CN112417195A

CN112417195A - Trademark inquiry system and method based on mobile terminal and storage medium

Info

Publication number: CN112417195A
Application number: CN202011371529.6A
Authority: CN
Inventors: 徐庆; 林丹燕
Original assignee: Miangu Image Technology Foshan Research Center; Foshan Guofang Identification Technology Co Ltd
Current assignee: Miangu Image Technology Foshan Research Center; Foshan Guofang Identification Technology Co Ltd
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2021-02-26

Abstract

The application provides a trademark inquiry system and method based on a mobile terminal and a storage medium. The system comprises: the system comprises a user side, a server, an image processor and a retrieval keyword processor, wherein the user side executes the following processing: the user side shoots a target trademark picture or selects the target trademark picture stored in the user side to obtain the target trademark picture to be inquired; carrying out trademark graphic element coding and/or automatic identification processing of retrieval character information and image feature extraction processing on the target trademark picture; confirming or editing and correcting the corresponding trademark graphic element codes and/or retrieval character information, and sending a trademark inquiry request to a server; performing word segmentation processing on target trademark retrieval information of the request data, and performing combination processing on word segmentation of various trademark data to obtain retrieval keywords; and performing matching search by taking the search key words as search conditions. The method and the device can effectively improve the recall ratio and the precision ratio of trademark inquiry.

Description

Trademark inquiry system and method based on mobile terminal and storage medium

Technical Field

The application relates to the technical field of trademark information query, in particular to a trademark query system and method based on a mobile terminal and a storage medium.

Background

Trademark inquiry is a very important task in trademark management, and according to the provisions of the fourth article of trademark law and the thirteenth article of regulations on trademark law, a natural person, a legal person or other organization needs to obtain trademark exclusive rights for its commodities or services in production and operation activities, and shall apply for trademark registration with the national intellectual property office. Generally, in order to obtain a high success rate of registering a trademark application, the applicant should perform trademark inquiry before submitting the trademark application to know the prior rights, and then decide whether to submit the trademark application after making a judgment according to the inquiry result. In the process of managing the trademark, the right condition of a certain trademark also needs to be known, and decision bases are provided for various activities of implementing the strategy of the enterprise trademark.

The existing trademark inquiry method and system mainly have two types: firstly, trademark query of input text, namely trademark information query performed by taking input text characters or characters as retrieval keywords, namely the traditional trademark query method; the second is trademark query by inputting trademark pictures, that is, by taking uploaded trademark pictures as search input, extracting image features of the pictures and performing trademark information query by taking the image features as search keywords, which is a novel trademark query method.

However, the above methods do not satisfy the application requirements for the recall ratio and precision ratio of trademarks.

In view of the above problems, no effective technical solution exists at present.

Disclosure of Invention

An object of the embodiments of the present application is to provide a mobile-end-based trademark query system, method, and storage medium, which can improve the recall ratio and precision ratio of trademarks.

In a first aspect, an embodiment of the present application provides a mobile-end-based trademark query system, including: the system comprises a user side, a server, an image processor and a retrieval keyword processor, wherein the user side is connected with the server through a wireless network or the Internet, and the server is connected with the image processor and the retrieval keyword processor through a local area network or the Internet and executes the following processing:

the user side is used for shooting a target trademark picture or selecting the target trademark picture stored in the user side to obtain the target trademark picture to be inquired;

the user side sends the target trademark picture to be inquired to the server, and the server receives the target trademark picture to be inquired and then instructs the image processor to perform feature extraction processing on the target trademark picture to be inquired, so that at least one or more of the following combinations corresponding to the target trademark picture to be inquired is obtained: coding the trademark graphic elements, retrieving the text information and the image feature descriptors, and sending the trademark graphic elements to the user side;

the user side confirms, edits, corrects or enters the trademark graphic element code and/or retrieval character information corresponding to the target trademark picture to be inquired, takes the trademark graphic element code and/or retrieval character information and the image feature descriptor after confirmation, editing, correction or entry processing as target trademark retrieval information to be inquired, and feeds back the target trademark retrieval information to the server and sends out a trademark inquiry request;

after the server receives a trademark inquiry request, instructing an image processor to perform word segmentation processing on target trademark retrieval information to be inquired of the trademark inquiry request, wherein the word segmentation processing comprises performing word segmentation processing on the retrieval character information to obtain character type trademark data words, performing word segmentation processing on the trademark graphic element codes to obtain trademark graphic element code type trademark data words, and performing word segmentation processing on the image feature descriptors to obtain image feature type trademark data words;

after the server receives the processed various trademark data participles, the server instructs a retrieval keyword processor to combine and process the various trademark data participles to obtain a retrieval keyword, wherein the retrieval keyword comprises at least one image characteristic type trademark data participle, and the retrieval keyword also comprises at least one trademark graphic element coding type trademark data participle and/or at least one character type trademark data participle, and the various trademark data participles comprise: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle;

and after receiving the returned search keywords, the server performs matching search by taking the search keywords as search conditions, finds out a sample trademark matched with any search keyword, obtains trademark search result data, and sends the trademark search result data to the user side for display.

Optionally, the server comprises an application service manager and a trademark retrieval server;

the application service manager is used for receiving a trademark query request with trademark retrieval information input by the user side, calling related trademark retrieval result data from the trademark retrieval server according to the trademark query request, and sending the trademark retrieval result data to the user side;

and the trademark retrieval server is used for performing matching retrieval by taking the retrieval keywords as retrieval conditions, finding out a sample trademark matched with any retrieval keyword, and obtaining trademark retrieval result data.

Optionally, the user side includes a mobile phone and other devices connected to the server through a wireless network or the internet, and further includes a computer logged in through the mobile phone or the wireless device.

Optionally, before obtaining the target trademark picture to be queried, the user further performs trademark area judgment and clipping processing on the captured target trademark picture or the target trademark picture selectively stored in the user, so as to obtain the target trademark picture to be queried.

The image feature descriptor corresponding to the target trademark picture to be inquired comprises at least one of the following:

image contour feature descriptors, image skeleton line feature descriptors, image texture-based feature descriptors, image shape-based feature descriptors, image color-based feature descriptors, and image convolutional neural network feature descriptors.

Optionally, the image processor performs word segmentation processing on the image feature descriptor to obtain image feature class trademark data word segmentation, including: segmenting multiple kinds and multiple groups of image feature descriptors in the target trademark retrieval information to be queried according to each extraction algorithm and/or each group of image feature descriptors to obtain segmented local image feature descriptor information, and using the segmented local image feature descriptor information as image feature descriptor trademark data participles;

the image processor performs word segmentation processing on the retrieval character information to acquire word type trademark data word segmentation, and the word type trademark data word segmentation processing comprises the following steps: and (3) dividing the following items or local parts of the items in the target trademark retrieval information to be inquired: chinese characters, letters and combinations thereof, numbers and combinations thereof, symbols and combinations thereof to obtain segmented information, and using the segmented information as word division of the character trademark data;

the image processor carries out word segmentation processing on the trademark graphic element codes to obtain trademark graphic element code type trademark data word segmentation, and the word segmentation processing comprises the following steps: dividing a plurality of groups of trademark graphic element codes in target trademark retrieval information to be inquired into each group to obtain divided trademark graphic element code information, and dividing the divided trademark graphic element code information into trademark graphic element code class trademark data participles.

Optionally, the word-class trademark data word segmentation includes: taking a set of all characters contained in the target trademark obtained by the identification processing or the input processing of the target trademark picture to be inquired as an integral retrieval character participle, and taking each character in the integral character participle independently as a local retrieval character participle;

the trademark graphic element coding type trademark data word segmentation comprises the following steps: the method comprises the steps that a set of two or more sets of trademark graphic element codes obtained by identifying and processing a plurality of objects described by a target trademark picture to be inquired is used as an integral trademark graphic element code participle, each set of trademark graphic element codes in the integral trademark graphic element code participle are separated out to be used as a local trademark graphic element code participle, and the local trademark graphic element code participle is used for describing single and different objects;

the image feature class trademark data word segmentation comprises the following steps: and taking the set of all image feature descriptors extracted from the target trademark picture to be inquired as an integral image feature descriptor participle, and independently taking each group of partial image feature descriptors with local features in the integral image feature descriptor participle as a local image feature descriptor participle, wherein the local image feature descriptor participle is used for describing local features in the target trademark picture to be inquired.

Optionally, the search keyword processor performs combination processing on the participles of various trademark data to obtain the search keyword, and the method includes the following steps: and carrying out combined processing on the overall search word segmentation, the local search word segmentation, the overall trademark graphic element coding segmentation, the local trademark graphic element coding segmentation, the overall image feature descriptor segmentation and the local image feature descriptor segmentation to obtain a search keyword.

In a second aspect, an embodiment of the present application further provides a mobile-end-based trademark query method, which is applied to a user end, and includes:

s110, shooting a target trademark picture or selecting the target trademark picture stored at a user side, and judging and cutting a trademark area of the target trademark picture to obtain the target trademark picture to be inquired;

s120, the target trademark picture to be inquired is sent to the server, the characteristic extraction processing is requested to be carried out on the target trademark picture to be inquired, and at least one or more of the following combinations corresponding to the target trademark picture to be inquired is obtained: trademark graphic element coding, retrieving text information and image feature descriptors;

s130, confirming, editing, correcting or inputting the returned trademark graphic element codes and/or retrieval character information corresponding to the target trademark picture to be inquired, taking the trademark graphic element codes and/or retrieval character information subjected to the confirmation, editing, correction or inputting as target trademark retrieval information to be inquired, feeding back the target trademark retrieval information to the server and sending a trademark inquiry request;

and S140, receiving and displaying the trademark search result data returned by the server.

In a third aspect, an embodiment of the present application further provides a mobile-terminal-based trademark query method, which is applied to a server, and includes:

s210, receiving a target trademark picture to be inquired transmitted by a user side and a feature extraction processing request for the target trademark picture to be inquired, instructing an image processor to perform feature extraction processing on the target trademark picture to be inquired, and acquiring at least one or more combinations of the following items corresponding to the target trademark picture to be inquired: coding the trademark graphic elements, retrieving the text information and the image feature descriptors, and sending the trademark graphic elements to the user side;

s220, receiving a trademark query request with target trademark retrieval information to be queried, which is sent by a user side, wherein the target trademark retrieval information to be queried comprises trademark graphic element codes and/or retrieval character information and image feature descriptors which are confirmed, edited, corrected or input by the user side; instructing an image processor to perform word segmentation processing on target trademark retrieval information to be queried of the trademark query request, wherein the word segmentation processing is performed on the retrieval character information to obtain word type trademark data word segmentation, the word segmentation processing is performed on the trademark graphic element codes to obtain trademark graphic element code type trademark data word segmentation, and the word segmentation processing is performed on the image feature descriptors to obtain image feature type trademark data word segmentation;

s230, after receiving the processed trademark data participles returned by the image processor, instructing the search keyword processor to perform combination processing on the trademark data participles to obtain a search keyword, where the search keyword includes at least one image feature type trademark data participle, and the search keyword also includes at least one trademark graphic element encoding type trademark data participle and/or at least one text type trademark data participle, where the trademark data participles include: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle;

and S240, after receiving the search keywords returned by the search keyword processor, performing matching search by using the search keywords as search conditions, finding out a sample trademark matched with any search keyword to obtain trademark search result data, and sending the trademark search result data to a user side for display.

In a fourth aspect, an embodiment of the present application further provides a mobile terminal-based trademark query method, applied to an image processor, including:

s310, receiving a target trademark picture to be inquired transmitted by a server, and performing feature extraction processing on the target trademark picture to be inquired according to an instruction to obtain at least one or more combinations of the following items corresponding to the target trademark picture to be inquired: coding the trademark graphic elements, retrieving the text information and the image characteristic descriptors and feeding back the character information and the image characteristic descriptors to the server;

s320, receiving a trademark query request which is transmitted by a server and carries target trademark retrieval information to be queried, wherein the target trademark retrieval information to be queried comprises trademark graphic element codes and/or retrieval character information and image feature descriptors which are confirmed or edited and corrected or input by a user side; performing word segmentation on target trademark retrieval information to be queried of the trademark query request, including performing word segmentation on the retrieval character information, acquiring character type trademark data words, performing word segmentation on the trademark graphic element codes, acquiring trademark graphic element code type trademark data words, performing word segmentation on the image feature descriptors, acquiring image feature type trademark data words, and feeding back the acquired character type trademark data words, trademark graphic element code type trademark data words and image feature type trademark data words to a server.

In a fifth aspect, an embodiment of the present application further provides a mobile-end-based trademark query method, which is applied to a search keyword processor, and includes:

receiving various processed trademark data participles transmitted by a server, combining the various trademark data participles according to an instruction, acquiring a search keyword and feeding the search keyword back to the server, wherein the search keyword comprises at least one image characteristic type trademark data participle, and the search keyword also comprises at least one trademark graphic element coding type trademark data participle and/or at least one character type trademark data participle, and the various trademark data participles comprise: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle.

In a sixth aspect, embodiments of the present application provide a storage medium, on which a computer program is stored, where the computer program runs the steps in the method provided in the second to fifth aspects when executed by a processor.

As can be seen from the above, in the trademark query system, method and storage medium based on a mobile terminal provided in the embodiment of the present application, the target trademark picture is photographed by the user terminal or the target trademark picture stored in the user terminal is selected, and the trademark area of the target trademark picture is determined and cut to obtain the target trademark picture to be queried; carrying out trademark graphic element coding and/or retrieval text information automatic identification processing and image feature extraction processing on the target trademark picture to be inquired to obtain the trademark graphic element coding and/or retrieval text information and image feature descriptors corresponding to the target trademark picture to be inquired; confirming or editing and correcting or inputting the corresponding trademark graphic element codes and/or retrieval character information, taking the confirmed or edited and corrected or inputted trademark graphic element codes and/or retrieval character information and the image feature descriptors as target trademark retrieval information to be queried, and sending a trademark query request to the server; performing word segmentation processing on target trademark retrieval information to be queried of the trademark query request to obtain word type trademark data word segmentation, trademark graphic element coding type trademark data word segmentation and image characteristic type trademark data word segmentation; combining the various trademark data participles to obtain search keywords; matching and searching by taking the search keywords as search conditions, finding out a sample trademark matched with any search keyword, and obtaining trademark search result data; thereby improving the recall ratio and the precision ratio of the trademark.

Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a schematic structural diagram of a mobile-end-based trademark query system according to an embodiment of the present disclosure.

Fig. 2 is a flowchart of a mobile-end-based trademark query method applied to a ue according to an embodiment of the present application.

Fig. 3 is a flowchart of a mobile-side based trademark query method applied to a server according to an embodiment of the present application.

Fig. 4 is a flowchart of a mobile-end-based trademark query method applied to an image processor according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

In a first specific embodiment, the present application provides a mobile terminal-based trademark query system, please refer to fig. 1, where fig. 1 is a schematic structural diagram of the mobile terminal-based trademark query system according to an embodiment of the present application, including: the system comprises a user end 201, a server 202, an image processor 203 and a retrieval keyword processor 204, wherein the user end 201 is connected with the server 202 through a wireless network or the Internet, and the server 202 is connected with the image processor 203 and the retrieval keyword processor 204 through a local area network or the Internet and executes the following processing:

the user terminal 201 is used for shooting a target trademark picture or selecting the target trademark picture stored in the user terminal 201 to obtain the target trademark picture to be inquired.

In some embodiments, the processing performed by the user terminal 201 may include: shooting a target trademark picture or selecting a target trademark picture stored in the user side 201; and cutting the target trademark picture to obtain the target trademark picture to be inquired. The target trademark picture comprises some backgrounds, shadings, watermarks and the like besides the target trademark image, and the image obtained through cutting only has the target trademark image and can be used as the target trademark picture to be inquired. In practical application, in general, during the photographing process, the area of the photograph is not equal to the area of the trademark image, but also includes the area of the non-trademark image, if these areas also enter the trademark retrieval, the accuracy of the trademark retrieval result is affected, in general, in practical application, the photograph needs to be cut, and after editing and cutting, the cut input target trademark picture is confirmed as the target trademark picture to be queried for the trademark retrieval. The scheme of the application uses the mobile terminal to dynamically acquire the target trademark picture to be retrieved in real time, can effectively overcome the limitation that the trademark inquiring system in the prior art can only upload the locally stored picture on a computer in an office place through the Internet to acquire the input of trademark inquiry, can acquire the retrieved original trademark picture in real time anytime and anywhere in any place where a mobile phone can use, and can edit and cut the original trademark picture in real time to acquire the target trademark picture to be retrieved, thereby bringing great convenience for trademark practitioners to retrieve trademarks.

The user 201 sends the target trademark picture to be queried to the server 202, and after receiving the target trademark picture to be queried, the server 202 instructs the image processor 203 to perform feature extraction processing on the target trademark picture to be queried, so as to obtain at least one or more combinations of the following items corresponding to the target trademark picture to be queried: and (3) coding the trademark graphic elements, retrieving the text information and the image characteristic descriptors, and sending the character information and the image characteristic descriptors to the user side 201.

Wherein, the trademark figure element code is a code generated according to the requirements of the International Classification Vienna protocol for establishing trademark figure elements.

It is understood that the characters in the target trademark image can be recognized by adopting an image character recognition method commonly used in the prior art, so as to obtain the retrieval character information. The retrieval character information is obtained by performing character recognition on the target trademark image, so that the entry of the retrieval character information can be more comprehensive (if the user only inputs the retrieval character information manually, the retrieval character information is probably incomplete due to different factors such as user operation, character expression and the like), and a more comprehensive retrieval result can be obtained according to the more comprehensive retrieval character information.

It will be appreciated that the brand graphic element code may be manually entered by the user in a corresponding input interface, for example by the user typing the brand graphic element code in a corresponding input box (the input interface may also directly provide a list of standard brand graphic element codes to facilitate the user's selection by clicking). In some embodiments, the image element codes are obtained by performing image element code recognition on the target trademark images, so that the entry of the image element codes can be more comprehensive (if the user only manually inputs the image element codes, the image element codes are likely to be inaccurate due to different factors such as user operation, insufficient cognition on the image element codes and the like), and thus, more accurate retrieval results are obtained according to the more accurate image element codes.

The user 201 confirms, edits, corrects or enters the trademark graphic element code and/or retrieval character information corresponding to the target trademark picture to be inquired, uses the trademark graphic element code and/or retrieval character information and the image feature descriptor after confirmation, editing, correction or entry processing as the target trademark retrieval information to be inquired, and feeds back to the server 202 and sends out a trademark inquiry request.

In practical application, the trademark retrieval information (such as retrieval character information, trademark graphic element codes and/or trademark pictures) is input in the manner, and the trademark retrieval information can be displayed in a trademark inquiry application program interface for the user to edit and confirm, and the user can also input new trademark retrieval information. In this way, interaction with a trademark inquiry software user is realized, and the trademark inquiry software user is generally a trademark professional practitioner, and in this embodiment, by providing auxiliary identification information (for example, acquiring the input trademark retrieval information in the above manner), the trademark inquiry software user can edit and confirm the above trademark retrieval information according to the own inquiry requirement to confirm the final trademark retrieval information (i.e., the target trademark retrieval information to be inquired), so as to effectively ensure the accuracy of the keyword input by the trademark retrieval, and thus the comprehensiveness of the trademark retrieval can be improved.

After the server 202 receives the trademark query request, the image processor 203 is instructed to perform word segmentation on target trademark retrieval information to be queried of the trademark query request, including performing word segmentation on retrieval character information, acquiring character trademark data words, performing word segmentation on trademark graphic element codes, acquiring trademark graphic element code trademark data words, and performing word segmentation on image feature descriptors to acquire image feature trademark data words.

In order to obtain better recall ratio and precision ratio of trademark retrieval, the key factor in trademark query is correctly determined as the keyword of trademark query. In practical application, text trademark data participles, trademark graphic element coding trademark data participles and image characteristic trademark data participles need to be combined respectively to achieve the effect of improving the trademark retrieval keywords.

After the server 202 receives the processed various trademark data participles, the server instructs the search keyword processor 204 to perform combination processing on the various trademark data participles to obtain a search keyword, wherein the search keyword comprises at least one image characteristic type trademark data participle, and the search keyword also comprises at least one trademark graphic element coding type trademark data participle and/or at least one character type trademark data participle, and the various trademark data participles comprise: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle.

After receiving the returned search keyword, the server 202 performs matching search using the search keyword as a search condition, finds a sample trademark matching any search keyword, obtains trademark search result data, and sends the trademark search result data to the user side 201 for display.

In the mobile terminal-based trademark inquiry system, the server 202 comprises an application service manager and a trademark retrieval server;

the application service manager is used for receiving an inquiry request with trademark retrieval information input by the user terminal 201, calling related trademark retrieval result data from the trademark retrieval server according to the inquiry request, and sending the trademark retrieval result data to the user terminal 201;

the trademark retrieval server is used for performing matching retrieval by taking the retrieval keywords as retrieval conditions, finding out a sample trademark matched with any retrieval keyword, and obtaining trademark retrieval result data.

In the mobile-terminal-based trademark inquiry system, the user terminal 201 includes a mobile phone and other devices connected to the server 202 via a wireless network or the internet, and further includes a computer that scans a code and logs in via the mobile phone or the wireless device.

In the trademark inquiring system based on the mobile terminal, the image feature descriptor corresponding to the target trademark picture to be inquired comprises at least one of the following:

In the trademark query system based on the mobile terminal, the image processor 203 performs segmentation processing on the image feature descriptors to obtain image feature trademark data segmentation, and the segmentation processing includes: and segmenting multiple kinds and groups of image feature descriptors in the target trademark retrieval information to be queried according to each extraction algorithm and/or each group of image feature descriptors to obtain segmented local image feature descriptor information, and taking the segmented local image feature descriptor information as image feature descriptor trademark data participles.

The image processor 203 performs word segmentation processing on the retrieved text information to obtain word type trademark data word segmentation, and the word type trademark data word segmentation processing includes: and (3) dividing the following items or local parts of the items in the target trademark retrieval information to be inquired: chinese characters, letters and combinations thereof, numbers and combinations thereof, symbols and combinations thereof, and obtaining segmented information, wherein the segmented information is used as word division of the character trademark data.

The image processor 203 carries out word segmentation processing on the trademark graphic element codes to obtain trademark data word segmentation of the trademark graphic element codes, and the word segmentation processing comprises the following steps: dividing a plurality of groups of trademark graphic element codes in target trademark retrieval information to be inquired into each group to obtain divided trademark graphic element code information, and dividing the divided trademark graphic element code information into trademark graphic element code class trademark data participles.

In the mobile-end-based trademark query system, after the server 202 receives the various trademark data participles after processing, the search keyword processor 204 is instructed to combine and process the various trademark data participles to obtain a search keyword, wherein the search keyword comprises at least one image feature type trademark data participle, and the search keyword also comprises at least one trademark graphic element coding type trademark data participle and/or at least one text type trademark data participle, and wherein the various trademark data participles comprise: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle.

The method comprises the steps of respectively carrying out word segmentation on retrieval character information, trademark graphic element codes and image feature descriptors in target trademark retrieval information to be inquired, obtaining word type trademark data word segmentation, trademark graphic element code type trademark data word segmentation and image feature type trademark data word segmentation, increasing the coverage of retrieval keywords from multiple dimensions, ensuring the consistency of certain trademark feature information of the same or similar sample trademark to be detected, and further effectively improving the recall ratio and precision ratio of trademark retrieval.

In some preferred embodiments, the word-like brand data participles include: and taking the set of all characters contained in the target trademark obtained by the identification processing or the input processing of the target trademark picture to be inquired as an integral retrieval character participle, and independently taking each character in the integral character participle as a local retrieval character participle. The trademark graphic element coding type trademark data word segmentation comprises the following steps: the method comprises the steps of taking a set of two or more trademark graphic element codes obtained by identifying and processing a plurality of objects described by a target trademark picture to be inquired as an integral trademark graphic element code participle, taking each group of trademark graphic element codes in the integral trademark graphic element code participle independently as a local trademark graphic element code participle, and using the local trademark graphic element code participle to describe a single different object. The image characteristic class trademark data word segmentation comprises the following steps: and taking the set of all image feature descriptors extracted from the target trademark picture to be queried as an overall image feature descriptor participle, and independently taking each group of partial image feature descriptors with local features in the overall image feature descriptor participle as a local image feature descriptor participle, wherein the local image feature descriptor participle is used for describing local features in the target trademark picture to be queried.

In some preferred embodiments, the search keyword processor 204 performs a combination process on the various trademark data participles to obtain the search keyword, including the following steps: and carrying out combined processing on the overall search word segmentation, the local search word segmentation, the overall trademark graphic element coding segmentation, the local trademark graphic element coding segmentation, the overall image feature descriptor segmentation and the local image feature descriptor segmentation to obtain a search keyword.

By the method, the word type trademark data participle, the trademark graphic element coding type trademark data participle and the image characteristic type trademark data participle are further divided into the whole participle and the local participle, and the whole participle and the local participle are combined, so that the number of the search keywords is further increased, the coverage of the search keywords is further improved, and the recall ratio and the precision ratio of trademark search are further improved.

In a second specific embodiment, the present application provides a mobile-end-based trademark query method applied to a user end, please refer to fig. 2, where fig. 2 is a flowchart of the mobile-end-based trademark query method applied to the user end in the embodiment of the present application, and the method includes the following steps:

s120, the target trademark picture to be inquired is sent to a server, feature extraction processing is requested to be carried out on the target trademark picture to be inquired, and at least one or more of the following combinations corresponding to the target trademark picture to be inquired is obtained: trademark graphic element coding, retrieving text information and image feature descriptors;

s130, confirming, editing, correcting or inputting the trademark graphic element codes and/or retrieval character information corresponding to the returned target trademark pictures to be inquired, taking the trademark graphic element codes and/or retrieval character information and the image feature descriptors after the confirmation, editing, correction or inputting processing as target trademark retrieval information to be inquired, feeding back the target trademark retrieval information to a server and sending a trademark inquiry request;

In a third specific embodiment, the present application provides a mobile-end-based trademark query method, which is applied to a server, please refer to fig. 3, where fig. 3 is a flowchart of a mobile-end-based trademark query method applied to a server in the embodiment of the present application, and the method includes the following steps:

s220, receiving a trademark query request with target trademark retrieval information to be queried, which is sent by a user side, wherein the target trademark retrieval information to be queried comprises trademark graphic element codes and/or retrieval character information and image feature descriptors after confirmation, editing, correction or input processing by the user side; instructing an image processor to perform word segmentation processing on target trademark retrieval information to be queried of the trademark query request, wherein the word segmentation processing comprises performing word segmentation processing on retrieval character information, acquiring word type trademark data word segmentation, performing word segmentation processing on trademark graphic element codes, acquiring trademark graphic element code type trademark data word segmentation, and performing word segmentation processing on image feature descriptors to acquire image feature type trademark data word segmentation;

s230, after receiving the processed trademark data participles returned by the image processor, instructing the search keyword processor 204 to perform combination processing on the trademark data participles to obtain a search keyword, where the search keyword includes at least one image feature type trademark data participle, and the search keyword also includes at least one trademark graphic element encoding type trademark data participle and/or at least one text type trademark data participle, and the various trademark data participles include: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle;

and S240, after receiving the search keywords returned by the search keyword processor, performing matching search by using the search keywords as search conditions, finding out a sample trademark matched with any search keyword to obtain trademark search result data, and sending the trademark search result data to the user side for display.

In a fourth specific embodiment, the present application provides a mobile terminal-based trademark query method, which is applied to an image processor, please refer to fig. 4, where fig. 4 is a flowchart of the mobile terminal-based trademark query method applied to the image processor in the embodiment of the present application, and the method includes the following steps:

s320, receiving a trademark query request which is transmitted by a server and contains target trademark retrieval information to be queried, wherein the target trademark retrieval information to be queried comprises trademark graphic element codes and/or retrieval character information and image feature descriptors which are confirmed or edited and corrected or input by a user side; the method comprises the steps of carrying out word segmentation on target trademark retrieval information to be queried of the trademark query request, carrying out word segmentation on the retrieval character information, obtaining character type trademark data words, carrying out word segmentation on trademark graphic element codes, obtaining trademark graphic element code type trademark data words, carrying out word segmentation on image feature descriptors, obtaining image feature type trademark data words, and feeding back the obtained character type trademark data words, trademark graphic element code type trademark data words and image feature type trademark data words to a server.

In a fifth specific embodiment, the present application provides a mobile-terminal-based trademark query method, applied to a search keyword processor, including the following steps:

In a sixth specific embodiment, the present application provides a mobile-end-based trademark query method, applied to a device, including: the user side display module, the application service management module, the trademark retrieval module, the image processing module and the retrieval keyword processing module, that is, the integrated device, executes the methods of the second to fifth embodiments, or may perform matching retrieval using the retrieval keywords obtained by the combination as retrieval conditions to find a sample trademark matching any of the retrieval keywords, thereby obtaining trademark retrieval result data. The trademark retrieval can be performed in a local database (for example, when the query method is applied to a stand-alone trademark retrieval system), or can be performed in a cloud database (for example, when the query method is applied to a network trademark retrieval system).

The combined search keywords are adopted to search the trademark, trademark inquiry of input text information and trademark inquiry of input trademark pictures are effectively fused, the combined search keywords not only comprehensively reflect the character characteristics and the characteristics of described objects contained in the input trademark, but also reflect the image characteristics such as the graphic shape and the like of the input trademark, organic combination of the traditional trademark inquiry method and the modern trademark inquiry method is realized, the defects of independent inquiry of the trademark of the input text and the trademark of the input trademark pictures can be effectively overcome, the effects of making good for the deficiencies of the two methods are achieved, and the recall ratio and the precision ratio of the trademark inquiry are obviously improved. Even if the trademark inquiry professional level of an inquirer is insufficient, the better trademark inquiry result quality can be obtained.

In some preferred embodiments, the system (e.g., server) may perform the operations of: and matching and searching in trademark inquiry systems with different trademark inquiry algorithms or trademark inquiry technical methods by taking the search key words as search conditions to obtain at least two inquiry results of the trademark inquiry systems with different trademark inquiry algorithms or trademark inquiry technical methods, and integrating the inquiry structures to obtain trademark search result data. The manner of integrating the query structure may include deduplication, sorting by relevance, and the like. According to the embodiment, the matching retrieval is carried out in the trademark query systems with different trademark query algorithms or trademark query technical methods according to the retrieval keyword, so that not only is the comprehensiveness of the retrieval keyword obtained ensured, but also the comprehensiveness of the technology adopted during the retrieval according to the retrieval keyword is ensured, and the technical problem that the comprehensiveness of the trademark retrieval is influenced due to the fact that the single trademark query system is adopted for query is solved (because the single trademark query system possibly has loopholes or incompleteness in the algorithm, the loopholes or incompleteness factors can directly influence the comprehensiveness of the trademark query result), so that the comprehensiveness of the trademark query result is further improved. In practical application, the search keyword can be sent to the same terminal or different terminals, the terminals can respectively search in different trademark query systems by using the search keyword to obtain query results of different trademark query systems, and finally the query results are integrated to obtain trademark search result data.

As can be seen from the above, the trademark inquiry system based on the mobile terminal provided in the embodiment of the present application takes a target trademark picture through the user terminal or selects a target trademark picture stored in the user terminal, and judges and cuts a trademark area of the target trademark picture to obtain a target trademark picture to be inquired; performing feature extraction processing on the target trademark picture to be inquired to obtain at least one or more combinations of the following items corresponding to the target trademark picture to be inquired: trademark graphic element coding, retrieving text information and image feature descriptors; confirming or editing and correcting the trademark graphic element code and/or retrieval character information corresponding to the target trademark picture to be inquired, taking the confirmed or edited and corrected trademark graphic element code and/or retrieval character information and the image feature descriptor as target trademark retrieval information to be inquired, and sending a trademark inquiry request to the server; performing word segmentation processing on target trademark retrieval information to be queried of the trademark query request to obtain word type trademark data word segmentation, trademark graphic element coding type trademark data word segmentation and image characteristic type trademark data word segmentation; combining the various trademark data participles to obtain search keywords; and matching and searching are carried out by taking the search keyword as a search condition, a sample trademark matched with any search keyword is found, trademark search result data is obtained, and the technical problem that the recall ratio and the precision ratio of trademark search by adopting a single trademark search mode and a single trademark search system in the prior art do not meet the application requirements is solved.

