target transaction data for converting a target digital resource (e.g., collection X vase drawing) 21 in the blockchain network into a first type of digital resource, and after the blockchain node 22 in the blockchain network obtains the target transaction data, it may obtain the resource circulation index information 23 associated with the first type of digital resource and the reference transaction data 24 associated with the second type of digital resource and input the prediction model 25. The call prediction model 25 predicts the conversion amount of the target digital resource 21 for the first type of digital resource based on the resource circulation index information 23 and the reference transaction data 24, and generates a predicted conversion amount 26 of the target digital resource for the first type of digital resource. The predictive conversion quantity 26 may be used to reflect the price of the target digital resource, for example, the predictive conversion quantity 26 is 10000 yuan. Further, the blockchain node 22 in the blockchain network may generate and send to the transaction client 20 transaction execution query information 27 containing the predicted conversion amount 26. The transaction client 20 may trigger a corresponding operation, such as a validation operation, for the transaction execution query information 27, thereby generating validation information 28 for the transaction execution query information 27, and send the validation information 28 for the transaction execution query information 27 to the blockchain nodes 22 in the blockchain network, the blockchain nodes 22 in the blockchain network may execute the target transaction data in the blockchain network based on the predicted conversion amount 26.
Further, referring to fig. 3, fig. 3 is a flow chart of a transaction processing method of a blockchain network according to an embodiment of the present application; as shown in fig. 3, the transaction processing method of the blockchain network can be applied to any blockchain node in the blockchain network, and the transaction processing method of the blockchain network includes, but is not limited to, the following steps:
s101, acquiring target transaction data.
In the embodiment of the application, the target transaction data is transaction data indicating that the target digital resource is transacted. For example, the target transaction data may be transaction data indicating selling or purchasing the target digital resource, and the ownership of the target digital resource, such as a transaction initiator, may initiate the target transaction data, and the transaction recipient may effect the change in ownership of the target digital resource by transferring the digital resource corresponding to the value of the target digital resource to the resource account of the transaction initiator, which delivers the target digital resource to the transaction recipient.
The digital resource may include multiple types, for example, in the embodiment of the present application, the digital resource that needs to be transacted in the target transaction data may refer to the target digital resource. The target digital resource may be, for example, NFT (Non-homogeneous Token), that is, the target digital resource is also called digital collection, and is a collection resource with exclusive rights. The digital collection can refer to the rights and the ticket of the virtual digital commodity, and also refer to the rights and the ticket of the entity asset. If the digital collection may refer to the rights and credentials of the virtual digital commodity, the target digital resource may be generated based on a digital collection protocol. The types of target digital resources may include, but are not limited to, artwork, collectibles, collection cultural relics, brand classes, games, music, movies, sports, and physical resources. Alternatively, the form of the target digital resource may include, for example, but is not limited to, various forms of digital drawings, pictures, music, video, 3D (3-Dimension) models, and the like.
Since the target digital resource is a collection, the number is small or the number of some collections is only one, it is difficult to evaluate the value of the target digital resource, so that the transaction price is difficult to determine when any target digital resource needing to be transacted is transacted, and thus, the transaction of the target digital resource is difficult. At present, the price of the collection in recent transaction is generally used as a reference, for example, the price of the near-term transaction is directly used as the price of the target digital resource in need of transaction at present, or the average or median of a plurality of collections in near-term transaction is used as the price of the target digital resource in need of transaction at present, and the pricing mode is simpler and can not reflect the value of the target digital resource well.
Therefore, the embodiment of the application provides a method for predicting pricing of the target digital resource, which solves the problem that the pricing is difficult when the target digital resource is transacted due to the sparse price data of the target digital resource through machine learning. By acquiring a great number of factors such as reference prices of target digital resources traded in historical time periods and other types of digital resources (such as first type digital resources obtained by trading the target digital resources) in the same period as a training data set, a prediction model is trained, so that the value of any target digital resources needing to be traded can be predicted by using the prediction model. When predicting the value of any target digital resource needing to be transacted, the target digital resource transacted in the historical period and reference prices of other types of digital resources in the same period are combined to predict, so that the price of any target digital resource needing to be transacted can be continuously and smoothly predicted, and the prediction accuracy is improved.
In this embodiment of the present application, the transaction client may initiate the target transaction data, and the transaction client may refer to any client that initiates the target transaction data. For example, a transaction client may refer to a client used by a transaction initiator that requires a targeted digital resource to be sold. The target transaction data may refer to transaction data for performing transactions on target digital resources that need to be transacted, i.e., the target digital resources in the target transaction data refer to target digital resources that do not perform transactions. The blockchain nodes in the blockchain network can acquire the target transaction data, so that the target transaction data is processed and then executed in the blockchain network. By executing the target transaction data in the blockchain network, the target transaction data can be ensured not to be tampered, so that the authenticity of the data is ensured, and the follow-up tracing of the target transaction data is facilitated.
The target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type. The second type of digital resource refers to a collection type of digital resource, i.e., the second type of digital resource is rare, such as a digital collection or other type of collection. The first type of digital resource refers to digital resources other than the second type of digital resource, namely the first type of digital resource can be widely applied to various transaction scenes. For example, a first type of digital resource may refer to a digital resource that is common to various regions or may be applied to some specific scenario, such as a game scenario. The first type of digital resource may refer to a tool for measuring the value of an item, i.e., the medium on which the transaction is conducted. For example, the greater the number of digital resources of the first type required to purchase an item, the higher the value of the item. The smaller the number of digital resources of the first type required to purchase an item, the lower the value of the item. The transaction initiator may convert the second type of digital resource to the first type of digital resource by way of sale or mortgage, etc. The transaction initiator may also convert the digital resources of the first type to digital resources of the second type by purchase or redemption, or the like. The range of use of the digital resources of the first type is wider than the range of use of the digital resources of the second type.
In the embodiment of the application, the target transaction data may include an identification of a target digital resource, an identification of a transaction initiator, an identification of a transaction receiver, a transaction initiation time, a transaction type, and the like. The identification of the target digital resource may include, but is not limited to, a name of the target digital resource, a stock number of the target digital resource, a picture of the target digital resource, and so forth. The identification of the transaction initiator may include, for example, but is not limited to, the name of the transaction initiator, the transaction address of the transaction initiator, and the like. The identification of the transaction recipient may include, for example, but is not limited to, the name of the transaction recipient, the transaction address of the transaction recipient, and so forth. The transaction types may include, for example, but are not limited to, sales, purchases, mortgages, and redemption, among others. By acquiring the target transaction data, the type of the target digital resource required to be transacted and the time required to be transacted by the target digital resource can be determined, and then the reference transaction data of the target transaction data can be determined based on the type of the target digital resource and the time required to be transacted by the target digital resource, so that the value of the target digital resource in the target transaction data can be predicted based on the reference transaction data, and the transaction can be performed based on the predicted price.
S102, acquiring the resource circulation index information associated with the first type of digital resources, and acquiring the reference transaction data associated with the second type of digital resources.
In the embodiment of the application, since the target transaction data for converting the target digital resource in the blockchain network into the digital resource of the first type is obtained, the value of the target digital resource can be evaluated, so that a reasonable price is selected as the price of the target digital resource transaction. Since the target digital resource is converted into the first type of digital resource, the price of the target digital resource transaction can be predicted by combining the resource circulation index information associated with the first type of digital resource and the reference transaction data associated with the second type of digital resource.
Wherein the reference transaction data refers to transaction data that has been performed, the reference transaction data belonging to transaction data that converts a digital resource of a second type into a digital resource of a first type. For example, the reference trading data may refer to a price for trading for a digital resource of the same type as the target digital resource. For example, the target digital resource is drawing 1 of object a, the target transaction data may refer to transaction data that converts drawing 1 of object a into a digital resource of a first type, and the reference transaction data may refer to transaction data that has transacted drawing 2 of object a, such as transaction data that converts drawing 2 of object a into a digital resource of a first type. Or the reference transaction data may also refer to transaction data that has been transacted for drawing 1 of object B, and so on. The reference transaction data may include, but is not limited to, transaction party information, type of target digital resource for the transaction (i.e., type of digital collection), amount of conversion of the second type of digital resource into the first type of digital resource (i.e., transaction price), number of transactions, time of transaction, and so forth. That is, the reference trading data may refer to prices of the same type of digital resource when trading the same type of digital resource over a historical period of time, and thus may serve as a reference for pricing the target digital resource.
Further, the resource circulation index information associated with the first type of digital resource may reflect a resource circulation condition of the first type of digital resource. The resource circulation index information associated with the digital resources of the first type may be used to indicate the value of the digital resources of the first type. For example, the resource circulation index information associated with the first type of digital resource can be used for reflecting the condition of value increment or value detraction of the first type of digital resource, and the resource circulation index information associated with the first type of digital resource can reflect the global trade situation. The value of the target digital resource may be reduced as the global trade situation changes, for example, the global trade situation is in a declining period. The global trade situation is in the rise phase and the value of the target digital resource will rise. Therefore, when the value of the target digital resource is predicted, the transaction price of the target digital resource is predicted by combining the resource circulation index information associated with the first type of digital resource, so that the prediction accuracy can be improved. The resource circulation index information associated with the first type of digital resource may include, for example, but is not limited to, trade data for the first type of digital resource-associated region, a total production value for the first type of digital resource-associated region, an overall trade market index for reflecting the first type of digital resource-associated region, and so forth.
It is understood that the resource circulation index information associated with the first type of digital resource may refer to resource circulation index information synchronized with the transaction time of the reference transaction data, that is, the resource circulation index information may be used to reflect the reference price of the first type of digital resource synchronized with the reference transaction data. For example, the resource circulation index information may indicate an impact of contemporaneous global trading situation of the reference trading data on the digital resource of the first type. The synchronization of the reference transaction data may refer to a period of time matching the transaction initiation time of the reference transaction data, for example, may refer to the transaction initiation time of the reference transaction data or a transaction period within which the transaction initiation time is located.
In one embodiment, reference transaction data associated with the second type of digital resource may be periodically acquired, and the transaction price of the target digital resource may be predicted based on the transaction price of the second type of digital resource in the periodically acquired reference transaction data. For example, the transaction initiation time of the target transaction data may be acquired, and the proximity period before the transaction initiation time is acquired; historical transaction data generated during the vicinity period for converting the digital resource of the second type into the digital resource of the first type is obtained as reference transaction data.
Wherein, the adjacent time period before the transaction initiation time may refer to a time period of one month, one week, or custom days before the transaction initiation time. For example, the transaction initiation time is 2023, 10 and 25 days, then the adjacent time period may refer to one week prior to the transaction initiation time, such as 2023, 10, 18, and 2023, 10, 25, or one month prior to the transaction initiation time, such as 2023, 9, 25, and 2023, 10, 25, and so on. By acquiring historical transaction data generated in a period adjacent to the transaction initiation time and used for converting the target digital resource into the digital resource of the first type as reference transaction data, namely taking the historical transaction data of the digital resource of the same type as the target digital resource as reference transaction data, the transaction price of the digital resource of the second type in the reference transaction data can be referenced.
In the embodiment of the application, by periodically acquiring the historical transaction data as the reference transaction data, the transaction price of the target digital resource to be transacted can be predicted by combining the transaction price of the second type digital resource in the reference transaction data.
In another embodiment, reference transaction data associated with the second type of digital resource may be quantitatively acquired, and the price of the target digital resource may be predicted based on the price of the second type of digital resource in the quantitatively acquired reference transaction data. For example, the transaction initiation time of the target transaction data may be acquired, and all the historical transaction data generated before the transaction initiation time for converting the second type of digital resource into the first type of digital resource may be acquired, and the target number of the historical transaction data may be selected from all the historical transaction data as the reference transaction data.
For example, if the target number is 1000, the transaction initiation time is 2023, 10 months, 25 days, and the total amount of all the history transaction data generated before the transaction initiation time for converting the second type of digital resource into the first type of digital resource is 10000, 1000 pieces of history transaction data may be selected as reference transaction data from 10000 pieces of history transaction data. Optionally, 1000 pieces of historical transaction data with the later transaction initiation time in 10000 pieces of historical transaction data can be used as reference transaction data.
In the embodiment of the application, by acquiring quantitative historical transaction data as the reference transaction data, the transaction price of the target digital resource to be transacted can be predicted by combining the transaction price of the digital resource of the second type in the reference transaction data.
In one possible implementation, the historical transaction data generated in the adjacent time period for converting the digital resource of the second type into the digital resource of the other general type may be used as reference transaction data, or all the historical transaction data generated before the transaction initiation time for converting the digital resource of the second type into the digital resource of the other general type may be used as reference transaction data, and the target number of the historical transaction data may be selected from all the historical transaction data. Since the types of digital resources can be of various types in addition to the second type. For example, the types of digital resources common to each region may be different, and when the reference transaction data is acquired, historical transaction data converted from the target digital resource into any type of digital resource may be determined as the reference transaction data, and by converting other common types of digital resources into the first type of digital resource, the price of the target digital resource may be determined, and more reference transaction data amounts are acquired, so that the prediction is facilitated.
In one embodiment, the resource circulation index information associated with the digital resource of the first type may be obtained by: acquiring transaction initiation time of target transaction data, and acquiring a neighboring period before the transaction initiation time; and acquiring resource circulation index information of the first type of digital resources in the adjacent time period.
The resource circulation index information associated with the first type of digital resource may refer to macro transaction market data of the first type of digital resource, where the macro transaction market data may be used to macroscopically reflect a value change condition of the first type of digital resource, for example, may be used to measure a transaction condition in a transaction platform, and the macro transaction market data may refer to an index reflecting prices of the digital resource of various transaction types in the transaction platform. For example, in a trading platform, pricing of a target digital resource may be affected by macroscopic trade market data, e.g., macroscopic trade market data may refer to a value case that macroscopically reflects a first type of digital resource across the country or world, etc. For example, the resource circulation index information associated with the digital resource of the first type may refer to resource circulation index information associated with the digital resource of the first type within a period matching the trading period of the reference trading data, i.e. may indicate the value of the digital resource of the first type contemporaneous with the trading period of the reference trading data.
For example, the resource circulation index information includes at least one of: conversion rate between the digital resources of the first type and the digital resources of the other general type, gain rate of the digital resources of the first type. The higher the conversion rate between the digital resources of the first type and the digital resources of the other general type, the greater the number of digital resources of the first type representing the same number of conversion into digital resources of the other general type, i.e. the higher the value of the digital resources of the first type. For example, twice as many digital resources of the other general type are available as would be the case if the target number of digital resources of the first type were converted to digital resources of the other general type. When the conversion rate between the digital resources of the first type and the digital resources of the other general types increases, three times as many digital resources of the other general types can be obtained when the target number of digital resources of the first type are converted into digital resources of the other general types. The lower the conversion rate between the digital resources of the first type and the digital resources of the other general type, the fewer the number of digital resources of the same number of the first type converted into the digital resources of the other general type, i.e. the lower the value of the digital resources of the first type. The gain ratio of the first type of digital resource may also be used to reflect the value change of the first type of digital resource. The resource circulation index information may also include other value change indicators reflecting the first type of digital resource, and so on.
In the embodiment of the present application, since the resource circulation index information associated with the first type of digital resource has an influence on the first type of digital resource, when the transaction price of the first type of digital resource of the reference transaction data is acquired, the transaction price of the first type of digital resource can be judged by combining with the resource circulation index information associated with the first type of digital resource, and then when the predicted conversion amount of the target digital resource for the first type of digital resource in the predicted target transaction data is predicted, the prediction accuracy can be improved. By acquiring the resource circulation index information associated with the first type of digital resources, namely acquiring the resource circulation index information of the same period of the reference transaction data, the overall value condition of the second type of digital resources in the same period of the reference transaction data can be macroscopically reflected, so that the subsequent price prediction of the target digital resources in the target transaction data can be more accurate.
S103, based on the resource circulation index information and the reference transaction data, predicting the conversion quantity of the target digital resource for the first type of digital resource, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource.
In the embodiment of the application, the conversion quantity of the target digital resource prediction can be used for reflecting the value of the target digital resource prediction. For example, a higher predicted conversion amount indicates a higher value of the target digital resource prediction, and a lower predicted conversion amount indicates a lower value of the target digital resource prediction. The conversion quantity of the target digital resource aiming at the first type of digital resource is predicted by acquiring the resource circulation index information related to the first type of digital resource and the reference transaction data related to the second type of digital resource and combining the resource circulation index information and the reference transaction data, so that the predicted conversion quantity of the target digital resource aiming at the first type of digital resource can be generated.
The predicted conversion amount of the target digital resource for the first type of digital resource may refer to the amount of converting the target digital resource into the first type of digital resource, that is, the predicted transaction price of the target digital resource for the first type of digital resource. When the prediction processing is performed, the actual transaction price of the second type of digital resources in the reference transaction data associated with the target digital resources is combined, and the macro transaction quotation data associated with the first type of digital resources is combined to perform the prediction processing, so that the value prediction accuracy can be improved, the conversion amount of the target digital resources into the first type of digital resources can be predicted, and the prediction accuracy can be improved.
In one embodiment, a predictive model may be invoked to predict the conversion of the target digital resource for the first type of digital resource based on the resource circulation indicator information and the reference transaction data, generating a predicted conversion of the target digital resource for the first type of digital resource. Specifically, a prediction model can be obtained, and the prediction model is called to perform fusion embedding processing on the resource circulation index information and the reference transaction data, so as to generate fusion prediction characteristics; and carrying out prediction processing on the conversion quantity of the target digital resource aiming at the first type of digital resource based on the fusion prediction characteristic, and generating a prediction conversion quantity.
The fusion prediction features not only comprise features corresponding to the resource circulation index information, but also comprise features of reference transaction data, and the prediction model can pay attention to more aspects of information when carrying out transaction price prediction processing by carrying out fusion prediction on two different features, so that the prediction accuracy of the prediction model for the transaction price is improved.
In one embodiment, the fusion embedding process may be performed in the following manner to generate the fusion prediction feature. Specifically, a prediction model is called to conduct embedding processing on the resource circulation index information, and embedding characteristics of the resource circulation index information are generated; invoking a prediction model to embed the reference transaction data, and generating embedded features of the reference transaction data; and carrying out fusion processing on the embedded features of the resource circulation index information and the embedded features of the reference transaction data to generate fusion prediction features.
The embedding of the resource circulation index information may be to encode the resource circulation index information into a feature vector, and the embedding feature of the resource circulation index information may be to encode the feature vector. The embedding of the reference transaction data may refer to encoding the reference transaction data into feature vectors, and the embedding of the reference transaction data may refer to encoding the resulting feature vectors. By encoding the two data as feature vectors, feature fusion is facilitated. Methods such as fusing the embedded features of the resource circulation index information with the embedded features of the reference transaction data may include, but are not limited to, a stitching process and a summing process. The splicing process may refer to splicing the embedded features of the resource circulation index information and the embedded features of the reference transaction data into a whole. The adding process may refer to adding the embedded feature of the resource circulation index information and the embedded feature of the reference transaction data according to bits to obtain the fusion prediction feature.
In an alternative implementation, the embedded features of the reference transaction data may include, but are not limited to, price trends of the second type of digital resource in the reference transaction data, volatility, transaction emotions of all transaction objects in the transaction platform for the transaction platform, which may reflect a comprehensive presentation of views of all transaction objects in the transaction market for the transaction platform, which may affect an overall transaction market direction of the transaction platform. After the reference transaction data is acquired, the prediction model can be called to analyze the multiple transaction reference data to determine the price trend and the fluctuation rate of the second type of digital resources in the reference transaction data, the transaction emotion and other data of all transaction objects in the transaction platform aiming at the transaction platform, so that the information is extracted to serve as the embedded feature of the reference transaction data, and the subsequent prediction model is convenient to learn.
