CN109327488B - Network information pushing method and device and server - Google Patents
Network information pushing method and device and server Download PDFInfo
- Publication number
- CN109327488B CN109327488B CN201710643388.0A CN201710643388A CN109327488B CN 109327488 B CN109327488 B CN 109327488B CN 201710643388 A CN201710643388 A CN 201710643388A CN 109327488 B CN109327488 B CN 109327488B
- Authority
- CN
- China
- Prior art keywords
- network
- rumor
- network information
- users
- information
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a network information pushing method, a device and a server, wherein the method divides each network user in advance, divides the network users with larger network rumor easy to forward into a first group, when the probability score of the network information pushed by the server to the network rumor is greater than or equal to the first preset score, prohibiting the network information from being pushed to network users belonging to the first group among the planned promotion users, so that the network users who easily forward the network rumor cannot see the network information, namely, the network users belonging to the first group of the planned promotion users are all shielded from the network information, in real life, the network users easy to spread the network rumors generally belong to the first group, since the network users belonging to the first group cannot view the network information of the network rumor to a large extent at all, the dissemination of the network information which may be the network rumor is effectively controlled.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a network information pushing method, an apparatus, and a server.
Background
Network rumors refer to utterances with no factual basis of aggressiveness and pertinence that are propagated through network media (e.g., web forums, social networking sites, chat software, etc.). Mainly relates to emergencies, public domains, celebrities, subversion traitors, traitors and the like. Rumor propagation is sudden and very fast, and thus tends to adversely affect normal social order. The concept of stealing and exchanging is general with the bias, and the food rumors are too much to prevent; it is rather convinced that it has or not, and the psychology of people accelerates the spread.
Therefore, how to control the propagation of the network rumors is a technical difficulty and a point in the field.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and a server for pushing network information, so as to overcome the problem of controlling the propagation of network rumors in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
a network information pushing method is applied to a server and comprises the following steps:
acquiring network information and a planned promotion user to which the network information is to be pushed;
acquiring a probability score of the network rumor of the network information;
obtaining a first pre-divided group, wherein the degree of network rumors easily forwarded by network users belonging to the first group is greater than the degree of network rumors easily forwarded by network users not belonging to the first group;
and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
A network information pushing apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring network information and a planned promotion user to which the network information is to be pushed;
the second acquisition module is used for acquiring the probability score of the network rumor of the network information;
a third obtaining module, configured to obtain a first pre-divided group, where a degree to which network users belonging to the first group easily forward a network rumor is greater than a degree to which network users not belonging to the first group easily forward a network rumor;
and the forbidding module is used for forbidding to push the network information to the network users belonging to the first group in the plan popularization users when the possibility score is larger than or equal to a first preset score.
A server, comprising:
a memory for storing a program;
the processor is configured to execute the program, and the program is specifically configured to:
acquiring network information and a planned promotion user to which the network information is to be pushed;
acquiring a probability score of the network rumor of the network information;
obtaining a first pre-divided group, wherein the degree of network rumors easily forwarded by network users belonging to the first group is greater than the degree of network rumors easily forwarded by network users not belonging to the first group;
and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
It can be known from the foregoing technical solutions that, compared with the prior art, in the network information pushing method provided in the embodiments of the present invention, each network user is divided in advance, the network users with a greater degree of network rumors easy to forward are divided into a first group, when the probability score of the network information pushed by the server for a network rumor is greater than or equal to a first preset score, the network information is prohibited from being pushed to the network users belonging to the first group among the planned popularization users, so that the network users easy to forward a network rumor cannot see the network information, that is, the network users belonging to the first group among the planned popularization users shield the network information, in real life, the network users easy to propagate a network rumor generally belong to the first group, because the network users belonging to the first group cannot view the network information of the network rumors at all, therefore, the propagation of network information which may be a network rumor is effectively controlled.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic diagram of a server implementing a network information pushing process according to an embodiment of the present invention;
fig. 2 is another schematic diagram of a process for implementing network information push by a server according to an embodiment of the present invention;
fig. 3 is a flowchart of a network information pushing method according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for obtaining a probability score of a network rumor according to the network information pushing method of the present invention;
fig. 5 is a schematic diagram illustrating a process of obtaining a likelihood score according to a keyword list and network information according to an embodiment of the present invention;
fig. 6 is an architecture diagram of an application of the network information pushing method according to the embodiment of the present invention;
fig. 7 is an architecture diagram of an application of the network information pushing method according to the embodiment of the present invention;
fig. 8 is a block diagram of a server according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Currently, network users can be exposed to network rumors in several application scenarios.
In the first application scenario, the server pushes the data uniformly.
For example, a news server and a news client, the server will push the network information to each client after receiving the network information. The network user can view the network rumor through the client.
And in the second application scenario, friend sharing.
For example, a network user may contact a network rumor by a friend circle or group where the friends may share in the group (e.g., a friend circle or a public number or group, such as a QQ group, a WeChat group, etc.). Merchants may share the network rumor on public numbers that network users who are interested in the public numbers may be exposed to.
After the network users contact the network rumor, if the network rumor is trusted, the phenomenon of reloading the network rumor may occur, increasing the possibility that more network users contact the network rumor.
In summary, in order to effectively control the propagation of the network rumor, it is critical to prevent the network users who are easy to believe the network rumor from contacting the network rumor. Therefore, the embodiment of the invention provides a network information pushing method. The method is described below with reference to the above two application scenarios.
For the first application scenario, the server may divide the network users already registered in the server in advance, specifically, as shown in fig. 1, the server 11 divides the network users with a greater degree of easy-to-forward network rumors into a first group 1, divides the network users with a lesser degree of easy-to-forward network rumors into a third group 2, when the server 11 wants to push network information, the server may obtain a probability score that the network information is the network rumors, and if the probability score is greater than or equal to a first preset score, the probability that the network information is the network rumors is great, at this time, when the server 11 promotes the network information, the server may prohibit pushing the network information to the network users belonging to the first group 1 among the network users already registered in the server, that is, prohibit pushing the network information to all the network users included in the first group 1, may prohibit pushing the network users not belonging to the first group among the network users already registered in the server, i.e. the network users comprised by the third group 2 push the network information.
Preferably, the network users registered in the server 11 are the network users included in the first group 1 and the network users included in the third group 2, and the server 11 divides the network users registered into the first group 1 and the third group 2.
For a second application scenario, referring to fig. 2, it is assumed that the network user 21 needs to share the network information to the second group 3, and if the second group 3 is a wechat friend circle, the network user 21 wants to share the network information to all friends in the wechat friend circle; if the second group 3 is a group of QQ, the network user 21 wants to share the network information to all members of the group; if the second group 3 is a public number, the network user 21 wants to share the network information to all network users who concern the public number; since the network users registered in the server 11 are divided, that is, the first group 1 and the third group 2 are divided, it is possible to determine which network users 31 belong to the first group 1 from the network users included in the second group 3, and if the probability score of the network information being a network rumor is greater than or equal to the first preset score, the network users 31 belonging to the first group 1 in the second group 3 may be prohibited from transmitting the network information. The network information may be sent to the network users 32 of the second group 3 belonging to the third group 2.
With reference to the two application scenarios, a flow of the network information pushing method provided by the embodiment of the present invention may be shown in fig. 3, where the method includes:
step S301: and acquiring network information and a planned promotion user to which the network information is to be pushed.
For the first application scenario, the scheduled push user may be all network users registered in the server, and the network information refers to network information to be pushed by the server.
For a second application scenario, the plan push user may share all network users included in the second group for the network users, and the network information is network information to be shared by the network users.
Step S302: and acquiring the probability score of the network information being the network rumor.
Step S303: a pre-partitioned first population is obtained.
The network users belonging to the first group are liable to forward the network rumor to a greater extent than the network users not belonging to the first group.
The server may divide all the network users that have been registered in advance, and may divide all the network users into two groups, i.e., a first group and a third group. Preferably, the network rumors may be divided based on the number of times each network user reprints the network rumors, for example, the total number of times the network users belonging to the first group reprint the network rumors is greater than the total number of times the network users belonging to the third group reprints the network rumors; or, the average number of times that the network users belonging to the first population reprint the network rumor is greater than the average number of times that the network users belonging to the third population reprint the network rumor; or, the education levels of the network users belonging to the first group are all lower than the education levels of the network users belonging to the third group; or, the easy-to-signal rumor score of the network users belonging to the first group is greater than the easy-to-signal rumor score of the network users belonging to the third group, wherein the easy-to-signal rumor score can be calculated based on user characteristics such as the network users' network rumor number of times of transferring, education level and age.
Step S304: and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
For a first application scenario, "prohibit pushing the network information to the network users belonging to the first group among the planned popularization users," means prohibit pushing the network information to all the network users belonging to the first group; for the second application scenario, "prohibit pushing the network information to the network users belonging to the first group in the planned popularization users," means prohibit pushing the network information to the network users belonging to the first group in the second group.
In the network information push method provided by the embodiment of the invention, each network user is divided in advance, the network users with larger degree of network rumors easy to forward are divided into a first group, when the probability score of the network information pushed by the server to the network rumor is greater than or equal to the first preset score, prohibiting the network information from being pushed to network users belonging to the first group among the planned promotion users, so that the network users who easily forward the network rumor cannot see the network information, namely, the network users belonging to the first group of the planned promotion users are all shielded from the network information, in real life, the network users easy to spread the network rumors generally belong to the first group, since the network users belonging to the first group cannot view the network information of the network rumor to a large extent at all, the dissemination of the network information which may be the network rumor is effectively controlled.
In a first application scenario, if the server performs steps S301 to S304 for each new network information at an initial stage of network information popularization, the network users belonging to the first group cannot view the network information from the client (e.g., news client), and the embodiment of the present invention can control the propagation of network rumors from the source (the initial stage of network information push by the server); in the second application scenario, if the server has already pushed the network information or pushed the network information to the network users belonging to the third group, when the network users belonging to the third group share the network information, the server may also shield the network users belonging to the first group from among the friends of the network users from seeing the network information, thereby controlling the propagation of the network rumor in the process of the network users sharing the network rumor.
In the first application scenario, when the server populates the network information, any network information newly added to the server may be executed in steps S301 to S304. In this way, the propagation of the network rumor can be controlled from the most source, because the network information does not have any capacity, and no network user sees the network information, so that the network user belonging to the first group does not see the network information at all in the process of network propagation. But the data processing amount of the server is greatly increased because a large amount of new network information is generated every day.
To solve this problem, network information whose amount of transshipment is greater than or equal to the threshold amount of transshipment may be used as the network information in step S301. After performing steps S301 to S304, the server may mask all network users belonging to the first group, but before this, since the network information already has a certain amount of forwarding, the network users belonging to the first group may have already viewed the network information in the process.
In the second application scenario, when the server receives an instruction of the network user to share the network information, the server may perform steps S301 to S304 on each network information shared by each network user, and the advantages and disadvantages are the same as those in the first application scenario; the server may record a transfer amount of each network information, and when receiving an instruction from a network user to share the network information, the server may first determine the transfer amount of the network information, and if the transfer amount is greater than or equal to a transfer amount threshold, perform steps S301 to S304 on the network information.
In the embodiments of the present invention, there are various methods for obtaining the network information as the probability score of the network rumor, and the embodiments of the present invention provide, but are not limited to, the following methods.
First, a probability score for obtaining the network information as a network rumor is shown in fig. 4, the method includes:
step S401: and matching the keywords contained in the network information with the keywords corresponding to the previously stored rumor categories respectively to obtain the probability scores of the network information in the rumor categories.
Step S401 may include: extracting keywords contained in the network information from the network information; and matching the keywords contained in the network information with the keywords corresponding to the previously stored rumor categories. Or, step S401 may include: and determining the number of keywords corresponding to each rumor category in the content contained in the network information.
The rumor categories of network rumors can be divided into: finance, sports, entertainment, automotive, political, scientific, military, historical, etc. rumor categories. The category of the network rumors may be divided into other categories, and the category of the rumors into which the network rumors are divided may be determined according to the actual situation, which is not limited herein.
Assume that the previously stored rumor categories include category a rumors, category B rumors, and category C rumors; suppose that keywords corresponding to category a rumors include a1, a2, A3, … AM; keywords corresponding to category B rumors include: b1, B2, B3, … BN; keywords corresponding to C-type rumors include: c1, C2, C3, … CQ; the previously stored categories of rumors may be stored in a table to form a keyword list. Wherein M, N and Q are positive integers greater than or equal to 1, and the size of M, N, Q is related to the total number of keywords contained in the corresponding rumor category.
The keywords included in the network information may be compared with the keywords corresponding to each category of rumors, and if the keywords included in the network information match the keywords of category a, which are M1, the probability score of the network information belonging to category a may be M1/M100; assuming that the number of keywords included in the network information matches N1 keywords of the category B rumors, the probability score of the network information belonging to the category B rumors may be SB 1/N100; assuming that the network information includes a total of Q1 keywords matching with the category C rumors, the probability score of the network information belonging to the category C rumors may be SC-Q1/Q100.
The process of pre-storing the keywords corresponding to the respective rumor categories includes:
dividing each network rumor into different rumor categories based on the matching degree of keywords contained in each network rumor; the keywords corresponding to the network rumors included in each rumor category are determined as the keywords corresponding to each rumor category.
Network rumors that have been historically identified may be classified into different rumor categories by text clustering. Respective rumor categories were obtained.
Text clustering (Text clustering) document clustering is mainly based on well-known clustering assumptions: the similarity of documents of the same class is larger, and the similarity of documents of different classes is smaller. As an unsupervised machine learning method, clustering does not need a training process and does not need to manually label categories of documents in advance, so that the method has certain flexibility and higher automatic processing capability, becomes an important means for effectively organizing, abstracting and navigating text information, and is concerned by more and more researchers.
Keywords may also be extracted from historically confirmed network rumors. And determining the network information with higher keyword coincidence degree as a rumor category.
After the rumor categories are determined, the nouns and verbs with higher occurrence frequency in the network rumors included in each rumor category can be counted, so as to obtain the corresponding keywords of each rumor category.
Step S402: and determining the maximum possibility score in the possibility scores corresponding to the rumor categories as the possibility score of the network information.
Fig. 5 shows a process of obtaining the probability score according to the keyword list and the network information, in which the network information 51 in fig. 5 is respectively matched with the respective rumors in the keyword list 52 to obtain the probability scores of the network information being the respective rumors, such as SA, SB, and SC, and assuming that SC is greater than SB and SA, the probability score of the network information is determined to be SC.
Assuming that 70 keywords in the network information are the same as 70 keywords of the C-type rumors, and the C-type rumors include 100 keywords in total, the probability score SC of the network information is 70.
It is understood that, if the network information is determined to be a network rumor, the keywords corresponding to the network information may be updated to the keywords corresponding to the category of the rumor, so that the server can continuously identify new network rumors. The specific method comprises the following steps:
determining the rumor category corresponding to the maximum likelihood score as the rumor category to which the network information belongs;
and updating the keywords corresponding to the rumor category to which the network information belongs according to the keywords corresponding to the network information.
Second, obtaining the probability score of the network information as the network rumor comprises:
analyzing a network user sharing network information, for example, whether the network user reloads a network rumor, and if so, acquiring the network rumor reloading times T of the network user; whether the network user actively releases the network rumor or not is judged, and if the network user actively releases the network rumor, the network rumor releasing times S of the network user is obtained.
And analyzing the audience of the network information, wherein the network users share the ratio R of the number of the network users belonging to the first group to the number of the network users not belonging to the first group in the second group of the network information.
The network information itself is analyzed to obtain the matching degree U (i.e., the probability score in the first method) between the keywords included in the network information and the keywords corresponding to each rumor category.
Combining the three analysis results, the probability score of the network rumor is determined. The specific formula may be as follows:
the probability score is P1 × S + P2 × T + P3 × R + P4 × U, where P1, P2, P3, and P4 are weights and may be set according to actual situations. The network rumors that have been determined historically may also be input into the classifier using a machine learning method to obtain P1, P2, P3, and P4.
The process of pre-dividing the first group in the embodiment of the invention comprises the following steps:
respectively determining easy-to-believe rumor scores of the network users according to the user characteristics of the network users, wherein the easy-to-believe rumor scores are used for representing the possibility that the network users believe the rumors; dividing the network users with the easy-to-signal rumor scores larger than or equal to a second preset score into the first group.
Optionally, the network users with the easy-to-signal rumor scores smaller than the second preset score are divided into a second group.
Wherein, the user characteristics may include: network rumor behavior and basic information, wherein the network rumor behavior comprises: forwarding network rumors and/or number of rumors released; the basic information includes: one or more of head portrait, gender, province city of the country to which the user belongs, age of the user, and education level.
Optionally, the easy-to-signal rumor score of each network user is W1 network rumor behavior + W2 basic information, where W1 and W2 are weights, and the specific values may be determined according to actual situations.
In a preferred embodiment, the easy-to-signal rumor score for each network user is W11 forwarded rumors + W12 published rumors + W21 educated + W22 age.
Wherein, W11+ W12 ═ W1; w21+ W22 ═ W2.
There are various methods for acquiring the network rumor behavior and basic information of each network user, and the embodiments of the present invention provide, but are not limited to, the following methods.
First, the server 11 in the embodiment of the present invention is a related server to which a client related to a login account used by the network user to log in the server 11 belongs.
The following illustrates an example of a "association server to which a client associated with a login account belongs", where if the login account is a wechat account, the client associated with the wechat account is a wechat client, the association server to which the wechat client belongs is a wechat server, and at this time, the server 11 is a wechat server; if the login account is a QQ account, the client associated with the WeChat account is a QQ client, the associated server to which the QQ client belongs is a QQ server, and the server 11 is a QQ server.
The network users can register through the clients, and the associated server to which the clients belong can store the data of the registered network users, such as the network rumor behaviors and the basic information of the network users.
Therefore, the server 11 can directly obtain the network rumor behavior and the basic information of each network user from the database storing the data of each network user registered in the server.
Secondly, the server 11 in the embodiment of the present invention is not a related server to which a client related to a login account used by the network user to log in the server 11 belongs.
To illustrate a second case, by way of example, if a login account used by a client of the user login server 11 is a WeChat account, the server 11 may be a news server, and a related server to which the client related to the WeChat account belongs is a WeChat server; if the login account used by the client of the user login server 11 is a QQ account, the server 11 may be a news server, and the association server to which the client associated with the QQ account belongs is a QQ server.
Since all data of the network users are stored in the wechat server or the QQ server, and do not exist in the server 11, the server 11 needs to obtain the network rumor behavior and the basic information of each network user from the associated server to which the client associated with the communication identifier of each network user belongs.
And the communication identifier is a login account of a client corresponding to the server for the network user to login.
Fig. 6 is a diagram illustrating an architecture applied to a network information pushing method according to an embodiment of the present invention.
It is assumed that the server 11 in the embodiment of the present invention is referred to as a first server 61; the server for acquiring and storing the network rumor behavior and the basic information of each network user is the second server 62; if the probability score of whether the network information is the network rumor is obtained as the third server 63, the relationship among the first server 61, the second server 62 and the third server 63 is shown in fig. 6.
The first server 61 may obtain the network rumor behavior and the basic information of each network user from the second server 62, and then calculate the easy-to-believe rumor score of each network user; or, the easy-to-signal rumor scores of the network users are directly obtained from the second server 62, and then the second server 62 can calculate the easy-to-signal rumor scores of the network users according to the network rumor behaviors and the basic information of the network users.
The first server 61 may obtain the probability score of the network information being the network rumor from the third server 63.
When the likelihood score is greater than or equal to the first preset score, the first server 61 prohibits the push of the network information to the network users belonging to the first group among the planned popularization users.
In different application scenarios, the first server 61, the second server 62, and the third server 63 may be the same server, for example, the first application scenario involved in the network rumor behavior of each network user and the basic information acquisition method. The first server 61 and the second server 62 may be independent servers, for example, the network rumor behaviors of the second network users and the application scenario involved in the basic information obtaining method.
The way for the server to acquire and store the network rumor behavior and the basic information of each network user may include:
the way of acquiring the age of each network user includes:
first, an identification number; the network user may bind the bank card with the client, and because the network user needs to input the identity card number in the process of binding the bank card, the age of the network user can be known according to the identity card number.
Second, average age of friends; the average of the ages of the friends of the network user is taken as the age of the network user.
Third, the client uses the average age of the population; the average age of each network user using the client is taken as the age of the network user.
Fourthly, if the head portrait is the network user, the age of the network user is identified by using the image identification function.
Fifthly, when registering, the network user inputs age; when the network user registers, the age of the network user may be input, and at this time, the age input by the network user may be determined as the age of the network user.
The way of acquiring the education level of each network user includes:
first, friends are grouped; the network user may group friends, such as "college classmates," "high school classmates," and so on, identify the names of the friend groups, and take the highest degree of education as the level of education of the network user.
Second, the learning of friends of the network user; and determining the highest or lowest academic calendar of friends of the network user as the education level of the network user.
And thirdly, determining the education degree of the network user according to the communication records of the network user and other friends and/or the network information shared by the network user.
Fourthly, the network user may input his/her graduation school when registering, and the education level of the network user is determined according to the graduation school filled by the user.
The way to acquire the network rumor behavior of the network user includes:
determining the number of the network rumors which are determined in the network information forwarded by the network users as the network rumor forwarding times;
and/or the presence of a gas in the gas,
and determining the number of the network rumors which are determined in the network information issued by the network users as the number of times of issuing the network rumors.
In a preferred embodiment, the easy-to-signal rumor scores for each network user may be calculated from the network rumor behavior, education level, and age.
It is understood that the easy-to-believe rumor score is positively correlated with age, network rumor behavior, and negatively correlated with academic history.
For example, if a person is very old (50 years), educated (elementary school) and historically has a large number of netrumors (10), his easy-to-signal rumor score L will be high. The formula may be as follows:
l ═ age (J1) + (J2 behavior of network rumors) — (J3 education degree)
Wherein J1, J2 and J3 are weights, which can be adjusted according to practical application scenarios. If the score L reaches a certain threshold (e.g., 70 points), then the user is considered to belong to a first group; otherwise, it belongs to the third population.
The embodiment of the invention also provides a network information pushing device corresponding to the network information pushing method, and the network information pushing device is explained below, wherein the network information pushing device comprises various modules. Each unit and each sub-unit correspond to a corresponding step in the network information pushing method, and therefore detailed description is omitted, and specific detailed description can refer to the description of the corresponding step in the network information pushing method.
As shown in fig. 7, a structure diagram of a network information pushing apparatus according to an embodiment of the present invention is provided, where the network information pushing apparatus includes:
a first obtaining module 71, configured to obtain network information and a planned promotion user to which the network information is to be pushed;
a second obtaining module 72, configured to obtain a probability score that the network information is a network rumor;
a third obtaining module 73, configured to obtain a first pre-divided group, where a degree to which network users belonging to the first group easily forward a network rumor is greater than a degree to which network users not belonging to the first group easily forward a network rumor;
a prohibiting module 74, configured to prohibit pushing the network information to the network user belonging to the first group in the planned popularization users when the possibility score is greater than or equal to a first preset score.
Optionally, the first obtaining module includes:
the first acquisition unit is used for acquiring network information to be shared to a second group by network users;
and the first determining unit is used for determining the network users contained in the second group as the planned popularization users.
Optionally, the first obtaining module includes:
the second acquisition unit is used for acquiring the network information to be promoted by the server;
and the second determining unit is used for determining the network user which is registered in the server as the planned popularization user.
Optionally, the second obtaining unit includes:
the first acquisition subunit is used for acquiring the network information of which the transfer amount is greater than or equal to a transfer amount threshold;
or the like, or, alternatively,
and the second acquisition subunit is used for acquiring the network information newly added to the server.
Optionally, the second obtaining module includes:
a third obtaining unit, configured to match keywords included in the network information with keywords corresponding to respective previously stored rumor categories, respectively, to obtain a probability score that the network information is of each rumor category;
a third determining unit, configured to determine a maximum likelihood score among likelihood scores corresponding to respective rumor categories as a likelihood score of the network information.
Optionally, the method further includes:
the first division module is used for dividing each network rumor into different rumor categories based on the matching degree of keywords contained in each network rumor;
the first determining module is used for determining the keywords corresponding to the network rumors included in each rumor category as the keywords corresponding to each rumor category.
Optionally, the method further includes:
a second determining module, configured to determine a rumor category corresponding to the maximum likelihood score as the rumor category to which the network information belongs;
and the updating module is used for updating the keywords corresponding to the rumor categories to which the network information belongs according to the keywords corresponding to the network information.
Optionally, the method further includes:
a third determining module, configured to determine, according to the user characteristics of each network user, an easy-to-believe rumor score of each network user, where the easy-to-believe rumor score is used to characterize a probability that the network user believes a rumor;
the second division module is used for dividing the network users with the easy-to-signal rumor scores larger than or equal to a second preset score into the first group.
Optionally, the third determining module includes:
a fourth obtaining unit, configured to obtain network rumor behaviors and basic information of each network user respectively;
and the computing unit is used for respectively computing the easy-to-believe rumor scores of the network users according to the preset weights respectively corresponding to the network rumor behaviors and the basic information and the network rumor behaviors and the basic information of the network users.
Optionally, the fourth obtaining unit includes:
a third obtaining subunit, configured to obtain, from a database in which data of each network user registered in the server is stored, a network rumor behavior and basic information of each network user, respectively;
or the like, or, alternatively,
and the fourth obtaining subunit is configured to obtain the network rumor behaviors and the basic information of each network user from an association server to which the client associated with the communication identifier of each network user belongs, where the communication identifier is a login account of the network user logging in the client corresponding to the server.
An embodiment of the present invention further provides a server, where a structure diagram of the server may be as shown in fig. 8, and the server includes:
a memory 81 for storing a program;
the program may include program code including computer operating instructions.
A processor 82 for executing the program.
The memory 81 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 82 may be a central processing unit CPU, or an application Specific Integrated circuit ASIC, or one or more Integrated circuits configured to implement embodiments of the present invention.
Wherein the program is specifically for:
acquiring network information and a planned promotion user to which the network information is to be pushed;
acquiring a probability score of the network rumor of the network information;
obtaining a first pre-divided group, wherein the degree of network rumors easily forwarded by network users belonging to the first group is greater than the degree of network rumors easily forwarded by network users not belonging to the first group;
and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
Optionally, the server may further include a communication bus 83 and a communication interface 84, wherein the memory 81, the processor 82, and the communication interface 84 complete communication with each other through the communication bus 83;
alternatively, the communication interface 84 may be an interface of a communication module, such as an interface of a GSM module.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (15)
1. A network information pushing method is applied to a server and comprises the following steps:
acquiring network information and a planned promotion user to which the network information is to be pushed;
acquiring a probability score of the network rumor of the network information;
obtaining a first pre-divided group, wherein the degree of network rumors easily forwarded by network users belonging to the first group is greater than the degree of network rumors easily forwarded by network users not belonging to the first group;
and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
2. The method according to claim 1, wherein the obtaining of the network information and the planned promotion user to which the network information is to be pushed comprises:
acquiring network information to be shared to a second group by network users;
and determining the network users included in the second group as the planned popularization users.
3. The method according to claim 1, wherein the obtaining of the network information and the planned promotion user to which the network information is to be pushed comprises:
acquiring network information to be promoted of the server;
and determining the network users registered in the server as the planned popularization users.
4. The method according to claim 3, wherein the obtaining the network information to be promoted by the server comprises:
acquiring network information of which the transfer amount is greater than or equal to a transfer amount threshold value;
or the like, or, alternatively,
and acquiring the network information newly added to the server.
5. The method of claim 1, wherein the obtaining the probability score of the network information being a network rumor comprises:
matching keywords contained in the network information with keywords corresponding to each previously stored rumor category respectively to obtain a probability score of the network information being each rumor category;
and determining the maximum possibility score in the possibility scores corresponding to the rumor categories as the possibility score of the network information.
6. The method of claim 5, wherein the pre-storing the keywords corresponding to the respective rumor categories comprises:
dividing each network rumor into different rumor categories based on the matching degree of keywords contained in each network rumor;
the keywords corresponding to the network rumors included in each rumor category are determined as the keywords corresponding to each rumor category.
7. The network information pushing method according to claim 6, further comprising:
determining the rumor category corresponding to the maximum likelihood score as the rumor category to which the network information belongs;
and updating the keywords corresponding to the rumor category to which the network information belongs according to the keywords corresponding to the network information.
8. The method according to claim 1, wherein the pre-dividing the first group comprises:
respectively determining easy-to-believe rumor scores of the network users according to the user characteristics of the network users, wherein the easy-to-believe rumor scores are used for representing the possibility that the network users believe the rumors;
dividing the network users with the easy-to-signal rumor scores larger than or equal to a second preset score into the first group.
9. The method of claim 8, wherein the determining the easy-to-signal rumor scores of the network users according to the user characteristics of the network users comprises:
respectively acquiring network rumor behaviors and basic information of each network user;
and respectively calculating the easy-to-signal rumor scores of the network users according to preset weights respectively corresponding to the network rumor behaviors and the basic information, and the network rumor behaviors and the basic information of the network users.
10. The method of claim 9, wherein the obtaining the network rumor behavior and the basic information of each network user respectively comprises:
respectively acquiring the network rumor behaviors and basic information of each network user from a database storing the data of each network user registered in the server;
or the like, or, alternatively,
respectively acquiring the network rumor behaviors and the basic information of each network user from an association server to which a client associated with the communication identifier of each network user belongs, wherein the communication identifier is a login account of the network user for logging in the client corresponding to the server.
11. A network information pushing apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring network information and a planned promotion user to which the network information is to be pushed;
the second acquisition module is used for acquiring the probability score of the network rumor of the network information;
a third obtaining module, configured to obtain a first pre-divided group, where a degree to which network users belonging to the first group easily forward a network rumor is greater than a degree to which network users not belonging to the first group easily forward a network rumor;
and the forbidding module is used for forbidding to push the network information to the network users belonging to the first group in the plan popularization users when the possibility score is larger than or equal to a first preset score.
12. The apparatus for pushing network information according to claim 11, wherein the first obtaining module comprises:
the first acquisition unit is used for acquiring network information to be shared to a second group by network users;
and the first determining unit is used for determining the network users contained in the second group as the planned popularization users.
13. The apparatus for pushing network information according to claim 11, wherein the first obtaining module comprises:
the second acquisition unit is used for acquiring the network information to be promoted by the server;
and the second determining unit is used for determining the network user which is registered in the server as the planned popularization user.
14. The apparatus for pushing network information according to claim 11, wherein the second obtaining module comprises:
a third obtaining unit, configured to match keywords included in the network information with keywords corresponding to respective previously stored rumor categories, respectively, to obtain a probability score that the network information is of each rumor category;
a third determining unit, configured to determine a maximum likelihood score among likelihood scores corresponding to respective rumor categories as a likelihood score of the network information.
15. A server, comprising:
a memory for storing a program;
the processor is configured to execute the program, which is specifically configured to:
acquiring network information and a planned promotion user to which the network information is to be pushed;
acquiring a probability score of the network rumor of the network information;
obtaining a first pre-divided group, wherein the degree of network rumors easily forwarded by network users belonging to the first group is greater than the degree of network rumors easily forwarded by network users not belonging to the first group;
and when the possibility score is larger than or equal to a first preset score, prohibiting the network information from being pushed to the network users belonging to the first group in the planned popularization users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710643388.0A CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710643388.0A CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109327488A CN109327488A (en) | 2019-02-12 |
| CN109327488B true CN109327488B (en) | 2021-08-13 |
Family
ID=65245111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710643388.0A Expired - Fee Related CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109327488B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291394B (en) * | 2020-01-31 | 2021-03-02 | 腾讯科技（深圳）有限公司 | False information management method, false information management device and storage medium |
| CN112417258A (en) * | 2020-12-02 | 2021-02-26 | 深圳市罗湖医院集团 | Crushing method, platform and terminal for rumor information in health knowledge search engine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902621A (en) * | 2012-12-28 | 2014-07-02 | 深圳先进技术研究院 | Method and device for identifying network rumor |
| CN104361231A (en) * | 2014-11-11 | 2015-02-18 | 电子科技大学 | Method for controlling rumor propagation in complicated network |
| CN105871700A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Message propagation method and server |
| CN106022856A (en) * | 2016-05-05 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Data display method and device |
-
2017
- 2017-07-31 CN CN201710643388.0A patent/CN109327488B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902621A (en) * | 2012-12-28 | 2014-07-02 | 深圳先进技术研究院 | Method and device for identifying network rumor |
| CN104361231A (en) * | 2014-11-11 | 2015-02-18 | 电子科技大学 | Method for controlling rumor propagation in complicated network |
| CN106022856A (en) * | 2016-05-05 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Data display method and device |
| CN105871700A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Message propagation method and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109327488A (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695033B (en) | Enterprise public opinion analysis method, enterprise public opinion analysis device, electronic equipment and medium | |
| US11783126B2 (en) | Enabling chatbots by detecting and supporting affective argumentation | |
| Alizadeh et al. | Content-based features predict social media influence operations | |
| US11086858B1 (en) | Context-based utterance prediction for assistant systems | |
| US10275418B2 (en) | Method for selecting valid variants in search and recommendation systems (variants) | |
| US20180357220A1 (en) | Enabling chatbots by detecting and supporting argumentation | |
| McMinn et al. | Building a large-scale corpus for evaluating event detection on twitter | |
| WO2019099805A1 (en) | Machine-leaning models based on non-local neural networks | |
| CN111615706A (en) | Analysis of spatial sparse data based on sub-manifold sparse convolutional neural network | |
| CN109509010B (en) | Multimedia information processing method, terminal and storage medium | |
| US10719889B2 (en) | Secondary profiles with confidence scores | |
| US9407589B2 (en) | System and method for following topics in an electronic textual conversation | |
| US20180349347A1 (en) | Measuring Phrase Association on Online Social Networks | |
| CN110348907A (en) | A kind of orientation method and device of advertisement crowd | |
| CN115130711A (en) | Data processing method and device, computer and readable storage medium | |
| CN109327488B (en) | Network information pushing method and device and server | |
| CN113011884A (en) | Account feature extraction method, device and equipment and readable storage medium | |
| US20190108416A1 (en) | Methods for more effectively moderating one or more images and devices thereof | |
| Friedl | Dis/similarities in the design and development of legal and algorithmic normative systems: the case of Perspective API | |
| CN114491149A (en) | Information processing method and apparatus, electronic device, storage medium, and program product | |
| CN112202889B (en) | Information pushing method, device and storage medium | |
| CN110972086A (en) | Short message processing method and device, electronic equipment and computer readable storage medium | |
| CN113656699A (en) | User feature vector determination method, related device and medium | |
| CN111919210A (en) | Media source metrics for incorporation into an audit media corpus | |
| Granskogen | Automatic detection of fake news in social media using contextual information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210813 |