Product Multi-Context Trademark Information Compliance Detection Method and System

Abstract

The present application provides a method and system for detecting compliance of product multi-context trademark information. When the terminal device detects a user's operation of putting a product to be put on the shelf in the product shelf management function interface, it extracts the first language text information and the second language text information of the product to be put on the shelf according to the product graphic and text information of the product to be put on the shelf; in response to the operation of putting the product on the shelf, it sends a compliance detection request message carrying reference trademark element information to the server; it receives a compliance detection response message from the server, and the compliance detection response message includes trademark infringement risk prompt information; it displays the trademark infringement risk prompt information in the product shelf management function interface. Therefore, the present application can perform splitting and combining processing on multi-language mixed trademark information to obtain multiple semantic element bodies, and comprehensively determine the trademark infringement risk of multi-language mixed trademark information according to the trademark similarity retrieval results of multiple semantic element bodies, improving the comprehensiveness and accuracy of product trademark compliance detection.

Description

Technical Field

[0001] This application relates to the field of information processing technologies, and in particular, to a method and system for detecting compliance of multi-context trademark information of products. Background Art

[0002] In the e-commerce scenario, there are more and more globalized products. Taking game products as an example, a single popular product often registers trademark information with multiple trademark offices in different context regions around the world, and the types of trademark languages registered with trademark offices in different regions are different. For example, in the Chinese context region, Chinese is mainly used, and in the English context region, English is mainly used. In addition, the audiovisual content elements of game products other than trademark elements are also registered and protected through copyright, such as character models, props, plots, high-frequency hot words, etc. in game products.

[0003] Currently, e-commerce platforms can perform relatively accurate similar trademark queries, infringement prompts and restrictions on the single-language trademark information of products to be listed, but it is difficult to meet the user's usage requirements for complex situations of multi-language mixing and multi-element mixing. Summary of the Invention

[0004] This application provides a method and system for detecting compliance of multi-context trademark information of products, which can split and combine multi-language mixed trademark information to obtain multiple semantic element bodies, and comprehensively determine the trademark infringement risk of multi-language mixed trademark information according to the trademark similarity retrieval results of multiple semantic element bodies, improve the comprehensiveness and accuracy of product trademark compliance detection, and enhance the user experience.

[0005] In a first aspect, the present application provides a method for detecting compliance of product multi-context trademark information, which is applied to a terminal device of an e-commerce platform, wherein the e-commerce platform includes the terminal device and a server, and the method includes: detecting a user's operation of placing a product on a shelf in a product placing management function interface, and extracting reference trademark element information of the product to be placed on the shelf according to the product graphic information of the product to be placed on the shelf, wherein the reference trademark information includes text information in a first language and text information in a second language, wherein the text information in the first language includes at least two first minimum semantic elements, and the text information in the second language includes at least two second minimum semantic elements, wherein at least one mixed semantic element body corresponding to the at least two first minimum semantic elements and the at least two second minimum semantic elements contains a target mixed semantic element body whose highest similarity with a single language registered trademark is greater than or equal to the first similarity threshold, and the highest similarity of each first combined semantic element body in at least one first combined semantic element body corresponding to the at least two first minimum semantic elements and the first language registered trademark is lower than the first similarity threshold, and the highest similarity of each second combined semantic element body in at least one second combined semantic element body corresponding to the at least two second minimum semantic elements and the second language registered trademark is lower than the first similarity threshold. similarities are all lower than the first similarity threshold, and there is a target semantic element body that is the same as the high-heat semantic element body in the semantic element body set, the semantic element body set is the union of the at least one mixed semantic element body, the at least one first combined semantic element body, and the at least one second combined semantic element body, the high-heat semantic element body is a text element body in the text element subset of the work element set of the high-network-heat game work, the product category of the product to be put on the shelf belongs to the peripheral product category set, and the peripheral product category set is the union of product categories that can be used as peripheral products of the game product; in response to the putting on the shelf operation, sending a compliance detection request message carrying the reference trademark element information to the server, and receiving a compliance detection response message from the server, the compliance detection response message containing trademark infringement risk warning information, the trademark infringement risk warning information is used to indicate the infringement risk caused by the confusion risk probability of the reference trademark element information being greater than a preset probability threshold, and the confusion risk probability refers to the probability of the target mixed semantic element body and the target semantic element body being identified as belonging to the single-language registered trademark under the condition of the joint action of the target mixed semantic element body and the target semantic element body; the trademark infringement risk warning information is displayed on the product putting on the shelf management function interface.

[0006] In a second aspect, an embodiment of the present application provides an e-commerce platform system, including a server and a terminal device, wherein the terminal device is used to execute the step instructions in the method as described in any one of the first aspects.

[0007] It can be seen that in the embodiment of the present application, the terminal device detects a user's operation of putting a product to be put on the shelf in the product shelf management function interface, extracts the reference trademark element information of the product to be put on the shelf according to the product graphic and text information of the product to be put on the shelf. The reference trademark information includes first language text information and second language text information. The first language text information includes at least two first minimum semantic elements, and the second language text information includes at least two second minimum semantic elements. Among them, there is a target hybrid semantic element body in at least one hybrid semantic element body corresponding to at least two first minimum semantic elements and at least two second minimum semantic elements, and the highest similarity with the single-language registered trademark is greater than or equal to the first similarity threshold. Moreover, the highest similarity between each first combined semantic element body in at least one first combined semantic element body corresponding to at least two first minimum semantic elements and the first-language registered trademark is lower than the first similarity threshold. The highest similarity between each second combined semantic element body in at least one second combined semantic element body corresponding to at least two second minimum semantic elements and the second-language registered trademark is lower than the first similarity threshold. And there is a target semantic element body in the semantic element body set that is the same as the high-heat semantic element body. The semantic element body set is the union of at least one hybrid semantic element body, at least one first combined semantic element body, and at least one second combined semantic element body. The high-heat semantic element body is a text element body in the text element subset of the work element set of a game work with high network heat. The product category of the product to be put on the shelf belongs to the peripheral product category set, and the peripheral product category set is the union of product categories that can be used as peripheral products of game products; in response to the operation of putting the product on the shelf, a compliance detection request message carrying the reference trademark element information is sent to the server, and, a compliance detection response message is received from the server. The compliance detection response message includes trademark infringement risk prompt information, and the trademark infringement risk prompt information is used to indicate the infringement risk caused by the confusion risk probability of the reference trademark element information being greater than the preset probability threshold. The confusion risk probability refers to the probability of being recognized as belonging to a single-language registered trademark under the condition of the joint action of the target hybrid semantic element body and the target semantic element body; the trademark infringement risk prompt information is displayed on the product shelf management function interface. Therefore, the present application can perform split-combination processing on multi-language hybrid trademark information to obtain multiple semantic element bodies, comprehensively determine the trademark infringement risk of multi-language hybrid trademark information according to the trademark similarity retrieval results of multiple semantic element bodies, improve the comprehensiveness and accuracy of product trademark compliance detection, and enhance the user experience. Brief Description of the Drawings

[0008] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0009] Figure 1 It is a schematic structural diagram of an e-commerce platform provided by an embodiment of the present application;

[0010] Figure 2 It is a schematic flow diagram of a method for detecting compliance of product multi-context trademark information provided by an embodiment of the present application;

[0011] Figure 3 It is a schematic diagram of the product listing management function interface when uploading product graphic and text information provided by an embodiment of the present application;

[0012] Figure 4 It is a schematic diagram of the product listing management function interface when displaying compliance detection items after clicking the listing control provided by an embodiment of the present application;

[0013] Figure 5 It is a schematic diagram of the product listing management function interface when the terminal device extracts product graphic and text information provided by an embodiment of the present application;

[0014] Figure 6 It is a schematic diagram of the product listing management function interface when displaying trademark infringement risk prompt information provided by an embodiment of the present application;

[0015] Figure 7 It is a schematic diagram of the product listing management function interface when displaying trademark detection compliance prompt information provided by an embodiment of the present application;

[0016] Figure 8 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0017] In order to enable those skilled in the art to better understand the solution of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0018] In the description, claims and the above-mentioned drawings of this application, terms such as "first", "second", etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0019] Reference to "embodiment" herein means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the description and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0020] The "and / or" in the embodiments of this application describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist simultaneously; B exists alone. Among them, A and B can be singular or plural.

[0021] In the embodiments of this application, the symbol " / " can represent an "or" relationship between the associated objects before and after. In addition, the symbol " / " can also represent a division sign, that is, perform a division operation. For example, A / B can represent A divided by B.

[0022] The "at least one (piece)" or its similar expression in the embodiments of this application refers to any combination of these items, including any combination of single item (piece) or plural items (pieces), and refers to one or more, and multiple refers to two or more. For example, at least one (piece) of a, b or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b and c. Among them, each of a, b, c can be an element or a set containing one or more elements.

[0023] The "equal to" in the embodiments of this application can be used in combination with "greater than" and is applicable to the technical solutions adopted when it is greater than, or can also be used in combination with "less than" and is applicable to the technical solutions adopted when it is less than. When "equal to" is used in combination with "greater than", it is not used in combination with "less than"; when "equal to" is used in combination with "less than", it is not used in combination with "greater than".

[0024] The present application provides a method and system for detecting compliance of product multi-context trademark information, which can split and combine multi-language mixed trademark information to obtain multiple semantic element bodies, and comprehensively determine the trademark infringement risk of the multi-language mixed trademark information according to the trademark similarity retrieval results of the multiple semantic element bodies, improving the comprehensiveness and accuracy of product trademark compliance detection and enhancing the user experience.

[0025] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0026] Please refer to Figure 1 to Figure 2 , Figure 1 which is a schematic structural diagram of an e-commerce platform provided by an embodiment of the present application, Figure 2 and which is a schematic flowchart of a method for detecting compliance of product multi-context trademark information provided by an embodiment of the present application.

[0027] The e-commerce platform 1 includes a terminal device 10 and a server 20, and the terminal device 10 and the server 20 are communicatively connected by wire or wirelessly.

[0028] Among them, the terminal device 10 may specifically include a front-end device applied to the user side that can implement functions such as data collection and data transmission, and can be a mobile phone, a smart phone, a laptop computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), and other user equipment (User Equipment, UE), a handheld device, a vehicle-mounted device, a wearable device, a computing device, or other processing devices connected to a wireless modem, a mobile station (Mobile Station, MS), a mobile terminal (Mobile Terminal), etc. Alternatively, the terminal device 10 may also be a software application that can run on the above electronic devices. For example, it can be a certain APP running on a mobile phone, etc.

[0029] Among them, the server 20 may specifically include a background server applied to the network platform side that can implement functions such as data transmission and data processing, and can be a physical server, or a server cluster or distributed system composed of multiple physical servers. In this embodiment, the number of servers is not specifically limited. Alternatively, it can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0030] The terminal device 10 is Figure 2 The execution subject of a product multi-context trademark information compliance detection method shown in the figure includes the following steps S201 to S204:

[0031] Step S201, the terminal device detects a user's operation of placing a product on the shelf in the product placing management function interface, and extracts reference trademark element information of the product on the shelf according to the product graphic information of the product on the shelf.

[0032] Among them, after the user uploads the product image and text information of the product to be put on the shelf, the terminal device extracts the trademark element information of the product to be put on the shelf based on the product image and text information. Specifically, extract keywords such as brand name and trademark name from the product description, and obtain the brand and trademark information of the product to be put on the shelf based on trademark and brand identification symbols such as "™" or "®"; use OCR technology to recognize the text in the product image and extract possible trademark information; use the trademark keywords obtained from the product description information and the trademark keywords obtained from the product image as reference trademark element information.

[0033] For specific implementation, please refer to Figure 3 , Figure 3 This is a schematic diagram of a product shelf management function interface when uploading product image and text information provided in an embodiment of the present application.

[0034] like Figure 3 As shown, the product listing management function interface 3 includes a product display area 31. Clicking the newly added control in the product display area 31 can display the file upload area 32, which is used to upload the appearance pictures and text description information of the products to be listed. Clicking other products such as product 1 can display the product compliance test results of product 1. After the user uploads the graphic information of the product to be listed, click the listing control to display the compliance test items on the product listing management function interface 3. Among them, the compliance test items include trademark compliance testing, and can also include appearance compliance testing, policy compliance testing and other testing items, such as Figure 4 shown.

[0035] When a trigger operation of a trademark compliance test item is detected, the terminal device obtains the reference trademark element information of the product to be put on the shelf based on the product image and text information, such as Figure 5As shown, a trademark extraction area 33 is displayed on the product listing management function interface 3, and trademark element information of the product to be listed is displayed on the right side of the product graphic information. The user can perform editing operations such as selection and modification on the automatically extracted trademark element information to obtain the final reference trademark element information. When the user confirms that the reference trademark element information is correct, click the trademark compliance detection control on the product listing management function interface 3 to send a compliance detection request message carrying the reference trademark element information to the server.

[0036] Among them, the reference trademark information includes first language text information and second language text information. The first language text information includes at least two first minimum semantic elements, and the second language text information includes at least two second minimum semantic elements. For example, for the trademark element information "Tianming Black WuKong" in a Chinese-English mix, the first language is Chinese, the first language text information is "Tianming Black", and the first minimum semantic elements include "Tian", "Ming", "Black"; the second language is English, the second language text information is "WuKong", and the second minimum semantic elements include "Wu", "Kong".

[0037] Among them, at least two first minimum semantic elements and at least two second minimum semantic elements correspond to at least one mixed semantic element body; that is, the first minimum semantic elements and the second minimum semantic elements are combined to form at least one mixed semantic element body. For example, the trademark element information "Tianming Black WuKong" can form the following mixed semantic element bodies: "Black Wu", "Black WuKong", "Ming Black Wu", "Ming Black WuKong", "Tianming Black Wu", "Tianming Black WuKong"; among them, single-language registered trademarks include first-language registered trademarks and second-language registered trademarks; in this example, the first-language registered trademark is the Chinese registered trademark included in the Chinese registered trademark database, and the second-language registered trademark is the English registered trademark in the English registered trademark database;

[0038] And at least two first minimum semantic elements correspond to at least one first combined semantic element body, and at least two second minimum semantic elements correspond to at least one second combined semantic element body; that is, the first combined semantic element body is composed of at least two first minimum semantic elements. For example, the trademark element information "Tianming Black WuKong" can form the following first combined semantic elements: "Tianming", "Tianming Black", "Ming Black"; the second combined semantic element body is composed of at least two second minimum semantic elements. For example, the trademark element information "Tianming Black WuKong" can form the following second combined semantic elements: "WuKong"; the highest similarity between the above first combined semantic element body, second combined semantic element body and the corresponding first-language registered trademark, second-language registered trademark is lower than the first similarity threshold;

[0039] The union of at least one hybrid semantic element body, at least one first combined semantic element body, and at least one second combined semantic element body is the semantic element body set;

[0040] When there is a target hybrid semantic element body in at least one hybrid semantic element body whose highest similarity to a monolingual registered trademark is greater than or equal to the first similarity threshold, and the highest similarity of each first combined semantic element body in at least one first combined semantic element body to the first-language registered trademark is lower than the first similarity threshold, the highest similarity of each second combined semantic element body in at least one second combined semantic element body to the second-language registered trademark is lower than the first similarity threshold, and there is a target semantic element body in the semantic element body set that is the same as the high-heat semantic element body, it indicates that the reference trademark element information may be determined to be similar to one or more registered trademarks in the monolingual registered trademarks, which may cause consumers to be difficult to distinguish or confused, that is, there is an infringement risk.

[0041] Among them, the high-heat semantic element body is the text element body in the text element subset of the work element set of the game work with high network heat. The product category of the product to be put on the shelf belongs to the peripheral product category set, and the peripheral product category set is the union of the product categories that can be used as peripheral products of the game product. Among them, the high-heat game can be a game with a network heat exceeding the preset network heat threshold, such as a game that has been continuously on the Weibo hot search for more than the preset duration, or a game with more than a specific number of concurrent online and cumulative online players; among them, the text element subset of the game work can include text element bodies such as story plots, character descriptions, text explanations, game lines, etc., and can also include the network heat of each text element body. For example, the text element body "destiny" in the text element set such as "face destiny" and "destiny person" that appear many times in "Black Myth: Wukong".

[0042] Step S202, the terminal device responds to the put-on-shelf operation and sends a compliance detection request message carrying the reference trademark element information to the server.

[0043] Among them, the compliance detection request message is used to instruct the server to determine the trademark infringement risk of the product to be put on the shelf according to the reference trademark association information of the product to be put on the shelf.

[0044] Among them, the put-on-shelf operation includes but is not limited to the steps shown in Figure 3 - Figure 5 as follows.

[0045] Step S203, the terminal device receives a compliance detection response message from the server.

[0046] Among them, the compliance detection response message includes trademark infringement risk prompt information, which is used to indicate the infringement risk caused by the confusion risk probability of the reference trademark element information being greater than the preset probability threshold. The confusion risk probability refers to the probability of being recognized as a monolingual registered trademark under the condition of the joint action of the target mixed semantic element body and the target semantic element body.

[0047] Step S204, the terminal device displays the trademark infringement risk prompt information on the product shelf management function interface.

[0048] Specifically, when the compliance detection response message includes trademark infringement risk prompt information, the trademark infringement risk prompt information 34 is displayed on the product shelf management function interface 3. As Figure 6 shown, the trademark infringement risk prompt information 34 includes the registered trademarks similar to the reference trademark element information and their similarity, the high-heat semantic element body and its network heat, as well as trademark-related information such as the current owner.

[0049] It can be seen that in the embodiment of the present application, the terminal device detects a user's shelf operation on a product to be listed in the product shelf management function interface, and extracts reference trademark element information of the product to be listed based on the product graphic information of the product to be listed, the reference trademark information includes text information in a first language and text information in a second language, the first language text information includes at least two first minimum semantic elements, and the second language text information includes at least two second minimum semantic elements, wherein at least one mixed semantic element body corresponding to the at least two first minimum semantic elements and the at least two second minimum semantic elements contains a target mixed semantic element body whose highest similarity with the single language registered trademark is greater than or equal to the first similarity threshold, and the highest similarity of each first combined semantic element body in at least one first combined semantic element body corresponding to the at least two first minimum semantic elements and the first language registered trademark is lower than the first similarity threshold, and the highest similarity of each second combined semantic element body in at least one second combined semantic element body corresponding to the at least two second minimum semantic elements and the second language registered trademark is lower than the first similarity threshold, and There is a target semantic element body that is the same as the high-heat semantic element body in the semantic element body set, the semantic element body set is the union of at least one mixed semantic element body, at least one first combined semantic element body, and at least one second combined semantic element body, the high-heat semantic element body is a text element body in the text element subset of the work element set of high-network-heat game works, the product category of the product to be put on the shelf belongs to the peripheral product category set, and the peripheral product category set is the union of product categories that can be used as peripheral products of game products; in response to the listing operation, a compliance detection request message carrying reference trademark element information is sent to the server, and a compliance detection response message is received from the server, the compliance detection response message contains trademark infringement risk warning information, the trademark infringement risk warning information is used to indicate the infringement risk caused by the confusion risk probability of the reference trademark element information being greater than a preset probability threshold, and the confusion risk probability refers to the probability of being identified as a single-language registered trademark under the joint action of the target mixed semantic element body and the target semantic element body; the trademark infringement risk warning information is displayed on the product listing management function interface. Therefore, the present application can split and combine multilingual mixed trademark information to obtain multiple semantic element bodies, and comprehensively determine the trademark infringement risk of the multilingual mixed trademark information based on the trademark similarity retrieval results of the multiple semantic element bodies, thereby improving the comprehensiveness and accuracy of product trademark compliance testing and enhancing user experience.

[0050] In some embodiments, the process of the server creating the compliance detection response message includes the following steps a-e:

[0051] Step a: The server obtains the semantic element body set according to the reference trademark element information.

[0052] In some embodiments, the at least one first semantic combination element body is composed of at least two first minimum semantic elements, the at least one second semantic combination element body is composed of at least two second minimum semantic elements, and the at least one hybrid semantic element body is jointly composed of at least one of the first minimum semantic elements and at least one of the second minimum semantic elements; two adjacent minimum semantic elements in a single semantic element body are also adjacent in the reference trademark element information. For example, in "Tianming Black WuKong", "Tian" and "Ming" are adjacent, so when forming the semantic element body, "Tian" and "Ming" must also be adjacent to form "Tianming", "Ming" and "Black" are adjacent to form "Minghei", and "Tian" and "Black" are not adjacent, so "Tianhei" cannot be formed.

[0053] It can be seen that in this embodiment, by ensuring that adjacent minimum semantic elements also remain adjacent during combination, the semantic structure of the original trademark can be more accurately reflected, avoiding misunderstandings or information loss.

[0054] Step b, the server performs trademark retrieval operations on the monolingual registered trademarks respectively according to each semantic combination element body in the semantic element body set, and obtains multiple similarities. The monolingual registered trademarks include the first-language registered trademarks and the second-language registered trademarks.

[0055] Step c, the server determines game works related to each semantic combination element body in the semantic element body set from the Internet, obtains the text element bodies in the text element subset of the work element set of the game works, and obtains the network popularity of the text element bodies; determines the network popularity set of the semantic element body set according to the text element bodies and their network popularity. The network popularity set includes the network popularity of each semantic element body in the semantic element body set.

[0056] Specifically, the server determines the game work "Black Myth: Wukong" according to "Tianming" and "Black WuKong", obtains the text element bodies in the text element subset according to this game work, including but not limited to game characters such as Black Wukong and Tianmingren, game name Black Myth, and other relevant text information, and obtains the network popularity of the foregoing text element bodies. Determines the network popularity of the semantic element bodies related to the text element bodies in the semantic element body set according to the network popularity of the text element bodies in the game text element subset, and forms a network popularity set.

[0057] Step d, the server determines the confusion risk probability according to the multiple similarities and the network popularity set;

[0058] Step e, the server generates the compliance detection response message according to the size relationship between the confusion risk probability and the preset probability threshold.

[0059] Among them, for step b, "The server performs trademark retrieval operations on the single-language registered trademark according to each semantic combination element body in the semantic element body set, and obtains multiple similarities", the following steps b1 - step b3 are included:

[0060] In step b1, the server performs trademark retrieval operations on the at least one first combined semantic element body and the first-language registered trademark, and obtains a first similarity that is the highest similarity to the at least one first combined semantic element body.

[0061] Among them, the process of the server performing the trademark retrieval operation on a single first combined semantic element body specifically includes the following steps b11 - step b13:

[0062] In step b11, retrieve at least one registered trademark that contains at least two first minimum semantic elements of the first combined semantic element body from the first-language registered trademark, and the at least two first minimum semantic elements are in an adjacent relationship in both the first combined semantic element body and the at least one registered trademark;

[0063] Exemplarily, if the first group and semantic element body is "Tianming Black", the server first searches for the first registered trademark set that contains "Tian"; secondly, searches for the second registered trademark set in which "Ming" follows "Tian" from the first registered trademark set; finally, searches for the third registered trademark set in which "Black" follows "Ming" from the second registered trademark set; assuming that the second registered trademark set includes four registered trademarks of "Happy Tianming", "Son of Tianming", and "Tianming People", and the third registered trademark set includes 0 registered trademarks, then determine the second registered trademark set as the at least one registered trademark.

[0064] In step b12, determine the similarity according to the number of first minimum semantic elements included in the first combined semantic element body and the number of first minimum semantic elements included in a single registered trademark;

[0065] Exemplarily, for the four registered trademarks of "Happy Tianming", "Son of Tianming", and "Tianming People", the similarity between "Tianming Black" and "Happy Tianming" is: 2 / 4 = 50%, the similarity with "Son of Tianming" is: 2 / 4 = 50%, and the similarity with "Tianming People" is: 2 / 3 = 67%.

[0066] In step b13, determine the first similarity as the highest similarity among the at least one similarity.

[0067] Therefore, determine that the first similarity with the highest similarity to "Tianming Black" is 67%.

[0068] It can be seen that in this embodiment, the use of adjacent relationships and comparison of minimum semantic elements can better capture the semantic relevance in different registered trademarks, enhance semantic matching capabilities, and improve retrieval accuracy, so that the system can more efficiently identify potential similar trademarks, reduce legal risks, and maintain brand uniqueness.

[0069] Step b2: the server performs the trademark search operation according to the at least one second combined semantic element body and the second language registered trademark to obtain the second similarity with the highest similarity to the at least one second combined semantic element body.

[0070] The second similarity is calculated using the same method as the first similarity, which will not be described in detail here.

[0071] Step b3: The server converts a single minimum semantic element in the at least one mixed semantic element body into the first language or the second language, performs the trademark search operation based on the translated mixed semantic element and the registered trademark in the first language or the registered trademark in the second language, and obtains a third similarity that is most similar to the translated mixed semantic element body.

[0072] Among them, for a single mixed semantic element body, it is necessary to translate the two different languages ​​in the mixed semantic element body into the same language, and then calculate the third similarity according to the method shown in step b11-step b13. For example, for "黑WuKong", it is uniformly translated into Chinese "黑武空", and the similarity is retrieved from the registered trademarks in the first language; it is uniformly translated into English "BlackWuKong", and the similarity is retrieved from the registered trademarks in the second language; the similarity with the highest similarity is determined from the two types of similarities obtained as the third similarity.

[0073] Wherein, step d "the server determines the confusion risk probability according to the multiple similarities and the network heat set" includes the following steps d1-d5:

[0074] Step d1: The server detects that both the first similarity and the second similarity are smaller than the first similarity threshold, and the third similarity is greater than or equal to the first similarity threshold.

[0075] In step d2, the server obtains at least one remaining semantic element body in the semantic element body set except for the minimum semantic element included in the target mixed semantic element body.

[0076] Exemplarily, the first combined semantic element body is "Tianming Black", the second combined semantic element body is "WuKong", and the mixed semantic element body is "Black WuKong". Then, the registered trademark similar to the mixed semantic element body is "Black Wukong", which is the registered trademark of the company to which the game work "Black Myth: Wukong" belongs. Translating "Black WuKong" as "Black Wukong", the third similarity is 100%; the registered trademark similar to the first combined semantic element body is "Tianming Man", and the first similarity is 67%; the registered trademark similar to the second combined semantic element body is "BlackWuKong", and the second similarity is 67%; assuming that the first similarity threshold is 90%, then both the first similarity and the second similarity are lower than the first similarity threshold, and the third similarity is higher than the first similarity threshold. The target mixed semantic element body is "Black WuKong". Removing "Black", "Wu", and "Kong", the remaining semantic element body is "Tianming".

[0077] Step d3, the server obtains at least one network popularity of the at least one remaining semantic element body from the network popularity set.

[0078] Step d4, if there is a remaining semantic element body in the at least one remaining semantic element body whose network popularity is greater than or equal to a preset network popularity threshold, and it is determined as the target semantic element body, then it is determined that the confusion risk probability is greater than the preset probability threshold; the network popularity of the high-popularity semantic element is greater than or equal to the preset network popularity threshold.

[0079] Among them, if the network popularity of "Tianming" is greater than the preset network popularity threshold, it indicates that on the premise that there is a similar trademark for "Black WuKong", the other semantic element "Tianming" of the reference trademark element information "Tianming Black WuKong" is also a high-popularity text element body under this game work. At this time, the reference trademark element information has a relatively high degree of confusion compared with the game work "Black Myth: Wukong", and it is determined that the confusion risk probability is greater than the preset probability threshold.

[0080] Step d5, if the network popularities are all less than the preset network popularity threshold, it is determined that the confusion risk probability is less than the preset probability threshold.

[0081] Among them, if the network popularity of "Tianming" is less than the preset network popularity threshold, it indicates that there are no similar trademarks for both the first combined semantic element body and the second combined semantic element body, and there is no relatively high network popularity either. Only the mixed semantic element body has a similar trademark. At this time, the reference trademark element information has a relatively low degree of confusion compared with the game work "Black Myth: Wukong", and it is determined that the confusion risk probability is less than the preset probability threshold.

[0082] It can be seen that in the embodiment, by integrating the trademark similarity and the network popularity, on the premise that there is no similar trademark in a single language trademark element of the multi-language mixed trademark element information, the confusion risk of the multi-language mixed trademark element information can be comprehensively determined by determining the similar trademarks of the mixed semantic element body and the network popularity of the remaining semantic element body, thereby improving the accuracy and reliability of trademark infringement risk identification.

[0083] Among them, for step e "the server generates the compliance detection response message according to the magnitude relationship between the confusion risk probability and the preset probability threshold", it includes: if the confusion risk probability is greater than or equal to the preset probability threshold, then generate the trademark infringement risk prompt information; if the confusion risk probability is less than the preset probability threshold, then generate the trademark detection compliance prompt information, and the compliance detection response message includes the trademark detection compliance prompt information.

[0084] Specifically, the schematic diagram of the trademark infringement risk prompt information is as Figure 6 shown.

[0085] When the compliance detection response message includes the trademark detection compliance prompt information, the trademark detection compliance prompt information 35 is displayed on the product shelf management function interface 3, and the trademark detection compliance prompt information is used to prompt the user of the compliance status of the trademark compliance detection items of the product to be shelved, as Figure 7 shown.

[0086] It can be seen that in this embodiment, by comprehensively analyzing multiple similarities and network popularity, the confusion risk between trademarks can be evaluated more accurately.

[0087] In some embodiments, the determining the confusion risk probability according to the multiple similarities and the network popularity set further includes the following steps d6-step d8:

[0088] Step d6, if it is detected that at least two of the first similarity, the second similarity, and the third similarity are greater than or equal to the first similarity threshold, then determine that the confusion risk probability is greater than the preset probability threshold.

[0089] Among them, detecting that at least two of the first similarity, the second similarity, and the third similarity are greater than or equal to the first similarity threshold includes: detecting that both the first similarity and the second similarity are greater than the first similarity threshold, that is, the similarity of the semantic element body corresponding to each single language in the multi-language is greater than the first similarity threshold, then determine that the confusion risk probability is greater than the preset probability threshold; and, detecting that one of the first similarity and the second similarity is greater than the first similarity threshold and the third similarity is greater than the first similarity threshold, then determine that the confusion risk probability is greater than the preset probability threshold.

[0090] Step d7: If any one of the first similarity and the second similarity is detected to be greater than or equal to the first similarity threshold, and the third similarity is less than the first similarity threshold, then determine the confusion risk probability according to the influence degree of the semantic element body corresponding to the any one similarity on the reference trademark element information.

[0091] Wherein, the method for determining the influence degree specifically includes the following steps: obtaining the first quantity of the minimum semantic elements of the semantic element body corresponding to the any one similarity, and obtaining the second quantity of the minimum semantic elements of the reference trademark element information; determining the influence degree according to the magnitude relationship between the first quantity and the second quantity.

[0092] Exemplarily, if the reference trademark element information is "Tianming Life Insurance", wherein the similarity between "Tianmingren" and the registered trademark "Tianmingren" is greater than the first similarity threshold, and the similarities of other semantic element bodies in the reference trademark element information are less than the first similarity threshold, then obtain the first quantity 3 of the minimum semantic elements of "Tianmingren", and obtain the second quantity 5 of the minimum semantic elements of "Tianming Life Insurance". Since the first quantity is less than the second quantity, it is determined that the influence degree of "Tianmingren" in the reference trademark element information "Tianming Life Insurance" is small, and then it is determined that the confusion risk probability is less than the preset probability threshold.

[0093] Step d8: If it is detected that the first similarity, the second similarity, and the third similarity are all less than the first similarity threshold, then determine that the confusion risk probability is less than the preset probability threshold.

[0094] It can be seen that in this embodiment, when there is a semantic element body in the first combined semantic element body and the second combined semantic element body whose similarity is greater than the first similarity threshold, the confusion risk probability can be directly determined by using the similarities of the semantic element bodies, reducing the judgment of the network popularity of each semantic element body, and can significantly reduce the computational burden of the system while ensuring the accuracy of trademark infringement risk detection, improving the processing efficiency.

[0095] It should be noted that the specific implementation process of this embodiment can refer to the specific implementation process described in the above method embodiment, and will not be described herein again.

[0096] Consistent with the above Figure 2 shown embodiment, please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a terminal device provided by an embodiment of the present application, as Figure 8As shown, the terminal device 10 includes a processor 81, a memory 83, a communication interface 82, and one or more programs 831. The one or more programs 831 are stored in the memory 83 and are configured to be executed by the processor 81. The above programs include those for executing the methods described in the above embodiments.

[0097] An embodiment of the present application also provides a computer storage medium. The computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute some or all of the steps of any of the methods described in the above method embodiments. The above computer includes an electronic device.

[0098] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0099] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above unit division is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0101] The units described as separate components above may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0103] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods in various embodiments of this application. The aforementioned memory includes: USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs, etc., which are various media that can store program codes.

[0104] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (English: Read-Only Memory, abbreviated: ROM), random access memories (English: Random Access Memory, abbreviated: RAM), magnetic disks, or optical discs, etc.

[0105] The above has introduced the embodiments of this application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for detecting compliance of trademark information in multiple contexts of a product, characterized in that, A terminal device applied to an e-commerce platform, wherein the e-commerce platform includes the terminal device and a server, and the method includes: A user's operation of placing a product on the shelf in a product placing management function interface is detected, and reference trademark element information of the product to be placed on the shelf is extracted according to product graphic information of the product to be placed on the shelf, wherein the reference trademark element information includes text information in a first language and text information in a second language, wherein the text information in the first language includes at least two first minimum semantic elements, and the text information in the second language includes at least two second minimum semantic elements. Among them, in at least one mixed semantic element body corresponding to the at least two first minimum semantic elements and the at least two second minimum semantic elements, there is a target mixed semantic element body whose highest similarity with the single language registered trademark is greater than or equal to the first similarity threshold, and in at least one first combined semantic element body corresponding to the at least two first minimum semantic elements, the highest similarity between each first combined semantic element body and the first language registered trademark is lower than the first similarity threshold, in at least one second combined semantic element body corresponding to the at least two second minimum semantic elements, the highest similarity between each second combined semantic element body and the second language registered trademark is lower than the first similarity threshold, and in the semantic element body set, there is a target semantic element body that is the same as the high-heat semantic element body, and the at least one first semantic combined element body is composed of at least two first minimum semantic elements. The at least one second semantic combination element body is composed of at least two second minimum semantic elements, the at least one mixed semantic element body is composed of at least one of the first minimum semantic elements and at least one of the second minimum semantic elements, and two adjacent minimum semantic elements in a single semantic element body are also adjacent in the reference trademark element information; the semantic element body set is the union of the at least one mixed semantic element body, the at least one first combination semantic element body, and the at least one second combination semantic element body, the high-heat semantic element body is a text element body in a text element subset in a work element set of a high-network-heat game work, the product category of the product to be listed belongs to a peripheral product category set, and the peripheral product category set is the union of product categories that can be used as peripheral products of game products; In response to the listing operation, a compliance detection request message carrying the reference trademark element information is sent to the server, and a compliance detection response message is received from the server, wherein the compliance detection response message includes trademark infringement risk warning information, wherein the trademark infringement risk warning information is used to indicate the infringement risk caused by the confusion risk probability of the reference trademark element information being greater than a preset probability threshold, wherein the confusion risk probability refers to the probability of the target mixed semantic element body and the target semantic element body being identified as belonging to the single language registered trademark under the condition of the joint action of the target mixed semantic element body and the target semantic element body; The trademark infringement risk warning information is displayed on the product listing management function interface.

2. The method according to claim 1, wherein The process of creating the compliance detection response message includes: Obtain the set of semantic element bodies according to the reference trademark element information; Perform trademark retrieval operations on the single-language registered trademarks respectively according to each semantic combination element body in the set of semantic element bodies, and obtain multiple similarity degrees. The single-language registered trademarks include the first-language registered trademark and the second-language registered trademark; Determine game works related to each semantic combination element body in the set of semantic element bodies from the Internet, obtain the text element bodies in the text element subset of the work element set of the game works, and obtain the network popularity of the text element bodies; determine the network popularity set of the set of semantic element bodies according to the text element bodies and their network popularity. The network popularity set includes the network popularity of each semantic element body in the set of semantic element bodies; Determine the confusion risk probability according to the multiple similarity degrees and the network popularity set; Generate the compliance detection response message according to the size relationship between the confusion risk probability and the preset probability threshold.

3. The method according to claim 2, wherein The performing trademark retrieval operations on the single-language registered trademarks respectively according to each semantic combination element body in the set of semantic element bodies and obtaining multiple similarity degrees includes: Perform trademark retrieval operations according to the at least one first combined semantic element body and the first-language registered trademark, and obtain the first similarity degree that is the highest in similarity to the at least one first combined semantic element body; Perform the trademark retrieval operations according to the at least one second combined semantic element body and the second-language registered trademark, and obtain the second similarity degree that is the highest in similarity to the at least one second combined semantic element body; Convert a single smallest semantic element in the at least one mixed semantic element body into the first language or the second language, and perform the trademark retrieval operations according to the translated mixed semantic element and the first-language registered trademark or the second-language registered trademark, and obtain the third similarity degree that is the most similar to the translated mixed semantic element body.

4. The method according to claim 3, characterized in that, The determining the confusion risk probability according to the multiple similarity degrees and the network popularity set includes: Detect that both the first similarity degree and the second similarity degree are less than the first similarity threshold, and the third similarity degree is greater than or equal to the first similarity threshold; Obtain at least one remaining semantic element body in the set of semantic element bodies except for the smallest semantic element included in the target mixed semantic element body; Obtain at least one network popularity of the at least one remaining semantic element body from the network popularity set; If there is a remaining semantic element body with a network popularity greater than or equal to the preset network popularity threshold among the at least one remaining semantic element bodies, and it is determined as the target semantic element body, then determine that the confusion risk probability is greater than the preset probability threshold; the network popularity of the high-popularity semantic element is greater than or equal to the preset network popularity threshold; If the network popularities are all less than the preset network popularity threshold, then determine that the confusion risk probability is less than the preset probability threshold.

5. The method according to any one of claims 2 to 4, characterized in that, The process of performing the trademark retrieval operation on a single first combined semantic element body specifically includes the following steps: Retrieve at least one registered trademark from the registered trademarks in the first language that contains at least two first minimum semantic elements of the first combined semantic element body, and the at least two first minimum semantic elements are adjacent in both the first combined semantic element body and the at least one registered trademark; Determine the similarity based on the number of first minimum semantic elements contained in the first combined semantic element body and the number of first minimum semantic elements contained in a single registered trademark; Determine the first similarity as the highest similarity among the at least one similarity.

6. The method according to claim 3, characterized in that, The determining the confusion risk probability according to the plurality of similarities and the network popularity set further includes: If it is detected that at least two of the first similarity, the second similarity, and the third similarity are greater than or equal to the first similarity threshold, then determine that the confusion risk probability is greater than the preset probability threshold; If it is detected that any one of the first similarity and the second similarity is greater than or equal to the first similarity threshold, and the third similarity is less than the first similarity threshold, then determine the confusion risk probability according to the influence degree of the semantic element body corresponding to the any one similarity on the reference trademark element information; If it is detected that the first similarity, the second similarity, and the third similarity are all less than the first similarity threshold, then determine that the confusion risk probability is less than the preset probability threshold.

7. The method according to claim 6, wherein The method for determining the influence degree specifically includes the following steps: Obtain the first quantity of the minimum semantic elements of the semantic element body corresponding to the any one similarity, and obtain the second quantity of the minimum semantic elements of the reference trademark element information; Determine the influence degree according to the magnitude relationship between the first quantity and the second quantity.

8. The method according to claim 1, characterized in that, The extracting the reference trademark element information of the product to be put on the shelf according to the product graphic and text information of the product to be put on the shelf includes: If the confusion risk probability is greater than or equal to the preset probability threshold, then generate the trademark infringement risk prompt information; If the confusion risk probability is less than the preset probability threshold, then generate a trademark detection compliance prompt information, and the compliance detection response message includes the trademark detection compliance prompt information.

9. An e-commerce platform system, characterized in that, It includes a server and a terminal device, and the terminal device is used to execute the step instructions in the method described in any one of claims 1-8.

Images