The technical scheme has the advantages that the mobile terminal is used for dynamically acquiring the trademark picture to be retrieved in real time, the limitation that the trademark inquiring system in the prior art can only upload the picture which is locally stored on a computer in an office place through the Internet to acquire the input of trademark inquiring can be effectively overcome, the scheme can be used for acquiring the retrieved trademark picture in real time in any place and any time in any place where a mobile phone can use, and the image can be edited and cut in real time to acquire the trademark picture to be retrieved, so that great convenience is brought to trademark practitioner retrieving trademarks. And the combined retrieval key words are adopted, the trademark query of the input text and the trademark query of the input trademark picture are effectively integrated, the organic combination of the traditional trademark query method and the modern trademark query method is realized, the defects of independent respective query of the trademark query of the input text and the trademark of the input trademark picture can be effectively overcome, the effects of making the best of the two methods are achieved, and the recall ratio and the precision ratio of the trademark query are obviously improved. Even if the trademark inquiry professional level of an inquirer is insufficient, the better trademark inquiry result quality can be obtained.

Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure, in which an electronic device 4 includes: the processor 401 and the memory 402, the processor 401 and the memory 402 being interconnected and communicating with each other via a communication bus 403 and/or other form of connection mechanism (not shown), the memory 402 storing a computer program executable by the processor 401, the processor 401 executing the computer program when the computing device is running to perform the method of any of the alternative implementations of the embodiments described above.

The embodiment of the present application provides a storage medium, and when being executed by a processor, the computer program performs the method in any optional implementation manner of the above embodiment. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A trademark inquiry system based on a mobile terminal is characterized by comprising: the system comprises a user side, a server, an image processor and a retrieval keyword processor, wherein the user side is connected with the server through a wireless network or the Internet, and the server is connected with the image processor and the retrieval keyword processor through a local area network or the Internet and executes the following processing:

2. The mobile-based trademark inquiry system of claim 1, wherein the server includes an application service manager and a trademark retrieval server;

3. The mobile-terminal-based trademark inquiry system according to claim 1, wherein the user terminal comprises a mobile phone and other devices connected to the server through a wireless network or the internet, and further comprises a computer for scanning a code and logging in through the mobile phone or the wireless device.

4. The mobile terminal-based trademark inquiring system of claim 1, wherein before obtaining the target trademark picture to be inquired, the user terminal further performs trademark area judgment and clipping processing on the captured target trademark picture or the target trademark picture selected and stored in the user terminal, so as to obtain the target trademark picture to be inquired.

5. The mobile terminal-based trademark inquiring system according to claim 1, wherein the image feature descriptor corresponding to the target trademark picture to be inquired comprises at least one of the following:

6. The mobile terminal-based trademark inquiry system according to claim 1, wherein the image processor performs word segmentation processing on the image feature descriptors to obtain image feature class trademark data words, and the word segmentation processing comprises: segmenting multiple kinds and multiple groups of image feature descriptors in the target trademark retrieval information to be queried according to each extraction algorithm and/or each group of image feature descriptors to obtain segmented local image feature descriptor information, and using the segmented local image feature descriptor information as image feature descriptor trademark data participles;

7. The mobile-based trademark inquiry system of claim 1, wherein the text-based trademark data word segmentation comprises: taking a set of all characters contained in the target trademark obtained by the identification processing or the input processing of the target trademark picture to be inquired as an integral retrieval character participle, and taking each character in the integral character participle independently as a local retrieval character participle;

8. The mobile terminal-based trademark inquiry system according to claim 7, wherein the search keyword processor performs combination processing on each type of trademark data participles to obtain a search keyword, comprising the steps of: and carrying out combined processing on the overall search word segmentation, the local search word segmentation, the overall trademark graphic element coding segmentation, the local trademark graphic element coding segmentation, the overall image feature descriptor segmentation and the local image feature descriptor segmentation to obtain a search keyword.

9. A trademark query method based on a mobile terminal is applied to a user terminal and is characterized by comprising the following steps:

10. A trademark inquiry method based on a mobile terminal is applied to a server and is characterized by comprising the following steps:

11. A trademark inquiry method based on a mobile terminal is applied to an image processor and is characterized by comprising the following steps:

12. A trademark query method based on a mobile terminal is applied to a processor for searching key words, and is characterized by comprising the following steps: receiving various processed trademark data participles transmitted by a server, combining the various trademark data participles according to an instruction, acquiring a search keyword and feeding the search keyword back to the server, wherein the search keyword comprises at least one image characteristic type trademark data participle, and the search keyword also comprises at least one trademark graphic element coding type trademark data participle and/or at least one character type trademark data participle, and the various trademark data participles comprise: word type trademark data participle, trademark graphic element coding type trademark data participle and image characteristic type trademark data participle.

13. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the method according to any of claims 9-12.