123 results about "Transaction account" patented technology

The invention discloses a financial behavior anomaly detection system based on big data, and relates to the field of financial behavior anomaly detection. Multi-source data such as customer transaction, account operation and basic information are collected and formats are unified; processing numeric data by using an isolated forest, extracting text features by using TF-IDF, and constructing a composite feature vector; constructing a customer behavior baseline model based on an LSTM network, and dynamically updating and triggering early warning; carrying out anomaly detection by combining ensemble learning and a graph neural network; and triggering a multi-level response mechanism according to the abnormal confidence coefficient, and feeding back an optimization model. According to the invention, multi-source data and an advanced algorithm are fused, a dynamic behavior baseline is constructed, millisecond-level anomaly detection is realized, complex abnormal behaviors are accurately identified, and the rate of missing report and false report is reduced; federal learning is adopted to guarantee data security, systematic risks are predicted and prevented through risk propagation, the response efficiency is improved through automatic grading disposal, and fund security is comprehensively guaranteed.

Systems and methods for automated linkage of enriched transaction data to a record of charge are provided. Electronic enriched transaction data, such as receipt information, provided by merchants, merchant aggregators, or third parties may be automatically associated with the corresponding transaction, and transmitted after the sale, or after authorization of the transaction, without user intervention. The enriched transaction data may be automatically associated with the record of charge at the acquirer or issuer end. Transaction account holders are able to view and / or download the electronic enriched transaction data with the record of charge, without the need for manually initiating emailing or attaching or the electronic enriched transaction data.

The invention discloses an abnormal transaction dynamic detection method and system fusing multi-scale analysis and information entropy, and the method comprises the steps: S01, constructing a dynamic heterogeneous graph which comprises account nodes, equipment nodes and IP nodes; s02, extracting node features of each node, extracting a spectrum feature matrix of the dynamic heterogeneous graph, and forming a node feature vector of each node; step S03, clustering the dynamic heterogeneous graph to screen out candidate detection sub-graphs, inputting node feature vectors of nodes in the candidate detection sub-graphs into a pre-trained graph classification model, and identifying an abnormal account node set; and S04, calculating a corresponding dynamic risk score in real time according to the memory state vector of each abnormal account node in the time sequence diagram network and the diagram information entropy change rate so as to evaluate a real-time risk and identify a core abnormal account. According to the method, the group type abnormal transaction account can be quickly and accurately identified, and the core abnormal account can be positioned.

Systems and methods are described related to using flexible circuitry in a payment device. In one embodiment, a payment device comprises a computing device and a memory. The computing device is configured to store a biometric identifier associated with a transaction account. The computing device is configured to at least receive, by the antenna, an interrogation signal from a point of sale (POS) device in order to activate the payment device for a payment transaction. The computing device is configured to determine a scanned fingerprint identifier of a user based at least in part on the interrogation signal activating the payment device and authenticate the scanned fingerprint identifier by matching the scanned fingerprint identifier to the biometric identifier. The transaction account is transmitted to the POS device for processing the payment transaction based at least in part on the authentication of the scanned fingerprint identifier.

The intelligent data processing system comprises a distributed edge probe group, a dynamic fraud strategy engine, an intelligent evidence chain construction module and a credible evidence storage interface, the distributed edge probe group is deployed in a core transaction system, a lightweight protocol analyzer is arranged in the distributed edge probe group, an SWIFT / UnionPay private protocol and a real-time desensitization module are adapted in the analyzer, and transaction account masking and behavior track hash solidification are executed at a data source end; the dynamic fraud strategy engine accesses an abnormal transaction flow of the edge probe group, and stores a cross-mechanism transaction mode vector through a graph neural network fraud feature library; the real-time threat evaluation unit detects the transaction time sequence abnormal probability based on a hidden Markov model; the self-adaptive evidence obtaining controller dynamically activates a targeted evidence obtaining instruction according to the threat value, capital flow of a cross-platform is captured through a high priority, and the evidence storage period of a suspicious session is prolonged.

Embodiments of the present invention provide a digital currency transaction method, apparatus, electronic device, and readable storage medium, relating to the field of digital currency technology. A specific implementation of the method includes: in the process of using a first digital currency wallet to conduct a digital currency transaction, determining a second digital currency wallet for reviewing the current transaction; sending pending review information for the current transaction to the second digital currency wallet and obtaining the review result; and determining whether to make payment and settlement for the transaction account corresponding to the current transaction based on the review result. According to an embodiment of the present invention, a digital currency transaction method capable of automatic approval is provided. After the approval process is completed, the payment process can be entered, thereby realizing the integrated automated processing of the approval process and the payment process during the digital currency transaction process, making the operation of digital currency-based transactions more convenient.

A device may determine that transaction account information, associated with a transaction account associated with a user, is to be updated. The device may identify a merchant account that is configured to use the transaction account for a transaction associated with the user and a merchant, and navigate, using a navigation model, a merchant portal associated with the merchant, to access the merchant account. The device may perform, using the navigation model and login credentials for the merchant account, a login operation to access the merchant account via the merchant portal, wherein the login credentials are stored in a credential mapping that indicates an authorization to update the transaction account information to permit the transaction account information to be used in association with the merchant account. The device may update, using the navigation model, a transaction setting of the merchant account to include updated transaction account information for the transaction account.

Systems and methods for transaction authorizations using a distributed database are disclosed. The system may allow registered transaction account holders and merchants to interact and complete transactions according to workflows enforced by smart contracts. The system may include an issuer system that receives a transaction authorization request comprising a merchant ID, a transaction account number, a transaction amount, and a transaction ID. The issuer system may retrieve a merchant public key and a smart contract based on the merchant ID, and a user public key based on the transaction account number. The issuer system may invoke the smart contract by passing the user public key and the transaction ID to the smart contract. The system may propagate transaction data (e.g., the merchant ID, the transaction account number, the payment amount, a transaction status, etc.) to a blockchain network for writing to a blockchain according to the invoked smart contract.

A method for conversion of digital assets to fiat currency using a secondary blockchain and mirrored accounting includes: receiving transaction data corresponding to a first blockchain transaction processed using a first blockchain, the transaction data including a payer identifier, recipient identifier, and blockchain currency amount; validating an entity as an authorized entity associated with the payer identifier; determining a fiat currency amount based on the blockchain currency amount; generating a second blockchain transaction, the second blockchain transaction including an unspent transaction output, destination address associated with the authorized entity, and the blockchain currency amount and / or the fiat currency amount; confirming addition of the second blockchain transaction to a second blockchain; and initiating a transfer for the fiat currency amount from a first transaction account to a second transaction account, the second transaction account being associated with the authorized entity.

The invention provides an inter-bank transaction account checking connection method and device based on new and old system switching. The method comprises the steps of determining a starting time point of T-day data migration of a new system and an old system, performing account checking processing by adopting the old system according to old account checking elements at a first preset time point before the starting time point, migrating to-be-migrated data of the old system to the new system under the condition that the starting time is reached, and monitoring the data migration progress, wherein in the data migration process of the old system and the new system, the old system is adopted to process services; and when it is detected that data migration is completed, taking the current time point as a migration completion time point, switching the old system into a new system to process the service, and at a second preset time point, adopting the new system to perform account checking processing on the migration time period and the service data generated in the (T-1) day according to the new account checking element. The problem that the accuracy of data reconciliation is low during the existing new and old system switching period is solved.

The invention provides a data table data updating method and device, equipment, a medium and a program product, relates to the field of big data, and can be applied to the field of financial science and technology. The method comprises the steps that transaction change data sent by an external mechanism is received, the transaction change data comprises transaction data of an account in a first data table in a preset time period up to the current, and the first data table is stored in the external mechanism; on the basis of the transaction change data, transaction accounting is carried out on account data in the second data table, change data of changed accounts in the second data table in the transaction accounting is recorded in an intermediate table, and the account data of the second data table is consistent with account data of the first data table before the preset time period; sending the intermediate meter to an external mechanism; receiving a checking result of the external mechanism on the intermediate table; and when the checking result shows that checking is correct, updating the second data table based on the intermediate table.

The invention discloses a block chain-based verification method and electronic equipment, and the method comprises the steps: carrying out the analysis of a transaction request, and obtaining identity certificate data carried by the transaction request; wherein the identity certificate data is generated based on the relationship between the transaction account and the account blacklist and the version information of the account blacklist; calculating the identity data according to a preset function to obtain to-be-verified data; generating first verification data according to a public key corresponding to the account blacklist and the to-be-verified data, and generating second verification data according to the public generator and the to-be-verified data; the public generator is a preset public parameter; and verifying the transaction request according to the identity proof data, the first verification value and the second verification value. According to the technical scheme, the volume of the verification data is compressed, the data transmission amount and the calculation amount of the block chain node in the verification process are reduced, and the verification speed of the transaction request can be remarkably improved.

The invention relates to the technical field of data processing, in particular to a fund allocation method, device and equipment and a storage medium, and the method adjusts a sub-account balance threshold value in real-time network account information based on network fund demand prediction information, achieves the dynamic optimization of the threshold value, can accurately match the demands of business peak and valley periods, and improves the efficiency of fund allocation. Low-efficiency occupation or shortage of funds is avoided; a three-dimensional tensor and mixed deep learning framework is constructed by adopting multi-source data, so that time sequence features, space correlation features and industry special laws of the data can be comprehensively captured, the problem of low prediction precision caused by the fact that a traditional prediction model depends on a simple method in the prior art is solved, and a prediction result better fits an actual business scene; by generating the scene-based fund scheduling scheme and combining the prediction information and the real-time account state, accurate fund distribution is realized, the problems of high-frequency transaction account congestion, deadlock and the like in the prior art are solved, the high-frequency account pressure can be relieved, transaction congestion can be reduced, and the fund circulation speed can be improved.

The invention belongs to the technical field of block chain information security, and relates to an Ethereum fraud detection method based on deep fusion of transaction semantics and graph structures, which comprises the following steps: acquiring and preprocessing Ethereum transaction records to obtain an account transaction sequence; inputting an account transaction sequence into the trained transaction sequence feature extraction network, and outputting a sequence embedding matrix; inputting the self-transaction sequence of the weighted undirected graph and the sequence embedding matrix into the trained graph neural network, and outputting a structural feature embedding matrix; performing element-level fusion on the self-transaction sequence of the sequence embedding matrix and the structural feature embedding matrix; inputting the self-transaction sequence of the sequence embedding matrix and the fused structure embedding matrix into a trained classifier to obtain a sequence prediction score and a structure prediction score, and combining the sequence prediction score and the structure prediction score to obtain an account prediction score; and judging whether the transaction account belongs to a fraudulent account or a normal account according to the account prediction score. According to the method, high-precision identification of the fraudulent account can be realized.

A method for account type registration of a blockchain wallet includes receiving, by a receiver of a processing server, a public key of a cryptographic key pair of a blockchain wallet associated with a blockchain; receiving, by a receiver of the processing server, an account identifier of the transaction account; identifying, by a processor of the processing server, an account type of the transaction account; and storing in a data entry at least the public key and an identifier associated with the identified account type.

This application discloses a transaction identifier management method, a transaction method, and a computer device. It can display a transaction management page on an instant messaging client for a transaction management user bound to a target organization; in response to an account setting trigger operation on the transaction management page, it displays a transaction account settings page, which includes a transaction identifier addition control; in response to a trigger operation on the transaction identifier addition control, it displays a transaction identifier addition page; in response to a transaction identifier addition operation on the transaction identifier addition page, it obtains the transaction identifier to be added and sends an identifier binding request to the merchant management terminal of the instant messaging client to request that the transaction identifier to be added be set as an associated transaction identifier of the target organization. Thus, multiple associated transaction identifiers that can be used for transactions can be set for an enterprise, which is beneficial for providing more convenient and flexible transaction solutions for enterprise employees, allowing them to select transaction identifiers for transactions as needed.

The invention belongs to the technical field of computers, and discloses a query method for a closely associated transaction account group, which comprises the following steps of: 1, extracting all connected k-trus communities in a global time interval of an account transaction network, and calculating a real time interval; step 2, carrying out forward evolution refinement; step 3, carrying out backward evolution refinement; step 4, constructing a DAG index structure of the time evolution community; step 5, querying the maximum connected k-trus community of the given account in a specified time interval by using the index; and step 6, returning a query result. According to the method, by constructing the account community structure diagram evolved in the time interval, the repeatedly stored community information is effectively compressed, and the expression ability and query efficiency of account community evolution in a cross-time range are improved. Through recursive stripping and sharing of edge sets among communities, minimum redundant community representation across multiple time windows is realized, and the storage overhead is remarkably reduced while the historical integrity of the communities is ensured.

This application provides a method, apparatus, device, and storage medium for comparing accounting migration data. It relates to the field of data migration technology. The method includes: obtaining transaction flow data of a points account based on a target database, and performing a first data verification process on the transaction flow data to obtain a first verification result corresponding to the transaction flow data; when the transaction flow data verification is determined to be passed, generating transaction accounting data for the points account based on the transaction flow data, and performing a second data verification process on the transaction accounting data to obtain a second verification result corresponding to the transaction accounting data; when the transaction accounting data verification is determined to be passed, determining the source transaction accounting data of the points account based on the source database, and generating a migration comparison result of the points account's accounting data based on the verification result corresponding to the source transaction accounting data and the transaction accounting data. The method of this application solves the problem of low accuracy of accounting data comparison results in the prior art.

The invention discloses a fund transaction anti-fraud interception method, device and equipment and a storage medium, and relates to the technical field of electronic fund transactions, and the method comprises the steps: receiving a Bloom filter generated based on a suspicious account list; when a fund transaction is accepted, a transaction account is preliminarily filtered based on a Bloom filter, and a suspicious account list in the transaction account is determined. And judging the suspicious account list, and determining the hit suspicious account list. And carrying out secondary filtering on the transaction accounts in the hit suspicious account list to obtain a verification result, and executing transaction interception or release operation according to the verification result to realize fund transaction fraud prevention interception. Through the above mode, on the premise that the performance of a fund transaction system is not affected and the complexity of a fund transaction link is not increased, suspicious transactions are accurately identified in massive online fund transactions, suspicious fund flow is effectively blocked, and the fund security of a user is protected.

The invention relates to a method, a device and equipment for promoting carbon reduction medium and long term transactions by using double accounts, which can set a transaction account and a consumption account for each user in a power transaction, record production information and transaction information of green power by using the transaction account, and record consumption information of the green power by using the consumption account. Executing a green electricity transaction according to a preset electricity transaction type, and recording transaction information in a transaction account; according to the production information and the transaction information recorded in the transaction account, green electricity transaction settlement is carried out on the user with the monthly as the cycle, and the green attribute and the settlement electric charge of the user are obtained; and according to the transaction information and the consumption information of the green power, calculating the power indirect carbon emission of the user. According to the technical scheme disclosed by the invention, a double-account mechanism can clearly record and manage the transaction and consumption process of the green electricity, and ensures that the green electricity can be circulated in the market and the environmental value of the green electricity is realized; and meanwhile, effective fusion of green power transaction and carbon emission management is ensured.

The invention provides a transaction matching method and system and related equipment, and the method comprises the following steps: obtaining transaction data, determining a plurality of matching rules matched with the transaction data, sorting the plurality of matching rules based on the score of each matching rule, and obtaining a sorting result, the score of each matching rule is in direct proportion to the refining degree of the condition in each matching rule, determining the transaction account used by the transaction data based on the sorting result, configuring the score representing the refining degree for each rule, and when the transaction occurs, if the number of the rules successfully matched with the transaction data is multiple, determining the transaction account used by the transaction data. At the moment, the transaction account can be determined by selecting the rule with the highest refining degree based on the score, so that the problem that the transaction cannot be carried out due to the fact that the matching result comprises a plurality of accounts is solved, manual participation is not needed, and the user experience is improved.

Aspects of the present disclosure describe secure user registration and device provisioning with respect to transaction systems. Some example embodiments use a Password-Authenticated Exchange (PAKE) protocol to facilitate secure registration of a user identifier (ID) and a password with a transaction account service, and provisioning of a user's client device with a client device provisioning service. Upon completion of the PAKE protocol, two keys can be generated: a session key for encrypting and authenticating communications with the server; and a client key for sharing information among client devices. For some example embodiments, a user registers their user ID and password, and subsequently uses their user ID and a personal identified number (PIN) code to provision a primary client device in association with the user ID. Additionally, for some example embodiments, a secondary client device is provisioned in association with the user ID via a provisioned primary client device.

Embodiments of the present application disclose block retrieval methods and devices, electronic equipment, storage media and program products; in the embodiments of the present application, the account address of the target retrieval account can be obtained, the account address is mapped through a preset address vector mapping relationship, the target address vector of the target retrieval account is obtained, the block address vector is obtained from the to-be-retrieved block of the block chain, the block address vector is the address vector obtained by mapping the transaction account address in the to-be-retrieved block through the address vector mapping relationship, vector matching is performed based on the target address vector and the block address vector, when the matching result is matching success, the to-be-retrieved block of matching success is taken as the retrieval result of the target retrieval account; without comparing the target retrieval account with all accounts corresponding to information in each block in the block chain, the block where the account related information of the target retrieval account is located can be quickly located, and the positioning and retrieval efficiency of the block chain for the account is improved.

A system and method for automated remote payments between a vehicle and a refueling station is disclosed. The system may enable the vehicle to initiate an automated remote payment to the refueling station without needing the user to manually input transaction account information, or to manually prepay for the transaction. The refueling station may detect when the vehicle is in proximity, and the vehicle and the refueling station may open communications to transmit data. The vehicle may transmit vehicle identifying data to the refueling station, and the refueling station may communicate the vehicle identifying data to a payment network to authorize the transaction. In response to authorizing the transaction, the vehicle may proceed with refueling at the refueling station.

The application discloses a tamper-proof trusted index query method and device and electronic equipment. The main idea of the application is that, in addition to saving complete and trusted information of blocks and transactions on the block chain, indexes of blocks, transactions, accounts, contracts and the like are constructed on the chain, only quick query information and the address of specific information on the chain are saved in the indexes, the database pressure is reduced, and real-time query is achieved. When the indexes are constructed, a hash locking mechanism is used, and meanwhile, context links are established between adjacent index rows through field information, the index storage error or tampering is prevented through the hash locking and context linking mechanism, the indexes are bound with the block chain or transaction information, and it is ensured that the data queried from the indexes is also trusted. Under the premise of safety and trustworthiness, the application solves the low performance problem encountered in the information query process of the block chain, transactions, accounts, contracts and the like under large data, and improves the availability of the block chain under large data.

Embodiments of the invention provide a rule generation method and apparatus, and an electronic device. The method comprises the steps of obtaining transaction data of a transaction account in a current period; for the in-use violation operation rule associated with the current period, determining validity information of the in-use violation operation rule according to the transaction data and the in-use violation operation rule; determining a to-be-combined violation operation rule based on the validity information; and iteratively processing the violation operation rules to be combined to obtain the in-use violation operation rules corresponding to the next period. According to the technical scheme, the to-be-combined violation operation rules are determined based on the violation operation rules in use, iteration processing is carried out on the to-be-combined violation operation rules, the rule generation efficiency is improved, an iteration processing mechanism enables the rules to be continuously adjusted and perfected according to real-time feedback, and the rule generation efficiency is improved. The effects of accurately optimizing the rule and remarkably improving the rule optimization efficiency and the rule operation accuracy are achieved.

In certain specific examples, aspects are directed to methods and systems involving selection and processing circuitry involving multiple transaction-directed user accounts registered by a service provider (e.g., banking or other type of financial institution) and with the selection and processing circuitry configured to enable selection of one of the accounts, based on an optimization algorithm which accounts for the rewards offerings. The recommended and / or selected one of the reward-type transaction accounts may realize a maximum level of value, according to user-specific criteria, for a particular prospective purchase transaction, and the transaction may be being carried out via a secure protocol that is to mitigate or prevent unauthorized use of the VTC circuit and that is in compliance with a secure protocol associated with the selected one of the reward-type transaction accounts.

The embodiment of the invention relates to the technical field of financial transaction risk identification, and discloses a programmed security transaction risk identification method and device, computer equipment and a storage medium, and the method comprises the steps: constructing effective features of programmed abnormal transaction identification; according to the characteristics of each transaction data segment, determining the association relationship between the security transaction accounts of each transaction data segment; according to a time sequence transaction record, and according to the effective features and the association relationship, constructing time sequence dynamic graph structure data; updating a current transaction data segment to the time sequence dynamic graph structure data to obtain updated time sequence dynamic graph structure data; and inputting the updated time sequence dynamic graph structure data into a time sequence dynamic graph neural network algorithm to obtain a programmed anomaly recognition result of the securitization transaction data. Through the above mode, the embodiment of the invention realizes the effective improvement of the identification accuracy of the programmed abnormal transaction.

The invention provides a coupon data processing method, device and equipment, and the method comprises the steps: configuring the coupon strategy information of a target coupon, and binding the target coupon with a business event; in response to a service event triggered based on the target transaction account, distributing the target coupon to the target transaction account; receiving an activation operation of the target transaction account for the target coupon, and generating charge item preferential information of the target transaction account according to the coupon strategy information; initial order information of the target transaction account is received, and target order information is generated based on the charge item preferential information and the initial order information in response to charge items corresponding to the charge item preferential information related to the initial order information; and performing transaction operation based on the target order information. The convenience and flexibility of card and coupon data processing are improved.

The application discloses an abnormal account monitoring method, system and device based on a feature graph model, and the method comprises the following steps: acquiring a transaction account and a transaction record to form a feature graph model; inputting the node attribute of each node into a scoring prediction model to obtain the predicted credit score of each node, and searching for a neighbor node; the predicted credit score is added to the neighbor node as a node attribute; it is judged whether the transaction account is abnormal, if abnormal, it is marked as a warning account, and a directed subgraph model is formed based on the warning account; based on the predicted credit score of each node in the directed subgraph model, the balance credit score of each node is calculated, all nodes of the directed subgraph model are traversed, if the balance credit score is lower than a preset credit score threshold, it is marked as a warning node; the community where the warning node is located is determined, each community is traversed, if there are multiple warning nodes in the community, all warning accounts are marked as abnormal accounts. The application improves the accuracy and response time.