Browser fingerprint generation method and device, equipment and storage medium
By collecting and preprocessing the feature information of the browser and user equipment, extracting multi-dimensional feature vectors and generating browser fingerprints, the problem of recognition instability caused by manual selection of features in the prior art is solved, and higher recognition accuracy is achieved.
Patent Information
- Application Number
- CN202510094920.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-21
- Publication Date
- 2025-05-30
AI Technical Summary
In the prior art, when generating browser fingerprints, there is contingency in manual experience selection of features, resulting in insufficient reliability of cross-browser recognition.
By collecting feature information from the browser and user equipment, preprocessing, extracting multi-dimensional feature vectors, and generating browser fingerprints based on these feature vectors.
It realizes the generation of stable and reliable browser fingerprints, improves the accuracy of user identification, and provides reliable support for online services.
Smart Images
Figure CN120067640A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and particularly to a method, apparatus, device, and storage medium for generating browser fingerprints. Background Art
[0002] Browser fingerprint generation technology is a technology used to identify and track users' online activities. It generates a unique identifier by collecting and analyzing various characteristic information of the browser and its environment. Currently, most traditional device fingerprint technologies select features based on manual experience. The way of manually selecting features has a great deal of contingency, making it difficult to ensure the reliability of fingerprints in cross-browser identification.
[0003] Therefore, how to generate a technical solution for stable and reliable browser fingerprints has become a technical problem that needs to be solved urgently by those skilled in the art. It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention
[0004] In view of the above, this application provides a method, apparatus, device, and storage medium for generating browser fingerprints, aiming to solve the above technical problems.
[0005] In a first aspect, this application provides a method for generating browser fingerprints, and the method includes:
[0006] Collect the characteristic information of the browser and the characteristic information of the user device, where the browser is installed in the user device;
[0007] Perform a preprocessing operation on the characteristic information of the browser and the characteristic information of the user device to obtain the target characteristics after preprocessing;
[0008] Extract the feature vectors of multiple dimensions corresponding to the target characteristics;
[0009] Generate a browser fingerprint based on the feature vectors of multiple dimensions.
[0010] Preferably, the performing a preprocessing operation on the characteristic information of the browser and the characteristic information of the user device to obtain the target characteristics after preprocessing includes:
[0011] Perform a data cleaning operation on the characteristic information of the browser and the characteristic information of the user device to obtain the characteristic information of the browser and the characteristic information of the user device after cleaning;
[0012] Perform a format conversion operation on the characteristic information of the browser and the characteristic information of the user device after cleaning to obtain the target characteristic data in a unified format.
[0013] Preferably, the data cleaning operation on the feature information of the browser and the feature information of the user device to obtain the feature information of the cleaned browser and the feature information of the user device includes:
[0014] Aggregate the duplicate data in the feature information of the browser and the feature information of the user device respectively to obtain the feature information of the browser and the feature information of the user device after duplicate removal;
[0015] Perform a data filling operation on the feature information of the browser and the feature information of the user device after duplicate removal to obtain the feature information of the browser and the feature information of the user device after the filling operation;
[0016] Concatenate the feature information of the browser and the feature information of the user device after filling to obtain the feature information of the cleaned browser and the feature information of the user device.
[0017] Preferably, the format conversion operation on the feature information of the cleaned browser and the feature information of the user device to obtain the target feature data in a unified format includes:
[0018] Convert the feature information of the cleaned browser and the feature information of the user device into data in a preset format respectively;
[0019] Concatenate the feature information of the browser and the feature information of the user device after format conversion to obtain the target feature data in a unified format.
[0020] Preferably, the extraction of the feature vectors of multiple dimensions corresponding to the target feature includes:
[0021] Extract the feature vector of the key information dimension corresponding to the target feature;
[0022] Extract the semantic feature vector corresponding to the target feature;
[0023] Extract the one-hot encoded feature vector corresponding to the target feature.
[0024] Preferably, the generation of the browser fingerprint based on the feature vectors of multiple dimensions includes:
[0025] Assign preset weights to the feature vectors of each dimension respectively;
[0026] Perform a weighted summation operation on the feature vector of the key information dimension, the semantic feature vector and the one-hot encoded feature vector according to the preset weights, and the result obtained is used as the browser fingerprint.
[0027] Preferably, the extraction of the semantic feature vector corresponding to the target feature includes:
[0028] Input the target feature into a pre-trained semantic feature extraction model to obtain the semantic feature vector corresponding to the target feature.
[0029] In a second aspect, the present application provides a browser fingerprint generation device, which includes:
[0030] A collection module: configured to collect the feature information of the browser and the feature information of the user device, where the browser is installed in the user device;
[0031] A preprocessing module: configured to perform preprocessing operations on the feature information of the browser and the feature information of the user device to obtain the preprocessed target feature;
[0032] An extraction module: configured to extract feature vectors of multiple dimensions corresponding to the target feature;
[0033] A generation module: configured to generate a browser fingerprint based on the feature vectors of multiple dimensions.
[0034] In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;
[0035] The memory is used to store a computer program;
[0036] The processor, when executing the program stored in the memory, implements the browser fingerprint generation method described in any embodiment of the first aspect.
[0037] In a fourth aspect, there is provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the browser fingerprint generation method described in any embodiment of the first aspect.
[0038] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art:
[0039] The present application collects the feature information of the browser and the feature information of the user device, where the browser is installed in the user device, performs preprocessing operations on the feature information of the browser and the feature information of the user device to obtain the preprocessed target feature, extracts feature vectors of multiple dimensions corresponding to the target feature, and generates a browser fingerprint based on the feature vectors of multiple dimensions. By comprehensively analyzing the browser feature information and the user device feature information, the present application can generate a stable and reliable browser fingerprint, thereby improving the accuracy of user identification and providing reliable support for various online services. Description of the Drawings
[0040] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.
[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0042] Figure 1 It is a schematic flowchart of an embodiment of the browser fingerprint generation method of this application;
[0043] Figure 2 It is a schematic framework diagram of the semantic feature extraction model in the embodiment of this application;
[0044] Figure 3 It is a schematic module diagram of an embodiment of the browser fingerprint generation device of this application;
[0045] Figure 4 It is a schematic diagram of an embodiment of the electronic device of this application;
[0046] The implementation, functional features, and advantages of the objectives of this application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Detailed Embodiments
[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are a part rather than all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts belong to the scope of protection of this application.
[0048] The following disclosure provides many different embodiments or examples for implementing different structures of this application. To simplify the disclosure of this application, the components and settings of specific examples are described below. Of course, they are only examples and are not intended to limit this application. In addition, this application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0049] This application provides a browser fingerprint generation method. Referring to Figure 1 As shown, it is a schematic flowchart of the method of an embodiment of the browser fingerprint generation method of this application. This method can be executed by an electronic device, which is implemented by software and / or hardware. The browser fingerprint generation method includes:
[0050] Step S10: Collect the feature information of the browser and the feature information of the user device, where the browser is installed in the user device;
[0051] Step S20: Perform a preprocessing operation on the feature information of the browser and the feature information of the user device to obtain the preprocessed target features;
[0052] Step S30: Extract the feature vectors of multiple dimensions corresponding to the target features;
[0053] Step S40: Generate a browser fingerprint based on the feature vectors of multiple dimensions.
[0054] In this embodiment, the user device refers to a device installed with a browser, such as a mobile phone, a computer, a tablet, etc. The feature information of the browser and the feature information of the user device can be automatically collected through scripts or collected by calling interfaces.
[0055] Among them, the feature information of the browser includes the HTTP header information of the browser, plugins and extensions, time zone settings, screen resolution, operating system type, font list, Canvas fingerprint, WebGL fingerprint and other feature information;
[0056] The feature information of the user device includes the operating system type and version of the device, device model, screen features, network information, battery status and other feature information.
[0057] Since the collected data may contain invalid data and redundant data, it is also necessary to perform a preprocessing operation on the feature information of the browser and the feature information of the user device to obtain the preprocessed target features. The preprocessing operation can be a data cleaning operation. The data cleaning operation refers to the operation of identifying, correcting and removing the error values, incompleteness, inconsistency or repetition in the collected feature data. The purpose of this operation is to ensure that the collected feature information can reflect the real data of the browser and the user device.
[0058] Specifically, the performing a preprocessing operation on the feature information of the browser and the feature information of the user device to obtain the preprocessed target features includes:
[0059] Perform a data cleaning operation on the feature information of the browser and the feature information of the user device to obtain the cleaned feature information of the browser and the feature information of the user device;
[0060] Perform a format conversion operation on the cleaned feature information of the browser and the feature information of the user device to obtain the target feature data in a unified format.
[0061] The data cleaning operation can be at least one of the operations of filling missing values and removing duplicate values. The data cleaning operation can also include data consistency detection, error data detection, etc. Since data from different sources will be presented in different data formats, the formats between the feature information of the browser after cleaning and the feature information of the user device are not unified. Therefore, it is also necessary to perform a format conversion operation on the feature information of the browser after cleaning and the feature information of the user device to make the formats of the feature information of the browser and the feature information of the user device unified, and use the data with unified formats as the target feature data. For example, all numbers (such as information on resolution, memory, etc.) can be represented in the same unit. For example, all storage sizes can be unified into bytes. The same character encoding (such as UTF-8) can also be used for all strings.
[0062] Further, the data cleaning operation on the feature information of the browser and the feature information of the user device to obtain the feature information of the browser after cleaning and the feature information of the user device includes:
[0063] Aggregate the duplicate data in the feature information of the browser and the feature information of the user device respectively to obtain the de-duplicated feature information of the browser and the feature information of the user device;
[0064] Perform a data filling operation on the de-duplicated feature information of the browser and the feature information of the user device to obtain the feature information of the browser and the feature information of the user device after the filling operation;
[0065] Concatenate the filled feature information of the browser and the feature information of the user device to obtain the feature information of the browser after cleaning and the feature information of the user device.
[0066] Since there may be duplicate data in the feature information of the browser and the feature information of the user device, the duplicate data in the feature information of the browser and the feature information of the user device can be aggregated first, and then the duplicate data can be deleted from the aggregation result to obtain the de-duplicated feature information of the browser and the feature information of the user device. The data filling operation can be at least one of global constant automatic filling, central measure automatic filling, and group mean automatic filling.
[0067] Global constant automatic filling replaces all missing values with the same constant;
[0068] Central measure filling fills the missing values by taking indicators such as the average value, median, and mode of the attribute;
[0069] Group mean filling refers to referring to the other attribute values of the records with missing values, classifying the data according to other attributes for aggregation operations, calculating the average or median of the column with missing values, and replacing the missing values with it.
[0070] The feature information of the filled browser and the feature information of the user device can be concatenated to obtain the feature information of the cleaned browser and the feature information of the user device.
[0071] Furthermore, performing a format conversion operation on the feature information of the cleaned browser and the feature information of the user device to obtain target feature data in a unified format, including:
[0072] Converting the feature information of the cleaned browser and the feature information of the user device into data in a preset format respectively;
[0073] Concatenating the feature information of the browser and the feature information of the user device after format conversion to obtain target feature data in a unified format.
[0074] The feature information of the cleaned browser and the feature information of the user device can be converted into a unified JSON format for easy data transmission and storage. Concatenating the feature information of the browser and the feature information of the user device after format conversion to obtain target feature data in a unified format. The specific concatenation method can be to use a delimiter for concatenation.
[0075] Extracting the feature vectors of the key information dimension, semantic feature dimension, and one-hot encoding dimension corresponding to the target feature. By extracting the feature vectors of multiple dimensions, the features of the browser and the user device can be described more comprehensively.
[0076] Specifically, the extracting of the feature vectors of multiple dimensions corresponding to the target feature includes:
[0077] Extracting the feature vector of the key information dimension corresponding to the target feature;
[0078] Extracting the semantic feature vector corresponding to the target feature;
[0079] Extracting the one-hot encoding feature vector corresponding to the target feature.
[0080] When extracting the feature vectors of the key information dimensions corresponding to the target features, for categorical features (e.g., user agent, operating system, etc.), the label encoding method can be used for representation. For numerical features (e.g., screen resolution, memory), their numerical values can be directly used for representation. When extracting the semantic feature vectors corresponding to the target features, the categorical features (e.g., user agent, operating system) can be mapped into a dense vector space through the Word2Vec bag-of-words model, or the semantic feature vectors corresponding to the target features can be extracted through the BERT model to generate context-related semantic feature vectors. When extracting the one-hot encoding feature vectors corresponding to the target features, the one-hot encoding (One-Hot Encoding) method is used to represent the target features as the one-hot encoding feature vectors corresponding to the target features.
[0081] Further, extracting the semantic feature vectors corresponding to the target features includes:
[0082] Inputting the target features into a pre-trained semantic feature extraction model to obtain the semantic feature vectors corresponding to the target features.
[0083] As Figure 2 shown, it is a schematic diagram of the framework of the semantic feature extraction model in the embodiments of the present application. The semantic feature extraction model includes a convolutional layer with 2 different convolutional kernels, 2 pooling layers, 2 attention layers, 2 double-parameterized convolutional layers, and 1 output layer. The process of extracting the semantic feature vectors corresponding to the target features includes: respectively using the convolutional layers with 2 different convolutional kernels to perform convolutional operations on the target features, and different levels of features can be extracted, which are respectively denoted as the first feature and the second feature. After being activated by the activation function, the first feature and the second feature respectively enter different pooling layers. Each convolutional layer is followed by a pooling layer. After the pooling layer performs pooling processing on the first feature and the second feature respectively, the spatial dimension of the features can be reduced, thereby reducing the computational complexity. The features output by the 2 pooling layers respectively enter the 2 attention layers, and through the attention mechanism for weighting, the model's understanding of the relationship between features can be enhanced. The features output by the 2 attention layers enter the 2 double-parameterized convolutional layers, which can fuse low-level and high-level features, thereby capturing more complex context information. After the features output by the 2 double-parameterized convolutional layers are fused and then output through the output layer, the semantic feature vectors corresponding to the target features can be obtained, and the feature vectors of the semantic dimension of the target features can be effectively extracted.
[0084] After extracting the feature vectors of multiple dimensions corresponding to the target features, a browser fingerprint can be generated according to the feature vectors of multiple dimensions. For example, the feature vectors of each dimension can be concatenated respectively, and the concatenation result can be used as the browser fingerprint.
[0085] Further, based on the feature vectors of the multiple dimensions, a browser fingerprint is generated, including:
[0086] Assign preset weights to the feature vectors of each dimension respectively;
[0087] Perform a weighted summation operation on the feature vectors of the key information dimension, semantic feature vectors, and one-hot encoded feature vectors according to the preset weights, and the obtained result is used as the browser fingerprint.
[0088] Corresponding weights can also be assigned to the feature vectors of each dimension in advance. For example, the weight of the feature vector of the key information dimension is 0.4, the semantic feature vector is 0.4, and the one-hot encoded feature vector is 0.2. Perform a weighted summation operation on the feature vectors of the key information dimension, semantic feature vectors, and one-hot encoded feature vectors according to the weights, and the obtained result is used as the browser fingerprint, so that the generated browser fingerprint focuses more on the feature vectors with higher weight coefficients.
[0089] In other embodiments, the fingerprint generation parameters can also be adjusted in real time according to changes in the browser and device environment. Update the browser fingerprint by regularly re-collecting and analyzing feature information to ensure the continuous effectiveness and flexibility of the browser fingerprint, and be able to adapt to dynamic changes in the user device and browser configuration.
[0090] By comprehensively analyzing browser feature information and user device feature information, this application can generate a stable browser fingerprint, thereby improving the accuracy of user identification and providing reliable support for various online services.
[0091] Refer to Figure 3 As shown, it is a schematic diagram of the functional modules of the browser fingerprint generation device 100 of this application.
[0092] The browser fingerprint generation device 100 of this application can be installed in an electronic device. According to the implemented functions, the browser fingerprint generation device 100 can include a collection module 110, a preprocessing module 120, an extraction module 130, and a generation module 140. The modules of this application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.
[0093] In this embodiment, the functions of each module / unit are as follows:
[0094] Collection module 110: Used to collect the feature information of the browser and the feature information of the user device, where the browser is installed in the user device;
[0095] Preprocessing module 120: It is used to perform preprocessing operations on the feature information of the browser and the feature information of the user device to obtain the target features after preprocessing;
[0096] Extraction module 130: It is used to extract feature vectors in multiple dimensions corresponding to the target features;
[0097] Generation module 140: It is used to generate a browser fingerprint based on the feature vectors in multiple dimensions.
[0098] In one embodiment, the performing preprocessing operations on the feature information of the browser and the feature information of the user device to obtain the target features after preprocessing includes:
[0099] Performing data cleaning operations on the feature information of the browser and the feature information of the user device to obtain the feature information of the browser and the feature information of the user device after cleaning;
[0100] Performing format conversion operations on the feature information of the browser and the feature information of the user device after cleaning to obtain target feature data in a unified format.
[0101] In one embodiment, the performing data cleaning operations on the feature information of the browser and the feature information of the user device to obtain the feature information of the browser and the feature information of the user device after cleaning includes:
[0102] Aggregating the duplicate data in the feature information of the browser and the feature information of the user device respectively to obtain the feature information of the browser and the feature information of the user device after duplicate data removal;
[0103] Performing data filling operations on the feature information of the browser and the feature information of the user device after duplicate data removal to obtain the feature information of the browser and the feature information of the user device after the filling operation;
[0104] Concatenating the feature information of the browser and the feature information of the user device after filling to obtain the feature information of the browser and the feature information of the user device after cleaning.
[0105] In one embodiment, the performing format conversion operations on the feature information of the browser and the feature information of the user device after cleaning to obtain target feature data in a unified format includes:
[0106] Converting the feature information of the browser and the feature information of the user device after cleaning into data in a preset format respectively;
[0107] Concatenating the feature information of the browser and the feature information of the user device after format conversion to obtain target feature data in a unified format.
[0108] In one embodiment, extracting the feature vectors of multiple dimensions corresponding to the target feature includes:
[0109] Extracting the feature vector of the key information dimension corresponding to the target feature;
[0110] Extracting the semantic feature vector corresponding to the target feature;
[0111] Extracting the one-hot encoded feature vector corresponding to the target feature.
[0112] In one embodiment, generating a browser fingerprint based on the feature vectors of multiple dimensions includes:
[0113] Assigning preset weights to the feature vectors of each dimension respectively;
[0114] Performing a weighted summation operation on the feature vector of the key information dimension, the semantic feature vector, and the one-hot encoded feature vector according to the preset weights, and using the obtained result as the browser fingerprint.
[0115] In one embodiment, extracting the semantic feature vector corresponding to the target feature includes:
[0116] Inputting the target feature into a pre-trained semantic feature extraction model to obtain the semantic feature vector corresponding to the target feature.
[0117] Refer to Figure 4 shown, which is a schematic diagram of a preferred embodiment of the electronic device of the present application.
[0118] The electronic device includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114. Among them, the processor 111, the communication interface 112, and the memory 113 complete mutual communication through the communication bus 114;
[0119] The memory 113 is used to store computer programs, for example, a browser fingerprint generation program;
[0120] Among them, the processor 111 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. This processor 111 is generally used to control the overall operation of the electronic device, such as performing control and processing related to data interaction or communication, etc. In this embodiment, the processor 111 is used to run the program code stored in the memory 113 or process data, such as running the program code of the browser fingerprint generation program, etc.
[0121] The communication interface 112 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and this communication interface 112 can also be used to establish a communication connection between the electronic device and other electronic devices.
[0122] The memory 113 includes at least one type of readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 113 may be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device. In other embodiments, the memory 113 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped with the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Of course, the memory 113 may also include both the internal storage unit and the external storage device of the electronic device. In this embodiment, the memory 11 is generally used to store the operating system installed on the electronic device and various computer programs, such as the program code of the browser fingerprint generation program. In addition, the memory 113 can also be used to temporarily store various types of data that have been output or will be output.
[0123] In an embodiment of the present application, when the processor 111 executes the program stored on the memory 113, it implements the browser fingerprint generation method provided by any one of the foregoing method embodiments, including:
[0124] Collect the feature information of the browser and the feature information of the user device, where the browser is installed in the user device;
[0125] Perform a preprocessing operation on the feature information of the browser and the feature information of the user device to obtain a preprocessed target feature;
[0126] Extract the feature vectors of multiple dimensions corresponding to the target feature;
[0127] Generate a browser fingerprint based on the feature vectors of the multiple dimensions.
[0128] For a detailed introduction to the above steps, please refer to the above Figure 1 Description of the flowchart of the browser fingerprint generation method embodiment.
[0129] In addition, an embodiment of the present application further provides a computer-readable storage medium, which may be non-volatile or volatile. The computer-readable storage medium includes a storage data area and a storage program area. The storage program area stores a browser fingerprint generation program, and when the browser fingerprint generation program is executed by a processor, the following operations are implemented:
[0130] Collect the feature information of the browser and the feature information of the user device, wherein the browser is installed in the user device;
[0131] Perform a preprocessing operation on the feature information of the browser and the feature information of the user device to obtain the preprocessed target features;
[0132] Extract the feature vectors of multiple dimensions corresponding to the target features;
[0133] Generate a browser fingerprint based on the feature vectors of multiple dimensions.
[0134] The specific implementation manner of the computer-readable storage medium of the present application is substantially the same as that of the above browser fingerprint generation method, and will not be repeated here.
[0135] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0136] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0137] It should be noted that the descriptions involving "first", "second", etc. in this application are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. Additionally, the technical solutions between various embodiments may be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.
[0138] It should be understood that the terms used herein are for the purpose of describing particular example embodiments only and are not intended to be limiting. Unless the context clearly dictates otherwise, the singular forms "a", "an", and "the" as used herein may also include the plural forms. The terms "comprises", "comprising", "includes", and "having" are inclusive and thus specify the presence of the stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or their combinations. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the particular order described or illustrated, unless the order of performance is explicitly stated. It should also be understood that additional or alternative steps may be used.
[0139] The above are only specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A browser fingerprint generation method, characterized in that: The method comprises: Collecting characteristic information of a browser and characteristic information of a user device, wherein the browser is installed in the user device; Performing a preprocessing operation on the characteristic information of the browser and the characteristic information of the user device to obtain preprocessed target characteristics; Extracting feature vectors of multiple dimensions corresponding to the target features; A browser fingerprint is generated based on the feature vectors of the multiple dimensions.
2. The browser fingerprint generation method according to claim 1, characterized in that: The preprocessing operation is performed on the characteristic information of the browser and the characteristic information of the user device to obtain the preprocessed target characteristics, including: Performing a data cleaning operation on the characteristic information of the browser and the characteristic information of the user device to obtain cleaned characteristic information of the browser and the characteristic information of the user device; The cleaned browser feature information and user device feature information are converted into a format to obtain target feature data in a unified format.
3. The browser fingerprint generation method according to claim 2, characterized in that: The performing of data cleaning operation on the characteristic information of the browser and the characteristic information of the user device to obtain cleaned characteristic information of the browser and the characteristic information of the user device includes: Respectively aggregating duplicate data in the characteristic information of the browser and the characteristic information of the user device to obtain deduplicated characteristic information of the browser and characteristic information of the user device; Performing a data filling operation on the deduplicated browser characteristic information and the user device characteristic information to obtain the browser characteristic information and the user device characteristic information after the filling operation; The filled browser feature information and the user device feature information are concatenated to obtain cleaned browser feature information and user device feature information.
4. The browser fingerprint generation method according to claim 2, characterized in that: The format conversion operation is performed on the cleaned browser feature information and the user device feature information to obtain target feature data in a unified format, including: The cleaned browser characteristic information and the user device characteristic information are respectively converted into data in a preset format; The converted browser feature information and the user device feature information are concatenated to obtain target feature data in a unified format.
5. The browser fingerprint generation method according to claim 1, characterized in that: The extracting feature vectors of multiple dimensions corresponding to the target features includes: Extracting a feature vector of a key information dimension corresponding to the target feature; Extracting a semantic feature vector corresponding to the target feature; Extract the one-hot encoded feature vector corresponding to the target feature.
6. The browser fingerprint generation method according to claim 5, characterized in that: The generating of the browser fingerprint based on the feature vectors of the multiple dimensions includes: Assign preset weights to the feature vectors of each dimension respectively; A weighted sum operation is performed on the feature vector, semantic feature vector and one-hot encoding feature vector of the key information dimension according to preset weights, and the obtained result is used as the browser fingerprint.
7. The browser fingerprint generation method according to claim 5, characterized in that: The extracting the semantic feature vector corresponding to the target feature includes: The target feature is input into a pre-trained semantic feature extraction model to obtain a semantic feature vector corresponding to the target feature, wherein the semantic feature extraction model includes two convolutional layers with different convolution kernels, two pooling layers, two attention layers, two dual parameterized convolutional layers and one output layer.
8. A browser fingerprint generation device, characterized in that: The device comprises: A collection module: used to collect characteristic information of a browser and characteristic information of a user device, wherein the browser is installed in the user device; Preprocessing module: used to perform preprocessing operation on the characteristic information of the browser and the characteristic information of the user device to obtain the preprocessed target characteristics; Extraction module: used to extract feature vectors of multiple dimensions corresponding to the target features; Generating module: used to generate browser fingerprint based on the feature vectors of the multiple dimensions.
9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the browser fingerprint generation method described in any one of claims 1 to 7 when executing the program stored in the memory.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the browser fingerprint generation method according to any one of claims 1 to 7 is implemented.