Cross-application advertisement behavior information application tracking method, device and equipment

Abstract

The application relates to a cross-application advertisement behavior information application tracking method, device and equipment, which comprises the following steps: in response to the action of backing up cross-application advertisement behavior information, sending application action information indicating the reporting of application advertisement behavior information to a second application program; constructing a feature vector according to the application action information and the advertisement behavior information; generating an application tracking fingerprint corresponding to the second application program according to the feature vector, adding the application tracking fingerprint to the advertisement behavior information and saving the application tracking fingerprint; backing up the advertisement behavior information with the added application tracking fingerprint to the second application program through pixel code of the second application program, and in response to the application action on the advertisement behavior information, obtaining the application action information corresponding to the application action through the application tracking fingerprint; generating a matching fingerprint for the application action according to the application action information, matching the matching fingerprint with the application tracking fingerprint, and obtaining the application tracking result of the application for the advertisement behavior information.

Description

Technical Field

[0001] This disclosure relates to the field of advertising technology, and in particular to a method, apparatus and device for tracking cross-application advertising behavior information. Background Technology

[0002] Advertising behavior tracking technology is crucial for advertisers, enabling them to more accurately target audiences and improve ad performance and conversion rates. However, with the proliferation of mobile devices and frequent multitasking, users may see ads in one app and then conduct related searches or purchases in another. Through business partnerships, cross-app advertising behavior tracking can provide more accurate user profiles, enabling more precise ad delivery.

[0003] However, the tracking of advertising behavior across apps has also raised concerns about user privacy. Users may want to know how their behavior is used across different apps. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, and device for tracking cross-application advertising behavior information, which aims to enable users to know how advertising behavior information is specifically used by other applications when backing up advertising behavior information across applications.

[0005] To achieve the above objectives, a first aspect of this disclosure provides a cross-application advertising behavior information tracking method, applied to a first application, wherein the target advertising playback page of the first application contains pixel code in its Hypertext Transfer Protocol for a second application to back up the advertising behavior information from the first application across applications, the method comprising: In response to the action of the second application backing up the advertising behavior information across applications from the target advertising playback page of the first application through the pixel code, an application action information instructing the second application to report the application of the advertising behavior information is sent to the second application; Receive the application action information reported by the second application, and construct the feature vector of the second application based on the application action information reported by the second application and the advertising behavior information; Based on the feature vector of the second application, generate the application tracking fingerprint corresponding to the second application, add the application tracking fingerprint to the advertising behavior information backed up by the second application, and save the application tracking fingerprint corresponding to the second application. The advertising behavior information with added application tracking fingerprint is backed up to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, the application action information corresponding to the application action is obtained through the application tracking fingerprint. Based on the application action information, a matching fingerprint for the application action of the second application is generated, and the matching fingerprint is matched with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

[0006] In one possible implementation, constructing the feature vector of the second application based on the application action information and the advertising behavior information reported by the second application includes: Based on the created advertising behavior vocabulary, each advertising behavior term in the advertising behavior information is converted into a vector as a text, resulting in multiple advertising behavior term vectors corresponding to the advertising behavior information. The advertising behavior vocabulary stores binary tags in the advertising behavior segment without repetition. The multiple advertising behavior vectors corresponding to the advertising behavior information are arranged into a two-dimensional matrix according to the preset order of advertising behavior terms. In the two-dimensional matrix, the vertical axis represents different advertising behavior terms, and the horizontal axis is the advertising behavior vector of each advertising behavior term. The application action information reported by the second application is vectorized to obtain the application action vector of each application action term in the application action information; The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix are standardized and then concatenated to obtain the feature vector of the second application.

[0007] In one possible implementation, the step of standardizing and concatenating the advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix to obtain the feature vector of the second application includes: Calculate the mean and standard deviation of the advertising behavior vector of each advertising behavior term and the application action vector of each application action term in the two-dimensional matrix; Based on the mean and the standard deviation, the advertising behavior vector of each advertising behavior term and the application action vector of each application action term are standardized by Z-score. The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term, after Z-score standardization, are concatenated to obtain the feature vector of the second application.

[0008] In one possible implementation, the step of obtaining application action information corresponding to the application action through the application tracking fingerprint in response to the application action of the second application regarding the advertising behavior information includes: Receive a reporting request sent by the second application, wherein the reporting request is generated by the second application in response to an application action on the advertising behavior information, based on the application tracking fingerprint, and sent to the first application based on the first application identifier corresponding to the application tracking fingerprint; Parse the reporting request to obtain specific API endpoint information and the application tracking fingerprint carried in the reporting request for obtaining application action information corresponding to the application action; The parsed application tracking fingerprint is compared with the saved application tracking fingerprint. If the comparison result indicates that the two fingerprints match, an encapsulation instruction is sent to the second application to encapsulate the application action information corresponding to the application action. Upon receiving feedback that the second application has been packaged, the application action information corresponding to the packaged application action is obtained through the specific API endpoint represented by the specific API endpoint information.

[0009] In one possible implementation, generating the application tracking fingerprint corresponding to the second application based on the feature vector of the second application includes: The initial hash value is determined by taking the first 32 decimal places of the square roots of several prime numbers in the mathematical constants. If the number of bits of the feature vector of the second application is filled to a preset number of bits, the filled feature vector is divided into multiple vector blocks of preset bytes; Each vector block corresponding to the feature vector is decomposed into multiple message blocks of preset length to obtain the basic message word in the hash algorithm; After arranging the information in the application action information of the second application in sequence, a specific vector is generated, and the extended message words corresponding to the remaining words in the hash algorithm are determined according to the values ​​at multiple specified positions in the specific vector. The multiple basic message words corresponding to each vector block are combined with the extended message words to generate the hash constants of the multiple message blocks corresponding to each vector block; The hash value of each message block is obtained by iteratively calculating the initial hash value and the hash constants of the multiple message blocks corresponding to each vector block. Based on the hash values ​​of the multiple message blocks corresponding to each vector block, an application tracking fingerprint corresponding to the second application is generated.

[0010] In one possible implementation, determining the extended message word corresponding to the remaining multiple words in the hash algorithm based on the values ​​at multiple specified positions in the specific vector includes: Calculate the square root of the values ​​at multiple specified positions in the specific vector to obtain the first value at a preset number of decimal places corresponding to each specified position; Convert the numerical values ​​at each specified position to binary representations of the predetermined number of decimal places. According to the order of the specified positions, the binary values ​​corresponding to each specified position are sequentially used as the extended message words corresponding to the remaining multiple words in the hash algorithm.

[0011] In one possible implementation, the application actions include at least one of the following: user profile building action, ad matching action, product matching action, ad behavior extension action, target audience matching action, behavior pattern recognition action, and activity statistics action.

[0012] In one possible implementation, the application action information includes at least one of the following: the frequency of using the advertising behavior information, the application action of using the advertising behavior information, the conditions for using the advertising behavior information, and the font of the application.

[0013] A second aspect of this disclosure provides a cross-application advertising behavior information application tracking device, applied to a first application, wherein the target advertising playback page of the first application contains pixel code added to its Hypertext Transfer Protocol for a second application to back up the advertising behavior information from the first application across applications, the device comprising: The sending module is configured to send application action information to the second application in response to the action of the second application backing up the advertising behavior information across applications from the target advertising playback page of the first application through the pixel code, instructing the second application to report the application of the advertising behavior information; The receiving and constructing module is configured to receive the application action information reported by the second application, and construct the feature vector of the second application based on the application action information and the advertising behavior information reported by the second application. The generation and saving module is configured to generate the application tracking fingerprint corresponding to the second application based on the feature vector of the second application, and to add the application tracking fingerprint to the advertising behavior information backed up by the second application and save the application tracking fingerprint corresponding to the second application. The acquisition module is configured to back up the advertising behavior information with the added application tracking fingerprint to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, acquire the application action information corresponding to the application action through the application tracking fingerprint; The generation and matching module is configured to generate a matching fingerprint for the application action of the second application based on the application action information, and match the matching fingerprint with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

[0014] A third aspect of this disclosure provides an electronic device, comprising: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspects.

[0015] This invention provides a method, apparatus, and device for tracking cross-application advertising behavior information. Compared with the prior art, it has the following advantages: By backing up advertising behavior information across applications, user behavior across different applications can be accurately tracked. Cross-application backup expands the evaluation of advertising effectiveness beyond a single application, improving the accuracy and comprehensiveness of the assessment. Feature vectors are constructed based on user behavior across different applications, generating corresponding application tracking fingerprints. These fingerprints inform the source application of the advertising behavior information when it is used across applications, allowing users to know which applications are using their behavior information across different applications, and how those applications are using it. This ensures the security of user data while supporting the analysis of user advertising preferences and consumption habits through cross-application backup of advertising behavior information.

[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a cross-application advertising behavior information tracking method according to an embodiment of the specification.

[0018] Figure 2This is a block diagram of a cross-application advertising behavior information tracking device according to an embodiment of the specification.

[0019] Figure 3 This is a block diagram of another cross-application advertising behavior information tracking device shown in the embodiment of the specification. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0022] This disclosure provides a cross-application advertising behavior information tracking method, applied to a first application, wherein the target advertising playback page of the first application contains pixel code in its Hypertext Transfer Protocol (HTTP) for a second application to back up the advertising behavior information from the first application across applications. Figure 1 This is a flowchart illustrating a cross-application advertising behavior information tracking method according to one embodiment. The method includes: In step S11, in response to the action of the second application backing up the advertising behavior information across applications from the target advertising playback page of the first application through the pixel code, an application action information instructing the second application to report the application of the advertising behavior information is sent to the second application. Pixel code, also known as tracking pixels, web worms, or web beacons, is a small piece of code (usually a 1x1 pixel transparent image) embedded in a webpage or application. It is used to trigger data tracking or send requests when a user visits a page, and can be used to track user behavior such as clicking, browsing, ignoring, or skipping advertisements.

[0023] In this publicly disclosed method, pixel code from the second application is embedded in the HTTP request for the target ad playback page of the first application. When that page of the first application is accessed, a request for the pixel code is triggered, containing information related to the ad activity (such as ad ID, display time, etc.). For example, if a user views an ad in application A (the first application), the HTTP request for that ad page includes pixel code from application B (the second application). When the user loads the ad page, application B receives a request from application A containing information about the ad activity.

[0024] Furthermore, the second application performs cross-application backup processing on the advertising behavior information received through pixel code. This may include storage and analysis; for example, after receiving advertising behavior information from application A, application B stores it in a database for subsequent analysis of whether the user has any further interaction in application B (such as being redirected to a product page in application B after clicking on an advertisement).

[0025] In step S12, the application action information reported by the second application is received, and a feature vector of the second application is constructed based on the application action information reported by the second application and the advertising behavior information. The feature vector may include features corresponding to user behaviors such as clicking, browsing, ignoring, and skipping ads, as well as information about the application actions the second application intends to use to utilize the ad behavior information. Application actions can be understood as actions taken to use or apply the ad behavior information. In other words, it describes how the second application uses, applies, or utilizes the ad behavior information.

[0026] In this disclosure, when a user needs to perform an operation related to advertising behavior information in the first application within the second application (such as building a user profile based on clicks, views, ignores, or skips in the advertising behavior information), the second application reports the operation-related information to the first application. For example, if a user sees an ad in application A and clicks it, and application B subsequently needs to use the clicked ad behavior to build a user profile, it needs to first inform application A of this user profile building information.

[0027] Furthermore, based on the application action information and advertising behavior information reported by the second application, a feature vector for the user is constructed. This feature vector is used to subsequently build an application tracking fingerprint. For example, after application A receives information from application B that it wants to use clicked advertising behavior to build a user profile, it generates a feature vector together with this information and the clicked advertising behavior.

[0028] In step S13, based on the feature vector of the second application, an application tracking fingerprint corresponding to the second application is generated, and an application tracking fingerprint is added to the advertising behavior information backed up by the second application and the application tracking fingerprint corresponding to the second application is saved. In this disclosure, a unique application tracking fingerprint is generated based on the feature vector of the second application using one or more hash algorithms (such as SHA-256, MD5, etc.). This fingerprint is calculated based on the feature vector of the second application, and therefore can uniquely identify the application and its application actions related to advertising behavior information. Subsequently, this application tracking fingerprint is associated with the advertising behavior information backed up by the second application; that is, the fingerprint is added to the advertising behavior information, and the fingerprinted advertising behavior information is sent to the second application. The corresponding application tracking fingerprint is then saved in the database corresponding to the first application.

[0029] In step S14, the advertising behavior information with the added application tracking fingerprint is backed up to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, the application action information corresponding to the application action is obtained through the application tracking fingerprint. In this disclosure, advertising behavior information with added application tracking fingerprints is backed up to the second application via pixel code. This allows the second application to perform operations such as user profiling using the advertising behavior information generated on the first application. Furthermore, after performing these operations, the second application can report application action information corresponding to the application actions to the first application via the application tracking fingerprint.

[0030] In step S15, a matching fingerprint for the application action of the second application is generated based on the application action information, and the matching fingerprint is matched with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

[0031] In this disclosure, a matching fingerprint is generated based on the application action information of the second application using the same hash algorithm (the same one used when generating the application tracking fingerprint). This matching fingerprint is calculated based on a specific part of the application action information (such as the name of the action of building a user profile). Then, this matching fingerprint is matched with the application tracking fingerprint to verify whether the application action is the same as the previously reported application action information. If the match is successful, the application action is considered a valid application of the previously reported application action information, and a corresponding application tracking result is generated.

[0032] For example, based on the user's actions in application B, including ad clicks and the corresponding application actions used to build a user profile, a matching fingerprint "ABC789" is generated using the SHA-256 algorithm. This matching fingerprint is then matched against a previously generated application tracking fingerprint. Since both fingerprints are calculated based on ad clicks and application actions used to build the user profile, they match successfully. Based on this, it is determined that the application action is a valid application of the previously reported application action information, and a corresponding application tracking result is generated.

[0033] In this embodiment of the disclosure, if the application tracking result indicates that the application action of using the advertising behavior information across applications has not been obtained, a reminder action can be executed. Alternatively, corresponding application logs can be generated based on the application tracking results, so that users can view the logs and understand how the cross-application applications used the advertising behavior information when it was backed up across applications.

[0034] The aforementioned technical solution, through cross-application backup of advertising behavior information, can accurately track user behavior across different applications. Cross-application backup expands the evaluation of advertising effectiveness beyond a single application, thereby improving the accuracy and comprehensiveness of the evaluation. Feature vectors are constructed based on user behavior across different applications, generating corresponding application tracking fingerprints. These fingerprints inform the source application of the advertising behavior information when it is used across applications, allowing users to know which applications are using their behavior information across different applications, and how those applications are using it. This ensures the security of user personal data while facilitating the analysis of user advertising preferences and consumption habits through cross-application backup of advertising behavior information.

[0035] In one possible implementation, step S12, constructing the feature vector of the second application based on the application action information and the advertising behavior information reported by the second application, includes: In step S121, based on the created advertising behavior vocabulary, each advertising behavior term in the advertising behavior information is converted into a vector as a text, resulting in multiple advertising behavior term vectors corresponding to the advertising behavior information. The advertising behavior vocabulary stores binary tags in the advertising behavior segment without repetition. In this disclosure, a pre-created Ad Behavior Vocabulary is used to convert each ad behavior term (such as "click ad," "view product details," etc.) in the ad behavior information into a vector. This vocabulary is a collection containing all possible ad behavior terms, and each term has a unique binary identifier (e.g., represented by an index) within the vocabulary. The conversion process typically uses word embedding techniques such as TF-IDF and Word2Vec, but here, since the vocabulary is predefined and relatively small, each term can be directly mapped to a fixed-dimensional vector (e.g., one-hot encoding or a simple indexed vector).

[0036] For example, suppose the advertising behavior vocabulary contains the following terms: {“Click on an ad”: 0, “View product details”: 1, “Add to cart”: 2, “Purchase product”: 3}. For an advertising behavior message “The user clicked on an ad and viewed product details”, first identify the advertising behavior terms “Click on an ad” and “View product details”, and then convert them into vectors [1, 0, 0, 0] and [0, 1, 0, 0] respectively according to the vocabulary.

[0037] In step S122, the multiple advertising behavior vectors corresponding to the advertising behavior information are arranged into a two-dimensional matrix according to the preset order of advertising behavior terms. In the two-dimensional matrix, the vertical axis represents different advertising behavior terms, and the horizontal axis is the advertising behavior vector of each advertising behavior term. In this disclosure, the vectors corresponding to all advertising behavior terms are arranged into a two-dimensional matrix according to a preset order of advertising behavior terms (i.e., the order in the vocabulary). The vertical axis of this matrix represents different advertising behavior terms, and the horizontal axis corresponds to the advertising behavior vector of each term. In this way, the system can integrate a series of discrete advertising behavior information into a structured data representation, which facilitates subsequent feature matching and tracking analysis.

[0038] Continuing the example above, suppose we have a vocabulary containing four advertising behavior terms, and a corresponding vector has been generated for each term in a given advertising behavior message. These vectors can then be arranged into a 4xN two-dimensional matrix according to the order of the vocabulary (i.e., "click ad", "view product details", "add to cart", "purchase product"), where N is the dimension of the vectors.

[0039] In step S123, the application action information reported by the second application is vectorized to obtain the application action vector of each application action term in the application action information; In this disclosure, the application action information reported by the second application is vectorized. The purpose of this step is to convert unstructured text or event information into structured numerical vectors. Vectorization can be based on a predefined application action vocabulary, which contains all possible application action terms and assigns a unique identifier or index to each term.

[0040] For each application action term, various methods can be used for vectorization, such as one-hot encoding, TF-IDF, and word embedding. However, since application action vocabularies are usually much smaller than vocabularies in natural language processing, and the types of actions are relatively fixed, simple one-hot encoding or index vectors may be sufficient.

[0041] For example, suppose the application action vocabulary contains the following entries: {"Name of user profile built": 0, "Frequency of user profile built": 1, "Font of user profile built": 2}. For the application action "Build user profile", first identify the application action entries "Name of user profile built", "Frequency of user profile built", and "Font of user profile built", and then convert them into vectors [1, 0, 0, 0], [0, 1, 0, 0] and [0,0, 1, 0] respectively according to the vocabulary.

[0042] In step S124, the advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix are standardized and then concatenated to obtain the feature vector of the second application.

[0043] In this disclosure, the advertising behavior term vectors obtained in step S122 and the application action term vectors obtained in step S123 are standardized. Standardization can help eliminate the dimensional differences between different features, making each feature numerically of the same order of magnitude, thereby improving the accuracy and efficiency of subsequent analysis.

[0044] There are many standardization methods, the most common being min-max scaling and Z-score standardization (also known as standard deviation standardization). After standardization, the vectors of advertising behavior terms and application action terms are concatenated in a specific order to form a longer vector, which is the feature vector of the second application. This feature vector integrates the application's advertising behavior information and the user's application action information, and can comprehensively reflect the application's behavioral characteristics.

[0045] Continuing the example above, consider the two-dimensional matrix of advertising behavior terms (for simplicity, we only consider the behavior of one user, so the matrix degenerates into a vector) and the vector of application action terms. The advertising behavior vector might be [1, 1, 0, 0] (corresponding to the behaviors of "clicking an ad" and "viewing an ad"), and the application action vector is [1, 1, 1, 0] (corresponding to "name of the user profile", "frequency of user profile construction", and "font of the user profile construction"). During the standardization phase, since these vectors are already in one-hot encoding or similar simple form, no additional numerical transformation may be needed. Finally, concatenate these two vectors to obtain the feature vector of the second application [1, 1, 0, 0, 1, 1, 1, 0].

[0046] In one possible implementation, step S124, which involves standardizing and concatenating the advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix to obtain the feature vector of the second application, includes: In step S1241, the mean and standard deviation of the advertising behavior vector of each advertising behavior term and the application action vector of each application action term in the two-dimensional matrix are calculated. In this disclosure, the mean and standard deviation of the advertising behavior vectors for all advertising behavior terms and the application action vectors for all application action terms in the two-dimensional matrix are calculated separately. The mean reflects the central tendency of the data, while the standard deviation measures the dispersion of the data. For example, suppose there is a two-dimensional matrix containing advertising behavior information for multiple users, and a series of application action vectors. For the advertising behavior vectors, the average behavior intensity of all users on each advertising behavior term (if the vectors are one-hot encoded, they may need to be converted to other forms of representation, such as frequency or duration), and the standard deviation of these behavior intensities can be calculated. Similarly, for the application action vectors, the average number of actions or duration of actions of all users on each application action term, and the corresponding standard deviation, can also be calculated.

[0047] In step S1242, Z-score standardization is performed on the advertising behavior vector of each advertising behavior term and the application action vector of each application action term based on the mean and the standard deviation. In this disclosure, after obtaining the mean and standard deviation, Z-score standardization (also known as standard deviation standardization) is used to standardize the advertising behavior vector for each advertising behavior term and the application action vector for each application action term. After Z-score standardization, the data will conform to a standard normal distribution, i.e., the mean is 0 and the standard deviation is 1. In this way, the dimensional differences between different features are eliminated.

[0048] For example: Continuing the example above, suppose we have an advertising behavior vector [2,3,0,1] (representing the intensity of a user's behavior on four advertising terms), with a mean μ=1.5 and a standard deviation σ=1.29. After Z-score standardization, this vector will become [(2−1.5) / 1.29,(3−1.5) / 1.29,(0−1.5) / 1.29,(1−1.5) / 1.29], or [0.39,1.16,−1.16,−0.39]. Similarly, action vectors will also be standardized in this way.

[0049] In step S1243, the advertising behavior vectors of each advertising behavior term after Z-score standardization and the application action vectors of each application action term are concatenated to obtain the feature vector of the second application.

[0050] In this disclosure, after Z-score standardization, the advertising behavior vectors of all advertising behavior terms and the application action vectors of all application action terms are concatenated in a specific order into a longer vector, namely the feature vector of the second application. This feature vector integrates the application's advertising behavior information and the user's application action information, and can comprehensively reflect the behavioral characteristics of the application and the user.

[0051] For example: Suppose that after standardization, we obtain two vectors: an advertising behavior vector [0.39, 1.16, −1.16, −0.39] and an application action vector [0.5, −0.8, 1.2, 0] (these values ​​are just examples). Then, concatenating these two vectors, we obtain the feature vector of the second application [0.39, 1.16, −1.16, −0.39, 0.5, −0.8, 1.2, 0].

[0052] In one possible implementation, in step S14, the step of obtaining application action information corresponding to the application action through the application tracking fingerprint in response to the application action of the second application regarding the advertising behavior information includes: In step S141, a reporting request sent by the second application is received, wherein the reporting request is generated by the second application in response to an application action on the advertising behavior information, based on the application tracking fingerprint, and sent to the first application based on the first application identifier corresponding to the application tracking fingerprint; In this disclosure, when the second application performs an application action associated with advertising behavior information, the second application generates a report request according to preset logic. This request contains key information for identifying user behavior, such as an application tracking fingerprint (ATF), and then identifies the source of the ATF as the first application identifier (i.e., the source of the advertising behavior information is the first application). The second application then sends this report request to the first application via a communication protocol (such as an HTTP request).

[0053] In step S142, the reporting request is parsed to obtain specific API endpoint information and the application tracking fingerprint carried in the reporting request for obtaining application action information corresponding to the application action. In this disclosure, after receiving a reporting request, the first application parses it to extract specific API endpoint information (API locations used to subsequently obtain application action information) and application tracking fingerprint (ATF). For example, the first application parses the reporting request to obtain API endpoint information (such as / api / track / action) and ATF (a unique identifier).

[0054] In step S143, the parsed application tracking fingerprint is compared with the saved application tracking fingerprint. If the comparison result indicates that the two fingerprints match, an encapsulation instruction is sent to the second application to encapsulate the application action information corresponding to the application action. In this disclosure, the first application compares the parsed Application Tracking Fingerprint (ATF) with the application tracking fingerprint stored in a local or remote database. If the comparison result shows that the two fingerprints match, then the reporting request is considered valid. For example, the server compares the received ATF with the ATF stored in the database, confirms that they match, considers the reporting request legitimate, and prepares to send an encapsulation instruction to the second application.

[0055] In step S144, upon receiving feedback information indicating that the second application has been encapsulated, the application action information corresponding to the encapsulated application action is obtained through the specific API endpoint represented by the specific API endpoint information.

[0056] After confirming the validity of the reporting request, the first application sends an encapsulation instruction (such as an HTTP response or message) to the second application, requesting the second application to encapsulate the application action information into a specific format and send it back through the specific API endpoint information previously parsed.

[0057] In one possible implementation, in step S13, generating the application tracking fingerprint corresponding to the second application based on the feature vector of the second application includes: In step S131, the first 32 decimal places of the square root of a plurality of prime numbers in the mathematical constant are taken to determine the initial hash value; In this disclosure, a set of prime numbers (such as Fermat numbers, Mersenne primes, etc.) are selected from mathematical constants, their square roots are calculated, and the first 32 decimal places are used as the initial value for the hash algorithm. This selection method utilizes the unique mathematical properties of prime numbers, which helps to increase the complexity and unpredictability of the hash value.

[0058] In step S132, if the number of bits of the feature vector of the second application is filled to a preset number of bits, the filled feature vector is divided into multiple vector blocks of preset bytes. In this disclosure, it is checked whether the feature vector of the second application has reached a preset number of bits. If not, a specific padding method (such as zero padding, random padding, etc.) is used to expand the feature vector to the required number of bits. Then, the padded feature vector is divided into multiple vector blocks according to a preset byte size for subsequent processing.

[0059] For example: Suppose the original feature vector length is 128 bits, but at least 256 bits are required. The feature vector is extended to 256 bits using zero padding, and then these 256 bits are divided into four 64-bit vector blocks.

[0060] In step S133, each vector block corresponding to the feature vector is decomposed into multiple message blocks of a preset length to obtain the basic message word in the hash algorithm; In this disclosure, each vector block is further decomposed into multiple message blocks of a preset length (also called basic message words), which serve as input to the hash algorithm. The decomposition can be done simply by bytes or by bits, depending on the requirements of the hash algorithm. For example, continuing the previous example, each 64-bit vector block is decomposed into eight 8-bit message blocks, each serving as a basic input to the hash algorithm.

[0061] In step S134, the information in the application action information of the second application is arranged in sequence to generate a specific vector, and the extended message words corresponding to the remaining words in the hash algorithm are determined according to the values ​​at multiple specified positions in the specific vector. In this disclosure, a specific vector is generated based on the application action information of the second application. Then, values ​​at multiple specified positions are selected from this specific vector as extended message words for the remaining words (i.e., additional inputs besides the basic message words) in the hash algorithm.

[0062] In step S135, the multiple basic message words corresponding to each vector block are combined with the extended message words to generate the hash constants of the multiple message blocks corresponding to each vector block; In this disclosure, for each vector block, the system combines the base message word and the extended message word to generate hash constants for multiple message blocks corresponding to that vector block. The combination can be a simple concatenation or a more complex function mapping. For example, each 8-bit base message word is concatenated with the corresponding extended message word (which may be one or more numerical values) to form a longer message block, which serves as the input to the hash algorithm.

[0063] In step S136, the initial hash value is iteratively calculated with the hash constants of the multiple message blocks corresponding to each vector block to obtain the hash value of each message block; In this disclosure, a hash algorithm (such as MD5, SHA-256, etc.) is used to iteratively calculate the initial hash value with the hash constant of the message block corresponding to each vector block. The specific steps and number of iterations depend on the implementation details of the hash algorithm. Ultimately, each message block will obtain a corresponding hash value. For example, using the SHA-256 algorithm, the initial hash value is iteratively calculated with the message block of the first vector block to obtain the first hash value. Then, the first hash value is used as the new initial value to iteratively calculate with the message block of the second vector block, and so on, until all vector blocks have been processed.

[0064] In step S137, the application tracking fingerprint corresponding to the second application is generated based on the hash values ​​of the multiple message blocks corresponding to each vector block.

[0065] In this disclosure, the hash values ​​corresponding to all vector blocks are merged (through operations such as concatenation and XOR) to generate a final string or number, which serves as the application tracking fingerprint (ATF) corresponding to the second application. This ATF will be used to uniquely identify the application and its behavior. For example, concatenating the hash values ​​corresponding to all vector blocks into a long string constitutes the application tracking fingerprint corresponding to the second application.

[0066] In one possible implementation, step S134, determining the extended message word corresponding to the remaining multiple words in the hash algorithm based on the values ​​at multiple specified positions in the specific vector, includes: In step S1341, the square root of the values ​​at multiple specified positions in the specific vector is calculated to obtain the first value at multiple preset decimal places corresponding to each specified position; In this disclosure, for a value at each specified position in a particular vector, its square root is first calculated. Then, a predetermined number of decimal places are extracted from the results of these square roots. The square root and its decimal part are chosen because they can provide another mathematical representation of the original value, which helps to increase the complexity and unpredictability of the data.

[0067] For example, suppose the square root of a value at a specific position in a vector is, for example, 3.14159... Then, extract the first N digits of this decimal part (e.g., N=4), and get 0141 as the first value.

[0068] In step S1342, the numerical values ​​of the preset multiple decimal places corresponding to each specified position are converted into binary values ​​in binary representation; In this disclosure, after obtaining the first value at each specified position, these values ​​are converted into binary representations. This is because computers internally store and process data in binary form, and converting the values ​​to binary facilitates their subsequent use in hash algorithms.

[0069] In step S1343, according to the order of the specified positions, the binary values ​​corresponding to each specified position are sequentially used as the extended message words corresponding to the remaining multiple words in the hash algorithm.

[0070] In this disclosure, the binary value corresponding to each specified position is sequentially used as the extended message word corresponding to the remaining multiple words in the hash algorithm, according to the order of the specified positions. These extended message words will participate in the hash value calculation process together with the basic message word.

[0071] For example, suppose a specific vector has three designated positions with corresponding binary values ​​of 1111, 0101, and 1010. These binary values ​​are used as extended message words in the order they appear in the vector. During the hash algorithm's execution, these extended message words are processed together with the base message words (i.e., the message blocks obtained by decomposing the vector block) to generate the final hash value.

[0072] In one possible implementation, the application actions include at least one of the following: user profile building action, ad matching action, product matching action, ad behavior extension action, target audience matching action, behavior pattern recognition action, and activity statistics action.

[0073] The user profile building process refers to creating one or more detailed descriptions or models of user characteristics by collecting, organizing, and analyzing multi-dimensional information about users (such as basic attributes, behavioral data, preferences, consumption habits, etc.).

[0074] In this embodiment of the disclosure, the data used for building user profiles may include data information acquired by the application itself and data information backed up from other applications. This data information may include, for example, user registration information, browsing history, purchase history, and social media activity. Building user profiles may include data cleaning (removing duplicate, erroneous, or irrelevant data) and data analysis (using statistical methods, machine learning algorithms, etc.) to extract key user characteristics. The constructed user profiles can better understand user needs, thereby providing more personalized service or product recommendations.

[0075] Ad matching refers to the process of matching the most suitable ads to target users based on ad behavior information backed up from other applications. This typically involves building an ad library based on ad behavior information from cross-application backups, classifying and tagging ad content, and matching ads with ad behavior information using algorithms (such as collaborative filtering and content recommendation). The matching results are based on multiple factors, including user interests, needs, and historical behavior, aiming to improve ad click-through rates, conversion rates, and user satisfaction.

[0076] Product matching is similar to ad matching, using cross-application backed-up ad behavior information from other applications to match the most suitable products and display them to the target user, but with a focus on recommending the most suitable products or services. By analyzing cross-application backed-up ad behavior information, combined with product features, prices, reviews, and other information, recommendation algorithms (such as content-based recommendations and collaborative filtering-based recommendations) are used to generate a personalized product recommendation list for the user. This process aims to improve user experience, increase purchase conversion rates, and foster user loyalty.

[0077] The ad behavior expansion mechanism, based on ad behavior information backed up from other apps across different applications, predicts and expands the types of ads or content that users might be interested in. By analyzing data such as ad clicks, browsing time, and conversion behavior from ad behavior information backed up from other apps across different applications, machine learning models are used to predict users' future ad preferences. Based on these predictions, more relevant or innovative ad content is pushed to users to increase ad exposure and user engagement.

[0078] Target audience matching is the precise matching of specific products, services, or information to the target audience most likely to be interested in or benefit from them. It relies on a deep understanding of the target audience's characteristics, including demographic traits, psychological traits, and behavioral patterns. By building detailed target audience profiles and combining them with product characteristics for matching analysis, businesses can more effectively position and promote their products in the market, improving the efficiency and effectiveness of their marketing activities.

[0079] Behavioral pattern recognition identifies unique user behavior patterns or habits by analyzing advertising behavior information backed up from other applications across different apps, either individually (long-term or short-term) or by combining advertising behavior information obtained from other applications across different apps. Behavioral patterns can include, for example, click time, click frequency, and click type. In-depth mining and pattern recognition of user behavior data aims to discover regularities, periodicities, or anomalies in user behavior. Identified behavioral patterns can be used to optimize user experience (e.g., personalized recommendations, interface optimization), assess risks (e.g., fraud detection), and adjust market strategies (e.g., pricing strategies, promotional strategies), among other things.

[0080] Activity statistics are actions taken based on the frequency, timing, or duration of ads viewed, clicked, or ignored by users on the target ad playback page of the first application, according to advertising behavior information.

[0081] In one possible implementation, the application action information includes at least one of the following: the frequency of using the advertising behavior information, the application action of using the advertising behavior information, the conditions for using the advertising behavior information, and the font of the application.

[0082] The frequency of using the advertising behavior information refers to how often the second application uses the advertising behavior information backed up across applications. The application actions using the advertising behavior information refer to the specific actions the second application takes using the advertising behavior information (e.g., user profile building, ad matching, product matching, ad behavior expansion, target audience matching, behavior pattern recognition, activity statistics). These actions may also include, but are not limited to, filling out forms.

[0083] The conditions for using the advertising behavior information refer to the circumstances under which different application actions will use advertising behavior information backed up from the first application across applications.

[0084] This disclosure also provides a cross-application advertising behavior information application tracking device, applied to a first application, wherein the target advertising playback page of the first application contains pixel code in its Hypertext Transfer Protocol for a second application to back up the advertising behavior information from the first application across applications. (See also...) Figure 2 As shown, the device includes: The sending module 210 is configured to send application action information to the second application in response to the action of the second application backing up the advertising behavior information across the application from the target advertising playback page of the first application through the pixel code, instructing the second application to report the application of the advertising behavior information; The receiving and constructing module 220 is configured to receive the application action information reported by the second application, and construct the feature vector of the second application based on the application action information and the advertising behavior information reported by the second application. The generation and saving module 230 is configured to generate the application tracking fingerprint corresponding to the second application based on the feature vector of the second application, and to add the application tracking fingerprint to the advertising behavior information backed up by the second application and save the application tracking fingerprint corresponding to the second application. The acquisition module 240 is configured to back up the advertising behavior information with the added application tracking fingerprint to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, acquire the application action information corresponding to the application action through the application tracking fingerprint; The generation and matching module 250 is configured to generate a matching fingerprint for the application action of the second application based on the application action information, and match the matching fingerprint with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

[0085] In one possible implementation, the receiving and constructing module 220 is configured as follows: Based on the created advertising behavior vocabulary, each advertising behavior term in the advertising behavior information is converted into a vector as a text, resulting in multiple advertising behavior term vectors corresponding to the advertising behavior information. The advertising behavior vocabulary stores binary tags in the advertising behavior segment without repetition. The multiple advertising behavior vectors corresponding to the advertising behavior information are arranged into a two-dimensional matrix according to the preset order of advertising behavior terms. In the two-dimensional matrix, the vertical axis represents different advertising behavior terms, and the horizontal axis is the advertising behavior vector of each advertising behavior term. The application action information reported by the second application is vectorized to obtain the application action vector of each application action term in the application action information; The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix are standardized and then concatenated to obtain the feature vector of the second application.

[0086] In one possible implementation, the receiving and constructing module 220 is configured as follows: Calculate the mean and standard deviation of the advertising behavior vector of each advertising behavior term and the application action vector of each application action term in the two-dimensional matrix; Based on the mean and the standard deviation, the advertising behavior vector of each advertising behavior term and the application action vector of each application action term are standardized by Z-score. The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term, after Z-score standardization, are concatenated to obtain the feature vector of the second application.

[0087] In one possible implementation, the acquisition module 240 is configured as follows: Receive a reporting request sent by the second application, wherein the reporting request is generated by the second application in response to an application action on the advertising behavior information, based on the application tracking fingerprint, and sent to the first application based on the first application identifier corresponding to the application tracking fingerprint; Parse the reporting request to obtain specific API endpoint information and the application tracking fingerprint carried in the reporting request for obtaining application action information corresponding to the application action; The parsed application tracking fingerprint is compared with the saved application tracking fingerprint. If the comparison result indicates that the two fingerprints match, an encapsulation instruction is sent to the second application to encapsulate the application action information corresponding to the application action. Upon receiving feedback that the second application has been packaged, the application action information corresponding to the packaged application action is obtained through the specific API endpoint represented by the specific API endpoint information.

[0088] In one possible implementation, the generation and saving module 230 is configured as follows: The initial hash value is determined by taking the first 32 decimal places of the square roots of several prime numbers in the mathematical constants. If the number of bits of the feature vector of the second application is filled to a preset number of bits, the filled feature vector is divided into multiple vector blocks of preset bytes; Each vector block corresponding to the feature vector is decomposed into multiple message blocks of preset length to obtain the basic message word in the hash algorithm; After arranging the information in the application action information of the second application in sequence, a specific vector is generated, and the extended message words corresponding to the remaining words in the hash algorithm are determined according to the values ​​at multiple specified positions in the specific vector. The multiple basic message words corresponding to each vector block are combined with the extended message words to generate the hash constants of the multiple message blocks corresponding to each vector block; The hash value of each message block is obtained by iteratively calculating the initial hash value and the hash constants of the multiple message blocks corresponding to each vector block. Based on the hash values ​​of the multiple message blocks corresponding to each vector block, an application tracking fingerprint corresponding to the second application is generated.

[0089] In one possible implementation, the generation and saving module 230 is configured as follows: Calculate the square root of the values ​​at multiple specified positions in the specific vector to obtain the first value at a preset number of decimal places corresponding to each specified position; Convert the numerical values ​​at each specified position to binary representations of the predetermined number of decimal places. According to the order of the specified positions, the binary values ​​corresponding to each specified position are sequentially used as the extended message words corresponding to the remaining multiple words in the hash algorithm.

[0090] In one possible implementation, the application actions include at least one of the following: user profile building actions, ad matching actions, product matching actions, ad behavior expansion actions, applicable audience matching actions, behavior pattern recognition actions, and activity statistics actions.

[0091] In one possible implementation, the application action information includes at least one of the following: the frequency of using the advertising behavior information, the application action of using the advertising behavior information, the conditions for using the advertising behavior information, and the font of the application.

[0092] This disclosure also provides an electronic device, including: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of any of the methods described in the foregoing embodiments.

[0093] Figure 3 The cross-application advertising behavior information tracking device 100 shown includes a processor 1001 and a memory 1003. The processor 1001 and the memory 1003 are connected, for example, via a bus 1002. Optionally, the cross-application advertising behavior information tracking device 100 may further include a communication component, which can be used for data interaction between the device 100 and other devices, such as sending and / or receiving data. It should be noted that in actual scheduling, the communication component is not limited to one, and the structure of this cross-application advertising behavior information tracking device 100 does not constitute a limitation on the embodiments of this application.

[0094] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0095] Bus 1002 may include a pathway for transmitting information between the aforementioned components. Bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 1002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0096] The memory 1003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing program code and capable of being read by a computer, without limitation herein.

[0097] The memory 1003 is used to store program code for executing embodiments of the present disclosure, and its execution is controlled by the processor 1001. The processor 1001 is used to execute the program code stored in the memory 1003 to implement the steps shown in the foregoing embodiments of the cross-application advertising behavior information application tracking method.

[0098] This disclosure also provides a computer-readable storage medium storing program code, which, when executed by a processor, can implement the steps and corresponding content of the aforementioned cross-application advertising behavior information application tracking method embodiment.

[0099] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present disclosure, various changes, modifications, substitutions and variations can be made to these embodiments, and all such changes, modifications, substitutions and variations fall within the protection scope of the present disclosure.

[0100] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction, and such combinations should also be considered as part of this disclosure. To avoid unnecessary repetition, this disclosure will not further describe the various possible combinations. The technical scope of this application is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for tracking cross-application advertising behavior information, characterized in that, The method, applied to a first application, wherein the target ad playback page of the first application contains pixel code in its Hypertext Transfer Protocol for a second application to back up the ad behavior information from the first application across applications, includes: In response to the action of the second application backing up the advertising behavior information across applications from the target advertising playback page of the first application through the pixel code, an application action information instructing the second application to report the application of the advertising behavior information is sent to the second application; Receive the application action information reported by the second application, and construct the feature vector of the second application based on the application action information reported by the second application and the advertising behavior information; Based on the feature vector of the second application, an application tracking fingerprint corresponding to the second application is generated, and the application tracking fingerprint is added to the advertising behavior information backed up by the second application and the application tracking fingerprint corresponding to the second application is saved. The advertising behavior information with added application tracking fingerprint is backed up to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, the application action information corresponding to the application action is obtained through the application tracking fingerprint. Based on the application action information, a matching fingerprint for the application action of the second application is generated, and the matching fingerprint is matched with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

2. The cross-application advertising behavior information application tracking method as described in claim 1, characterized in that, The step of constructing a feature vector for the second application based on the application action information and advertising behavior information reported by the second application includes: Based on the created advertising behavior vocabulary, each advertising behavior term in the advertising behavior information is converted into a vector as a text, resulting in multiple advertising behavior term vectors corresponding to the advertising behavior information. The advertising behavior vocabulary stores binary tags in the advertising behavior segment without repetition. The multiple advertising behavior vectors corresponding to the advertising behavior information are arranged into a two-dimensional matrix according to the preset order of advertising behavior terms. In the two-dimensional matrix, the vertical axis represents different advertising behavior terms, and the horizontal axis is the advertising behavior vector of each advertising behavior term. The application action information reported by the second application is vectorized to obtain the application action vector of each application action term in the application action information; The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix are standardized and then concatenated to obtain the feature vector of the second application.

3. The cross-application advertising behavior information tracking method as described in claim 2, characterized in that, The step of standardizing and concatenating the advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term in the two-dimensional matrix to obtain the feature vector of the second application includes: Calculate the mean and standard deviation of the advertising behavior vector for each advertising behavior term and the application action vector for each application action term in the two-dimensional matrix; Based on the mean and the standard deviation, the advertising behavior vector of each advertising behavior term and the application action vector of each application action term are standardized by Z-score. The advertising behavior vectors of each advertising behavior term and the application action vectors of each application action term, after Z-score standardization, are concatenated to obtain the feature vector of the second application.

4. The cross-application advertising behavior information tracking method as described in claim 1, characterized in that, The step of responding to the application action of the second application regarding the advertising behavior information, and obtaining the application action information corresponding to the application action through the application tracking fingerprint, includes: Receive a reporting request sent by the second application, wherein the reporting request is generated by the second application in response to an application action on the advertising behavior information, based on the application tracking fingerprint, and sent to the first application based on the first application identifier corresponding to the application tracking fingerprint; Parse the reporting request to obtain specific API endpoint information and the application tracking fingerprint carried in the reporting request for obtaining application action information corresponding to the application action; The parsed application tracking fingerprint is compared with the saved application tracking fingerprint. If the comparison result indicates that the two fingerprints match, an encapsulation instruction is sent to the second application to encapsulate the application action information corresponding to the application action. Upon receiving feedback that the second application has been packaged, the application action information corresponding to the packaged application action is obtained through the specific API endpoint represented by the specific API endpoint information.

5. The cross-application advertising behavior information tracking method as described in claim 1, characterized in that, The step of generating the application tracking fingerprint corresponding to the second application based on the feature vector of the second application includes: The initial hash value is determined by taking the first 32 decimal places of the square roots of several prime numbers in the mathematical constants. If the number of bits of the feature vector of the second application is filled to a preset number of bits, the filled feature vector is divided into multiple vector blocks of preset bytes; Each vector block corresponding to the feature vector is decomposed into multiple message blocks of preset length to obtain the basic message word in the hash algorithm; After arranging the information in the application action information of the second application in sequence, a specific vector is generated, and the extended message words corresponding to the remaining words in the hash algorithm are determined according to the values ​​at multiple specified positions in the specific vector. The multiple basic message words corresponding to each vector block are combined with the extended message words to generate the hash constants of the multiple message blocks corresponding to each vector block; The hash value of each message block is obtained by iteratively calculating the initial hash value and the hash constants of the multiple message blocks corresponding to each vector block. Based on the hash values ​​of the multiple message blocks corresponding to each vector block, an application tracking fingerprint corresponding to the second application is generated.

6. The method as described in claim 5, characterized in that, The step of determining the extended message word corresponding to the remaining multiple words in the hash algorithm based on the values ​​at multiple specified positions in the specific vector includes: Calculate the square root of the values ​​at multiple specified positions in the specific vector to obtain the first value at a preset number of decimal places corresponding to each specified position; Convert the numerical values ​​at each specified position to binary representations of the preset number of decimal places; Based on the order of the specified positions, the binary values ​​corresponding to each specified position are sequentially used as the extended message words corresponding to the remaining multiple words in the hash algorithm.

7. The method according to any one of claims 1-6, characterized in that, The application actions include at least one of the following: user profile building action, ad matching action, product matching action, ad behavior expansion action, applicable audience matching action, behavior pattern recognition action, and activity statistics action.

8. The method according to any one of claims 1-6, characterized in that, The application action information includes at least one of the following: the frequency of using the advertising behavior information, the application action of using the advertising behavior information, the conditions for using the advertising behavior information, and the font of the application.

9. A cross-application advertising behavior information tracking device, characterized in that, The device, applied to a first application, wherein the target ad playback page of the first application contains pixel code added to its Hypertext Transfer Protocol for a second application to back up the ad behavior information from the first application across applications, comprises: The sending module is configured to send application action information to the second application in response to the action of the second application backing up the advertising behavior information across applications from the target advertising playback page of the first application through the pixel code, instructing the second application to report the application of the advertising behavior information; The receiving and constructing module is configured to receive the application action information reported by the second application, and construct the feature vector of the second application based on the application action information and the advertising behavior information reported by the second application. The generation and saving module is configured to generate an application tracking fingerprint corresponding to the second application based on the feature vector of the second application, and to add the application tracking fingerprint to the advertising behavior information backed up by the second application and save the application tracking fingerprint corresponding to the second application. The acquisition module is configured to back up the advertising behavior information with the added application tracking fingerprint to the second application through the pixel code of the second application, and in response to the application action of the second application on the advertising behavior information, acquire the application action information corresponding to the application action through the application tracking fingerprint; The generation and matching module is configured to generate a matching fingerprint for the application action of the second application based on the application action information, and match the matching fingerprint with the application tracking fingerprint to obtain the application tracking result for the second application in response to the advertising behavior information.

10. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-8.

Images