The price trend, the fluctuation rate of the second type of digital resources in the reference transaction data and the transaction emotion and other data of all transaction objects in the transaction platform aiming at the transaction platform can reflect the transaction market trend of the reference transaction and the synchronous transaction market conditions, so that the prediction model is trained by extracting the data, and the prediction model can be used for predicting any transaction data which are not subjected to transaction in the follow-up process, and the prediction accuracy is improved by combining the factors of the aspects.
Optionally, when the embedding feature of the resource circulation index information and the embedding feature of the reference transaction data are fused to generate the fusion prediction feature, the fusion processing can be performed by combining weights corresponding to the two features. For example, a first weight corresponding to the resource circulation index information may be obtained, a second weight corresponding to the reference transaction data may be obtained, the first weight is used to perform weighting processing on the embedded feature of the resource circulation index information to obtain first weighted data, the second weight is used to perform weighting processing on the embedded feature of the reference transaction data to obtain second weighted data, and the first weighted data and the second weighted data are added to obtain the fusion prediction feature. For example, in the scenario of some types of target digital resources, the first weight corresponding to the resource circulation index information is greater than a first threshold, the second weight corresponding to the reference transaction data is less than a second threshold, and the first threshold (e.g., 90%) is greater than the second threshold (e.g., 10%). In other types of target digital resource scenarios, the first weight corresponding to the resource circulation index information is greater than the third threshold and smaller than the first threshold, and the second weight corresponding to the reference transaction data is greater than the second threshold and smaller than the fourth threshold. The third threshold (e.g., 80%) is less than the first threshold and greater than the second threshold and the fourth threshold (e.g., 20%), the fourth threshold being less than the second threshold.
For example, in a case where some types of macroscopic data have a large influence on the digital collection, the second weight corresponding to the resource circulation index information is greater than the second threshold by 10% and less than the fourth threshold by 20%, for example, in a case where the digital collection is an artwork, a collectable, or the like. Or in the case that some types of macroscopic data have less influence on the digital collection, the second weight corresponding to the reference transaction data is smaller than the second threshold value by 10%, for example, in the case that the digital collection is a game or sports, etc. By acquiring the weights corresponding to the resource circulation index information and the weights corresponding to the reference transaction data in different scenes, the two features can be fused based on the weights, the acquisition accuracy of the fused prediction features can be improved, and the prediction accuracy can be improved.
Alternatively, the prediction model may refer to, for example, a deep neural network model (Deep Neural Networks, DNN), a recurrent neural network model (Recurrent Neural Network, RNN), a residual neural network model (rest), a convolutional neural network model (Convolutional Neural Network, CNN), a long and short term memory model (Long Short Term Memory, LSTM), a portal recurrent unit model (Gated recurrent units, GRU), and the like.
In the embodiment of the present application, before the prediction model is invoked to predict the conversion amount of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate the predicted conversion amount of the target digital resource for the first type of digital resource, the prediction model and the training sample to be trained may be obtained in advance, and the training sample is used to train the prediction model to be trained, so that the prediction model obtained after training has the capability of predicting the conversion amount of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate the predicted conversion amount of the target digital resource for the first type of digital resource, thereby realizing price prediction.
In an alternative implementation manner, source data can be acquired from a transaction platform or a data analysis platform to acquire different collection sets, factors such as historical transaction prices of target digital resources of the different collection sets and prices of digital resources of a contemporaneous first type are taken as training data sets, and therefore training samples in the training data sets are used for training a prediction model. Because a large number of training samples are used for training the prediction model, the prediction model can learn more features, and the prediction accuracy of the prediction model can be improved.
In one implementation, a method for training a predictive model to be trained to predict a predicted conversion of a target digital resource for a first type of digital resource may be as follows: obtaining a prediction model to be trained and sample transaction data; the sample transaction data has a sample tag for indicating an actual conversion amount of the sample transaction data for the first type of digital resource; acquiring sample resource circulation index information associated with a first type of digital resource, and acquiring sample reference transaction data associated with a second type of sample digital resource; the sample reference transaction data pertains to transaction data that converts a sample digital resource of a second type to a digital resource of a first type; invoking a prediction model to be trained, and generating a sample prediction conversion quantity of the sample digital resource aiming at the first type digital resource based on sample resource circulation index information and sample reference transaction data; and correcting model parameters of the prediction model to be trained based on the difference between the sample prediction conversion quantity and the conversion quantity indicated by the sample label to obtain the prediction model.
The sample resource circulation index information can be used for reflecting macroscopic transaction quotation data related to the first type of digital resources in the sample transaction data, namely, can be used for macroscopically reflecting the value condition of the first type of digital resources in the sample transaction data. The sample reference transaction data may refer to historical transaction data generated within a period of time adjacent to the sample transaction initiation time of the sample transaction data that converts the digital resources of the second type into the digital resources of the first type, i.e., the sample reference transaction data may refer to historical transaction data of the same type as the target digital resources in the sample transaction data. The sample resource circulation index information and the sample reference transaction data may be contemporaneous data. Because the sample resource circulation index information of each period is continuously changed, the model prediction accuracy can be improved by acquiring the sample resource circulation index information of the same period of sample reference transaction data as the model training index.
In this embodiment of the present application, the sample label may refer to a sample true value, and the sample prediction conversion amount may refer to a model prediction value, and the purpose of training the prediction model is to make the model prediction value and the sample true value as consistent as possible. And when the model predicted value is inconsistent with the sample true value, continuously correcting the model parameters in the predicted model to be trained, and reducing the loss function in the predicted model to be trained, so that the model predicted value is consistent with the sample true value as much as possible. When the model predicted value is consistent with the sample true value, the model parameters of the predicted model to be trained can be stopped from being corrected to obtain a predicted model, and the predicted conversion quantity of the target digital resource for the first type of digital resource can be predicted by calling the predicted model obtained by training.
Optionally, the process of training the prediction model to be trained is a process of continuously adjusting model parameters in the prediction model to be trained, and by continuously adjusting model parameters in the prediction model to be trained, a loss function in the prediction model to be trained can be reduced, so that the prediction model after training meets a convergence condition, and when the prediction model to be trained meets the convergence condition, the correction of model parameters of the prediction model to be trained can be stopped to obtain the prediction model. The convergence condition may include, but is not limited to, a loss function in the predictive model being less than a loss threshold, a number of iterative training of the predictive model reaching a target number, and so forth.
Alternatively, the loss function in the prediction model may include, but is not limited to, a mean square error function (MSE), a classification function (Softmax), a support vector machine loss function (finger), a Logistic regression function (Logistic), and the like, and the selection of the loss function in the embodiment of the present application is not limited.
According to the method and the device for predicting the conversion quantity of the digital resources, the prediction model to be trained can be trained by acquiring macroscopic transaction quotation data associated with the digital resources of the first type in the sample transaction data and sample reference transaction data associated with the digital resources of the second type in the sample reference transaction data and combining the actual transaction price of the digital resources of the second type in the sample reference transaction data and the macroscopic transaction quotation data associated with the digital resources of the first type, so that the prediction model to be trained can learn the characteristics from different dimensions, and the prediction result of the prediction model for the prediction conversion quantity is improved.
In one embodiment, when sample transaction data is obtained, the source data may be preprocessed in advance to obtain the sample transaction data, so that model training is performed using the sample transaction data obtained after preprocessing. For example, source data may be obtained from a transaction platform or a data analysis platform, and the source data may be preprocessed to obtain training samples, which may include sample transaction data, sample resource flow index information associated with a first type of digital resource, and sample reference transaction data associated with a second type of sample digital resource. Specifically, the data preprocessing performed on the acquired source data may include operations such as data cleaning and preprocessing, so as to obtain input data of the prediction model. The data cleaning and preprocessing mainly comprises the following steps: removing abnormal values, processing missing values, normalizing data, resampling time sequence and the like. Removing outliers may refer to removing outlier values in the source data. The missing value processing may refer to filling 0 or filling a preset character to missing values in the source data. The data normalization may be, for example, normalization of a numerical value in the source data to a range of 0 to 1, and may also be classification of text type data in the source data, for example, the source data includes the sex of both parties of the transaction, the sex female may be normalized to 0, the sex male may be normalized to 1, and so on. Time series resampling may refer to repartitioning the source data by time length, sampling from the partitioned data to determine training samples. For example, the length of time for each sample may not be equal.
In the embodiment of the application, the training sample is obtained by carrying out data cleaning and preprocessing on the source data acquired from the transaction platform, and the processed data can be used as the input data of the prediction model, so that the follow-up training of the prediction model is facilitated.
Optionally, for the collected source data, whether the data types of the source data belong to risk types or not may be detected in advance, and if the data types of the source data belong to risk types, in order to improve data security, desensitization processing may be further performed on the source data, so that model training is performed by using the data after the desensitization processing, and data security is improved. The risk type data may include, but is not limited to, identity information of both parties to the transaction and fund information such as transaction price, number of transactions, total number of transactions, etc. The method of desensitizing may include, but is not limited to, converting the source data, for example, converting the source data into a semantically equivalent commitment file, which may refer to encrypted source data. For example, in the authentication scenario, identity information of the transaction object needs to be provided for authentication, but the identity information of the transaction object belongs to risk information, so that the identity information of the transaction object can be converted into an identity promise file and then submitted to a blockchain network for model training, thereby ensuring the safety of source data.
In another implementation, the transaction may be performed in a secure execution environment, for example, risk type data may be pre-written into a foresight machine contract, and the foresight machine contract is deployed in the secure execution environment, and when the foresight machine contract is invoked to predict the transaction price of the target transaction data, the transaction price of the target transaction data is predicted in the secure execution environment, so that transaction security may be ensured. For data outside of the secure execution environment, an index of risk type data or other attestation information that may be used to represent risk type data.
Wherein, the propulsor contract refers to an intelligent contract for providing propulsor service, and is deployed in the blockchain node. When the blockchain node detects that the target digital resource needs to be transacted on the chain, the predicting model under the chain can be acquired by calling the predictor contract to predict the transaction price of the target digital resource needing to be transacted, so that the target transaction data is executed based on the predicted transaction price. The predictor (Oracle) is a mechanism for writing data under the blockchain into the blockchain. Because the blockchain is a closed system environment, the blockchain generally acquires data in the blockchain at present, but cannot acquire data under the chain, namely cannot receive data outside the blockchain. Thus items running on different blockchains can import the under-chain data into the blockchain network with the aid of the propulsor, which functions to provide external data or computation for the intelligent contract. For example, the predictive model may be trained by the predictor acquiring the in-chain reference trading data and invoking the predictive model to predict the trading prices of the target digital resources.
In an alternative implementation manner, other index information which can be used for measuring the transaction condition can be obtained, and the model is trained by combining with other index information, so that the trained prediction model can pay attention to and learn more aspects, and the model prediction accuracy is improved.
S104, executing target transaction data in the blockchain network based on the predicted conversion amount.
In the embodiment of the application, the predicted conversion amount of the target digital resource for the first type of digital resource is obtained through prediction, which is equivalent to determining the transaction price in the target transaction data, so that the target transaction data can be executed in the blockchain network based on the predicted conversion amount. The prediction model is used for predicting the transaction price of the target digital resource, so that the prediction accuracy can be improved, the target digital resource can be transacted by using the predicted conversion quantity obtained by prediction, and the transaction loss can be reduced by adopting reasonable transaction price.
In the embodiment of the application, the blockchain network node can obtain the sample transaction data, the sample resource circulation index information associated with the first type of digital resource and the sample reference transaction data associated with the second type of sample digital resource through obtaining the sample transaction data from the blockchain network (on-chain), so that a prediction model is trained and obtained under the chain. And subsequently, when target transaction data initiated by the transaction client is detected, a prediction model under the chain can be called to predict the price of the target digital resource in the target transaction data, and the predicted conversion quantity of the target digital resource for the first type of digital resource is generated, so that the target transaction data can be executed on the chain based on the predicted conversion quantity.
In one embodiment, the operations of the transaction client may be further acquired prior to executing the target transaction data in the blockchain network, and a determination may be made as to whether to execute the target transaction data in conjunction with the operations of the transaction client. For example, when the transaction initiating object corresponding to the transaction client is unsatisfactory for the predicted conversion amount, for example, when the transaction price of the target digital resource is considered to be too low, the operation corresponding to the transaction client can be triggered, the execution of the target transaction data is stopped, and the loss of the transaction initiator is reduced.
For example, the manner of processing for the target transaction data may be determined in conjunction with the operation of the transaction client by: generating transaction execution inquiry information based on the predicted conversion quantity, and transmitting the transaction execution inquiry information to a transaction client; if the confirmation information of the transaction execution inquiry information sent by the transaction client is received, the predicted conversion quantity is packaged into target transaction data, and first packaged transaction data are generated; broadcasting the first packaged transaction data to a blockchain network for consensus processing; if the first encapsulated transaction data is successful in the blockchain network, the target digital resource is converted to a first type of data resource in the blockchain network. Wherein the resource amount of the first type of digital resource of the target digital resource conversion is a predicted conversion amount.
The transaction execution inquiry information is used for prompting a transaction initiating object of the transaction client to target the transaction price of the digital resource. By sending the transaction execution query information to the transaction client, the transaction initiator may view the query information, thereby triggering a corresponding operation. The validation information is used to validate the execution target transaction data, the predicted conversion amount may be uploaded into the target transaction data. Since the transaction client does not know the pricing of the target digital resource when initiating the target transaction data, the target transaction data does not contain the transaction price, and packaging the predicted conversion amount into the target transaction data is equivalent to packaging the transaction price into the target transaction data, so that the target transaction data can be executed according to the predicted conversion amount in the blockchain network. The first packaged transaction data is data obtained by packaging the predicted conversion amount into the target transaction data. Performing consensus processing by broadcasting the first encapsulated transaction data to a blockchain network; if the first encapsulated transaction data is successfully identified in the blockchain network, which means that the transaction data is truly effective, the target digital resource is converted into a first type of data resource in the blockchain network, so that successful transaction aiming at the target digital resource is realized. By the method, the first packaged transaction data are commonly known and then are uplink, so that the authenticity and the safety of the transaction can be ensured, and the first packaged transaction data can be traced later.
Alternatively, if cancellation information of the execution inquiry information for the transaction sent by the transaction client is received, the execution target transaction data may be cancelled. Because the transaction client can determine whether to execute the target transaction data according to the predicted conversion amount, for example, the transaction initiator considers that the predicted conversion amount does not meet the expectation, the target transaction data can be canceled, and the transaction flexibility is improved.
In one embodiment, after generating the predicted conversion amount, the blockchain node may further generate a selection interval corresponding to the predicted conversion amount, so that a transaction price of the target transaction data may be determined in combination with a selection operation of the transaction client for a certain value in the selection interval. Specifically, a selection interval of the conversion amount of the target digital resource for the second type of digital resource may be generated based on the predicted conversion amount, and the selection interval is transmitted to the transaction client; receiving a target conversion amount sent by a transaction client; the target conversion amount is a conversion amount selected by the transaction client from within the selection interval; encapsulating the target conversion amount into target transaction data, generating second encapsulated transaction data, and broadcasting the second encapsulated transaction data to a block chain network for consensus processing; if the target transaction data is successfully shared in the blockchain network, the target digital resource is converted into a first type of data resource in the blockchain network. Wherein the resource amount of the digital resource of the first type of the target digital resource conversion is the target conversion amount.
In this embodiment of the present invention, the selection interval includes at least one conversion amount, and since the prediction conversion amount is obtained by prediction of the prediction model, the conversion amount in the selection interval may refer to a conversion amount within a reasonable range by the selection interval of the conversion amount of the target digital resource for the second type of digital resource generated by the prediction conversion amount, for example, the selection interval may be generated according to a trade price or a range to which a numerical value between the trade price and the prediction conversion amount in the historical trade data belongs, for example, the minimum conversion amount in the historical trade data is determined as the minimum value of the selection interval, and the maximum conversion amount or the prediction conversion amount in the historical trade data is determined as the maximum value of the selection interval. By transmitting the selection interval to the transaction client, the transaction initiating object can select an appropriate target conversion amount from the selection interval as the transaction price of the target transaction data. When the target digital resource is priced, the operation of the transaction initiator can be combined for pricing, so that the pricing mode is more reasonable. Further, the target transaction data can be executed in combination with the target conversion quantity selected by the transaction client, the target conversion quantity is packaged into the target transaction data, and the transaction data can be traced later by linking the transaction data.
In an alternative implementation, the transaction risk of the target digital resource may also be predicted, so as to generate a predicted risk level of the target digital resource. For example, when predicting the predicted risk level of the target digital resource, the prediction model may be called to predict the transaction risk of the target digital resource based on the resource circulation index information and the reference transaction data, so as to generate the predicted risk level of the target digital resource.
The predicted risk level is used for reflecting risks possibly existing in the transaction of the target digital resource based on the predicted conversion quantity, for example, the risk that the target digital resource is transacted at the current time can be reflected, and a transaction initiator loses a large amount of property. The predicted risk level may include, for example, a first risk level, a second risk level, and a third risk level. The first risk level is greater than the second risk level, which is greater than the third risk level. For example, a first risk level may refer to a high risk level, a second risk level may refer to a medium risk level, and a third risk level may refer to a low risk level. Alternatively, more risk level gradients or fewer risk level gradients may be provided, which are not limited in this embodiment of the present application. By predicting which risk level the transaction risk of the target digital resource belongs to, for example, when the transaction risk of the target digital resource belongs to the first risk level, the transaction client can be prompted to transact carefully, so that property loss is reduced. Or when the transaction risk of the target digital resource belongs to the third risk level, the transaction client can be not prompted to directly conduct the transaction, so that the transaction efficiency is improved.
In the embodiment of the application, the risk prediction efficiency can be improved by calling the prediction model to predict the risk level. And because the risk prediction is carried out on the two aspects of the resource circulation index information and the reference transaction data when the risk level is predicted, the accuracy of the risk prediction can be improved. By predicting the transaction risk of the target digital resource, the risk condition of the current target transaction data of the transaction client can be prompted, the transaction safety is improved, and the transaction property loss is reduced.
For example, for a transaction initiator, by predicting the transaction risk of the target digital resource, the risk condition of the current target transaction data of the transaction client can be prompted, the transaction safety is improved, and the transaction property loss is reduced. For the transaction receiver, the risk of the transaction receiver buying the target digital resource currently, such as the property quantity lost when buying the target digital resource currently, whether the target digital resource is a counterfeit, etc., can also be prompted, so that the transaction receiver is prompted to conduct careful transaction, and the property loss of the transaction receiver is reduced.
Alternatively, the predicted risk level of the target digital resource may be predicted by: acquiring a prediction model, and calling the prediction model to perform fusion embedding processing on the resource circulation index information and the reference transaction data to generate fusion prediction characteristics; and carrying out prediction processing on the transaction risk of the target digital resource based on the fusion prediction characteristics, and generating a predicted risk level of the target digital resource.
The fusion prediction features not only comprise the features corresponding to the resource circulation index information, but also comprise the features of the reference transaction data, and the prediction model can pay attention to more aspects of information when carrying out risk prediction by carrying out fusion prediction on two different features, so that the accuracy of the model for risk prediction is improved.
In one embodiment, a predictive model may be invoked to predict a transaction price and a transaction risk for a target digital resource, generating a predicted conversion amount for the target digital resource for a first type of digital resource and a predicted risk level for the target digital resource. Specifically, a prediction model can be obtained, and the prediction model is called to perform fusion embedding processing on the resource circulation index information and the reference transaction data, so as to generate fusion prediction characteristics; predicting the conversion quantity of the target digital resource aiming at the first type of digital resource based on the fusion prediction characteristic to generate a predicted conversion quantity; and predicting transaction risk of the target digital resource based on the fusion prediction feature, and generating a predicted risk level of the target digital resource.
In the embodiment of the application, the risk level and the transaction price refer to two-dimensional data, and when the prediction model predicts the risk level and the transaction price, the two-dimensional data can be predicted based on the same characteristics. For example, two classifiers may be provided in the predictive model, such as a first classifier for predicting transaction prices and a second classifier for predicting risk levels. That is, when predicting the target digital resource, by inputting the resource circulation index information associated with the first type of digital resource and the reference transaction data associated with the second type of digital resource into the prediction model, the prediction model may respectively classify and predict the resource circulation index information and the reference transaction data using different classifiers, thereby respectively outputting the predicted conversion amount of the target digital resource for the first type of digital resource and the predicted risk level of the target digital resource based on the prediction model.
In one embodiment, since the predictive model can predict the predicted transition amount and the predicted risk level, the transaction client can be prompted in combination to process the target transaction data based on the operation of the transaction client. For example, transaction execution inquiry information may be generated based on the predicted conversion amount and the predicted risk level, and transmitted to the transaction client; if the confirmation information of the transaction execution inquiry information sent by the transaction client is received, the predicted conversion quantity is packaged into target transaction data, and first packaged transaction data are generated; broadcasting the first packaged transaction data to a blockchain network for consensus processing; if the first encapsulated transaction data is successful in the blockchain network, converting the target digital resource into a first type of data resource in the blockchain network; wherein the resource amount of the first type of digital resource of the target digital resource conversion is a predicted conversion amount.
In this embodiment of the present application, the transaction execution query information may be used to prompt the transaction client for the current transaction risk level and the predicted conversion amount, and by sending the transaction execution query information to the transaction client, the transaction initiator may view the query information, thereby triggering the corresponding operation. Through consensus processing and uplink of transaction data, the authenticity and the safety of the transaction can be ensured, and the transaction data can be traced back conveniently.
Alternatively, if cancellation information of the execution inquiry information for the transaction sent by the transaction client is received, the execution target transaction data may be cancelled. Because the transaction client can determine whether to execute the target transaction data according to the predicted conversion amount, for example, the transaction initiator considers that the predicted conversion amount does not conform to the expectation or the transaction risk is too high, the target transaction data can be canceled, and the transaction flexibility is improved.
In one embodiment, after generating the predicted conversion amount and the predicted risk level, the blockchain node may further generate a selection interval corresponding to the predicted conversion amount, so that a transaction price of the target transaction data may be determined in combination with a selection operation of the transaction client for a certain value in the selection interval.
Specifically, a selection interval of the conversion amount of the target digital resource for the second type of digital resource can be generated based on the predicted conversion amount, and the selection interval and the predicted risk level are transmitted to the transaction client; receiving a target conversion amount sent by a transaction client; the target conversion amount is a conversion amount selected from within the selection interval by the transaction client after performing a confirmation operation on the predicted risk level. Generating second packaged transaction data by packaging the target conversion amount into target transaction data, and broadcasting the second packaged transaction data to a blockchain network for consensus processing; if the target transaction data is successfully shared in the blockchain network, the target digital resource is converted into a first type of data resource in the blockchain network. Wherein the resource amount of the digital resource of the first type of the target digital resource conversion is the target conversion amount.
In the embodiment of the application, by sending the selection interval and the predicted risk level to the transaction client, the transaction initiating object determines whether to execute the target transaction data under the predicted risk level, for example, the transaction initiating party may select an appropriate target conversion amount from the selection interval as the transaction price of the target transaction data. When the transaction initiator selects the target conversion amount from the selection interval, it indicates that the target transaction data needs to be executed even at the predicted risk level. Since the target conversion amount is selected by the transaction initiator, the pricing mode is more reasonable when the target digital resource is priced. Further, the target transaction data can be executed in combination with the target conversion quantity selected by the transaction client, the target conversion quantity is packaged into the target transaction data, and the transaction data can be traced later by linking the transaction data.
In the embodiment of the application, the price of the target digital resource is quantified by using the trained prediction model, so that when the target digital resource is transacted on the chain, a foreseeing machine contract can be called to acquire the transaction price (predicted conversion quantity) of the target digital resource to be transacted currently, and the transaction of the corresponding target digital resource is executed on the chain based on the transaction price predicted by the prediction model. Because the machine learning algorithm is used for training the prediction model, the trained prediction model can be used for predicting the transaction price of the target digital resource, and the transaction price of the target digital resource on the pricing chain is quantized by adopting the prediction model, so that the accuracy of the transaction price prediction of the target digital resource can be improved. Furthermore, as the data for training the prediction model is not only the transacted reference transaction data, but also macroscopic transaction quotation data which can influence transaction quotation is introduced, the accuracy of the prediction model obtained by training can be improved, and the accuracy of the prediction model on transaction price prediction is improved. In addition, the prediction model predicts the price of the target digital resource and can evaluate the risk level of the target digital resource, so as to remind a transacting party to carefully transact, and reduce the possibility of asset loss of the transacting party.
In the embodiment of the application, target transaction data are acquired; acquiring resource circulation index information associated with a first type of digital resource and reference transaction data associated with a second type of digital resource, and performing prediction processing on the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate a predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed in the blockchain network based on the predicted conversion amount. Since the reference transaction data refers to transaction data which belongs to the same type as the target digital resource in the target transaction data and is already transacted, the reference transaction data can be used as a reference of the conversion quantity of the target digital resource for the first type of digital resource in the target transaction data, and the resource circulation index information associated with the first type of digital resource can reflect the resource circulation condition of the first type of digital resource. Therefore, the conversion amount of the target digital resource converted into the first type of digital resource is predicted by combining the reference transaction data and the resource circulation index information associated with the first type of digital resource, and the conversion amount of the target digital resource can be predicted from different dimensions, so that the accuracy of the conversion amount prediction of the target digital resource is improved. Further, the predicted risk level of the target digital resource can be predicted, so that the transaction risk of the target digital resource of the transaction client can be prompted, and the transaction safety is improved.
Further, referring to fig. 4, fig. 4 is a flow chart of another transaction processing method of a blockchain network according to an embodiment of the present application. The transaction processing method of the blockchain network can be applied to a transaction processing system, and the blockchain node and the transaction client in the transaction processing system jointly execute the function of realizing transaction processing; as shown in fig. 4, the transaction processing method of the blockchain network includes, but is not limited to, the following steps:
s201, obtaining a prediction model to be trained and sample transaction data by the block chain link points.
In the embodiment of the present application, before the price of the target digital resource is predicted by using the prediction model, the prediction model may be trained first, and then when transaction data initiated by any transaction client is acquired, the conversion amount of the target digital resource in the transaction data for the first type of digital resource may be predicted, so as to generate the predicted conversion amount of the target digital resource for the first type of digital resource.
In an alternative implementation, since the transaction risk of the target digital resource also needs to be predicted, a prediction model to be trained can also be trained, so that the trained prediction model can not only predict the conversion amount for the first type of digital resource, but also predict the transaction risk level of the target digital resource. Because the prediction model needs to predict two tasks, namely, a task of predicting the price of the target digital resource and a task of predicting the transaction risk of the target digital resource, different sample tags can be used for training the prediction model respectively, so that the prediction model obtained by training can output the price of the target digital resource and the predicted transaction risk of the target digital resource.
Specifically, a predictive model to be trained and sample transaction data may be obtained. The sample transaction data has a first sample tag for indicating an actual conversion amount of the sample transaction data for the first type of digital resource and a second sample tag for indicating an actual transaction risk level of the sample transaction data. The first sample tag is a sample true value of the pointer to the conversion amount and the second sample tag is a sample true value of the pointer to the transaction risk level. By pre-determining the real conversion amount and the real transaction risk level of the sample transaction data, the model parameters of the prediction model to be trained can be adjusted based on the sample prediction conversion amount, the sample prediction risk level, the first sample tag and the second sample tag predicted by the model, so as to obtain the prediction model.
Optionally, when the second sample tag is obtained, a fluctuation interval may be preset, for each sample transaction data in the plurality of sample transaction data, and if the conversion amount for the first type of digital resource in the sample transaction data does not belong to the fluctuation interval, the second sample tag of the sample transaction data is determined to be the first risk level. If the conversion amount of the sample transaction data for the first type of digital resource belongs to the fluctuation interval, the second sample label can be determined to be the second risk level or the third risk level according to the specific conversion amount value of the sample transaction data. For example, if the conversion amount of the digital resource of the first type in the sample transaction data belongs to a target fluctuation interval in the fluctuation intervals, determining that the second sample label is a third risk level. And if the conversion quantity of the sample transaction data belongs to the fluctuation interval but does not belong to the target fluctuation interval in the fluctuation interval, determining the second sample label as a third risk level. The target fluctuation interval is used for reflecting that the fluctuation rate is in a stable interval, and the conversion quantity of the first type of digital resource in the sample transaction data belonging to the interval is relatively stable.
Further alternatively, the risk level may also be determined in connection with whether the second type of digital resource in the sample transaction data is a counterfeit. If the second type of digital resource in the sample reference data is a counterfeit, the second sample label of the sample transaction data can be determined to be the first risk level. If the second type of digital resource in the sample reference data is not counterfeit, a second sample tag of the sample transaction data may be determined to be a specific risk level in combination with the conversion amount of the first type of digital resource in the sample transaction data. For example, if the second type of digital resource in the sample reference data is not a counterfeit and the conversion amount of the sample transaction data for the first type of digital resource does not belong to the fluctuation interval, determining that the second sample label of the sample transaction data is a second risk level. And if the digital resource of the second type in the sample reference data is not a counterfeit, and the conversion quantity of the digital resource of the first type in the sample transaction data belongs to a fluctuation interval, determining that the second sample label of the sample transaction data is a third risk level.
In this embodiment of the present application, the second sample tag of the sample transaction data may be further divided by combining more factors, which is not limited in this embodiment of the present application. By automatically dividing the transaction risk level of the sample transaction data according to the conversion quantity of the sample transaction data for the first type of digital resources and whether the second type of digital resources in the sample transaction data are counterfeit, the risk level dividing efficiency is improved.
S202, the blockchain node acquires sample resource circulation index information associated with the first type of digital resources and acquires sample reference transaction data associated with the second type of sample digital resources.
Wherein the sample reference transaction data pertains to transaction data that converts a sample digital resource of a second type to a digital resource of a first type. The sample digital resource may refer to a target digital resource, i.e., the sample digital resource may be an index collection. Alternatively, the sample reference transaction data may also pertain to transaction data that converts a sample digital resource of the second type into another digital resource of a generic type. The sample reference transaction data is converted into the digital resources of other general types, and then the digital resources of other general types can be converted into the digital resources of the first type according to the conversion rate between the digital resources of the first type and the digital resources of other general types, so that the conversion of the sample digital resources of the second type into the digital resources of the first type can be realized. Therefore, the number of sample reference transaction data can be increased, namely the number of training samples is increased, and the model training accuracy can be improved.
S203, calling a prediction model to be trained by the block chain link points, and generating a sample prediction conversion quantity of the sample digital resource aiming at the first type digital resource and a sample prediction risk level of the sample digital resource based on sample resource circulation index information and sample reference transaction data.
Optionally, a prediction model can be called to perform fusion embedding processing on the sample resource circulation index information and the sample reference transaction data to generate sample fusion prediction characteristics; predicting conversion quantity of the target digital resource aiming at the first type of digital resource based on the sample fusion prediction characteristics to generate sample prediction conversion quantity; and predicting transaction risk of the target digital resource based on the sample fusion prediction features, and generating a sample prediction risk level of the target digital resource.
The sample fusion prediction features comprise features corresponding to the resource circulation index information and features of sample reference transaction data, and the prediction model can pay attention to more aspects of information when carrying out transaction price prediction processing by fusion prediction on two different features, so that the prediction accuracy of the model for sample transaction price and sample transaction grade is improved.
In one embodiment, the sample fusion prediction feature may be generated by performing a fusion embedding process in the following manner. Specifically, a prediction model is called to conduct embedding processing on the sample resource circulation index information, and embedding characteristics of the sample resource circulation index information are generated; invoking a prediction model to embed sample reference transaction data, and generating embedded features of the sample reference transaction data; and carrying out fusion processing on the embedded features of the sample resource circulation index information and the embedded features of the sample reference transaction data to generate sample fusion prediction features.
The embedding of the sample resource circulation index information may refer to encoding the sample resource circulation index information as a feature vector, and the embedding feature of the sample resource circulation index information may refer to the feature vector obtained by encoding. The embedding of the sample reference transaction data may refer to encoding the sample reference transaction data into a feature vector, and the embedding of the sample reference transaction data may refer to encoding the resulting feature vector. By encoding the two data as feature vectors, feature fusion is facilitated. Methods such as fusing embedded features of sample resource flow index information with embedded features of sample reference transaction data may include, but are not limited to, a stitching process and a summing process.
In an alternative implementation, the embedded features of the sample reference transaction data may include, but are not limited to, price trends, volatility, and transaction moods for all transaction objects in the transaction market for the transaction platform for the digital resources of the second type in the sample reference transaction data. After the sample reference transaction data is obtained, a prediction model to be trained can be called to analyze the plurality of sample transaction reference data, so that the price trend, the fluctuation rate, the transaction emotion and other data of all transaction objects in the transaction market aiming at the transaction platform of the second type of digital resources in the sample reference transaction data can be determined, and the information is extracted to serve as embedded features of the sample reference transaction data, so that the prediction model can learn conveniently.
Alternatively, when generating the predicted risk level of the target digital resource, the predicted risk level of the target digital resource may also be generated based on one of the resource circulation index information or the reference transaction data. For example, the embedded features of one of the resource circulation index information or the reference transaction data may be extracted, and the predicted risk level of the target digital resource may be generated based on the extracted embedded features.
S204, the block chain node corrects model parameters of the prediction model to be trained based on the sample prediction conversion amount, the sample prediction risk level, the first sample label and the second sample label to obtain the prediction model.
In this embodiment of the present application, the sample prediction conversion amount may refer to a conversion amount predicted based on a prediction model, the sample prediction risk level may refer to a risk level predicted based on the prediction model, the first sample tag may refer to an actual conversion amount in sample transaction data, and the second sample tag may refer to an actual risk level in sample transaction data. Therefore, the model parameters of the prediction model to be trained can be corrected based on the two differences by comparing the sample prediction conversion amount with the difference between the first sample tags and comparing the sample prediction risk level with the difference between the second sample tags to obtain the prediction model.
The model parameters of the prediction model to be trained are corrected to reduce the prediction deviation in the model, and the smaller the prediction deviation in the model is, the higher the model prediction accuracy is, so that the more accurate the result predicted based on the model is, namely the more the model prediction result is the same as the sample real result.
In one implementation, the model parameters of the predictive model to be trained may be modified to obtain the predictive model in the following manner. For example, a first prediction bias of the predictive model to be trained for the sample predicted conversion amount may be generated based on a difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag; generating a second prediction deviation of the prediction model to be trained for the sample prediction risk level based on the difference between the sample prediction risk level and the transaction risk level indicated by the second sample tag; adding the first prediction deviation and the second prediction deviation to generate a model integral prediction deviation of a prediction model to be trained; and correcting model parameters of the prediction model to be trained based on the integral prediction deviation to obtain the prediction model.
Wherein both the first prediction bias and the second prediction bias may refer to a loss function. In the calculation process of the loss function of the model, for any sample transaction data, the actual transaction price of the sample transaction data can be used as a first sample label, and the calculation of the loss function is performed on the predicted price obtained by predicting the sample transaction data based on the prediction model to be trained. The larger the difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag, the larger the first prediction deviation. The first prediction bias can be reduced by continuously adjusting the difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag. The greater the difference between the sample predicted risk level and the transaction risk level indicated by the second sample tag, the greater the second predicted deviation. The second prediction bias may be reduced by continuously adjusting the difference between the sample predicted risk level and the transaction risk level indicated by the second sample tag. The process of training the model is a process of continuously reducing the first prediction bias and the second prediction bias. When the prediction model to be trained is trained to a certain degree, the model can be verified, and whether the prediction model at the moment meets the convergence condition is verified. If the convergence condition is not satisfied, the iterative training of the prediction model to be trained can be continued. If the convergence condition is met, the correction of the model parameters in the prediction model to be trained can be stopped, and the prediction model is obtained.
Alternatively, the mode of generating the model overall prediction bias of the prediction model to be trained based on the first prediction bias and the second prediction bias may be other modes besides addition processing, so long as the model parameters of the prediction model to be trained are corrected by combining the first prediction bias and the second prediction bias.
In this embodiment of the present application, the process of training the prediction model may be a process performed under a chain, and sample transaction data may be obtained from a blockchain and sample reference transaction data may be trained under the chain to obtain the prediction model. When target transaction data is executed on the blockchain, an off-line prediction model can be called to predict the price of the target digital resource in the target transaction data, so that the target transaction data is executed on the chain based on a prediction result.
In the embodiment of the application, a new prediction model can be trained each time transaction data is acquired. Because the time for acquiring transaction data is different each time, the acquired resource circulation index information associated with the first type of digital resource and the acquired reference transaction data associated with the second type of digital resource are different, so that model parameters in a prediction model obtained through training are different, and further, when the prediction model trained in each period is used for predicting the price of the target digital resource in the same transaction data, the obtained prediction conversion quantity (prediction price) is also different. Therefore, when the same transaction data is predicted in different time periods, the prediction model corresponding to the time period required to conduct transaction prediction can be trained, so that the prediction model corresponding to the time period is used for prediction, and the prediction rationality and accuracy are improved.
S205, the transaction client executes the target transaction data and sends the target transaction data to the blockchain node.
S206, the blockchain node acquires the resource circulation index information associated with the first type of digital resources and acquires the reference transaction data associated with the second type of digital resources.
S207, the block link point predicts the conversion quantity of the target digital resource aiming at the first type digital resource based on the resource circulation index information and the reference transaction data, and generates the predicted conversion quantity of the target digital resource aiming at the first type digital resource and the predicted risk level of the target digital resource.
In an alternative implementation manner, when the trained prediction model is used to predict the price of the target digital resource in the target transaction data, a rolling prediction method, that is, an iterative prediction method, may be used to continuously update the prediction result of the model, so as to improve the accuracy of the prediction model.
S208, the block link point generates transaction execution inquiry information based on the predicted conversion amount and the predicted risk level, and transmits the transaction execution inquiry information to the transaction client.
S209, the transaction client transmits acknowledgement information of the transaction execution inquiry information to the block link point.
S210, the blockchain node executes target transaction data in the blockchain network.
In this embodiment, the specific implementation manner in steps S205 to S210 may refer to the implementation manner in steps S101 to S104, and will not be described herein.
In an alternative implementation manner, feedback data of the price of the target digital resource predicted by the transaction object aiming at the prediction model can be collected in the transaction platform, for example, information such as satisfaction of both transaction parties to the predicted price of the target digital resource, and the trained prediction model is finely tuned based on the feedback data so as to further optimize the prediction model.
In the embodiment of the application, because the transaction platform has larger risks for the target digital resource, such as larger transaction market change, malicious imitation of the target digital resource by an illegal user (namely, the target digital resource in the target transaction data is a counterfeit product), and the like, the risk prompt and risk warning can be carried out on both transaction parties by further predicting the transaction risk level of the target digital resource when the price of the target digital resource is predicted, so that the property loss caused by the transaction is reduced.
In the embodiment of the application, target transaction data are acquired; acquiring resource circulation index information associated with a first type of digital resource and reference transaction data associated with a second type of digital resource, and performing prediction processing on the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate a predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed in the blockchain network based on the predicted conversion amount. Since the reference transaction data refers to transaction data which belongs to the same type as the target digital resource in the target transaction data and is already transacted, the reference transaction data can be used as a reference of the conversion quantity of the target digital resource for the first type of digital resource in the target transaction data, and the resource circulation index information associated with the first type of digital resource can reflect the resource circulation condition of the first type of digital resource. Therefore, the conversion amount of the target digital resource converted into the first type of digital resource is predicted by combining the reference transaction data and the resource circulation index information associated with the first type of digital resource, and the conversion amount of the target digital resource can be predicted from different dimensions, so that the accuracy of the conversion amount prediction of the target digital resource is improved.
Having described the methods of embodiments of the present application, the apparatus of embodiments of the present application are described below.
Referring to fig. 5, fig. 5 is a schematic diagram of a component structure of a transaction processing device of a blockchain network according to an embodiment of the present application, where the transaction processing device of the blockchain network may be disposed on a computer device, and the computer device may refer to, for example, a blockchain node in the blockchain network; the transaction processing device of the blockchain network can be used for executing corresponding steps in the transaction processing method of the blockchain network. The transaction processing device 50 of the blockchain network includes:
a transaction acquisition unit 501 for acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
an index obtaining unit 502, configured to obtain resource circulation index information associated with the first type of digital resource, and obtain reference transaction data associated with the second type of digital resource; the reference transaction data pertains to transaction data that converts the second type of digital resource into the first type of digital resource;
A data prediction unit 503, configured to perform prediction processing on the conversion amount of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data, and generate a predicted conversion amount of the target digital resource for the first type of digital resource;
a transaction execution unit 504 for executing the target transaction data in the blockchain network based on the predicted conversion amount.
Optionally, the index obtaining unit 502 is specifically configured to:
acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
historical transaction data generated during the adjacent time period for converting the second type of digital resource to the first type of digital resource is obtained as the reference transaction data.
Optionally, the index obtaining unit 502 is specifically configured to:
acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
acquiring the resource circulation index information of the first type of digital resource in the adjacent time period;
wherein the resource circulation index information includes at least one of: conversion rate between the first type of digital resource and other general type of digital resource, gain rate of the first type of digital resource.
Optionally, the data prediction unit 503 is specifically configured to:
acquiring a prediction model, and calling the prediction model to perform fusion embedding processing on the resource circulation index information and the reference transaction data to generate fusion prediction characteristics;
predicting the conversion quantity of the target digital resource aiming at the digital resource of the first type based on the fusion prediction characteristic, and generating the prediction conversion quantity; the method comprises the steps of,
and predicting transaction risk of the target digital resource based on the fusion prediction feature, and generating a predicted risk level of the target digital resource.
Optionally, the target transaction data is initiated by a transaction client; the transaction execution unit 504 is specifically configured to:
generating transaction execution inquiry information based on the predicted conversion amount and the predicted risk level, and transmitting the transaction execution inquiry information to the transaction client;
if the confirmation information of the transaction execution inquiry information sent by the transaction client is received, packaging the predicted conversion quantity into the target transaction data to generate first packaged transaction data;
broadcasting the first packaged transaction data to the blockchain network for consensus processing;
if the first encapsulated transaction data is successfully identified in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
Wherein the amount of the first type of digital resource converted by the target digital resource is the predicted conversion amount.
Optionally, the target transaction data is initiated by a transaction client; the transaction execution unit 504 is specifically configured to:
generating a selection interval of the conversion quantity of the target digital resource for the second type of digital resource based on the predicted conversion quantity, and transmitting the selection interval and the predicted risk level to the transaction client;
receiving a target conversion amount sent by the transaction client; the target conversion amount is a conversion amount selected from the selection interval by the transaction client after performing a confirmation operation on the predicted risk level;
packaging the target conversion amount into the target transaction data, generating second packaged transaction data, and broadcasting the second packaged transaction data to the blockchain network for consensus processing;
if the target transaction data is successfully identified in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
wherein the resource amount of the first type of digital resource of the target digital resource conversion is the target conversion amount.
Optionally, the transaction processing device 50 of the blockchain network further includes: a model training unit 505, the model training unit 505 being configured to:
Obtaining a prediction model to be trained and sample transaction data; the sample transaction data has a first sample tag for indicating an actual conversion amount of the sample transaction data for the first type of digital resource and a second sample tag for indicating an actual transaction risk level of the sample transaction data;
acquiring sample resource circulation index information associated with the first type of digital resources, and acquiring sample reference transaction data associated with the second type of sample digital resources; the sample reference transaction data pertains to transaction data that converts the second type of sample digital resource to the first type of digital resource;
invoking the prediction model to be trained to generate a sample prediction conversion quantity of the sample digital resource for the first type of digital resource and a sample prediction risk level of the sample digital resource based on the sample resource circulation index information and the sample reference transaction data;
and correcting model parameters of the prediction model to be trained based on the sample prediction conversion quantity, the sample prediction risk level, the first sample label and the second sample label to obtain the prediction model.
Optionally, the model training unit 505 is specifically configured to:
generating a first prediction bias of the prediction model to be trained for the sample predicted conversion amount based on a difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag;
generating a second prediction deviation of the prediction model to be trained for the sample prediction risk level based on the difference between the sample prediction risk level and the transaction risk level indicated by the second sample tag;
adding the first prediction deviation and the second prediction deviation to generate a model integral prediction deviation of the prediction model to be trained;
and correcting model parameters of the prediction model to be trained based on the overall prediction deviation to obtain the prediction model.
It should be noted that, in the embodiment corresponding to fig. 5, the content not mentioned may be referred to the description of the method embodiment, and will not be repeated here.
In the embodiment of the application, target transaction data are acquired; acquiring resource circulation index information associated with a first type of digital resource and reference transaction data associated with a second type of digital resource, and performing prediction processing on the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate a predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed in the blockchain network based on the predicted conversion amount. Since the reference transaction data refers to transaction data which belongs to the same type as the target digital resource in the target transaction data and is already transacted, the reference transaction data can be used as a reference of the conversion quantity of the target digital resource for the first type of digital resource in the target transaction data, and the resource circulation index information associated with the first type of digital resource can reflect the resource circulation condition of the first type of digital resource. Therefore, the conversion amount of the target digital resource converted into the first type of digital resource is predicted by combining the reference transaction data and the resource circulation index information associated with the first type of digital resource, and the conversion amount of the target digital resource can be predicted from different dimensions, so that the accuracy of the conversion amount prediction of the target digital resource is improved.
Referring to fig. 6, fig. 6 is a schematic diagram of a composition structure of a computer device according to an embodiment of the present application. As shown in fig. 6, the above-described computer device 60 may include: a processor 601 and a memory 602. The processor 601 is connected to the memory 602, for example, the processor 601 may be connected to the memory 602 through a bus. Optionally, the computer device 60 may further include: a network interface 603, wherein the network interface 603 is connected to the processor 601 and the memory 602, e.g. the processor 601 may be connected to the memory 602 and the network interface 603 via a bus. The computer device may be a terminal device or a server.
The processor 601 is configured to support the transaction processing device of the blockchain network to perform the corresponding functions in the transaction processing method of the blockchain network described above. The processor 601 may be a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a hardware chip or any combination thereof. The hardware chip may be an Application-specific integrated circuit (ASIC), a programmable logic device (Programmable Logic Device, PLD), or a combination thereof. The PLD may be a complex programmable logic device (Complex Programmable Logic Device, CPLD), a Field programmable gate array (Field-Programmable Gate Array, FPGA), general array logic (Generic Array Logic, GAL), or any combination thereof.
The memory 602 stores program codes and the like. The Memory 602 may include Volatile Memory (VM), such as random access Memory (Random Access Memory, RAM); the Memory 602 may also include a Non-Volatile Memory (NVM), such as Read-Only Memory (ROM), flash Memory (flash Memory), hard Disk (HDD) or Solid State Drive (SSD); the memory 602 may also include a combination of the types of memory described above.
The network interface 603 is used to provide network communication functions.
The processor 601 may call the program code to:
acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
acquiring the resource circulation index information associated with the first type of digital resources, and acquiring the reference transaction data associated with the second type of digital resources; the reference transaction data pertains to transaction data that converts the second type of digital resource into the first type of digital resource;
Based on the resource circulation index information and the reference transaction data, predicting the conversion quantity of the target digital resource for the first type of digital resource, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource;
the target transaction data is executed in the blockchain network based on the predicted conversion amount.
It should be understood that the computer device 60 described in the embodiments of the present application may perform the description of the transaction processing method of the blockchain network in the embodiments corresponding to fig. 3 and 4, and may also perform the description of the transaction processing apparatus of the blockchain network in the embodiments corresponding to fig. 5, which are not repeated herein. In addition, the description of the beneficial effects of the same method is omitted.
In the embodiment of the application, target transaction data are acquired; acquiring resource circulation index information associated with a first type of digital resource and reference transaction data associated with a second type of digital resource, and performing prediction processing on the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data to generate a predicted conversion quantity of the target digital resource for the first type of digital resource; target transaction data is executed in the blockchain network based on the predicted conversion amount. Since the reference transaction data refers to transaction data which belongs to the same type as the target digital resource in the target transaction data and is already transacted, the reference transaction data can be used as a reference of the conversion quantity of the target digital resource for the first type of digital resource in the target transaction data, and the resource circulation index information associated with the first type of digital resource can reflect the resource circulation condition of the first type of digital resource. Therefore, the conversion amount of the target digital resource converted into the first type of digital resource is predicted by combining the reference transaction data and the resource circulation index information associated with the first type of digital resource, and the conversion amount of the target digital resource can be predicted from different dimensions, so that the accuracy of the conversion amount prediction of the target digital resource is improved.
Optionally, the program instructions may further implement other steps of the method in the above embodiment when executed by the processor, which is not described herein.
The present application also provides a computer readable storage medium storing a computer program comprising program instructions which, when executed by a computer, cause the computer to perform a method as in the previous embodiments, the computer being part of a computer device as mentioned above. As an example, the program instructions may be executed on one computer device or on multiple computer devices located at one site, or alternatively, on multiple computer devices distributed across multiple sites and interconnected by a communication network, which may constitute a blockchain network.
Embodiments of the present application also provide a computer program product comprising a computer program/instruction which, when executed by a processor, performs some or all of the steps of the above method. For example, the computer instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps performed in the embodiments of the methods described above.
The terms first, second and the like in the description and in the claims and drawings of the embodiments of the present application are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the term "include" and any variations thereof is intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or modules but may, in the alternative, include other steps or modules not listed or inherent to such process, method, apparatus, article, or device.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in this description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The methods and related devices provided in the embodiments of the present application are described with reference to the method flowcharts and/or structure diagrams provided in the embodiments of the present application, and each flowchart and/or block of the method flowcharts and/or structure diagrams may be implemented by computer program instructions, and combinations of flowcharts and/or blocks in the flowchart and/or block diagrams. These computer program instructions may 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 means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or structural diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or structures.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, and the above program may be stored in a computer readable storage medium, and the above program may include processes in the embodiments of the above methods when executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The foregoing disclosure is only illustrative of the preferred embodiments of the present application and is not intended to limit the scope of the claims herein, as the equivalent of the claims herein shall be construed to fall within the scope of the claims herein.
Claims (12)
1. A method of transaction processing for a blockchain network, the method comprising:
acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
acquiring the resource circulation index information associated with the first type of digital resources, and acquiring the reference transaction data associated with the second type of digital resources; the reference transaction data pertains to transaction data that converts the second type of digital resource to the first type of digital resource;
Based on the resource circulation index information and the reference transaction data, predicting the conversion quantity of the target digital resource for the first type of digital resource, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource;
the target transaction data is executed in the blockchain network based on the predicted conversion amount.
2. The method of claim 1, wherein the obtaining the reference transaction data associated with the second type of digital resource comprises:
acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
historical transaction data generated during the adjacent time period for converting the second type of digital resource into the first type of digital resource is obtained as the reference transaction data.
3. The method of claim 1, wherein the obtaining the resource circulation indicator information associated with the first type of digital resource comprises:
acquiring transaction initiation time of the target transaction data, and acquiring a neighboring period before the transaction initiation time;
Acquiring the resource circulation index information of the first type of digital resource in the adjacent time period;
wherein the resource circulation index information includes at least one of the following: conversion rate between the digital resource of the first type and other digital resources of the general type, gain rate of the digital resource of the first type.
4. The method of claim 1, wherein the predicting the conversion amount of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data, generating the predicted conversion amount of the target digital resource for the first type of digital resource comprises:
acquiring a prediction model, and calling the prediction model to perform fusion embedding processing on the resource circulation index information and the reference transaction data to generate fusion prediction characteristics;
performing prediction processing on the conversion quantity of the target digital resource aiming at the digital resource of the first type based on the fusion prediction characteristic to generate the prediction conversion quantity; the method comprises the steps of,
and predicting transaction risk of the target digital resource based on the fusion prediction feature, and generating a predicted risk level of the target digital resource.
5. The method of claim 4, wherein the target transaction data is initiated by a transaction client; the performing the target transaction data in the blockchain network based on the predicted conversion amount includes:
generating transaction execution inquiry information based on the predicted conversion quantity and the predicted risk level, and sending the transaction execution inquiry information to the transaction client;
if the confirmation information of the transaction execution inquiry information sent by the transaction client is received, the predicted conversion quantity is packaged into the target transaction data, and first packaged transaction data are generated;
broadcasting the first packaged transaction data to the blockchain network for consensus processing;
if the first encapsulated transaction data is successful in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
wherein the amount of resources of the first type of digital resources of the target digital resource conversion is the predicted conversion amount.
6. The method of claim 4, wherein the target transaction data is initiated by a transaction client; the performing the target transaction data in the blockchain network based on the predicted conversion amount includes:
Generating a selection interval of the conversion quantity of the target digital resource for the second type of digital resource based on the predicted conversion quantity, and transmitting the selection interval and the predicted risk level to the transaction client;
receiving a target conversion amount sent by the transaction client; the target conversion amount is a conversion amount selected from within the selection interval by the transaction client after performing a confirmation operation on the predicted risk level;
packaging the target conversion amount into the target transaction data, generating second packaged transaction data, and broadcasting the second packaged transaction data to the blockchain network for consensus processing;
if the target transaction data is successfully shared in the blockchain network, converting the target digital resource into the first type of data resource in the blockchain network;
wherein the amount of resources of the first type of digital resources of the target digital resource conversion is the target conversion amount.
7. The method according to claim 4, wherein the method further comprises:
obtaining a prediction model to be trained and sample transaction data; the sample transaction data has a first sample tag for indicating an actual conversion amount of the sample transaction data for the first type of digital resource and a second sample tag for indicating an actual transaction risk level of the sample transaction data;
Acquiring sample resource circulation index information associated with the first type of digital resources, and acquiring sample reference transaction data associated with the second type of sample digital resources; the sample reference transaction data pertains to transaction data that converts the second type of sample digital resource to the first type of digital resource;
invoking the prediction model to be trained to generate a sample prediction conversion quantity of the sample digital resource for the first type of digital resource and a sample prediction risk level of the sample digital resource based on the sample resource circulation index information and the sample reference transaction data;
and correcting model parameters of the prediction model to be trained based on the sample prediction conversion quantity, the sample prediction risk level, the first sample label and the second sample label to obtain the prediction model.
8. The method of claim 7, wherein modifying model parameters of the predictive model to be trained based on the sample predicted transition amount, the sample predicted risk level, the first sample tag, and the second sample tag to obtain the predictive model comprises:
Generating a first prediction bias of the predictive model to be trained for the sample predicted conversion amount based on a difference between the sample predicted conversion amount and the conversion amount indicated by the first sample tag;
generating a second prediction deviation of the prediction model to be trained for the sample prediction risk level based on the difference between the sample prediction risk level and the transaction risk level indicated by the second sample tag;
adding the first prediction deviation and the second prediction deviation to generate a model overall prediction deviation of the prediction model to be trained;
and correcting model parameters of the prediction model to be trained based on the integral prediction deviation to obtain the prediction model.
9. A transaction processing device of a blockchain network, the device comprising:
a transaction acquisition unit for acquiring target transaction data; the target transaction data is used for converting target digital resources in the blockchain network into digital resources of a first type, wherein the target digital resources are digital resources of a second type;
the index acquisition unit is used for acquiring the resource circulation index information associated with the first type of digital resources and acquiring the reference transaction data associated with the second type of digital resources; the reference transaction data pertains to transaction data that converts the second type of digital resource to the first type of digital resource;
The data prediction unit is used for predicting the conversion quantity of the target digital resource for the first type of digital resource based on the resource circulation index information and the reference transaction data, and generating the predicted conversion quantity of the target digital resource for the first type of digital resource;
and a transaction execution unit for executing the target transaction data in the blockchain network based on the predicted conversion amount.
10. A computer device comprising a processor and a memory, wherein the processor is connected to the memory, the memory being for storing a computer program, the processor being for invoking the computer program to cause the computer program to perform the method of any of claims 1-8.
11. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program adapted to be loaded and executed by a processor to cause a computer device having the processor to perform the method of any of claims 1-8.
12. A computer program product, characterized in that it comprises a computer program/instruction which, when executed by a processor, implements the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311436637.0A CN117422553A (en) | 2023-10-31 | 2023-10-31 | Transaction processing method, device, equipment, medium and product of blockchain network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311436637.0A CN117422553A (en) | 2023-10-31 | 2023-10-31 | Transaction processing method, device, equipment, medium and product of blockchain network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117422553A true CN117422553A (en) | 2024-01-19 |
Family
ID=89529859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311436637.0A Pending CN117422553A (en) | 2023-10-31 | 2023-10-31 | Transaction processing method, device, equipment, medium and product of blockchain network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117422553A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117874733A (en) * | 2024-03-12 | 2024-04-12 | 北京营加品牌管理有限公司 | Transaction execution method and system |
-
2023
- 2023-10-31 CN CN202311436637.0A patent/CN117422553A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117874733A (en) * | 2024-03-12 | 2024-04-12 | 北京营加品牌管理有限公司 | Transaction execution method and system |
| CN117874733B (en) * | 2024-03-12 | 2024-05-24 | 北京营加品牌管理有限公司 | Transaction execution method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11257070B2 (en) | Computer-implemented system and method for generating and extracting user related data stored on a blockchain | |
| WO2018040944A1 (en) | System, method, and device for identifying malicious address/malicious purchase order | |
| CN106779975B (en) | Tamper-proof method of reputation information based on block chain | |
| CN111008335B (en) | Information processing method, device, equipment and storage medium | |
| EP4242955A1 (en) | User profile-based object recommendation method and device | |
| CN111860865B (en) | Model construction and analysis method, device, electronic equipment and medium | |
| CN112785157B (en) | Risk identification system updating method and device and risk identification method and device | |
| CN110598118A (en) | Resource object recommendation method and device and computer readable medium | |
| CN117422553A (en) | Transaction processing method, device, equipment, medium and product of blockchain network | |
| KR102290481B1 (en) | Method and apparatus for providing real estate transaction service interacting with fintech based on block chain | |
| CN114416313A (en) | Task scheduling method and device based on resource prediction model | |
| KR102459466B1 (en) | Integrated management method for global e-commerce based on metabus and nft and integrated management system for the same | |
| JP7257172B2 (en) | COMMUNICATION PROGRAM, COMMUNICATION DEVICE, AND COMMUNICATION METHOD | |
| US11888991B2 (en) | Universally trusted bridges for heterogenous blockchain networks | |
| CN113011911B (en) | Data prediction method and device based on artificial intelligence, medium and electronic equipment | |
| CN109829593B (en) | Credit determining method and device for target object, storage medium and electronic device | |
| US10956698B2 (en) | Systems and methods for using machine learning to determine an origin of a code | |
| CN109685527B (en) | Method, device, system and computer storage medium for detecting merchant false transaction | |
| CN110765350A (en) | Data fusion method and device for member points | |
| CN111882436B (en) | Data processing method, device and equipment based on block chain | |
| CN113935738B (en) | Transaction data processing method, device, storage medium and equipment | |
| CN114493850A (en) | Artificial intelligence-based online notarization method, system and storage medium | |
| CN115836315A (en) | Artificial intelligence based e-commerce system and method for manufacturers, suppliers and purchasers | |
| Gutowska et al. | Evaluation of Reputation Metric for the B2C e-Commerce Reputation System. | |
| US20230377004A1 (en) | Systems and methods for request validation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |