Data processing method, device and electronic device for social media hybrid platform

Abstract

In the embodiment of the present invention, a data processing method, device and electronic device for a social media hybrid platform are provided, which belongs to the field of data processing technology. The method includes: cleaning the collected raw data to obtain the cleaned data of the social media hybrid platform; establishing a unified field naming and data format standard for the data fields from different platforms in the cleaned data; using a feature extraction function to extract features from the data in the standardized data set to form a unified data set containing q data fields; setting a data analysis function to analyze and calculate the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance; after displaying the data analysis results in a visual display mode, generating decision data based on the data analysis results. This solution can comprehensively, accurately and efficiently analyze and process the social media data of the hybrid platform.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data processing method, device and electronic equipment for a social media hybrid platform. Background Art

[0002] As social media platforms diversify, companies and researchers increasingly need cross-platform data analysis methods to gain a comprehensive perspective. Traditional data analysis methods are usually performed on a single social media platform, resulting in data silos that make comprehensive analysis difficult.

[0003] Specifically, most of the data analysis tools currently on the market can only process data from a single platform, or cannot effectively integrate data from multiple platforms. Data integration and analysis across social media platforms faces multiple challenges such as data heterogeneity, indicator inconsistency, data quality control, user identification, real-time and privacy compliance, which directly affect the comprehensiveness, accuracy and efficiency of data analysis.

[0004] The cross-platform data integration tools in the prior art have the following defects:

[0005] 1. Incomplete data integration: The data structures and indicator definitions of different social media platforms vary, and there is a lack of effective integration methods.

[0006] 2. Low analysis efficiency: Analyzing data from different platforms separately increases workload and reduces analysis efficiency.

[0007] 3. Inconsistent information: Differences in data between different platforms lead to inconsistencies in analysis results, affecting the accuracy of decision-making.

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

[0009] In view of this, embodiments of the present invention provide a data processing method, device and electronic device for a social media hybrid platform, 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 data processing method for a social media hybrid platform, comprising:

[0011] The raw data of n social media platforms are collected through the APIs of the social media platforms, and the collected raw data are cleaned to obtain the cleaned data of the social media hybrid platform;

[0012] For the data fields from different platforms in the cleaned data, a unified field naming and data format standard is established. Through data type conversion, all data in the cleaned data is converted into standardized data types to form a standardized data set D={D1,D2,…Dn} containing n social media data. A standard field set G={G1,G2,…Gk} consisting of k standard data fields contained in the standardized data set D is extracted.

[0013] Using a feature extraction function, feature extraction is performed on the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and using the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk}, data mapping is performed on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields;

[0014] A data analysis function is set to analyze and calculate the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance, and a display data set Z={Z1, Z2, ...Zp} containing p display features is extracted based on the unified data set W, and the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result;

[0015] After the data analysis results are displayed in a visual presentation manner, decision data are generated based on the data analysis results.

[0016] According to a specific implementation of the embodiment of the present disclosure, the raw data of n social media platforms are collected through the APIs of the social media platforms, and the collected raw data are cleaned to obtain the cleaned data of the social media hybrid platform, including:

[0017] After selecting the social media platform to collect data, clarify the time range, geographical scope and user groups of data collection to ensure that the collected data meets the analysis objectives;

[0018] After dealing with the frequency limit and permission application of API calls, use the APIs provided by various social media platforms to collect data;

[0019] After determining the key data fields that must be collected by each social media platform, obtain the original data of each social media platform and back up the collected original data to prevent data loss or damage;

[0020] For the original data, remove duplicate data entries, remove irrelevant data and process erroneous data, identify missing values ​​in the data, and perform deletion, filling or prediction processing on the missing values;

[0021] Structural processing is performed on unstructured data, text content is converted into numerical indicators, string type dates are converted into date types, and all time data are converted into a unified time zone.

[0022] According to a specific implementation of the embodiment of the present disclosure, a unified field naming and data format standard is established for data fields from different platforms in the cleaned data, and all data in the cleaned data are converted into standardized data types through data type conversion to form a standardized data set D={D1, D2, ...Dn} containing n social media data, including:

[0023] Develop a unified field naming specification to specify the format, naming method, and terminology of field names, ensure that fields in all data sets follow the field naming specification, and rename the fields in the collected data according to the field naming specification;

[0024] Ensure that the same field uses the same measurement unit and date unit in different datasets. For fields with enumeration values, unify the expression of enumeration values, clarify the data type of each field, and ensure that the data type of the same field in different datasets is consistent.

[0025] When merging different data sets, create a field mapping table to list the corresponding relationships between fields with the same meaning in different data sets. According to the mapping table, map the fields in different data sets to a unified standard field.

[0026] Document the rules, processes, and mapping relationships for field standardization, and maintain and update the rules and mapping relationships for field standardization when data sources change and data sets expand.

[0027] According to a specific implementation method of an embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, including:

[0028] Perform word segmentation on the standardized data set to obtain the word segmentation phrase set U={U1,U2,…Ux};

[0029] Calculate the activity value of the participle phrase Ui

[0030]

[0031] Indicates the frequency of occurrence of the participle phrase Ui in the data Dj, Represents the sum of the frequencies of all participle phrases in the data Dj;

[0032] Select activity value Greater than the preset activity value words, and obtain a feature data set F={F1,F2,…Fm} containing m feature fields.

[0033] According to a specific implementation of an embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, and further includes:

[0034] Calculate the gradient value Trj between any field Gr and Gj in the standard field set G={G1,G2,…Gk}:

[0035]

[0036] LBL() is a character vectorization function, r≤k, j≤k, r≠j;

[0037] The fields whose gradient values ​​Trj are less than the preset gradient value Trj0 are merged to obtain a standard merged field set G'={G'1,G'2,…G'y}, y≤k.

[0038] According to a specific implementation of an embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, and further includes:

[0039] Calculate the gradient value Tij between any field Fi in the feature data set F={F1,F2,…Fm} and any field G'j in the standard merged field set G'={G'1,G'2,…G'y}:

[0040]

[0041] LBL() is a character vectorization function, i≤m, j≤y;

[0042] The field Fi whose gradient value Tij is less than the preset gradient value μ*Trj0 is deleted from the feature data set F={F1,F2,…Fm} to obtain the feature merged data set F'={F'1,F'2,…F'b}, where z≤m and μ is the preset mediation parameter;

[0043] The feature merged data set F'={F'1,F'2,…F'b} is merged with the standard merged field set G'={G'1,G'2,…G'y} to form a unified data set W={W1,W2,…Wq} containing q data fields.

[0044] According to a specific implementation of the embodiment of the present disclosure, the data analysis function is set to analyze and calculate the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance, and extract a display data set Z={Z1, Z2, ...Zp} containing p display features based on the unified data set W, and the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result, including:

[0045] Build an indicator library containing analysis dimensions, select indicators related to the analysis dimensions from the indicator library, and extract the data required to calculate the indicators from the integrated unified data set;

[0046] Calculate the value of a single indicator, or combine the calculation results of multiple basic indicators to analyze the changes of indicators over time and identify trends and patterns in the data;

[0047] Interpret the calculated indicator results, conduct in-depth analysis of abnormal results or important changes, and analyze the correlation between different indicators.

[0048] According to a specific implementation of the embodiment of the present disclosure, after displaying the data analysis result in a visual display manner, generating decision data based on the data analysis result includes:

[0049] Extract key information related to the decision-making goal from the visualization results, wherein the key information includes key data points, trend lines, and outliers;

[0050] Generate decision-making data based on the extracted key information;

[0051] Validate and test the generated decision data using historical data or simulated scenarios.

[0052] In a second aspect, an embodiment of the present invention provides a data processing device for a social media hybrid platform, including:

[0053] The collection module collects the raw data of n social media platforms through the APIs of each social media platform, and cleans the collected raw data to obtain the cleaned data of the social media hybrid platform;

[0054] The conversion module establishes a unified field naming and data format standard for data fields from different platforms in the cleaned data, converts all data in the cleaned data into standardized data types through data type conversion, forms a standardized data set D={D1,D2,…Dn} containing n social media data, and extracts a standard field set G={G1,G2,…Gk} consisting of k standard data fields contained in the standardized data set D;

[0055] A mapping module, using a feature extraction function, performs feature extraction on the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, uses the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, merges the mapped data into a unified data framework, and forms a unified data set W={W1, W2, ...Wq} containing q data fields;

[0056] The analysis module analyzes and calculates the data indicators in the unified data set by setting a data analysis function to evaluate and analyze the cross-platform social media performance, and extracts a display data set Z={Z1, Z2, ...Zp} containing p display features based on the unified data set W, wherein the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result;

[0057] The display module displays the data analysis results in a visual display manner and generates decision data based on the data analysis results.

[0058] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0059] at least one processor; and,

[0060] a memory communicatively connected to the at least one processor; wherein,

[0061] 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 to enable the at least one processor to execute the data processing method of the social media mixing platform in any of the aforementioned first aspects or any of the implementations of the first aspect.

[0062] 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 data processing method of the social media hybrid platform in the aforementioned first aspect or any implementation of the first aspect.

[0063] 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 data processing method of the social media hybrid platform in the aforementioned first aspect or any implementation of the first aspect.

[0064] The data processing scheme of the social media hybrid platform in the embodiment of the present invention includes: collecting raw data of n social media platforms through the API of each social media platform, and cleaning the collected raw data to obtain cleaned data of the social media hybrid platform; establishing a unified field naming and data format standard for data fields from different platforms in the cleaned data, converting all data in the cleaned data into standardized data types through data type conversion to form a standardized data set D={D1,D2,…Dn} containing n social media data, extracting a standard field set G={G1,G2,…Gk} consisting of k standard data fields contained in the standardized data set D; using a feature extraction function, extracting features of the data in the standardized data set D={D1,D2,…Dn} to obtain a feature data set F={F1,F2,… Fm}, use the feature data set F={F1,F2,…Fm} and the standard field set G={G1,G2,…Gk} to perform data mapping on the data in the standardized data set D={D1,D2,…Dn}, merge the mapped data into a unified data framework, and form a unified data set W={W1,W2,…Wq} containing q data fields; set a data analysis function to analyze and calculate the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance, and extract a display data set Z={Z1,Z2,…Zp} containing p display features based on the unified data set W, the display data set Z={Z1,Z2,…Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result; after displaying the data analysis result in a visual display manner, generate decision data based on the data analysis result. The scheme of the present application has the following beneficial effects:

[0065] Comprehensiveness: By integrating data from multiple social media platforms, it provides a comprehensive view, helping organizations gain more complete insights into market and user behavior.

[0066] Accuracy: Standardized and unified data processing processes improve data accuracy and reduce analysis errors caused by data inconsistency.

[0067] Improved efficiency: Automated data collection, mapping, and fusion processes reduce the workload of manual data processing and improve the efficiency of data analysis.

[0068] Insight: The comprehensive use of multi-platform data provides more insightful analysis results than a single platform, revealing user behavior and market trends across platforms.

[0069] Customizability: Allows you to define and calculate metrics based on different business needs, providing a flexible analysis framework.

[0070] Support Decisions: Help users gain an edge over their competition by providing data-driven insights to support decision making. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] 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.

[0072] Figure 1 A schematic flow chart of a data processing method for a social media hybrid platform provided by an embodiment of the present invention;

[0073] Figure 2 A schematic flow chart of another data processing method for a social media hybrid platform provided by an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of the structure of a data processing device for a social media hybrid platform provided by an embodiment of the present invention;

[0075] Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] The disclosed embodiment provides a data processing method for a social media mixing platform. The data processing method for a social media mixing platform 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 which can be integrated in a server, a terminal device, etc.

[0082] See also Figure 1 and Figure 2 The present disclosure provides a data processing method for a social media hybrid platform, including:

[0083] S101, collecting raw data of n social media platforms through APIs of the social media platforms, and cleaning the collected raw data to obtain cleaned data of the social media hybrid platform.

[0084] Data collection is the basis of data analysis. It is necessary to ensure that the collected data is comprehensive, accurate, and in line with the purpose of analysis. For this purpose, social media platforms such as Facebook, Twitter, Instagram, etc. need to be selected to collect data. The selection criteria include the popularity of the platform, the activity of the target user group, and the feasibility of data acquisition.

[0085] The data scope needs to be set: clarify the time range, geographical range, user group, etc. of data collection to ensure that the collected data meets the analysis objectives. You can use the API provided by various social media platforms to collect data. You need to handle issues such as frequency limits on API calls and permission applications to ensure smooth data collection.

[0086] In the process of data collection, it is necessary to determine the key data fields that must be collected, such as user ID, post content, post time, number of interactions (likes, comments, shares), etc., to ensure that these fields can support subsequent data analysis needs. Accordingly, the collected raw data should be backed up to prevent data loss or damage and ensure data security.

[0087] Data preprocessing is performed on the collected data. Data preprocessing is a key step to ensure data quality and improve the accuracy of data analysis.

[0088] Duplicate data entries can be removed to ensure data uniqueness. Irrelevant data, such as advertisements and spam, can be removed to improve data relevance and quality. Error data can be processed, such as incorrect date format and data type mismatch. Missing values ​​in the data can be identified and handled with appropriate strategies, such as deletion, filling, or using model prediction. Different missing value processing methods can be selected according to the characteristics of different fields and the needs of data analysis.

[0089] Structuring unstructured data, such as converting text content into analyzable numerical indicators. Converting string-type dates into date types to facilitate subsequent time series analysis.

[0090] Standardize data, such as converting all time data to a unified time zone. Standardize text data, such as unifying brand names mentioned by users to eliminate differences caused by aliases or abbreviations.

[0091] If the data comes from multiple sources or platforms, data integration is required to merge them into a unified data set. During the integration process, the consistency and integrity of the data should be maintained and data conflicts should be resolved.

[0092] Through the above detailed data collection and preprocessing steps, we can ensure that the data used in subsequent analysis are of high quality, laying a solid foundation for obtaining accurate and reliable analysis results.

[0093] S102, establishing a unified field naming and data format standard for data fields from different platforms in the cleaned data, converting all data in the cleaned data into standardized data types through data type conversion to form a standardized data set D={D1,D2,…Dn} containing n social media data, and extracting a standard field set G={G1,G2,…Gk} consisting of k standard data fields contained in the standardized data set D.

[0094] Field standardization is an important step in data preprocessing, which aims to ensure consistency when merging, comparing or analyzing data from different sources or platforms. This process involves the following main steps:

[0095] Unified field naming:

[0096] Establish naming standards: Develop a unified set of field naming standards that specify the format, naming method, and terminology used for field names, and ensure that all fields in all data sets follow this standard.

[0097] Rename fields: Rename the fields in the collected data according to the naming convention. For example, rename "fb_likes", "insta_likes", and "tw_likes" to "likes".

[0098] Use descriptive names: Field names should be descriptive and clearly express the content and meaning of the field, such as changing the abbreviation "ct" to the more descriptive "comment_count".

[0099] Unified field content:

[0100] Standardize measurement units: Ensure that the same field in different datasets uses the same measurement unit, for example, standardize the length units of all related fields to meters or feet.

[0101] Unify data formats: For fields such as date and time, unify the data formats, such as unifying all date fields into the "YYYY-MM-DD" format.

[0102] Standardize enumeration values: For fields with enumeration values ​​(such as gender, status, etc.), unify the expression of enumeration values. For example, the gender field only uses "Male" and "Female".

[0103] Data type unification:

[0104] Determine data type: Clarify the data type of each field, such as number, string, date, etc., and ensure that the data type of the same field is consistent in different data sets.

[0105] Type conversion: Convert inconsistent data types, for example, convert a numeric string to a numeric type to facilitate subsequent mathematical operations.

[0106] Field Mapping:

[0107] Create a mapping table: When merging different data sets, create a field mapping table to list the correspondence between fields with the same meaning in different data sets.

[0108] Implement mapping: According to the mapping table, map the fields in different data sets to unified standard fields to facilitate data merging and analysis.

[0109] Documentation and maintenance:

[0110] Documentation: Document the rules, processes, and mapping relationships for field standardization to ensure the transparency and traceability of the standardization process.

[0111] Continuous maintenance: As data sources change and data sets expand, field standardization rules and mapping relationships are continuously maintained and updated.

[0112] Through the above detailed field standardization steps, we can ensure that data from different sources are consistent at the field level, providing a solid foundation for data merging, comparison and in-depth analysis.

[0113] S103, using a feature extraction function, perform feature extraction on the data in the standardized data set D={D1,D2,…Dn} to obtain a feature data set F={F1,F2,…Fm} containing m feature fields, and use the feature data set F={F1,F2,…Fm} and the standard field set G={G1,G2,…Gk} to perform data mapping on the data in the standardized data set D={D1,D2,…Dn}, merge the mapped data into a unified data framework, and form a unified data set W={W1,W2,…Wq} containing q data fields.

[0114] Data mapping and fusion is the process of integrating data from different sources into a unified data set to ensure data consistency and integrity. This process is particularly critical for cross-platform data analysis.

[0115] Specifically, the following steps may be included:

[0116] Data Mapping

[0117] Data mapping refers to identifying fields with the same or similar meanings in different data sources and establishing the correspondence between them.

[0118] Establish mapping relationships: Establish mapping relationships between fields in different data sources based on business logic and data meaning. For example, "retweets" in Twitter and "shares" in Facebook may both be mapped to "reposts".

[0119] Use data mapping tools: Data mapping tools or software can be used to assist in establishing and managing mapping relationships, especially when dealing with a large number of data sources or a complex structure.

[0120] Algorithm application: In some cases, natural language processing (NLP) algorithms can be applied to identify and map field names with similar meanings. For example, possible mapping relationships can be automatically suggested by calculating word meaning similarity.

[0121] Data Fusion

[0122] Data fusion refers to merging the mapped data sets together to form a unified and tidy data set.

[0123] Determine fusion rules: Determine data fusion rules based on business needs and data characteristics, such as how to handle conflicts in field values, how to merge duplicate records, etc.

[0124] Data deduplication: During the fusion process, duplicate data entries need to be identified and processed. Duplicates can be identified using a specific identifier or a set of key fields and a decision can be made as to whether to retain, delete, or merge them.

[0125] Data quality assurance: During the data fusion process, continuously monitor and evaluate data quality to ensure the accuracy and reliability of the fused data set.

[0126] Use ETL tools: Data fusion can be performed using ETL (extract, transform, load) tools, which provide powerful data processing capabilities and can handle large-scale data fusion tasks.

[0127] Algorithm application: When dealing with complex data fusion requirements, algorithms may need to be applied to assist. For example, machine learning algorithms can be used for entity resolution to identify data records representing the same entity in different data sources for easy merging.

[0128] Data Validation

[0129] After data fusion, data verification is a key step to ensure data quality.

[0130] Verify data consistency: Check whether the data in the fused dataset maintains logical consistency, such as whether the foreign key relationship is complete and whether the data range is reasonable.

[0131] Verify data integrity: Ensure that important data was not lost during the fusion process and that the new dataset can support the intended analysis task.

[0132] As another specific implementation, the present invention also provides a specific algorithm, which mainly includes:

[0133] Perform word segmentation on the standardized data set to obtain the word segmentation phrase set U={U1,U2,…Ux};

[0134] Calculate the activity value of the participle phrase Ui

[0135]

[0136] Indicates the frequency of occurrence of the participle phrase Ui in the data Dj, Represents the sum of the frequencies of all participle phrases in the data Dj;

[0137] Select activity value Greater than the preset activity value words, and obtain a feature data set F={F1,F2,…Fm} containing m feature fields.

[0138] Calculate the gradient value Trj between any field Gr and Gj in the standard field set G={G1,G2,…Gk}:

[0139]

[0140] LBL() is a character vectorization function, r≤k, j≤k, r≠j;

[0141] The fields whose gradient values ​​Trj are less than the preset gradient value Trj0 are merged to obtain a standard merged field set G'={G'1,G'2,…G'y}, y≤k.

[0142] Calculate the gradient value Tij between any field Fi in the feature data set F={F1,F2,…Fm} and any field G'j in the standard merged field set G'={G'1,G'2,…G'y}:

[0143]

[0144] LBL() is a character vectorization function, i≤m, j≤y;

[0145] The field Fi whose gradient value Tij is less than the preset gradient value μ*Trj0 is deleted from the feature data set F={F1,F2,…Fm} to obtain the feature merged data set F'={F'1,F'2,…F'b}, where z≤m and μ is the preset mediation parameter;

[0146] The feature merged data set F'={F'1,F'2,…F'b} is merged with the standard merged field set G'={G'1,G'2,…G'y} to form a unified data set W={W1,W2,…Wq} containing q data fields. The unified data set W={W1,W2,…Wq} can be used to effectively integrate data from different sources.

[0147] Through the above detailed data mapping and fusion steps, data from different sources can be effectively integrated to provide a unified, high-quality data foundation for subsequent data analysis.

[0148] S104, setting a data analysis function, analyzing and calculating the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance, and extracting a display data set Z={Z1, Z2, ...Zp} containing p display features based on the unified data set W, wherein the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result.

[0149] Indicator calculation and analysis is the process of extracting key information from the fused data set to support decision making. This process requires not only quantitative processing of the data, but also the ability to provide in-depth understanding and insights into the data. The following are the detailed steps of this process:

[0150] Indicator definition and selection:

[0151] Understanding business needs: Clarifying analysis goals and business needs is the first step in defining indicators. Different business goals may require different indicators to measure.

[0152] Indicator library construction: According to business needs, build an indicator library containing various indicators that may be needed. These indicators should cover different aspects of business performance, such as growth indicators, user behavior indicators, content interaction indicators, etc.

[0153] Establish key performance indicators (KPIs): Select key performance indicators from the indicator library that best reflect business success. These KPIs should be closely related to the strategic goals of the organization.

[0154] Data preparation:

[0155] Data extraction: Extract the data required to calculate the indicator from the fused data set. This may involve operations such as querying the database and executing SQL statements.

[0156] Data preprocessing: Preprocess the extracted data, including data cleaning, formatting, missing value processing, etc., to ensure the accuracy and completeness of the data.

[0157] Indicator calculation:

[0158] Single indicator calculation: Calculate the value of a single indicator. This may be a simple calculation process such as sum, average or count.

[0159] Combined indicator calculation: For more complex indicators, it may be necessary to combine the calculation results of multiple basic indicators. For example, user engagement may need to be calculated by combining the user's click-through rate, number of comments, and number of shares.

[0160] Trend analysis: Analyze changes in indicators over time to identify trends and patterns in the data.

[0161] Results analysis and interpretation:

[0162] Result interpretation: Explain the calculated indicator results and understand the specific meaning of the indicator changes to the business.

[0163] In-depth analysis: Conduct in-depth analysis of unusual results or important changes to explore the reasons and drivers behind them.

[0164] Correlation analysis: Analyze the correlation between different indicators and understand the interaction between different business elements.

[0165] Visualization and Reporting:

[0166] Data Visualization: Visualize indicator results using charts and graphs to make data easier to understand and communicate.

[0167] Report Preparation: Prepare analytical reports summarizing key findings and providing recommendations or insights to support decision making.

[0168] Presentation and Sharing: Share analysis results and insights with stakeholders through presentations or meetings to facilitate information transfer and collaborative decision-making.

[0169] Through the above steps, indicator calculation and analysis can provide organizations with data-driven insights to help optimize strategies and improve decision-making efficiency. This process requires continuous iteration and optimization to adapt to the ever-changing business environment and data landscape.

[0170] S105, after displaying the data analysis results in a visual display manner, generating decision data based on the data analysis results.

[0171] You can use visualization tools such as charts, graphs, and dashboards to intuitively display the analysis results. Make sure the display content is clear, easy to understand, and can intuitively reflect the data analysis results across platforms.

[0172] Apply the analysis results to actual business scenarios, such as market trend analysis, user behavior research, etc. Provide data support to help decision makers make more reasonable and effective decisions.

[0173] The solution of this application has the following beneficial effects:

[0174] Comprehensiveness: By integrating data from multiple social media platforms, it provides a comprehensive view, helping organizations gain more complete insights into market and user behavior.

[0175] Accuracy: Standardized and unified data processing processes improve data accuracy and reduce analysis errors caused by data inconsistency.

[0176] Improved efficiency: Automated data collection, mapping, and fusion processes reduce the workload of manual data processing and improve the efficiency of data analysis.

[0177] Insight: The comprehensive use of multi-platform data provides more insightful analysis results than a single platform, which can reveal user behavior and market trends across platforms.

[0178] Customizability: Allows you to define and calculate metrics based on different business needs, providing a flexible analysis framework.

[0179] Support decision making: Help enterprises gain an edge over the competition by providing data-driven insights to support decision making.

[0180] The solution of this application has the following application scenarios:

[0181] Market Trend Analysis: Identify and track market trends on social media to understand changes in consumer interests and demands.

[0182] Brand Monitoring: Track and analyze brand performance on different social media platforms, including brand mentions, user sentiment, and interactions.

[0183] Competitive analysis: Compare the performance of different competitors on social media and analyze their strategies and user reactions.

[0184] Content effectiveness analysis: Evaluate the performance of different types of content on social media and guide the formulation of content strategies.

[0185] User Behavior Research: Gain insights into user behavior patterns on social media, including how they interact, share, and discuss.

[0186] Through the above advantages and application scenarios, this solution provides an effective data analysis tool to help users use social media data more effectively in the data-driven era.

[0187] According to a specific implementation of the embodiment of the present disclosure, the raw data of n social media platforms are collected through the APIs of the social media platforms, and the collected raw data are cleaned to obtain the cleaned data of the social media hybrid platform, including:

[0188] After selecting the social media platform to collect data, clarify the time range, geographical scope and user groups of data collection to ensure that the collected data meets the analysis objectives;

[0189] After dealing with the frequency limit and permission application of API calls, use the APIs provided by various social media platforms to collect data;

[0190] After determining the key data fields that must be collected by each social media platform, obtain the original data of each social media platform and back up the collected original data to prevent data loss or damage;

[0191] For the original data, remove duplicate data entries, remove irrelevant data and process erroneous data, identify missing values ​​in the data, and perform deletion, filling or prediction processing on the missing values;

[0192] Structural processing is performed on unstructured data, text content is converted into numerical indicators, string type dates are converted into date types, and all time data are converted into a unified time zone.

[0193] According to a specific implementation of the embodiment of the present disclosure, a unified field naming and data format standard is established for data fields from different platforms in the cleaned data, and all data in the cleaned data are converted into standardized data types through data type conversion to form a standardized data set D={D1, D2, ...Dn} containing n social media data, including:

[0194] Develop a unified field naming specification to specify the format, naming method, and terminology of field names, ensure that fields in all data sets follow the field naming specification, and rename the fields in the collected data according to the field naming specification;

[0195] Ensure that the same field uses the same measurement unit and date unit in different datasets. For fields with enumeration values, unify the expression of enumeration values, clarify the data type of each field, and ensure that the data type of the same field in different datasets is consistent.

[0196] When merging different data sets, create a field mapping table to list the corresponding relationships between fields with the same meaning in different data sets. According to the mapping table, map the fields in different data sets to a unified standard field.

[0197] Document the rules, processes, and mapping relationships for field standardization, and maintain and update the rules and mapping relationships for field standardization when data sources change and data sets expand.

[0198] According to a specific implementation of the embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, including:

[0199] Perform word segmentation on the standardized data set to obtain the word segmentation phrase set U={U1,U2,…Ux};

[0200] Calculate the activity value of the participle phrase Ui

[0201]

[0202] Indicates the frequency of occurrence of the participle phrase Ui in the data Dj, Represents the sum of the frequencies of all participle phrases in the data Dj;

[0203] Select activity value Greater than the preset activity value words, and obtain a feature data set F={F1,F2,…Fm} containing m feature fields.

[0204] According to a specific implementation of an embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, and further includes:

[0205] Calculate the gradient value Trj between any field Gr and Gj in the standard field set G={G1,G2,…Gk}:

[0206]

[0207] LBL() is a character vectorization function, r≤k, j≤k, r≠j;

[0208] The fields whose gradient values ​​Trj are less than the preset gradient value Trj0 are merged to obtain a standard merged field set G'={G'1,G'2,…G'y}, y≤k.

[0209] According to a specific implementation of an embodiment of the present disclosure, the feature extraction function is used to extract features from the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, and the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} are used to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and the mapped data are merged into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields, and further includes:

[0210] Calculate the gradient value Tij between any field Fi in the feature data set F={F1,F2,…Fm} and any field G'j in the standard merged field set G'={G'1,G'2,…G'y}:

[0211]

[0212] LBL() is a character vectorization function, i≤m, j≤y;

[0213] The field Fi whose gradient value Tij is less than the preset gradient value μ*Trj0 is deleted from the feature data set F={F1,F2,…Fm} to obtain the feature merged data set F'={F'1,F'2,…F'b}, where z≤m and μ is the preset mediation parameter;

[0214] The feature merged data set F'={F'1,F'2,…F'b} is merged with the standard merged field set G'={G'1,G'2,…G'y} to form a unified data set W={W1,W2,…Wq} containing q data fields.

[0215] According to a specific implementation of the embodiment of the present disclosure, the data analysis function is set to analyze and calculate the data indicators in the unified data set to evaluate and analyze the cross-platform social media performance, and extract a display data set Z={Z1, Z2, ...Zp} containing p display features based on the unified data set W, and the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result, including:

[0216] Build an indicator library containing analysis dimensions, select indicators related to the analysis dimensions from the indicator library, and extract the data required to calculate the indicators from the integrated unified data set;

[0217] Calculate the value of a single indicator, or combine the calculation results of multiple basic indicators to analyze the changes of indicators over time and identify trends and patterns in the data;

[0218] Interpret the calculated indicator results, conduct in-depth analysis of abnormal results or important changes, and analyze the correlation between different indicators.

[0219] According to a specific implementation of the embodiment of the present disclosure, after displaying the data analysis result in a visual display manner, generating decision data based on the data analysis result includes:

[0220] Extract key information related to the decision-making goal from the visualization results, wherein the key information includes key data points, trend lines, and outliers;

[0221] Generate decision-making data based on the extracted key information;

[0222] Validate and test the generated decision data using historical data or simulated scenarios.

[0223] Corresponding to the above method embodiment, see Figure 3 The embodiment of the present invention further discloses a data processing device 30 for a social media hybrid platform, comprising:

[0224] The collection module 301 collects raw data of n social media platforms through the APIs of the social media platforms, and cleans the collected raw data to obtain cleaned data of the social media hybrid platform;

[0225] The conversion module 302 establishes a unified field naming and data format standard for data fields from different platforms in the cleaned data, converts all data in the cleaned data into standardized data types through data type conversion, forms a standardized data set D={D1, D2, ...Dn} containing n social media data, and extracts a standard field set G={G1, G2, ...Gk} consisting of k standard data fields contained in the standardized data set D;

[0226] The mapping module 303 uses a feature extraction function to perform feature extraction on the data in the standardized data set D={D1, D2, ...Dn} to obtain a feature data set F={F1, F2, ...Fm} containing m feature fields, uses the feature data set F={F1, F2, ...Fm} and the standard field set G={G1, G2, ...Gk} to perform data mapping on the data in the standardized data set D={D1, D2, ...Dn}, and merges the mapped data into a unified data framework to form a unified data set W={W1, W2, ...Wq} containing q data fields;

[0227] The analysis module 304 analyzes and calculates the data indicators in the unified data set by setting a data analysis function to evaluate and analyze the cross-platform social media performance, and extracts a display data set Z={Z1, Z2, ...Zp} containing p display features based on the unified data set W, wherein the display data set Z={Z1, Z2, ...Zp} is used to provide a cross-platform comprehensive analysis perspective to form a data analysis result;

[0228] The display module 305 displays the data analysis results in a visual display manner and then generates decision data based on the data analysis results.

[0229] See also Figure 4 The embodiment of the present invention further provides an electronic device 60, the electronic device comprising:

[0230] at least one processor; and,

[0231] a memory communicatively connected to the at least one processor; wherein,

[0232] 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 to enable the at least one processor to execute the data processing method of the social media mixing platform in the aforementioned method embodiment.

[0233] 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.

[0234] 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. The computer program includes program instructions, which, when executed by a computer, enable the computer to execute the data processing method of the social media mixing platform in the aforementioned method embodiment.

[0235] 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.

[0236] 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.

[0237] 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, an accelerometer, 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.

[0238] 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 contains 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.

[0239] 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 data processing method for a social media hybrid platform, characterized in that: include: The raw data of n platforms are collected and cleaned through the API of each social media platform to obtain cleaned data; For the data fields from different platforms in the cleaned data, a unified field naming and data format standard is established. Through data type conversion, all data is converted into standardized data types to form a standardized data set D={D1,D2,…Dn}, and the standard field set G={G1,G2,…Gk} consisting of k fields contained in the set D is extracted; Using the feature extraction function, the data in set D is feature extracted to obtain a feature data set F={F1,F2,…Fm} containing m feature fields. Using the feature data set F and the standard field set G, the data in set D is mapped to form a unified data set W={W1,W2,…Wq} containing q data fields, including: Perform word segmentation on set D to obtain a set of word segmentation phrases U={U1,U2,…Ux}; Calculate the activity value Hy of the participle phrase Ui i,j : , Indicates the frequency of occurrence of the participle phrase Ui in the data Dj, Represents the sum of the frequencies of all participle phrases in the data Dj; Select activity value Greater than the preset activity value words, and obtain a feature data set F containing m feature fields; Calculate the gradient value Trj between any fields Gr and Gj in the standard field set G: , LBL() is a character vectorization function, r≤k, j≤k, r≠j; Merge the fields whose gradient values ​​Trj are less than the preset gradient value Trj0 to obtain a standard merged field set G'={G'1,G'2,…G'y}, y≤k; Calculate the gradient value Tij between any field Fi in the feature data set F and any field G'j in the standard merged field set G': ,i≤m,j≤y; The fields Fi whose gradient values ​​Tij are less than the preset gradient value μ*Trj0 are deleted from the feature data set F to obtain the feature merged data set F'={F'1,F'2,…F'z}, where z≤m and μ is the preset adjustment parameter; Merge the feature merged data set F' and the standard merged field set G' to form a unified data set W containing q data fields; A data analysis function is set to analyze and calculate the data indicators in the data set w to evaluate and analyze the cross-platform social media performance, and a display data set Z={Z1,Z2,…Zp} containing p display features is extracted based on the data set W to provide a comprehensive cross-platform analysis perspective. After the data analysis results are formed and displayed in a visual manner, decision data is generated based on the data analysis results.

2. The method according to claim 1, characterized in that The raw data of n platforms are collected and cleaned through the API of each social media platform to obtain cleaned data, including: After selecting the social media platform to collect data, clarify the time range, geographical scope and user groups of data collection to ensure that the collected data meets the analysis objectives; After dealing with the frequency limit and permission application of API calls, use the APIs provided by various social media platforms to collect data; After determining the key data fields that must be collected by each social media platform, obtain the original data of each social media platform and back up the collected original data to prevent data loss or damage; For the original data, remove duplicate data entries, remove irrelevant data and process erroneous data, identify missing values ​​in the data, and perform deletion, filling or prediction processing on the missing values; Structural processing is performed on unstructured data, text content is converted into numerical indicators, string type dates are converted into date types, and all time data are converted into a unified time zone.

3. The method according to claim 2, characterized in that The method establishes a unified field naming and data format standard for the data fields from different platforms in the cleaned data, converts all data into standardized data types through data type conversion, and forms a standardized data set D={D1, D2, ...Dn}, including: Develop a unified field naming specification to specify the format, naming method, and terminology of field names, ensure that fields in all data sets follow the field naming specification, and rename the fields in the collected data according to the field naming specification; Ensure that the same field uses the same measurement unit and date unit in different datasets. For fields with enumeration values, unify the expression of enumeration values, clarify the data type of each field, and ensure that the data type of the same field in different datasets is consistent. When merging different data sets, create a field mapping table to list the corresponding relationships between fields with the same meaning in different data sets. According to the mapping table, map the fields in different data sets to a unified standard field. Document the rules, processes, and mapping relationships for field standardization, and maintain and update the rules and mapping relationships for field standardization when data sources change and data sets expand.

4. The method according to claim 1, characterized in that The data analysis function is set to analyze and calculate the data indicators in the data set w to evaluate and analyze the cross-platform social media performance, and extract a display data set Z={Z1, Z2, ...Zp} containing p display features based on the data set W to provide a cross-platform comprehensive analysis perspective and form a data analysis result, including: Build an indicator library containing analysis dimensions, select indicators related to the analysis dimensions from the indicator library, and extract the data required to calculate the indicators from the integrated unified data set; Calculate the value of a single indicator, or combine the calculation results of multiple basic indicators to analyze the changes of indicators over time and identify trends and patterns in the data; Interpret the calculated indicator results, conduct in-depth analysis of abnormal results or important changes, and analyze the correlation between different indicators.

5. The method according to claim 4, characterized in that After the visual display, decision data is generated based on the data analysis results, including: Extract key information related to the decision-making goal from the visualization results, wherein the key information includes key data points, trend lines, and outliers; Generate decision-making data based on the extracted key information; Validate and test the generated decision data using historical data or simulated scenarios.

6. A data processing device for a social media hybrid platform, characterized in that: include: The acquisition module collects the raw data of n platforms through the APIs of various social media platforms and cleans them to obtain cleaned data; The conversion module establishes a unified field naming and data format standard for the data fields from different platforms in the cleaned data. Through data type conversion, all data are converted into standardized data types to form a standardized data set D={D1,D2,…Dn}, and a standard field set G={G1,G2,…Gk} consisting of k fields contained in the set D is extracted; The mapping module uses the feature extraction function to extract features from the data in the set D to obtain a feature data set F={F1, F2, …Fm} containing m feature fields. The feature data set F and the standard field set G are used to perform data mapping on the data in the set D to form a unified data set W={W1, W2, …Wq} containing q data fields, including: Perform word segmentation on set D to obtain a set of word segmentation phrases U={U1,U2,…Ux}; Calculate the activity value Hy of the participle phrase Ui i,j : , Indicates the frequency of occurrence of the participle phrase Ui in the data Dj, Represents the sum of the frequencies of all participle phrases in the data Dj; Select activity value Greater than the preset activity value words, and obtain a feature data set F containing m feature fields; Calculate the gradient value Trj between any fields Gr and Gj in the standard field set G: , LBL() is a character vectorization function, r≤k, j≤k, r≠j; Merge the fields whose gradient values ​​Trj are less than the preset gradient value Trj0 to obtain a standard merged field set G'={G'1,G'2,…G'y}, y≤k; Calculate the gradient value Tij between any field Fi in the feature data set F and any field G'j in the standard merged field set G': ,i≤m,j≤y; The fields Fi whose gradient values ​​Tij are less than the preset gradient value μ*Trj0 are deleted from the feature data set F to obtain the feature merged data set F'={F'1,F'2,…F'z}, where z≤m and μ is the preset adjustment parameter; Merge the feature merged data set F' and the standard merged field set G' to form a unified data set W containing q data fields; The analysis and display module sets a data analysis function, analyzes and calculates the data indicators in the data set w, so as to evaluate and analyze the cross-platform social media performance, and extracts a display data set Z={Z1,Z2,…Zp} containing p display features based on the data set W, so as to provide a comprehensive analysis perspective across platforms, form data analysis results and display them in a visual way, and then generate decision data based on the data analysis results.

7. 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 to enable the at least one processor to execute the data processing method for the social media mixing platform according to any one of claims 1 to 5.

Images