CN110048936B - Method for judging junk mail by semantic associated words - Google Patents
Method for judging junk mail by semantic associated words Download PDFInfo
- Publication number
- CN110048936B CN110048936B CN201910312461.5A CN201910312461A CN110048936B CN 110048936 B CN110048936 B CN 110048936B CN 201910312461 A CN201910312461 A CN 201910312461A CN 110048936 B CN110048936 B CN 110048936B
- Authority
- CN
- China
- Prior art keywords
- mails
- image
- junk
- semantic
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/42—Mailbox-related aspects, e.g. synchronisation of mailboxes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0236—Filtering by address, protocol, port number or service, e.g. IP-address or URL
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0245—Filtering by information in the payload
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a method for judging junk mails by semantic associated words, and relates to the field of network security. The invention comprises the following steps: acquiring a large amount of normal mails and junk mails to perform automatic semantic associated word labeling; storing a large number of marked mails to a mail body library; classifying all the labeled samples by using an SVM algorithm, and generating a strong classifier of the junk mail; when the system monitors that unread mails appear in the mailbox, starting a junk mail retrieval service; the service acquires the content of the unread mail, performs primitive extraction on the image in the mail, performs semantic related word extraction on the text in the mail, and introduces the text into a strong spam classifier for judgment. According to the invention, the unread mails in the mailboxes of the users are monitored in real time through the system, the pictures in the unread mails are judged by utilizing the positive and negative sample pictures, and then the judgment is carried out by utilizing the strong spam classifier generated by the semantic associated words, so that the spam is prevented from flooding, and the network experience of the users is improved.
Description
Technical Field
The invention belongs to the field of network security, and particularly relates to a method for judging junk mails by semantic associated words.
Background
With the popularity of the internet, e-mail is increasingly widely used as a basic service provided by the internet. However, the accompanying spam is also becoming more and more rampant. According to the statistical report of the development conditions of the internet in china published by the information center of internet in china 2004 and 1 month, the netizens in china receive 13.7 e-mails each week averagely, wherein 7.9 e-mails are occupied by spam mails, and the number of spam mails exceeds the number of normal mails, and the number of spam mails tends to increase further. The mailboxes are filled with junk mail so that it takes a significant amount of time for an e-mail user to find a closed mail. Spam has severely impacted the normal use of email. Although various methods have been devised to attempt to prevent the propagation of spam, they are bypassed one by the spammer. In addition, when using various tools for identifying spam, users often worry that a large amount of legitimate mail is erroneously identified as spam, such as real-time blacklist (RBL), and while blocking spam, some users' legitimate mail are left behind. None of the methods is entirely satisfactory at present.
The reason for the massive outbreak of spam is the inherent weakness of the Simple Mail Transfer Protocol (SMTP), which lacks a comprehensive means of confirming the identity of the sender of the email. Sending spam is very easy by forging the reply address and masking the identity by means of an hacked computer or the like. But modifying or replacing the SMTP protocol requires a significant capital investment. In addition, the cost for sending the junk mails is low, so that a part of enterprises or websites can be publicized in a mail sending mode to obtain the personal interests. They obtain email addresses in various ways, such as purchasing a list of email addresses of users or third parties from a portion of an unscrupulous web service provider or owner of a web site, or programmatically automatically obtaining email addresses from a web page; even, thousands of english character strings are generated as the mail addresses of the users by a permutation and combination method and then automatically transmitted by a program. Common contents of spam include: earning information, adult advertisements, commercial or personal web site advertisements, electronic magazines, comic books, and the like. Some spam is even accompanied by viruses. If the user inadvertently opens these mail items, it can lead to leakage of secrets or damage to the machine, causing significant damage. Therefore, the junk mails have no value for most users, but the user burden is increased, and a lot of time and energy are wasted in order to find out the legal mails from a large pile of junk mails.
The contents of the junk mails are characterized clearly, the words are very close or similar, and the junk mails have certain universality. But for legal mails, the users are in different industries, and all industries have their own special terms, so the legal mails have exclusivity. In the case where the SMTP protocol cannot be changed, it is desirable to restrict or punish spammers by law, and to provide a method for automatically identifying spam so that internet users can be freed from spam without misjudging legitimate mail as spam.
Disclosure of Invention
The invention aims to provide a method for judging junk mails by semantic related words, which monitors unread mails in a mailbox of a user in real time through a system, judges pictures in the unread mails by utilizing positive and negative sample pictures, and judges by utilizing a junk mail strong classifier generated by the semantic related words, thereby solving the problems of flooding of the existing junk mails and increasing the burden of the user.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a method for judging junk mails by semantic associated words, which comprises the following steps:
step S1: acquiring a large amount of normal mails and junk mails to perform automatic semantic associated word labeling;
step S2: storing a large number of marked mails to a mail body library;
step S3: classifying all the labeled samples by using an SVM algorithm, and generating a strong classifier of the junk mail;
step S4: the system monitors the user mailbox in real time;
step S5: when the situation that unread mails appear in the mailbox is monitored, the system starts a junk mail retrieval service;
step S6: the service acquires the content of the unread mail, and performs primitive extraction on the image in the mail and semantic associated word extraction on the text in the mail;
step S7: leading the extracted primitive attributes and semantic associated words into a strong classifier of the junk mail for judgment;
step S8: when the junk mails are judged, the mails are directly deleted or pulled to a blacklist;
step S9: when the mail is judged to be normal mail, reminding the user to check and accept;
in the step S1, the automatic semantic related word annotation includes two parts:
the first part is a training stage; the training phase comprises the following steps:
step S11: training an email image set and an email description text;
step S12: capturing text semantic associated word information of the mail;
step S13: extracting image elements in the mail for clustering;
step S14: carrying out statistical learning on primitive classes of the image and text semantic associated word information through a machine to obtain mail attributes;
the second part is an image labeling stage; the image labeling stage comprises the following steps:
step S21: acquiring a mail image set to be processed and a text description;
step S22: extracting image elements in the mail and carrying out primary labeling to obtain mail attributes;
step S23: capturing text semantic associated word information of the mail;
step S24: and carrying out secondary labeling on the image elements by utilizing the text semantic associated word information to obtain an image concept.
Preferably, in step S7, the strong spam classifier determines the semantic related word judgment by similarity comparison, and the specific formula is as follows:
wherein d (C)i) And d (C)j) Respectively refer to concept CiAnd CjHierarchy of corresponding ontology tree nodes in the tree, Dist (C)i,Cj) Is referred to as CiAnd CjThe sum of all weights with the weight edges on the shortest path between the nodes; CE (C)i,Cj) Is CiAnd CjThe number of all edges on the shortest path between nodes; dep refers to the maximum depth of the body book; r (C)i,Cj) The closer to 1, the higher the similarity.
Preferably, in step S13, the clustering of the image elements in the mail is performed by using histogram representation, each feature representation is itself a vector composed of a plurality of components, and the semantic vector represents the weight of each component in the vector in the image element.
The invention has the following beneficial effects:
according to the invention, the unread mails in the mailboxes of the users are monitored in real time through the system, the pictures in the unread mails are judged by utilizing the positive and negative sample pictures, and then the judgment is carried out by utilizing the strong spam classifier generated by the semantic associated words, so that the spam is prevented from flooding, and the network experience of the users is improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a diagram illustrating steps of a method for determining spam based on semantic related words according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a method for determining spam by semantic associated words, comprising the following steps:
step S1: acquiring a large number of normal mails and junk mails to perform automatic semantic associated word labeling, and taking the normal mails as positive samples and the junk mails as negative samples;
step S2: storing a large number of marked mails to a mail body library; the establishment of the mail ontology library is used for interpreting the image library under the framework of the ontology, and low-level features of the images are mapped to an ontology semantic concept, so that the combination of high-level semantics and bottom-level features can be realized;
step S3: classifying all the labeled samples by using an SVM algorithm, and generating a strong classifier of the junk mail;
step S4: the system monitors the user mailbox in real time;
step S5: when the situation that unread mails appear in the mailbox is monitored, the system starts a junk mail retrieval service;
step S6: the service acquires the content of the unread mail, and performs primitive extraction on the image in the mail and semantic associated word extraction on the text in the mail;
step S7: leading the extracted primitive attributes and semantic associated words into a strong classifier of the junk mail for judgment;
step S8: when the junk mails are judged, the mails are directly deleted or pulled to a blacklist;
step S9: when the mail is judged to be normal mail, reminding the user to check and accept;
in step S1, the automatic semantic related word annotation includes two parts:
the first part is a training stage; the training phase comprises the following steps:
step S11: training an email image set and an email description text;
step S12: capturing text semantic associated word information of the mail;
step S13: extracting image elements in the mail for clustering;
step S14: carrying out statistical learning on primitive classes of the image and text semantic associated word information through a machine to obtain mail attributes;
the second part is an image labeling stage; the image labeling stage comprises the following steps:
step S21: acquiring a mail image set to be processed and a text description;
step S22: extracting image elements in the mail and carrying out primary labeling to obtain mail attributes;
step S23: capturing text semantic associated word information of the mail;
step S24: and carrying out secondary labeling on the image elements by utilizing the text semantic associated word information to obtain an image concept.
In step S7, the strong spam classifier determines the semantic related word judgment by similarity comparison, and the specific formula is as follows:
wherein d (C)i) And d (C)j) Respectively refer to concept CiAnd CjHierarchy of corresponding ontology tree nodes in the tree, Dist (C)i,Cj) Is referred to as CiAnd CjThe sum of all weights with the weight edges on the shortest path between the nodes; CE (C)i,Cj) Is CiAnd CjThe number of all edges on the shortest path between nodes; dep refers to the maximum depth of the body book; r (C)i,Cj) The closer to 1 the value of (d) indicates higher similarity, and the higher similarity indicates closer to spam.
In step S13, clustering image primitives in the mail is represented by using a histogram, where each feature representation is a vector consisting of a plurality of components, and the semantic vector represents the weight of each component in the vector in the image primitives.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (3)
1. A method for judging spam mails by semantic associated words is characterized by comprising the following steps:
step S1: acquiring a large amount of normal mails and junk mails to perform automatic semantic associated word labeling;
step S2: storing a large number of marked mails to a mail body library;
step S3: classifying all the labeled samples by using an SVM algorithm, and generating a strong classifier of the junk mail;
step S4: the system monitors the user mailbox in real time;
step S5: when the situation that unread mails appear in the mailbox is monitored, the system starts a junk mail retrieval service;
step S6: the service acquires the content of the unread mail, and performs primitive extraction on the image in the mail and semantic associated word extraction on the text in the mail;
step S7: leading the extracted primitive attributes and semantic associated words into a strong classifier of the junk mail for judgment;
step S8: when the junk mail is judged, the mail is directly deleted or pulled to a blacklist;
step S9: when the mail is judged to be normal mail, reminding the user to check and accept;
in the step S1, the automatic semantic related word annotation includes two parts:
the first part is a training stage; the training phase comprises the following steps:
step S11: training an email image set and an email description text;
step S12: capturing text semantic associated word information of the mail;
step S13: extracting image elements in the mail for clustering;
step S14: carrying out statistical learning on primitive classes of the image and text semantic associated word information through a machine to obtain mail attributes;
the second part is an image labeling stage; the image labeling stage comprises the following steps:
step S21: acquiring a mail image set to be processed and a text description;
step S22: extracting image elements in the mail and carrying out primary labeling to obtain mail attributes;
step S23: capturing text semantic associated word information of the mail;
step S24: and carrying out secondary labeling on the image elements by utilizing the text semantic associated word information to obtain an image concept.
2. The method according to claim 1, wherein in step S7, the strong spam classifier determines the semantic related word judgment by similarity comparison, and the specific formula is as follows:
wherein d (C)i) And d (C)j) Respectively refer to concept CiAnd CjHierarchy of corresponding ontology tree nodes in the tree, Dist (C)i,Cj) Is referred to as CiAnd CjThe sum of all weights with the weight edges on the shortest path between the nodes; CE (C)i,Cj) Is CiAnd CjThe number of all edges on the shortest path between nodes; dep refers to the maximum depth of the body book; r (C)i,Cj) The closer to 1, the higher the similarity.
3. The method for determining spam according to claim 1, wherein in step S13, the image elements in the mail are clustered by histogram representation, each feature representation is a vector consisting of a plurality of components, and the semantic vector represents the weight of each component in the vector in the image element.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910312461.5A CN110048936B (en) | 2019-04-18 | 2019-04-18 | Method for judging junk mail by semantic associated words |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910312461.5A CN110048936B (en) | 2019-04-18 | 2019-04-18 | Method for judging junk mail by semantic associated words |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110048936A CN110048936A (en) | 2019-07-23 |
CN110048936B true CN110048936B (en) | 2021-09-10 |
Family
ID=67277762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910312461.5A Active CN110048936B (en) | 2019-04-18 | 2019-04-18 | Method for judging junk mail by semantic associated words |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110048936B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110610213A (en) * | 2019-09-20 | 2019-12-24 | 苏州大学 | Mail classification method, device, equipment and computer readable storage medium |
CN113159736A (en) * | 2021-05-21 | 2021-07-23 | 北京天空卫士网络安全技术有限公司 | Mailbox management method and device |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101106539A (en) * | 2007-08-03 | 2008-01-16 | 浙江大学 | Filtering method for spam based on supporting vector machine |
WO2008059237A1 (en) * | 2006-11-14 | 2008-05-22 | Keycorp Limited | Electronic mail filter |
CN101520848A (en) * | 2008-02-27 | 2009-09-02 | 中国科学院自动化研究所 | Method for filtering image-based junk mails |
CN101887523A (en) * | 2010-06-21 | 2010-11-17 | 南京邮电大学 | Method for detecting image spam email by picture character and local invariant feature |
CN101917352A (en) * | 2010-06-12 | 2010-12-15 | 盈世信息科技(北京)有限公司 | Method for recognizing picture spam mails and system thereof |
CN103020645A (en) * | 2013-01-06 | 2013-04-03 | 深圳市彩讯科技有限公司 | System and method for junk picture recognition |
CN103684971A (en) * | 2012-09-07 | 2014-03-26 | 盈世信息科技(北京)有限公司 | Method and system for processing mails |
CN104268203A (en) * | 2014-09-23 | 2015-01-07 | 深圳市中兴移动通信有限公司 | Mobile terminal and junk information effectively filtering method and device thereof |
CN106506327A (en) * | 2016-10-11 | 2017-03-15 | 东软集团股份有限公司 | A kind of spam filtering method and device |
CN106815200A (en) * | 2015-11-30 | 2017-06-09 | 任子行网络技术股份有限公司 | Objectionable text detection method and device based on keyword |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
BRPI0407451A (en) * | 2003-02-14 | 2006-02-07 | Nervana Inc | System and method for knowledge retrieval, semantics, management and presentation |
US7502785B2 (en) * | 2006-03-30 | 2009-03-10 | Microsoft Corporation | Extracting semantic attributes |
CN104834891A (en) * | 2015-02-16 | 2015-08-12 | 北京建筑大学 | Method and system for filtering Chinese character image type spam |
-
2019
- 2019-04-18 CN CN201910312461.5A patent/CN110048936B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008059237A1 (en) * | 2006-11-14 | 2008-05-22 | Keycorp Limited | Electronic mail filter |
CN101106539A (en) * | 2007-08-03 | 2008-01-16 | 浙江大学 | Filtering method for spam based on supporting vector machine |
CN101520848A (en) * | 2008-02-27 | 2009-09-02 | 中国科学院自动化研究所 | Method for filtering image-based junk mails |
CN101917352A (en) * | 2010-06-12 | 2010-12-15 | 盈世信息科技(北京)有限公司 | Method for recognizing picture spam mails and system thereof |
CN101887523A (en) * | 2010-06-21 | 2010-11-17 | 南京邮电大学 | Method for detecting image spam email by picture character and local invariant feature |
CN103684971A (en) * | 2012-09-07 | 2014-03-26 | 盈世信息科技(北京)有限公司 | Method and system for processing mails |
CN103020645A (en) * | 2013-01-06 | 2013-04-03 | 深圳市彩讯科技有限公司 | System and method for junk picture recognition |
CN104268203A (en) * | 2014-09-23 | 2015-01-07 | 深圳市中兴移动通信有限公司 | Mobile terminal and junk information effectively filtering method and device thereof |
CN106815200A (en) * | 2015-11-30 | 2017-06-09 | 任子行网络技术股份有限公司 | Objectionable text detection method and device based on keyword |
CN106506327A (en) * | 2016-10-11 | 2017-03-15 | 东软集团股份有限公司 | A kind of spam filtering method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110048936A (en) | 2019-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9325649B2 (en) | Signature generation using message summaries | |
US20060149820A1 (en) | Detecting spam e-mail using similarity calculations | |
CN101087259A (en) | A system for filtering spam in Internet and its implementation method | |
CN110048936B (en) | Method for judging junk mail by semantic associated words | |
RU2763921C1 (en) | System and method for creating heuristic rules for detecting fraudulent emails attributed to the category of bec attacks | |
Iyengar et al. | Integrated spam detection for multilingual emails | |
Mallampati et al. | A machine learning based email spam classification framework model: related challenges and issues | |
Paul et al. | A privatised approach in enhanced spam filtering techniques using TSAS over cloud networks | |
Issac et al. | Improved Bayesian anti-spam filter implementation and analysis on independent spam corpuses | |
Patidar et al. | A novel technique of email classification for spam detection | |
CN113746814A (en) | Mail processing method and device, electronic equipment and storage medium | |
Chhabra | Fighting spam, phishing and email fraud | |
Youn et al. | Improved spam filter via handling of text embedded image e-mail | |
Adamkani et al. | A content filtering scheme in social sites | |
Manek et al. | ReP-ETD: A Repetitive Preprocessing technique for Embedded Text Detection from images in spam emails | |
CN106713108B (en) | A kind of process for sorting mailings of combination customer relationship and bayesian theory | |
Barbar et al. | Image spam detection using FENOMAA technique | |
Zamel et al. | Analysis study of spam image-based emails filtering techniques | |
Babu et al. | USING MACHINE LEARNING AND NLP TECHNIQUES FOR EFFICIENT SPAM EMAIL DETECTION | |
RU2766539C1 (en) | Method of detecting fraudulent letter relating to category of internal bec attacks | |
US20230328034A1 (en) | Algorithm to detect malicious emails impersonating brands | |
Ming et al. | Spam filtering by stages | |
Kaur et al. | A Survey on Various Classification Techniques in Email Spamming | |
RU2758358C2 (en) | Method for generating signature for spam detection | |
Chim | To build a blocklist based on the cost of spam |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210823 Address after: 315100 no.959, Chengxin Road, Panhuo street, Yinzhou District, Ningbo City, Zhejiang Province Applicant after: Ningbo youth YOUPIN Information Technology Co.,Ltd. Address before: 230000 room 323, Sangxia 1 complex building, information industry base, Hefei high tech Zone, Anhui Province Applicant before: HEFEI TIANYI NETWORK MEDIUM Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |