CN113343149A - Agent-based mobile terminal social media propagation effect evaluation method, system and application - Google Patents
Agent-based mobile terminal social media propagation effect evaluation method, system and application Download PDFInfo
- Publication number
- CN113343149A CN113343149A CN202110694811.6A CN202110694811A CN113343149A CN 113343149 A CN113343149 A CN 113343149A CN 202110694811 A CN202110694811 A CN 202110694811A CN 113343149 A CN113343149 A CN 113343149A
- Authority
- CN
- China
- Prior art keywords
- agent
- social
- social media
- target
- effect evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000694 effects Effects 0.000 title claims abstract description 74
- 238000011156 evaluation Methods 0.000 title claims abstract description 67
- 230000003993 interaction Effects 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000004891 communication Methods 0.000 claims abstract description 13
- 230000006872 improvement Effects 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 claims description 49
- 238000012545 processing Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000013480 data collection Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000011273 social behavior Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 6
- 230000004927 fusion Effects 0.000 abstract description 2
- 230000008447 perception Effects 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000005728 strengthening Methods 0.000 abstract 1
- 238000010606 normalization Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 230000002354 daily effect Effects 0.000 description 6
- 238000009792 diffusion process Methods 0.000 description 5
- 230000009193 crawling Effects 0.000 description 4
- 230000002996 emotional effect Effects 0.000 description 4
- 238000011835 investigation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention discloses a method, a system and application for evaluating social media propagation effect of a mobile terminal based on Agent, and relates to the technical field of internet. The method comprises five modules of Agent social identity model modeling, Agent media interaction behavior modeling, Agent social communication propagation capacity improvement, media data analysis and Agent effect evaluation. The invention utilizes a method of implanting data acquisition agents in a social media platform, and all the agents perform preset role modeling and platform strengthening training from human setting, behavior to social relation, so that the agents have the capability of replacing netizens in the target field. The Agent is used as a group representative, so that the number of the evaluation sampling samples is greatly reduced, the economic cost of the social media transmission effect evaluation is greatly reduced, the working efficiency of the social media transmission effect evaluation is remarkably improved, and the scientificity of the social media transmission effect evaluation is improved by carrying out data perception and fusion analysis through the Agent of multiple platforms.
Description
Technical Field
The invention belongs to the technical field of internet, and particularly relates to a method, a system and application for evaluating social media propagation effect of a mobile terminal based on Agent.
Background
With the rapid development of 4G/5G mobile communication technology, various types of social media (such as microblog, today's headline, tremble, Facebook, and the like) are turning to the mobile internet era, the mobile terminal users have a larger and larger usage ratio, and sharing information and expressing viewpoints at any time and any place through the intelligent mobile terminal social APP has become a main channel for vast netizens to participate in social life, which also causes the social media platform to give up the PC terminal gradually and concentrate on the construction of the mobile terminal channel. For governments releasing policy information on mobile terminal social media and enterprises developing advertising marketing, how to evaluate the propagation effect of the delivered information on the social media more scientifically and efficiently will have important influence on subsequent government network social science governance and accurate customization of enterprise marketing strategies.
The existing social media propagation effect analysis method mainly comprises three types: the method comprises the steps of collecting information such as praise quantity, forwarding quantity, reading quantity, comment quantity, user attention quantity and the like of published information from a target social media platform by using a web crawler, and analyzing and evaluating the information spreading extent through data statistics and trends. And secondly, collecting the reply information or network public sentiment clustering information from the target social media by using a web crawler, acquiring the emotional tendency of the audience of the user to the published information by using natural language processing and semantic analysis and recognition, and analyzing and evaluating the information transmission depth. And thirdly, utilizing market research personnel to open offline sampling survey aiming at the media promotion content, and evaluating the media information propagation effect by statistically analyzing the feedback opinions of the people through arranging set problems.
The current propagation effect analysis method has three problems:
firstly, mass data are generated by social media every day, the relevance between most data and data concerned by governments and enterprises is not high, only relevant information and data of published topics are collected, then evaluation samples are too few, the cost is too high when the social media platform is cleaned after full-coverage collection, and once collection action influences the operation of the media platform, a large legal risk is generated.
Second, mobile terminal social media is different from PC end social media, has stronger software encryption means and stricter content anti-crawl mechanism, needs extremely professional technical personnel, carries out a series of complicated operations such as reverse analysis, APP shelling, communication protocol capture package, and crawler crawls all is public data in addition, all need the authorization to visit many private data (such as instant messaging data, professional group data etc.) that government enterprise focuses on, causes the unable collection of data or gathers incomplete problem.
Third, malicious network behaviors such as traffic and comments are brushed in social media propagation, a difference is obvious between data collected according to crawlers and real netizen feelings, the data obtained by using offline sampling investigation is often real compared with online data, but the offline sampling investigation is low in working efficiency, less in sample data and limited by regions. Therefore, a new method for evaluating social media propagation effects of a mobile terminal is needed to achieve more scientific and efficient evaluation of social media propagation effects.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method and a system for evaluating the social media propagation effect of a mobile terminal based on Agent.
The invention is realized in such a way that the Agent-based mobile terminal social media propagation effect evaluation method comprises the following steps:
the method comprises the steps that firstly, a data acquisition Agent is preset on a social platform, and Agent social identity model modeling, Agent media interaction behavior modeling, Agent social communication transmission capacity improvement, Agent social media data acquisition and social media transmission effect evaluation are achieved;
secondly, directionally and accurately sampling and intelligently analyzing social media propagation data;
and step three, evaluating the effect of social media information propagation in the netizens.
In one embodiment, the Agent social identity model modeling is to perform group portrayal according to a target people facing government and enterprise information popularization, construct an Agent projection model of the target people on social media, automatically generate batch, oriented, accurate and comprehensive person-set identity files for the agents, and highly restore the social identity model of the target people by using multi-dimensional information of gender, age, region, professional field, hobbies, income level and education level.
In one embodiment, the Agent media interactive behavior modeling is that an Agent account is created on a plurality of associated social media platforms by using a social identity model, a network behavior model of an Agent group is built through a computer-aided technology according to a network behavior rule of a social media user, a personified social life is built by the model according to social identity, work and rest time, behavior habits and network activeness, and the Agent group is automatically controlled to perform daily social action behaviors of praise, comment and forward.
In one embodiment, the Agent social communication propagation capacity is improved by controlling the Agent group orientation to establish a friend relationship with a designated area or industry netizen according to a social circle of a target public, adding an area or industry forum, a live channel and a social group, focusing on a domain key media account and an opinion leader account, and utilizing a copying and accompanying capacity improvement mode to shape a human setting image of the Agent group in a preset domain of a social media platform.
In one embodiment, the Agent social media data collection is realized by accessing a social media platform in an authorized manner by using a preset multi-platform Agent account group, actively collecting social platform interaction information, instant messaging information and social group information related to a target group netizen, and passively acquiring media information which is recommended by the social media platform through an intelligent algorithm and conforms to the Agent setting.
In one embodiment, the social media propagation effect evaluation is a propagation effect evaluation algorithm formed according to the information propagation extent, the information propagation depth and the audience interaction degree of the delivered information on the target social platform; and adjusting the external Agent identity model, the behavior model and the social circle parameter input by a machine learning method, and performing optimization iteration on the propagation effect evaluation algorithm.
Another object of the present invention is to provide a system for implementing the Agent-based mobile terminal social media propagation effect evaluation method, where the Agent-based mobile terminal social media propagation effect evaluation system includes:
the Agent role generation unit extracts Agent role metadata through analyzing user characteristics in the field of social platforms, generates corresponding Agent role information in batches through an Agent role knowledge graph model aiming at the role characteristics obtained by the network citizen portrait of a target group, and realizes automatic registration and identity verification of the target platform, wherein each Agent role is the projection of the network citizen of the target group in a network space;
the Agent scheduling and evaluating unit is used for constructing a network behavior model of an Agent group through a computer-assisted technology according to a network behavior rule of a social media user and on the basis of Agent role attributes, establishing a personified social life according to different social identities, interests and hobbies, rest time, behavior habits and network liveness, controlling the Agent group to orient to form friends with a designated area or industry netizen according to a social circle of a target public, adding an area or industry discussion area, a live broadcast channel and a social group, paying attention to key media accounts and opinion leader accounts in a specific field, and automatically controlling the Agent group to perform daily praise, comment and forward social action behaviors by copying and along with a plurality of social propagation capacity modeling modes;
the Agent network Agent unit provides network Agent links meeting the social platform rules and the target person regional characteristics according to the network access requirements of the target social platform and the target Agent living habits and regional settings
The Agent media communication unit provides a mobile terminal Agent bearing platform meeting social platform rules and target person set language and position characteristics according to the operation configuration requirements of a target social platform and target person set settings, and comprises a group control Agent in a wired USB mode and a group control Agent in a wireless WiFi mode or a cloud control software installed at a mobile terminal to realize the group control Agent through the Internet cloud.
In one embodiment, the specific process of Agent social dissemination ability modeling comprises the following steps: a human setting modeling stage and a behavior modeling stage;
the human modeling stage is used for designing periodic human modeling activities for the Agent according to different platform characteristics; and in the behavior modeling stage, aiming at a social relation graph of a target user in the industry field of effect evaluation, searching and adding target friends, adding professional groups, paying attention to opinion leaders and participating in hot topic interaction to perform social behavior modeling.
Another object of the present invention is to provide a computer program product stored on a computer readable medium, which includes a computer readable program for providing a user input interface to implement the Agent-based mobile-side social media propagation effect evaluation method when the computer program product is executed on an electronic device.
Another object of the present invention is to provide an information data processing terminal, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the Agent-based mobile terminal social media propagation effect evaluation method.
By combining all the technical schemes, the invention has the advantages and positive effects as shown in the following table.
(1) According to the social media propagation effect evaluation method, the method that the data acquisition agents are implanted into the social media platform is utilized, preset roles are formed and the platform is strengthened and trained from human setting, behaviors to social relations of all the agents, so that the agents have the capability of replacing netizens in a target field, the agents are used as group representatives, the number of evaluation sampling samples is greatly reduced, and the economic cost of social media propagation effect evaluation can be greatly reduced.
(2) The invention carries out network data acquisition by a self-establishment Agent method, compared with a crawler data acquisition mode, the Agent collects self data, the acquisition method is simple and quick, the operation burden of a social media platform can not be increased due to wide crawling range and high crawling frequency, the account is sealed or the legal risk is not brought, and the safety of media propagation effect evaluation can be improved.
(3) The method depends on the user authority of the self-built Agent, can solve the problem that the social private information (such as information of friend interaction, group chat and the like) is difficult to obtain due to data encryption or lack of authorization of the mobile terminal, and can obviously improve the data acquisition depth of social media propagation effect evaluation.
(4) According to the method, online agents are used for replacing offline market researchers to conduct online data investigation, compared with real people, the number of the online agents can be expanded at will, the agents can work in a non-time and non-regional mode, and the working efficiency of social media propagation effect evaluation is improved remarkably.
(5) According to the method, a social media propagation effect evaluation system of a cross-social platform is established, and according to cross-platform transmission attributes of social media information, agents preset in a plurality of social platforms are used for data perception and fusion analysis, so that the scientificity of social media propagation effect evaluation can be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic diagram of modules for evaluating social media propagation effects of a mobile terminal of Agent according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of Agent social identity model modeling provided by the embodiment of the invention.
Fig. 3 is a schematic diagram of Agent media interaction behavior modeling provided in the embodiment of the present invention.
Fig. 4 is a schematic diagram of social media data collection according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of social media data collection according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of evaluation of social media propagation effect according to an embodiment of the present invention.
Fig. 7 is a block diagram of a device design provided by an embodiment of the present invention.
Fig. 8 is a diagram of an Agent role generation unit according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of a specific process of Agent role capability promotion according to an embodiment of the present invention.
Fig. 10 is a diagram of a media propagation effect evaluation index system according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as broadly as the present invention is capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. As used herein, the terms "vertical," "horizontal," "left," "right," and the like are for purposes of illustration only and are not intended to represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The invention provides an Agent-based mobile terminal social media propagation effect evaluation method and device, which can preset a data acquisition Agent on a social platform, directionally and accurately sample and intelligently analyze social media propagation data, and evaluate the effect of social media information propagation in netizens. The technology mainly comprises 5 modules of Agent social identity model modeling, Agent media interaction behavior modeling, Agent social propagation capacity improvement, Agent social media data acquisition and Agent propagation effect evaluation, and the relationship among the modules is shown in figure 1. The Agent social identity model modeling module carries out group portrait modeling according to the target people to restore the social identity model and generate a plurality of Agent personal devices. The Agent media interaction behavior modeling module registers Agent accounts of the multi-social media platform by utilizing the personal device generated by the social identity model, and simulates real user behaviors to browse, like praise and pay attention to. The Agent social communication transmission capability improving module builds a field task image through a plurality of capability improving modes such as copying and accompanying. The Agent social media data acquisition module acquires information such as Agent account numbers, friends, interaction, groups, instant messaging and the like. The Agent transmission effect evaluation module intelligently analyzes the information obtained by the data acquisition module and performs media effect transmission evaluation by using an evaluation algorithm to obtain an evaluation result. The specific implementation of these 5 modules will be detailed below.
As shown in FIG. 2, the Agent social identity model models: the method comprises the steps of carrying out group portrayal according to target people oriented to government and enterprise information popularization, constructing an Agent projection model of the target people on social media, automatically generating batch, directional, accurate and comprehensive people-set identity files for the agents, highly reducing the social identity model of the target people according to multi-dimensional information such as gender, age, region, professional field, interests, income level, education degree and the like, and generating a plurality of Agent people sets.
As shown in fig. 3, Agent media interaction behavior modeling: the social identity model is utilized to create Agent accounts on a plurality of associated social media platforms, a network behavior model of an Agent group is built through a computer-aided technology according to the network behavior rules of social media users, an anthropomorphic social life is built through the model according to different social identities, work and rest time, behavior habits, network activeness and the like, and the Agent group is automatically controlled to perform daily social action behaviors such as praise, comment and forwarding.
As shown in fig. 4, the Agent social communication ability promotion module: according to the social circle of a target people, the Agent group is controlled to be oriented to form friends with a designated area or industry netizen, the friends are added into an area or industry forum, a live broadcast channel and a social group, key media accounts and opinion leader accounts in a specific field are concerned, and the human set image of the Agent group in the preset field of the social media platform is formed by utilizing multiple capability promotion modes such as copying, accompanying and the like.
As shown in fig. 5, the Agent media data collection module: the method comprises the steps of utilizing a preset multi-platform Agent account group to access a social media platform in an authorized mode, actively collecting social platform interaction information, instant messaging information, social group information and the like related to social people of a target group network, and passively obtaining media information which is recommended by the social media platform through an intelligent algorithm and accords with the setting of an Agent.
As shown in fig. 6, the Agent propagation effect evaluation module: and forming a propagation effect evaluation algorithm according to the information propagation extent, the information propagation depth and the audience interaction degree of the delivery information on the target social platform. The propagation effect evaluation method comprises the steps of adjusting parameter input of an external Agent identity model, a behavior model, a social circle and the like through a machine learning method, optimizing and iterating a propagation effect evaluation algorithm, and finally displaying the propagation effect evaluation by taking an Agent-based mobile terminal social media propagation effect evaluation system as a result, wherein the propagation effect evaluation system comprises an Agent role generation unit, an Agent scheduling evaluation unit, an Agent network Agent unit and an Agent media communication unit, as shown in fig. 7.
The working principle is as follows:
(1) the Agent role generation unit, as shown in fig. 8, stores the relationship between each entity in the internet by using a knowledge graph. The basic constituent units are four-tuples of two types, namely < entity, attribute value > and < entity, relationship and entity >. Extracting Agent role metadata through analyzing the user characteristics in the field of social platform, wherein the metadata is an entity; in the present example, the metadata of the Agent character is divided into age, location, sex, occupation, education, etc. The embodiment of the invention utilizes an ontology editing tool, uses a resource description framework, constructs an Agent role knowledge graph model based on a universal ontology model, and semantically associates the metadata of the Agent role with the entity of the role level. And aiming at the role characteristics obtained by the portrait of the target group netizen, generating corresponding Agent role information in batches through an Agent role knowledge graph model, wherein each Agent role is the projection of the target group netizen in a network space, and realizing the automatic registration and identity verification of a target platform.
(2) The Agent scheduling evaluation unit: according to the network behavior rule of a social media user, based on the Agent role attributes, a network behavior model of an Agent group is built through a computer-aided technology, a personalized social life is built according to different social identities, interests, rest time, behavior habits, network liveness and the like, meanwhile, according to a social circle of a target public, the Agent group is controlled to be oriented to form friends with a designated area or industry netizen, an area or industry forum, a live broadcast channel and a social group are added, key media accounts and opinion leader accounts in a specific field are concerned, and the Agent group is automatically controlled to perform daily social action behaviors such as approval, comment and forwarding by utilizing a plurality of social propagation capacity modeling modes such as copying and accompanying. The replication mode means that the Agent role imitates the behavior habit of a target group user, and an interest topic carries out a series of social actions; the accompanying mode refers to the fact that the Agent role conducts approval, comment and forwarding on social operations of users of the target group, and therefore deep interaction with the target is achieved.
The specific process of Agent social communication ability modeling is divided into a human modeling stage and a behavior modeling stage, as shown in fig. 9. (1) A person-set modeling stage: aiming at different platform characteristics, the Agent is designed with periodic human design and modeling activities, including basic information completion classes and daily behavior activity classes. The basic information completion type simulates the archive information externally disclosed by the Agent of a target user, namely the supplement of the basic information of the role and the effect evaluation aiming at the industry fieldAnd the related information of the domain, such as work units, hobbies, residence places and the like. The daily behavior activity simulates the operation behavior habits of target users in different stages, such as the social user browsing peak period, the number of posts per day, the number of friends added each time and other personified behavior traits. (2) A behavior modeling stage: and aiming at the social relationship graph of a target user in the industry field of effect evaluation, searching and adding target friends, adding professional groups, paying attention to opinion leaders, participating in hot topic interaction and the like to carry out socialized behavior modeling. After the social communication capability of the account is modeled, the account becomes an Agent role with field representativeness, the Agent role receives information and performs data collection, and information transmission is evaluated from three dimensions of information transmission breadth, transmission depth and audience interaction degree (secondary indexes) (primary indexes), wherein a specific evaluation index system is shown in fig. 10. The account influence refers to the social media influence of an Agent receiving an information source account/a public homepage/a group, and for a specific target, crawling and calculating the influence of information released by the target in the last week (weighted calculation of fan number and average praise, comment and forwarding number of single information) and normalizing to obtain the account influence x0∈[0，1]And the account influence is used for calculating a plurality of three-level indexes. The three-level index specification and calculation method comprises the following steps:
the touching user group refers to the number of areas or industries involved in target subject information transmission, and information transmission number x is obtained by collecting and counting information of each area or industry Agent and carrying out normalization processing1∈[0，1](ii) a The propagation quantity refers to the total quantity of the relevant information of each platform, and x is obtained by crawling the information of the relevant information of the theme on each platform and performing weighting processing2′＝∑x0Wherein x is0Account number influence. Obtaining information propagation quantity x through normalization processing2∈[0，1](ii) a The information diffusion speed refers to the maximum value of the number of the related information of each platform theme in the propagation time, and the information diffusion speed x is obtained through normalization processing3∈[0，1](ii) a The propagation time refers to the duration of time that the information diffusion speed is higher than a minimum threshold value (generated by expert evaluation and other methods), and the propagation time x is obtained through normalization processing4∈[0，1](ii) a Overlay platform finger messagingSum of the platform influences contained in the source, overlay platform x5＝∑piWherein p isiFor the impact weight of each platform (calculated from the user statistics), when the total number of platforms is n,
the number of covered users refers to users with information contactable, and because the contact of different propagation ways with the users is repeated, the number of covered users x is obtained by calculating the sum of the Agent representative group number of the contact related information and performing normalization processing6∈[0，1](ii) a The propagation media type refers to a message propagation form, and the propagation media type x7＝∑miWherein m isiWeights for propagation forms of text, images, video, etc. (generated by expert evaluation, etc.), when the total number of propagation forms is n,
the content attaching degree refers to the correlation degree of the transmission information and the target subject, the correlation degree of each piece of information and the subject is calculated in the modes of keyword matching and the like, and x is obtained8′＝∑ciWherein c isi∈[0，1]The relevance of a single posting text and a theme is obtained through normalization processing to obtain the content posting degree x8∈[0，1](ii) a The number of user participating themes with the influence of touching the key user in the target field exceeding a set threshold is obtained, and x is obtained9′＝∑x0Wherein x is0Obtaining touch key users x through normalization processing for account influence9∈[0，1](ii) a The touch key organization refers to the number of target areas or industries (specified by a user) participating in the topic discussion, and the touch key organization x is obtained by collecting statistics and carrying out normalization processing on the information of each area or industry Agent10∈[0，1](ii) a The secondary propagation diffusion refers to the number of times of secondary propagation of information, and secondary propagation diffusion x is obtained by counting the forwarding number of the information and performing normalization processing11∈[0，1](ii) a The domain popularity is subjected to normalization by weighting and counting the data of the propagation quantity, praise, forwarding, comment, share and the like before normalization of the topics in the target area or industryThen, the domain heat x is obtained12∈[0，1](ii) a The direct interaction condition is obtained by weighting and calculating praise, comment and reply number under the postscript, and normalization processing is carried out to obtain a direct interaction condition x13∈[0，1](ii) a Calculating the evaluation result of the sub-topic of the derived topic situation, and normalizing to obtain a derived topic situation x14∈[0，1](ii) a The viewpoint tendency is the emotional tendency when the user comments and forwards topic information, and the emotional tendency e of the single text is calculated through a preset emotional discrimination modeliThen, the viewpoint before normalization tends to be x15′＝∑eiNormalization processing to obtain the viewpoint tendency x15∈[0，1](ii) a The topic popularity is obtained by counting the number of topic related searches of the user on different platforms. Using the keywords as statistical objects, scientifically analyzing and calculating the weight of the search frequency of each keyword in each platform search, normalizing the topic heat per unit time in the transmission time to obtain normalized topic heat x16∈[0，1]. The invention adopts a fuzzy comprehensive evaluation method to determine each three-level index xiA weight value of (i ═ 1, 2.., 16). Taking three-level index as factor set F ═ x1，x2，...，xnAnd generating a comment set C ═ C by expert assessment or other methods1，c2，...，cmIn which c isi＝{ri1，ri2，...，rin}TThen F ℃ ═ Σ aiObtaining the value of the secondary index (wherein a)i＝xi*ci) And finally obtaining an information propagation effect E: e ═ KR*R+KD*D+KII, wherein KS+KD+KF1 is the weight of three secondary indexes, R is the propagation extent of the information, D is the propagation depth of the information, and I is the audience interaction degree of the information.
(3) Agent network Agent unit: according to the network access requirement of a target social platform, the living habits of target agents, regional settings and the like, network Agent links meeting the social platform rules and the regional characteristics of target people are provided, and the network Agent links comprise a localization link and a cloud link.
(4) The Agent media communication unit: according to the operation configuration requirement of a target social platform and the setting of target agents, a mobile terminal Agent bearing platform meeting the social platform rules and the characteristics of target people such as language and position is provided, and the method comprises the steps of controlling the agents through a wired USB mode group, controlling the agents through a wireless WiFi mode group or installing cloud control software at a mobile terminal to realize the control of the agents through an internet cloud group and the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.
Claims (10)
1. The Agent-based mobile terminal social media propagation effect evaluation method is characterized by comprising the following steps of:
the method comprises the steps that firstly, a data acquisition Agent is preset on a social platform, and Agent social identity model modeling, Agent media interaction behavior modeling, Agent social communication transmission capacity improvement, Agent social media data acquisition and social media transmission effect evaluation are achieved;
secondly, directionally and accurately sampling and intelligently analyzing social media propagation data;
and step three, evaluating the effect of social media information propagation in the netizens.
2. The Agent-based mobile terminal social media propagation effect evaluation method is characterized in that the Agent social identity model is modeled, group portraits are carried out according to target people for government and enterprise information popularization, an Agent projection model of the target people on the social media is constructed, identity archives are automatically generated for the agents in batches, directionally, accurately and comprehensively, and the social identity model of the target people is highly restored by multi-dimensional information of gender, age, region of the target people, professional field, hobbies, income level and education degree.
3. The Agent-based mobile terminal social media propagation effect evaluation method of claim 1, wherein the Agent media interaction behavior modeling is implemented by creating Agent accounts on a plurality of associated social media platforms by using a social identity model, constructing a network behavior model of an Agent group through a computer-assisted technology according to a network behavior rule of a social media user, constructing a personified social life according to social identity, rest time, behavior habits and network activity of the model, and automatically controlling the Agent group to perform daily social action behaviors of praise, comment and forward.
4. The Agent-based mobile terminal social media propagation effect evaluation method according to claim 1, wherein the Agent social propagation capability improvement is that according to a social circle of a target public, an Agent group is controlled to orient and establish a friend relationship with a specified area or industry netizen, an area or industry forum, a live channel and a social group are added, a key media account and an opinion leader account are focused, and a preset human setting image of the Agent group on a social media platform is shaped by using a copying and accompanying capability improvement mode.
5. The Agent-based mobile terminal social media propagation effect evaluation method according to claim 1, wherein the Agent social media data collection is implemented by accessing a social media platform in an authorized manner by using a preset multi-platform Agent account group, actively collecting social platform interaction information, instant messaging information and social group information related to a target group netizen, and passively acquiring media information which is recommended by the social media platform through an intelligent algorithm and conforms to the Agent setting.
6. The Agent-based mobile terminal social media propagation effect evaluation method according to claim 1, wherein the social media propagation effect evaluation is a propagation effect evaluation algorithm formed according to information propagation extent, information propagation depth and audience interaction degree of the delivered information on the target social platform; and adjusting the external Agent identity model, the behavior model and the social circle parameter input by a machine learning method, and performing optimization iteration on the propagation effect evaluation algorithm.
7. A system for realizing the Agent-based mobile terminal social media propagation effect evaluation method according to any one of claims 1 to 6, wherein the Agent-based mobile terminal social media propagation effect evaluation system comprises:
the Agent role generation unit extracts Agent role metadata through analyzing the user characteristics of the social platform, generates corresponding Agent role information in batches through an Agent role knowledge graph model aiming at the role characteristics obtained by the network citizen portrait of the target group, and realizes automatic registration and identity verification of the target platform, wherein each Agent role is the projection of the network citizen of the target group in a network space;
the Agent scheduling and evaluating unit is used for constructing a network behavior model of an Agent group through a computer-assisted technology according to a network behavior rule of a social media user and on the basis of Agent role attributes, establishing a personified social life according to different social identities, interests and hobbies, rest time, behavior habits and network liveness, controlling the Agent group to orient to form friends with a designated area or industry netizen according to a social circle of a target public, adding the area or industry discussion area, a live broadcast channel and a social group, paying attention to key media accounts and opinion leader accounts, and automatically controlling the Agent group to perform daily praise, comment and forward social action by copying and accompanying with a plurality of social propagation capacity modeling modes;
the Agent network Agent unit is used for providing a network Agent link meeting the social platform rule and the target person regional characteristics according to the network access requirement of the target social platform and the target Agent living habit and regional setting;
the Agent media communication unit provides a mobile terminal Agent bearing platform meeting social platform rules and target person set language and position characteristics according to the operation configuration requirements of a target social platform and target person set settings, and comprises a group control Agent in a wired USB mode and a group control Agent in a wireless WiFi mode or a cloud control software installed at a mobile terminal to realize the group control Agent through the Internet cloud.
8. The Agent-based mobile-end social media propagation effect evaluation system according to claim 7, wherein the Agent social propagation capability modeling comprises: a human setting modeling stage and a behavior modeling stage;
the human modeling stage is used for designing periodic human modeling activities for the Agent according to different platform characteristics; and in the behavior modeling stage, aiming at a social relation graph of a target user in the industry field of effect evaluation, searching and adding target friends, adding professional groups, paying attention to opinion leaders and participating in hot topic interaction to perform social behavior modeling.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the Agent-based mobile-side social media propagation effect evaluation method according to any one of claims 1 to 6 when the computer program product is executed on an electronic device.
10. An information data processing terminal, characterized in that the information data processing terminal comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor, so that the processor executes the Agent-based mobile terminal social media propagation effect evaluation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110694811.6A CN113343149A (en) | 2021-06-22 | 2021-06-22 | Agent-based mobile terminal social media propagation effect evaluation method, system and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110694811.6A CN113343149A (en) | 2021-06-22 | 2021-06-22 | Agent-based mobile terminal social media propagation effect evaluation method, system and application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113343149A true CN113343149A (en) | 2021-09-03 |
Family
ID=77477661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110694811.6A Pending CN113343149A (en) | 2021-06-22 | 2021-06-22 | Agent-based mobile terminal social media propagation effect evaluation method, system and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343149A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079884A (en) * | 2022-06-29 | 2022-09-20 | 北京字跳网络技术有限公司 | Session message display method, device, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110125826A1 (en) * | 2009-11-20 | 2011-05-26 | Avaya Inc. | Stalking social media users to maximize the likelihood of immediate engagement |
| CN102223393A (en) * | 2010-04-16 | 2011-10-19 | 英特尔公司 | Methods and systems for relationship characterization and utilization from a user's social networks |
| CN102254265A (en) * | 2010-05-18 | 2011-11-23 | 北京首家通信技术有限公司 | Rich media internet advertisement content matching and effect evaluation method |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN109064347A (en) * | 2017-06-11 | 2018-12-21 | 南京理工大学 | Information based on multiple agent is propagated and public sentiment evolution simulation method |
| CN111562972A (en) * | 2020-04-24 | 2020-08-21 | 西北工业大学 | Ubiquitous operating system for crowd sensing |
| CN112000929A (en) * | 2020-07-29 | 2020-11-27 | 广州智城科技有限公司 | Cross-platform data analysis method, system, equipment and readable storage medium |
| CN112364468A (en) * | 2020-11-04 | 2021-02-12 | 昆明理工大学 | Corruption propagation model modeling simulation method based on agent social circle network |
| CN112598468A (en) * | 2020-12-23 | 2021-04-02 | 浙江省产品质量安全科学研究院 | Method for evaluating consumer goods public opinion internet influence index |
| CN112686765A (en) * | 2020-12-09 | 2021-04-20 | 天津大学 | Information propagation rule mining method based on social network |
-
2021
- 2021-06-22 CN CN202110694811.6A patent/CN113343149A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110125826A1 (en) * | 2009-11-20 | 2011-05-26 | Avaya Inc. | Stalking social media users to maximize the likelihood of immediate engagement |
| CN102223393A (en) * | 2010-04-16 | 2011-10-19 | 英特尔公司 | Methods and systems for relationship characterization and utilization from a user's social networks |
| CN102254265A (en) * | 2010-05-18 | 2011-11-23 | 北京首家通信技术有限公司 | Rich media internet advertisement content matching and effect evaluation method |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN109064347A (en) * | 2017-06-11 | 2018-12-21 | 南京理工大学 | Information based on multiple agent is propagated and public sentiment evolution simulation method |
| CN111562972A (en) * | 2020-04-24 | 2020-08-21 | 西北工业大学 | Ubiquitous operating system for crowd sensing |
| CN112000929A (en) * | 2020-07-29 | 2020-11-27 | 广州智城科技有限公司 | Cross-platform data analysis method, system, equipment and readable storage medium |
| CN112364468A (en) * | 2020-11-04 | 2021-02-12 | 昆明理工大学 | Corruption propagation model modeling simulation method based on agent social circle network |
| CN112686765A (en) * | 2020-12-09 | 2021-04-20 | 天津大学 | Information propagation rule mining method based on social network |
| CN112598468A (en) * | 2020-12-23 | 2021-04-02 | 浙江省产品质量安全科学研究院 | Method for evaluating consumer goods public opinion internet influence index |
Non-Patent Citations (3)
| Title |
|---|
| 于卫红: "基于多Agent的高校网络舆情监测与分析系统", 现代情报, 15 October 2017 (2017-10-15), pages 53 - 57 * |
| 吴鹏;王夏婷;金贝贝;: "基于BDI-Agent模型的网民集群行为建模研究", 情报理论与实践, no. 04, 19 November 2018 (2018-11-19), pages 140 - 148140 * |
| 陈帅: "基于SEIR的双层社交网络舆情传播研究", 情报探索, 15 September 2020 (2020-09-15), pages 30 - 35 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079884A (en) * | 2022-06-29 | 2022-09-20 | 北京字跳网络技术有限公司 | Session message display method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11100411B2 (en) | Predicting influence in social networks | |
| Nie et al. | Data-driven answer selection in community QA systems | |
| Fogués et al. | BFF: A tool for eliciting tie strength and user communities in social networking services | |
| Silva et al. | A methodology for community detection in Twitter | |
| CN107958317A (en) | A kind of method and apparatus that crowdsourcing participant is chosen in crowdsourcing project | |
| CN112104642B (en) | Abnormal account number determination method and related device | |
| CN111885399A (en) | Content distribution method, content distribution device, electronic equipment and storage medium | |
| CN112765480A (en) | Information pushing method and device and computer readable storage medium | |
| Chamberlain | Groupsourcing: Distributed problem solving using social networks | |
| Wang | Analysis of students’ behavior in english online education based on data mining | |
| CN113343149A (en) | Agent-based mobile terminal social media propagation effect evaluation method, system and application | |
| Yashkina et al. | Artificial intelligence in mobile marketing: conditions, obstacles and prospects of using | |
| Soulier et al. | MineRank: Leveraging users’ latent roles for unsupervised collaborative information retrieval | |
| Synko | The method of trust level of publications hosted in virtual communities | |
| Khazaei et al. | Detecting privacy preferences from online social footprints: A literature review | |
| Lee et al. | Coherence analysis of research and education using topic modeling | |
| Cui et al. | Perceiving group themes from collective social and behavioral information | |
| Shi et al. | Identifying Impact Factors of Question Quality in Online Health Q&A Communities: an Empirical Analysis on MedHelp. | |
| Liu et al. | Small Data Fusion Algorithm for Personalized Library Recommendations | |
| Hong et al. | Contextual keyword extraction by building sentences with crowdsourcing | |
| Zhang et al. | Post classification and recommendation for an online smoking cessation community | |
| Zhang et al. | LLM-Driven Agents for Influencer Selection in Digital Advertising Campaigns | |
| Wang et al. | Group Behavior Prediction and Evolution in Social Networks | |
| Longo et al. | A context-aware approach based on self-organizing maps to study web-users' tendencies from their behaviour | |
| CN116108285A (en) | Network water army user and behavior detection method based on dynamic low-rank matrix decomposition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |