A passive sensing based multi-domain propagation reach effectiveness evaluation method and device
By using a passively perceived multi-domain communication reach effectiveness assessment method, this paper solves the problems of distorted data collection methods, single assessment dimensions, and insufficient dynamic adaptability in existing technologies for assessing the effectiveness of international communication reach. It enables direct assessment of the ability of information to reach naturally and the construction of cross-platform assessment benchmarks, thereby improving the strategic adaptability and practicality of the assessment.
Patent Information
- Application Number
- CN202610258076.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-04
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies for assessing the effectiveness of international communication suffer from problems such as distorted data collection methods, limited assessment dimensions, and insufficient dynamic adaptability, making it difficult to accurately reflect the ability of information to naturally reach users through platform recommendation mechanisms.
We employ a passive perception-based multi-domain communication reach effectiveness evaluation method. By processing cross-platform feature alignment, we obtain social media data from different platforms, languages, and data modalities worldwide, generate cross-platform reach effectiveness indicators, and integrate the preset weights of each platform for evaluation.
It enables direct and qualitative assessment of the ability to naturally access information, constructs a unified and computable cross-platform assessment benchmark, improves the strategic adaptability and practicality of the assessment, and forms an end-to-end assessment framework.
Smart Images

Figure CN122175570A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of Internet technology, specifically providing a method and apparatus for evaluating the effectiveness of multi-domain propagation reach based on passive perception. Background Technology
[0002] Social media platforms have become crucial arenas for the global dissemination of information and the formation of communication trends. In the dissemination of international hot topics, whether information can overcome platform barriers and transcend language and cultural differences, and naturally reach and be presented to the target audience through the platform's own recommendation algorithms, directly relates to the breadth, timeliness, and ultimate impact of the communication. Therefore, accurate and dynamic evaluation of "reach effectiveness" in international communication is an important prerequisite for communication analysis and strategy optimization.
[0003] Currently, research and practice on evaluating the effectiveness of social media dissemination have made some progress. Some methods focus on collecting publicly available data through technologies such as keyword retrieval and web crawling, and measuring the popularity of dissemination based on explicit interaction indicators such as the number of reposts, comments, and likes. However, this type of proactive data collection model has inherent defects: First, it relies on preset keywords or rules, making it difficult to capture relevant content that is not within the expected vocabulary range but is recommended through the platform's semantic understanding and user interest matching mechanisms, resulting in an incomplete assessment of the dissemination scope; second, it cannot effectively distinguish whether content appears due to users' active search and attention or benefits from the natural distribution of the platform's recommendation algorithm, thus making it difficult to truly measure the "natural reach" of information within the algorithmic ecosystem, that is, to assess whether it has successfully entered the daily information flow of ordinary users.
[0004] Other methods attempt to construct multi-dimensional evaluation systems. For example, Chinese invention patent CN117764627B proposes a method for determining the dissemination effect of an activity, which extracts multiple indicators, including the activity's reach. However, such methods mostly serve commercial marketing scenarios, and their "reach" usually refers to the number of people covered or the number of exposures in a statistical sense, without delving into the core process of "natural reach through platform recommendation mechanisms," and lacking specific consideration for the consistency and comparability of reach across platforms and languages. Chinese invention patent application CN120492864A provides a method for analyzing the dissemination effect of internet information based on multi-dimensional data, but it focuses on the presentation of dissemination paths and nodes, and has shortcomings in the quantitative modeling and dynamic evaluation of reach effects.
[0005] Furthermore, regarding cross-platform evaluation, while some technologies, such as the patent with authorization announcement number CN111949848B, have achieved cross-platform dissemination trend analysis for specific events, their indicator systems are usually geared towards security monitoring or marketing, failing to focus on deconstructing reach effectiveness from the perspective of platform recommendation algorithms. On the other hand, while the patent with authorization announcement number CN113781250B applies advanced deep learning models, its model training and evaluation are often based on the data ecosystem of a single platform, making it difficult to handle the challenges posed by differences in recommendation logic across multiple platforms and data heterogeneity. This limits the universality and cross-platform comparability of its reach evaluation model.
[0006] In summary, existing technologies face three prominent challenges in assessing the effectiveness of international communication outreach: (1) Distorted data collection methods: relying on active retrieval makes it difficult to capture naturally disseminated content under the platform's recommendation mechanism, resulting in incomplete and unreliable basic data for outreach assessment; (2) Single assessment dimension: existing "outreach" indicators are mostly limited to quantitative statistics, failing to depict the qualitative characteristic of "whether it naturally enters the user's visible range through recommendation algorithms," and lacking the ability to make cross-platform horizontal comparisons; (3) Insufficient dynamic adaptability: assessment models are mostly static, unable to adapt to the dynamic characteristics of the recommendation popularity of different platforms changing with time windows during the dissemination of hot events, making it difficult to provide real-time and continuous insights into the outreach situation.
[0007] Therefore, there is an urgent need in this field for an innovative evaluation method that can simulate real user reception scenarios based on passive perception, and be used to accurately and dynamically evaluate the ability of target event information to naturally reach users through the recommendation mechanisms of various platforms in a multi-platform environment. This would fill the gap in existing technologies and provide a more scientific and accurate core dimension analysis tool for evaluating the effectiveness of international communication.
[0008] In view of this, this invention patent is hereby proposed. Summary of the Invention
[0009] To address the above technical problems, this invention proposes a method and apparatus for evaluating the effectiveness of multi-domain propagation reach based on passive sensing. Specifically, the following technical solution is adopted: In a first aspect, the present invention provides a method for evaluating the effectiveness of multi-domain propagation reach based on passive sensing, comprising: Data acquisition and preprocessing: Obtain raw social media data from different platform domains and / or different language domains and / or different data modal domains worldwide; perform cross-platform feature alignment processing on the raw social media data to obtain a computable set of structured social media data. Based on the structured social media dataset, for each social media platform, it is determined whether content related to the target event is passively perceived on each platform. Based on the determination results, the preset weights of each social media platform are integrated to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism.
[0010] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the data acquisition and preprocessing steps for obtaining raw social media data from different platform domains and / or different language domains and / or different data modal domains globally include: By creating and operating multiple social media accounts that match the geographic location and language environment of the target event, data is collected by passively receiving recommended content from various social media platforms, thereby obtaining raw social media data related to the target event from different platform domains and / or different language domains and / or different data modal domains.
[0011] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the data acquisition and preprocessing step of the present invention performs cross-platform feature alignment processing on the original social media data to obtain a computable structured social media data set, including: Structured alignment of content from raw social media data across different platform domains; Data cleaning and standardization are performed on the original social media dataset based on structured alignment; By aligning all cleaned and standardized data sets based on a unified timestamp and employing a sliding time window mechanism, a computable structured social media data set is obtained.
[0012] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the structured alignment of content for original social media data from different platform domains includes: An abstract set of common elements is used to structurally align the content of raw social media data from different platform domains, as defined below: ;
[0013] in, This indicates information at the content level. Indicators representing behavioral aspects, This represents the structure at the interaction layer.
[0014] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the data set after data cleaning based on the original social media data set with structured alignment is denoted as: ; Where n is the total amount of original data and m is the amount of data after cleaning.
[0015] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the method aligns all cleaned and standardized data sets based on a unified timestamp and employs a sliding time window mechanism to obtain a computable structured social media data set, including: Let the time window scale be k, then within the time period... The internal data set is defined as a time window. : ; in, Represents data items Timestamp.
[0016] As an optional embodiment of the present invention, in a multi-domain propagation reach effectiveness evaluation method based on passive perception, the generation of a cross-platform reach effectiveness index that comprehensively evaluates the ability of the target event information to naturally reach users through the recommendation mechanism of social media platforms includes: For each social media platform and each time window Calculate the platform-level binary reach index If in the time window If at least one piece of content related to the target event is passively collected, then ,otherwise ; The platform-level binary reach index of each social media platform is weighted and its corresponding platform weight is then combined to generate the time window. Reach effectiveness index : ; in, , , ..., Each social media platform has a preset reach weight to meet [the needs of]... .
[0017] As an optional embodiment of the present invention, in a multi-domain propagation reach effectiveness evaluation method based on passive perception, multiple time window scales k of different sizes are executed in parallel to generate dynamic reach effectiveness index sequences corresponding to the time window scales respectively: ;
[0018] The dynamic reach effectiveness index sequences of all time window scales k are merged into a multi-scale reach trajectory:
[0019] The multi-scale reach trajectory is used for comprehensive analysis of reach effectiveness.
[0020] In a second aspect, the present invention provides a multi-domain propagation reach effectiveness evaluation device based on passive sensing, comprising: The data acquisition and preprocessing module is used to acquire raw social media data from different platform domains and / or different language domains and / or different data modal domains around the world, and to perform cross-platform feature alignment processing on the raw social media data to obtain a computable structured social media data set; The reach effectiveness index calculation module is configured to perform the following: based on the structured social media data set, for each social media platform, determine whether the content related to the target event is passively perceived on each social media platform, and based on the determination result, integrate the preset weights of each social media platform to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism.
[0021] In a third aspect, the present invention provides an electronic device including a processor and a memory, the memory being used to store a computer-executable program, wherein when the computer program is executed by the processor, the processor executes the aforementioned method for evaluating the effectiveness of multi-domain propagation reach based on passive perception.
[0022] In a fourth aspect, the present invention provides a computer-readable recording medium storing a computer-executable program, which, when executed, implements the aforementioned method for evaluating the effectiveness of multi-domain propagation reach based on passive perception.
[0023] Compared with the prior art, the beneficial effects of the present invention are as follows: It enables a direct and qualitative assessment of the ability to naturally reach information.
[0024] This invention presents a multi-domain dissemination reach effectiveness assessment method based on passive perception. It directly "determines whether content related to the target event has been passively perceived." This "whether" judgment is a qualitative assessment that directly answers the fundamental question of "whether the information has successfully appeared within the observation range of the designated platform." This avoids the noise interference (such as fake traffic) and indirectness that may exist in traditional quantitative indicators (such as exposure), making the assessment of the initial link of the dissemination chain—"reach"—more pure, direct, and accurate.
[0025] A unified and computable cross-platform evaluation benchmark was constructed, solving the problem of data heterogeneity.
[0026] To address the data disparities across different platform domains, language domains, and modal domains globally, this invention employs a passively perceptual multi-domain communication reach effectiveness assessment method. A key preprocessing step—"cross-platform feature alignment processing to obtain a computable structured social media data set"—transforms the original heterogeneous data into a standardized dataset with a unified format. This step provides a common computational foundation for subsequent cross-platform "judgment" and "fusion." Based on this unified dataset, it becomes possible to assess and compare reach across different platforms, thereby overcoming the fragmentation problem caused by multi-platform data barriers and achieving unified assessment scales and comparability of results.
[0027] A comprehensive evaluation model integrating the weights of multiple platforms was established, which improved the adaptability of the evaluation strategy.
[0028] This invention, based on a passively perceived multi-domain communication reach effectiveness evaluation method, innovatively introduces a step of "integrating the preset weights of various social media platforms" beyond simply judging whether each platform "reached" the target audience. This means the evaluation is not a simple, equal sum of the results from each platform, but rather a comprehensive calculation based on factors such as geographical coverage, user influence, and strategic importance of each platform, assigning appropriate weights. The resulting "cross-platform reach effectiveness index" is no longer a simple technical count, but a comprehensive evaluation result that reflects strategic considerations, making the evaluation conclusions better serve the needs of differentiated resource allocation and strategic decision-making.
[0029] This has led to the formation of an end-to-end evaluation framework, from data processing to indicator generation, which has improved the systematicity and practicality of the methodology.
[0030] This invention presents a multi-domain propagation reach effectiveness evaluation method based on passive sensing, explicitly proposing two core steps: "data acquisition and preprocessing" and "index calculation and generation," forming a complete logical closed loop. This method not only defines the core evaluation algorithm (judgment and weighted fusion) but also emphasizes the necessary data foundation (structured dataset) for its operation. This end-to-end design allows the method to be implemented and applied as an independent system or module, ensuring feasibility throughout the entire process from raw data to final decision support indicators, significantly enhancing the practical value and implementability of the technology. Attached Figure Description
[0031] Figure 1 A flowchart of a multi-domain propagation reach effectiveness evaluation method based on passive sensing according to Embodiment 1 of the present invention; Figure 2A flowchart of a dynamic evaluation method for multi-domain propagation effectiveness based on passive sensing according to Embodiment 2 of the present invention; Figure 3 A schematic diagram of the structure of the electronic device according to an embodiment of the present invention; Figure 4 A schematic diagram of a computer-readable recording medium according to an embodiment of the present invention. Detailed Implementation
[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.
[0033] Therefore, the following detailed description of embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely illustrates some embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0034] It should be noted that, unless otherwise specified, the embodiments and features and technical solutions in the present invention can be combined with each other.
[0035] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0036] In the description of this invention, it should be noted that the terms "upper," "lower," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. These terms are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. In addition, the terms "first," "second," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance. Example 1
[0037] like Figure 1 As shown in this embodiment, a multi-domain propagation reach effectiveness evaluation method based on passive perception includes: Data acquisition and preprocessing: Obtain raw social media data from different platform domains and / or different language domains and / or different data modal domains worldwide; perform cross-platform feature alignment processing on the raw social media data to obtain a computable set of structured social media data. Based on the structured social media dataset, for each social media platform, it is determined whether content related to the target event is passively perceived on each platform. Based on the determination results, the preset weights of each social media platform are integrated to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism.
[0038] The reach effectiveness index in this embodiment effectively assesses the natural spread under algorithm recommendation by judging whether information "naturally enters the user's visible range through the platform's recommendation mechanism," thus solving the problems of traditional active crawling methods failing to reflect the platform's true traffic distribution and lagging early hotspot identification.
[0039] The multi-domain propagation reach effectiveness evaluation method based on passive sensing provided in this embodiment has the following significant beneficial effects: It enables a direct and qualitative assessment of the ability to naturally reach information.
[0040] This method directly "determines whether content related to the target event has been passively perceived." This "whether" judgment is a qualitative assessment that directly answers the fundamental question of "whether the information has successfully appeared within the observation range of the designated platform." This avoids the noise interference (such as fake traffic) and indirectness that may exist in traditional quantitative indicators (such as exposure), making the assessment of the initial link of the "reach" in the communication chain more pure, direct, and accurate.
[0041] A unified and computable cross-platform evaluation benchmark was constructed, solving the problem of data heterogeneity.
[0042] To address the data disparities across different platform domains, language domains, and modal domains globally, this method employs a crucial preprocessing step—"cross-platform feature alignment processing to obtain a computable, structured social media dataset"—transforming the original heterogeneous data into a standardized dataset with a unified format. This step provides a common computational foundation for subsequent cross-platform "judgment" and "fusion." Based on this unified dataset, it becomes possible to assess and compare reach across different platforms, thereby overcoming the fragmentation problem caused by multi-platform data barriers and achieving uniformity in evaluation scales and comparability of results.
[0043] A comprehensive evaluation model integrating the weights of multiple platforms was established, which improved the adaptability of the evaluation strategy.
[0044] This method, building upon the simple assessment of whether each platform "reached" its users, innovatively introduces a step of "integrating the preset weights of various social media platforms." This means that the evaluation is not a simple, equal sum of the results from each platform, but rather a comprehensive calculation that assigns appropriate weights based on factors such as geographical coverage, user influence, and strategic importance of each platform. The resulting "cross-platform reach effectiveness index" is no longer a simple technical count, but a comprehensive evaluation result that reflects strategic considerations, making the evaluation conclusions better suited to differentiated resource allocation and strategic decision-making needs.
[0045] This has led to the formation of an end-to-end evaluation framework, from data processing to indicator generation, which has improved the systematicity and practicality of the methodology.
[0046] This method explicitly proposes two core steps: "data acquisition and preprocessing" and "indicator calculation and generation," forming a complete logical closed loop. It not only defines the core evaluation algorithm (judgment and weighted fusion) but also emphasizes the necessary data foundation (structured datasets) for its operation. This end-to-end design allows the method to be implemented and applied as an independent system or module, ensuring feasibility throughout the entire process from raw data to final decision support indicators, significantly enhancing the practical value and implementability of the technology.
[0047] As an optional embodiment of the present invention, in a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the data acquisition and preprocessing steps for obtaining raw social media data from different platform domains and / or different language domains and / or different data modal domains globally include: By creating and operating multiple social media accounts that match the geographic location and language environment of the target event, data is collected by passively receiving recommended content from various social media platforms, thereby obtaining raw social media data related to the target event from different platform domains and / or different language domains and / or different data modal domains.
[0048] like Figure 2 As shown, in the multi-domain communication reach effectiveness evaluation method based on passive perception of the present invention, a unified computing architecture and indicator system are constructed to achieve systematic quantitative analysis of different platform domains (such as TikTok, X, YouTube and other mainstream international social media), different language domains (covering multilingual communication environments), and different data modal domains (text and user interaction data).
[0049] Furthermore, in the multi-domain dissemination reach effectiveness evaluation method based on passive perception in this embodiment, the data acquisition and preprocessing step involves cross-platform feature alignment processing of the original social media data to obtain a computable structured social media data set, including: Structured alignment of content from raw social media data across different platform domains; Data cleaning and standardization are performed on the original social media dataset based on structured alignment; By aligning all cleaned and standardized data sets based on a unified timestamp and employing a sliding time window mechanism, a computable structured social media data set is obtained.
[0050] Specifically, in this embodiment, the method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception includes the following: The structured alignment of content from original social media data across different platform domains includes: An abstract set of common elements is used to structurally align the content of raw social media data from different platform domains, as defined below: ;
[0051] in, This indicates information at the content level. Indicators representing behavioral aspects, This represents the structure at the interaction layer.
[0052] Specifically, in this embodiment of a method for evaluating the effectiveness of multi-domain dissemination reach based on passive perception, the data set after data cleaning based on the original social media data set with structured alignment is denoted as: ;
[0053] Where n is the total amount of original data, and m is the amount of data after cleaning; The process involves aligning the cleaned and standardized data sets based on a unified timestamp and employing a sliding time window mechanism to obtain a computable, structured social media data set, including: Let the time window scale be k, then within the time period... The internal data set is defined as a time window. : ; in, Represents data items Timestamp.
[0054] In summary, the multi-domain communication reach effectiveness assessment method based on passive perception in this embodiment includes, in sequence, data collection and preprocessing steps: data collection and preprocessing, reach effectiveness modeling, information ontology effectiveness modeling, communication popularity effectiveness modeling, interaction effectiveness modeling, and comprehensive fusion and evaluation judgment, forming an end-to-end processing mechanism from raw multi-domain data acquisition to comprehensive evaluation output. This invention innovatively introduces a passive perception acquisition strategy, a multi-domain feature alignment method, and a dynamic weight optimization mechanism, effectively improving the accuracy, comparability, and strategy adaptability of international communication effect assessment, providing solid technical support for international communication analysis and communication decision-making.
[0055] In this embodiment of a method for evaluating the effectiveness of multi-domain propagation reach based on passive perception, a specific example of the data acquisition and preprocessing process includes: Step 1: Data acquisition and preprocessing.
[0056] In the quantitative evaluation of the dissemination effect of an event, data collection and preprocessing are core foundational steps. This invention differs from traditional data collection methods that rely on keyword retrieval. Instead, it creates multiple new accounts based on generalized factors such as geographic location and language environment, and acquires multi-platform, multi-modal social media data by passively receiving platform-recommended content. This strategy reduces bias and omissions caused by keyword settings, thereby obtaining raw data that more closely reflects the actual flow of information.
[0057] To ensure data consistency across platforms, this invention abstracts a set of universal elements to align and unify content from different platforms at the content level (e.g., title, body text, author, publication time), the behavior level (e.g., number of likes, comments, and favorites), and the interaction level (e.g., comment network relationships). After cleaning, standardization, and time alignment, all data is transformed into a computable, structured set.
[0058] Unlike traditional single-platform or single-modal studies, this method places particular emphasis on multi-platform integration and time synchronization, enabling cross-sectional comparison and quantitative analysis of the propagation trajectory of the same event in different social media environments within a unified evaluation framework.
[0059] Sub-step 1-1: Passive acquisition of multi-platform, multi-modal data.
[0060] Unlike existing methods that rely on active keyword retrieval and web crawling, this invention creates multiple new accounts and passively collects content automatically recommended to these accounts by the platform, based on generalized factors such as the geographical location and language environment of the target event. The collection scope covers multiple social media platforms, including TikTok, Twitter (formerly Twitter), and YouTube. To ensure the standardization and comparability of data across multiple platforms, this invention abstracts a set of common elements to structurally align content from different platforms. These elements are defined as follows: ;
[0061] in This indicates information at the content level (such as title, body text, publication time, author). Metrics representing behavioral aspects (such as the number of likes, comments, and favorites). This represents the structure at the interaction level (such as comment network relationships). This structured approach makes the data collected from different platforms comparable and traceable under a unified dimension, laying the foundation for subsequent analysis.
[0062] Sub-steps 1-2: Data cleaning and standardization.
[0063] Since passively collected content may still contain advertisements, duplicate recommendations, garbled text, and low-value information, this invention employs two methods in the cleaning stage: rule-based filtering, which uses regular expression matching to remove text containing advertising features or invalid symbols; and similarity-based redundancy detection, which filters duplicate or highly similar recommended content by comparing text similarity with interaction features. The cleaned dataset is denoted as: ;
[0064] Where n is the total amount of original data and m is the amount of data after cleaning.
[0065] In the standardization process, this invention uniformly adopts UTF-8 encoding, performs word segmentation, stop word removal and lemmatization on the text, and aligns heterogeneous elements from multiple platforms to a unified general set, thereby achieving cross-platform data consistency.
[0066] As an optional implementation of this embodiment, in a method for evaluating the effectiveness of multi-domain dissemination based on passive perception, the method for obtaining reach effectiveness indicators through parallel processing of the structured social media data set using a multi-dimensional indicator calculation engine includes: For each social media platform and each time window Calculate the platform-level binary reach index If in the time window If at least one piece of content related to the target event is passively collected, then ,otherwise ; The platform-level binary reach index of each social media platform is weighted and its corresponding platform weight is then combined to generate the time window. Reach effectiveness index : ; in, , , ..., Each social media platform has a preset reach weight to meet [the needs of]... .
[0067] The binary mechanism based on passive recommendation results in this embodiment can avoid incomparability caused by differences in platform recommendation logic.
[0068] Specifically, the process is executed in parallel for multiple time window scales k of different sizes, generating a dynamic reach effectiveness index sequence corresponding to each time window scale: ;
[0069] The dynamic reach effectiveness index sequences of all time window scales k are merged into a multi-scale reach trajectory: ;
[0070] The multi-scale reach trajectory is used for comprehensive analysis of reach effectiveness.
[0071] This "maximization" fusion emphasizes the explosive effect of a single key platform; while parallel computing at a multi-scale time window scale k provides a dynamic characterization from high temporal resolution to smooth trends, making it more suitable for research on the spread of sudden and short-term hot topics.
[0072] This embodiment of a multi-domain propagation reach effectiveness evaluation method based on passive perception does not perform a one-time static evaluation, but instead corely employs a "sliding time window". The mechanism divides the continuous data stream into analysis windows of different scales. This allows the system to continuously calculate and output a time-varying reach effectiveness index sequence, and even further integrate it into a "multi-scale reach trajectory." This design enables assessors to observe the evolution trend of the reach effect of target events at different time granularities (such as hours, days, and weeks) in near real-time, accurately identify reach peaks, attenuation inflection points, or long-term dissemination platforms, thereby achieving continuous monitoring and in-depth analysis of dissemination dynamics, greatly improving the timeliness and process insight of the assessment.
[0073] The core of the reach effectiveness index modeling and analysis in this embodiment lies in assessing whether event information can naturally enter the user's visible range through the platform's recommendation mechanism. In a passive perception-based data collection mode, if a platform automatically pushes content related to an event, it indicates that the event has already achieved a certain level of popularity and recommendation priority on that platform. Therefore, this step not only measures the reach coverage of the target event on different platforms but also reflects the platform's support for event dissemination under algorithmic driving and its potential bottlenecks. Unlike traditional single-platform analysis that relies on explicit indicators, this method emphasizes cross-platform comparison and weighted fusion to ensure comparability and robustness in multi-platform dissemination scenarios. This is achieved using structured data defined in the data collection and preprocessing steps. and time window division This step achieves cross-platform and cross-time dynamic characterization within a unified framework. To obtain multi-scale dynamic indicators, several different time window sizes are introduced. And the reach index is calculated separately at each scale.
[0074] This embodiment also provides a multi-domain propagation reach effectiveness evaluation device based on passive sensing, including: The data acquisition and preprocessing module is used to acquire raw social media data from different platform domains and / or different language domains and / or different data modal domains around the world, and to perform cross-platform feature alignment processing on the raw social media data to obtain a computable structured social media data set; The reach effectiveness index calculation module is configured to perform the following: based on the structured social media data set, for each social media platform, determine whether the content related to the target event is passively perceived on each social media platform, and based on the determination result, integrate the preset weights of each social media platform to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism. Example 2
[0075] like Figure 2 As shown, this embodiment, based on the passive sensing-based multi-domain propagation reach effectiveness evaluation method of Embodiment 1, further provides a passive sensing-based multi-domain propagation performance dynamic evaluation method, including: Data acquisition and preprocessing: Obtain raw social media data from different platform domains and / or different language domains and / or different data modal domains worldwide; perform cross-platform feature alignment processing on the raw social media data to obtain a computable set of structured social media data. Based on the structured social media data set, the reach effectiveness index, and / or information ontology effectiveness index, and / or dissemination popularity effectiveness index, and / or interaction effectiveness index are obtained through parallel processing by a multi-dimensional index calculation engine. The reach effectiveness index is used to assess whether the target event information can naturally enter the user's visible range through the platform's recommendation mechanism. The information ontology effectiveness index is used to measure the dissemination adaptability of the target event content at the language and topic levels. The dissemination popularity effectiveness index is used to measure the exposure and interaction of the target event content on social media platforms. The interaction effectiveness index is used to measure the emotional distribution and structural characteristics of users in the comment section, reflecting the audience's attitude tendencies during the dissemination of the target event.
[0076] Specifically, in the dynamic evaluation method for multi-domain propagation effectiveness based on passive perception in this embodiment, the data acquisition and preprocessing steps are the same as in Embodiment 1.
[0077] In this embodiment of a dynamic evaluation method for multi-domain propagation effectiveness based on passive perception, the reach effectiveness index is obtained using the multi-domain propagation reach effectiveness evaluation method described in Embodiment 1.
[0078] Due to the adoption of the above technical solution, the multi-domain propagation efficiency dynamic evaluation method based on passive sensing in this embodiment has significant technical effects: It achieves unified and comparable analysis of cross-platform and cross-domain data. Through innovative "cross-platform feature alignment processing," it transforms raw social media data from different platforms, languages, and modalities worldwide into a "computable structured social media data set." This fundamentally solves the problem that existing technologies cannot perform horizontal comparison and fusion analysis due to differences in data formats and indicator systems, laying a reliable data foundation for the unified measurement of global communication trends.
[0079] A comprehensive, multi-dimensional, and flexibly configurable multi-dimensional evaluation system has been constructed. The solution employs four core effectiveness indicators (reach, information ontology, dissemination popularity, and interaction) calculated in parallel, quantitatively deconstructing communication effectiveness from four key dimensions: channel penetration (whether it is recommended), content adaptability (language and cultural fit), audience influence (exposure and interaction scale), and communication guidance (emotional inclination and structure). This multi-dimensional parallel evaluation framework overcomes the one-sidedness of traditional single or limited indicator evaluations, achieving a panoramic portrayal of the complex effects of international communication. Furthermore, the indicators employ an "AND / OR" relationship, allowing the evaluation system to flexibly select evaluation dimensions according to specific scenarios, possessing a high degree of customizability and adaptability.
[0080] The core evaluation metrics directly address the pain points of traditional methods, accurately quantifying key dissemination characteristics: The reach effectiveness index effectively assesses the natural spread of information under algorithm recommendation by judging whether information "naturally enters the user's visible range through the platform's recommendation mechanism," and solves the problems of traditional active crawling methods failing to reflect the platform's true traffic distribution and lagging early hotspot identification.
[0081] The Information Ontology Effectiveness Index focuses on "language and topic-level dissemination adaptability," which can quantify the potential of content to cross cultural barriers and provide a direct basis for evaluating the international design and localization effects of information.
[0082] The effectiveness index of dissemination popularity combines "exposure and interaction" to objectively reflect the overall activity level and depth of engagement of content on the user side.
[0083] The Interaction Effectiveness Index goes beyond simple quantitative statistics by analyzing the "emotional distribution and structural characteristics of the comment section," providing in-depth insights into audience attitudes and communication risks, and offering crucial insights for assessing the social impact of communication.
[0084] This method enhances the dynamism, timeliness, and decision support value of communication effectiveness assessment. The entire approach is based on dynamic calculations using preprocessed structured datasets, continuously generating multi-dimensional indicators. This transforms the assessment from a static, post-hoc summary into a real-time or near-real-time reflection of the evolution of the communication landscape, enabling timely identification of inflection points, risks, or opportunities. Consequently, it provides quantitative data support and direct decision-making basis for dynamically adjusting communication strategies and optimizing resource allocation.
[0085] In summary, this embodiment, based on a dynamic evaluation method for multi-domain communication effectiveness using passive perception, advances the evaluation of international communication effectiveness from the traditional qualitative, one-sided, and static model to a new stage of quantitative, comprehensive, and dynamic evaluation through systematic data fusion processing and multi-dimensional index modeling. This significantly improves the scientific rigor, accuracy, and practicality of the evaluation.
[0086] The raw social media data processed in this embodiment mainly covers multimodal data generated during the dissemination of international hot events across multiple social media platforms globally. This includes textual information such as posts, comments, and reposts in multiple languages; metadata information reflecting user attributes and interaction characteristics (such as timestamps, likes, comments, and shares); and topic tags and sentiment markers reflecting semantic and contextual features. This multi-source raw social media data collectively constitutes the data foundation for cross-platform, multi-dimensional dissemination effect evaluation, providing input support for the computational model of this invention.
[0087] As an optional implementation of this embodiment, in a dynamic evaluation method for multi-domain propagation effectiveness based on passive perception, the step of obtaining information ontology effectiveness indicators through parallel processing of the structured social media data set using a multi-dimensional indicator calculation engine includes: Based on the aforementioned structured social media dataset, the analysis focuses on the time windows related to the target event within each time window scale k. Language effectiveness index by language type and topic effectiveness index by topic category; In each time window Internally, the language effectiveness index and topic effectiveness index are weighted and integrated to form the information ontology effectiveness index.
[0088] Specifically, the language effectiveness index analysis process includes: For each time window scale k, there exists a corresponding time window For language sets ,language The amount of information is: ;
[0089] The language effectiveness index is defined as follows: .
[0090] Within the passive data collection framework, a predominantly homogeneous language distribution indicates a strong local influence of the event within its target geographical and linguistic environment; conversely, a diverse language distribution suggests that the event has transcended language barriers and possesses strong international reach. To avoid single-platform language bias, this method employs statistical indicators across multiple platforms to ensure the universality of the results.
[0091] The topic validity index analysis process includes: Topic Collection In the time window Internal topic categories The amount of information is: ;
[0092] The topic validity index is defined as: .
[0093] In the passive perception mode, if the topic categories are concentrated, it indicates that the event has a clear issue and a focused audience, and has the potential for in-depth dissemination; if the topic categories are diverse, it indicates that the event has attracted attention across issues and has a wider dissemination range.
[0094] In each time window Within this framework, the language effectiveness index and the topic effectiveness index are weighted and fused to form the information ontology effectiveness index:
[0095] in, , The weights are for the language dimension and the topic dimension, respectively.
[0096] Specifically, the process is executed in parallel for multiple time window scales k of different sizes, generating dynamic information ontology validity index sequences corresponding to each time window scale: ; Merging all time window scales forms a multi-scale information ontology evolution trajectory: ; The multi-scale information ontology evolution trajectory is used for comprehensive analysis of the effectiveness of information ontology.
[0097] Unlike traditional static settings, this invention allows for adaptive weight adjustment and can be learned and updated through the propagation effects of historical events, thereby enhancing the model's dynamic adaptability to different propagation scenarios.
[0098] This embodiment's information ontology effectiveness index modeling and analysis aims to measure the dissemination adaptability of event content at the language and topic levels. Based on a passive perception collection model, this step not only verifies whether the event is recommended and reached, but also focuses on its presentation within the language and topic system familiar to the audience. Since this method specifies the geographical location and language environment during the account setup stage, the distribution of language and topics can more intuitively reflect the event's dissemination potential both locally and globally.
[0099] As an optional implementation of this embodiment, in a dynamic evaluation method for multi-domain dissemination effectiveness based on passive perception, the step of obtaining dissemination popularity effectiveness indicators through parallel processing of the structured social media data set using a multi-dimensional indicator calculation engine includes: Obtain the time window corresponding to each time window scale k. The total exposure of content related to the target event is calculated, and the total exposure is normalized using a correction function to obtain the exposure index. Summary in the time window Within the content, the total number of user interaction behaviors triggered by the content is normalized using a correction function to obtain the interaction volume index; The exposure index and the interaction index are weighted and summed to generate the time window. The effectiveness index of the spread of information.
[0100] Specifically, the exposure index calculation process includes: For each time window scale k, there exists a time window The total passive exposure of the target event on a certain social media platform is (Play count or page view count), then through the correction function After normalization, the exposure index is obtained as follows: .
[0101] The correction function can be a logarithmic mapping or a piecewise linear function to reduce the long-tail effect of the play volume distribution and make the exposure volume between platforms of different scales comparable.
[0102] The calculation process for the interaction index includes: In the time window Within, interaction volume is defined as: ; in, , , The interaction index is obtained by mapping the number of likes, comments, and shares of the target event using a corresponding correction function. .
[0103] Within the passive perception framework, a higher level of interaction indicates a stronger user response to the event, representing greater virality.
[0104] In the time window Internally, the effectiveness index of dissemination popularity is obtained by weighting and integrating exposure and interaction: .
[0105] Specifically, the process is executed in parallel for multiple time window scales k of different sizes, generating a propagation heat effectiveness index sequence corresponding to each time window scale: ; By merging the propagation heat effectiveness index sequences across all time windows, a multi-scale propagation heat evolution trajectory is formed: ; The multi-scale propagation heat evolution trajectory is used for comprehensive analysis of the effectiveness of propagation heat.
[0106] This weighted fusion mechanism reflects both the breadth of an event's reach (exposure) within the platform's recommendation stream and the depth of user engagement (interaction). Compared to traditional methods, this invention emphasizes measuring popularity based on passively perceived data, thus better aligning with the actual logic of content dissemination.
[0107] This embodiment uses a modeling and analysis of the effectiveness of dissemination popularity metrics to measure the exposure and engagement of event content on social media platforms. In a passive perception-based data collection mode, if an account continuously receives event-related content, and this content is accompanied by high levels of behavioral metrics such as views, likes, comments, and shares, it directly indicates that the event is in a high-popularity state within the platform's recommendation system. This method ensures the comparability of popularity metrics across different platforms through standardization and weighted fusion mechanisms.
[0108] As an optional implementation of this embodiment, in a dynamic evaluation method for multi-domain propagation effectiveness based on passive perception, the step of obtaining interaction effectiveness indicators through parallel processing of the structured social media data set using a multi-dimensional indicator calculation engine includes: In the time window The comments within the content are assumed to be the total number of passively perceived comments. Of these, the number of positive comments was The number of neutral comments is The number of negative comments is Defined separately: ; ; .
[0109] This ratio can intuitively depict the emotional distribution characteristics of the comment section.
[0110] In each time window Internally, define the interaction effectiveness index: ;
[0111] in, , , These represent the weights of positive, neutral, and negative emotions, respectively. Researchers can flexibly adjust these weights based on the type of event. For example, in political and social issues, the weight of negative comments can be increased to enhance sensitivity to controversy and risk.
[0112] Specifically, the process is executed in parallel for multiple time window scales k of different sizes, generating interaction effectiveness index sequences corresponding to each scale: ; The interaction effectiveness index sequences at all scales are then merged to form a multi-scale user emotion evolution trajectory: ; The multi-scale user emotion evolution trajectory is used for comprehensive analysis of interaction effectiveness.
[0113] Within the framework of passive perception, the emotional distribution in the comments section represents the true inclination of the event among the audience: if the proportion of positive comments is high, it indicates that the event has been actively disseminated; if negative comments are concentrated, it indicates that the event is controversial and has potential risks; if neutral comments dominate, it indicates that the event has a wide reach but attitudes have not yet been formed.
[0114] Interaction effectiveness index modeling analysis measures the distribution and structured characteristics of user emotions in the comment section, reflecting the audience's attitudinal tendencies during event dissemination. In a passive perception-based data collection model, the emotional distribution in the comment section directly reflects the genuine reactions elicited after the event is recommended to users. Therefore, this step is not only a statistical analysis of the total number of comments but also a quantitative representation of the direction of dissemination. Unlike traditional methods that rely solely on sentiment polarity classification, this invention uses a distribution-weighted model to comprehensively examine the proportions and weights of positive, neutral, and negative emotions to obtain the interaction effectiveness index.
[0115] This embodiment of a method for dynamic evaluation of multi-domain propagation effectiveness based on passive sensing also includes: The effectiveness of reach, and / or effectiveness of information ontology, and / or effectiveness of dissemination popularity, and / or effectiveness of interaction are calculated at multiple time window scales. The dissemination effect of the target event is dynamically integrated and judged across dimensions to form a time-seriesd and interpretable comprehensive index, which is used to dynamically observe the changes in the dissemination effect of the target event within different time window scales.
[0116] Specifically, this embodiment of a method for dynamic evaluation of multi-domain propagation effectiveness based on passive sensing includes: For each time window scale k and time window Define the comprehensive index as follows: ;
[0117] in, For the weights of each dimension, To dynamically reach the effectiveness index sequence, This is a sequence of dynamic information ontology validity indices. For the effective index sequence of dissemination popularity, Interaction effectiveness index sequence; Execution is performed in parallel for multiple time window scales k of different sizes, generating comprehensive index sequences corresponding to each scale: ;
[0118] The composite index sequences at all scales are then merged to form a multi-scale composite analysis trajectory: .
[0119] Furthermore, this embodiment of a multi-domain propagation effectiveness dynamic evaluation method based on passive sensing includes: For each time window Composite Index Set a judgment threshold : ; Dynamically observe the changes in the propagation effect of the target event within different time windows, and ultimately form a multi-time-window dynamic judgment sequence: .
[0120] In summary, compared with existing technologies, this invention has achieved a breakthrough in evaluating the multi-platform dissemination effect of international hot topics, effectively solving the core pain points in the current field. Traditional methods are limited by single-platform data collection and isolated indicator analysis, making it difficult to comprehensively capture the complex dissemination trends of international hot topics in the global social media ecosystem. In contrast, this invention, through a multi-platform integrated computing architecture and dynamic weighting model, has for the first time achieved a truly cross-platform, multi-dimensional, and multilingual quantitative evaluation of dissemination effects.
[0121] This invention significantly improves the accuracy and comparability of international communication effectiveness assessment. Through an innovatively designed mechanism that maximizes reach effectiveness and a multilingual, multi-topic weighted model for information ontology effectiveness, it overcomes the assessment biases caused by platform data isolation and cultural differences inherent in traditional methods. This invention can accurately quantify the effects of geopolitical influence and cultural soft power dissemination; it provides quantifiable strategic decision-making indicators; and it establishes a truly global multi-platform assessment system.
[0122] At the technical implementation level, this invention solves the challenges of cross-border data heterogeneity and cultural context adaptation through multimodal data alignment processing and dynamic weight optimization mechanisms. The system can automatically process multilingual text, images, and video content, and adapt to the needs of different types of international events and dissemination stages through adaptive weight adjustments. This invention maintains the objectivity and comprehensiveness of strategy evaluation.
[0123] Ultimately, this invention provides unprecedented decision support capabilities for international communication strategies. By comprehensively integrating four dimensions of effectiveness indices, it generates quantitative assessment results with clearly defined thresholds, enabling decision-makers to quickly identify communication bottlenecks, optimize resource allocation, and adjust communication strategies. This end-to-end assessment solution not only significantly improves the efficiency and quality of international communication analysis but also provides reliable technical support for gaining the initiative in discourse and enhancing cultural soft power in the global social media environment.
[0124] This embodiment also provides a dynamic evaluation device for multi-domain propagation effectiveness based on passive sensing, including: The data acquisition and preprocessing module acquires raw social media data from different platform domains and / or different language domains and / or different data modal domains worldwide, and performs cross-platform feature alignment processing on the raw social media data to obtain a computable structured social media data set. The multi-dimensional indicator calculation module, based on the structured social media data set, obtains reach effectiveness indicators, and / or information ontology effectiveness indicators, and / or dissemination popularity effectiveness indicators, and / or interaction effectiveness indicators through parallel processing by the multi-dimensional indicator calculation engine; The reach effectiveness index is used to assess whether event information can naturally enter the user's visible range through the platform's recommendation mechanism. The information ontology effectiveness index is used to measure the dissemination adaptability of event content at the language and topic levels. The dissemination popularity effectiveness index is used to measure the exposure and interaction of event content on social media platforms. The interaction effectiveness index is used to measure the emotional distribution and structural characteristics of users in the comment section, reflecting the audience's attitude tendencies during the event dissemination process.
[0125] The following describes embodiments of the electronic device of the present invention, which can be considered as specific implementations of the methods and apparatus embodiments of the present invention described above. Details described in the embodiments of the electronic device of the present invention should be considered as supplements to the methods or apparatus embodiments described above; details not disclosed in the embodiments of the electronic device of the present invention can be implemented with reference to the methods or apparatus embodiments described above.
[0126] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. The electronic device includes a processor and a memory. The memory is used to store a computer-executable program. When the computer program is executed by the processor, the processor executes a method for evaluating the effectiveness of multi-domain propagation based on passive perception according to Embodiment 1 of the present invention and / or a method for dynamically evaluating the effectiveness of multi-domain propagation based on passive perception according to Embodiment 2 of the present invention.
[0127] like Figure 3 As shown, the electronic device is embodied in the form of a general-purpose computing device. There can be one or more processors working collaboratively. This invention also does not preclude distributed processing, meaning that processors can be distributed across different physical devices. The electronic device of this invention is not limited to a single entity, but can also be the sum of multiple physical devices.
[0128] The memory stores a computer-executable program, typically machine-readable code. The computer-readable program can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least some steps of the method.
[0129] The memory includes volatile memory, such as random access memory (RAM) and / or cache memory, and may also be non-volatile memory, such as read-only memory (ROM).
[0130] Optionally, in this embodiment, the electronic device further includes an I / O interface for exchanging data with external devices. The I / O interface can represent one or more of several bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.
[0131] It should be understood that Figure 3 The electronic device shown is merely one example of the present invention, and the electronic device of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as displays, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. Any electronic device capable of executing a computer-readable program in memory to implement the method of the present invention or at least some steps of the method can be considered as an electronic device covered by the present invention.
[0132] Figure 4 This is a schematic diagram of a computer-readable recording medium according to an embodiment of the present invention. Figure 4 As shown, a computer-readable recording medium stores a computer-executable program. When the computer-executable program is executed, it implements the passive sensing-based multi-domain propagation reach effectiveness evaluation method of Embodiment 1 of the present invention and / or the passive sensing-based multi-domain propagation performance dynamic evaluation method of Embodiment 2 of the present invention. The computer-readable recording medium may include data signals propagated in baseband or as part of a carrier wave, wherein readable program code is carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable recording medium may also be any readable medium other than a readable recording medium, which can send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable recording medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.
[0133] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java and C++, and conventional procedural programming languages such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0134] From the above description of the embodiments, those skilled in the art will readily understand that the present invention can be implemented by hardware capable of executing specific computer programs, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. included in the system. The present invention can also be implemented by computer software executing the methods of the present invention, for example, by control software executed by a microprocessor, electronic control unit, client, server, etc. However, it should be noted that the computer software executing the methods of the present invention is not limited to execution in one or a specific set of hardware entities; it can also be implemented in a distributed manner by unspecified hardware. For computer software, the software product can be stored on a computer-readable recording medium (such as a CD-ROM, USB flash drive, portable hard disk, etc.) or distributed across a network, as long as it enables electronic devices to execute the methods according to the present invention.
[0135] Furthermore, it should be noted that several alternative solutions exist in achieving the objectives of this invention. Regarding the overall methodology, the end-to-end evaluation framework employed in this invention is not the only approach. A distributed architecture can be used, deploying lightweight evaluation modules locally on each data platform for preliminary calculations, followed by a central system aggregating the results for comprehensive judgment. While this approach increases system complexity, it reduces compliance risks associated with cross-platform data transmission, while still achieving an overall assessment of the international dissemination effect.
[0136] At the level of specific implementation steps, there are also alternative methods for each step of this invention. Data acquisition can be obtained through platform APIs, web crawlers, or third-party services; multimodal data alignment can be achieved through unified feature space mapping or semantic association methods based on knowledge graphs; sentiment analysis can be based on deep neural networks, or it can use dictionary rule methods or hybrid models. The execution order of each step is flexible. For example, the order of data cleaning and time alignment can be interchanged, and the order of propagation popularity calculation and interaction calculation can be dynamically adjusted according to system resources, without significantly affecting the final evaluation result.
[0137] The above embodiments are only used to illustrate the present invention and are not intended to limit the technical solutions described herein. Although the present invention has been described in detail with reference to the above embodiments, the present invention is not limited to the specific embodiments described above. Therefore, any modifications or equivalent substitutions to the present invention, as well as all technical solutions and improvements that do not depart from the spirit and scope of the invention, are covered within the scope of the claims of the present invention.
Claims
1. A method for evaluating the effectiveness of multi-domain propagation reach based on passive perception, characterized in that, include: Data acquisition and preprocessing: Obtain raw social media data from different platform domains and / or different language domains and / or different data modal domains worldwide; perform cross-platform feature alignment processing on the raw social media data to obtain a computable set of structured social media data. Based on the structured social media dataset, for each social media platform, it is determined whether content related to the target event is passively perceived on each platform. Based on the determination results, the preset weights of each social media platform are integrated to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism.
2. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 1, characterized in that, The data acquisition and preprocessing steps involve obtaining raw social media data from different platform domains and / or different language domains and / or different data modal domains globally, including: By creating and operating multiple social media accounts that match the geographic location and language environment of the target event, data is collected by passively receiving recommended content from various social media platforms, thereby obtaining raw social media data related to the target event from different platform domains and / or different language domains and / or different data modal domains.
3. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 2, characterized in that, The data acquisition and preprocessing steps involve cross-platform feature alignment of the raw social media data to obtain a computable structured social media data set, including: Structured alignment of content from raw social media data across different platform domains; Data cleaning and standardization are performed on the original social media dataset based on structured alignment; By aligning all cleaned and standardized data sets based on a unified timestamp and employing a sliding time window mechanism, a computable structured social media data set is obtained.
4. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 3, characterized in that, The structured alignment of content from raw social media data across different platform domains includes: An abstract set of common elements is used to structurally align the content of raw social media data from different platform domains, as defined below: ; in, This indicates information at the content level. Indicators representing behavioral aspects, This represents the structure at the interaction layer.
5. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 4, characterized in that, The dataset after data cleaning based on the original social media dataset with structured alignment is denoted as: ; in, This represents the total amount of the original data. This represents the amount of data after cleaning.
6. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 5, characterized in that, The process involves aligning the cleaned and standardized data sets based on a unified timestamp and employing a sliding time window mechanism to obtain a computable, structured social media data set, including: Let the time window scale be Then in the time period The internal data set is defined as a time window. : ; in, Represents data items Timestamp.
7. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 6, characterized in that, The generation of cross-platform reach effectiveness metrics, which comprehensively evaluate the ability of the target event information to naturally reach users through the recommendation mechanism of social media platforms, includes: For each social media platform and each time window Calculate the platform-level binary reach index If in the time window If at least one piece of content related to the target event is passively collected, then ,otherwise ; The platform-level binary reach index of each social media platform is weighted and its corresponding platform weight is then combined to generate the time window. Reach effectiveness index : ; in, , , ..., Each social media platform has a preset reach weight to meet [the needs of]... .
8. The method for evaluating the effectiveness of multi-domain propagation reach based on passive perception according to claim 7, characterized in that, For multiple time window scales of different sizes Execute in parallel to generate dynamic reach effectiveness index sequences corresponding to different time windows: ; All time window scales The dynamic reach effectiveness index sequence is merged into a multi-scale reach trajectory: ; The multi-scale reach trajectory is used for comprehensive analysis of reach effectiveness.
9. A device for evaluating the effectiveness of multi-domain propagation reach based on passive sensing, characterized in that, include: The data acquisition and preprocessing module is used to acquire raw social media data from different platform domains and / or different language domains and / or different data modal domains around the world, and to perform cross-platform feature alignment processing on the raw social media data to obtain a computable structured social media data set; The reach effectiveness index calculation module is configured to perform the following: based on the structured social media data set, for each social media platform, determine whether the content related to the target event is passively perceived on each social media platform, and based on the determination result, integrate the preset weights of each social media platform to generate a cross-platform reach effectiveness index for evaluating the ability of target event information to naturally reach users through the platform recommendation mechanism.
10. An electronic device, comprising a processor and a memory, the memory being used to store a computer-executable program, characterized in that, When the computer program is executed by the processor, the processor executes a method for evaluating the effectiveness of multi-domain propagation reach based on passive perception as described in any one of claims 1-8.
11. A computer-readable recording medium storing a computer-executable program, characterized in that, When the computer executable program is executed, it implements the multi-domain propagation reach effectiveness evaluation method based on passive perception as described in any one of claims 1-8.
Citation Information
Patent Citations
A method for assessing and classifying cross-platform propagation trends based on specific events
CN111949848B
Social media information dissemination evaluation method and device
CN113781250B
Method and device for determining activity communication effect, storage medium, and terminal
CN117764627B
Internet information propagation effect analysis method based on multi-dimensional data
CN120492864A
