CN108306811B - Message processing method and device - Google Patents
Message processing method and device Download PDFInfo
- Publication number
- CN108306811B CN108306811B CN201710065821.7A CN201710065821A CN108306811B CN 108306811 B CN108306811 B CN 108306811B CN 201710065821 A CN201710065821 A CN 201710065821A CN 108306811 B CN108306811 B CN 108306811B
- Authority
- CN
- China
- Prior art keywords
- message
- user
- propagation
- historical record
- target
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 230000000644 propagated effect Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 230000001902 propagating effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a message processing method and a device, wherein the method comprises the following steps: the method comprises the steps of obtaining a first message in propagation and a first user set on a path where the first message has been propagated, determining the message type of the first message, obtaining a target reference user characteristic corresponding to the message type of the first message from a pre-generated reference user characteristic set, determining a second user set from the first user set according to the target reference user characteristic, counting the propagation condition of each user in the second user set on the first message, and further limiting the propagation of the first message according to the counting result. The embodiment of the invention can accurately and effectively limit the message transmission according to the message transmission condition of the user.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a message processing method and apparatus.
Background
With the rapid development of communication technology and internet technology, social applications such as instant messaging and the like are very popular, so that the message spreading becomes faster, the contact between people becomes tighter, people can receive a large amount of messages every day or even all the time, false messages such as rumors can be disguised as real valuable messages and spread rapidly and widely, and many people without false message identification ability are likely to be cheated and even injured. Therefore, how to accurately and effectively limit the propagation of the message so as to reduce the harm of the false message becomes an urgent problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a message processing method and a message processing device, which can accurately and effectively limit the propagation of a message according to the propagation condition of a user to the message.
A first aspect of an embodiment of the present invention provides a message processing method, including:
acquiring a first message in propagation and a first user set on a propagated path of the first message.
And determining the message category of the first message, and acquiring a target reference user characteristic corresponding to the message category of the first message from a pre-generated reference user characteristic set.
And determining a second user set from the first user set according to the target reference user characteristics.
And counting the propagation condition of each user in the second user set to the first message, and limiting the propagation of the first message according to the counting result.
A second aspect of the present invention provides a message processing apparatus, including:
an obtaining module, configured to obtain a first message in propagation and a first user set on a propagated path of the first message.
A determination module to determine a message category of the first message.
The obtaining module is further configured to obtain a target reference user feature corresponding to the message category of the first message from a reference user feature set generated in advance.
The determining module is further configured to determine a second user set from the first user set according to the target reference user characteristic.
And the processing module is used for counting the propagation condition of each user in the second user set to the first message and limiting the propagation of the first message according to the counting result.
The embodiment of the invention can obtain the first message in propagation and the first user set on the propagation path of the first message, after the message type of the first message is determined, the target reference user characteristic corresponding to the message type of the first message is obtained from the reference user characteristic set, the second user set is determined from the first user set according to the target reference user characteristic, the propagation condition of each user in the second user set to the first message (including the propagation of the first message and the non-propagation of the first message) is counted, and the propagation of the first message is limited according to the counting result, so that the propagation of the message can be accurately and effectively limited according to the propagation condition of the user to the message.
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 some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a message processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a message propagation path provided by an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a message processing apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural 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.
Fig. 1 is a schematic flow chart illustrating a message processing method according to an embodiment of the present invention. The message processing method described in this embodiment includes the following steps:
101. the server acquires a first message in propagation and a first user set on a propagated path of the first message.
The first message may specifically be any one of the messages currently in a propagation state.
In a specific implementation, the server may track and record a propagation path of each message in real time, and for a first message, the server obtains a user set (denoted as a first user set) on the first message propagated path, that is, all users that receive the first message. As shown in fig. 2, there are 8 propagation paths of r 1-r 8, and all users currently receiving the first message are 8 users, i.e., a-H, and the first user set consists of 8 users, i.e., a-H.
