CN112860934A - Trademark retrieval system based on machine learning - Google Patents
Trademark retrieval system based on machine learning Download PDFInfo
- Publication number
- CN112860934A CN112860934A CN202110125561.4A CN202110125561A CN112860934A CN 112860934 A CN112860934 A CN 112860934A CN 202110125561 A CN202110125561 A CN 202110125561A CN 112860934 A CN112860934 A CN 112860934A
- Authority
- CN
- China
- Prior art keywords
- trademark
- jqs
- iis
- proxy server
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 23
- 238000004891 communication Methods 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 11
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Library & Information Science (AREA)
- Computer Hardware Design (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of trademark retrieval, and discloses a trademark retrieval system based on machine learning, which comprises: trademark inquiry server RISiRetrieval proxy server IIS running with machine learning system softwareiThe trademark index server cluster JQS which is provided with a web crawler and runs with security authentication system software, and the trademark database RD which stores trademark big data and supports access and downloadi(ii) a The trademark index server cluster JQS comprises trademark index servers JQS1… trademark index Server JQSiTrademark index server JQSj… trademark index Server JQSn(ii) a Operating on a brand index server JQSiPair of security authentication system on the search proxy server IISiThe identity of (2) is subjected to security authentication onlySearch proxy server IISiThe identity of (2) passes the security authentication of the security authentication system, trademark index server JQSiOnly executes the search proxy server IISiThe call request of (2). The invention solves the technical problem that the trademark index server in the trademark retrieval system is illegally called.
Description
Technical Field
The invention relates to the technical field of trademark retrieval, in particular to a trademark retrieval system based on machine learning.
Background
The trademark is a special image, mainly formed by characters, patterns and the like, and is a mark for distinguishing products or services after being registered. In trademark search, there are many features to be searched for, for example, color, shape, texture, and the like, and spatial similarity measurement can be performed using the spatial relationship of an object in a trademark image.
Because the trademark image often contains rich information such as colors, characters, graphs, character and graph mixture and the like, semantic gaps are easy to appear in the trademark retrieval algorithm, namely the problem that the accuracy of the trademark is not ideal due to the fact that the correlation between bottom-layer visual features and high-layer semantics is not strong is solved.
Before solving the semantic gap problem of trademark retrieval, the illegal calling problem of the trademark index server needs to be solved, because if the trademark index server is illegally called in variable time, the efficiency and the accuracy of the trademark retrieval are greatly reduced.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a trademark retrieval system based on machine learning, which aims to solve the technical problem that a trademark index server in the trademark retrieval system is illegally called.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme:
a machine learning based brand retrieval system, comprising: trademark inquiry server RISiRetrieval proxy server IIS running with machine learning system softwareiThe trademark index server cluster JQS which is provided with a web crawler and runs with security authentication system software, and the trademark database RD which stores trademark big data and supports access and downloadi;
The trademark index server cluster JQS comprises trademark index servers JQS1… trademark index Server JQSiTrademark index server JQSj… trademark index Server JQSn;
Trademark inquiry server RISiIIS with search proxy server through network communication deviceiPerforming communication connection between each other; search proxy server IISiCommunicating with any one of the brand index servers JQS within the brand index server cluster JQS via a network communication deviceiPerforming communication connection between each other; within a brand index server cluster JQSAny trademark index server JQSiBy means of network communication equipment with trademark database RDiPerforming communication connection between each other;
search proxy server IISiMachine learning system software to self-trademark inquiry server RISiAnalyzing the input search trademark image IRP and outputting a trademark image RPiAccording to the trademark image RPiSelecting to invoke a brand index server JQS within a cluster of brand index servers JQSiTrademark index Server JQSiMethod for grabbing trademark database RD by using web crawleriTrademark big data inside;
trademark index server JQSiTo search proxy server IISiThe identity of (2) is securely authenticated, and the authentication method comprises the following steps:
the method comprises the following steps: search proxy server IISiIn trademark index server JQSiThe user registration is performed on the security authentication system, which specifically comprises:
(1) safety authentication system pops up and retrieves proxy server IIS on registration pageiA dialog box for interactive communication;
(2) setting an elliptic curve Q to be defined on a finite field R, generating an element g belonging to Q, and searching an IIS (inter-server information system)iSelecting an integer fiAs the private key, calculate p ═ fiX g, inputting p and g into a dialog box by taking the p and the g as public keys, namely sending the public keys to a security authentication system;
step two: security authentication system IIS for search proxy serveriThe identity of the user is subjected to security authentication, and the specific authentication process is as follows:
(1) safety authentication system pops up and retrieves proxy server IIS on verification pageiA dialog box for interactive communication;
(2) search proxy server IISiRandomly selecting an integer a, calculating that z is a multiplied by g, and sending z to a security authentication system, namely inputting the z into a dialog box;
(3) random selection k of security authentication systemi0 or 1, and k isiIs sent to the detectorIis of cable proxy serveriI.e. displayed within a dialog box;
(4) if k isiIf 0, search the proxy server IISiTransmitting a to a security authentication system; if k isiIf 1, search proxy server IISiA + fiTransmitting to a security authentication system;
(5) the security authentication system performs the following verification: if k isiVerifying whether z is true or not, wherein the z is 0 and a multiplied by g; if k isiVerify that p + z ═ 1 (a + f)i) Whether x g is true;
if the equation z is a × g or p + z is (a + f)i) X g is established, proving the search proxy server IISiKnowledge of private key fiIf the security authentication system passes the search proxy server IISiThe identity authentication of (1).
Further, the trademark index server JQSiAnd trademark index server JQSjThe communication connection is not carried out between the two, and the mutually independent distributed operation states are presented.
Further, the search proxy server IISiThe machine learning system running on the computer adopts a supervised learning algorithm, and the supervised learning algorithm comprises the following steps:
the method comprises the following steps: giving k groups of training sets, the training set takes the retrieval trademark image IRP as an input layer, and takes the trademark image RP similar to the retrieval trademark image IRPiIs an output layer;
step two: the supervised learning algorithm extracts the main color in the retrieval trademark image IRP, combines all connection points with labels with the same color, generates a color area, defines a color classifier, a shape classifier and a relation classifier according to the color area, and learns how to correlate the retrieval trademark image IRP and the trademark image RP by utilizing each classifieriAnd obtaining a machine learning model for searching the trademark image IRP.
Further, in the second step, the step (2), the step (3), the step (4) and the step (5) form a round of authentication, the round of authentication is repeatedly executed for t times, and in the execution process of a certain round of authentication, the proxy server IIS is searchediIf the authentication is not passed, the whole authentication process is terminatedI.e. search proxy server IISiThe identity authentication of the security authentication system is not passed.
(III) advantageous technical effects
Compared with the prior art, the invention has the following beneficial technical effects:
1. the invention operates in a brand index server JQSiPair of security authentication system on the search proxy server IISiOnly the search proxy server IIS performs security authenticationiThe identity of (2) passes the security authentication of the security authentication system, trademark index server JQSiOnly executes the search proxy server IISiThe security authentication mechanism not only greatly promotes any trademark index server JQS in the trademark index server cluster JQSiEffectively prevents illegal users from implementing any brand index server JQS in the brand index server cluster JQSiPlays a role in protecting any one of the brand index servers JQS within the brand index server cluster JQSiThe technical effect of illegal calling is avoided.
2. The invention extracts the main color in the searched trademark image IRP, combines all the connection points with the same color label to generate a color area, defines a color classifier, a shape classifier and a relation classifier according to the color area, and learns how to correlate the searched trademark image IRP and the trademark image RP by utilizing each classifieriThe method solves the problem that semantic gap is easy to appear in a trademark retrieval algorithm, namely the trademark precision is not ideal due to weak correlation between bottom-layer visual features and high-layer semantics.
3. The invention is to search the proxy server IIS in the safety certification systemiAfter the identity authentication is completed, the security authentication system only knows the IIS of the search proxy serveriIs legitimate, it does not know the search proxy server IISiI.e. the search proxy server IISiUnder the premise of not revealing the private key of the user, the identity security authentication is completed, and the authentication mode remarkably improves the IIS of the retrieval proxy serveriThe security performance of the identity authentication process of (1).
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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.
A machine learning based brand retrieval system, comprising: trademark inquiry server RISiRetrieval proxy server IIS running with machine learning system softwareiThe trademark index server cluster JQS which is provided with a web crawler and runs with security authentication system software, and the trademark database RD which stores trademark big data and supports access and downloadi;
The trademark index server cluster JQS comprises trademark index servers JQS1… trademark index Server JQSiTrademark index server JQSj… trademark index Server JQSn(ii) a Trademark index server JQSiAnd trademark index server JQSjThe communication connection is not carried out between the two groups of the distributed operation states, and the mutually independent distributed operation states are presented;
the organization mode of the trademark index server cluster JQS can reduce the communication overhead between nodes to the maximum extent, and the whole index query system has high fault tolerance because the index nodes work independently;
trademark inquiry server RISiIIS with search proxy server through network communication deviceiPerforming communication connection between each other; search proxy server IISiCommunicating with any one of the brand index servers JQS within the brand index server cluster JQS via a network communication deviceiPerforming communication connection between each other; any one brand index server JQS within a cluster of brand index servers JQSiBy means of network communication equipment with trademark database RDiCommunicate with each otherConnecting;
search proxy server IISiMachine learning system software to self-trademark inquiry server RISiAnalyzing the input search trademark image IRP and outputting a trademark image RPiAccording to the trademark image RPiSelecting to invoke a brand index server JQS within a cluster of brand index servers JQSiTrademark index Server JQSiMethod for grabbing trademark database RD by using web crawleriTrademark big data inside;
wherein, the trademark image RPiIs a trademark image similar to the search trademark image IRP;
search proxy server IISiThe machine learning system running on the computer adopts a supervised learning algorithm, and the supervised learning algorithm comprises the following steps:
the method comprises the following steps: giving k groups of training sets, the training set takes the retrieval trademark image IRP as an input layer, and takes the trademark image RP similar to the retrieval trademark image IRPiIs an output layer;
step two: aiming at the problem that semantic gap is easy to appear in a trademark retrieval algorithm, namely, the trademark precision is not ideal due to the fact that the bottom layer visual characteristics are not strongly correlated with the high layer semantics, a supervised learning algorithm extracts the main color in a retrieved trademark image IRP, combines all connection points with labels of the same color to generate a color area, defines a color classifier, a shape classifier and a relation classifier according to the color area, and learns how to correlate the retrieved trademark image IRP and the trademark image RP by utilizing each classifieriObtaining a machine learning model for searching the trademark image IRP;
wherein the color classifier is based on the trademark image RP in the trademark databaseiCarrying out associated retrieval with the color similarity of the retrieved trademark image IRP;
the shape classifier operates on the basis of the trademark image RP in the trademark databaseiCarrying out correlation retrieval on the shape similarity of the IRP and the retrieved trademark image;
the relationship classifier operates on the basis of the trademark image RP in the trademark databaseiCarrying out correlation retrieval on the relationship similarity with the retrieval trademark image IRP;
to prevent retrieval of proxy server IISiIllegitimate invocation of any one of the brand index servers JQS within the brand index server cluster JQSiWhen searching for the proxy server IISiTrademark indexing Server JQSiWhen a call request is sent, the trademark index server JQSiTo search proxy server IISiOnly the search proxy server IIS performs security authenticationiThe identity of (2) passes the security authentication of the security authentication system, trademark index server JQSiOnly executes the search proxy server IISiOtherwise the brand index server JQSiRejection and search proxy server IISiCarrying out communication;
trademark index server JQSiTo search proxy server IISiThe identity of (2) is securely authenticated, and the authentication method comprises the following steps:
the method comprises the following steps: search proxy server IISiIn trademark index server JQSiThe user registration is performed on the security authentication system, which specifically comprises:
(1) safety authentication system pops up and retrieves proxy server IIS on registration pageiA dialog box for interactive communication;
(2) setting an elliptic curve Q to be defined on a finite field R, generating an element g belonging to Q, and searching an IIS (inter-server information system)iSelecting an integer fiAs the private key, calculate p ═ fiX g, inputting p and g into a dialog box by taking the p and the g as public keys, namely sending the public keys to a security authentication system;
wherein, said fiIs a private key that is the only legitimate attestation key and is only the search proxy server IISiOwned separately, i.e. the secure authentication system does not know the private key fi;
Step two: security authentication system IIS for search proxy serveriThe identity of the user is subjected to security authentication, and the specific authentication process is as follows:
(1) safety authentication system pops up and retrieves proxy server IIS on verification pageiA dialog box for interactive communication;
(2) search proxy server IISiRandomly selecting an integer a, calculating that z is a multiplied by g, and sending z to a security authentication system, namely inputting the z into a dialog box;
(3) random selection k of security authentication systemi0 or 1, and k isiSent to search proxy server IISiI.e. displayed within a dialog box;
(4) if k isiIf 0, search the proxy server IISiTransmitting a to a security authentication system; if k isiIf 1, search proxy server IISiA + fiTransmitting to a security authentication system;
(5) the security authentication system performs the following verification: if k isiVerifying whether z is true or not, wherein the z is 0 and a multiplied by g; if k isiVerify that p + z ═ 1 (a + f)i) Whether x g is true;
if the equation z is a × g or p + z is (a + f)i) X g is established, proving the search proxy server IISiKnowledge of private key fiIf the security authentication system passes the search proxy server IISiThe identity authentication of (2);
(6) forming one round of authentication by the step (2), the step (3), the step (4) and the step (5), repeatedly executing for t times, and searching the proxy server IIS in the execution process of one round of authenticationiWithout authentication, the whole authentication process is terminated, i.e. the proxy server IIS is retrievediIdentity authentication which fails the security authentication system;
the security authentication mechanism not only greatly promotes any trademark index server JQS in the trademark index server cluster JQSiEffectively prevents illegal users from implementing any brand index server JQS in the brand index server cluster JQSiPlays a role in protecting any one of the brand index servers JQS within the brand index server cluster JQSiThe technical effect of illegal calling is avoided;
in trademark index server JQSiTo search proxy server IISiOfAfter the authentication is completed, the security authentication system only knows the IIS of the search proxy serveriIs legitimate, it does not know the search proxy server IISiPrivate key f ofiThat is to say the retrieval proxy server IISiWithout revealing its private key fiUnder the premise of (1), the safety authentication of the identity is completed, and the authentication mode remarkably improves the IIS of the retrieval proxy serveriThe security performance of the identity authentication process of (1).
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. A trademark retrieval system based on machine learning, characterized by comprising: trademark inquiry server RISiRetrieval proxy server IIS running with machine learning system softwareiThe trademark index server cluster JQS which is provided with a web crawler and runs with security authentication system software, and the trademark database RD which stores trademark big data and supports access and downloadi;
The trademark index server cluster JQS comprises trademark index servers JQS1… trademark index Server JQSiTrademark index server JQSj… trademark index Server JQSn;
Trademark inquiry server RISiIIS with search proxy server through network communication deviceiPerforming communication connection between each other; search proxy server IISiCommunicating with any one of the brand index servers JQS within the brand index server cluster JQS via a network communication deviceiPerforming communication connection between each other; any one brand index server JQS within a cluster of brand index servers JQSiBy means of network communication equipment with trademark database RDiPerforming communication connection between each other;
trademark ropeReferral server JQSiTo search proxy server IISiThe identity of (2) is securely authenticated, and the authentication method comprises the following steps:
the method comprises the following steps: search proxy server IISiIn trademark index server JQSiThe user registration is performed on the security authentication system, which specifically comprises:
(1) safety authentication system pops up and retrieves proxy server IIS on registration pageiA dialog box for interactive communication;
(2) setting an elliptic curve Q to be defined on a finite field R, generating an element g belonging to Q, and searching an IIS (inter-server information system)iSelecting an integer fiAs the private key, calculate p ═ fiX g, inputting p and g into a dialog box by taking the p and the g as public keys, namely sending the public keys to a security authentication system;
step two: security authentication system IIS for search proxy serveriThe identity of the user is subjected to security authentication, and the specific authentication process is as follows:
(1) safety authentication system pops up and retrieves proxy server IIS on verification pageiA dialog box for interactive communication;
(2) search proxy server IISiRandomly selecting an integer a, calculating that z is a multiplied by g, and sending z to a security authentication system, namely inputting the z into a dialog box;
(3) random selection k of security authentication systemi0 or 1, and k isiSent to search proxy server IISiI.e. displayed within a dialog box;
(4) if k isiIf 0, search the proxy server IISiTransmitting a to a security authentication system; if k isiIf 1, search proxy server IISiA + fiTransmitting to a security authentication system;
(5) the security authentication system performs the following verification: if k isiVerifying whether z is true or not, wherein the z is 0 and a multiplied by g; if k isiVerify that p + z ═ 1 (a + f)i) Whether x g is true;
if the equation z is a × g or p + z is (a + f)i) X g is established, proving the search proxy server IISiKnowledge of private keysfiIf the security authentication system passes the search proxy server IISiThe identity authentication of (1).
2. The machine-learning-based trademark retrieval system of claim 1, wherein the trademark index server JQSiAnd trademark index server JQSjThe communication connection is not carried out between the two, and the mutually independent distributed operation states are presented.
3. The machine-learning-based trademark retrieval system of claim 2, wherein the retrieval proxy server IISiThe machine learning system running on the computer adopts a supervised learning algorithm, and the supervised learning algorithm comprises the following steps:
the method comprises the following steps: giving k groups of training sets, the training set takes the retrieval trademark image IRP as an input layer, and takes the trademark image RP similar to the retrieval trademark image IRPiIs an output layer;
step two: the supervised learning algorithm extracts the main color in the retrieval trademark image IRP, combines all connection points with labels with the same color, generates a color area, defines a color classifier, a shape classifier and a relation classifier according to the color area, and learns how to correlate the retrieval trademark image IRP and the trademark image RP by utilizing each classifieriAnd obtaining a machine learning model for searching the trademark image IRP.
4. The trademark retrieval system based on machine learning of claim 1, wherein in the second step, the steps (2) - (5) are formed into one round of authentication, the authentication is repeatedly executed t times, and in the execution process of one round of authentication, the retrieval proxy server IIS is used foriWithout authentication, the whole authentication process is terminated, i.e. the proxy server IIS is retrievediThe identity authentication of the security authentication system is not passed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110125561.4A CN112860934A (en) | 2021-01-29 | 2021-01-29 | Trademark retrieval system based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110125561.4A CN112860934A (en) | 2021-01-29 | 2021-01-29 | Trademark retrieval system based on machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112860934A true CN112860934A (en) | 2021-05-28 |
Family
ID=75986112
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110125561.4A Pending CN112860934A (en) | 2021-01-29 | 2021-01-29 | Trademark retrieval system based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112860934A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116522014A (en) * | 2023-07-03 | 2023-08-01 | 北京万合之众科技有限公司 | Data processing method and device |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150324469A1 (en) * | 2014-05-09 | 2015-11-12 | Thomson Reuters Global Resources | System and Methods for Automating Trademark and Service Mark Searches |
US20190114505A1 (en) * | 2016-04-14 | 2019-04-18 | Ader Bilgisayar Hizmetleri Ve Ticaret A.S. | Content based search and retrieval of trademark images |
CN111125418A (en) * | 2020-01-15 | 2020-05-08 | 广东工业大学 | Trademark retrieval system |
CN111428109A (en) * | 2020-03-25 | 2020-07-17 | 浙江知多多网络科技有限公司 | Patent early warning system based on patent big data machine learning |
CN111428111A (en) * | 2020-03-25 | 2020-07-17 | 浙江知多多网络科技有限公司 | Big data patent retrieval system based on deep learning |
CN111600713A (en) * | 2020-04-10 | 2020-08-28 | 张谷应 | Security protection system based on cloud computing server |
CN111611617A (en) * | 2020-05-12 | 2020-09-01 | 李黎莎 | Reading authentication management system based on intelligent power grid database |
CN111698216A (en) * | 2020-05-18 | 2020-09-22 | 陈程 | Data transmission system based on heterogeneous redundant transmission mechanism |
CN111695147A (en) * | 2020-05-13 | 2020-09-22 | 刘中恕 | Data security management system based on cloud storage technology |
CN111898114A (en) * | 2020-07-15 | 2020-11-06 | 浙江甬恒科技有限公司 | Intelligent early warning type intellectual property monitoring management platform |
-
2021
- 2021-01-29 CN CN202110125561.4A patent/CN112860934A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150324469A1 (en) * | 2014-05-09 | 2015-11-12 | Thomson Reuters Global Resources | System and Methods for Automating Trademark and Service Mark Searches |
US20190114505A1 (en) * | 2016-04-14 | 2019-04-18 | Ader Bilgisayar Hizmetleri Ve Ticaret A.S. | Content based search and retrieval of trademark images |
CN111125418A (en) * | 2020-01-15 | 2020-05-08 | 广东工业大学 | Trademark retrieval system |
CN111428109A (en) * | 2020-03-25 | 2020-07-17 | 浙江知多多网络科技有限公司 | Patent early warning system based on patent big data machine learning |
CN111428111A (en) * | 2020-03-25 | 2020-07-17 | 浙江知多多网络科技有限公司 | Big data patent retrieval system based on deep learning |
CN111600713A (en) * | 2020-04-10 | 2020-08-28 | 张谷应 | Security protection system based on cloud computing server |
CN111611617A (en) * | 2020-05-12 | 2020-09-01 | 李黎莎 | Reading authentication management system based on intelligent power grid database |
CN111695147A (en) * | 2020-05-13 | 2020-09-22 | 刘中恕 | Data security management system based on cloud storage technology |
CN111698216A (en) * | 2020-05-18 | 2020-09-22 | 陈程 | Data transmission system based on heterogeneous redundant transmission mechanism |
CN111898114A (en) * | 2020-07-15 | 2020-11-06 | 浙江甬恒科技有限公司 | Intelligent early warning type intellectual property monitoring management platform |
Non-Patent Citations (1)
Title |
---|
田崇峰等: "基于区域生长耦合多分类器的商标检索算法", 《包装工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116522014A (en) * | 2023-07-03 | 2023-08-01 | 北京万合之众科技有限公司 | Data processing method and device |
CN116522014B (en) * | 2023-07-03 | 2023-09-05 | 北京万合之众科技有限公司 | Data processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Fast range query processing with strong privacy protection for cloud computing | |
Zhang et al. | On efficient and robust anonymization for privacy protection on massive streaming categorical information | |
CN108900464A (en) | Electronic device, data processing method and computer storage medium based on block chain | |
CN108921696B (en) | Intelligent contract calling and contract transaction verification method based on block chain | |
CN109063138A (en) | For in block chain, that is, service platform search data method, equipment and storage medium | |
Arshad et al. | Efficient and scalable integrity verification of data and query results for graph databases | |
Papadopoulos et al. | Lightweight authentication of linear algebraic queries on data streams | |
CN110190969B (en) | User identity clone detection method and system in anonymous information system | |
Hu et al. | VERDICT: Privacy-preserving authentication of range queries in location-based services | |
Tong et al. | VFIRM: Verifiable fine-grained encrypted image retrieval in multi-owner multi-user settings | |
Hanmanthu et al. | SQL Injection Attack prevention based on decision tree classification | |
CN111835514A (en) | Method and system for realizing safe interaction of front-end and back-end separated data | |
CN110111218A (en) | A kind of software copyright managing and control system and method based on block chain | |
CN114996664B (en) | Digital copyright protection method based on block chain | |
Andola et al. | A secure searchable encryption scheme for cloud using hash-based indexing | |
Zhang et al. | LIAS: A lightweight incentive authentication scheme for forensic services in IoV | |
CN116324766A (en) | Optimizing crawling requests by browsing profiles | |
Zhang et al. | Privacy‐assured substructure similarity query over encrypted graph‐structured data in cloud | |
CN112860934A (en) | Trademark retrieval system based on machine learning | |
Etemad et al. | Database outsourcing with hierarchical authenticated data structures | |
CN110581841A (en) | Back-end anti-crawler method | |
CN111917760B (en) | Network collaborative manufacturing cross-domain fusion trust management and control method based on identification analysis | |
CN104038344B (en) | Identity authentication method based on regular expression | |
CN106888200A (en) | Mark correlating method, method for sending information and device | |
Lipp | A mechanised computational analysis of the wireguard virtual private network protocol |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210528 |
|
RJ01 | Rejection of invention patent application after publication |