A method and system for measuring multi-agent influence in social media

Abstract

The application discloses a kind of social media in the measurement method and system of multi-subject influence, method includes: based on social media, the influence index attribute value of preset user subject is obtained, the basic influence of user subject is calculated;According to the synergic relationship intensity between user subject, the comprehensive basic influence of multi-subject is calculated;According to user behavior and corresponding preset weight coefficient and nonlinear effect, the interactive influence of user subject is calculated;According to the maximum saturation value of interactive influence and preset weight coefficient, the multi-subject interactive influence of user subject is calculated;According to the comprehensive basic influence of multi-subject and multi-subject interactive influence and corresponding weight coefficient, the comprehensive influence of multi-subject of user subject is calculated.By the technical scheme of the application, the precise evaluation of multi-subject comprehensive influence is realized, and the timeliness of user interactive behavior and its decreasing effect on multi-subject interactive influence are dynamically reflected.

Description

Technical Field

[0001] This invention relates to the field of information dissemination technology, and in particular to a method and system for measuring the influence of multiple parties in social media. Background Technology

[0002] With the rapid development and widespread adoption of social media, it has become an important platform for research on information dissemination, user interaction, and social behavior. In social networks, user influence is not only a key driver of information dissemination but also a core factor in understanding network dynamics and optimizing communication strategies. However, traditional research on user influence often focuses on single actors, neglecting the comprehensive influence measurement under the combined influence of multiple actors.

[0003] A significant proportion of shared content on current social networks is jointly owned by multiple entities. Examples include a group photo involving multiple users or an advertisement post containing multiple brand logos. In multi-entity contexts, the breadth and depth of information dissemination depend not only on the influence of a single user but also on the characteristics, connections, and overall synergy of multiple entities. Therefore, scientifically quantifying the comprehensive influence of multiple entities and revealing their driving mechanisms for information dissemination has become an important direction for current research.

[0004] In recent years, with the widespread application of social networks and the diversification of information dissemination methods, the study of user influence has gradually become an important direction in social network analysis.

[0005] Existing technologies in user influence research often rely too heavily on single dimensions, such as social relationships or dissemination paths, lacking a comprehensive consideration of users' multi-dimensional characteristics. This leads to insufficient accuracy and comprehensiveness in influence measurement. Furthermore, deep learning-based measurement methods are computationally inefficient in large-scale social networks, struggling to handle real-time requirements and massive datasets. Moreover, existing user influence measurement models typically do not adequately consider multi-agent scenarios, focusing primarily on assessing the influence of a single user. This limits their ability to handle multi-agent interactions, failing to fully reflect the interplay between multiple stakeholders in information dissemination and their combined impact on the overall dissemination effect. Summary of the Invention

[0006] To address the aforementioned issues, this invention provides a method and system for measuring multi-agent influence in social media. By introducing multi-dimensional factors and fully considering the complex interaction effects among multiple agents, a collaborative relationship parameter is introduced to quantify the collaborative effects between users. A multi-agent comprehensive influence measurement model is formed by combining basic influence and interactive influence, achieving accurate assessment of multi-agent comprehensive influence. By combining a time decay function and a nonlinear adjustment coefficient, the timeliness of user interaction behavior and its diminishing effect on multi-agent interactive influence are dynamically reflected.

[0007] To achieve the above objectives, this invention provides a method for measuring the influence of multiple stakeholders in social media, comprising:

[0008] The influence index attribute values ​​of a preset user subject are obtained based on social media, and the basic influence of the user subject is calculated based on the influence index attribute values ​​and preset weight coefficients.

[0009] Based on the strength of the collaborative relationship between user entities, the comprehensive basic influence of multiple entities is calculated based on the basic influence of the user entities.

[0010] The interactive influence of the user subject is calculated based on the user behavior of the user subject and the corresponding preset weight coefficients and nonlinear effects.

[0011] The multi-subject interactive influence of the user subject is calculated based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject.

[0012] The multi-subject comprehensive influence is calculated based on the multi-subject comprehensive basic influence, the multi-subject interactive influence, and the corresponding weighting coefficients.

[0013] In the above technical solution, preferably, the process of obtaining the influence index attribute value of a preset user subject based on social media, and calculating the basic influence of the user subject based on the influence index attribute value and a preset weight coefficient, specifically includes:

[0014] The user's follower count and number of followers / followers are obtained based on the social media platform. Then, the user's u is calculated using a logarithmic function based on these follower and follower counts. i Basic influence The calculation formula is:

[0015]

[0016] Where α and β are weighting coefficients, F i User subject u i Number of followers; G i Indicates user ui The number of followers.

[0017] In the above technical solution, preferably, the process of calculating the comprehensive basic influence of multiple entities based on the basic influence of the user entities according to the strength of the collaborative relationship between the user entities includes:

[0018] Define the user group U in the social media as U = {u1, u2, ..., u...} n};

[0019] User subject u is calculated using the Jaccard similarity coefficient. i and u j Strength of synergy between them C ij The calculation formula is:

[0020]

[0021] in, and Representing user subject u respectively i and user subject u j A collection of groups, interactive activities, or shared interests;

[0022] Based on the basic influence of the user entities and the strength of the collaborative relationships between them, the multi-entity comprehensive basic influence of the user group is calculated using the following formula:

[0023]

[0024] Where γ represents the weighting coefficient of the synergistic effect.

[0025] In the above technical solution, preferably, the process of calculating the interactive influence of the user subject based on the user behavior and corresponding preset weight coefficients and nonlinear effects specifically includes:

[0026] Obtain the parameter values ​​of the user's liking, commenting, and forwarding behaviors;

[0027] Based on the weight coefficient of each user behavior and the corresponding nonlinear effect, the individual user subject u is calculated. i Interactive influence The formula is:

[0028]

[0029] Where ζ,η,θ represent the weighting coefficients of likes, comments, and shares. Indicates user u i At time t ′ The number of likes on the published content. Indicates user u i At time t ′ Number of comments on the published content Indicates user u i At time t ′ The number of reposts of published content, δ,ε,∈ are non-linear adjustment coefficients, δ,ε,∈<1 indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. λ is the time decay coefficient.

[0030] In the above technical solution, preferably, the process of calculating the multi-subject interactive influence of the user subject based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject specifically includes:

[0031] Based on the maximum saturation value C of the interactive influence, and the adjustment parameters k for the growth rate and saturation level of the interactive influence, the multi-subject interactive influence of the user subject is calculated. The calculation formula is:

[0032]

[0033] Among them, the maximum saturation value C of interactive influence represents the upper limit of interactive influence, w i Indicates user u i The weighting coefficients.

[0034] In the above technical solution, preferably, the process of calculating the multi-subject comprehensive influence of the user subject based on the multi-subject comprehensive basic influence, the multi-subject interactive influence, and the corresponding weight coefficients includes:

[0035] Combining the aforementioned multi-entity comprehensive basic influence and the influence of multi-subject interaction The multi-subject comprehensive influence I was calculated U (t), the calculation formula is:

[0036]

[0037] Wherein, ξ is the weighting coefficient of the comprehensive basic influence of multiple entities. The weighted contribution of the influence of multi-entity interaction.

[0038] This invention also proposes a system for measuring the influence of multiple stakeholders in social media, applying the method for measuring the influence of multiple stakeholders in social media disclosed in any of the above-described technical solutions, including:

[0039] The basic indicator influence calculation module is used to obtain the influence indicator attribute values ​​of a preset user subject based on social media, and calculate the basic influence of the user subject based on the influence indicator attribute values ​​and preset weight coefficients.

[0040] The multi-subject basic influence calculation module is used to calculate the comprehensive basic influence of multiple subjects based on the basic influence of the user subjects according to the strength of the collaborative relationship between the user subjects.

[0041] The single-subject interaction influence calculation module is used to calculate the interaction influence of the user subject based on the user behavior of the user subject and the corresponding preset weight coefficient and nonlinear effect.

[0042] The multi-subject interaction influence calculation module is used to calculate the multi-subject interaction influence of the user subject based on the maximum saturation value of the interaction influence and the preset weight coefficient of the user subject.

[0043] The multi-entity comprehensive influence calculation module is used to calculate the multi-entity comprehensive influence of the user entity based on the multi-entity comprehensive basic influence, the multi-entity interactive influence, and the corresponding weight coefficients.

[0044] In the above technical solution, preferably, the basic indicator influence calculation module is specifically used for:

[0045] The user's follower count and number of followers / followers are obtained based on the social media platform. Then, the user's u is calculated using a logarithmic function based on these follower and follower counts. i Basic influence The calculation formula is:

[0046]

[0047] Where α and β are weighting coefficients, F i User subject u i Number of followers; G i Indicates user u i The number of followers.

[0048] In the above technical solution, preferably, the multi-entity basic influence calculation module is specifically used for:

[0049] Define the user group U in the social media as U = {u1, u2, ..., u...} n};

[0050] User subject u is calculated using the Jaccard similarity coefficient. i and u j Strength of synergy between them C ijThe calculation formula is:

[0051]

[0052] in, and Representing user subject u respectively i and user subject u j A collection of groups, interactive activities, or shared interests;

[0053] Based on the basic influence of the user entities and the strength of the collaborative relationships between them, the multi-entity comprehensive basic influence of the user group is calculated using the following formula:

[0054]

[0055] Where γ represents the weighting coefficient of the synergistic effect.

[0056] In the above technical solution, preferably, the single-subject interaction impact calculation module is specifically used for:

[0057] Obtain the parameter values ​​of the user's liking, commenting, and forwarding behaviors;

[0058] Based on the weight coefficient of each user behavior and the corresponding nonlinear effect, the individual user subject u is calculated. i Interactive influence The formula is:

[0059]

[0060] Where ζ,η,θ represent the weighting coefficients of likes, comments, and shares. Indicates user u i At time t ′ The number of likes on the published content. Indicates user u i At time t ′ Number of comments on the published content Indicates user u i At time t ′ The number of reposts of published content, δ,ε,∈ are non-linear adjustment coefficients, δ,ε,∈<1 indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. λ is the time decay coefficient;

[0061] The multi-agent interaction impact calculation module is specifically used for:

[0062] Based on the maximum saturation value C of the interactive influence, and the adjustment parameters k for the growth rate and saturation level of the interactive influence, the multi-subject interactive influence of the user subject is calculated. The calculation formula is:

[0063]

[0064] Among them, the maximum saturation value C of interactive influence represents the upper limit of interactive influence, w i Indicates user u i The weighting coefficients.

[0065] Compared with the prior art, the beneficial effects of the present invention are as follows: by introducing multi-dimensional factors and fully considering the complex interaction effects between multiple subjects, a collaborative relationship parameter is introduced to quantify the collaborative effects between users. The basic influence and interactive influence are combined to form a multi-subject comprehensive influence measurement model, which realizes the accurate assessment of the comprehensive influence of multiple subjects. By combining the time decay function and the nonlinear adjustment coefficient, the timeliness of user interaction behavior and its diminishing effect on the multi-subject interactive influence are dynamically reflected. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating a method for measuring the influence of multiple entities in social media, as disclosed in an embodiment of the present invention.

[0067] Figure 2 This is a schematic diagram of a module of a multi-subject influence measurement system in social media disclosed in an embodiment of the present invention.

[0068] In the diagram, the correspondence between the components and the reference numerals is as follows:

[0069] 1. Basic indicator influence calculation module; 2. Multi-subject basic influence calculation module; 3. Single-subject interactive influence calculation module; 4. Multi-subject interactive influence calculation module; 5. Multi-subject comprehensive influence calculation module. Detailed Implementation

[0070] 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, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] The present invention will now be described in further detail with reference to the accompanying drawings:

[0072] like Figure 1As shown, a method for measuring multi-agent influence in social media according to the present invention includes:

[0073] The influence index attribute values ​​of the user subject are obtained based on social media, and the basic influence of the user subject is calculated based on the influence index attribute values ​​and the preset weight coefficient.

[0074] Based on the strength of the collaborative relationship between user entities, the comprehensive basic influence of multiple entities is calculated based on the basic influence of user entities.

[0075] The interactive influence of a user subject is calculated based on the user's behavior and the corresponding preset weight coefficients and nonlinear effects.

[0076] The multi-subject interactive influence of a user subject is calculated based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject.

[0077] The comprehensive influence of a user entity is calculated based on the multi-entity basic influence and multi-entity interactive influence, as well as the corresponding weighting coefficients.

[0078] In this implementation, by introducing multi-dimensional factors and fully considering the complex interaction effects among multiple subjects, a collaborative relationship parameter is introduced to quantify the collaborative effects among users. The basic influence and interactive influence are combined to form a multi-subject comprehensive influence measurement model, which realizes the accurate assessment of the comprehensive influence of multiple subjects. By combining the time decay function and the nonlinear adjustment coefficient, the timeliness of user interaction behavior and its diminishing effect on the multi-subject interactive influence are dynamically reflected.

[0079] Specifically, to accurately assess the comprehensive influence of multiple users in the information dissemination process, firstly, based on the social network structure, a user's basic influence is defined by combining the number of followers and the number of people they follow. A collaborative relationship parameter is introduced to quantify the synergistic effect between users, thus obtaining the comprehensive basic influence of multiple entities. Secondly, considering user interaction behaviors (such as likes, comments, and reposts), this invention further defines interactive influence and uses a time decay function and a nonlinear adjustment coefficient to reflect the timeliness of multi-entity interactive behaviors and their diminishing effect on influence. Finally, combining basic influence and interactive influence, a weighted coefficient is used for fusion, ultimately forming a more comprehensive and accurate multi-entity comprehensive influence measurement model.

[0080] In the above implementation, preferably, the basic influence of the user subject is calculated based on the influence index attribute value obtained from social media and the preset weight coefficient. The specific process includes:

[0081] Based on the number of followers and followings of a user entity obtained from social media, the user entity u is calculated using a logarithmic function. i Basic influence The calculation formula is:

[0082]

[0083] Where α and β are weighting coefficients, F i User subject u i Number of followers; G i Indicates user u i The number of followers.

[0084] Specifically, the structure of social networks forms the basis for the diffusion and spread of influence. Within social networks, a user's number of followers typically reflects their popularity, while the number of followers represents their influence online. Therefore, the number of followers and the number of followers can serve as important indicators for measuring a user's social influence.

[0085] The use of a logarithmic function aims to eliminate the order-of-magnitude difference between the number of followers and the number of followers, avoiding an imbalance in influence assessment caused by excessively large values. Furthermore, the logarithmic transformation ensures that the contribution of increasing followers and the number of followers to influence gradually decreases, aligning with the diminishing marginal utility characteristic in reality.

[0086] In the above implementation, the multi-entity influence model does not simply sum the influence of multiple user bases; it also requires consideration of the structured synergistic effects among the multiple entities. For example, when multiple opinion leaders (Influencers) promote the same product simultaneously, their combined influence far exceeds the sum of the influence of a single opinion leader.

[0087] Therefore, preferably, the comprehensive basic influence of multiple entities is calculated based on the basic influence of user entities according to the strength of the collaborative relationship between user entities. The specific process includes:

[0088] Define a user group U = {u1, u2, ..., u} in social media. n};

[0089] User subject u is calculated using the Jaccard similarity coefficient. i and u j Strength of synergy between them C ij The calculation formula is:

[0090]

[0091] in, and Representing user subject u respectively i and user subject u jA collection of groups, interactive activities, or shared interests;

[0092] Based on the user entity's basic influence and the strength of collaborative relationships among user entities, the multi-entity comprehensive basic influence of the user group is calculated using the following formula:

[0093]

[0094] Where γ represents the weighting coefficient of the synergistic effect.

[0095] In the above implementation, preferably, the interactive influence of the user subject is calculated based on the user subject's user behavior and the corresponding preset weight coefficients and nonlinear effects. The specific process includes:

[0096] Obtain parameter values ​​for a user's likes, comments, and shares.

[0097] Based on the weight coefficient of each user behavior and the corresponding nonlinear effect, the individual user subject u is calculated. i Interactive influence The formula is:

[0098]

[0099] Where ζ,η,θ represent the weighting coefficients of likes, comments, and shares. Indicates user u i At time t ′ The number of likes on the published content. Indicates user u i At time t ′ Number of comments on the published content Indicates user u i At time t ′ The number of reposts of published content, δ,ε,∈ are non-linear adjustment coefficients, δ,ε,∈<1 indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. λ is the time decay coefficient.

[0100] Specifically, user behavior (likes, comments, reposts) reflects a user's activity, interactivity, and content dissemination ability on social networks, and is a direct indicator of a user's influence on social networks. The interactive influence generated by user behavior on social networks decays over time; therefore, a time decay function is used to adjust the interactive influence to better reflect real-world scenarios.

[0101] Furthermore, in real-world social networks, the impact of user interaction on influence is not constant but gradually decreases as interaction increases. In particular, once content has already garnered a large number of likes, the marginal contribution of each subsequent like to influence diminishes. Therefore, this invention employs exponential weighting to adjust the effect of interaction on user influence.

[0102] In the above implementation, preferably, the multi-subject interactive influence of the user subject is calculated based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject. The specific process includes:

[0103] Based on the maximum saturation value C of interactive influence, and the adjustment parameters k for the growth rate and saturation degree of interactive influence, the multi-subject interactive influence of the user subject is calculated. The calculation formula is:

[0104]

[0105] Among them, the maximum saturation value C of interactive influence represents the upper limit of interactive influence, w i Indicates user u i The weighting coefficients.

[0106] Specifically, in real-world social networks, a user's attention and influence have their limits. When the interactions of multiple high-influence users accumulate, the overall influence does not increase linearly, but tends to a stable level, reflecting the phenomenon of audience attention saturation and information overload.

[0107] In the above implementation, preferably, the multi-subject comprehensive influence of the user subject is calculated based on the multi-subject comprehensive basic influence and multi-subject interactive influence, as well as the corresponding weight coefficients. The specific process includes:

[0108] Combining the comprehensive basic influence of multiple entities Multi-subject interactive influence The multi-subject comprehensive influence I was calculated U (t), the calculation formula is:

[0109]

[0110] Wherein, ξ is the weighting coefficient of the comprehensive basic influence of multiple entities. The weighted contribution of the influence of multi-entity interaction.

[0111] Specifically, in social networks, a user's influence depends not only on their position within the network structure (such as the number of followers and following), but also on their activity and interactive behaviors on the platform (such as likes, comments, and reposts). Therefore, to comprehensively measure the combined influence of multiple stakeholders, this invention combines basic influence and interactive influence to obtain the comprehensive influence of multiple stakeholders.

[0112] In summary, by combining the fundamental influence of social networks and the influence of user behavior interactions, this invention accurately quantifies the influence of multiple stakeholders, overcoming the limitations of existing research that focuses solely on the influence of a single user. By introducing a synergy strength parameter and utilizing the Jaccard similarity coefficient to quantify the synergistic effect among users, the nonlinear synergistic effect of the fundamental influence of multiple stakeholders is effectively captured. Furthermore, by incorporating a time decay function and a nonlinear adjustment coefficient, the timeliness and diminishing effects of user interaction behavior are dynamically assessed, enhancing the model's adaptability and responsiveness. Overall, this invention achieves accurate and dynamic evaluation of the comprehensive influence of multiple stakeholders, significantly enhancing the comprehensiveness and practicality of influence measurement.

[0113] like Figure 2 As shown, this invention also proposes a system for measuring multi-agent influence in social media, applying any of the disclosed methods for measuring multi-agent influence in social media as described in the above embodiments, including:

[0114] The basic indicator influence calculation module 1 is used to obtain the influence indicator attribute values ​​of preset user subjects based on social media, and calculate the basic influence of user subjects based on the influence indicator attribute values ​​and preset weight coefficients.

[0115] Multi-subject basic influence calculation module 2 is used to calculate the comprehensive basic influence of multiple subjects based on the basic influence of user subjects according to the strength of the collaborative relationship between user subjects.

[0116] The single-subject interaction influence calculation module 3 is used to calculate the user subject's interaction influence based on the user subject's user behavior and the corresponding preset weight coefficients and nonlinear effects.

[0117] The multi-subject interaction influence calculation module 4 is used to calculate the multi-subject interaction influence of the user subject based on the maximum saturation value of the interaction influence and the preset weight coefficient of the user subject.

[0118] The multi-subject comprehensive influence calculation module 5 is used to calculate the multi-subject comprehensive influence of the user subject based on the multi-subject comprehensive basic influence, multi-subject interactive influence, and corresponding weight coefficients.

[0119] In this implementation, by introducing multi-dimensional factors and fully considering the complex interaction effects among multiple subjects, a collaborative relationship parameter is introduced to quantify the collaborative effects among users. The basic influence and interactive influence are combined to form a multi-subject comprehensive influence measurement model, which realizes the accurate assessment of the comprehensive influence of multiple subjects. By combining the time decay function and the nonlinear adjustment coefficient, the timeliness of user interaction behavior and its diminishing effect on the multi-subject interactive influence are dynamically reflected.

[0120] In the above embodiments, preferably, the basic indicator influence calculation module 1 is specifically used for:

[0121] Based on the number of followers and followings of a user entity obtained from social media, the user entity u is calculated using a logarithmic function. i Basic influence The calculation formula is:

[0122]

[0123] Where α and β are weighting coefficients, F i User subject u i Number of followers; G i Indicates user u i The number of followers.

[0124] In the above embodiment, preferably, the multi-subject basic influence calculation module 2 is specifically used for:

[0125] Define a user group U = {u1, u2, ..., u} in social media. n};

[0126] User subject u is calculated using the Jaccard similarity coefficient. i and u j Strength of synergy between them C ij The calculation formula is:

[0127]

[0128] in, and Representing user subject u respectively i and user subject u j A collection of groups, interactive activities, or shared interests;

[0129] Based on the user entity's basic influence and the strength of collaborative relationships among user entities, the multi-entity comprehensive basic influence of the user group is calculated using the following formula:

[0130]

[0131] Where γ represents the weighting coefficient of the synergistic effect.

[0132] In the above embodiments, preferably, the single-subject interaction impact calculation module 3 is specifically used for:

[0133] Obtain parameter values ​​for a user's likes, comments, and shares.

[0134] Based on the weight coefficient of each user behavior and the corresponding nonlinear effect, the individual user subject u is calculated. i Interactive influence The formula is:

[0135]

[0136] Where ζ,η,θ represent the weighting coefficients of likes, comments, and shares. Indicates user u i At time t ′ The number of likes on the published content. Indicates user u i At time t ′ Number of comments on the published content Indicates user u i At time t ′ The number of reposts of published content, δ,ε,∈ are non-linear adjustment coefficients, δ,ε,∈<1 indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. λ is the time decay coefficient;

[0137] Multi-agent interaction impact calculation module 4 is specifically used for:

[0138] Based on the maximum saturation value C of interactive influence, and the adjustment parameters k for the growth rate and saturation degree of interactive influence, the multi-subject interactive influence of the user subject is calculated. The calculation formula is:

[0139]

[0140] Among them, the maximum saturation value C of interactive influence represents the upper limit of interactive influence, w i Indicates user u i The weighting coefficients.

[0141] The functions to be implemented by each module of the social media multi-entity influence measurement system disclosed in the above embodiments correspond to the steps of the social media multi-entity influence measurement method disclosed in the above embodiments. In the implementation process, the operation is carried out with reference to the above embodiments, and will not be repeated here.

[0142] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for measuring the influence of multiple stakeholders in social media, characterized in that, include: The influence index attribute values ​​of a preset user subject are obtained based on social media, and the basic influence of the user subject is calculated based on the influence index attribute values ​​and preset weight coefficients. Based on the strength of the collaborative relationship between user entities, the comprehensive basic influence of multiple entities is calculated based on the basic influence of the user entities. The interactive influence of the user subject is calculated based on the user behavior of the user subject and the corresponding preset weight coefficients and nonlinear effects. The multi-subject interactive influence of the user subject is calculated based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject. The multi-subject comprehensive influence is calculated based on the multi-subject comprehensive basic influence and the multi-subject interactive influence, as well as the corresponding weight coefficients. The process of calculating the comprehensive basic influence of multiple entities based on the strength of the collaborative relationship between user entities and the basic influence of the user entities includes: Define the user composition in the social media ; User subject calculated using Jaccard similarity coefficient and Strength of synergy between The calculation formula is: in, and Representing user subjects respectively and user subject A collection of groups, interactive activities, or shared interests; Based on the basic influence of the user entities and the strength of the collaborative relationships between them, the multi-entity comprehensive basic influence of the user group is calculated using the following formula: in, This is represented by the weighting coefficients of the synergistic effect. Representing the user subject The foundation of influence; The process of calculating the multi-subject interactive influence of a user subject based on the maximum saturation value of the interactive influence and the preset weight coefficient of the user subject includes: Based on the maximum saturation value of interactive influence C And adjustment parameters for the growth rate and saturation level of interactive influence. k The multi-subject interactive influence of the user subject is calculated. The calculation formula is: Among them, the maximum saturation value of interactive influence Indicates the upper limit of interactive influence. Indicates user The weighting coefficients, Represents a single user entity The interactive influence.

2. The method for measuring multi-subject influence in social media according to claim 1, characterized in that, The process of obtaining the influence indicator attribute values ​​of a preset user subject based on social media, and calculating the basic influence of the user subject based on the influence indicator attribute values ​​and preset weight coefficients, specifically includes: The user's follower count and following count are obtained based on the social media platform. The user's identity is then calculated using a logarithmic function based on these numbers. Basic influence The calculation formula is: in, , These are weighting coefficients. Representing the user subject The number of followers; Indicates user The number of followers.

3. The method for measuring multi-subject influence in social media according to claim 1, characterized in that, The process of calculating the interactive influence of the user subject based on the user behavior and corresponding preset weight coefficients and nonlinear effects includes: Obtain the parameter values ​​of the user's liking, commenting, and forwarding behaviors; Based on the weighting coefficients of each user behavior and the corresponding nonlinear effects, the individual user entity is calculated. Interactive influence The formula is: in, The weighting coefficients representing likes, comments, and shares. Indicates user In time The number of likes on the published content. Indicates user In time Number of comments on the published content Indicates user In time The number of times the published content is forwarded. It is a non-linear adjustment coefficient. This indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. , This is the time decay coefficient.

4. The method for measuring multi-subject influence in social media according to claim 1, characterized in that, The process of calculating the multi-entity comprehensive influence of the user entity based on the multi-entity comprehensive basic influence, the multi-entity interactive influence, and the corresponding weighting coefficients includes: Combining the aforementioned multi-entity comprehensive basic influence and the influence of multi-subject interaction The comprehensive influence of multiple entities was calculated. The calculation formula is: in, The weighting coefficients represent the comprehensive fundamental influence of multiple entities. The weighted contribution of the influence of multi-entity interaction.

5. A measurement system for multi-agent influence in social media, characterized in that, The method for measuring multi-agent influence in social media as described in any one of claims 1 to 4 includes: The basic indicator influence calculation module is used to obtain the influence indicator attribute values ​​of a preset user subject based on social media, and calculate the basic influence of the user subject based on the influence indicator attribute values ​​and preset weight coefficients. The multi-subject basic influence calculation module is used to calculate the comprehensive basic influence of multiple subjects based on the basic influence of the user subjects according to the strength of the collaborative relationship between the user subjects. The single-subject interaction influence calculation module is used to calculate the interaction influence of the user subject based on the user behavior of the user subject and the corresponding preset weight coefficient and nonlinear effect. The multi-subject interaction influence calculation module is used to calculate the multi-subject interaction influence of the user subject based on the maximum saturation value of the interaction influence and the preset weight coefficient of the user subject. The multi-entity comprehensive influence calculation module is used to calculate the multi-entity comprehensive influence of the user entity based on the multi-entity comprehensive basic influence, the multi-entity interactive influence, and the corresponding weight coefficients.

6. The multi-agent influence measurement system in social media according to claim 5, characterized in that, The basic indicator influence calculation module is specifically used for: The user's follower count and following count are obtained based on the social media platform. The user's identity is then calculated using a logarithmic function based on these numbers. Basic influence The calculation formula is: in, , These are weighting coefficients. Representing the user subject The number of followers; Indicates user The number of followers.

7. The multi-agent influence measurement system in social media according to claim 5, characterized in that, The single-agent interaction impact calculation module is specifically used for: Obtain the parameter values ​​of the user's liking, commenting, and forwarding behaviors; Based on the weighting coefficients of each user behavior and the corresponding nonlinear effects, the individual user entity is calculated. Interactive influence The formula is: in, The weighting coefficients representing likes, comments, and shares. Indicates user In time The number of likes on the published content. Indicates user In time Number of comments on the published content Indicates user In time The number of times the published content is forwarded. It is a non-linear adjustment coefficient. This indicates that the relationship between user behavior and influence is decreasing. This represents the non-linear effect of likes, comments, and shares. Represented as a time decay function, it indicates that the impact of user behavior decays over time. , This is the time decay coefficient.

Images