Pirate link detection method and device, equipment and storage medium

Abstract

The invention relates to the technical field of Internet, and discloses a pirate link detection method and device, equipment and a storage medium. The method comprises the following steps: extracting a network disk name from a network disk link to be detected, and extracting multi-dimensional information to be detected from the network disk name; the multi-dimensional to-be-detected information at least comprises a to-be-detected film name; matching the multi-dimensional information to be detected with a basic information base to obtain a matching result of each dimension; the basic information base stores feature information of a plurality of copyright works; calculating a matching score corresponding to the network disk name according to the matching result of each dimension and the corresponding weight; and identifying whether the network disk link is a pirated link or not according to the matching score. By adopting the method, the pirate link of the network disk can be efficiently and accurately identified, and time, labor and money cost are saved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, apparatus, device and storage medium for detecting pirated links. Background Art

[0002] In the internet age, copyrighted works such as television series, films, novels, and audiobooks are widely available through online platforms for paid access and viewing (or listening). Online streaming services allow users to easily access paid copyrighted works, generating revenue for copyright owners. However, the problem of piracy and infringement of copyrighted works is becoming increasingly serious. Sharing pirated, infringing content through online disk links has become a common method of dissemination, seriously disrupting normal market order, harming the legitimate rights and interests of copyright owners, and causing significant economic losses. Therefore, effective measures are needed to identify pirated links circulating online.

[0003] Currently, pirated link detection is primarily performed manually, either by manually downloading the file corresponding to the network disk link and analyzing its content, or by identifying it based on the network disk name. However, downloading network disk files for analysis is subject to download restrictions imposed by the network disk from which the pirated link originated, making the process cumbersome and inefficient, wasting time, labor, and money. Summary of the Invention

[0004] In view of this, the present application aims to propose a method, apparatus, device and storage medium for detecting pirated links, so as to accurately and efficiently identify pirated links on network disks and save labor costs and monetary costs.

[0005] To achieve the above objectives, the technical solutions of this application are as follows:

[0006] A first aspect of an embodiment of the present application provides a method for detecting pirated links, the method comprising:

[0007] Extracting a network disk name from the network disk link to be detected, and extracting multi-dimensional information to be detected from the network disk name; the multi-dimensional information to be detected includes at least the title of the film to be detected;

[0008] Matching the multi-dimensional information to be detected with a basic information database to obtain matching results in each dimension; the basic information database stores characteristic information of multiple copyrighted works;

[0009] Calculate the matching score of the network disk name based on the matching results of each dimension and the corresponding weights;

[0010] According to the matching score, it is identified whether the network disk link is a pirated link.

[0011] According to a second aspect of an embodiment of the present application, there is provided an apparatus for detecting pirated links, for implementing the steps of the method provided in the first aspect of the embodiment of the present application, the apparatus comprising:

[0012] An information extraction module is configured to extract a network disk name from a network disk link to be detected, and extract information to be detected from the network disk name; the information to be detected includes the title of the film to be detected and at least one of the following: the genre to be detected, the year to be detected, and the number of episodes to be detected;

[0013] a matching module configured to match the information to be detected with a basic information database to obtain a matching result; the basic information database stores characteristic information of multiple copyrighted works;

[0014] The judgment module is configured to calculate a matching score corresponding to the network disk name according to the matching result; compare the matching score with a matching threshold, and determine that the network disk link is a pirated link if the matching score is not less than the matching threshold.

[0015] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method provided in the first aspect of the embodiment of the present application are implemented.

[0016] According to the fourth aspect of the embodiments of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the steps in the method provided in the first aspect of the embodiments of the present application are implemented.

[0017] The method for detecting pirated links provided by this application extracts multiple dimensions of information to be detected from the network disk name, matches the information to be detected in each dimension to obtain corresponding matching results, and then calculates the total matching score based on a comprehensive evaluation of each matching result, thereby achieving rapid identification of whether the network disk link is pirated. There is no need to manually download the file corresponding to the network disk link for judgment, saving time, labor and money costs. In addition, this method evaluates the network disk name from multiple dimensions, calculates the matching score based on the multi-dimensional evaluation results, and thus comprehensively judges whether the network disk link is a pirated link. Compared with traditional manual identification solutions, it can also effectively avoid the situation where different staff members make misjudgments based on their own subjective judgments or only focus on partial information, thereby improving the accuracy of pirated link identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flow chart of a method for detecting pirated links proposed in one embodiment of the present application;

[0020] Figure 2 This is a flow chart for determining a first result in one embodiment of the present application;

[0021] Figure 3 is a partial flow chart for determining a first result in one embodiment of the present application;

[0022] Figure 4 is a schematic diagram of calculating a matching score in one embodiment of the present application;

[0023] Figure 5 This is a schematic diagram of a device for detecting pirated links proposed in one embodiment of the present application;

[0024] Figure 6 FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0027] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0028] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with certain aspects as detailed herein.

[0029] It should be noted that, unless there is any conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0030] Related solutions for detecting pirated links on online disks mainly use manual analysis, which involves manually downloading the corresponding files based on the online disk link and analyzing the content to determine whether they are infringing, or identifying them based on the name of the online disk. The former is due to the restrictions on file downloads imposed by various brands of online disks, such as the need to download an online disk client, or to purchase an online disk membership to download, download speed restrictions, etc., which results in cumbersome operations, low identification efficiency, and a waste of manpower, financial resources, and time. The latter is due to the wide variety of online disk names and content, which often contain a large number of interference elements such as duplicate names and duplicates. Given the differences in experience among different staff members, subjective judgments or focusing on only part of the information can easily lead to misjudgments, and therefore the effect of identifying pirated links is poor.

[0031] This application achieves efficient and accurate identification of pirated links by comprehensively evaluating the feature information of multiple dimensions contained in the network disk name.

[0032] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0033] Figure 1 This is a flow chart of a method for detecting pirated links proposed in one embodiment of the present application. Figure 1 As shown, the method includes:

[0034] S1: Obtaining a first result from the network disk link to be tested, including: extracting the network disk name from the network disk link to be tested, and extracting the information to be tested from the network disk name; the information to be tested includes the title of the film to be tested and at least one of the following: the genre to be tested, the year to be tested, and the number of episodes to be tested;

[0035] S2: matching the information to be detected with a basic information database to obtain a matching result; the basic information database stores characteristic information of multiple copyrighted works;

[0036] S3: Calculate a matching score corresponding to the network disk name based on the matching result;

[0037] S4: Compare the matching score with a matching threshold, and if the matching score is not less than the matching threshold, determine that the network disk link is a pirated link.

[0038] In this embodiment, the network disk name is first extracted from the network disk link to be detected, and multiple dimensions of information are extracted from the network disk name as the information to be detected. Specifically, the information to be detected includes the title of the film and at least one of the following information: genre, year, number of episodes, etc.

[0039] The extracted information to be tested in each dimension is then matched against the characteristic information of each copyrighted work in the basic information database to obtain corresponding matching results. The basic information database stores the characteristic information of all works owned by the copyright owner (i.e., copyrighted works). By matching each piece of information to be tested against the characteristic information of copyrighted works stored in the basic information database, a more comprehensive analysis of the network disk name can be achieved, improving the accuracy of the judgment on whether the network disk link is infringing.

[0040] Furthermore, based on the matching results of each piece of information to be tested, a total matching score for the network disk name is calculated. This matching score is compared with a matching threshold. If the matching score exceeds the matching threshold, the network disk link is determined to be an infringing and pirated link. In practical applications, network disk links determined to be infringing can be added to a list of available complaints for future use.

[0041] In this embodiment, a unified scoring rule is proposed. According to the matching results of the information to be detected in each dimension, the final matching score of the network disk name is determined according to the unified scoring rule, thereby achieving accurate judgment on whether the network disk link is a pirated link. Compared with the traditional manual detection method, this embodiment conducts a comprehensive evaluation based on a unified evaluation standard, which can avoid the situation where different staff members make misjudgments based on their own subjective judgments or only focus on part of the information, thereby improving the accuracy of pirated link detection. In addition, this solution can make infringement judgments based on the network disk link without downloading specific files for analysis. Compared with the traditional manual detection method, it saves a lot of tedious operations, realizes efficient and accurate pirated link detection, and saves time, labor and money costs. By efficiently and accurately identifying infringing network disk links, it helps to protect the intellectual property rights and legal content of copyright owners and protect the value of original content.

[0042] As an implementation manner of the present application, before the above step S1, the method further includes:

[0043] S01-1: Pre-acquire basic features of all copyrighted works; the basic features include: official name, alias, year, number of episodes, and type of work;

[0044] S01-2: Integrate the basic features of each copyrighted work to obtain corresponding structured data; wherein the structured data of at least one copyrighted work includes: multiple years and multiple episodes corresponding to the copyrighted work;

[0045] S01-3: Build a basic information database based on the structured data corresponding to each copyrighted work.

[0046] In one embodiment, a basic information library is pre-built based on each copyrighted work in the copyright information library to provide reference information for matching network disk name information. Specifically, basic features of each copyrighted work are extracted from the copyright information library. Basic features are used to describe information closely related to the copyrighted work itself. For example, for a TV series, basic features include "official name, alias, production year, broadcast year, editing version, number of episodes, work type (e.g., movie, TV series, audiobook, etc.), main creative staff", etc.

[0047] After obtaining the basic features of each copyrighted work, the feature information of copyrighted works with the same official name or alias is integrated, and corresponding structured data is generated for copyrighted works with different names or aliases. For example, the official name of a TV series is "Dream of the Red Chamber" and its alias is "The Story of the Stone". There are two identical TV series in the copyright information database. Due to different editing versions, the number of episodes and broadcast years are inconsistent. The names are "Dream of the Red Chamber" and "The Story of the Stone". During the integration, the two are combined into one TV series, and the official name, alias, and the number of episodes and broadcast years corresponding to each editing version are recorded in the structured data. A basic information database is constructed based on the structured data of each copyrighted work to facilitate the subsequent extraction of corresponding information for feature matching.

[0048] As an implementation manner of the present application, before the above step S1, the method further includes:

[0049] S02-1: Pre-acquire auxiliary features of all copyrighted works; the auxiliary features include the identifier of the episode set;

[0050] S02-2: Obtaining multiple auxiliary matching words based on auxiliary features of each copyrighted work; the auxiliary matching words are related to the type of work;

[0051] S02-3: Construct an auxiliary vocabulary based on each auxiliary matching word.

[0052] In one embodiment, auxiliary features of copyrighted works are extracted from a copyright information database. Based on these auxiliary features, auxiliary matching terms are generated to construct an auxiliary vocabulary for matching common information. Auxiliary features are descriptive information common to all copyrighted works, with little relevance to the copyrighted works themselves. These include identifiers for episode collections. For example, for a television series, the identifiers for episode collections might be "part, season, collection, complete series," etc. Auxiliary matching terms generated based on the identifiers for episode collections might include "xx collection, season x, part x, complete x series."

[0053] During the subsequent detection process, if the cloud disk name matches the auxiliary matching word, the type of the cloud disk name to be detected can be determined based on the auxiliary matching word. For example, if the cloud disk name hits the auxiliary matching word "American drama", it can be inferred that the type of the cloud disk name to be detected is a TV series.

[0054] As an implementation manner of the present application, before the above step S1, the method further includes:

[0055] S03: Building a replacement word library based on the special characters in the pirated link and the corresponding replacement characters; at least one replacement character in the replacement word library has corresponding special characters.

[0056] In one embodiment, a replacement word library is also constructed based on the special characters and corresponding replacement characters present in the pirated links. The replacement characters are used to replace the special characters hit in the network disk name, so as to extract the corresponding information to be detected from the network disk name. Special characters include content that has no effect on information matching, as well as some characters used to interfere with the title of the film. For example, special characters include "の, HTML tags, clarity (such as 1080p), DVD, completion, introduction, plot summary", etc.

[0057] The embodiment of the present application matches multiple dimensions such as film title, type, year, number of episodes, etc., and thus conducts a comprehensive evaluation based on the matching results of multiple dimensions to improve the accuracy of pirated link detection.

[0058] As an implementation manner of the present application, the multi-dimensional information to be detected includes: the title of the film to be detected, and the type to be detected, the year to be detected, and the number of episodes to be detected of the title to be detected;

[0059] In the above step S2, "matching the multi-dimensional information to be detected with the basic information database to obtain matching results in each dimension" specifically includes:

[0060] S21: Match the title of each copyrighted work in the basic information database with the title of the film to be detected character by character to obtain a first result; the title of the copyrighted work includes: the official name and an alias; the first result is: complete match, partial match or no match;

[0061] S22: Based on the fully matched and partially matched copyrighted works in the first result, perform at least one of the following matching operations:

[0062] S23: Matching the work type of each copyrighted work with the type to be detected to obtain a second result; the second result is: match or mismatch;

[0063] S24: Matching the year of each copyrighted work with the year to be detected to obtain a third result; the third result is: match or mismatch;

[0064] S25: Match the number of episodes of each copyrighted work with the number of episodes to be detected to obtain a fourth result; the fourth result is: match or mismatch.

[0065] Pirated online disk names often contain variant titles, meaning extra characters have been inserted into the original title. Traditional matching methods make it difficult to accurately match these variant titles to the corresponding copyrighted works. Therefore, this embodiment uses a character-by-character matching method to match the titles to be detected in the online disk link.

[0066] In this embodiment, the title of the film to be detected, the type to be detected, the year to be detected, and the number of episodes to be detected in the network disk name are matched with the basic information library respectively to obtain corresponding matching results. Specifically, the title of each copyrighted work in the basic information library (including the official name and alias) is first split into single characters, and then the characters are matched with the title of the film to be detected in the order of the characters to obtain the first result. There are three possible situations for the first result: complete match, partial match, and no match.

[0067] Furthermore, for copyright works whose first results are complete matches or partial matches, the work types, years, and episodes of these three copyright works are further matched with the types to be detected, the years to be detected, and the episodes to be detected to obtain corresponding matching results.

[0068] As an implementation manner of the present application, before the above step S1, the method further includes:

[0069] S101: Match the network disk name with a replacement word library; the replacement word library stores a plurality of special characters and corresponding replacement characters;

[0070] S102: When the network disk name contains a special character, update the network disk name based on a replacement character corresponding to the special character;

[0071] S103: extracting the information to be detected from the network disk name specifically includes: extracting the information to be detected from the updated network disk name.

[0072] In one embodiment, before extracting the information to be detected from the name of the network disk, the name of the network disk is matched with a replacement word library, and the special characters included in the name of the network disk are detected. When the special characters in the name of the network disk are hit, the replacement characters corresponding to the special characters stored in the replacement word library are used to replace the special characters existing in the name of the network disk, and the name of the network disk is updated. For example, special characters such as "HTML tags, clarity, DVD, completed" in the name of the network disk are replaced with empty characters, and the Japanese symbol "の" in the name of the network disk is replaced with the Chinese character "的". After updating the name of the network disk with the replacement characters, the corresponding information to be detected is extracted from the name of the network disk.

[0073] In this embodiment, before extracting the information to be detected from the name of the network disk, the name of the network disk is first cleaned with replacement characters to remove the interference information irrelevant to the information to be detected in the name of the network disk and correct the title of the film, reducing the difficulty of matching the title of the film to be detected and further improving the detection efficiency of pirated links.

[0074] As an implementation manner of the present application, in the above step S21, "each character is matched with the title of the film to be detected character by character to obtain a first result", which specifically includes:

[0075] S211: Each character in the name of the copyright work is used as a character to be matched, and the character to be matched is sequentially matched with each character in the title of the film to be detected;

[0076] S212: When the character to be matched first hits the same character in the title of the film to be detected, record the hit position of the hit same character in the title of the film to be detected;

[0077] S213: For any two adjacent characters in the name of the copyright work, if the previous character does not hit the same character in the title of the film to be detected, stop matching the name of the copyright work; if the previous character hits the same character in the title of the film to be detected, continue to match the next character with all characters after the previous hit position in the title of the film to be detected;

[0078] S214: After all characters in the name of the copyright work are matched, a first result is obtained based on the hit positions corresponding to each character in the name of the copyright work.

[0079] In the above embodiment, the title of the film to be detected is matched by a character-by-character matching method, and the specific steps are as follows:

[0080] (1) The title of the film to be detected is matched with the first character of each copyright work in the basic information library in a traversal manner;

[0081] (2) determining whether the first character hits the same character in the title of the film to be detected; if so, recording the corresponding hit position of the first same character in the title of the film to be detected;

[0082] (3) For any character of each copyrighted work, if the previous character does not match the same character in the title of the film to be detected, then the character matching of the copyrighted work will be stopped and it will be determined that the copyrighted work does not match the network disk name;

[0083] (4) If the previous character of any character in the copyrighted work matches the same character, then the character is determined as the next character to be matched according to the order of the characters, and the character to be matched is matched with each character after the previous hit position in the title of the film to be tested until all characters in the copyrighted work are matched;

[0084] (5) When all characters are matched, a first result is obtained based on the hit positions corresponding to the recorded characters. Since the title to be tested is usually a variant, there may be a partial match between the title to be tested and a copyrighted work in the basic information database. Based on this, in this embodiment, whether the first result is a complete match, a partial match, or a mismatch is determined based on the hit position of the copyrighted work with the title to be tested during the matching process.

[0085] As an implementation of the present application, the above step S214 of "obtaining a first result based on the hit position corresponding to each character in the title of the copyrighted work" includes:

[0086] S2141: If any character does not have a corresponding hit position, determine the first result as not matching;

[0087] S2142: When all characters have corresponding hit positions, determining whether there are redundant characters in the title to be detected;

[0088] S2143: If there are no extra characters, determine that the first result is a complete match;

[0089] S2144: If there are extra Chinese characters, determine the first result as not matching;

[0090] S2145: If there are extra non-Chinese characters, check whether the extra non-Chinese characters are located between two adjacent hit positions; if the extra non-Chinese characters are located between two adjacent hit positions, determine the first result to be a complete match; if the extra non-Chinese characters are located before the first hit position or after the last hit position, determine the first result to be a partial match.

[0091] In one embodiment, the first result is determined based on the hit positions corresponding to each character in the name of the copyrighted work. Figure 2 It is a flowchart for determining the first result in an embodiment of the present application. As Figure 2 shown, first, it is detected whether each character in the name of the copyrighted work has a corresponding hit position. In the case where there is a character in the copyrighted work without a hit position, the first result is determined to be unmatched. For example, the copyrighted work is "Journey to the West" and the name of the video to be detected is "Romance of the Western Chamber", and the character "游" has no corresponding hit position.

[0092] In the case where all characters have corresponding hit positions, it is determined whether there are any extra characters in the name of the video to be detected other than the hit identical characters. If there are no extra characters in the name of the video to be detected, it means that the name of the copyrighted work completely matches the name of the video to be detected.

[0093] If there are extra characters in the name of the video to be detected, the first result is further determined based on the coding attributes of the extra characters and their relative positions to the hit positions. Specifically, first, it is determined whether the extra characters are Chinese characters. If the extra characters are Chinese characters, the first result is determined to be unmatched. For example, the copyrighted work is "Journey to the West" and the name of the video to be detected is "Journey to the West Diary", with the extra Chinese character "日" appearing.

[0094] If the extra characters are non - Chinese characters, the relative positions of the extra characters to the hit positions are further judged. The extra characters may be located between adjacent hit positions, before the first hit position, or after the last hit position. For the case where non - Chinese characters are located between adjacent hit positions, the first result is determined to be a complete match. For example, the copyrighted work is "Journey to the West" and the name of the video to be detected is "西@#%游记", with non - Chinese characters "@#%". For the case where non - Chinese characters are located before the first hit position or after the last hit position, the first result is determined to be a partial match. For example, the copyrighted work is "Journey to the West" and the name of the video to be detected is "@#%Journey to the West".

[0095] Optionally, for the case where the name of the copyrighted work is in English, the determination process is similar to that of the Chinese name. When detecting extra characters, it is mainly detected whether the extra characters are English characters. For extra English characters, the first result is determined to be unmatched. For extra non - English characters, the determination is further made according to the positions of the extra characters, which will not be elaborated here.

[0096] As an implementation manner of the present application, in the above step S214, "obtaining the first result based on the hit positions corresponding to each character in the name of the copyrighted work" further includes:

[0097] S2144': If there are extra Chinese characters, detect whether the extra Chinese characters are the same as the adjacent characters; if the extra Chinese characters are the same as the adjacent characters, determine the first result as a complete match; if the extra Chinese characters are not the same as the adjacent characters, determine the first result as a mismatch.

[0098] In one embodiment, some pirated titles use repeated characters to interfere with the matching of film titles. For example, the network disk name in the pirated link changes "Journey to the West" to "Journey to the West". For this type of variant film title, traditional matching methods will interpret the presence of redundant Chinese characters in the film title as a different work, resulting in misjudgment. In this embodiment, in order to deal with the situation of repeated Chinese characters, after determining the presence of redundant Chinese characters, it is necessary to further determine whether the redundant Chinese characters are duplicates, that is, to detect whether the redundant Chinese characters are the same as the adjacent characters.

[0099] Figure 3 This is a partial flow chart of determining the first result in one embodiment of the present application. Figure 3 As shown, if there are redundant Chinese characters in the title to be tested, the Chinese characters are checked to see if they are identical to the adjacent characters. If the redundant Chinese characters are identical to the adjacent characters, the redundant Chinese characters are determined to be repeated characters. If the title to be tested only contains redundant and repeated Chinese characters, the first result is determined to be an exact match. For example, if the copyrighted work is "Journey to the West" and the title to be tested is "Journey to the West", the first result is determined to be an exact match.

[0100] If the extra Chinese characters are different from the adjacent characters, it means that the extra Chinese characters are not repeated characters. In this case, the first result is determined to be a mismatch. For example, if the copyrighted work is "Journey to the West" and the title of the film to be tested is "Journey to the West Diary", the first result is determined to be a mismatch.

[0101] The method provided in this embodiment further detects redundant Chinese characters in the case of repeated characters in the film title to be detected, thereby achieving accurate recognition of the special type of pirated links containing repeated Chinese characters and further reducing the misjudgment rate.

[0102] As an implementation of the present application, the above step S24 of "matching the year of each copyrighted work with the year to be detected to obtain a third result" specifically includes:

[0103] S241: If the difference between the year of the copyrighted work and the year to be detected is not greater than a first threshold, determine that the third result is a match;

[0104] The above step S25 specifically includes:

[0105] S251: When the difference between the number of episodes of the copyrighted work and the number of episodes to be detected is not greater than a second threshold, determine that the fourth result is a match.

[0106] In one embodiment, there may be differences between the production year and the release (broadcast) year of the copyrighted work, and there may also be discrepancies in the number of episodes of different edited versions. In order to avoid misjudging the matching copyrighted works, an error range is set when matching the year and the number of episodes. Specifically, when the difference between the year of the copyrighted work and the year to be detected is not greater than a first threshold (for example, 2 years), the third result is determined to be a match. When the difference between the number of episodes of the copyrighted work and the number of episodes to be detected is not greater than a second threshold (for example, 8 episodes), the fourth result is determined to be a match.

[0107] Optionally, when a new editing version and new year information appear in a copyrighted work, the number of episodes corresponding to the new editing version and the new year information are added to the basic information library to keep the basic information library updated in real time and reduce the misjudgment rate.

[0108] As an implementation of the present application, the above step S3 specifically includes:

[0109] S31: Obtaining a scoring weight for the first result, wherein the scoring weight is determined based on multiple factors; the multiple factors include at least: whether the first result is a match, and the relationship between the position of the redundant characters in the title to be detected and the hit position in the title to be detected;

[0110] S32: Obtaining score weights for the second result, the third result, and the fourth result; wherein the score weights for the second and third results being matches are lower than a reference weight value, and the score weights for the second and third results being mismatches are higher than the reference weight value; and the score weights for the fourth result being either a match or a mismatch are both lower than the reference weight value;

[0111] S33: Calculate a matching score corresponding to the network disk name based on each result in the matching results and the corresponding scoring weight.

[0112] In one embodiment, after matching the information to be detected in multiple dimensions of the network disk name, the total matching score is calculated based on the matching results. In this embodiment, different scoring weights are set for the matching results of different dimensions. Among them, the scoring weight of the matching result (first result) of the title to be detected is determined based on multiple factors. Optionally, the multiple factors used to determine the scoring weight of the first result include: whether the first result is a match; and the encoding attributes of the redundant characters in the title to be detected; and the relationship between the position of the redundant characters in the title to be detected and the hit position.

[0113] Specifically, a corresponding benchmark value is set according to whether the first result is a match (including a complete match and a partial match) or a mismatch, and then, on the basis of the benchmark value, the final score of the dimension of the title to be detected is adjusted according to the redundant characters in the title to be detected. The deduction weight is determined based on whether the encoding attribute of the redundant characters is a non-Chinese character (for example, an English character or a punctuation mark), and the positional relationship between the position of the redundant characters in the title to be detected and the hit position. Based on the deduction weight, the corresponding score is deducted from the benchmark value of the first result to obtain the final score. Specifically, if the redundant characters are non-Chinese characters, and the redundant characters are before the first hit position or after the last hit position, it indicates that the first result is a partial match. In the case of a partial match, the corresponding score is deducted based on the pre-set deduction weight. If the redundant characters are non-Chinese characters, and the redundant characters are between two adjacent hit positions, it indicates that the first result is a complete match. In the case of a complete match, the deduction weight is set to 0, i.e., no points are deducted.

[0114] For the matching result of the type to be detected (second result), the matching result of the year to be detected (third result) and the matching result of the number of episodes to be detected (fourth result), it is determined based on whether they match.

[0115] In practice, streaming platforms are more strict about distinguishing between types of copyrighted works, but are generally more lenient regarding years and episodes. This is because copyrighted works with the same title can exist in multiple genres (e.g., TV series, movies, audiobooks, etc.), and streaming platforms typically only hold copyrights for some of these genres. For example, a streaming platform might only hold the copyright to TV series A, but not the copyright to movie A of the same name. As for years, because classic works are constantly being remade or republished, copyrights from different years may belong to different streaming platforms. Therefore, to strictly distinguish between copyrighted works of different genres and years and avoid misjudgments, higher scoring weights are assigned when the second and third results are mismatched compared to when they are matched. Regarding the number of episodes, the same copyrighted work may have multiple edited versions, resulting in significant discrepancies in the number of episodes. For example, a TV series may have multiple edited versions, including DVD, TV, and webcast versions, each with a different number of episodes. Therefore, it is necessary to reduce the impact of the episode number matching result on the overall matching score, assigning a lower scoring weight regardless of whether the episode number matches or does not match.

[0116] Furthermore, to enhance the impact of the scoring weights of each dimension on the overall match score under different outcome conditions, a weight reference value is used as the critical value for the scoring weights. Specifically, the scoring weights of the second and third results are set to values ​​higher than the weight reference value if they are mismatches, and lower than the weight reference value if they are matches. The scoring weight of the fourth result is set to a value lower than the weight reference value if it is a match or mismatch.

[0117] Figure 4 FIG. 1 is a schematic diagram of calculating a matching score in an embodiment of the present application. Figure 4 As shown, in one embodiment, the scoring weights for each dimension are set as follows:

[0118] (1) For the first result of the Chinese title match, the benchmark value is set to 6, and the scoring weights are set as follows:

[0119] In case of mismatch, 0 points were scored;

[0120] In the case of a complete match or partial match, 6 points are scored; on this basis, if there are non-Chinese characters before the first hit position, 2 points are deducted; if non-Chinese characters appear after the last hit position, 2 points are deducted; if there are non-Chinese characters between two adjacent hit positions, no points are deducted.

[0121] Optionally, taking into account the special case that the movie title has only a single character, for a completely matched single-character movie title, +1 point is added to the base value of 6, that is, the first result of the completely matched single-character movie title has a final score of 7 points.

[0122] (2) For the second result of type matching, the base value is set to 4, and the scoring weights are set as follows:

[0123] In the case of a match, 2 points are awarded;

[0124] In case of mismatch, -6 points are scored;

[0125] If there is no matching result for this dimension, a score of 0 is given.

[0126] (3) For the third result of year matching, the base value is set to 2, and the scoring weights are set as follows:

[0127] In the case of a match, 1 point is scored;

[0128] In case of mismatch, -4 points are scored;

[0129] If there is no matching result for this dimension, a score of 0 is given.

[0130] (4) For the fourth result of episode matching, the base value is set to 4, and the scoring weights are set as follows:

[0131] In the case of a match, 1 point is scored;

[0132] In case of mismatch, -2 points are scored;

[0133] If there is no matching result for this dimension, a score of 0 is given.

[0134] In this embodiment, the final scores of the matching results of each dimension are summed to obtain the total matching score of the network disk name. The matching score of the network disk name is compared with the matching threshold (for example, 6 points). If the matching score is greater than or equal to the matching threshold, the network disk link is determined to be a pirated link. Based on the characteristics of each dimensional information in actual application, corresponding weights are set to achieve accurate evaluation of the dimensional information of the network disk name, thereby improving the accuracy of pirated link detection.

[0135] As an implementation manner of the present application, after "comparing the matching score with the matching threshold" in step S4, the following steps are further included:

[0136] S5: Obtaining the audit result of the network disk link, determining whether there is any misjudgment based on the audit result, and recording the number of misjudgments;

[0137] S6: When the number of misjudgments within the detection time period reaches a warning threshold, lower the first threshold or the second threshold.

[0138] In one embodiment, the network disk links that are determined to be pirated links are further manually reviewed to determine whether there are any misjudgments. By manually reviewing the determined network disk links and analyzing the factors that lead to misjudgments, it is possible to quickly understand the behavior patterns and trends of pirated links and better specify the detection and judgment strategies. In this embodiment, the error range corresponding to the year and episode number is adjusted based on the review results of the manual review. If the misjudgment rate is high in a nearby period of time, the first threshold or the second threshold is correspondingly lowered to improve the accuracy of the detection.

[0139] For example, with the rapid development of self-made short dramas, when a new TV series is broadcast, a self-made short drama with the same name as the copyrighted TV series may appear on the streaming platform in the same year. Based on this, considering that the number of episodes of the short drama is different from the number of episodes of the copyrighted TV series with the same name, the second threshold is lowered and a stricter matching strategy is adopted for the episode dimension to reduce the occurrence of misjudgments.

[0140] As an implementation manner of the present application, in the above step S1, “extracting the information to be detected from the network disk name” specifically includes:

[0141] S11: Matching the network disk name with an auxiliary vocabulary; the auxiliary vocabulary stores auxiliary matching words related to the work type;

[0142] S12: When the network disk name matches any auxiliary matching word related to the work type, the type to be detected of the network disk name is determined according to the auxiliary matching word.

[0143] In one embodiment, in addition to extracting the information to be detected in a specified dimension, the network disk name is also matched against an auxiliary vocabulary to determine whether the network disk name contains auxiliary matching words. The auxiliary matching words can be used to infer the type of network disk name to be detected. If the type of network disk name to be detected is missing, the auxiliary matching words can be used to determine the type of network disk name to be detected for subsequent matching, thereby increasing the dimensional information used for evaluation and improving the accuracy of the detection results.

[0144] For example, the network disk name of a TV series does not contain the type information of "TV series, drama", but contains the auxiliary matching word "xx episode". Based on the auxiliary matching word, it can be determined that the type to be detected of the network disk name is "TV series".

[0145] As an implementation manner of the present application, before "extracting the information to be detected from the network disk name" in the above step S1, the following steps are further included:

[0146] S103: Detect whether the network disk name includes a content qualifier;

[0147] S104: If the network disk name includes a content qualifier, determine whether the network disk name is within the copyright scope based on the content qualifier;

[0148] S105: If the network disk name is outside the copyright scope, determine that the network disk link is not a pirated link;

[0149] S106: If the network disk name is within the copyright scope, extract the information to be detected from the network disk name.

[0150] In one embodiment, before extracting multiple dimensions of information to be detected from the network disk name, the process also includes detecting whether the network disk name contains content qualifiers. The network disk name may describe the content of the file package. In this embodiment, considering that streaming media platforms usually only own some types of copyrights, by detecting whether the network disk name contains content qualifiers, it is pre-determined whether the information to be detected needs to be extracted for subsequent matching. Content qualifiers include "only, include, contain, contain, not contain", etc.

[0151] For example, a certain streaming media platform only owns the copyright of TV drama B, but does not own the copyright of the audiobook B with the same name. When it is detected that the content qualifier "only" is included in the name of the network disk, it is recognized that the file in the name of the network disk is "only an audiobook", so it is determined that the name of the network disk is not within its own copyright scope, and thus it is judged that it is not a pirated link and there is no need to further extract the information to be detected for subsequent matching.

[0152] If it is detected that the content qualifier "including" is included in the name of the network disk, and it is recognized that the file in the title of the network disk includes an audiobook, it is determined to be within the copyright scope, and it is necessary to further extract the information to be recognized for matching. Moreover, when the matching score reaches the matching threshold, it is also necessary to further download all the files in the file package for content analysis.

[0153] By pre-detecting the content qualifier in the name of the network disk, it is possible to save the operations of extracting and matching the information of the network disk names outside the copyright scope, and further improve the detection efficiency of pirated links.

[0154] Based on the same inventive concept, an embodiment of the present application provides a device for detecting pirated links. Refer to Figure 5 , Figure 5 is a schematic diagram of a device 500 for detecting pirated links proposed in an embodiment of the present application.

[0155] As Figure 5 shown, the device includes: [[ID=(19]]

[0156] An information extraction module 501, configured to extract the name of the network disk from the network disk link to be detected, and extract multi-dimensional information to be detected from the name of the network disk; the multi-dimensional information to be detected at least includes the name of the film to be detected;

[0157] A matching module 502, configured to match the multi-dimensional information to be detected with a basic information library to obtain matching results for each dimension; the basic information library stores the characteristic information of multiple copyrighted works;

[0158] A judgment module 503, configured to calculate the matching score corresponding to the name of the network disk according to the matching results of each dimension and the corresponding weights; and identify whether the network disk link is a pirated link according to the matching score.

[0159] As an implementation manner of the present application, the multi-dimensional information to be detected includes: the name of the film to be detected, and the type to be detected, the year to be detected, and the number of episodes to be detected of the name of the film to be detected; the matching module 502 is specifically configured to perform the following steps:

[0160] Matching the title of each copyrighted work in the basic information database with the title of the film to be detected character by character to obtain a first result; the title of the copyrighted work includes: the official name and an alias; the first result is: complete match, partial match or no match;

[0161] Based on the fully matched and partially matched copyright works in the first result, perform at least one of the following matching operations:

[0162] Matching the work type of each copyrighted work with the type to be detected to obtain a second result; the second result is: match or mismatch;

[0163] Matching the year of each copyrighted work with the year to be detected to obtain a third result; the third result is: match or no match;

[0164] The number of episodes of each copyrighted work is matched with the number of episodes to be detected to obtain a fourth result; the fourth result is: match or mismatch.

[0165] As an embodiment of the present application, the matching module 502 is configured to match the name of each copyrighted work in the basic information database with the title of the film to be detected character by character to obtain a first result, specifically including:

[0166] Taking each character in the title of the copyrighted work as a character to be matched, and sequentially matching the character to be matched with each character in the title of the film to be detected;

[0167] When the character to be matched hits the same character in the title to be detected for the first time, recording the hit position of the same character in the title to be detected;

[0168] For any two adjacent characters of the copyrighted work's title, if the preceding character does not match the same character in the title to be detected, then stop matching the copyrighted work's title; if the preceding character matches, then check whether the redundant non-Chinese character is located between the two adjacent hit positions; if the redundant non-Chinese character is located between the two adjacent hit positions, then determine the first result as a complete match;

[0169] If the extra non-Chinese characters are located before the first hit position or after the last hit position, the first result is determined to be a partial match.

[0170] As an embodiment of the present application, the matching module 502 is configured to obtain a first result based on the hit position corresponding to each character in the title of the copyrighted work, and further includes:

[0171] If there are redundant Chinese characters, detecting whether the redundant Chinese characters are identical to adjacent characters;

[0172] In the case where the redundant Chinese characters are identical to the adjacent characters, the first result is determined to be a complete match;

[0173] In the case that the redundant Chinese characters are different from the adjacent characters, the first result is determined to be mismatched.

[0174] As an implementation manner of the present application, the judgment module 503 is configured to calculate the matching score corresponding to the network disk name based on the matching results and corresponding weights of each dimension, including:

[0175] Obtaining a scoring weight for the first result, the scoring weight being determined based on a plurality of factors; the plurality of factors including at least: whether the first result is a match, and a relationship between a position of the redundant characters in the title to be detected and a hit position in the title to be detected;

[0176] Obtaining score weights for the second result, the third result, and the fourth result; wherein, if the second result and the third result are matches, the score weights are lower than a reference weight value, and if the second result and the third result are mismatches, the score weights are higher than the reference weight value; and if the fourth result is a match or a mismatch, the score weights are both lower than the reference weight value;

[0177] Calculate the matching score of the network disk name based on each result in the matching results and the corresponding scoring weight.

[0178] As an embodiment of the present application, the judgment module 503 is configured to match the year of each copyrighted work with the year to be detected to obtain a third result, specifically including: if the difference between the year of the copyrighted work and the year to be detected is not greater than a first threshold, determining that the third result is a match;

[0179] The judgment module 503 is configured to match the number of episodes of each copyrighted work with the number of episodes to be detected to obtain a fourth result, specifically including: when the difference between the number of episodes of the copyrighted work and the number of episodes to be detected is not greater than a second threshold, determining that the fourth result is a match.

[0180] As an embodiment of the present application, the apparatus 500 further includes an adjustment module configured to perform the following steps:

[0181] Obtaining the audit result of the network disk link, determining whether there is a misjudgment based on the audit result, and recording the number of misjudgments;

[0182] When the number of misjudgments within the detection time period reaches the warning threshold, the first threshold or the second threshold is lowered.

[0183] As an embodiment of the present application, the apparatus 500 further includes a first management module configured to perform the following steps:

[0184] Obtaining basic features of all copyrighted works in advance; the basic features include: official name, alias, year, number of episodes, and type of work;

[0185] Integrate the basic features of each copyrighted work to obtain corresponding structured data; wherein the structured data of at least one copyrighted work includes: multiple years and multiple episodes corresponding to the copyrighted work;

[0186] Build a basic information database based on the structured data corresponding to each copyrighted work.

[0187] As an implementation manner of the present application, the information extraction module 501 is configured to extract the information to be detected from the network disk name, and further includes:

[0188] Matching the network disk name with an auxiliary vocabulary library; the auxiliary vocabulary library stores auxiliary matching words related to the work type;

[0189] In the case that the network disk name hits any auxiliary matching word related to the work type, the type to be detected of the network disk name is determined according to the auxiliary matching word.

[0190] As an implementation manner of the present application, the apparatus 500 further includes a second management module configured to perform the following steps:

[0191] Acquire auxiliary features of all copyrighted works in advance; the auxiliary features include an identifier of the episode collection;

[0192] Obtaining multiple auxiliary matching words based on auxiliary features of each copyrighted work; the auxiliary matching words are related to the type of the work;

[0193] An auxiliary vocabulary is constructed based on each auxiliary matching word.

[0194] As an embodiment of the present application, the apparatus 500 further includes a first pre-processing module configured to perform the following steps:

[0195] Detecting whether the network disk name includes a content qualifier;

[0196] If the network disk name includes a content qualifier, determining whether the network disk name is within the copyright scope based on the content qualifier;

[0197] If the network disk name is outside the copyright scope, it is determined that the network disk link is not a pirated link;

[0198] If the network disk name is within the copyright scope, the information to be detected is extracted from the network disk name.

[0199] As an embodiment of the present application, the apparatus 500 further includes a second pre-processing module configured to perform the following steps:

[0200] Matching the network disk name with a replacement word library; the replacement word library stores a plurality of special characters and corresponding replacement characters;

[0201] In the case where the network disk name contains special characters, updating the network disk name based on the replacement characters corresponding to the special characters;

[0202] The information extraction module 501 is further configured to extract the information to be detected from the updated network disk name.

[0203] As an embodiment of the present application, the device 500 further includes a third management module, which is configured to construct a replacement vocabulary based on special characters and corresponding replacement characters in the pirated link; at least one replacement character in the replacement vocabulary has corresponding multiple special characters.

[0204] Based on the same inventive concept, an embodiment of the present application provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the method for detecting pirated links as described in any of the above embodiments of the present application are implemented.

[0205] Based on the same inventive concept, an embodiment of the present application provides an electronic device, referring to Figure 6 , Figure 6 Schematic diagram of an electronic device according to one embodiment of the present application. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the steps of the method for detecting pirated links as described in any of the above embodiments of the present application.

[0206] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0207] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0208] For the sake of simplicity, the method embodiments are described as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and components involved are not necessarily required by this application.

[0209] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the embodiments of the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0211] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0212] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0213] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the underlying inventive concepts. Therefore, this application is intended to include the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0214] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0215] The above is a detailed introduction to the method, device, equipment and storage medium for detecting pirated links provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for detecting pirated links, characterized in that: include: Extracting a network disk name from the network disk link to be detected, and extracting multi-dimensional information to be detected from the network disk name; the multi-dimensional information to be detected includes at least the title of the film to be detected; Matching the multi-dimensional information to be detected with a basic information database to obtain matching results in each dimension; the basic information database stores characteristic information of multiple copyrighted works; Calculate the matching score of the network disk name based on the matching results of each dimension and the corresponding weights; According to the matching score, it is identified whether the network disk link is a pirated link.

2. The method for detecting pirated links according to claim 1, characterized in that: The multi-dimensional information to be detected includes: the title of the film to be detected, and the genre to be detected, the year to be detected, and the number of episodes to be detected of the film to be detected; Matching the multi-dimensional information to be detected with the basic information database to obtain matching results for each dimension, specifically including: Matching the title of each copyrighted work in the basic information database with the title of the film to be detected character by character to obtain a first result; the title of the copyrighted work includes: the official name and an alias; the first result is: complete match, partial match or no match; Based on the fully matched and partially matched copyright works in the first result, perform at least one of the following matching operations: Matching the work type of each copyrighted work with the type to be detected to obtain a second result; the second result is: match or mismatch; Matching the year of each copyrighted work with the year to be detected to obtain a third result; the third result is: match or no match; The number of episodes of each copyrighted work is matched with the number of episodes to be detected to obtain a fourth result; the fourth result is: match or mismatch.

3. The method for detecting pirated links according to claim 2, characterized in that: Matching the title of each copyrighted work in the basic information database with the title of the film to be detected character by character to obtain a first result, including: Taking each character in the title of the copyrighted work as a character to be matched, and sequentially matching the character to be matched with each character in the title of the film to be detected; When the character to be matched hits the same character in the title to be detected for the first time, recording the hit position of the same character in the title to be detected; For any two adjacent characters of the copyrighted work's title, if the preceding character does not match the same character in the title to be detected, then stop matching the copyrighted work's title; if the preceding character does match the same character in the title to be detected, then continue matching the following character with all characters after the preceding character in the title to be detected; After all characters in the name of the copyrighted work are matched, a first result is obtained based on the hit position corresponding to each character in the name of the copyrighted work.

4. The method for detecting pirated links according to claim 3, wherein: Obtaining a first result based on the hit positions corresponding to the characters in the title of the copyrighted work includes: If any character does not have a corresponding hit position, the first result is determined to be a mismatch; In the case that all characters have corresponding hit positions, determining whether there are redundant characters in the title to be detected; If there are no extra characters, the first result is determined to be a complete match; If there are extra Chinese characters, the first result is determined to be mismatched; If there are extra non-Chinese characters, then detecting whether the extra non-Chinese characters are located between two adjacent hit positions; if the extra non-Chinese characters are located between the two adjacent hit positions, then determining that the first result is a complete match; If the extra non-Chinese characters are located before the first hit position or after the last hit position, the first result is determined to be a partial match.

5. The method for detecting pirated links according to claim 4, characterized in that: Obtaining a first result based on the hit position corresponding to each character in the title of the copyrighted work, further comprising: If there are redundant Chinese characters, detecting whether the redundant Chinese characters are identical to adjacent characters; In the case where the redundant Chinese characters are identical to the adjacent characters, the first result is determined to be a complete match; In the case that the redundant Chinese characters are different from the adjacent characters, the first result is determined to be mismatched.

6. The method for detecting pirated links according to any one of claims 4 or 5, characterized in that: Calculate the matching score corresponding to the network disk name based on the matching results and corresponding weights of each dimension, including: Obtaining a scoring weight for the first result, the scoring weight being determined based on a plurality of factors; the plurality of factors including at least: whether the first result is a match, and a relationship between a position of the redundant characters in the title to be detected and a hit position in the title to be detected; Obtaining score weights for the second result, the third result, and the fourth result; wherein, if the second result and the third result are matches, the score weights are lower than a reference weight value, and if the second result and the third result are mismatches, the score weights are higher than the reference weight value; and if the fourth result is a match or a mismatch, the score weights are both lower than the reference weight value; Calculate the matching score of the network disk name based on each result in the matching results and the corresponding scoring weight.

7. The method for detecting pirated links according to claim 6, characterized in that: Matching the year of each copyrighted work with the year to be detected to obtain a third result, including: if the difference between the year of the copyrighted work and the year to be detected is not greater than a first threshold, determining the third result to be a match; Matching the number of episodes of each copyrighted work with the number of episodes to be detected to obtain a fourth result, including: when the difference between the number of episodes of the copyrighted work and the number of episodes to be detected is not greater than a second threshold, determining that the fourth result is a match.

8. The method for detecting pirated links according to claim 7, characterized in that: After comparing the matching score with the matching threshold, the method further comprises: Obtaining the audit result of the network disk link, determining whether there is a misjudgment based on the audit result, and recording the number of misjudgments; When the number of misjudgments within the detection time period reaches the warning threshold, the first threshold or the second threshold is lowered.

9. The method for detecting pirated links according to claim 1, wherein: Also includes: Obtain the basic characteristics of all copyrighted works in advance; The basic features include: official name, alias, year, number of episodes, and type of work; Integrate the basic features of each copyrighted work to obtain corresponding structured data; wherein the structured data of at least one copyrighted work includes: multiple years and multiple episodes corresponding to the copyrighted work; Build a basic information database based on the structured data corresponding to each copyrighted work.

10. The method for detecting pirated links according to claim 1, wherein: Extracting the information to be detected from the network disk name also includes: Matching the network disk name with an auxiliary vocabulary library; the auxiliary vocabulary library stores auxiliary matching words related to the work type; In the case that the network disk name hits any auxiliary matching word related to the work type, the type to be detected of the network disk name is determined according to the auxiliary matching word.

11. The method for detecting pirated links according to claim 10, characterized in that: Also includes: Obtaining auxiliary features of all copyrighted works; the auxiliary features including an identifier of a collection of episodes; Obtaining multiple auxiliary matching words based on auxiliary features of each copyrighted work; The auxiliary matching words are related to the type of work; An auxiliary vocabulary is constructed based on each auxiliary matching word.

12. The method for detecting pirated links according to claim 1, wherein: Before extracting the information to be detected from the network disk name, the method further includes: Detecting whether the network disk name includes a content qualifier; If the network disk name includes a content qualifier, determining whether the network disk name is within the copyright scope based on the content qualifier; If the network disk name is outside the copyright scope, it is determined that the network disk link is not a pirated link; If the network disk name is within the copyright scope, the information to be detected is extracted from the network disk name.

13. The method for detecting pirated links according to claim 1, wherein: Before extracting the information to be detected from the network disk name, the method further includes: Matching the network disk name with a replacement word library; the replacement word library stores a plurality of special characters and corresponding replacement characters; In the case where the network disk name contains special characters, updating the network disk name based on the replacement characters corresponding to the special characters; The extracting the information to be detected from the network disk name specifically includes: extracting the information to be detected from the updated network disk name.

14. The method for detecting pirated links according to claim 13, wherein: Also includes: Build a replacement word library based on the special characters in the pirated links and the corresponding replacement characters; At least one replacement character in the replacement vocabulary has corresponding multiple special characters.

15. A device for detecting pirated links, characterized in that: include: An information extraction module is configured to extract a network disk name from a network disk link to be detected, and extract multi-dimensional information to be detected from the network disk name; the multi-dimensional information to be detected includes at least a title of the film to be detected; A matching module is configured to match the multi-dimensional information to be detected with the basic information database to obtain matching results of each dimension; The basic information database stores characteristic information of multiple copyrighted works; The judgment module is configured to calculate the matching score corresponding to the network disk name according to the matching results of each dimension and the corresponding weights; and identify whether the network disk link is a pirated link based on the matching score.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 14 are implemented.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps in the method according to any one of claims 1 to 14 are implemented.

Images