Method and device for calculating contact ratio of target objects in social media account

Abstract

The embodiment of the invention provides a method and device for calculating the contact ratio of target objects in social media accounts and electronic equipment, and belongs to the technical field of data processing.The method comprises the steps that a first data set DA and a second data set DB are collected from n social media platforms; on the basis of a user identifier correlation function fu and a behavior feature matching function ft, cross-platform target object matching operation is executed on the first data set DA and the second data set DB, and a third data set DA'and a fourth data set DB 'are obtained; based on the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap ratio value J3, determining an overlap ratio value JAB of target objects included in the first account A and the first account B; calculating an incremental overlap ratio value delta J corresponding to the changed target object; and based on the contact ratio value JAB and the incremental contact ratio value delta J, generating a visual chart V, a feature analysis report R and dynamic trend tracking data Tr. According to the invention, the accuracy and flexibility of target object coincidence degree calculation are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and electronic device for calculating the overlap degree of target objects in a social media account. Background Art

[0002] "Overlapping users" in social media refer to groups of users who follow or like two or more social media accounts at the same time. This phenomenon is very common on social media platforms, especially between brands, individuals or organizations with similar interests, topics or audiences. These "overlapping users" become the target objects that need to be processed during data processing.

[0003] In the prior art, the calculation of target object overlap in social media accounts has the following problems:

[0004] 1. High computational complexity: When processing large-scale target object data, existing methods are often computationally inefficient and cannot obtain the target object overlap in real time.

[0005] 2. Cross-platform target object matching is difficult: Different social media platforms have different user identification methods, and existing methods cannot effectively match target object data across platforms.

[0006] 3. Single definition of overlap: Traditional methods usually calculate the overlap of target objects through simple intersection / union, failing to consider multi-dimensional factors such as the target objects’ interactive behavior and influence, resulting in inaccurate results.

[0007] 4. Insufficient dynamic update capability: In an environment where the target object data changes in real time, existing algorithms are difficult to effectively update the overlap analysis results and lack dynamic adjustment capabilities.

[0008] The above problems become technical problems that need to be solved. Summary of the invention

[0009] In view of this, an embodiment of the present invention provides a method, device and electronic device for calculating the overlap degree of target objects in a social media account, which at least partially solve the problems existing in the prior art.

[0010] In a first aspect, an embodiment of the present invention provides a method for calculating the overlap degree of target objects in a social media account, comprising:

[0011] Collect a first data set DA={uA, idA, tA, fA} of the target objects included in the first account A and a second data set DB={uB, idB, tB, fB} of the target objects included in the second account B from n social media platforms, where uA represents the user name of the target object included in the first account A, idA represents the user ID of the target object included in the first account A, tA represents the attention time of the target object included in the first account A, fA represents the interaction frequency of the target object included in the first account A, uB represents the user name of the target object included in the second account B, idB represents the user ID of the target object included in the second account B, tB represents the attention time of the target object included in the second account B, and fB represents the interaction frequency of the target object included in the second account B;

[0012] Based on the user identifier association function fu and the behavior feature matching function ft, a cross-platform target object matching operation is performed on the first data set DA and the second data set DB respectively to obtain a third data set DA' and a fourth data set DB';

[0013] Calculate the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determine the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3;

[0014] Within a preset time period Δt, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, the incremental coincidence value ΔJ corresponding to the changed target objects is calculated;

[0015] Based on the overlap value JAB and the incremental overlap value ΔJ, a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr are generated.

[0016] According to a specific implementation of an embodiment of the present invention, the first data set DA={uA, idA, tA, fA} of the target objects included in the first account A and the second data set DB={uB, idB, tB, fB} of the target objects included in the second account B are collected from n social media platforms, including:

[0017] Through the API interface of the social media platform, the target object data of the target account is collected. The target object data includes the target object's username, user ID, follow-up time, and interaction frequency.

[0018] According to a specific implementation of an embodiment of the present invention, after collecting a first data set DA={uA, idA, tA, fA} of target objects included in a first account A and a second data set DB={uB, idB, tB, fB} of target objects included in a second account B from n social media platforms, the method further includes:

[0019] Standardize the collected target object data and unify the target object identifier formats of different platforms;

[0020] Remove duplicate data, invalid data, and noise data contained in the target object data.

[0021] According to a specific implementation of an embodiment of the present invention, the cross-platform target object matching operation is performed on the first data set DA and the second data set DB respectively based on the user identifier association function fu and the behavior feature matching function ft to obtain the third data set DA' and the fourth data set DB', including:

[0022] Based on the user identifier association function fu, the user identifier matching result set M1 is calculated:

[0023]

[0024] It is the user identifier association function used to determine the user name and Whether it matches;

[0025] Based on the behavior feature matching function ft, calculate the interaction frequency similarity between target object i and target object j :

[0026]

[0027] Set the similarity threshold θ, calculate all target object pairs whose similarities are higher than the threshold, and obtain the behavior feature matching result set M2:

[0028]

[0029] By merging the matching results, we obtain the final matching result set M containing all target object pairs matched by user identifiers and behavioral features:

[0030]

[0031] Based on the final matching result set M, a third data set DA' and a fourth data set DB' are generated:

[0032]

[0033] .

[0034] According to a specific implementation of an embodiment of the present invention, the calculation of the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and the determination of the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, include:

[0035] J1 is obtained by calculating the sum of the interaction frequencies of the matched target objects on the two accounts and dividing it by the union of the total number of target objects in the two accounts:

[0036]

[0037] The multi-influence weighted value J2 is obtained by calculating the sum of the product of the interaction frequency of the matched target objects on the two accounts and their influence scores, and dividing it by the union of the total number of target objects of the two accounts:

[0038]

[0039] The target feature portrait overlap value J3 is obtained by calculating the sum of the products of the interaction frequency, influence score, and portrait feature similarity of the matched target object on the two accounts and dividing it by the union of the total number of target objects of the two accounts:

[0040]

[0041] wAi represents the influence score of the i-th target object in the first account A, fAi represents the interaction frequency of the i-th target object in the first account A, S v,i represents the similarity of the image features of the i-th target object in the first account A, wBj represents the influence score of the j-th target object in the second account B, fBj represents the interaction frequency of the j-th target object in the second account B, S v,j represents the similarity of the image features of the jth target object in the second account B, Represents the union of the total number of target objects of two accounts.

[0042] According to a specific implementation of an embodiment of the present invention, the calculation of the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determining the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, also includes:

[0043] Set the calculation formula for the comprehensive overlap value JAB:

[0044]

[0045] Among them, α, β, γ are weight coefficients, and k is the adjustment factor.

[0046] According to a specific implementation of an embodiment of the present invention, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, calculating the incremental coincidence value ΔJ corresponding to the changed target object includes:

[0047] Monitor the number of target objects of the first account A and the second account B. If the change value of the number of target objects of any account exceeds a preset value η, obtain the first data set DA and the second data set DB before the change, and obtain the first data set DA' and the second data set DB' after the change;

[0048] Calculate the comprehensive coincidence value JAB of the first account A and the second account B before the change, and calculate the comprehensive coincidence value JAB' of the first account A and the second account B after the change;

[0049] Calculate the difference in overlap values ​​before and after the change, ΔJ = JAB'-JAB.

[0050] According to a specific implementation of an embodiment of the present invention, generating a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ includes:

[0051] Generate a visualization chart V of the target object overlap using a chart tool;

[0052] Based on the target object portrait features, generate the target object coincidence feature analysis table R;

[0053] Through the dynamic update module, the changing trend of the overlap degree of the target object is tracked in real time to form the dynamic trend tracking data Tr.

[0054] In a second aspect, an embodiment of the present invention provides a device for calculating the overlap degree of target objects in a social media account, comprising:

[0055] A collection module collects a first data set DA={uA, idA, tA, fA} of target objects contained in a first account A and a second data set DB={uB, idB, tB, fB} of target objects contained in a second account B from n social media platforms, where uA represents the user name of the target object contained in the first account A, idA represents the user ID of the target object contained in the first account A, tA represents the attention time of the target object contained in the first account A, fA represents the interaction frequency of the target object contained in the first account A, uB represents the user name of the target object contained in the second account B, idB represents the user ID of the target object contained in the second account B, tB represents the attention time of the target object contained in the second account B, and fB represents the interaction frequency of the target object contained in the second account B;

[0056] A matching module, based on the user identifier association function fu and the behavior feature matching function ft, performs a cross-platform target object matching operation on the first data set DA and the second data set DB respectively to obtain a third data set DA' and a fourth data set DB';

[0057] A determination module calculates the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determines the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3;

[0058] A calculation module, within a preset time period Δt, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, calculates an incremental coincidence value ΔJ corresponding to the changed target objects;

[0059] The generation module generates a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ.

[0060] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0061] at least one processor; and,

[0062] a memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for calculating the overlap degree of target objects in a social media account in any of the first aspects or any of the implementations of the first aspect.

[0064] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the method for calculating the overlap degree of target objects in a social media account in the aforementioned first aspect or any implementation method of the first aspect.

[0065] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for calculating the overlap degree of target objects in a social media account in the aforementioned first aspect or any implementation of the first aspect.

[0066] The scheme for calculating the overlap of target objects in social media accounts in an embodiment of the present invention includes: collecting a first data set DA={uA, idA, tA, fA} of target objects included in a first account A and a second data set DB={uB, idB, tB, fB} of target objects included in a second account B from n social media platforms, where uA represents the user name of the target object included in the first account A, idA represents the user ID of the target object included in the first account A, tA represents the attention time of the target object included in the first account A, fA represents the interaction frequency of the target object included in the first account A, uB represents the user name of the target object included in the second account B, idB represents the user ID of the target object included in the second account B, tB represents the attention time of the target object included in the second account B, and fB represents the interaction frequency of the target object included in the second account B; based on the user identifier association function fu and behavioral feature matching function ft, respectively perform cross-platform target object matching operations on the first data set DA and the second data set DB to obtain a third data set DA' and a fourth data set DB'; calculate the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determine the overlap value JAB of the target objects contained in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3; within the preset time period Δt, when the number change value of the target objects in the first account A or the second account B exceeds the preset value η, calculate the incremental overlap value ΔJ corresponding to the changed target object; based on the overlap value JAB and the incremental overlap value ΔJ, generate a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr. The present invention has the following beneficial effects:

[0067] aMulti-dimensional comprehensive analysis:

[0068] By introducing interaction frequency, influence and target object portrait features, the system realizes a multi-dimensional comprehensive analysis of target object overlap, providing a more accurate and comprehensive target object overlap assessment.

[0069] bCross-platform target object matching:

[0070] By associating user identifiers and matching behavioral features, the system can effectively solve the problem of cross-platform target object matching and ensure the accuracy of overlap calculations.

[0071] cReal-time dynamic update:

[0072] The system supports incremental calculation and real-time data stream processing, and can quickly update the analysis results when the target object data changes, ensuring the real-time and dynamic response capabilities of the overlap assessment.

[0073] d. Efficient computing and strong generalization ability:

[0074] The optimized algorithm and incremental update mechanism significantly improve the efficiency of large-scale target object data processing, can run efficiently in a big data environment, and is suitable for any social media platform in the world. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0076] Figure 1 A schematic flow chart of a method for calculating the overlap of target objects in a social media account provided by an embodiment of the present invention;

[0077] Figure 2 A schematic flow chart of another method for calculating the overlap of target objects in social media accounts provided by an embodiment of the present invention;

[0078] Figure 3 A schematic diagram of the structure of a device for calculating the degree of overlap of target objects in a social media account provided by an embodiment of the present invention;

[0079] Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0081] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0082] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0083] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0084] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0085] The disclosed embodiment provides a method for calculating the coincidence of target objects in a social media account. The method for calculating the coincidence of target objects in a social media account provided in the embodiment can be executed by a computing device, which can be implemented as software, or as a combination of software and hardware, and the computing device can be integrated in a server, a terminal device, etc.

[0086] See also Figure 1 and Figure 2 The present disclosure provides a method for calculating the overlap of target objects in social media accounts, including:

[0087] S101, collect a first data set DA={uA, idA, tA, fA} of the target objects included in the first account A and a second data set DB={uB, idB, tB, fB} of the target objects included in the second account B from n social media platforms, where uA represents the user name of the target object included in the first account A, idA represents the user ID of the target object included in the first account A, tA represents the attention time of the target object included in the first account A, fA represents the interaction frequency of the target object included in the first account A, uB represents the user name of the target object included in the second account B, idB represents the user ID of the target object included in the second account B, tB represents the attention time of the target object included in the second account B, and fB represents the interaction frequency of the target object included in the second account B.

[0088] The target object data collection module can be used to obtain the target object data of the target account from multiple social media platforms and perform preliminary processing. The specific steps include:

[0089] aData interface access:

[0090] Through the API interface or crawler technology of the social media platform, the target object data of the target account is collected. This data includes the target object’s username, user ID, follow-up time, interaction frequency, etc.

[0091] bData standardization processing:

[0092] Standardize the collected target object data and unify the target object identifier format on different platforms. For example, convert the user ID and user name on different platforms into a unified identifier format for subsequent cross-platform matching.

[0093] cData deduplication and cleaning:

[0094] Remove duplicate data, invalid data, and noise data to ensure the accuracy and completeness of the target object data. Remove invalid target objects (such as zombie accounts and robots) through algorithms and format the data.

[0095] S102, based on the user identifier association function fu and the behavior feature matching function ft, respectively perform a cross-platform target object matching operation on the first data set DA and the second data set DB to obtain a third data set DA' and a fourth data set DB'.

[0096] The user identifier association function fu can be used to compare the user names of the target objects in DA and DB. If the user names of the two target objects are the same, they are considered to be the same user and the matching relationship is recorded.

[0097] Use the behavior feature matching function ft to compare the interaction frequencies of the target objects in DA and DB. Calculate the similarity of the interaction frequencies of each pair of target objects. Set a similarity threshold θ. If the similarity is greater than θ, the two are considered to be the same user and the matching relationship is recorded.

[0098] The results obtained by username matching and interaction frequency matching are combined to form a final matching result set M. The matching results in MM are verified to ensure the accuracy of the matching.

[0099] The third data set DA′ contains the information of the successfully matched target objects in the first account A and their user IDs in the second account B. Each element is a five-tuple (uAi, idAi, tAi, fAi, idB, j), which represents the i-th target object in the first account A and its matching ID in the second account B.

[0100] The fourth data set DB′ contains the information of the successfully matched target objects in the second account B and their user IDs in the first account A. Each element is a five-tuple (uBj, idBj, tBj, fBj, idA, i), which represents the jjth target object in the second account B and its matching ID in the first account A.

[0101] Through the above steps, based on the user identifier association function fu and the behavior feature matching function ftft, the first data set DA and the second data set DB are matched across platforms to obtain the new third data set DA' and the fourth data set DB'. These new data sets contain the target object information that has been successfully matched, which provides a basis for the subsequent coincidence calculation and other analysis.

[0102] S103, calculate the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determine the overlap value JAB of the target objects contained in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3.

[0103] In the process of calculating the interaction frequency weighted value J1, each pair of matching target objects (idAi, idBj) in the matching result set M can be traversed. For each pair of matching target objects, their interaction frequencies fAi and fBj in the first account A and the second account B are obtained, and the sum of the interaction frequencies of this pair of target objects fAi+fBj is calculated. The sum of the interaction frequencies of all matching target objects is added up, and the union of the total number of target objects of the two accounts |A∪B| is calculated. The sum of the accumulated interaction frequencies is divided by |A∪B| to obtain the interaction frequency weighted value J1.

[0104] In the process of calculating the multi-influence weighted value J2, each pair of matching target objects (idAi, idBj) in the matching result set M can be traversed. For each pair of matching target objects, their interaction frequencies fAi and fBj in the first account A and the second account B, as well as influence scores wAi and wBj are obtained. The multi-influence weighted value wAi×fAi+wBj×fBj of this pair of target objects is calculated. The multi-influence weighted values ​​of all matching target objects are added up. The union of the total number of target objects of the two accounts |A∪B| is calculated. The accumulated multi-influence weighted value is divided by |A∪B| to obtain the multi-influence weighted value J2.

[0105] In the process of calculating the target feature portrait overlap value J3, each pair of matching target objects (idAi, idBj) in the matching result set M can be traversed. For each pair of matching target objects, their interaction frequencies fAi and fBj in the first account A and the second account B, influence scores wAi and wBj, and portrait feature similarity S are obtained. v,i and S v,j , calculate the overlap value of the target feature image of this pair of target objects: wAi×fAi×S v,i +wBj×fBj×S v,j , add up the target feature portrait overlap values ​​of all matching target objects, calculate the union of the total number of target objects of the two accounts |A∪B|, divide the accumulated target feature portrait overlap values ​​by |A∪B|, and get the target feature portrait overlap value J3.

[0106] Finally, the overlap value JAB can be determined. After determining the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, the weight coefficients α, β, and γ are assigned to these three values ​​to ensure that α+β+γ=1. Calculate the weighted index of each value, use the adjustment factor k to control the sensitivity, sum the weighted index values, take the square root of the sum, and get the final overlap value JAB.

[0107] S104, within a preset time period Δt, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, calculating the incremental coincidence value ΔJ corresponding to the changed target objects.

[0108] The number of target objects of the first account A and the second account B can be continuously monitored within a preset time period Δt. The change in the number of target objects within each time period is recorded. It is checked whether the change value of the number of target objects exceeds a preset value η.

[0109] When the change value of the number of target objects exceeds η, the changed target objects are recorded, the newly added target objects and the deleted target objects are determined, and the detailed information of these target objects is collected, including user name, user ID, attention time and interaction frequency.

[0110] The first data set DA and the second data set DB before the change may be acquired, and the first data set DA′ and the second data set DB′ after the change may be acquired.

[0111] Calculate the comprehensive overlap value JAB of the first account A and the second account B before the change, calculate the comprehensive overlap value JAB' of the first account A and the second account B after the change, and calculate the difference between the overlap values ​​before and after the change, that is, ΔJ=JAB'-JAB, where ΔJ represents the overlap change value caused by the change in the number of target objects.

[0112] If ΔJ is positive, it means that the newly added target object increases the overlap between the two accounts; if ΔJ is negative, it means that the overlap decreases.

[0113] Through these steps, the incremental coincidence value ΔJ corresponding to the changed target object can be effectively calculated when the change value of the number of target objects in the first account A or the second account B exceeds the preset value η within the preset time period Δt. This helps to monitor and analyze the change of the coincidence of target objects between accounts in real time.

[0114] S105 , generating a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ.

[0115] Based on the overlap value JAB and the incremental overlap value ΔJ, a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr may be generated.

[0116] 1. Generate a visual chart V

[0117] a. Visualization of the overlap value JAB

[0118] Chart type: bar chart or line chart

[0119] Content: Displays the comprehensive overlap value JAB of the first account A and the second account B.

[0120] Example: Use a bar chart to display the value of JAB, with different colors representing different time points or different account combinations.

[0121] b. Visualization of incremental overlap value ΔJ

[0122] Chart type: bar chart or line chart

[0123] Content: Displays the change of the incremental overlap value ΔJ each time the number of target objects changes.

[0124] Example: Use a line graph to show the trend of ΔJ over time, marking the time point when the number of target objects changes each time.

[0125] c. Comprehensive visualization of overlap and incremental overlap

[0126] Chart type: Overlay line chart or dual axis chart

[0127] Content: Show the changing trends of JAB and ΔJ in the same chart for intuitive comparison.

[0128] Example: Using a dual-axis graph, the left axis shows JAB, the right axis shows ΔJ, and the two broken lines represent the changes in these two values.

[0129] 2. Generate feature analysis report R

[0130] a. Demographic Characteristics Analysis

[0131] Content: Analyze the demographic characteristics of overlapping target objects, such as age, gender, region, occupation, etc.

[0132] Example:

[0133] Age distribution: Displays the age distribution of overlapping target objects, such as a pie chart or bar chart.

[0134] Gender ratio: Displays the gender ratio of overlapping target objects, such as a pie chart.

[0135] Geographic distribution: Displays the geographic distribution of overlapping target objects, such as a map heat map.

[0136] b. Interest and hobby analysis

[0137] Content: Analyze the interests and hobbies of overlapping target objects, such as the topics they follow, the communities they participate in, the types of content they like, etc.

[0138] Example:

[0139] Topic distribution: Displays the topic distribution of overlapping target objects, such as a word cloud diagram.

[0140] Community participation: Displays the proportion of different communities in which overlapping target objects participate, such as a pie chart.

[0141] c. Behavioral characteristics analysis

[0142] Content: Analyze the behavioral characteristics of overlapping target objects, such as browsing habits, purchasing behavior, content consumption preferences, etc.

[0143] Example:

[0144] Browsing habits: Displays the browsing time distribution of overlapping target objects, such as a line graph.

[0145] Purchase behavior: Display the purchase frequency and amount distribution of overlapping target objects, such as a bar chart.

[0146] Content consumption preference: Displays the distribution of content types that the overlapping target objects like, such as a pie chart.

[0147] 3. Dynamic trend tracking data Tr

[0148] a. Time Series Analysis

[0149] Content: Record the time point of each change in the number of target objects, as well as the corresponding JAB and ΔJ values.

[0150] Example:

[0151] Time series graph: shows the changing trend of JAB and ΔJ over time, marking the time point when the number of target objects changes each time.

[0152] Data table: lists the specific data of each change, including time, JAB value before and after the change, incremental ΔJ value, etc.

[0153] b. Analysis of influencing factors

[0154] Content: Analyze the main factors affecting JAB and ΔJ, such as the characteristics of the newly added or deleted target objects.

[0155] Example:

[0156] Influencing factor pie chart: shows the influence ratio of each factor on JAB and ΔJ.

[0157] Factor analysis table: lists the main influencing factors of each change and their contribution.

[0158] c. Dynamic change trend

[0159] Content: Summarize the dynamic change trend of the overlap value and predict the future change trend.

[0160] Example:

[0161] Trend prediction chart: Use time series analysis method to predict future overlap trend.

[0162] Dynamic Report: Prepare an analysis report on dynamic change trends, including the causes of change, influencing factors and predictions of future trends.

[0163] Through these steps and methods, detailed visualization charts, feature analysis reports, and dynamic trend tracking data can be generated to help users fully understand and analyze changes in the overlap of target objects between the first account A and the second account B.

[0164] According to a specific implementation of an embodiment of the present invention, the first data set DA={uA, idA, tA, fA} of the target objects included in the first account A and the second data set DB={uB, idB, tB, fB} of the target objects included in the second account B are collected from n social media platforms, including:

[0165] Through the API interface of the social media platform, the target object data of the target account is collected. The target object data includes the target object's username, user ID, follow-up time, and interaction frequency.

[0166] According to a specific implementation of an embodiment of the present invention, after collecting a first data set DA={uA, idA, tA, fA} of target objects included in a first account A and a second data set DB={uB, idB, tB, fB} of target objects included in a second account B from n social media platforms, the method further includes:

[0167] Standardize the collected target object data and unify the target object identifier formats of different platforms;

[0168] Remove duplicate data, invalid data, and noise data contained in the target object data.

[0169] According to a specific implementation of an embodiment of the present invention, the cross-platform target object matching operation is performed on the first data set DA and the second data set DB respectively based on the user identifier association function fu and the behavior feature matching function ft to obtain the third data set DA' and the fourth data set DB', including:

[0170] Based on the user identifier association function fu, the user identifier matching result set M1 is calculated:

[0171]

[0172] It is the user identifier association function used to determine the user name and Whether it matches;

[0173] Based on the behavior feature matching function ft, calculate the interaction frequency similarity between target object i and target object j :

[0174]

[0175] Set the similarity threshold θ, calculate all target object pairs whose similarities are higher than the threshold, and obtain the behavior feature matching result set M2:

[0176]

[0177] By merging the matching results, we obtain the final matching result set M containing all target object pairs matched by user identifiers and behavioral features:

[0178]

[0179] Based on the final matching result set M, a third data set DA' and a fourth data set DB' are generated:

[0180]

[0181] .

[0182] According to a specific implementation of an embodiment of the present invention, the calculation of the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and the determination of the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, include:

[0183] J1 is obtained by calculating the sum of the interaction frequencies of the matched target objects on the two accounts and dividing it by the union of the total number of target objects in the two accounts:

[0184]

[0185] The multi-influence weighted value J2 is obtained by calculating the sum of the product of the interaction frequency of the matched target objects on the two accounts and their influence scores, and dividing it by the union of the total number of target objects of the two accounts:

[0186]

[0187] The target feature portrait overlap value J3 is obtained by calculating the sum of the products of the interaction frequency, influence score, and portrait feature similarity of the matched target object on the two accounts and dividing it by the union of the total number of target objects of the two accounts:

[0188]

[0189] wAi represents the influence score of the i-th target object in the first account A, fAi represents the interaction frequency of the i-th target object in the first account A, S v,irepresents the similarity of the image features of the i-th target object in the first account A, wBj represents the influence score of the j-th target object in the second account B, fBj represents the interaction frequency of the j-th target object in the second account B, S v,j represents the similarity of the image features of the jth target object in the second account B, Represents the union of the total number of target objects of two accounts.

[0190] According to a specific implementation of an embodiment of the present invention, the calculation of the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determining the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, also includes:

[0191] Set the calculation formula for the comprehensive overlap value JAB:

[0192]

[0193] Among them, α, β, γ are weight coefficients, and k is the adjustment factor.

[0194] According to a specific implementation of an embodiment of the present invention, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, calculating the incremental coincidence value ΔJ corresponding to the changed target object includes:

[0195] Monitor the number of target objects of the first account A and the second account B. If the change value of the number of target objects of any account exceeds a preset value η, obtain the first data set DA and the second data set DB before the change, and obtain the first data set DA' and the second data set DB' after the change;

[0196] Calculate the comprehensive coincidence value JAB of the first account A and the second account B before the change, and calculate the comprehensive coincidence value JAB' of the first account A and the second account B after the change;

[0197] Calculate the difference in overlap values ​​before and after the change, ΔJ = JAB'-JAB.

[0198] According to a specific implementation of an embodiment of the present invention, generating a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ includes:

[0199] Generate a visualization chart V of the target object overlap using a chart tool;

[0200] Based on the target object portrait features, generate the target object coincidence feature analysis table R;

[0201] Through the dynamic update module, the changing trend of the overlap degree of the target object is tracked in real time to form the dynamic trend tracking data Tr.

[0202] Corresponding to the above method embodiment, see Figure 3 The embodiment of the present invention further discloses a device 30 for calculating the target object overlap in a social media account, comprising:

[0203] The collection module 301 collects a first data set DA={uA, idA, tA, fA} of target objects included in a first account A and a second data set DB={uB, idB, tB, fB} of target objects included in a second account B from n social media platforms, where uA represents the user name of the target object included in the first account A, idA represents the user ID of the target object included in the first account A, tA represents the attention time of the target object included in the first account A, fA represents the interaction frequency of the target object included in the first account A, uB represents the user name of the target object included in the second account B, idB represents the user ID of the target object included in the second account B, tB represents the attention time of the target object included in the second account B, and fB represents the interaction frequency of the target object included in the second account B;

[0204] A matching module 302 performs a cross-platform target object matching operation on the first data set DA and the second data set DB based on the user identifier association function fu and the behavior feature matching function ft, respectively, to obtain a third data set DA' and a fourth data set DB';

[0205] The determination module 303 calculates the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determines the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3;

[0206] The calculation module 304 calculates the incremental coincidence value ΔJ corresponding to the changed target objects when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η within a preset time period Δt;

[0207] The generating module 305 generates a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ.

[0208] See also Figure 4The embodiment of the present invention further provides an electronic device 60, the electronic device comprising:

[0209] at least one processor; and,

[0210] a memory communicatively connected to the at least one processor; wherein,

[0211] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for calculating the overlap degree of target objects in social media accounts in the aforementioned method embodiment.

[0212] An embodiment of the present invention further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the aforementioned method embodiment.

[0213] An embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for calculating the overlap degree of target objects in social media accounts in the aforementioned method embodiment.

[0214] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device 60 suitable for implementing the embodiment of the present disclosure. The electronic device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0215] like Figure 4 As shown, the electronic device 60 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 60 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0216] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, a gage, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 60 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 60 is shown with various devices, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.

[0217] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0218] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for calculating the overlap of target objects in social media accounts, characterized in that: include: Collect a first data set DA={uA, idA, tA, fA} of the target objects included in the first account A and a second data set DB={uB, idB, tB, fB} of the target objects included in the second account B from n social media platforms, where uA represents the user name of the target object included in the first account A, idA represents the user ID of the target object included in the first account A, tA represents the attention time of the target object included in the first account A, fA represents the interaction frequency of the target object included in the first account A, uB represents the user name of the target object included in the second account B, idB represents the user ID of the target object included in the second account B, tB represents the attention time of the target object included in the second account B, and fB represents the interaction frequency of the target object included in the second account B; Based on the user identifier association function fu and the behavior feature matching function ft, a cross-platform target object matching operation is performed on the first data set DA and the second data set DB respectively to obtain a third data set DA' and a fourth data set DB'; Calculate the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determine the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3; Within a preset time period Δt, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, the incremental coincidence value ΔJ corresponding to the changed target objects is calculated; Based on the overlap value JAB and the incremental overlap value ΔJ, a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr are generated.

2. The method according to claim 1, characterized in that The method of collecting a first data set DA={uA, idA, tA, fA} of target objects included in a first account A and a second data set DB={uB, idB, tB, fB} of target objects included in a second account B from n social media platforms includes: Through the API interface of the social media platform, the target object data of the target account is collected. The target object data includes the target object's username, user ID, follow-up time, and interaction frequency.

3. The method according to claim 2, characterized in that After collecting a first data set DA={uA, idA, tA, fA} of target objects included in the first account A and a second data set DB={uB, idB, tB, fB} of target objects included in the second account B from n social media platforms, the method further includes: Standardize the collected target object data and unify the target object identifier formats of different platforms; Remove duplicate data, invalid data, and noise data contained in the target object data.

4. The method according to claim 3, characterized in that The method of performing cross-platform target object matching operations on the first data set DA and the second data set DB based on the user identifier association function fu and the behavior feature matching function ft, respectively, to obtain a third data set DA' and a fourth data set DB', comprises: Based on the user identifier association function fu, the user identifier matching result set M1 is calculated: It is the user identifier association function used to determine the user name and Whether it matches; Based on the behavior feature matching function ft, calculate the interaction frequency similarity between target object i and target object j : Set the similarity threshold θ, calculate all target object pairs whose similarities are higher than the threshold, and obtain the behavior feature matching result set M2: By merging the matching results, we obtain the final matching result set M containing all target object pairs matched by user identifiers and behavioral features: Based on the final matching result set M, a third data set DA' and a fourth data set DB' are generated: 。 5. The method according to claim 4, characterized in that The calculating of the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determining the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3, includes: J1 is obtained by calculating the sum of the interaction frequencies of the matched target objects on the two accounts and dividing it by the union of the total number of target objects in the two accounts: The multi-influence weighted value J2 is obtained by calculating the sum of the product of the interaction frequency of the matched target objects on the two accounts and their influence scores, and dividing it by the union of the total number of target objects of the two accounts: The target feature portrait overlap value J3 is obtained by calculating the sum of the products of the interaction frequency, influence score, and portrait feature similarity of the matched target object on the two accounts and dividing it by the union of the total number of target objects of the two accounts: wAi represents the influence score of the i-th target object in the first account A, fAi represents the interaction frequency of the i-th target object in the first account A, S v,i represents the similarity of the image features of the i-th target object in the first account A, wBj represents the influence score of the j-th target object in the second account B, fBj represents the interaction frequency of the j-th target object in the second account B, S v,j represents the similarity of the image features of the jth target object in the second account B, Represents the union of the total number of target objects of two accounts.

6. The method according to claim 5, characterized in that The calculating of the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determining the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2 and the target feature portrait overlap value J3, further includes: Set the calculation formula for the comprehensive overlap value JAB: Among them, α, β, γ are weight coefficients, and k is the adjustment factor.

7. The method according to claim 6, characterized in that When the change value of the number of target objects in the first account A or the second account B exceeds the preset value η, the incremental overlap value ΔJ corresponding to the changed target objects is calculated, including: Monitor the number of target objects of the first account A and the second account B. If the change value of the number of target objects of any account exceeds a preset value η, obtain the first data set DA and the second data set DB before the change, and obtain the first data set DA' and the second data set DB' after the change; Calculate the comprehensive coincidence value JAB of the first account A and the second account B before the change, and calculate the comprehensive coincidence value JAB' of the first account A and the second account B after the change; Calculate the difference in overlap values ​​before and after the change, ΔJ = JAB'-JAB.

8. The method according to claim 7, characterized in that The generating of a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ includes: Generate a visualization chart V of the target object overlap using a chart tool; Based on the target object portrait features, generate the target object coincidence feature analysis table R; Through the dynamic update module, the changing trend of the overlap degree of the target object is tracked in real time to form the dynamic trend tracking data Tr.

9. A device for calculating the overlap of target objects in social media accounts, characterized in that: include: A collection module collects a first data set DA={uA, idA, tA, fA} of target objects contained in a first account A and a second data set DB={uB, idB, tB, fB} of target objects contained in a second account B from n social media platforms, where uA represents the user name of the target object contained in the first account A, idA represents the user ID of the target object contained in the first account A, tA represents the attention time of the target object contained in the first account A, fA represents the interaction frequency of the target object contained in the first account A, uB represents the user name of the target object contained in the second account B, idB represents the user ID of the target object contained in the second account B, tB represents the attention time of the target object contained in the second account B, and fB represents the interaction frequency of the target object contained in the second account B; A matching module, based on the user identifier association function fu and the behavior feature matching function ft, performs a cross-platform target object matching operation on the first data set DA and the second data set DB respectively to obtain a third data set DA' and a fourth data set DB'; A determination module calculates the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3 between the third data set DA' and the fourth data set DB', and determines the overlap value JAB of the target objects included in the first account A and the first account B based on the interaction frequency weighted value J1, the multi-influence weighted value J2, and the target feature portrait overlap value J3; A calculation module, within a preset time period Δt, when the change value of the number of target objects in the first account A or the second account B exceeds a preset value η, calculates an incremental coincidence value ΔJ corresponding to the changed target objects; The generation module generates a visualization chart V, a feature analysis report R and dynamic trend tracking data Tr based on the overlap value JAB and the incremental overlap value ΔJ.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for calculating the overlap degree of target objects in a social media account as described in any one of claims 1 to 8.

Images