CN110580301A - efficient trademark retrieval method, system and platform - Google Patents
efficient trademark retrieval method, system and platform Download PDFInfo
- Publication number
- CN110580301A CN110580301A CN201810589205.6A CN201810589205A CN110580301A CN 110580301 A CN110580301 A CN 110580301A CN 201810589205 A CN201810589205 A CN 201810589205A CN 110580301 A CN110580301 A CN 110580301A
- Authority
- CN
- China
- Prior art keywords
- trademark
- element library
- sub
- searched
- retrieval
- 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.)
- Withdrawn
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
the invention discloses a high-efficiency trademark retrieval method, a system and a platform, which are used for solving the technical problems of low retrieval efficiency and frequent occurrence of unsmooth in the prior art, and are applied to trademark query or approximate retrieval, wherein the method comprises the following steps of: acquiring a trademark sample, preprocessing, and identifying or extracting character parts and/or graphs of the trademark; establishing an element library according to the extracted text parts and/or the images; inputting a trademark needing to be searched by a user; matching a trademark the same as or similar to the input according to the input; searching in an element library according to the matched same or similar trademarks, if an element is searched, returning all searched elements, calling a trademark number corresponding to the searched element, and returning a search result according to the called trademark number; if the element is not searched, the information that the same or similar result is not searched is returned.
Description
Technical Field
The invention relates to the field of information retrieval, in particular to a method, a system and a platform for trademark inquiry or retrieval.
Background
Trademark is a kind of mark widely used in commerce to distinguish products and services, however, the value of a good trademark is not limited to only the function of distinguishing goods or services, but rather its influence and brand effect, which expresses quality, reputation and uniqueness. To obtain brand rights, registration with the trademark office is necessary. However, with the development of social economy, people have more and more contact with trademarks and have stronger consciousness of applying trademarks. At present, the application amount of trademarks increases year by year, particularly in the last two years, the application amount of trademarks is suddenly and violently increased, and the application amount in 2017 reaches 590 ten thousand, which is 54.96% on a par. By now the total trademark application volume has broken 2960 thousands of pieces. Since registration of a subsequent trademark is increasingly difficult due to application of numerous trademarks, and a trademark scheme that the applicant has spent a long time thinking may have been registered by others earlier, it is often desirable to search for a trademark at the time of trademark registration to determine whether a prospective scheme has been applied.
the ability of a brand to be registered is not dependent on whether there is a prior application for a completely identical scheme, but rather on the degree of similarity of the brand, i.e. only if all the similar brands to the proposed brand scheme are retrieved and compared to determine whether registration is possible.
however, the conventional search method is inefficient in searching, and particularly, when the search target has many similar trademarks, the system often has a search delay or is stuck.
Disclosure of Invention
the invention aims to provide a quick and effective trademark retrieval method aiming at trademarks, aiming at the problems that the retrieval efficiency is low and the blockage is easy to occur in the conventional trademark query or approximate retrieval process.
According to the technical scheme of the invention, the invention provides a trademark retrieval method, which comprises the following steps:
Step S101, acquiring a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
Step S102, establishing an element library according to the extracted character parts and/or the images; wherein, each element of the element library comprises all trademarks with the same identification characters or graphs;
Step S103, inputting a trademark needing to be searched by a user;
Step S104, searching in an element library, if the same elements as the input elements are searched, calling one or more trademark numbers corresponding to the elements, and returning trademark information corresponding to each trademark number, otherwise, returning the information without searching the same result;
wherein each element comprises one or more trademark numbers, and each trademark number corresponds to a unique trademark file.
According to the technical scheme of the invention, the invention provides a trademark retrieval method, which comprises the following steps:
Step S201, obtaining a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
Step S202, establishing an element library according to the extracted character parts and/or the images; wherein, each element of the element library comprises all trademarks with the same identification characters or graphs;
Step S203, inputting a trademark needing to be searched by a user;
Step S204, matching the same or similar trademark according to the input;
Step S205, searching in the element library according to the same or similar trademark, if an element is searched, returning the names of all searched elements, calling the trademark number corresponding to the searched element, and returning the search result according to the called trademark number; if the element is not searched, returning the information of which the same or similar result is not searched; wherein each element corresponds to at least one trademark number, and each trademark number corresponds to a unique trademark file.
According to the technical scheme of the invention, the element library can be further divided into a plurality of element libraries, such as a Chinese element library, a Pinyin element library, an English element library, a prefix element library, a graphic element library and the like. During retrieval, the user can select to retrieve in the corresponding element library according to the type input by the user, so that the retrieval efficiency is further improved.
according to the technical scheme of the invention, the obtaining mode of the approximate trademark is not limited, and any judgment mode of the approximate trademark determined according to the modes of sound, shape, meaning and the like can be used in the application.
according to the technical scheme of the invention, any mode of determining the similarity according to the grading mode and setting the similarity threshold value can be used for obtaining the approximate trademark in the application.
according to the technical scheme of the invention, any mode of presetting an approximate rule base or an approximate trademark base can be used for obtaining the approximate trademark of the application.
According to the technical scheme of the invention, the trademark query or search can be based on ES (elastic search), lucene or ES + lucene, so as to improve the search efficiency.
According to the technical scheme of the invention, the retrieval results are sorted according to a certain criterion, for example, the retrieval results can be sorted according to the approximation degree.
according to a technical solution of the present invention, there is provided a trademark retrieval system, characterized in that: the system comprises a preprocessing module, a database, a memory, an input module and a display module;
the preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
the database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises the identified or extracted character part and/or all the same trademarks, and each trademark corresponds to a unique number;
the processor is used for finishing data or information processing;
the input module is used for inputting retrieval contents by a user;
the display module is used for displaying the retrieval result;
A memory on which a program for conducting trademark retrieval is stored, wherein the program causes the processor to execute the steps of:
Searching the database according to the elements according to the search content input by the user, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, returning the search result to a display module according to the called trademark number, and displaying the searched trademark; if the same element is not searched, the information of the same result which is not searched is returned to the display module to be displayed.
according to a technical solution of the present invention, there is provided a trademark retrieval system, characterized in that: the system comprises a preprocessing module, a database, an approximate rule base, a processor, a memory, an input module and a display module;
the preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
the database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises all trademarks with the same recognized or extracted character parts and/or graphs, and each trademark corresponds to a unique number;
an approximate rule base: used for storing and updating approximate Chinese characters, pronunciation, trade names and the like;
the input module is used for inputting retrieval contents by a user;
The display module is used for displaying the retrieval result;
the processor is used for finishing data or information processing;
a memory having stored thereon a computer program for conducting trademark retrieval, wherein the computer program causes the computer to execute the steps of:
matching a result which is the same as or similar to the input content in the approximate rule base according to the retrieval content input by the user; searching the database according to the matched result by elements, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, and returning the corresponding trademark according to the called trademark number to be displayed on a display module as a searching result; if the same element is not searched, the information of which the same or similar result is not searched is returned to the display module to be displayed.
according to the technical scheme of the invention, the system further comprises a sorting module for sorting the retrieval results according to the approximation degree.
according to the technical scheme of the invention, the result displayed by the display module comprises information such as the name of a trademark, the registered class, the application date, the legal state and the like.
according to the technical scheme of the invention, the element library can be divided into a plurality of element libraries, such as a Chinese element library, a Pinyin element library, an English element library, a prefix element library, a graphic element library and the like. During retrieval, the user can select to retrieve in the corresponding element library according to the type input by the user, so that the retrieval efficiency is further improved. Wherein the prefix indicates a case that only one or more letters are included, but not pinyin or english.
the database may be a relational database or a non-relational database. The trademark query or search may be based on the ES (elastic search), lucene, or ES + lucene search engine.
Drawings
FIG. 1 is a flowchart of a method for searching for the same trademark according to an embodiment of the present invention
FIG. 2 is a flowchart of an approximate trademark retrieval method according to an embodiment of the present invention
FIG. 3 is a partial schematic view of the library of elements of the present invention
FIG. 4 is a same trademark retrieval system according to an embodiment of the present invention
FIG. 5 is an approximate trademark retrieval system of the embodiment of the present invention
FIG. 6 is an approximate trademark retrieval system according to another embodiment of the present invention
Detailed Description
In order to make the objects, technical solutions and innovations of the present invention clearer and clearer, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. It should be emphasized that the specific embodiments described herein are merely illustrative of the invention and are not limiting.
the invention provides a trademark retrieval method, which specifically comprises the following steps as shown in figure 1:
Step S101, acquiring a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
Since the constituents of the trademark mainly include characters, characters and images, and the characters and characters in the trademark are most easily recognized and are in a conventional form input by a user during trademark retrieval, all sample trademarks are acquired, and the character parts of the trademark are recognized or extracted and used as preprocessed data for subsequent use. The character recognition can also be used for uniformly recognizing characters of different ethnic groups, such as Chinese characters, Tibetan characters and the like. Graphics are important forms and content in trademarks, and parts of graphics are extracted and categorized for subsequent use. The classification of the figure may be divided and classified into a plurality of categories according to people, animals, buildings, natural phenomena, and the like, and the present invention is not particularly limited thereto.
Due to the update of the trademark data, it is necessary to periodically acquire or update the sample trademark and perform the recognition or extraction process of the character part.
Step S102, establishing an element library according to the extracted character parts and/or the extracted graphics, wherein each element of the element library comprises all trademarks with the same identification characters or graphics;
in the trademark retrieval, since each trademark can be registered into different classes, there is a case where trademarks having the same trademark name but belonging to different fields coexist; meanwhile, the font, position, etc. of the trademark may cause that there exist a plurality of corresponding trademarks although having the same character recognition result. In particular, some large enterprises may have multiple trademarks with the same or similar text portions, which are very inefficient and even deadly if searched through one-by-one tradition. Therefore, the element library concentrates trademarks with the same character recognition result or figure classification as one element, and searches in the element library, thereby greatly reducing the searching time. Through the establishment of the element library, the retrieval of each piece of data can be reduced from the original retrieval of more than ten thousand trademarks of 2960 to the retrieval of dozens or millions of elements. As another embodiment, the element library can be divided into a Chinese element library, an English element library, a Pinyin element library, a prefix element library and a graph database. Specifically, the selection may be made by the user upon input, or automatically recognized by a system setup program.
step S103, inputting a trademark needing to be searched by a user;
in particular, the user input may define or select input types including text, pinyin, English, text header, graphics, and the like. Of course, the type of user input may also be automatically recognized by the system.
and step S104, searching in the element library, if the same elements as the input elements are searched, calling one or more trademark numbers corresponding to the elements, and returning trademark information corresponding to each trademark number, otherwise, returning the information of which the same result is not searched.
Since the search is performed for each element in the element library, and the result of the search is only an element, it is also necessary to see through the trademark information obtained by the search based on one or more trademark data corresponding to the element. As another embodiment, in the searching in the element library, the searching may be performed in the element library corresponding to chinese, pinyin, english, graphics, word head, and the like according to the type selected by the user.
The invention provides a trademark retrieval method, which specifically comprises the following steps as shown in fig. 2:
Step S201, obtaining a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
Since the constituents of the trademark mainly include characters, characters and images, and the characters and characters in the trademark are most easily recognized and are in a conventional form input by a user during trademark retrieval, all sample trademarks are acquired, and the character parts of the trademark are recognized or extracted and used as preprocessed data for subsequent use. The classification of the figure may be performed according to a person, an animal, a building, a natural phenomenon, and the like, and is not particularly limited in the present application. Due to the update of the trademark data, it is necessary to periodically acquire or update the sample trademark and perform the recognition or extraction process of the character part.
step S202, establishing an element library according to the extracted character parts and/or the images;
in the trademark retrieval, since each trademark can be registered into different classes, there is a case where trademarks having the same trademark name but belonging to different fields coexist; meanwhile, the font, position, etc. of the trademark may cause that there exist a plurality of corresponding trademarks although having the same character recognition result. In particular, some large enterprises may have a plurality of trademarks with the same or similar text parts, which are very inefficient and even stuck if they are searched in a conventional manner in a one-by-one traversal. Therefore, the element library concentrates trademarks with the same character recognition result or figure classification as one element, and searches in the element library, thereby greatly reducing the searching time. As a specific embodiment, the component library may be divided into two or more component libraries to further improve the search efficiency. There may be a variety of division criteria, such as division including but not limited to Chinese, Pinyin, English, graphic, prefix element library. The Chinese element library can be further divided into a next-level element library such as simplified, traditional and Tibetan language, and specifically, the Chinese element library can be selected by a user during input or automatically identified by a system setting program.
Step S203, inputting a trademark needing to be searched by a user;
in particular, the user input may define or select input types including text, pinyin, English, text header, graphics, and the like. Of course, the type of user input may also be automatically recognized by the system.
step S204, matching the same or similar trademark according to the input;
according to the technical scheme of the invention, the acquisition mode of the approximate trademark is not limited, and any judgment mode of the approximate trademark determined according to the modes of sound, shape, meaning and the like can be used in the application; any method of determining the similarity according to the scoring method and setting the similarity threshold value can be used for obtaining the approximate trademark in the application; any way of presetting the approximate rule base or the approximate trademark base can be used for obtaining the approximate trademark of the application. The approximation rules may include exact identity, inclusion, arbitrary position insertion, arbitrary position increase and decrease, reverse order, etc.
Step S205, searching in the element library according to the same or similar trademark name, if an element is searched, returning the names of all searched elements, calling the trademark number corresponding to the searched element, and returning the search result according to the called trademark number; if the element is not searched, returning the information of which the same or similar result is not searched; wherein each element corresponds to at least one trademark, and each trademark corresponds to a unique trademark number.
According to the technical scheme of the invention, the obtaining mode of the approximate trademark is not limited, and any judgment mode of the approximate trademark determined according to the modes of sound, shape, meaning and the like can be used in the application.
according to the technical scheme of the invention, any mode of presetting an approximate rule base or an approximate trademark base can be used for obtaining the approximate trademark of the application.
according to the technical scheme of the invention, the database on which the search depends can be a relational database or a non-relational database. The relational database includes Oracle, DB2, Microsoft SQL Server, Microsoft Access, MySQL, etc. Non-relational databases include NoSql, Cloudant, and the like.
according to the technical scheme of the invention, the trademark inquiry or retrieval can be based on ES (elastic search), lucene or ES + lucene.
the ElasticSearch is a Lucene-based search server that provides a distributed multi-user capable full-text search engine. The Elasticisearch is developed by Java, issued as an open source code under Apache licensing terms, is a current popular enterprise-level search engine, designed to be used in cloud computing, capable of achieving real-time search, stable, reliable, fast and convenient to install and use. In addition, multi-value query and multi-value index can be supported, so that the retrieval efficiency is improved.
according to the technical scheme of the invention, the retrieval results are also sorted according to the approximation degree, and then the sorted retrieval results are displayed. Where the degree of approximation may be quantified as a specific score. As a specific embodiment, the score of the approximation degree may be calculated according to different approximation types, for example, the inclusion relation, the arbitrary position insertion, the inverse order, and the like, and the approximation degree may be quantized according to different calculation formulas, which is not limited in the present invention. According to the technical scheme of the invention, any mode of determining the similarity according to the grading mode and setting the similarity threshold value can be used for obtaining the approximate trademark in the application.
the element library is composed of a plurality of elements, each element corresponds to a unique element name, each element corresponds to at least one or more trademark numbers, and each trademark number corresponds to a unique trademark text. As shown in fig. 3, which is a specific example of the design of the element library, the element name 1 is followed by two trademark numbers CN00000001 and CN00000002, which correspond to a trademark a having a character recognition portion identical to the element name 1 and a trademark B having a character recognition portion identical to the element name 1, respectively.
furthermore, the element library of the present invention can be divided into a plurality of parts, for example, according to the character part and the graphic part, and the character part can be further divided into Chinese, pinyin, English, word head, etc.
according to the technical scheme of the invention, a trademark retrieval system is provided, as shown in fig. 4, which comprises a preprocessing module, a database, a processor, a memory, an input module and a display module;
The preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
Since the constituents of the trademark mainly include characters, and images, and the characters and characters in the trademark are most easily recognized and are also the conventional forms input by the user during the trademark retrieval, it is necessary to acquire all sample trademarks through the processing module, recognize or extract the character parts of the trademarks, and use them as preprocessed data for subsequent use. The classification of the figure may be performed according to a person, an animal, a building, a natural phenomenon, and the like, and is not particularly limited in the present application.
Due to the update of the trademark data, the preprocessing module needs to periodically acquire or update the sample trademark and perform the recognition or extraction processing of the text part.
The database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises the identified or extracted character part and/or all the same trademarks, and each trademark corresponds to a unique number;
The input module is used for inputting retrieval contents by a user;
As one example, the input module may be configured to be user-defined or user-selectable to input types including text, pinyin, English, text, graphics, and the like. As another embodiment, the input module has an automatic recognition function, which can automatically recognize the type to which the user input belongs.
The display module is used for displaying the retrieval result;
the processor is used for finishing data or information processing;
A memory having stored thereon a computer program for conducting trademark retrieval, wherein the computer program causes the processor to execute the steps of:
searching the database according to the elements according to the search content input by the user, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, and returning the search result to the display module to display the searched trademark according to the called trademark number; if the same element is not searched, the information of the same result which is not searched is returned to the display module to be displayed.
according to an aspect of the present invention, there is provided a trademark retrieval system, as shown in fig. 5, characterized in that: the system comprises a preprocessing module, a database, an approximate rule base, a processor, a memory, an input module and a display module;
The preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
The database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises all trademarks with the same recognized or extracted character parts and/or graphs, and each trademark corresponds to a unique number;
an approximate rule base: used for storing and updating approximate Chinese characters, pronunciation, trade names and the like;
The input module is used for inputting retrieval contents by a user;
The display module is used for displaying the retrieval result;
the processor is used for finishing data or information processing;
a memory having stored thereon a computer program for conducting trademark retrieval, wherein the computer program causes the processor to execute the steps of:
Matching a result which is the same as or similar to the input content in the approximate rule base according to the retrieval content input by the user; searching the database according to the matched result by elements, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, and returning the corresponding trademark according to the called trademark number to be displayed on a display module as a searching result; if the same element is not searched, the information of which the same or similar result is not searched is returned to the display module to be displayed.
According to the technical scheme of the invention, the obtaining mode of the approximate trademark is not limited, and any judgment mode of the approximate trademark determined according to the modes of sound, shape, meaning and the like can be applied to the application.
According to the technical scheme of the invention, any mode of presetting an approximate rule base or an approximate trademark base can be used for obtaining the approximate trademark of the application.
according to the technical scheme of the invention, the database on which the search depends can be a relational database or a non-relational database. Relational databases include Oracle, DB2, Microsoft SQL Server, Microsoft Access, MySQL, and the like. Non-relational databases include NoSql, Cloudant, and the like.
According to the technical scheme of the invention, the trademark inquiry or retrieval can be based on ES (elastic search), lucene or ES + lucene.
the ElasticSearch is a Lucene-based search server that provides a distributed multi-user capable full-text search engine. The Elasticisearch is developed by Java, issued as an open source code under Apache licensing terms, is a current popular enterprise-level search engine, designed to be used in cloud computing, capable of achieving real-time search, stable, reliable, fast and convenient to install and use. In addition, multi-value query and multi-value index can be supported, so that the retrieval efficiency is improved.
according to the technical scheme of the invention, as shown in fig. 6, the method further comprises the steps of sorting the retrieval results according to the approximation degree by a sorting module, and then displaying the sorted retrieval results. Where the degree of approximation may be quantified as a specific score. As a specific embodiment, the scores of the approximation degrees may be calculated according to different approximation types, for example, the similarity degrees are quantized according to different calculation formulas, such as exact identity, inclusion, arbitrary position insertion, arbitrary position increase and decrease, reverse order, and the like, and the specific quantization formula is not limited in the present invention.
according to the technical scheme of the invention, any mode of determining the similarity according to the grading mode and setting the similarity threshold value to screen the retrieval result can be used for acquiring the approximate trademark.
according to the technical scheme of the invention, the user can also input the screening conditions during retrieval, and the results meeting the conditions are screened according to the conditions input by the user before display. The display conditions include one or more of a brand classification, an application time, a bulletin option number, and a legal status. As a specific embodiment, the user can check the category of the trademark to be queried during the search, for example, select 9 categories, and the search results displayed should all contain the 9 th category trademark; the user may also check all or a number of categories.
According to the technical scheme of the invention, the user can print, export and share the retrieval result to friends such as QQ or WeChat.
according to the technical scheme of the invention, the trademark retrieval platform is provided, the functions of the trademark retrieval method or the trademark retrieval system can be realized through the platform, and meanwhile, the platform is also provided with a user authority management unit for managing the registration, login, authority, password and the like of a user.
as another embodiment, according to the technical solution of the present invention, the platform of the present invention is a cloud platform, and the same and similar retrieval of trademarks is realized based on cloud computing and cloud storage.
the present invention has been described above with reference to specific embodiments, which are provided to aid understanding of the concepts of the present invention. The invention is not restricted to the details of the above embodiments, but any simple modifications of the inventive concept fall within the scope of the invention.
In addition, it should be noted that the technical features disclosed in the above embodiments can be combined in any suitable way without contradiction, and all of them belong to the protection scope of the present invention.
Claims (27)
1. an information retrieval method is applied to trademark retrieval and is characterized by comprising the following steps:
Step S101, acquiring a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
step S102, establishing an element library according to the extracted character parts and/or the images; wherein, each element of the element library comprises all trademarks with the same identification characters or graphs;
step S103, inputting a trademark needing to be searched by a user;
Step S104, searching in an element library, if the same elements as the input elements are searched, calling one or more trademark numbers corresponding to the elements, and returning trademark information corresponding to each trademark number, otherwise, returning the information without searching the same result;
wherein each element corresponds to at least one trademark number, and each trademark number corresponds to a unique trademark file.
2. the information retrieval method according to claim 1, characterized in that:
The element library may be divided into a plurality of sub-element libraries;
the user can select the input type during inputting or the input type is automatically recognized by the system;
and searching in the corresponding sub-element library according to the input type.
3. the information retrieval method according to claim 2, characterized in that:
the sub-element library comprises a Chinese sub-element library, a pinyin sub-element library, an English sub-element library, a word head sub-element library and a graph sub-element library.
4. the information retrieval method according to claim 1 or 2, characterized in that:
the retrieval method is based on the elastic search, lucene or elastic search + lucene.
5. an information retrieval method is applied to trademark retrieval and is characterized by comprising the following steps:
step S201, obtaining a sample trademark, and identifying or extracting a character part and/or a graph of the trademark;
Step S202, establishing an element library according to the extracted character parts and/or the images; wherein, each element of the element library comprises all trademarks with the same identification characters or graphs;
step S203, inputting a trademark needing to be searched by a user;
Step S204, approximate matching, namely matching the same or similar trademark according to the input;
Step S205, searching in the element library according to the same or similar trademark, if an element is searched, returning the names of all searched elements, calling the trademark number corresponding to the searched element, and returning the search result according to the called trademark number; if the element is not searched, returning the information of which the same or similar result is not searched;
Wherein each element corresponds to at least one trademark number, and each trademark number corresponds to a unique trademark file.
6. The information retrieval method according to claim 5, characterized in that:
the element library may be divided into a plurality of sub-element libraries;
The user can select the input type during inputting or the input type is automatically recognized by the system;
And searching in the corresponding sub-element library according to the input type.
7. the information retrieval method according to claim 6, characterized in that:
The sub-element library comprises a Chinese sub-element library, a pinyin sub-element library, an English sub-element library, a word head sub-element library and a graph sub-element library.
8. the information retrieval method according to claim 7, characterized in that: the retrieval method is based on the elastic search, lucene or elastic search + lucene.
9. the information retrieval method according to any one of claims 5 to 7, characterized in that:
the user can select the trademark display condition during input, and when a result is searched, the trademark meeting the condition is screened according to the display condition and displayed.
10. The information retrieval method according to claim 9, characterized in that:
the display conditions include one or more of a trademark classification, an application time, a bulletin term number, and a legal status.
11. the information retrieval method according to any one of claims 5 to 7, characterized in that:
The search results are also sorted by degree of approximation before display.
12. the information retrieval method according to claim 11, characterized in that:
The sorting comprises the following steps:
Respectively setting different calculation modes according to different approximation types to quantize specific approximation scores, wherein the approximation types comprise the exact same, the inclusion, the insertion of any position, the increase and decrease of any position or the reverse order;
Filtering to obtain trademarks with the similarity exceeding a preset threshold;
And sorting the trademarks obtained by filtering according to the scores of the similarity.
13. an information retrieval system is applied to trademark retrieval, and is characterized in that: the system comprises a preprocessing module, a database, a memory, a processor, an input module and a display module;
The preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
The database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises all trademarks with the same recognized or extracted character parts or figures, and each trademark corresponds to a unique number;
The input module is used for inputting retrieval contents by a user;
The display module is used for displaying the retrieval result;
A memory on which a program for conducting trademark retrieval is stored, wherein the program causes the processor to execute the steps of:
Searching the database according to the elements according to the search content input by the user, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, and returning the search result to the display module to display the searched trademark according to the called trademark number; if the same element is not searched, the information of the same result which is not searched is returned to the display module to be displayed.
14. The information retrieval system as recited in claim 13, wherein:
the element library may be divided into a plurality of sub-element libraries;
the user can select the input type during inputting or the input type is automatically recognized by the system;
and searching in the corresponding sub-element library according to the input type.
15. the information retrieval system of claim 14, wherein:
The sub-element library comprises a Chinese sub-element library, a pinyin sub-element library, an English sub-element library, a word head sub-element library and a graph sub-element library.
16. The information retrieval system as recited in claim 15, wherein:
the retrieval system is based on the elastic search, lucene or elastic search + lucene.
17. an information retrieval system is applied to trademark retrieval, and is characterized in that: the system comprises a preprocessing module, a database, an approximate rule base, a processor, a memory, an input module and a display module;
the preprocessing module is used for acquiring all sample trademarks and identifying or extracting character parts and/or graphs of the trademarks;
The database is used for storing the extracted trademark data, wherein the trademark data is classified and stored according to an element library, each element of the element library comprises all trademarks with the same recognized or extracted character parts or figures, and each trademark corresponds to a unique number;
an approximate rule base: used for storing and updating approximate Chinese characters, pronunciation, trade names and the like;
the input module is used for inputting retrieval contents by a user;
The display module is used for displaying the retrieval result;
The processor is used for finishing data or information processing;
A memory on which a program for conducting trademark retrieval is stored, wherein the program causes the processor to execute the steps of:
matching a result which is the same as or similar to the input content in the approximate rule base according to the retrieval content input by the user; searching the database according to the matched result by elements, if the same element is searched, returning the name of the searched element, calling the numbers of a plurality of trademarks corresponding to the element, and returning the corresponding trademark according to the called trademark number to be displayed on a display module as a searching result; if the same element is not searched, the information of which the same or similar result is not searched is returned to the display module to be displayed.
18. the information retrieval system as recited in claim 17, wherein:
The element library may be divided into a plurality of sub-element libraries;
The user can select the input type during inputting or the input type is automatically recognized by the system;
and searching in the corresponding sub-element library according to the input type.
19. the information retrieval system of claim 18, wherein:
The sub-element library comprises a Chinese sub-element library, a pinyin sub-element library, an English sub-element library, a word head sub-element library and a graph sub-element library.
20. The information retrieval system as recited in claim 19, wherein: the retrieval method is based on the elastic search, lucene or elastic search + lucene.
21. An information retrieval system as claimed in any one of claims 17 to 20 wherein:
the user can select the trademark display condition during input, and when a result is searched, the trademark meeting the condition is screened according to the display condition and displayed.
22. The information retrieval system as recited in claim 21, wherein:
the display conditions include one or more of a trademark classification, an application time, a bulletin term number, and a legal status.
23. an information retrieval system as claimed in any one of claims 17 to 20 wherein:
The system comprises a sorting module which sorts the retrieval results according to the approximation degree before displaying.
24. The information retrieval system as recited in claim 23, wherein:
The sorting module respectively quantizes the specific approximate scores according to different approximate types and filters the specific approximate scores to obtain trademarks of which the approximation degrees exceed a preset threshold;
wherein the approximate types include exact identity, inclusion, arbitrary position insertion, arbitrary position increase or decrease, or reverse order.
25. An information retrieval system as claimed in any one of claims 17 to 20 wherein:
and a unit for printing, exporting and sharing the retrieval result to the QQ or the WeChat friend is also arranged.
26. a trademark retrieval platform comprising the information retrieval system as recited in any one of claims 17 to 20, wherein: the platform is also provided with a user authority management unit for managing the registration, login, authority, password and the like of the user.
27. The platform of claim 26, wherein: the platform is a cloud platform, and the same or similar retrieval of trademarks is realized based on cloud computing and cloud storage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810589205.6A CN110580301A (en) | 2018-06-08 | 2018-06-08 | efficient trademark retrieval method, system and platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810589205.6A CN110580301A (en) | 2018-06-08 | 2018-06-08 | efficient trademark retrieval method, system and platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110580301A true CN110580301A (en) | 2019-12-17 |
Family
ID=68808942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810589205.6A Withdrawn CN110580301A (en) | 2018-06-08 | 2018-06-08 | efficient trademark retrieval method, system and platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110580301A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125418A (en) * | 2020-01-15 | 2020-05-08 | 广东工业大学 | Trademark retrieval system |
| CN113157960A (en) * | 2021-02-25 | 2021-07-23 | 北京金堤科技有限公司 | Method and device for acquiring similar data, electronic equipment and computer readable storage medium |
| CN115329319A (en) * | 2022-08-31 | 2022-11-11 | 重庆市规划和自然资源信息中心 | Spatial operator searching system based on elastic search technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006065651A (en) * | 2004-08-27 | 2006-03-09 | Toshiba Corp | Program, apparatus and method for retrieving trademark name |
| CN104636428A (en) * | 2014-12-24 | 2015-05-20 | 四川超凡知识产权服务股份有限公司 | Trademark recommendation method and device |
| CN104809142A (en) * | 2014-01-29 | 2015-07-29 | 北京瑞天科技有限公司 | Trademark inquiring system and method |
| CN107563720A (en) * | 2017-08-07 | 2018-01-09 | 深圳益强信息科技有限公司 | The method of trademark application based on big data and artificial intelligence |
-
2018
- 2018-06-08 CN CN201810589205.6A patent/CN110580301A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006065651A (en) * | 2004-08-27 | 2006-03-09 | Toshiba Corp | Program, apparatus and method for retrieving trademark name |
| CN104809142A (en) * | 2014-01-29 | 2015-07-29 | 北京瑞天科技有限公司 | Trademark inquiring system and method |
| CN104636428A (en) * | 2014-12-24 | 2015-05-20 | 四川超凡知识产权服务股份有限公司 | Trademark recommendation method and device |
| CN107563720A (en) * | 2017-08-07 | 2018-01-09 | 深圳益强信息科技有限公司 | The method of trademark application based on big data and artificial intelligence |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125418A (en) * | 2020-01-15 | 2020-05-08 | 广东工业大学 | Trademark retrieval system |
| CN113157960A (en) * | 2021-02-25 | 2021-07-23 | 北京金堤科技有限公司 | Method and device for acquiring similar data, electronic equipment and computer readable storage medium |
| CN115329319A (en) * | 2022-08-31 | 2022-11-11 | 重庆市规划和自然资源信息中心 | Spatial operator searching system based on elastic search technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144723B (en) | Person post matching recommendation method, system and storage medium | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| JP6893209B2 (en) | Automatic interpretation of structured multifield file layout | |
| CA2836220C (en) | Methods and systems for matching records and normalizing names | |
| CN111105209B (en) | Job resume matching method and device suitable for person post matching recommendation system | |
| CN110929125B (en) | Search recall method, device, equipment and storage medium thereof | |
| CN111859195A (en) | Information display method, information search method and device | |
| CN104809142A (en) | Trademark inquiring system and method | |
| CN111353014B (en) | Position keyword extraction and position demand updating method and device | |
| CN111767716A (en) | Method and device for determining enterprise multilevel industry information and computer equipment | |
| CA3138556A1 (en) | Apparatuses, storage medium and method of querying data based on vertical search | |
| CN110580301A (en) | efficient trademark retrieval method, system and platform | |
| CN110209659A (en) | A kind of resume filter method, system and computer readable storage medium | |
| CN112395881A (en) | Material label construction method and device, readable storage medium and electronic equipment | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| KR100876214B1 (en) | Apparatus and method for context aware advertising and computer readable medium processing the method | |
| EP3301603A1 (en) | Improved search for data loss prevention | |
| US20120278356A1 (en) | Resembling character-code-group search supporting method, resembling candidate extracting method, and resembling candidate extracting apparatus | |
| CN117077668A (en) | Risk image display method, apparatus, computer device, and readable storage medium | |
| CN111104422A (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN112559324B (en) | Software test case generation method based on in-application visual mining | |
| CN110888894A (en) | Patent search method, server and computer readable medium | |
| CN107885808B (en) | Shared resource file anti-cheating method | |
| US9846739B2 (en) | Fast database matching | |
| US8498988B2 (en) | Fast search |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191217 |