Method and system for assessing the intra-group mobility

Abstract

This invention provides a method and system for assessing the internal action capabilities of a group. The method includes: constructing a data matrix to assess the consistency of topics, objects of interest, and activity times of all individuals within the group, thereby obtaining group synergy information of the social network group; obtaining group action timeliness information, determining the time information of individuals in the social network group to be assessed regarding specific events, and processing this information to obtain a group action timeliness index; constructing a six-element activity array for all individuals within the current time period to obtain group behavior activity information; and assessing the internal action capabilities of the social network group to be assessed based on the group synergy information, the timeliness of the group action timeliness index, and the group behavior activity information. This invention solves the technical problems of the difficulty in quantifying the internal action capabilities of a group, the difficulty in collecting and processing internal organizational information of multi-source heterogeneous network groups, and the difficulty in comprehensively and quantitatively assessing the internal action capabilities of a group.

Description

Technical Field

[0001] This invention relates to the field of social network data processing, specifically to a method and system for assessing the action capabilities of groups. Background Technology

[0002] (1) Influence assessment techniques based on topological features (such as node degree, betweenness number, etc.).

[0003] These technologies focus on assessing group influence and information dissemination capabilities, but do not consider assessing the group's organizational capabilities.

[0004] (2) Existing social network group discovery and analysis technologies

[0005] Existing technologies can discover community structures and groups in networks. For example, the existing invention patent application document CN106650972A, entitled "A Recommendation System Rating Prediction Method Based on Cloud Model for Social Networks," includes the following steps: obtaining users' historical rating records and social network relationships on comment or social network platforms; constructing a one-dimensional rating cloud based on users' historical rating records, merging all one-dimensional rating clouds using comprehensive cloud technology to form a parent cloud, and generating new user ratings through the parent cloud; clustering users based on the new user ratings to discover similar groups of users, and clustering users based on the new ratings to discover similar groups of users through the clustering results, i.e., other users within the user's class are similar groups of that user; constructing two high-dimensional rating clouds for the similar groups of the predicted user based on the social relationships of the predicted user, calculating the membership degree of the user's historical ratings in each cloud to represent the position of the predicted user in its two similar groups, and constructing a comprehensive prediction mechanism based on Gaussian transform. The existing invention patent application document CN116150507A, entitled "Method, Device, Equipment and Medium for Identifying Online Troll Groups," describes a method that includes: analyzing whether two user pairs forward the same article source within a very short time interval based on social network events; if the number of such occurrences reaches a preset threshold, a collaborative forwarding relationship exists between the user pairs; extracting the collaborative forwarding relationships of all user pairs in the social network event to construct a global collaborative relationship network; weighted fusion of first-order direct proximity similarity and neighborhood similarity based on the global collaborative relationship network to obtain a comprehensive node similarity; and using a hierarchical partitioning method to divide the collaborative relationship network into groups based on the comprehensive node similarity to obtain the various online troll groups participating in the social network event. However, the aforementioned existing solutions mainly focus on identifying and dividing groups, without addressing the assessment of the group's internal action capabilities and organizational capabilities. Currently, the assessment of the capabilities of individuals or groups in social networks mostly focuses on the assessment of influence, which is a relatively broad concept. This solution proposes a comprehensive and multi-faceted assessment scheme for the organizational capabilities of groups in social networks.

[0006] Meanwhile, existing social network individual or group evaluation techniques have the following drawbacks:

[0007] The assessment of internal group capability indicators lacks a systematic approach and fails to accurately reflect the group's internal action capabilities.

[0008] Existing methods for assessing the capabilities within a group lack objective quantitative indicators, and the assessment results are highly subjective.

[0009] In summary, existing technologies suffer from the technical challenges of quantifying the internal action capabilities of groups, difficulties in collecting and processing internal organizational information of multi-source heterogeneous network groups, and the inability to comprehensively and quantitatively assess the internal action capabilities of groups. Summary of the Invention

[0010] The technical problem to be solved by this invention is how to address the difficulties in quantifying the internal action capabilities of groups, the challenges in collecting and processing internal organizational information of multi-source heterogeneous network groups, and the difficulty in comprehensively and quantitatively assessing the internal action capabilities of groups in the existing technology.

[0011] This invention solves the above-mentioned technical problems by employing the following technical solution: A method for enhancing the internal action capabilities of a group includes:

[0012] S1. Collect and construct a data matrix based on the group collaboration-related dataset to evaluate the topic consistency, attention consistency, and activity time consistency of all individuals in the group, so as to obtain the group collaboration information of the social network group.

[0013] S2. Obtain information on the timeliness of group actions, and construct a behavioral data matrix to determine the time information of individuals in the social network group to be evaluated when they refer to specific events, and process it to obtain the timeliness index of group actions.

[0014] S3. Collect data on individuals in the social network group to be evaluated to construct a six-element activity array R for all individuals in the current time period: [a,b,c,d,e,f]. Calculate the group behavior activity information based on the six-element activity array for all individuals in the current time period.

[0015] S4. Based on information on group collaboration, timeliness of group actions, and activity of group behavior, assess the internal action capabilities of the social network group to be evaluated.

[0016] This invention proposes a comprehensive, multi-faceted evaluation scheme for the internal action capabilities of groups in social networks. It addresses the problem of single evaluation dimensions in existing technologies by fully considering multi-dimensional information regarding group coordination, the timeliness of group action indicators, and group behavioral activity. Based on multi-source data, this invention quantifies the internal action capabilities of groups in social networks using quantitative indicators of internal organizational capabilities. It systematically evaluates these capabilities, comprehensively reflecting their internal action capacity and contributing to a clearer definition of their connotation.

[0017] In a more specific technical solution, step S1 includes:

[0018] S11. Perform data collection operations on the social network group to be evaluated to obtain a dataset related to group synergy;

[0019] S12. Construct a data matrix based on the group collaboration-related dataset, wherein the data matrix includes: topic data matrix, object data matrix and active time data matrix.

[0020] S13. Based on the topic data matrix, use the Jaccard similarity index to calculate the Jaccard similarity between individuals in the social network group to be evaluated and other individuals, as an indicator of topic consistency of the network group to be evaluated.

[0021] S14. Based on the object data matrix, use the Jaccard similarity index to calculate the Jaccard similarity between an individual and the other individuals, as an indicator of consistency of the objects of interest.

[0022] S15. Based on the active time data matrix, use the Jaccard similarity index to calculate the consistency index of active time between an individual and the other individuals.

[0023] S16. Calculate and use information entropy to determine weights, and use these weights to evaluate the topic consistency index, the object of interest consistency index, and the activity time consistency index of the social network group to be evaluated. Perform normalization and weighted summation operations to obtain the group synergy index.

[0024] In a more specific technical solution, in step S11, the group collaboration-related dataset includes: topic dataset, attention object dataset, and active time dataset.

[0025] In a more specific technical solution, in step S15, the following logic is used to determine the topic consistency index K of the network group to be evaluated. topic Consistency index K of the objects of focus follow and the active time consistency index K active :

[0026]

[0027]

[0028]

[0029] Where J(i,j) is the Jaccard similarity between any two individuals i and j, and A represents the topics mentioned, objects of interest, or activity time matrix of the individuals:

[0030]

[0031] In a more specific technical solution, in step S16, the group synergy index T is obtained using the following logic. group :

[0032] T group =λ1K topic +λ2K follow +λ2K active ;

[0033] In the formula, λ1 is the weight of the topic consistency index, λ2 is the weight of the object of interest consistency index, and λ3 is the weight of the activity time consistency index.

[0034] In a more specific technical solution, step S2 includes:

[0035] S21. Collect user behavior information and the time of behavior participation;

[0036] S22. Construct a behavior data matrix based on user behavior information and behavior participation time;

[0037] S23. Based on the behavioral data matrix, calculate the first participation time t of all individuals participating in a specific event j, and the first participation time t of the social network group to be evaluated. min The average time difference is used as the average time difference of group participation in a specific event, and based on this, an indicator of the timeliness of group action is obtained.

[0038] In a more specific technical solution, step S22 involves constructing a behavioral data matrix using the following logic:

[0039] M = [T(i,j)] n×k

[0040] In the formula, n is the number of individuals in the group, k represents the number of specific events, and each cell T(i,j) in the behavioral data matrix represents the earliest participation time of individual i in specific event j.

[0041] This invention replaces the traditional approach of studying group relationships from the perspective of influence. It focuses on collaborative organizational capabilities and, based on the synergy, timeliness of action, and activity level within the social network group to be evaluated, can quantitatively and accurately assess the group's collaborative organizational capabilities.

[0042] In a more specific technical solution, step S23 includes:

[0043] S231. Using the following logic, obtain the average time difference T of group participation in a specific event. j :

[0044]

[0045] Among them, t min The earliest time the group participates in the event is the minimum of the earliest times all individuals participate.

[0046] S232. Using the following logic, the timeliness index of group action is obtained:

[0047]

[0048] In a more specific technical solution, step S3 uses the following logic to process and obtain the group behavior activity information:

[0049]

[0050] In the formula, n is the number of individuals within the group, and λ j R represents the weights of different active behaviors, and R is the array of individual active behaviors.

[0051] This invention proposes an evaluation index system for group organizational capacity, which can quantitatively and comprehensively reflect the group's organizational and mobilization capabilities; it designs an evaluation method that combines multi-source heterogeneous network data, making full use of different types of data to support the evaluation; this invention adopts objective quantitative indicators and calculation methods, making the evaluation results more objective and credible.

[0052] The evaluation model and method of this invention are adaptable to different application scenarios, demonstrating strong applicability. They can support the dynamic evaluation of group organizational capabilities and monitor changes in these capabilities. The evaluation results of this invention are visually intuitive, facilitating result analysis and decision support.

[0053] The assessment strategy for the internal organizational capacity of a group in this invention is simple to implement, easy to engineering and promote, and highly flexible. It can provide effective support for online public opinion monitoring, online group management, and organizational behavior research.

[0054] In a more specific technical solution, the internal operational capability assessment system includes:

[0055] The group collaboration acquisition module is used to collect and construct a data matrix based on the group collaboration-related dataset. This matrix is ​​then used to evaluate the consistency of topics, objects of interest, and activity times of all individuals within the group, in order to obtain group collaboration information of the social network group.

[0056] The group action timeliness acquisition module is used to acquire group action timeliness information, thereby constructing a behavioral data matrix to determine the time information of individuals in the social network group to be evaluated when they refer to specific events, and then processing it to obtain group action timeliness indicators.

[0057] The group behavior activity acquisition module is used to evaluate individuals in a social network group. It collects behavioral data of all individuals in the group within a certain time period, such as following (a), liking (b), replying (c), forwarding (d), mentioning (e), and posting (f), to construct a six-element activity array R for all individuals in the current time period: [a,b,c,d,e,f]. Based on the six-element activity array for all individuals in the current time period, the group behavior activity information is obtained.

[0058] The internal action capability assessment module is used to assess the internal action capability of the social network group to be evaluated based on group collaboration information, timeliness indicators of group action, and group behavior activity information. The internal action capability assessment module is connected to the group collaboration acquisition module, the group action timeliness acquisition module, and the group behavior activity acquisition module.

[0059] The present invention has the following advantages over the prior art:

[0060] This invention proposes a comprehensive, multi-faceted evaluation scheme for the internal action capabilities of groups in social networks. It addresses the problem of single evaluation dimensions in existing technologies by fully considering multi-dimensional information regarding group coordination, the timeliness of group action indicators, and group behavioral activity. Based on multi-source data, this invention quantifies the internal action capabilities of groups in social networks using quantitative indicators of internal organizational capabilities. It systematically evaluates these capabilities, comprehensively reflecting their internal action capacity and contributing to a clearer definition of their connotation.

[0061] This invention replaces the traditional approach of studying group relationships from the perspective of influence. It focuses on collaborative organizational capabilities and, based on the synergy, timeliness of action, and activity level within the social network group to be evaluated, can quantitatively and accurately assess the group's collaborative organizational capabilities.

[0062] This invention proposes an evaluation index system for group organizational capacity, which can quantitatively and comprehensively reflect the group's organizational and mobilization capabilities; it designs an evaluation method that combines multi-source heterogeneous network data, making full use of different types of data to support the evaluation; this invention adopts objective quantitative indicators and calculation methods, making the evaluation results more objective and credible.

[0063] The evaluation model and method of this invention are adaptable to different application scenarios, demonstrating strong applicability. They can support the dynamic evaluation of group organizational capabilities and monitor changes in these capabilities. The evaluation results of this invention are visually intuitive, facilitating result analysis and decision support.

[0064] The assessment strategy for the internal organizational capacity of a group in this invention is simple to implement, easy to engineering and promote, and highly flexible. It can provide effective support for online public opinion monitoring, online group management, and organizational behavior research.

[0065] This invention solves the technical problems existing in the prior art, such as the difficulty in quantifying the internal action capabilities of a group, the difficulty in collecting and processing internal organizational information of multi-source heterogeneous network groups, and the difficulty in comprehensively and quantitatively assessing the internal action capabilities of a group. Attached Figure Description

[0066] Figure 1 This is a schematic diagram of the basic steps of the group intra-group action capability assessment method in Embodiment 1 of the present invention;

[0067] Figure 2 This is a schematic diagram illustrating the specific steps for obtaining group synergy in Embodiment 1 of the present invention;

[0068] Figure 3 This is a schematic diagram illustrating the specific steps of obtaining the timeliness of group actions in Embodiment 1 of the present invention;

[0069] Figure 4 This is a schematic diagram illustrating the specific steps of obtaining group activity levels in Embodiment 1 of the present invention. 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 in conjunction with the embodiments of the present invention. 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] Example 1

[0072] As a crucial aspect of group influence assessment, the evaluation of internal action capabilities has numerous applications in social network analysis, including political sentiment analysis, marketing strategy optimization, product promotion, and social media advertising. For certain groups within social networks that exhibit aggregation or organizational characteristics, assessing their internal action capabilities is of significant value. For example… Figure 1 As shown, the method for assessing the intra-group action capability provided by this invention includes the following basic steps:

[0073] S1. Obtain information on the group collaboration of groups in social networks;

[0074] In this embodiment, group coordination is an important characteristic of group behavior in social networks, used to measure the ability of group members to achieve common goals and coordinate actions. Groups with high group coordination indices have the ability to form organized and coordinated actions for common goals, and are an important indicator of group organizational capacity.

[0075] like Figure 2 As shown, in this embodiment, step S1 of obtaining group synergy further includes the following specific steps:

[0076] S11. Data collection to obtain a dataset related to group synergy;

[0077] In this embodiment, the group collaboration-related datasets include, but are not limited to: topic datasets, attention object datasets, and active time datasets;

[0078] In this embodiment, the user's behavioral information is obtained by sending a request to the social network platform through the open API (Application Programming Interface) provided by the social network platform or other legitimate means.

[0079] In this embodiment, the topic dataset includes, but is not limited to: data on topics mentioned by all individuals within the group; the follower dataset includes, but is not limited to: data on people followed by all individuals within the group, and other users followed by each individual; the active time dataset includes, but is not limited to: the time during which an individual engages in posting, liking, following, replying, or mentioning within a certain time period.

[0080] S12. Construct a data matrix based on the group synergy-related dataset;

[0081] In this embodiment, the data matrix includes, but is not limited to: a topic data matrix, an object data matrix, and an activity time data matrix;

[0082] In this embodiment, the collected topic data is constructed into a topic data matrix A. n×k, where n represents the number of individuals within the group, and k represents the number of topics mentioned. Cell A in the matrix. ij This can indicate whether individual i has mentioned topic j; 1 indicates mentioning it, and 0 indicates otherwise.

[0083] In this embodiment, the collected objects of interest are constructed into an object of interest data matrix B. n×k , where n represents the number of individuals within the group, and k represents the total number of objects of interest in the group. Cell B in the matrix. ij This can indicate whether individual i follows object j; 1 indicates following, 0 indicates otherwise. When collecting data on followed objects, considering the complexity and realities of individual followed objects, only individuals with more than a threshold of followers are collected.

[0084] In this embodiment, the collected active time data is constructed into an active time data matrix C. n×k , where n represents the number of individuals within the group, and k represents the number of time periods. Cell C in the matrix. ij This indicates whether individual i is active during time period j; 1 indicates activity, and 0 indicates otherwise. The range of values ​​for the time period is determined by the time range of the collected data. Each time period can be set appropriately according to the data situation, such as one hour.

[0085] S13. Evaluate the consistency of topics among all individuals by collecting the topics mentioned by individuals within the group;

[0086] In the topic consistency index calculation process of this embodiment, the Jaccard similarity index is used to calculate the topic consistency value between an individual and other individuals. For any two individuals i and j, the Jaccard similarity between them is calculated as follows:

[0087]

[0088] Among them, A i The set of topics mentioned by individual i refers to the i-th row of the topic data matrix A. The final topic consistency index for the group is obtained as follows:

[0089]

[0090] Where n is the number of individuals within the group.

[0091] S14. By collecting the objects of interest of individuals within the group, assess the consistency of the objects of interest of all individuals;

[0092] In the calculation of the object of interest consistency index in this embodiment, the Jaccard similarity index is used to calculate the object of interest consistency value between an individual and other individuals. For any two individuals i and j, the Jaccard similarity between them is calculated as follows:

[0093]

[0094] Among them, B i The set of objects that an individual focuses on refers to the i-th row of the object data matrix B. This ultimately yields the group's attention consistency index:

[0095]

[0096] S15. Collect the time of a specific individual's posting, liking, following, replying, mentioning, etc. over a relatively long period of time, and evaluate the consistency of the active time of all individuals;

[0097] In the calculation of the active time consistency index in this embodiment, the Jaccard similarity index is used to calculate the active time consistency value between an individual and other individuals. For any two individuals i and j, the Jaccard similarity between them is calculated as follows:

[0098]

[0099] Among them, C i The set of times in which an individual is active refers to the i-th row of the active time data matrix C. This ultimately yields the consistency index of the group's active times:

[0100]

[0101] S16. Calculate the consistency of topics mentioned, the consistency of objects followed, and the consistency of active time for social network groups respectively. Select the information entropy method to determine the weights, and normalize and weight the aforementioned indicators to obtain the group synergy index.

[0102] In this embodiment, based on the three consistency indicators of topic, target audience, and activity time mentioned above, the group's synergy indicator can be obtained:

[0103] T group =λ1K topic +λ2K follow +λ2K active ;

[0104] The weights are determined using information entropy; see the supplement for details.

[0105] S2. Obtain timely information on group actions;

[0106] In this embodiment, assessing the timeliness of group actions is an important aspect of understanding the speed and immediacy of a group's behavioral responses on social networks. The timeliness of group behavior can be measured based on different behavior types. This scheme collects relevant posts and interactions of a group participating in a specific event within a time period, obtaining the earliest time each individual participated in the event at that specific time. The timeliness of group actions is measured based on the average time difference of individual participation. In this embodiment, behavior types include, but are not limited to: posting, liking, commenting, forwarding, and mentioning.

[0107] like Figure 3 As shown, step S2, which obtains the timeliness of group actions, also includes the following specific steps:

[0108] S21. Collect data to obtain user behavior information and the time of behavior participation;

[0109] In this embodiment, user behavior information is obtained by sending requests to the social network platform via the open API (Application Programming Interface) or other legitimate means provided by the social network platform. Specifically, this embodiment collects relevant posts and interactions of a group participating in a specific event within a certain time period, and calculates the earliest participation time of all individuals in that specific behavior.

[0110] S22. Construct a data matrix based on user behavior information and behavior participation time;

[0111] In this embodiment, a data matrix is ​​constructed based on the collected data:

[0112] M = [T(i,j)] n×k

[0113] Where n is the number of individuals in the group, and k represents the number of specific events. Each cell T(i,j) in the matrix can represent the earliest time that individual i participated in a specific event j; if it did not participate, it is set to empty.

[0114] S23. Obtain the average participation time difference of individuals in the group at a specific time.

[0115] In this embodiment, the average time difference T of group participation in a specific event j The earliest participation time t of all individuals participating in event j and the earliest participation time t of the group. min Average time difference:

[0116]

[0117] The timeliness indicator for group actions is:

[0118]

[0119] S3. Obtain the activity level of group behavior in social networks;

[0120] In this embodiment, the time taken by all individuals within a group in a social network to perform actions such as posting, liking, following, replying, and mentioning over a relatively long period of time can be used to assess the activity level of the group.

[0121] like Figure 4 As shown, in this embodiment, step S3, which involves obtaining the activity level of behavior in the group, further includes the following specific steps:

[0122] S31. Collect data on individuals in the group and construct a six-element active array for all individuals during the time period;

[0123] In this embodiment, the time data of all individuals within the group performing actions such as following (a), liking (b), replying (c), forwarding (d), mentioning (e), and posting (f) (without mentioning or forwarding) within a relatively long time period of interest are collected to obtain a six-element active array R for all individuals within this time period: [a,b,c,d,e,f], where the array value is the number of active actions during this period.

[0124] S32. Based on the six-element active data set of all individuals during this time period, calculate the group activity using the following formula:

[0125]

[0126] Where n is the number of individuals within the group, λ j The weights for different active behaviors are determined by the weight λ corresponding to the attention relationship. a Set a fixed value of 1 as the baseline; if the number of posts in the data collected in this embodiment is t times the number of followers, then λ f Set it to t.

[0127] S4. Assess the intra-group action capability in social networks based on group coordination, timeliness of group actions, and group activity.

[0128] In summary, this invention proposes a comprehensive, multi-faceted evaluation scheme for the internal action capabilities of groups in social networks. This addresses the problem of single evaluation dimensions in existing technologies, fully considering multi-dimensional information regarding group coordination, the timeliness of group action indicators, and group behavioral activity within the group's internal action capabilities. Based on multi-source data, this invention quantifies the organizational capabilities of groups in social networks, systematically evaluating their internal action capabilities. It comprehensively reflects the internal action capabilities of groups and helps to clearly define the connotation of group internal action capabilities.

[0129] This invention replaces the traditional approach of studying group relationships from the perspective of influence. It focuses on collaborative organizational capabilities and, based on the synergy, timeliness of action, and activity level within the social network group to be evaluated, can quantitatively and accurately assess the group's collaborative organizational capabilities.

[0130] This invention proposes an evaluation index system for group organizational capacity, which can quantitatively and comprehensively reflect the group's organizational and mobilization capabilities; it designs an evaluation method that combines multi-source heterogeneous network data, making full use of different types of data to support the evaluation; this invention adopts objective quantitative indicators and calculation methods, making the evaluation results more objective and credible.

[0131] The evaluation model and method of this invention are adaptable to different application scenarios, demonstrating strong applicability. They can support the dynamic evaluation of group organizational capabilities and monitor changes in these capabilities. The evaluation results of this invention are visually intuitive, facilitating result analysis and decision support.

[0132] The assessment strategy for the internal organizational capacity of a group in this invention is simple to implement, easy to engineering and promote, and highly flexible. It can provide effective support for online public opinion monitoring, online group management, and organizational behavior research.

[0133] This invention solves the technical problems existing in the prior art, such as the difficulty in quantifying the internal action capabilities of a group, the difficulty in collecting and processing internal organizational information of multi-source heterogeneous network groups, and the difficulty in comprehensively and quantitatively assessing the internal action capabilities of a group.

[0134] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An internal operational capability assessment method, characterized in that, The method includes: S1. Collect and construct a data matrix based on the group collaboration-related dataset to evaluate the topic consistency, attention consistency, and activity time consistency of all individuals in the group, so as to obtain the group collaboration information of the social network group. S2. Obtain information on the timeliness of group actions, and construct a behavioral data matrix to determine the time information of individuals in the social network group to be evaluated when they refer to specific events, and process it to obtain the timeliness index of group actions. S1 includes: S11. Perform data collection operations on the social network group to be evaluated to obtain a dataset related to group synergy; S12. Construct a data matrix based on the group collaboration-related dataset, wherein the data matrix includes: topic data matrix, object data matrix and active time data matrix; S13. Based on the topic data matrix, use the Jaccard similarity index to calculate the Jaccard similarity between individuals in the social network group to be evaluated and other individuals, as an indicator of topic consistency of the network group to be evaluated. S14. Based on the object data matrix, use the Jaccard similarity index to calculate the Jaccard similarity between an individual and the other individuals, as an indicator of consistency of the objects of interest. S15. Based on the active time data matrix, use the Jaccard similarity index to calculate the consistency index of active time between an individual and the other individuals. In S15, the following logic is used to determine the topic consistency index of the network groups to be evaluated. Consistency indicators of the objects of focus and active time consistency index : In the formula, Let A be the Jaccard similarity between any two individuals i and j, and let A represent the topics mentioned, objects of interest, or activity time matrix of the individuals: S16. Calculate and use information entropy to determine weights, and use them to evaluate the topic consistency index, the object of interest consistency index, and the activity time consistency index of the social network group to be evaluated. Perform normalization and weighted summation operations to obtain the group synergy index. S3. To evaluate individuals within a social network group, data is collected to construct a six-element activity array R for all individuals within the current time period: Based on the six-element activity array of all individuals in the current time period, the group behavior activity information is obtained; S4. Based on information on group collaboration, timeliness of group actions, and activity of group behavior, assess the internal action capabilities of the social network group to be evaluated.

2. The internal operational capability assessment method according to claim 1, characterized in that, In step S11, the group collaboration-related dataset includes: topic dataset, attention object dataset, and active time dataset.

3. The internal operational capability assessment method according to claim 1, characterized in that, In step S16, the group synergy index is obtained by processing using the following logic. : ； In the formula, The weight of the topic consistency index, The weight of the consistency index of the object of interest. The weight of the active time consistency index.

4. The internal operational capability assessment method according to claim 1, characterized in that, Step S2 includes: S21. Collect user behavior information and the time of behavior participation; S22. Construct the behavior data matrix based on user behavior information and behavior participation time; S23. Based on the behavioral data matrix, calculate the first participation time t of all individuals participating in the specific event j, and the first participation time of the social network group to be evaluated. The average time difference is used as the average time difference of group participation in a specific event, and the timeliness index of group action is obtained accordingly.

5. The internal operational capability assessment method according to claim 4, characterized in that, In step S22, the behavioral data matrix is ​​constructed using the following logic: M= In the formula, n is the number of individuals in the group, k represents the number of specific events, and each cell in the behavioral data matrix... This represents the earliest time that individual i participates in a specific event j.

6. The internal operational capability assessment method according to claim 4, characterized in that, Step S23 includes: S231. Using the following logic, the average time difference of group participation in the specific event is obtained. : In the formula, The earliest time the group participates in the event is the minimum of the earliest times all individuals participate. S232. Using the following logic, the timeliness index of group action is obtained: 。 7. The internal operational capability assessment method according to claim 1, characterized in that, In step S3, the group behavior activity information is obtained by processing using the following logic: In the formula, n is the number of individuals within the group. R represents the weights of different active behaviors, and R is the array of individual active behaviors.

8. An internal operational capability assessment system, used to execute the internal operational capability assessment method according to any one of claims 1 to 7, characterized in that, The system includes: The group collaboration acquisition module is used to collect and construct a data matrix based on the group collaboration-related dataset, and to evaluate the topic consistency, attention object consistency, and activity time consistency of all individuals in the group, so as to obtain the group collaboration information of the social network group. The group action timeliness acquisition module is used to acquire group action timeliness information, thereby constructing a behavioral data matrix to determine the time information of individuals in the social network group to be evaluated when they refer to specific events, and to process the data to obtain group action timeliness indicators. The group behavior activity acquisition module is used to collect data on the individuals in the social network group to be evaluated, in order to construct the six-element activity array R of all the individuals in the current time period: Based on the six-element activity array of all the individuals in the current time period, the group behavior activity information is obtained; An internal action capability assessment module is used to assess the internal action capability of the social network group to be assessed based on the group coordination information, the timeliness of the group action timeliness indicator, and the group behavior activity information. The internal action capability assessment module is connected to the group coordination acquisition module, the group action timeliness acquisition module, and the group behavior activity acquisition module.

Images