CN111008872A - User portrait construction method and system suitable for Ether house - Google Patents
User portrait construction method and system suitable for Ether house Download PDFInfo
- Publication number
- CN111008872A CN111008872A CN201911295828.3A CN201911295828A CN111008872A CN 111008872 A CN111008872 A CN 111008872A CN 201911295828 A CN201911295828 A CN 201911295828A CN 111008872 A CN111008872 A CN 111008872A
- Authority
- CN
- China
- Prior art keywords
- account
- classification
- data
- ether house
- category
- 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.)
- Granted
Links
Images
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
- G06Q20/3829—Payment protocols; Details thereof insuring higher security of transaction involving key management
Abstract
The invention discloses a user portrait construction method and a system suitable for an Ether house, which belong to the field of block chains and comprise the following steps: collecting and analyzing synchronized Ether shop data; collecting account data of the completed account classification as verification data; based on the information obtained by analysis, carrying out primary classification by using a heuristic classification algorithm to obtain a primary account category; carrying out secondary classification on accounts under the primary account category by using a machine learning algorithm to obtain a target account category; comparing the data of the target account type with the corresponding verification data to obtain the accuracy of secondary classification, if the requirements are met, taking the current target account type as the final account type, and reversely deducing the behavior characteristics of each account according to the account type to which the account belongs to construct a user portrait corresponding to each account; and if the accuracy requirement is not met, re-performing the primary classification and the secondary classification after adjusting the parameters. The invention can realize the construction of the user image in the ether house.
Description
Technical Field
The invention belongs to the field of block chains, and particularly relates to a user portrait construction method and system suitable for an ether house.
Background
As the largest public blockchain system with the ability to run intelligent contracts, etherhouses have attracted widespread attention in both academic and industrial sectors. Users on the Ether house can not only perform simple transfer transactions such as bitcoin, but also trigger continuous transactions by deploying intelligent contracts, thereby bringing endless imagination space for technical transformation and revolution by adopting a block chain. The ethernet house network has undergone tremendous changes since the birth of 2015, as more and more users are added to the ethernet house (increasing from thousands of people at the end of 2015 to millions of people now), correspondingly more and more accounts are created and added to the ethernet house network. Accounts can be classified into different categories according to different roles played in the blockchain ecology. For example, miners, one of the most important categories, play a major role in verifying transactions and obtaining mine-cut rewards in an ethernet network. In addition, as another broad category of exchange, a platform for exchanging a legal instrument with cryptocurrency is provided. Smart contracts make it possible to create various decentralized applications based on blockchains, which has prompted the birth of applications for tokens, games, etc.
The user portrait is originally applied in the E-commerce field, and under the background of the big data era, user information is flooded in a network, each concrete information of a user is abstracted into labels, and the labels are utilized to concretize the user image, so that targeted services are provided for the user. Constructing a user portrait on an ether house has a very profound meaning for deep understanding of a blockchain system. For example, building a user image of an account would help de-anonymize the account. In particular, if an account has been identified as being of the exchange type, it may be easier to associate it with a particular exchange. In addition, the influence of the intelligent contract on the block chain platform can be analyzed by comparing the classification components of different account categories on the ether houses and the bitcoin.
However, there is currently little work on ether house user representation construction, the most relevant being de-anonymization of accounts, which can be considered to be a broad account classification work. The existing de-anonymization work is mainly developed on bitcoin. According to different classification principles, de-anonymization methods on bitcoin can be divided into two main categories: one type of method is mainly based on a UTXO data model, and according to the classification principle, different sending accounts of one transaction can be attributed to the same user; another method is based on the behavior pattern of the user, and according to the classification principle, the one-time change account in the transaction and the sending account can belong to the same user. Because the account model is different from the UTXO model in the bit currency when the data model in the Ether mill is different from the UTXO model in the bit currency, the de-anonymization method suitable for the bit currency cannot be directly applied to the Ether mill. In general, how to construct a user portrait for an ether house is an urgent problem to be solved.
Disclosure of Invention
Aiming at the defects and the improvement requirements of the prior art, the invention provides a user portrait construction method and a user portrait construction system suitable for an ether house, and aims to realize the construction of the user portrait in the ether house.
To achieve the above object, according to a first aspect of the present invention, there is provided a user representation construction method for an etherhouse, including:
(1) after the Ether house data are synchronized, collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data;
(2) collecting data of the accounts with the completed account classification as verification data of the corresponding account classification;
(3) based on information obtained by analyzing the Ether house data, carrying out primary classification on accounts in the Ether house by using a heuristic classification algorithm to obtain a plurality of primary account categories;
(4) extracting a feature vector representing account neighbor information in an ether house for each account under the primary account category, performing secondary classification on the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by the secondary classification as a target account category;
(5) comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, taking the current target account type as the final account type, and turning to the step (6); otherwise, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and after parameter adjustment is completed, switching to the step (3);
(6) and for each account in the ether house, reversely deducing the behavior characteristics of the account according to the account category to which the account belongs so as to construct a user portrait corresponding to the account according to the behavior characteristics of the account.
Further, in the method for constructing a user representation applicable to an ethernet workshop according to the first aspect of the present invention, the step (1) further includes:
before collecting the Ether house data, detecting whether the system carries out data synchronization on the Ether house nodes, if so, directly collecting the Ether house data; if not, the system synchronizes the Ether house data in a full node mode and then collects the Ether house data.
Further, in the method for constructing a user representation applicable to an ethernet workshop according to the first aspect of the present invention, the step (1) further includes:
after the Ether house data is analyzed, the information obtained by analysis is stored in an external database so as to accelerate the subsequent data query.
Further, the user portrait construction method applicable to the etherhouse provided by the first aspect of the present invention further includes:
for any account category, analyzing the behavior characteristics of each account under the account category to obtain the behavior tendency of the account in the blockchain network.
Further, the step (2) comprises:
for the account with the completed account classification, crawling the data of the account from the Internet as the verification data of the corresponding account classification;
or, for the account with the completed account classification, performing transaction with the account of the corresponding account classification to acquire the account address of the account as the verification data of the corresponding account classification.
Further, in the step (3), accounts in the ether house are preliminarily classified by using a heuristic classification algorithm, and the obtained primary account categories include: exchange, mine pool, independent miner, joint miner, Oracle contract.
Further, in the step (4), extracting a feature vector representing the account neighbor information in the ether house includes:
and calculating a probability matrix of the adjacent node type of the node where the account is located in the Etherd, and extracting a characteristic vector representing the neighbor information of the account from the probability matrix.
According to a second aspect of the present invention, there is provided a user representation construction system for an etherhouse, comprising: the system comprises a classification data collection module, a verification data collection module, a primary classification module, a secondary classification module, a verification module and a user portrait construction module;
the classification data collection module is used for collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data after the Ether house data are synchronized;
the verification data collection module is used for collecting the data of the accounts with the completed account classification as the verification data of the corresponding account classification;
the primary classification module is used for carrying out primary classification on accounts in the ether house by utilizing a heuristic classification algorithm based on information obtained by analyzing the ether house data by the classification data collection module to obtain a plurality of primary account categories, and triggering the secondary classification module after the primary classification is finished;
the secondary classification module is used for extracting a feature vector representing the neighbor information of the account in the ether house for each account under the primary account category, secondarily classifying the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by secondary classification as a target account category;
the verification module is used for comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, the current target account type is used as the final account type, and the user portrait construction module is triggered; if the preset accuracy requirement is not met, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and triggering a primary classification module after parameter adjustment is completed;
and the user portrait construction module is used for reversely deducing the behavior characteristics of each account in the Ether house according to the account category to which the account belongs so as to construct the user portrait corresponding to the account according to the behavior characteristics of the account.
Generally, by the above technical solution conceived by the present invention, the following beneficial effects can be obtained:
(1) according to the invention, after the ether house data is collected and analyzed, the accounts in the ether house are primarily classified by adopting a heuristic classification algorithm, and then on the basis of the primary classification, the accounts are secondarily classified by adopting a machine learning algorithm based on the characteristic vector of the account neighbor information, so that the account classification can be rapidly completed; the accuracy of the classification result is verified by combining the information of the account subjected to account classification, so that the accuracy of the ether house account classification can be ensured; and after the classification is finished, constructing a user portrait corresponding to the account according to the behavior characteristics of the account based on the account classification result, thereby realizing the user portrait construction in the ether house.
(2) After the user portrait in the ether house is constructed, the behavior tendency of the account in the specific category in the block chain network can be analyzed based on the user portrait, namely the account behavior characteristics under the account category, so that the real-time behavior of the account in the ether house can be monitored more accurately.
Drawings
FIG. 1 is a schematic diagram of a user sketch construction method applied to an Etherhouse according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a user representation construction system suitable for an Etherhouse according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the present application, the terms "first," "second," and the like (if any) in the description and the drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
In order to implement the construction of the user portrait in the ether house, the user portrait construction method applicable to the ether house provided by the invention, as shown in fig. 1, includes:
(1) after the Ether house data are synchronized, collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data;
in an optional embodiment, in order to ensure the accuracy of the account classification, step (1) may further include:
before collecting the Ether house data, detecting whether the system carries out data synchronization on the Ether house nodes, if so, directly collecting the Ether house data; if not, the system synchronizes the Ether house data in a full node mode and then collects the Ether house data;
in an optional embodiment, in order to speed up the information query, step (1) may further include:
after the Etheng data is analyzed, the information obtained by analysis is stored in an external database so as to accelerate the subsequent data query;
optionally, the collected etherhouse data includes, but is not limited to, block header data, status data, transaction data, receipt data, and the like;
(2) collecting data of the accounts with the completed account classification as verification data of the corresponding account classification;
in an alternative embodiment, step (2) comprises:
for the account with the completed account classification, crawling the data of the account from the Internet as the verification data of the corresponding account classification;
or, for the account with the completed account classification, performing a transaction with the account of the corresponding account classification (for example, depositing cryptocurrency into the exchange or extracting cryptocurrency from the exchange, etc.) to obtain the account address of the account as the verification data of the corresponding account classification;
it is easy to understand that the verification data collected here is the verification data used for verifying the accuracy of the subsequent account classification result, and in order to ensure the validity of the verification, enough verification data should be collected, for example, data that is analyzed for more than three years in an accumulated manner;
(3) based on information obtained by analyzing the Ether house data, carrying out primary classification on accounts in the Ether house by using a heuristic classification algorithm to obtain a plurality of primary account categories;
when the heuristic classification algorithm is used for primarily classifying the Etheng accounts, some rules need to be designed specifically, and data to be classified are screened according to the rules; for example, for the analysis result already stored in the database, relevant rules can be formulated through SQL statements to filter the account data in the database;
when the preliminary classification is specifically carried out, the specific primary account category can be determined according to the actual application characteristics; in an optional embodiment, in step (3), the accounts in the etherhouses are preliminarily classified by using a heuristic classification algorithm, and the obtained primary account categories include: exchange, mine pool, independent miner, joint miner, Oracle contract; these 5 account categories can cover substantially all users in the Etherhouse; it should be noted that the primary account set forth herein is merely an exemplary description and should not be construed as the only limitation on the invention;
(4) extracting a feature vector representing account neighbor information in an ether house for each account under the primary account category, performing secondary classification on the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by the secondary classification as a target account category;
in an optional embodiment, in step (4), extracting a feature vector representing account neighbor information in the ether house includes:
calculating a probability matrix of the adjacent node type of the node where the account is located in the Etherhouse, and extracting a characteristic vector representing the neighbor information of the account from the probability matrix;
on the basis of carrying out primary classification by using a heuristic classification learning algorithm, carrying out secondary classification by using a machine learning algorithm, and improving the coverage rate of classification; alternatively, the machine learning algorithm for performing the secondary classification may be any machine learning algorithm, such as a machine learning algorithm for maximum likelihood estimation, a graph convolution network, or other machine learning algorithms, which will not be listed herein;
(5) comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, taking the current target account type as the final account type, and turning to the step (6); otherwise, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and after parameter adjustment is completed, switching to the step (3);
(6) for each account in the ether house, reversely deducing the behavior characteristics of the account according to the account category to which the account belongs so as to construct a user portrait corresponding to the account according to the behavior characteristics of the account;
optionally, when the account behavior characteristics are reversely deduced according to the account types, a transaction tracking analysis method can be specifically adopted; for example, by tracking roll-out and roll-in transactions between different exchanges, arbitrage behavior of an account is easily discovered;
according to the user portrait construction method applicable to the ether house, after the ether house data are collected and analyzed, accounts in the ether house are primarily classified by adopting a heuristic classification algorithm, and then on the basis of the primary classification, the accounts are secondarily classified by adopting a machine learning algorithm based on the feature vectors of the account neighbor information, so that account classification can be rapidly completed; the accuracy of the classification result is verified by combining the information of the account subjected to account classification, so that the accuracy of the ether house account classification can be ensured; and after the classification is finished, constructing a user portrait corresponding to the account according to the behavior characteristics of the account based on the account classification result, thereby realizing the user portrait construction in the ether house.
In order to accurately monitor the users in the ether house in real time based on the constructed user portrait, the user portrait construction method applicable to the ether house may further include:
for any account type, analyzing the behavior characteristics of each account under the account type to obtain the behavior tendency of the account in the block chain network; for example, some accounts tend to roll in and out of arbitrage between exchanges, greatly increasing network congestion;
it should be noted that the behaviors of different types of accounts are different, and when the behavior tendency of an account under a certain account type is specifically analyzed, the behavior tendency should be specifically analyzed by combining the constructed user image.
The invention also provides a user portrait construction system suitable for an ether house, as shown in fig. 2, comprising: the system comprises a classification data collection module, a verification data collection module, a primary classification module, a secondary classification module, a verification module and a user portrait construction module;
the classification data collection module is used for collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data after the Ether house data are synchronized;
the verification data collection module is used for collecting the data of the accounts with the completed account classification as the verification data of the corresponding account classification;
the primary classification module is used for carrying out primary classification on accounts in the ether house by utilizing a heuristic classification algorithm based on information obtained by analyzing the ether house data by the classification data collection module to obtain a plurality of primary account categories, and triggering the secondary classification module after the primary classification is finished;
the secondary classification module is used for extracting a feature vector representing the neighbor information of the account in the ether house for each account under the primary account category, secondarily classifying the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by secondary classification as a target account category;
the verification module is used for comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, the current target account type is used as the final account type, and the user portrait construction module is triggered; if the preset accuracy requirement is not met, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and triggering a primary classification module after parameter adjustment is completed;
the user portrait construction module is used for reversely deducing the behavior characteristics of each account in the Ether house according to the account category to which the account belongs so as to construct a user portrait corresponding to the account according to the behavior characteristics of the account;
in the embodiment of the present invention, the detailed implementation of each module may refer to the description of the method embodiment described above, and will not be repeated here.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A user portrait construction method suitable for an Ether house is characterized by comprising the following steps:
(1) after the Ether house data are synchronized, collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data;
(2) collecting data of the accounts with the completed account classification as verification data of the corresponding account classification;
(3) based on information obtained by analyzing the Ether house data, carrying out primary classification on accounts in the Ether house by using a heuristic classification algorithm to obtain a plurality of primary account categories;
(4) extracting a feature vector representing account neighbor information in an ether house for each account under the primary account category, performing secondary classification on the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by the secondary classification as a target account category;
(5) comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, taking the current target account type as the final account type, and turning to the step (6); otherwise, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and after parameter adjustment is completed, switching to the step (3);
(6) and for each account in the ether house, reversely deducing the behavior characteristics of the account according to the account category to which the account belongs so as to construct a user portrait corresponding to the account according to the behavior characteristics of the account.
2. The user representation construction method for an etherhouse according to claim 1, wherein the step (1) further comprises:
before collecting the Ether house data, detecting whether the system carries out data synchronization on the Ether house nodes, if so, directly collecting the Ether house data; if not, the system synchronizes the Ether house data in a full node mode and then collects the Ether house data.
3. The user representation construction method for an etherhouse according to claim 1, wherein the step (1) further comprises:
after the Ether house data is analyzed, the information obtained by analysis is stored in an external database so as to accelerate the subsequent data query.
4. The user representation construction method for an etherhouse according to claim 1, further comprising:
for any account category, analyzing the behavior characteristics of each account under the account category to obtain the behavior tendency of the account in the blockchain network.
5. The user representation construction method for an etherhouse according to any one of claims 1 to 4, wherein the step (2) comprises:
for the account with the completed account classification, crawling the data of the account from the Internet as the verification data of the corresponding account classification;
or, for the account with the completed account classification, performing transaction with the account of the corresponding account classification to acquire the account address of the account as the verification data of the corresponding account classification.
6. The method for constructing a user profile applicable to an etherhouse according to any one of claims 1 to 4, wherein in the step (3), the accounts in the etherhouse are preliminarily classified by using a heuristic classification algorithm, and the obtained primary account category comprises: exchange, mine pool, independent miner, joint miner, Oracle contract.
7. The method for constructing a user portrait in an ethernet workshop according to any one of claims 1-4, wherein the step (4) of extracting feature vectors representing account neighbor information in the ethernet workshop includes:
and calculating a probability matrix of the adjacent node type of the node where the account is located in the Etherd, and extracting a characteristic vector representing the neighbor information of the account from the probability matrix.
8. A user representation construction system for an etherhouse, comprising: the system comprises a classification data collection module, a verification data collection module, a primary classification module, a secondary classification module, a verification module and a user portrait construction module;
the classification data collection module is used for collecting the Ether house data and analyzing external transaction information, internal transaction information and account category information from the Ether house data after the Ether house data are synchronized;
the verification data collection module is used for collecting the data of the accounts with the completed account classification as the verification data of the corresponding account classification;
the primary classification module is used for carrying out primary classification on accounts in the ether house by using a heuristic classification algorithm based on information obtained by analyzing the ether house data by the classification data collection module to obtain a plurality of primary account categories, and triggering the secondary classification module after the primary classification is finished;
the secondary classification module is used for extracting a feature vector representing the neighbor information of the account in the ether house for each account under the primary account category, secondarily classifying the accounts under the primary account category according to the extracted feature vector by using a machine learning algorithm, and taking the category obtained by secondary classification as a target account category;
the verification module is used for comparing the data of each target account type with the verification data of the corresponding account type to obtain the accuracy of secondary classification, if the preset accuracy requirement is met, the current target account type is used as the final account type, and the user portrait construction module is triggered; if the preset accuracy requirement is not met, adjusting parameters of a heuristic classification algorithm and a calculation learning algorithm to improve the accuracy of account classification, and triggering the primary classification module after parameter adjustment is completed;
and the user portrait construction module is used for reversely deducing the behavior characteristics of each account in the Ether house according to the account category to which the account belongs so as to construct the user portrait corresponding to the account according to the behavior characteristics of the account.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911295828.3A CN111008872B (en) | 2019-12-16 | 2019-12-16 | User portrait construction method and system suitable for Ether house |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911295828.3A CN111008872B (en) | 2019-12-16 | 2019-12-16 | User portrait construction method and system suitable for Ether house |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111008872A true CN111008872A (en) | 2020-04-14 |
| CN111008872B CN111008872B (en) | 2022-06-14 |
Family
ID=70114897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911295828.3A Active CN111008872B (en) | 2019-12-16 | 2019-12-16 | User portrait construction method and system suitable for Ether house |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008872B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112600810A (en) * | 2020-12-07 | 2021-04-02 | 中山大学 | Ether house phishing fraud detection method and device based on graph classification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170140301A1 (en) * | 2015-11-16 | 2017-05-18 | Alibaba Group Holding Limited | Identifying social business characteristic user |
| CN108537542A (en) * | 2018-04-02 | 2018-09-14 | 北京天材科技有限公司 | Data processing method for social networks |
| CN108564469A (en) * | 2018-04-11 | 2018-09-21 | 北京奇虎科技有限公司 | Representation data acquisition methods, device and the computing device of block chain node |
| CN109711849A (en) * | 2018-12-29 | 2019-05-03 | 北京金山安全软件有限公司 | Ether house address portrait generation method and device, electronic equipment and storage medium |
| EP3561710A1 (en) * | 2018-04-25 | 2019-10-30 | Freeformers Holdings Limited | Data processing system utilising distributed ledger technology |
| CN110457404A (en) * | 2019-08-19 | 2019-11-15 | 电子科技大学 | Social media account-classification method based on complex heterogeneous network |
-
2019
- 2019-12-16 CN CN201911295828.3A patent/CN111008872B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170140301A1 (en) * | 2015-11-16 | 2017-05-18 | Alibaba Group Holding Limited | Identifying social business characteristic user |
| CN108537542A (en) * | 2018-04-02 | 2018-09-14 | 北京天材科技有限公司 | Data processing method for social networks |
| CN108564469A (en) * | 2018-04-11 | 2018-09-21 | 北京奇虎科技有限公司 | Representation data acquisition methods, device and the computing device of block chain node |
| EP3561710A1 (en) * | 2018-04-25 | 2019-10-30 | Freeformers Holdings Limited | Data processing system utilising distributed ledger technology |
| CN109711849A (en) * | 2018-12-29 | 2019-05-03 | 北京金山安全软件有限公司 | Ether house address portrait generation method and device, electronic equipment and storage medium |
| CN110457404A (en) * | 2019-08-19 | 2019-11-15 | 电子科技大学 | Social media account-classification method based on complex heterogeneous network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112600810A (en) * | 2020-12-07 | 2021-04-02 | 中山大学 | Ether house phishing fraud detection method and device based on graph classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111008872B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194623B (en) | Group partner fraud discovery method and device | |
| CN110427433B (en) | Block chain consensus method and storage medium | |
| Duman et al. | Solving credit card fraud detection problem by the new metaheuristics migrating birds optimization | |
| CN113344562B (en) | Method and device for detecting Etheng phishing accounts based on deep neural network | |
| CN106599230A (en) | Method and system for evaluating distributed data mining model | |
| CN107908645B (en) | Online social platform rumor propagation immune method based on seepage analysis | |
| CN113422695B (en) | Optimization method for improving robustness of topological structure of Internet of things | |
| Li et al. | An efficient DAG blockchain architecture for IoT | |
| CN109617994A (en) | A kind of method and system positioning block chain interior joint position | |
| CN110009416A (en) | A kind of system based on big data cleaning and AI precision marketing | |
| CN111008872B (en) | User portrait construction method and system suitable for Ether house | |
| CN110287237B (en) | Social network structure analysis based community data mining method | |
| Bai et al. | Evolution of transaction pattern in Ethereum: A temporal graph perspective | |
| CN113938290B (en) | Website de-anonymization method and system for user side flow data analysis | |
| CN112235254B (en) | Rapid identification method for Tor network bridge in high-speed backbone network | |
| CN110995770B (en) | Fuzzy test application effect comparison method | |
| Yu et al. | Research on the tenacity survivability of wireless sensor networks | |
| Chu et al. | Exploiting spatial-temporal behavior patterns for fraud detection in telecom networks | |
| CN116074092B (en) | Attack scene reconstruction system based on heterogram attention network | |
| He et al. | A comparative study of different approaches for tracking communities in evolving social networks | |
| CN111651484B (en) | Method and device for analyzing accompanying relation of moving object based on semantic track similarity | |
| CN109040075A (en) | Management method, server and the system of wireless mobile sensor network interior joint | |
| CN114862588A (en) | Block chain transaction behavior-oriented anomaly detection method | |
| CN109255433B (en) | Community detection method based on similarity | |
| Tikka et al. | Convolutional neural networks in estimating the spatial distribution of electric vehicles to support electricity grid planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |