240 results about "Digital fingerprint" patented technology

The invention discloses a logistics order management system and method, and belongs to the technical field of logistics information management. The method comprises the following steps: step 1, generating a unique digital fingerprint for each logistics order; step 2, performing multi-level security encryption and state synchronization management on order information; 3, constructing a digital twinborn model corresponding to the order, collecting and preprocessing key data in real time and visually displaying the key data in the logistics process, and realizing dynamic monitoring of the whole process; step 4, based on an order state consensus mechanism, automatically matching optimal logistics resources and driving an order processing flow, and generating a verifiable order execution proof chain at the same time; and step 5, performing intelligent analysis and adaptive optimization on the full-life-cycle data of the order, and continuously improving the overall efficiency and precision of logistics management.

The systems and methods disclosed herein monitor application (e.g., artificial intelligence (AI) model) operations using interactions between the application and a kernel. The systems and methods disclosed herein intercept, using a kernel interface, one or more function invocations transmitted from the application (e.g., an AI model without model modification). Event record(s) are generated for one or more functions to define process identifiers, resource interaction types, timestamps, and / or resource identifiers. Observed pattern(s) for the application are identified by comparing current event record(s) with previous record(s), and the identified observed pattern(s) are evaluated against reference pattern(s) to generate score(s). Data packet(s) that indicate observed pattern(s), corresponding score(s), and / or cryptographic digital fingerprint(s) of the one or more functions are generated. The data packet(s) are transmitted to distributed ledgers for immutable storage.

The invention provides an intelligent education resource sharing and authority management system based on a block chain, and belongs to the technical field of intelligent education, and the system comprises a block chain network layer, a resource right confirmation module, an intelligent contract module, a distributed storage network, a cross-chain interaction gateway and a dynamic optimization module, comprising a resource authentication chain, an authority management chain and a cross-chain interaction chain, and the chains realize data intercommunication through relay nodes; the resource right confirmation module adopts a three-level Hash nested structure to generate a non-tampering digital fingerprint, and binding and uplink the educational resource metadata and the creator DID; the intelligent contract module comprises a dynamic authority management contract and a resource transaction contract, and supports an access control strategy based on context awareness. According to the intelligent education resource sharing system, the core problems that the right of the education resources is difficult to confirm, the sharing efficiency is low, and the right management is inflexible are solved, and the safe, intelligent and extensible intelligent education resource sharing system is constructed.

The invention discloses an artificial intelligence auxiliary authentication method and system for data element right confirmation, and relates to the technical field of data element management and credible circulation. Comprising the following steps: data acquisition: acquiring a data product, an ownership statement and contract terms, and calculating an initial digital fingerprint of the data product; and ownership identification: extracting core value elements and features of the data product based on a multi-modal intelligent analysis model, quantifying value contribution weights formed by all links to the data product, and automatically generating a data element circulation graph. According to the method, the multi-modal intelligent analysis model is constructed, and the data product is deeply scanned and analyzed automatically, so that the dependence on predefined rules is reduced, and the intellectualization and automation of ownership identification are realized; by constructing an intelligent compliance verification model, data operation behaviors are monitored and compared in real time, substantive compliance control over the whole data use process is achieved, and a credible use closed loop is established.

The invention discloses a universal control box and method based on a programmable control logic library, and the method is characterized in that the method comprises the steps: capturing an operation feature signal of controlled equipment in real time through a signal collection module, and extracting an equipment feature vector to construct an equipment digital fingerprint; performing matching degree calculation on the feature vector and a control module of a pre-stored logic library, selecting a target logic control module, and generating an expected control parameter in a virtual sandbox; driving equipment to run through the target module, acquiring running data in real time, and comparing the running data with expected parameters to generate a deviation report; aggregating historical data based on the deviation report, and performing parameter increment optimization on the target module to generate a versioned patch; fusing the patch and the equipment full-dimension log to construct a digital twinborn body, predicting the health state of the equipment based on twinborn data, and outputting a logic library iteration instruction; and flexible control is driven by a data closed loop, so that the problems of customized cables and non-standard mechanical trepanning caused by the difference of controlled equipment of the industrial control box are solved, and one box is universal.

The invention relates to the technical field of computer data processing, and discloses a cross-border e-commerce compliance tax refund method and an intelligent declaration system based on block chain evidence storage, and the method comprises the steps: constructing a reference library containing commodity physical attributes and fair density intervals; order transaction, logistics actual measurement and fund time sequence data are acquired; executing multi-dimensional cross validation based on the reference library, wherein the multi-dimensional cross validation comprises physical space logic verification based on geometric boxing simulation, attribute consistency verification based on density distribution matching and quality and time sequence joint verification; a risk level is determined by integrating results; and generating digital fingerprints for compliance data, writing the digital fingerprints into a distributed account book, and generating a declaration file by using an on-chain index. According to the invention, trade authenticity is verified through physical simulation and multi-dimensional logic, evidence is ensured not to be tampered in combination with a block chain technology, and compliance and auditing efficiency of tax refund declaration are effectively improved.

The invention relates to the technical field of block chain anti-counterfeiting, in particular to an artwork anti-counterfeiting traceability system and method based on a block chain, and the method comprises the steps: obtaining the multi-modal feature data of an artwork, and generating a unique digital fingerprint through a Hash algorithm; continuously acquiring a moving track image of the artwork and extracting spatial-temporal characteristics to generate a dynamic track password; encrypting the digital fingerprint, the track password and the artwork ownership information together, writing the encrypted information into a tamper-resistant distributed account book of a block chain, forming block chain data, and binding the block chain data with a two-dimensional code corresponding to the artwork; scanning the two-dimensional code attached to the artwork, calling the block chain data, and comparing the block chain data with the physical features and the track password to verify the artwork. Therefore, the position of the artwork can be continuously tracked in combination with the historical trajectory of the artwork, the artwork can be better traced through association between the position of the artwork and other anti-counterfeiting information of the artwork, and the transparency and credibility of an artwork transaction market are improved.

The invention discloses an archive information security storage and tamper-proof method and system based on a block chain, and belongs to the field of information security, the method comprises the following steps: obtaining archive information to be processed and generating standard archive data; a time sequence accumulation state hash model is adopted to process the standard archive data to generate digital fingerprints, and the time sequence accumulation state hash model constructs an academic state hash chain which takes initial academic state hash as a starting point and is recursively deduced along with time for each student; the generation of each new academic state hash is forced to depend on a previous academic state hash, a current period archive data abstract, a timestamp and a context challenge factor derived from a previous state; the digital fingerprints, the unique identity identifiers of the students and the operation metadata are packaged into archive information transactions, and the archive information transactions are signed by an authorization mechanism and then broadcasted to a block chain network; and a personal electronics file is formed. According to the invention, powerful and provable time sequence integrity is provided for auditing and tracing of archives.

The invention discloses a lightweight container X-ray intelligent security check method and system based on anti-distillation, and belongs to the technical field of image recognition. The method comprises the following steps: acquiring qualified image data, and respectively extracting metadata of the qualified image data to carry out hash verification marking for subsequent block chain evidence storage; generating a confrontation sample and a qualified image to form an enhanced data set; constructing a double-teacher confrontation distillation framework combined with a self-supervision pseudo-label generation mechanism, and after determining an optimal framework, completing model self-supervision training by using the enhanced data set as a training sample to obtain a target model; generating a model compression strategy of structured pruning and mixing precision quantification collaborative optimization, completing lightweight deployment of a target model, and executing an actual container security check task; a pixel-level risk heat map is generated according to X-ray image information obtained by an actual container security check task, and a risk assessment result is obtained; and generating a unique digital fingerprint record to the block chain by using a chain type evidence storage mechanism constructed based on the block chain to complete evidence storage.

The invention discloses a digital fingerprint generation method for terminal equipment, and relates to the technical field of digital fingerprint generation, comprising the following steps: S1, collecting multi-dimensional hierarchical features; s2, privacy enhancement; s3, fingerprint anti-regeneration generation is carried out; and S4, fingerprint life cycle management. According to the terminal equipment digital fingerprint generation method, multi-dimensional fine-grained feature acquisition is realized from a non-sensitive layer, a semi-sensitive layer and a high-sensitive layer, a feature weight is optimized through a federated learning framework, fingerprint drift caused by hardware replacement and software updating is effectively resisted, and the user experience is improved. Dynamic Gaussian noise is injected into numerical semi-sensitive features to balance privacy protection and feature effectiveness, 2048-bit key Paillier homomorphic encryption is adopted for high-sensitive features, meanwhile, cross-scene tracking risks are blocked through scenarized sub-fingerprint generation and an original feature immediate destruction mechanism, and the privacy protection and feature effectiveness are improved. And an anti-duplication architecture fusing a Merkle tree and a bloom filter is introduced to greatly reduce the fingerprint coincidence collision rate.

The invention discloses a watermark processing method and device, a storage medium and a computer readable storage medium, and relates to the technical field of digital watermarking. The watermark processing method comprises the following steps: capturing a current data packet flowing into a target gateway; according to the grading label of the current data packet, the corresponding watermark embedding strength is determined, and the watermark embedding strength is in positive correlation with the priority degree corresponding to the grading label; obtaining identification information of the current data packet, and generating a dynamic digital fingerprint based on the identification information; and embedding the dynamic digital fingerprint into the current data packet based on the watermark embedding strength to obtain a target data packet, and sending the target data packet to a specified delivery address corresponding to the current data packet through the target gateway. The technical problem that an existing watermark processing method is difficult to effectively protect real-time data streams is solved.

The invention relates to the field of Internet of Things data processing, in particular to a hydropower station IoT real-time data acquisition and uplink method based on edge computing, the core technology comprises data acquisition and preliminary screening processing of received data, and the screening processing method comprises a threshold detection algorithm and a moving average anomaly detection algorithm. Cleaning the data through a quartile distance judgment algorithm; judging and calculating the state of the equipment, and calculating the credibility of the data vector to obtain the running state of the equipment; data packaging and uploading: generating a data uploading block chain collected by a digital fingerprint combination through dual hash; the oracle machine establishes a contract rule to monitor the uploaded data in real time, and pushes abnormal information to the early warning platform when the data is abnormal, so that real-time early warning is realized; through the three-level architecture of edge calculation, the block chain and the oracle machine, on the premise of ensuring data credibility, the decision-making precision and the response speed are improved, and the three pain points of uncredibility, high delay and many false alarms in the industrial monitoring field are solved.

The invention discloses an electric energy metering box leakage protection switch trip detection method, which comprises the following steps of: when power failure is detected, generating event context data under the constraint of limited energy based on multi-mode original data, execution energy and buffer combined arrangement; executing short window early warning analysis to obtain an early warning trigger instruction and an early warning feature set; and responding to the early warning trigger instruction, constructing a transient fingerprint and executing parallel crosstalk decoupling to obtain a transient fingerprint and decoupling conclusion. The fingerprint construction adopts logarithmic time scattering fingerprint and electric arc physical fitting, and the decoupling adopts geometric constraint sparse chromatography decoupling to identify a responsibility loop. And fusing the transient fingerprint, the decoupling conclusion and the early warning feature set, applying a multi-modal time sequence consistency constraint, and forming a tripping conclusion and a leakage protection type suggestion. According to the method, the technical problems of loss of evidence at the moment of tripping power failure and strong crosstalk of parallel loops are solved, the responsibility loop can be positioned with high confidence, and interpretable tripping mechanism diagnosis and type suggestions are provided.

The invention provides a music copyright credibility verification and circulation method, system and device and a medium, and belongs to the technical field of block chains. The method comprises the following steps: uploading an audio to a circulation platform, framing and windowing a smart contract, calculating short-time energy, and generating time domain hash through random projection hash; after windowing, an MFCC coefficient is extracted through Fourier transform, Mel filtering, logarithm compression and DCT, and after dimensionality reduction, frequency domain Hash is generated through locality sensitive Hash. And setting weights according to music types, splicing time domain and frequency domain Hash to obtain composite Hash, forming digital fingerprints by combining with copyright person biological characteristic Hash, and linking and binding songs and creator vouchers by taking copyright numbers as keys. Based on the digital fingerprint, a music copyright NFT token is generated by using an ERC-721 protocol, and a circulation NFT token is generated by using an ERC-1155 protocol. And when the copyright is checked, the target audio is uploaded to generate a digital fingerprint, infringement is judged by comparing the similarity, and a corresponding NFT token is inquired for evidence collection.

The invention discloses an intelligent substation secondary equipment online reconstruction control method and system, and relates to the technical field of power system automation, and the method comprises the following steps: broadcasting fault information containing digital fingerprints generated by fault secondary equipment to adjacent equipment; enabling the adjacent equipment to verify the digital fingerprint and carry out lightweight consensus confirmation, and obtaining a dynamic reputation score of the secondary equipment based on the operation data of the secondary equipment; screening out a candidate takeover equipment set from the adjacent equipment according to the dynamic reputation score; determining target takeover equipment from the candidate takeover equipment set through a multi-target optimization algorithm; and causing the target takeover device to execute the reconstruction logic. The method is used for solving the problems of insufficient authenticity of fault information of existing secondary equipment, low equipment cooperation efficiency, lack of intelligence of takeover decision and poor cohesion of a reconstruction process.

Disclosed are a method and computer system for quantifying identity risk associated with an agent's request for access to online resources using valid credentials of an authorized user. The likelihood that the agent is the authorized user is computed using access request data, historical access data for the authorized user, and identity risk signal data collected from open source intelligence (OSINT) and other external identity risk data sources. The likelihood may be based on the distance between the current digital fingerprint, which in an embodiment is a high-dimensional vector comprising identity risk signal data, and a similar historical digital fingerprint for the authorized user, or, alternatively, the deviation from mean between a current weighted risk score comprising the identity risk signal data and the historical weighted risk scores for the authorized use.

The invention relates to the technical field of bill risk assessment, and discloses a bill circulation process risk assessment block chain system and method. The method comprises the following steps: in a block chain node network initialization stage, establishing a bill feature classification library and a circulation path topological structure; and when a bill circulation event is detected, extracting the bill digital fingerprint and the identity label of the current holder. According to the risk weight coefficient in the digital fingerprint matching feature classification library, the credit rating data is inquired in combination with the identity, and the two are input into a dynamic evaluation model to generate an initial risk evaluation value; and calculating a path complexity index based on a flow path topological structure, dynamically correcting the initial evaluation value according to the path complexity index, and outputting a final risk score. According to the method, distributed storage and sharing of bill information are realized based on the block chain, dynamic evaluation and path complexity analysis are combined, a bill circulation risk evaluation effect is optimized, and bill market risk management and control requirements are met.

The invention relates to a dental drilling hardness real-time monitoring method based on vibration signal analysis and a dental hardness sensor. The dental drilling hardness real-time monitoring method comprises the following steps: acquiring a three-dimensional vibration displacement signal; after filtering and multi-dimensional feature extraction, obtaining a vibration feature vector representing the mechanical impedance of the tooth body; inputting the hardness index and the vibration displacement into a trained machine learning model, and mapping and outputting the hardness index and the vibration displacement of the current drilling area in real time; packaging with a timestamp, and serializing and storing as a traceable historical record; the system continuously presents hardness change in a dynamic waveform and a color gradient, and prompts when detecting that the hardness changes suddenly or crosses a boundary. Compared with the prior art, the method has the advantages that the three-dimensional micro-vibration signal of the drill bit can be converted into the digital fingerprint of the mechanical impedance of the tooth tissue in real time, and a visualization-reminding closed loop is driven by the hardness index flow synchronized with the timestamp, so that the drilling hardness in-situ sensing is realized.

The invention discloses a real-time circulation monitoring method and platform in a trusted data space, relates to the technical field of data management and security, and solves the problems that a traditional data monitoring scheme depends on batch log analysis, minute-level delay exists, and a verifiable joint auditing mechanism is lacked during cross-organization data circulation, so that the dispute rate is relatively high, and the reliability is high. And the monitoring coverage rate of multi-organization data collaboration is relatively low due to the facts that monitoring data between heterogeneous systems is split and a standardized interface is lacked. The real-time circulation monitoring method and platform in the trusted data space comprises a monitoring system, and the monitoring system comprises a digital fingerprint generation module, a probe deployment module, a dynamic trust evaluation engine, an audit tracking module and a visual console. Through cooperation of all module components, millisecond-level monitoring delay is achieved, compared with a traditional scheme, the response speed is increased by multiple times, real-time analysis of a hundred million-level data event / second is supported, and the risk of data leakage is effectively prevented.

The invention discloses a block chain evidence storage system of a secret-related level optical disc all-in-one machine, which comprises an acquisition module, an encryption module, an authority management module, a data verification module, an audit tracking module, a decryption module and a data sharing module, and is characterized in that the acquisition module is used for acquiring electronic medical records and image data to generate original data; the encryption module is used for encryption processing; the authority management module is used for performing access control rule configuration on the encrypted data and generating a corresponding access credential; the data verification module is used for generating a digital fingerprint for the encrypted data by adopting a hash function and generating a block chain record; the audit tracking module is used for recording log information of all data access behaviors to form an audit track; the decryption module carries out decryption operation by adopting a decryption algorithm and outputs original data; and the data sharing module is used for realizing cross-mechanism data transmission and generating and outputting a shared data packet.

The invention relates to the technical field of traceability of a meta-universe platform, and discloses an agricultural product traceability system and method based on the meta-universe. According to the method, firstly, key events such as harvesting, farming operation, quality inspection and transportation of agricultural products in the whole process from planting to selling are automatically collected through a collection end, parameters and evidence hash values are spliced, a data abstract is calculated, digital signature is carried out, and it is ensured that a data source is credible; the gateway carries out triple defense line verification on the received data packet; then the data association module performs knowledge graph construction on the discrete events passing verification, quantifies the credibility of the causal relationship through multi-dimensional weight calculation, and finally determines a main causal path representing the most credible life trajectory; and finally, the upper chain traceability module adopts a mixed architecture of a Merkle tree and distributed storage, generates a digital fingerprint from the key information of the main path, stores the digital fingerprint in a block chain, stores a complete evidence packet in an IPFS, and finally provides immersive traceability experience capable of being verified by one key for consumers in the meta universe to form a closed-loop credible traceability chain.

The invention discloses a digital delivery management platform and method based on a BIM technology, and relates to the technical field of digital delivery, and the method comprises the steps: carrying out the geometric and logic consistency checking of a BIM model component by component according to an LOD-LOR rule dictionary and a progress mapping table, recognizing lacks and conflicts, and generating a repaired high-credibility model; based on the high-credibility model, dividing delivery units in combination with professional partitions and a work decomposition structure WBS, and generating a delivery data set; performing field normalization, hierarchical hash and signature operation on the delivery data set to generate a verifiable delivery packet with a digital fingerprint, and obtaining the digital fingerprint, a signature record and a hash index table; and based on the digital fingerprint and the signature record, importing the verifiable delivery package into a digital delivery platform, verifying consistency in combination with the Hash index table, generating a delivery verification report, and storing the delivery verification report as a digital archiving result. According to the method, the BIM digital delivery process has high credibility and verifiability.

The invention relates to a security platform upgrading optimization method and system based on a software architecture. The method comprises the steps that after current operation state data of system components are obtained, deep mining and feature classification are conducted through a data analysis algorithm, and a target component list needing to be upgraded is accurately recognized; based on the version information, the function features and the dependency graph in the list, intelligently matching an optimal upgrade resource package combination from a preset upgrade resource library; then, according to the optimal upgrading resource bundle combination, updating the target component by adopting an incremental updating technology in combination with a difference comparison algorithm, and generating component state data containing digital fingerprints; and finally, comparing the digital fingerprint of the component state data with an expected version fingerprint through Hash check, and generating an adaptive upgrade data packet through conflict detection and version compatibility processing. By adopting the method, efficient, accurate and stable upgrading of the security platform can be realized.

The invention discloses a digital display system and method for non-abandoned cultural heritage, and the system comprises a multi-mode active data collection layer which is used for recording non-abandoned dynamic performance and building a handicraft material decay model; meanwhile, constructing a digital twinborn scene of a non-occurrence place, and forming a holographic data set integrating forms, actions and contexts; the intelligent culture analysis and reconstruction layer is responsible for constructing a non-abandoned knowledge graph and combining the non-abandoned knowledge graph with the extracted core elements to form a culture gene pool; meanwhile, the cultural evolution process of non-abandoned projects is simulated, and personalized non-abandoned cultural experience and service are provided for users; the immersive interactive display layer is used for constructing a three-dimensional display space of non-perpetual items, deploying a personalized guide system, generating a customized explanation path according to user behavior data, and designing personalized digital cultural and creative products; and the sustainable ecological maintenance layer is used for establishing a unique digital fingerprint, storing a creation track in the whole course, providing AI-assisted digital skill training and remote guidance tools, and constructing an inheritor activeness index.

The present application relates to the technical field of artificial intelligence technology and blockchain technology, specifically to an intelligent copyright protection and infringement identification method for students' innovative works, aiming to solve the problems of no traceability in the creation process, poor adaptation of multi-type works, difficulty in deep infringement identification, blurred boundaries of AI-assisted creation, and low adaptability in the campus scene in the prior art. The method comprises: receiving the innovative works uploaded by students, extracting multi-modal main features and auxiliary features according to the type, and generating a unique digital fingerprint through feature distillation fusion; recording the whole process of creating tracks, and combining time sequence blockchains to generate a timestamped evidence certificate. The present application realizes the whole process of copyright protection for students' innovative works, adapts to various types of works such as text, code, vision and multi-modal combination, has high accuracy in infringement identification, is convenient and low in cost, is suitable for large-scale popularization and application in the campus, and provides strong support for students' rights protection.

The embodiment of the invention provides a data auditing method and device, equipment, a storage medium and a program product, relates to the technical field of data processing, and can be applied to the field of financial science and technology. According to the method, a hash value of an operation log is stored in a private block chain network, then a digital fingerprint corresponding to the operation log is determined based on the hash value, then abnormity auditing is performed on the operation log based on the hash value of the operation log in the private block chain network and an auditing contract, and when it is determined that a target operation log is abnormal, the operation log is subjected to abnormal auditing. And verifying the target operation log based on the target digital fingerprint corresponding to the target operation log in the public block chain network, and generating an audit report of the target operation log when the verification is passed. According to the method, the hash value of the operation log and the auditing contract are stored in the public chain, on the basis that the compliance requirement of the financial industry for data storage is met and auditing credibility is ensured, automatic auditing is achieved, and the storage cost is reduced.

The invention relates to the technical field of federated learning, and discloses an image omics-oriented cross-domain federated machine learning training method, which comprises the following steps that: a server distributes a global orthogonal semantic base to establish a shared gradient space recessive semantic coordinate system, and when the stability of a local training process meets a preset condition, a client sends the global orthogonal semantic base to the client; a local gradient is projected to a coordinate system and uploaded together with a digital fingerprint representing the physical characteristics of imaging equipment, and a server groups clients according to the digital fingerprint and performs weighted aggregation based on the information concentration degree on received projection vectors in each group so as to reconstruct a global gradient to update a model. According to the method, through an aggregation mode of firstly performing grouping according to physical causes and then performing weighting in groups according to information values, systematic deviation from equipment differences and real pathological semantics from data contents can be effectively stripped, and sensitivity to key clinical features is kept.

The invention relates to a method for identifying vehicle license plates in ticketless car parks, in which, as a digital fingerprint of the license plate, a raw evaluation matrix is used, which is obtained in a character recognition phase, as a step prior to generating the read of the license plate and an evaluation matrix converted into a character string. The invention also proposes a method for comparing two or more license plates and a method for managing ticketless car parks.

The invention discloses a credible storage method, device and system for electronic evidence and a storage medium, and relates to the technical field of data storage, and the method comprises the steps: obtaining customer behavior data of a risk customer from a multi-dimensional data source, and integrating the customer behavior data into multi-dimensional electronic evidence; storing the multi-dimensional electronic evidence in an evidence storage server in real time, and generating an evidence digital fingerprint of the multi-dimensional electronic evidence by adopting a dynamic self-adaptive fragmentation strategy; performing multiple encryption signature processing on the evidence digital fingerprint to generate a composite digital signature; and writing the composite digital signature into a judicial block chain network through a cross-chain protocol to realize credible storage of the multi-dimensional electronic evidence. The reliability of the electronic evidence can be improved.

This disclosure provides a data processing method and related equipment based on deep learning, relating to the field of intelligent recommendation technology. It includes: acquiring graph structure data corresponding to a set of items, and determining a target item node and a set of neighboring item nodes based on multiple item nodes in the graph structure; identifying a subset of feature data from the feature data of the item set that is inconsistent with the neighboring feature data of the target item node; matching digital fingerprints to the feature data in the feature data subset and determining the similarity between the feature data and the digital fingerprints; filtering based on similarity, storing feature data that meets preset conditions in a uniform pool corresponding to the target item node, and aggregating the feature data in the uniform pool to generate updated target feature data for the target item node; and determining user preferences based on the updated target feature data of at least one target item node. This disclosure can reduce computational complexity and improve computational efficiency.