102. And the server determines the message category of the first message and acquires the target reference user characteristics corresponding to the message category of the first message from a pre-generated reference user characteristic set.
The message category may be defined according to a keyword of the message, for example, the message category may be defined according to a title of the message.
The reference user characteristics refer to user characteristics corresponding to a user having a higher recognition capability for a message (for example, recognizing whether the message is a false message such as a rumor), and the user characteristics may specifically include sub-characteristics such as age, gender, academic history, occupation, marriage, city, working life, income level, hobbies, and usage frequency of a terminal such as a smart phone. Users with higher recognition capability usually have the characteristic of being willing to spread messages, not spreading false messages such as rumors, etc., the willing to spread messages can be evaluated by the probability of spreading the messages, for example, the probability of spreading the messages is greater than or equal to a preset probability threshold (e.g., 50%) and it is considered that the preferred to spread messages, and whether to spread false messages such as rumors, etc., can be determined historically by the spreading condition of the false messages such as rumors, etc. Different message categories correspond to different reference user characteristics, reference user characteristics corresponding to multiple message categories form a reference user characteristic set, and the reference user characteristic set comprises the corresponding relation between the message categories and the reference user characteristics.
In a specific implementation, the server may extract a keyword of the first message, for example, the title of the first message may be used as the keyword or the keyword is extracted from the title of the first message, and analyze the keyword of the first message to determine the message category of the first message, for example, match the keyword of the first message with the keyword corresponding to the message category, and use the message category with the highest matching degree as the message category of the first message.
Further, the server queries the reference user feature set according to the identifier of the message category of the first message, so as to obtain a target reference user feature corresponding to the message category of the first message, where the target reference user feature is a user feature corresponding to a user who has an ability to identify a false message such as a rumor belonging to the message category of the first message.
103. And the server determines a second user set from the first user set according to the target reference user characteristics.
In a specific implementation, the server matches the user characteristics of each user in the first user set with the target reference user characteristics to obtain a matching degree of the user characteristics, and obtains a second user set composed of users whose matching degree of the user characteristics is greater than or equal to a preset matching degree threshold, where the users included in the second user set have an ability to identify a false message such as a rumor belonging to the message category of the first message, that is, can identify whether the first message is a false message such as a rumor.
In some possible embodiments, the matching the user characteristics of each user in the first user set with the target reference user characteristics respectively to obtain the matching degree of the user characteristics may specifically include: and matching each sub-feature in the user features of each user with the corresponding sub-feature in the target reference user features to obtain the matching degree of each sub-feature, wherein each sub-feature is provided with a corresponding weight value, the product of the matching degree of each sub-feature and the weight value is obtained, and the value obtained by summing the products of the matching degree of each sub-feature and the weight value is used as the matching degree of the user features.
In some possible embodiments, for a special user who cannot temporarily determine whether the user has the capability of identifying a false message such as a rumor, for example, a new user or a user with a small number of historically received messages (because it cannot be determined accurately whether the user is willing to propagate a message when the number of historically received messages is small), the special user may be directly removed from the first user set, and then a second user set is determined from the first user set after the special user is removed, so as to reduce the amount of computation and ensure the accuracy in determining the second user set.
104. And the server counts the propagation condition of each user in the second user set to the first message, and limits the propagation of the first message according to the statistical result.
The user propagates the first message, wherein the user propagates the first message and does not propagate the first message.
In a specific implementation, the server performs statistics on the propagation condition of each user in the second user set on the first message, and specifically may obtain a proportion occupied by a user in the second user set who does not propagate the first message, and use the proportion as a statistical result, so that the propagation of the first message may be limited according to the statistical result.
In some possible embodiments, the limiting, by the server, propagation of the first message according to the statistical result may specifically include: if the statistical result is greater than or equal to a preset first proportion (e.g. 50%) and less than a preset second proportion (e.g. 90%), that is, half or more of the users in the second user set do not continue to propagate the first message, it indicates that the first message is likely to be a rumor and other false messages, and the server may alarm when other users continue to propagate the first message, including adding an alarm prompt tag to the first message, or outputting alarm prompt information in a propagation page for propagating the first message, so as to alarm other users that the first message is likely to be a rumor and other false messages, thereby effectively limiting the propagation range of the first message, and reducing the harm caused when the first message is indeed a rumor and other false messages. If the statistical result is greater than or equal to a preset second proportion (for example, 90%), that is, most users in the second user set do not continue to propagate the first message, it is indicated that the first message is determined to be a rumor or and other false messages, the server may directly terminate the propagation of the first message, for example, when other users continue to propagate the first message, it is suggested that the first message has been deleted or cannot be displayed due to a suspected violation.
For example, if the message type of the first message is a technology class, the preset first proportion is 50%, and the preset second proportion is 90%, as shown in fig. 2, it is assumed that the user E, H, G does not propagate the first message, and the second user set determined from the first user set (i.e., users a to H) is composed of users C, D, E, H, G, that is, the user C, D, E, H, G has the ability to recognize false messages such as rumors of the technology class, the server obtains the propagation condition of the first message from the user C, D, E, H, G, that is, the user C, D propagates the first message, the user E, H, G does not propagate the first message, the number of users who do not propagate the first message is 3, and the proportion of the number of users to the total number of users 5 in the second user set is 3/5 ═ 60%, since 60% is greater than 50% and less than 90%, the server may give an alarm when the other user (i.e., user B) continues to propagate the first message (e.g., share the first message to a friend or share the first message to a social space), including adding an alarm prompt tag to the first message, or outputting alarm prompt information in a sharing page where the first message is shared, so as to alarm that the first message of user B is likely to be a false message such as a rumor, thereby greatly reducing the probability that the user B continues to propagate the first message, further effectively limiting the propagation range of the first message, and reducing the harm caused when the first message is indeed a false message such as a rumor.
In some possible embodiments, the first message may be specifically in an initial propagation state, where the initial propagation state is a state when the propagation range is small (for example, the propagation path and/or the number of users propagated to the first message is small), and the steps 101 to 104 are performed on the first message in the initial propagation state, so as to find out the fake message such as rumor as early as possible, and limit propagation of the fake message such as rumor in time, thereby effectively reducing harm of the fake message. It should be noted that, in order to ensure the accuracy of the final determination result of whether the first message is a fake message such as a rumor, the initial propagation state described in the embodiment of the present invention is a state when the number of users propagated to the first message reaches the preset first value. The initial propagation state may also be a state in which the server continuously performs steps 101 to 103 until the number of users included in the determined second user set reaches a preset second value, and after the first message reaches the initial propagation state, the server performs step 104 again.
In some possible embodiments, the specific way for the server to generate the reference user feature set may be: the server acquires a historical record message set meeting target characteristics, wherein the target characteristics are specifically the historical record messages included in the historical record message set are rumors and other false messages. The server obtains reference user characteristics corresponding to the message types of the historical record messages according to the message types of the historical record messages in the historical record message set and the user set on the propagation path, namely, the user characteristics of the users having identification capability for the historical record messages are obtained for the historical record messages of each message type and are used as the reference user characteristics, and then the reference user characteristics corresponding to the message types of the historical record messages are combined to generate a reference user characteristic set, wherein the reference user characteristic set comprises the corresponding relation between the message types and the reference user characteristics, and the reference user characteristics corresponding to different message types are convenient to query.
Further, the specific way for the server to obtain the reference user characteristics corresponding to the message category of each history message according to the message category of each history message in the history message set and the user set on the propagation path may be: the method comprises the steps of acquiring a message type of a target historical record message and a third user set on a propagation path aiming at any historical record message (marked as the target historical record message) in a historical record message set, and determining a fourth user set which does not propagate the target historical record message and has the probability of message propagation larger than or equal to a preset probability threshold from the third user set, wherein the fourth user set comprises users having identification capacity for the target historical record message, so that a reference user characteristic corresponding to the message type of the target historical record message can be obtained according to the user characteristics of each user in the fourth user set.
In some possible embodiments, the specific way for the server to determine the probability of each user in the third set of users propagating the message may be: acquiring the number of times that each user in the third user set propagates the message after receiving the message and the number of times that each user does not propagate the message, and determining the probability that each user in the third user set propagates the message according to the number of times that each user propagates the message and the number of times that each user does not propagate the message, for example, if the number of times that a user in the third user set recorded by the server propagates the message after receiving the message is 30 times and the number of times that each user propagates the message is 20 times, the probability that the user propagates the message may be determined to be 30/(30+20) ═ 60%.
In some possible embodiments, for the server adopting the solutions of steps 101 to 104, which cannot identify the messages such as the fake messages such as the rumors or the suspected rumors, for example, the fake messages such as the rumors actively submitted by the target user (denoted as the second message), the server may add the second message to the history message set, continuously expand the history message set, and further update the reference user characteristics corresponding to the message categories of the second message in the reference user characteristic set according to the user characteristics of the target user, so as to improve the accuracy of the determination result of whether the propagated messages of the same message category as the second message are the fake messages such as the rumors.
Further, the server may also periodically (e.g., once a month) generate a new reference user feature set according to the expanded historical record message set, so as to further improve the accuracy of the determination result of whether the message in propagation is a fake message such as a rumor.
In the embodiment of the invention, a server acquires a first message in propagation and a first user set on a propagation path of the first message, determines a message type of the first message, acquires a target reference user characteristic corresponding to the message type of the first message from a reference user characteristic set, determines a second user set from the first user set according to the target reference user characteristic, counts the propagation condition of each user in the second user set on the first message (including propagation of the first message and non-propagation of the first message), and then limits the propagation of the first message according to a statistical result, so that the propagation of the message can be accurately and effectively limited according to the propagation condition of the user on the message, and the harm of false messages is reduced.
Please refer to fig. 3, which is a schematic structural diagram of a message processing apparatus according to an embodiment of the present invention. The message processing apparatus described in this embodiment includes:
an obtaining module 301, configured to obtain a first message in propagation and a first user set on a propagated path of the first message.
A determining module 302, configured to determine a message category of the first message.
The obtaining module 301 is further configured to obtain a target reference user feature corresponding to the message category of the first message from a reference user feature set generated in advance.
The determining module 302 is further configured to determine a second user set from the first user set according to the target reference user characteristic.
A processing module 303, configured to count propagation conditions of the first message by each user in the second user set, and perform limitation processing on propagation of the first message according to a statistical result.
In some possible embodiments, the processing module 303 includes:
a counting unit 3030, configured to count propagation conditions of the first message by each user in the second user set, and use a ratio of users in the second user set that have not propagated the first message as a statistical result.
An alarm unit 3031, configured to alarm propagation of the first message if the statistical result is greater than or equal to a preset first ratio and less than a preset second ratio.
A terminating unit 3032, configured to terminate propagation of the first message if the statistical result is greater than or equal to the preset second ratio.
In some possible implementations, the apparatus further includes a generation module 304, wherein:
the obtaining module 301 is further configured to obtain a history message set satisfying the target feature.
The obtaining module 301 is further configured to obtain, according to the message category of each historical record message in the historical record message set and the user set on the propagation path, a reference user feature corresponding to the message category of each historical record message.
The generating module 304 is configured to generate a reference user feature set according to the reference user features corresponding to the message categories of the history messages.
Wherein the reference user feature set comprises a correspondence between a message category and a reference user feature.
In some possible embodiments, the obtaining module 301 is specifically configured to:
and aiming at a target historical record message in the historical record message set, acquiring a message category and a third user set on a propagation path of the target historical record message, wherein the target historical record message is any one of the historical record messages included in the historical record message set.
And determining a fourth user set which is not transmitted to the target historical record message and has a probability of transmitting the message larger than or equal to a preset probability threshold in the third user set.
And obtaining a reference user characteristic corresponding to the message category of the target historical record message according to the user characteristics of each user in the fourth user set.
In some possible embodiments, the obtaining module 301 is further configured to obtain the recorded number of times that each user in the third user set has propagated a message after receiving the message and the number of times that each user has not propagated a message.
The determining module 302 is further configured to determine, according to the number of times of message propagation and the number of times of message propagation, a probability that each user in the third user set propagates a message.
In some possible embodiments, the apparatus further comprises an update module 305, wherein:
the obtaining module 301 is further configured to obtain a second message submitted by a target user, and add the second message to the history message set.
The updating module 305 is configured to update the reference user characteristic corresponding to the message category of the second message in the reference user characteristic set according to the user characteristic of the target user.
It can be understood that the functions of each functional module and unit of the message processing apparatus in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
In this embodiment of the present invention, the obtaining module 301 obtains the first message in propagation and the first user set on the path along which the first message has propagated, after the determining module 302 determines the message type of the first message, the obtaining module 301 obtains a target reference user characteristic corresponding to the message category of the first message from a reference user characteristic set, the determining module 302 determines a second user set from the first user set according to the target reference user characteristic, the processing module 303 performs statistics on the propagation condition of each user in the second user set to the first message (including propagating the first message and not propagating the first message), and performs limitation processing on the propagation of the first message according to the statistical result, therefore, the propagation of the message can be accurately and effectively limited according to the propagation condition of the user to the message, so that the harm of false messages is reduced.
Fig. 4 is a schematic structural diagram of a server according to an embodiment of the present invention. The server described in this embodiment includes: a processor 401, a network interface 402, and a memory 403. The processor 401, the network interface 402 and the memory 403 may be connected by a bus or other means, and the embodiment of the present invention is exemplified by being connected by a bus.
The processor 401 (or Central Processing Unit, CPU) is a computing core and a control core of the server. The network interface 402 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.), controlled by the processor 401, for transceiving data. The Memory 403(Memory) is a Memory device of the server for storing programs and data. It is understood that the memory 403 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory; optionally, at least one memory device may be located remotely from the processor 401. Memory 403 provides storage space that stores the operating system and executable program code of the server, which may include, but is not limited to: windows system (an operating system), Linux system (an operating system), etc., which are not limited in this regard.
In the embodiment of the present invention, the processor 401 executes the executable program code in the memory 403 to perform the following operations:
a processor 401 configured to obtain a first message in propagation and a first set of users on a propagated path of the first message.
The processor 401 is further configured to determine a message category of the first message.
The processor 401 is further configured to obtain a target reference user feature corresponding to the message category of the first message from a pre-generated reference user feature set.
The processor 401 is further configured to determine a second user set from the first user set according to the target reference user characteristic.
The processor 401 is further configured to count propagation conditions of the first message by each user in the second user set, and limit propagation of the first message according to a statistical result.
In some possible embodiments, the processor 401 is specifically configured to:
and counting the propagation condition of each user in the second user set to the first message, and taking the proportion of users in the second user set which do not propagate the first message as a statistical result.
And if the statistical result is greater than or equal to a preset first proportion and less than a preset second proportion, alarming the transmission of the first message through a network interface 402.
And if the statistical result is greater than or equal to the preset second proportion, terminating the propagation of the first message.
In some possible embodiments, the processor 401 is further configured to obtain a set of history messages that satisfy the target feature.
The processor 401 is further configured to obtain a reference user characteristic corresponding to the message category of each history message according to the message category of each history message in the history message set and the user set on the propagation path.
The processor 401 is further configured to generate a reference user feature set according to the reference user features corresponding to the message categories of the history messages.
Wherein the reference user feature set comprises a correspondence between a message category and a reference user feature.
In some possible embodiments, the processor 401 is specifically configured to:
and aiming at a target historical record message in the historical record message set, acquiring a message category and a third user set on a propagation path of the target historical record message, wherein the target historical record message is any one of the historical record messages included in the historical record message set.
And determining a fourth user set which is not transmitted to the target historical record message and has a probability of transmitting the message larger than or equal to a preset probability threshold in the third user set.
And obtaining a reference user characteristic corresponding to the message category of the target historical record message according to the user characteristics of each user in the fourth user set.
In some possible embodiments, the processor 401 is further configured to obtain the recorded number of times that each user in the third set of users has propagated to the message after receiving the message and the number of times that each user has not propagated to the message.
The processor 401 is further configured to determine, according to the number of times of message propagation and the number of times of message propagation, a probability that each user in the third user set propagates a message.
In some possible embodiments, the processor 401 is further configured to obtain a second message submitted by a target user, and add the second message to the history message set.
The processor 401 is further configured to update, according to the user characteristic of the target user, a reference user characteristic corresponding to the message category of the second message in the reference user characteristic set.
In a specific implementation, the processor 401, the network interface 402, and the memory 403 described in this embodiment of the present invention may execute the implementation described in the flow of the message processing method provided in this embodiment of the present invention, or may execute the implementation described in a message processing apparatus provided in this embodiment of the present invention, which is not described herein again.
In this embodiment of the present invention, the processor 401 obtains a first message in propagation and a first user set on a path through which the first message has been propagated, determines a message type of the first message, obtains a target reference user feature corresponding to the message type of the first message from a reference user feature set, determines a second user set from the first user set according to the target reference user feature, counts propagation conditions (including propagation of the first message and non-propagation of the first message) of each user in the second user set, and further performs limitation processing on propagation of the first message according to a statistical result, so that propagation of the message can be accurately and effectively limited according to the propagation conditions of the message by the user, and thus harm of false messages is reduced.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. A message processing method, comprising:
acquiring a first message in propagation and a first user set on a propagated path of the first message;
extracting keywords of the first message, analyzing the keywords of the first message to determine the message category of the first message, and acquiring target reference user features corresponding to the message category of the first message from a pre-generated reference user feature set, wherein the target reference user features comprise user features corresponding to users having identification capability on false messages belonging to the message category of the first message;
determining a second user set from the first user set according to the target reference user characteristics;
and counting the propagation condition of each user in the second user set to the first message, and limiting the propagation of the first message according to the counting result.
2. The method according to claim 1, wherein the counting propagation conditions of the first message by each user in the second set of users, and limiting propagation of the first message according to the statistical result comprises:
counting the propagation condition of each user in the second user set to the first message, and taking the proportion of users in the second user set which do not propagate the first message as a statistical result;
if the statistical result is greater than or equal to a preset first proportion and less than a preset second proportion, alarming the transmission of the first message;
and if the statistical result is greater than or equal to the preset second proportion, terminating the propagation of the first message.
3. The method of claim 1 or 2, wherein before the obtaining the first message in flight and the first set of users on the first message-propagated path, the method further comprises:
acquiring a historical record message set meeting target characteristics;
obtaining reference user characteristics corresponding to the message categories of the historical record messages according to the message categories of the historical record messages in the historical record message set and the user set on the propagation path;
generating a reference user characteristic set according to the reference user characteristics corresponding to the message categories of the historical record messages;
wherein the reference user feature set comprises a correspondence between a message category and a reference user feature.
4. The method according to claim 3, wherein obtaining the reference user characteristics corresponding to the message category of each history message according to the message category of each history message in the history message set and the user set on the propagation path comprises:
aiming at a target historical record message in the historical record message set, acquiring a message category and a third user set on a propagation path of the target historical record message, wherein the target historical record message is any one of the historical record messages included in the historical record message set;
determining a fourth user set which is not transmitted to the target historical record message and has a probability of transmitting the message larger than or equal to a preset probability threshold in the third user set;
and obtaining a reference user characteristic corresponding to the message category of the target historical record message according to the user characteristics of each user in the fourth user set.
5. The method of claim 4, wherein before determining the third set of users, the method further comprises, before determining a fourth set of users in the third set of users who have not propagated the target history message and have a probability of propagating the target history message greater than or equal to a preset probability threshold:
acquiring the recorded times of message transmission and the times of message transmission failure of each user in the third user set after receiving the message;
and determining the probability of the message transmission of each user in the third user set according to the number of the message transmission and the number of the message transmission which is not performed.
6. The method of claim 3, further comprising:
acquiring a second message submitted by a target user, and adding the second message to the historical record message set;
and updating the reference user characteristics corresponding to the message categories of the second message in the reference user characteristic set according to the user characteristics of the target user.
7. A message processing apparatus, comprising:
an obtaining module, configured to obtain a first message in propagation and a first user set on a propagated path of the first message;
the determining module is used for extracting keywords of the first message and analyzing the keywords of the first message to determine the message category of the first message;
the obtaining module is further configured to obtain a target reference user feature corresponding to the message category of the first message from a pre-generated reference user feature set, where the target reference user feature includes a user feature corresponding to a user having an identification capability for a false message belonging to the message category of the first message;
the determining module is further configured to determine a second user set from the first user set according to the target reference user characteristics;
and the processing module is used for counting the propagation condition of each user in the second user set to the first message and limiting the propagation of the first message according to the counting result.
8. The apparatus of claim 7, wherein the processing module comprises:
a statistical unit, configured to perform statistics on propagation conditions of the first message by each user in the second user set, and use a proportion of users in the second user set that have not propagated the first message as a statistical result;
the alarm unit is used for alarming the propagation of the first message if the statistical result is greater than or equal to a preset first proportion and less than a preset second proportion;
a terminating unit, configured to terminate propagation of the first message if the statistical result is greater than or equal to the preset second ratio.
9. The apparatus of claim 7 or 8, further comprising a generation module, wherein:
the acquisition module is also used for acquiring a historical record message set meeting the target characteristics;
the acquisition module is further configured to obtain a reference user characteristic corresponding to the message category of each historical record message according to the message category of each historical record message in the historical record message set and the user set on the propagation path;
the generating module is used for generating a reference user characteristic set according to the reference user characteristics corresponding to the message categories of the historical record messages;
wherein the reference user feature set comprises a correspondence between a message category and a reference user feature.
10. The apparatus of claim 9, wherein the obtaining module is specifically configured to:
aiming at a target historical record message in the historical record message set, acquiring a message category and a third user set on a propagation path of the target historical record message, wherein the target historical record message is any one of the historical record messages included in the historical record message set;
determining a fourth user set which is not transmitted to the target historical record message and has a probability of transmitting the message larger than or equal to a preset probability threshold in the third user set;
and obtaining a reference user characteristic corresponding to the message category of the target historical record message according to the user characteristics of each user in the fourth user set.
11. The apparatus of claim 10,
the obtaining module is further configured to obtain the recorded times of message propagation and the times of message propagation failure of each user in the third user set after receiving the message;
the determining module is further configured to determine, according to the number of times of message propagation and the number of times of message propagation, a probability that each user in the third user set propagates a message.
12. The apparatus of claim 9, further comprising an update module, wherein:
the acquisition module is further configured to acquire a second message submitted by a target user, and add the second message to the history message set;
and the updating module is used for updating the reference user characteristics corresponding to the message categories of the second message in the reference user characteristic set according to the user characteristics of the target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710065821.7A CN108306811B (en) | 2017-02-06 | 2017-02-06 | Message processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710065821.7A CN108306811B (en) | 2017-02-06 | 2017-02-06 | Message processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108306811A CN108306811A (en) | 2018-07-20 |
| CN108306811B true CN108306811B (en) | 2021-03-26 |
Family
ID=62872394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710065821.7A Expired - Fee Related CN108306811B (en) | 2017-02-06 | 2017-02-06 | Message processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108306811B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101056281A (en) * | 2007-06-01 | 2007-10-17 | 清华大学 | Email transfer method for the online protocol and credit mechanism based on scalable message |
| CN101909261A (en) * | 2010-08-10 | 2010-12-08 | 中兴通讯股份有限公司 | Method and system for monitoring spam |
| CN102567340A (en) * | 2010-12-09 | 2012-07-11 | 腾讯科技（深圳）有限公司 | Method and device for filtering Microblog information |
| CN102752279A (en) * | 2012-04-27 | 2012-10-24 | 中国科学院信息工程研究所 | Simulation system and simulation method of social network service malicious code propagation |
| CN103970832A (en) * | 2014-04-01 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing spam |
| CN106355449A (en) * | 2016-08-31 | 2017-01-25 | 腾讯科技（深圳）有限公司 | User selecting method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070233861A1 (en) * | 2006-03-31 | 2007-10-04 | Lucent Technologies Inc. | Method and apparatus for implementing SMS SPAM filtering |
-
2017
- 2017-02-06 CN CN201710065821.7A patent/CN108306811B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101056281A (en) * | 2007-06-01 | 2007-10-17 | 清华大学 | Email transfer method for the online protocol and credit mechanism based on scalable message |
| CN101909261A (en) * | 2010-08-10 | 2010-12-08 | 中兴通讯股份有限公司 | Method and system for monitoring spam |
| CN102567340A (en) * | 2010-12-09 | 2012-07-11 | 腾讯科技（深圳）有限公司 | Method and device for filtering Microblog information |
| CN102752279A (en) * | 2012-04-27 | 2012-10-24 | 中国科学院信息工程研究所 | Simulation system and simulation method of social network service malicious code propagation |
| CN103970832A (en) * | 2014-04-01 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing spam |
| CN106355449A (en) * | 2016-08-31 | 2017-01-25 | 腾讯科技（深圳）有限公司 | User selecting method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108306811A (en) | 2018-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107566358B (en) | Risk early warning prompting method, device, medium and equipment | |
| CN105590055B (en) | Method and device for identifying user credible behaviors in network interaction system | |
| CN111835760B (en) | Alarm information processing method and device, computer storage medium and electronic equipment | |
| US20190171724A1 (en) | Method and apparatus for determining hot event | |
| CN108616654B (en) | Message reminding method, device, terminal and computer readable storage medium | |
| CN107634897B (en) | Group recommendation method and device | |
| US20170169062A1 (en) | Method and electronic device for recommending video | |
| CN112770129A (en) | Live broadcast-based group chat establishing method, related device, equipment and medium | |
| CN112861963A (en) | Method, device and storage medium for training entity feature extraction model | |
| CN113412607A (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN113992340A (en) | User abnormal behavior recognition method, device, equipment, storage medium and program | |
| CN108090193B (en) | Abnormal text recognition method and device | |
| CN111488529A (en) | Information processing method, information processing apparatus, server, and storage medium | |
| CN107451247B (en) | User identification method and device | |
| CN110972086A (en) | Short message processing method and device, electronic equipment and computer readable storage medium | |
| CN111340574B (en) | Risk user identification method and device and electronic equipment | |
| CN114902702B (en) | Short message pushing method, device, server and storage medium | |
| CN111027065B (en) | Leucavirus identification method and device, electronic equipment and storage medium | |
| CN108306811B (en) | Message processing method and device | |
| CN108388652B (en) | Method and device for sending song list identification | |
| CN113505272B (en) | Control method and device based on behavior habit, electronic equipment and storage medium | |
| CN113010579B (en) | Data processing method, device, equipment and storage medium | |
| KR101804020B1 (en) | Method for sns bot detection using geographic information | |
| CN113961810A (en) | News pushing method and device, computer equipment and storage medium | |
| CN113891323A (en) | WiFi-based user tag acquisition system |
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 |
Granted publication date: 20210326 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |