CN110750735A

CN110750735A - False event identification method, device, equipment and storage medium based on block chain network

Info

Publication number: CN110750735A
Application number: CN201911013150.5A
Authority: CN
Inventors: 王星雅
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-10-23
Filing date: 2019-10-23
Publication date: 2020-02-04
Anticipated expiration: 2039-10-23
Also published as: CN110750735B

Abstract

The embodiment of the invention discloses a false event identification method, a false event identification device, false event identification equipment and a storage medium based on a block chain network. The method comprises the following steps: when detecting that a user generates a propagation behavior, the forwarding node acquires a propagation event corresponding to the propagation behavior; the forwarding node determines whether the event content is tampered based on the digital signature, and sends the propagation event to the identification node when the propagation event is not tampered; the identification node determines a first probability that the propagation event is a false event based on the event content and the propagation path; the identifying node determines whether the propagated event is a spurious event based on the first probability. By adopting the embodiment of the invention, the false event in the propagation event can be identified, the diffusion of the false event can be prevented, and the applicability is high.

Description

False event identification method, device, equipment and storage medium based on block chain network

Technical Field

The invention relates to the technical field of computers, in particular to a false event identification method, a false event identification device, false event identification equipment and a storage medium based on a block chain network.

Background

In the current era of internet information outbreak, people are very easy to transmit or acquire various information, and when facing mass information, people often lack the ability of distinguishing objects and are confused by some words with professional skills, transmission properties and kneading, so that errors are made, and even judgment of social development is not facilitated.

Nowadays, the blockchain network not only improves the information transmission efficiency, but also further improves the information security problem, but the internet is still full of a large amount of false information. Therefore, how to identify the false information based on the block chain network becomes an urgent problem to be solved.

Disclosure of Invention

The embodiment of the invention provides a false event identification method, a device, equipment and a storage medium based on a block chain network, which can identify false events in propagation events, can prevent the diffusion of the false events and have high applicability.

In a first aspect, an embodiment of the present invention provides a false event identification method based on a block chain network, where the method includes:

when a user is detected to generate a propagation behavior, a forwarding node acquires a propagation event corresponding to the propagation behavior, wherein the propagation event comprises event content, a propagation path and a digital signature of the event content;

the forwarding node determines whether the event content is tampered based on the digital signature, and sends the propagation event to an identification node when the propagation event is not tampered;

the identification node determines a first probability that the propagated event is a false event based on the event content and the propagation path;

the identifying node determines whether the propagated event is a spurious event based on the first probability.

With reference to the first aspect, in one possible implementation manner, the determining, based on the event content and the propagation path, a first probability that the propagation event is a false event includes:

determining a second probability that the event content is false content based on a text prediction model;

determining a distribution user of the event content, a forwarding user of the event content and a receiving user of the event content from the propagation path, and determining the false event propagation rate of the distribution user, the forwarding user and the receiving user;

determining a third probability that the propagation path is a false event propagation path based on the false event propagation rates of the publishing user, the forwarding user and the receiving user;

determining a first probability that the propagated event is a spurious event based on the second probability and the third probability.

With reference to the first aspect, in a possible implementation manner, the determining, by the forwarding node, whether the event content is tampered with based on the digital signature includes:

the forwarding node acquires a public key of the user and decrypts the digital signature based on the public key to obtain first summary information of the propagation event;

the forwarding node performs hash calculation on the propagation event to obtain second summary information of the propagation event;

the forwarding node compares the first summary information with the second summary information, and determines that the propagation event is not tampered if the first summary information is consistent with the second summary information.

With reference to the first aspect, in one possible implementation manner, the determining, by the identifying node, whether the propagated event is a spurious event based on the first probability that the propagated event is a spurious event includes:

the identification node verifies the validity of the first probability, and if the first probability is a valid probability, the propagation event is sent to the nursery rhyme node so that the nursery rhyme node can determine whether the propagation event is a false event based on the event content;

if the said splitting node determines that the said propagation event is not a false event, the said identification node writes the said propagation event into block chain network;

if the splitting node determines that the propagation event is a false event, the identification node intercepts the propagation event and generates a false event identifier, and writes the false event identifier into a block chain network, wherein the false event identifier is used for marking the propagation event as a false event.

With reference to the first aspect, in one possible implementation manner, the verifying the validity of the first probability by the identification node includes:

the identification node sends the propagation event to each consensus node;

each consensus node determines a fourth probability that the propagation event is a false event based on the event content included in the propagation event and the propagation path, and sends each fourth probability to the identification node;

the identification node identifies a target consensus node from the consensus nodes based on fourth probabilities, wherein the fourth probability sent by the target consensus node is consistent with the first probability;

and the identification node determines the number of the target consensus nodes, and determines the first false probability as an effective probability when the number of the target consensus nodes is not less than a preset number threshold.

With reference to the first aspect, in a possible implementation manner, the text prediction model is obtained by training a propagation network structure feature and a training sample feature, where the propagation network structure feature is a structure feature obtained by performing feature construction on a propagation network in which the propagation event is located, and the training sample feature is a training sample keyword obtained by performing keyword extraction on a false event content training sample and a real event content training sample.

With reference to the first aspect, in a possible implementation manner, before the identifying node determines the number of times of propagation of the target propagation event including the event content, the method further includes:

the identification node sends the propagation event to each consensus node so that each consensus node verifies the propagation event and generates a signature confirmation message after the verification is passed;

the identification node receives the signature confirmation messages sent by the consensus nodes and determines whether the signature messages meet a preset consensus strategy;

if the signature confirmation message meets the preset consensus strategy, the identification node determines that the propagation event is a valid event, and if the signature confirmation message does not meet the preset consensus strategy, the identification node determines that the propagation event is not a valid event.

In a second aspect, an embodiment of the present invention provides a false event identification device based on a block chain network, where the device includes:

an obtaining module, configured to, when it is detected that a user generates a propagation behavior, obtain, by a forwarding node, a propagation event corresponding to the propagation behavior, where the propagation event includes event content, a propagation path, and a digital signature of the event content;

a first determining module, configured to determine whether the event content is tampered based on the digital signature, and send the propagated event to an identification node when the propagated event is not tampered;

a second determining module, configured to determine a first probability that the propagation event is a false event based on the event content and the propagation path;

a third determining module for determining whether the propagated event is a false event based on the first probability.

With reference to the second aspect, in one possible implementation manner, the second determining module includes:

the first prediction unit is used for determining a second probability that the event content is false content based on a text prediction model;

a determining unit, configured to determine a distribution user of the event content, a forwarding user of the event content, and a receiving user of the event content from the propagation path, and determine a false event propagation rate of the distribution user, the forwarding user, and the receiving user;

a second prediction unit, configured to determine a third probability that the propagation path is a false event propagation path based on false event propagation rates of the publishing user, the forwarding user, and the receiving user;

a third prediction unit configured to determine a first probability that the propagation event is a false event based on the second probability and the third probability.

With reference to the second aspect, in one possible implementation manner, the first determining module includes:

the first processing unit is used for acquiring the public key of the user and decrypting the digital signature based on the public key to obtain first abstract information of the propagation event;

the second processing unit is used for carrying out Hash calculation on the propagation event to obtain second abstract information of the propagation event;

and a comparing unit, configured to compare the first summary information with the second summary information, and determine that the propagation event has not been tampered if the first summary information is consistent with the second summary information.

With reference to the second aspect, in one possible implementation manner, the third determining module includes:

a verification unit for verifying the validity of the first probability, and if the first probability is a valid probability, sending the propagation event to a nursery rhyme node so that the nursery rhyme node determines whether the propagation event is a false event based on the event content;

a third processing unit, for writing the propagation event into a blockchain network when the nodes determine that the propagation event is not a false event;

and a fourth processing unit, configured to intercept the propagation event and generate a false event identifier when the rumor node determines that the propagation event is a false event, and write the false event identifier into a block chain network, where the false event identifier is used to mark the propagation event as a false event.

With reference to the second aspect, in one possible implementation manner, the verification unit includes:

a sending subunit, configured to send the propagation event to each consensus node;

a predicting subunit, configured to determine fourth probabilities that the propagation event is a false event based on the event content included in the propagation event and the propagation path, and send each fourth probability to the identification node;

a first determining subunit, configured to determine a target consensus node from the respective consensus nodes based on respective fourth probabilities, where the fourth probability sent by the target consensus node is consistent with the first probability;

and the second determining subunit is configured to determine the number of the target consensus nodes, and determine that the first false probability is an effective probability when the number of the target consensus nodes is not less than a preset number threshold.

With reference to the second aspect, in a possible implementation manner, the text prediction model is obtained by training a propagation network structure feature and a training sample feature, the propagation network structure feature is a structure feature obtained by feature construction of a propagation network in which the propagation event is located, and the training sample feature is a training sample keyword obtained by keyword extraction of a false event content training sample and a true event content training sample.

With reference to the second aspect, in a possible implementation manner, the apparatus further includes:

the verification module is further used for sending the propagation event to each consensus node so that each consensus node verifies the propagation event and generates a signature confirmation message after the verification is passed;

the fourth determining module is further configured to receive the signature confirmation messages sent by the respective consensus nodes and determine whether the signature messages satisfy a preset consensus strategy;

the fifth determining module is further configured to determine that the propagation event is an effective event when the signature confirmation message satisfies the preset consensus policy, and determine that the propagation event is not an effective event when the signature confirmation message does not satisfy the preset consensus policy.

In a third aspect, an embodiment of the present invention provides an apparatus, which includes a processor and a memory, where the processor and the memory are connected to each other. The memory is configured to store a computer program that supports the terminal device to execute the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect, where the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect.

In the embodiment of the invention, after the forwarding node acquires the propagation event, whether the event content in the propagation event is tampered can be determined based on the digital signature in the propagation event, so that the event content in the propagation event can be ensured not to be tampered when the propagation event is identified, and the completeness and the accuracy of the propagation event are ensured. Secondly, the identification node can determine the probability that the propagation event is the false event from the two dimensions of the event content and the propagation path, so that the accuracy and the flexibility of the probability that the propagation event is the false event can be improved, and the applicability is higher.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a block chain network architecture according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating a false event identification method based on a blockchain network according to an embodiment of the present invention;

FIG. 3a is a schematic diagram of a scenario in which a user generates a propagation behavior according to an embodiment of the present invention;

FIG. 3b is a schematic diagram of another scenario in which a user generates a propagation behavior according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a scenario for determining a digital signature of event content according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of the components of a propagated event provided by an embodiment of the invention;

FIG. 6 is a schematic diagram of the components of a propagation path provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of a method for determining whether event content is tampered according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a construction scenario of a text prediction model according to an embodiment of the present invention;

FIG. 9 is a block diagram according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of a false event identification device based on a blockchain network according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of an apparatus provided in 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. The false event identification method based on the block chain network (for convenience of description, the method provided by the embodiment of the invention can be abbreviated as the method) provided by the embodiment of the invention can be applied to any event propagation network in any field.

Referring to fig. 1, fig. 1 is a block chain network architecture according to an embodiment of the present invention. In fig. 1, the blockchain network 10 includes a plurality of nodes, and 10a, 10b, 10c, 10d, and 10e in fig. 1 are partial nodes in the blockchain network 10, respectively. The node 10a, the node 10b, and the node 10c may correspond to any user in the access block chain network, and the users corresponding to the node 10a, the node 10b, and the node 10c may implement mutual communication through the forwarding node 10 d. Wherein, the users corresponding to the

nodes

10a, 10b and 10c realize data communication among users based on the block chain network and depending on the communication-capable devices and clients (applications). For example, taking the user corresponding to the node 10a as an example, when the user corresponding to the node 10a generates a propagation behavior (e.g., shares a piece of news with the user corresponding to the node 10 b), the forwarding node 10d may obtain a propagation event corresponding to the propagation behavior of the user corresponding to the node 10 a. At this time, the forwarding node 10d obtains the propagation event and verifies the propagation event to determine whether the event content of the propagation event is tampered, and if the event content of the propagation event is not tampered after the user corresponding to the node 10a generates the propagation action until the forwarding node 10d obtains the propagation event, the forwarding node 10d sends the propagation event to the identification node 10e in the blockchain network 20. At this time, the identification node can calculate the probability that the propagation event is a false event, so as to determine whether the propagation event is a false event according to the obtained probability that the propagation event is a false event. If the propagated event is a false event, the propagated event may be intercepted based on the blockchain network 20 to be sent to the user corresponding to the node 10b, and if the propagated event is not a false event (real event), the propagated event may be written to the blockchain network 20 to be sent to the user corresponding to the node 10 b. The propagation behavior includes, but is not limited to, sending, forwarding a message, news, and the like to a certain user, and may be determined based on an actual application scenario, which is not limited herein.

Referring to fig. 2, fig. 2 is a schematic flowchart of a false event identification method based on a blockchain network according to an embodiment of the present invention. The false event identification method based on the block chain network provided by the embodiment of the invention can comprise the following steps S101 to S104.

S101, when the fact that the user generates the propagation behavior is detected, the forwarding node obtains the propagation event corresponding to the propagation behavior.

In some possible embodiments, a forwarding node in the blockchain network may detect a user behavior of each user accessing the blockchain network, and when it is detected that any user generates a propagation behavior, the forwarding node in the blockchain network may obtain a propagation event corresponding to the propagation behavior generated by the user. The propagation behavior generated by the user may be to send a message to another user, or to forward a message to make the message see other users (friends of the user, or one or more users specified by the user, without limitation), or may be a behavior in which the user edits and publishes news, texts, pictures, and the like by himself or herself, which may be determined according to an actual application scenario, without limitation. Optionally, when the forwarding node in the blockchain network acquires the propagation event corresponding to the propagation behavior generated by the user, it needs to acquire event content (news, pictures, messages, etc.) propagated by the propagation behavior, and also needs to acquire a propagation path corresponding to the propagation behavior, that is, a transmission path of the event content this time (for example, from the user to the user B) and a forwarding path of the event (for example, from the user a to the user B), etc. The propagation path includes all users that the event content passes through and the path direction, for example, a piece of news is initially published by the user C, and the news that the user D sees is shared by the user E after seeing the publication of the user C. At this time, when the user D sees the news for more users, that is, when the news is sent to the user F, and when the forwarding node in the blockchain network detects the propagation behavior of the user D, the event content of the event propagated this time can be acquired as the news, and the propagation paths of the event content are from the user C to the user E, from the user E to the user D, and from the user D to the user F.

For example, as shown in fig. 3a, fig. 3a is a schematic view of a scenario in which a user generates a propagation behavior according to an embodiment of the present invention. In fig. 3a, the user edited a piece of earthquake prediction news on a social application, i.e., "reportedly, day 16 of 10 months, the prefecture … of the prefecture, of fig. 3 a. "the user clicks on the news of earthquake prediction to see to other users of the user's social circle that is a broadcast event, wherein the news content of earthquake prediction news" reportedly, day 16 of 10 months, the city of Sichuan radio & television bureau … accounts for 76% of the county of Sichuan province. "is the event content of the propagated event. As is apparent in fig. 3a, the travel path of the event content is from the user to other users (users designated as visible by the user when the seismic news is released).

For another example, as shown in fig. 3b, fig. 3b is another schematic view of a scenario in which a user generates a propagation behavior according to an embodiment of the present invention. In fig. 3b, when a user (assumed to be lie four) browses to a earthquake prevention message posted (or forwarded) by zhang in a social application, lie four wants to share the message to friends. At this time, the sharing option below the earthquake prevention message issued by lie four clicks and one third click (please spread | tomorrow in Shenzhen region will have 6 levels of earthquake, please make prevention preparation in advance) is selected and sent to the Xiaobai in the friend list selected and sent. At this time, the process of lie IV choosing to share to white is the propagation behavior of lie IV, and the earthquake prevention message ((please spread | there will be 6 levels of earthquakes in the Shenzhen region in tomorrow morning, please make prevention preparation in advance)) is the event content of this propagation event. In fig. 3b, if the earthquake prevention message is released by zhang san, the propagation path of the event content (earthquake prevention message) is zhang san to lie four, and lie four to small white.

In some possible embodiments, since the user is a user accessing a blockchain network, the user generates a propagation event based on its own propagation behavior and sends the propagation event to the forwarding node (or before the forwarding node acquires the propagation event corresponding to the propagation behavior generated by the user), and in order to ensure that the event content of the propagation event is not tampered during the sending process, the event content needs to be encrypted. Specifically, when the user edits the event content or forwards the event content, the hash calculation may be performed on the event content to obtain the summary of the event content. Since the event content is finally obtained by the forwarding node in the blockchain network, the user needs to encrypt (sign) the digest with its own private key to ensure that the event content is not tampered by other users and nodes, thereby obtaining a digital signature of the event content. As shown in fig. 4, fig. 4 is a schematic view of a scenario for determining a digital signature of event content according to an embodiment of the present invention. In fig. 4, (event content AABB) assumes that the corresponding event content is "AABB" when the user generates the propagation behavior, at this time, the user performs hash calculation on the event content "AABB" to obtain a digest "1000100" of the event content "AABB", and signs the digest "1000100" with its own private key to obtain a digital signature "0010101". After the user obtains the digital signature of the event content, when the forwarding node detects that the user generates the propagation behavior, the event content of the propagation event, the propagation path of the event content and the digital signature of the event content are obtained as the propagation event of the propagation behavior. The content of the broadcast event may be referred to fig. 5, and fig. 5 is a schematic composition diagram of the broadcast event according to the embodiment of the present invention. As shown in fig. 5, the forwarding event obtained by the forwarding node in the blockchain network may include event content, a propagation path (propagation path of the event content), and a digital signature (digital signature of the event content), where specific content of the event content may be determined based on an actual application scenario, which is not limited herein, and a determination manner of the digital signature may refer to the above-mentioned manner, which is not described herein again. The propagation path may further include a propagation time (timestamp) for each user to propagate the event content to another user, so as to determine the precedence order of each propagation path based on the timestamp. For example, fig. 6 is a schematic diagram of components providing a propagation path according to an embodiment of the present invention. In fig. 6, the propagation path of an event content may be user 1 to user 2, user 2 to user 3, user 3 to user 4, user 4 to user 5, user 5 to user 6, and user 6 to user 7. Wherein, the user 6 is the user generating the propagation behavior, and the user 7 is the user receiving the event content corresponding to the propagation behavior. The user involved in the propagation path and the specific path direction may be determined based on the application where the user generates the propagation behavior, the usage environment of the device, and related data, which are not limited herein.

S102, the forwarding node determines whether the event content is tampered or not based on the digital signature, and transmits the propagation event to the identification node when the event content is not tampered.

In some possible embodiments, since the event content is possibly tampered by other users, computer programs, and other nodes in the blockchain network during the transmission process, the event content included in the propagated event received by the forwarding node is not the true event content propagated by the user based on the propagation behavior, and therefore, after the forwarding node receives the propagated event containing the tampered event content, no matter what processing is performed on the propagated event or the event content, the digital signature, and the propagation path included in the propagated event, whether the event content before being tampered is the true content or not cannot be determined, and whether the propagated event containing the untampered event content is a false event or not cannot be determined based on the tampered event content. Therefore, after the forwarding node acquires the propagation event corresponding to the propagation behavior generated by the user, in order to ensure that the event content contained in the received propagation event is not tampered and ensure the accuracy of false event identification on the propagation event, the event content contained in the propagation event can be verified based on the digital signature contained in the propagation event. For example, if a user wants to send information of "raining tomorrow" to another user, after the forwarding node acquires a propagation event corresponding to the sending behavior (propagation behavior) of the user, it needs to verify that the propagation content included in the propagation event is actually "raining tomorrow". If the propagation content is tampered with as 'raining afterday' before the forwarding node acquires the propagation event, after the forwarding node sends the propagation event to the identification node, the identification node cannot determine whether the propagation event that the user sends 'raining afterday' to another user is a real event or a false event. Specifically, the forwarding node may obtain a user identifier of the user, use a public key corresponding to the user identifier as the public key of the user, and decrypt the digital signature based on the public key of the user to obtain summary information of the event content (for convenience of description, hereinafter referred to as first summary information of the event content). Meanwhile, the forwarding node needs to perform hash calculation on the event content to obtain another summary information of the event content (for convenience of description, hereinafter referred to as second summary information of the event content). After the first summary information and the second summary information of the event content are obtained, the forwarding node compares the first summary information and the second summary information of the event content, if the first summary information and the second summary information of the event content are consistent, it can be shown that the event content of the propagated event is not tampered before the forwarding node obtains the propagated event corresponding to the user propagation behavior, and the propagated event is sent to the identification node under the condition that the event content is not tampered, so that the propagation node determines whether the propagated event is a false event. If the first summary information and the second summary information of the event content are not consistent, it indicates that the event content is tampered before the forwarding node acquires the propagation event corresponding to the user propagation behavior, and therefore the event content included in the propagation event is not the event content to be propagated by the user based on the propagation behavior, and at this time, the forwarding node can refuse to send the propagation event to the identification node, so that the purpose of preventing the user from sending the event content based on the propagation behavior is indirectly achieved.

Referring to fig. 7, fig. 7 is a schematic diagram illustrating a method for determining whether event content is tampered according to an embodiment of the present invention. In fig. 7, it is assumed that the digital signature included in the propagation event acquired by the forwarding node is "0010101", and the forwarding node may acquire the public key of the user and decrypt the digital signature "0010101" by using the public key of the user to obtain a first digest "1000100" of the event content. Meanwhile, the forwarding node may perform a hash calculation on the event content included in the broadcast event to obtain a second digest "1000100" of the event content. At this point it is readily apparent that the first digest "1000100" and the second digest "1000100" are identical, indicating that the event content of the propagated event has not been tampered with before being retrieved by the forwarding node.

S103, the identification node determines a first probability that the propagation event is a false event based on the event content and the propagation path.

In some possible embodiments, after the identifying node receives the propagation event sent by the forwarding node, a probability (hereinafter referred to as a first probability for convenience of description) that the propagation event is a false event may be determined, so as to determine whether the propagation event is a false event based on the first probability that the propagation event is a false event. Specifically, when the identification node determines that the propagation event is a first probability of a false event based on the event content and the propagation path included in the propagation event, the event content may be extracted and subjected to word segmentation to obtain a feature word of the event content, the feature word of the event content is input into a text prediction model to obtain a numerical value of text prediction output, and the numerical value output by the text prediction model is determined as the probability of the time content. On the other hand, the identification node may determine, based on the respective users involved in the propagation path, a publishing user (source of the propagation path), a forwarding user (intermediate user in the propagation path) of the event content, and a receiving user (destination in the propagation path) of the event content, and determine the false event propagation rates of the publishing user, the forwarding user, and the receiving user. The false event propagation rate of each user includes, but is not limited to, a distribution rate of the false event content of the user, a forwarding rate of the false event content, an acceptance rate of the false event content, a forwarding amount of the false event content in a preset time period, and the like, and may be determined based on an actual application scenario, which is not limited herein. In addition, the specific calculation mode of the distribution rate of the false event content, the forwarding rate of the false event content, the acceptance rate of the false event content, and the forwarding amount of the false event content in the preset time period may also be determined based on the actual application scenario, and no limitation is made herein. After the identification node obtains the false event propagation rates of the publishing user, the forwarding user and the receiving user, the false event propagation rates of the publishing user, the forwarding user and the receiving user can be converted into the probability that the propagation path is the false event propagation path based on a preset probability algorithm, wherein the preset probability algorithm includes but is not limited to a normalization algorithm, a calculation method based on a preset coefficient and the like. Further, the identification node may determine, based on the obtained second probability that the event content is false content and the obtained probability that the propagation path is a false event propagation path, that the propagation event is a false event, and the specific implementation manner may also be determined based on an actual application scenario, which is limited herein.

The text prediction model can be obtained by training based on the propagation network structure characteristics of the propagation network where the propagation event is located and training sample characteristics, and the training sample characteristics can be training sample keywords obtained by extracting keywords based on a false event content training sample and a true event content training sample. Referring to fig. 8, fig. 8 is a schematic view of a construction scenario of a text prediction model according to an embodiment of the present invention. As shown in fig. 8, a plurality of false event contents may be obtained in advance as false event content training samples, a plurality of real event contents may be obtained as real event content training samples, and a training sample feature set including a false event keyword and a training sample feature set including a real event keyword are obtained by performing keyword extraction from each training sample. When the keywords are extracted from each training sample, each training sample can be preprocessed to replace wrongly written characters, infrequently written words and the like, so that the trainability of the training samples is improved. On the other hand, a propagation network where a propagation path to be predicted is located can be predetermined, and structural features of the propagation network, such as node arrangement, network topology, structure type and the like, of the propagation network are constructed, so that a text prediction model is constructed on the basis of machine learning based on the obtained structural features of the propagation network, the obtained training sample feature set containing the false event keywords and the obtained training sample feature set containing the real event keywords. The specific content of the propagation network structural feature may be determined based on a specific text prediction model construction method and an actual application scenario, which is not limited herein. Optionally, the algorithms applied in the machine learning include, but are not limited to, a decision tree algorithm, a bayesian algorithm, a support vector machine algorithm, an association rule algorithm, an artificial neural network algorithm, a deep learning algorithm, and the like, and may be determined based on an actual application scenario without limitation.

In some possible embodiments, a piece of information may be spread among different users in the social network, that is, users may forward the same information to each other, so that a piece of information is spread in the social network continuously, and if the information is a false information, the information may adversely affect each user in the social network. On the contrary, the communication content that two users communicate with each other (based on instant messaging application, social application, etc.) is assumed, and no matter whether the communication content is real content or false content, no influence is caused on other users. Therefore, on one hand, in order to avoid that the identification node determines that the first probability of all the propagation events leads to the reduction of the false event identification efficiency, and on the other hand, the identification node judges the propagation events containing the possibly widely propagated event contents, the identification node can determine the propagation times of all the propagation events containing the same event contents after receiving the propagation events sent by the forwarding node, and further determine whether the propagation events are the first probability of the false events according to the propagation times.

Specifically, all event contents sent or forwarded by all users are sent to the identification node through the forwarding node in the form of a propagation event, so that the identification node can determine a target propagation event with the same event content from the acquired historical propagation events (at this time, the propagation event sent by the forwarding node and received by the identification node just now is also the target propagation event), and acquire a propagation path in each target propagation event to determine the propagation times of the event contents in each target propagation event so as to determine the propagation times of each target time. The propagation times of the event content in each target propagation event can be determined, and further the total times of all target propagation events containing the same event content can be determined. Optionally, if the forwarding node sends the propagation event to the identification node, the sent propagation event is stored, and at this time, the identification node obtains the target propagation event with the same event content from the propagation events stored in the forwarding node based on the event content, so as to determine the propagation times of all the target propagation events. Optionally, since the identification node determines the propagation times of the propagation event containing the same event content as the propagation event after receiving one propagation event each time, therefore, when the identification node receives a retransmission event (hereinafter referred to as a first propagation event for convenience of description) sent by the forwarding node, the identification node may directly determine, based on the stored propagation times of the respective propagation events, a first propagation time of a target propagation event having the same event content as that included in the first propagation event, and then determine, based on a propagation path included in the received first propagation event, a second propagation time of the event content included in the first propagation event, and adding the first propagation times and the second propagation times to obtain the propagation times of the target propagation event containing the event content of the first propagation event, namely the propagation times of all the propagation events containing the same event content.

Further, after determining the number of times of playing the target propagation event including the event content (the number of times of propagation of all propagation events including the same event content), the identification node may compare the number of times of playing the target propagation event with a preset number of times of propagation, and if the number of times of propagation of the target propagation event is less than or equal to the preset number of times of propagation, it is determined that the propagation event is not propagated to most users, and at this time, the identification node may directly determine that the propagation event is a non-false event. In other words, when the propagation event of the target propagation event is less than or equal to the preset propagation times, it can be indirectly stated that the event content of the propagation event is only a discussion of communication between two or a very few users, and even if the propagation event is a false event, the propagation event will not propagate in a large scale. When the propagation frequency of the target propagation event is greater than the preset propagation frequency, it is indicated that the propagation event has been propagated among a large number of users, and if the propagation event is a false event, adverse effects are brought to a large number of users, so that the identification node needs to determine the probability (for convenience of description, hereinafter referred to as a first probability) that the propagation event is the false event based on the propagation path of the event content of the propagation event, and then determine whether the propagation event is the false event based on the first probability of the propagation event.

In some possible embodiments, since false information that is forwarded, shared and sent by not all users in the social network, for example, content of events propagated by government, enterprise and individual users subjected to official certification is often really information, in order to further improve the efficiency of false event identification of the identification node, the identification node determines whether to determine whether the propagated event is the first probability of the false event based on user information of the user after receiving the propagated event sent by the forwarding node. Specifically, the identification node may obtain user information of a user (the user information may also be sent to the identification node by the forwarding node when a propagation event is sent to the identification node), an implementation manner of specifically obtaining the user information of the user may be determined based on an actual application scenario, and is not limited herein), and determine whether the user is a user in a preset user set based on the user information of the user, if the user is a user in the preset user set, it is determined that the propagation event corresponding to the propagation behavior generated by the user is a real event, event content included in the propagation event is real content, and at this time, the identification node does not need to determine the first probability of the propagation event. On the contrary, the identification node determines the first probability of the propagation event based on the event content and the propagation path contained in the propagation event. The preset user set includes, but is not limited to, users authenticated by a third party who will not propagate a false event, users with a predetermined false event propagation rate of zero, users with a predetermined confidence level higher than a preset threshold, government users, enterprise users, and the like, and may be determined specifically based on an actual application scenario, which is not limited herein. It should be particularly noted that, the specific implementation manner of the trigger identifying node determining, based on the event content and the propagation path included in the propagation event, that the propagation event is the first probability of the false event may be determined based on an actual application scenario, and is not limited herein.

In some possible embodiments, since the identified node is a node in the blockchain network, before the identified node processes the propagated event to determine whether the propagated event is a false event, the propagated event needs to be consensus-processed to ensure that the blockchain network recognizes that the identified node can process the propagated event. Specifically, the identification node may send the propagation event to each consensus node in the blockchain network, so that each consensus node verifies the propagation event. When the verification of the propagation event by each consensus node passes, a signature confirmation message can be generated and sent to the identification node, and at this time, the identification node can determine whether the signature confirmation message sent by each consensus node meets a preset consensus strategy, and if the signature confirmation message sent by each consensus node meets the preset consensus strategy, the identification node can determine the propagation event as a valid event, that is, the identification node can further determine a first probability that the propagation event is a false event and determine whether the propagation event is a false event based on the first probability. If the signature confirmation message sent by each consensus node does not meet the preset consensus strategy, the identification node can determine that the propagation event is not a valid event (invalid event), and at the moment, the identification node does not perform any further processing on the propagation event, so that the purpose of indirectly achieving resistance value propagation of the propagation event is achieved. When the propagation event is verified, it can be verified whether the event content of the propagation event includes illegal words, sensitive words such as transactions and account numbers, and bad information related to fraud and crime, and the like. Optionally, the content of the signature confirmation message sent by each consensus node is content that any identification node can identify and determine whether the consensus node verifies the propagation event, and the specific representation form and composition may be determined based on an actual application scenario, which is not limited herein. Furthermore, because the verification passing message sent by each consensus node to the identification node is subjected to signature processing, the verification passing message cannot be tampered in the sending process to influence the consensus result, and the identification node can also determine the node sending the signature confirmation message based on the signature after receiving a plurality of signature confirmation messages. Optionally, the preset consensus policy may be verification that the propagation event passes through a preset consensus node, or verification that the propagation event passes through a certain percentage (e.g., eighty percent) of consensus nodes, and the specific consensus policy may still be determined based on an actual application scenario, which is not limited herein.

In some possible embodiments, when there are multiple identified nodes in the blockchain network, after an identified node determines that the propagated event is a first probability of a false event, a notification message may be generated to broadcast to all nodes in the blockchain network so that other nodes do not perform any processing on the propagated event. For example, after the forwarding node receives the notification message sent by the identification node, the forwarding node will not send the propagation event to other identification nodes in the blockchain network, so as to avoid the other identification nodes from repeatedly processing the propagation event. Similarly, after other identification nodes receive the notification message, even if the propagation event sent by the forwarding node is received, the first probability that the propagation event is a false event is determined by determining the propagation of the target propagation event containing the same event content at this time, so that the processing efficiency of the propagation event is improved, and the resource waste of the block chain network is avoided.

And S104, the identification node determines whether the propagation event is a false event or not based on the first probability.

In some possible embodiments, since the first probability that the propagation event determined by the identification node is a false event is calculated only by the identification node alone, the calculation result may have an error. Therefore, in order to improve the accuracy of the false event identification, after the identification node determines that the propagation event is the first probability of the false event, the validity verification can be carried out on the first probability. Specifically, the identifying node may send the propagation event to each consensus node, so that each consensus node calculates again the probability that the propagation event is a false event (for convenience of description, hereinafter referred to as a second probability) based on the event content and the propagation path included in the propagation event. And after obtaining the second probability, each consensus node sends the calculated second probability back to the identification node. At this time, the identifying node may compare each received second probability with the first probability, and if the processing of the second probability consistent with the first probability exceeds a preset probability number, or determine the consensus node having the second probability consistent with the first probability as the target node, and if the number of the target consensus node is not less than a preset number threshold, the identifying node may determine that the first false probability is a valid probability. The specific process of determining the second probability by each consensus node based on the event content of the propagation event and the propagation path may refer to the implementation manner shown in step S103, which is not described herein again.

In some possible embodiments, when the identification node determines that the first probability is a valid probability, the propagation event may be sent to the nursery nodes so that the nursery nodes determine that the propagation event is a sufficient spurious event based on the event content included in the propagation event. Specifically, the nursery rhyme node may determine an event type of the event content, and send the event content to a nursery rhyme department corresponding to the event type for identification. For example, when the event content is an earthquake forecast, the event content may be sent to a third-party organization or a website, such as a national earthquake platform network or a disaster prevention department, to identify whether the earthquake forecast content is false content, and if the earthquake forecast content is false content, the event is a propagated event, and otherwise, the event is a real event. Optionally, the splitting node may further match the event content with real content on the network through a network interface based on the event content, and if the event content is consistent with the real content, the splitting node may indicate that the propagation event is a real event, otherwise, the splitting node may indicate that the propagation event is a false event. It should be noted that, the specific implementation manner of the above-mentioned ballad node determining whether the propagation event is a false event may be determined based on the actual application scenario, and is not limited herein.

In some possible embodiments, when the nursery rhyme node determines that the propagation event is not a false event (a real event), the identification node may send another notification message to the forwarding node to enable the forwarding node to forward the propagation event to the user to be sent by the user based on the propagation path included in the propagation event, so as to complete the propagation of the propagation event. Meanwhile, the identification node stores the propagation event and packs the collected propagation event into a block in a preset time period to be written into a block chain network. Specifically, after obtaining a certain number of propagation events (for convenience of description, hereinafter referred to as a propagation event set), the identifying node may pack all the propagation events in the propagation event set into a new block. The block chain comprises a plurality of blocks, each block comprises a block head and a block main body, the block head stores an input information characteristic value, a version number, a timestamp and a difficulty value, and the block main body stores input information; the block above each block is a parent block, the next block also comprises a block head and a block main body, the block head stores the input information (each propagation event in the propagation event set) characteristic value of the current block, the block head characteristic value, the version number, the timestamp and the difficulty value of the parent block, and the like, so that the block data stored in each block in the block chain is associated with the block data stored in the parent block, and the safety of the input information in the block is ensured. When a new block is generated, the hash value of the root of the mercker tree of the new block can be obtained based on each propagation event, then the timestamp is updated to the time when the input information is received, different random numbers are tried, and the characteristic value calculation is performed for multiple times, so that the calculated characteristic value can satisfy the following formula:

SHA256(SHA256(version+prev_hash+merkle_root+ntime+nbits+x))<TARGET

wherein, SHA256 is a characteristic value algorithm used for calculating a characteristic value; version is version information of the relevant block protocol in the block chain; prev _ hash is a block header characteristic value of a parent block of the new block; merkle root is an input information characteristic value; ntime is the update time of the update timestamp; nbits is the current difficulty, is a fixed value within a period of time, and is determined again after exceeding a fixed time period; x is a random number; TARGET is a feature threshold, which can be determined from nbits. Thus, when the random number meeting the formula is obtained through calculation, the information can be correspondingly stored, and a block header and a block main body are generated to obtain a new block.

Fig. 9 is a schematic diagram of a block structure provided in an embodiment of the present invention, and fig. 9 is a specific example of a process for calculating an input information feature value. In FIG. 9, the propagated event 1, the propagated event 2, the propagated event 3, and the propagated event 4 may be organized together in the form of a Mercker tree. Taking the propagation event 1 and the propagation event 2 in fig. 9 as an example, the hash value 1 corresponding to the propagation event 1 can be obtained by hash calculation; similarly, a hash value 2 corresponding to the propagation event 2 can be calculated through hash calculation. Further, the hash value 1 and the hash value 2 are concatenated, and then hash transformation is continued, so as to obtain the hash value 12 shown in fig. 9. By analogy, for the propagated events 3 and 4, the hash value 34 shown in fig. 9 can be obtained by recursively calculating layer by layer, so that the hash value 12 and the hash value 34 can be further concatenated to perform hash transformation until a root (i.e., the hash value 1234 shown in fig. 9) is finally left. At this time, the resulting hash value of all propagation events may be used as the input information characteristic value of the new chunk. It can be seen that the mercker tree is very scalable, and no matter how much traffic data is, a mercker tree and fixed-length input information characteristic values can be generated finally. Further, after the new block is generated, the new block may be added to the uplink of the current blockchain in the blockchain network to complete the uplink storage of the broadcast event.

In some possible embodiments, when the said nursery rhyme node determines that the said propagation event is a false event (real event), the identifying node may send a notification message to the forwarding node to make the forwarding node refuse to propagate the said propagation event, so as to intercept the false event. Optionally, the identification node may generate a false event identifier based on the propagation event, and send the false event identifier to the forwarding node, so that the forwarding node no longer acquires the propagation event marked by the false event identifier after detecting the propagation behavior of the user, and completes interception of the false event from the root. Optionally, the identification node may further broadcast the false event identifier over the entire network, so that the consensus node in the blockchain network does not process the propagation event marked by the false event any more, and at the same time, the user accessing the blockchain network stops propagating the propagation event marked by the false event, thereby achieving an effect of creating a ballad at the user plane. Optionally, the identification node may further write the false event identifier into the blockchain network to store the false event, so that the propagation event represented by the false event identifier may be intercepted at any time based on the false event identifier stored in the blockchain network.

In the embodiment of the invention, after the forwarding node acquires the propagation event, whether the event content in the propagation event is tampered can be determined based on the digital signature in the propagation event, so that the event content in the propagation event can be ensured not to be tampered when the propagation event is identified, and the completeness and the accuracy of information are ensured. Secondly, the identification node can determine the propagation times of the target propagation event containing the same event content and determine the probability that the propagation event is a false event when the propagation times are larger than the preset propagation times, so that the propagation event which cannot be widely propagated and has extremely low influence can be screened to a certain extent, and the flexibility of false event identification is improved. Meanwhile, the first probability of the false event obtained based on the text prediction model and the propagation rate of the false event of each user in the propagation path is validated based on the first probability obtained by the consensus node pair according to stability and credibility, so that the first probability obtained by the identification node is determined to be a true valid probability, the accuracy of false event identification is further improved, and the applicability is higher.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a false event identification apparatus based on a block chain network according to an embodiment of the present invention. The device 1 provided by the embodiment of the invention comprises:

an obtaining module 11, configured to, when it is detected that a user generates a propagation behavior, obtain, by a forwarding node, a propagation event corresponding to the propagation behavior, where the propagation event includes an event content, a propagation path, and a digital signature of the event content;

a first determining module 12, configured to determine whether the event content is tampered based on the digital signature, and send the propagated event to an identification node when the propagated event is not tampered;

a second determining module 13, configured to determine a first probability that the propagation event is a false event based on the event content and the propagation path;

a third determining module 14, configured to determine whether the propagated event is a false event based on the first probability.

In some possible embodiments, the second determining module 13 includes:

a first prediction unit 131, configured to determine a second probability that the event content is false content based on a text prediction model;

a determining unit 132 configured to determine a distribution user of the event content, a forwarding user of the event content, and a receiving user of the event content from the propagation path, and determine a false event propagation rate of the distribution user, the forwarding user, and the receiving user;

a second prediction unit 133, configured to determine a third probability that the propagation path is a false event propagation path based on false event propagation rates of the publishing user, the forwarding user, and the receiving user;

a third prediction unit 134, configured to determine the first probability that the propagation event is a false event based on the second probability and the third probability.

In some possible embodiments, the first determining module 12 includes:

a first processing unit 121, configured to obtain a public key of the user, and decrypt the digital signature based on the public key to obtain first digest information of the propagation event;

a second processing unit 122, configured to perform hash calculation on the propagation event to obtain second summary information of the propagation event;

a comparing unit 123, configured to compare the first summary information with the second summary information, and if the first summary information is consistent with the second summary information, determine that the propagation event has not been tampered with.

In some possible embodiments, the third determining module 14 includes:

a verification unit 141, configured to verify validity of the first probability, and if the first probability is a valid probability, send the propagation event to a nursery node so that the nursery node determines whether the propagation event is a false event based on the event content;

a third processing unit 142, for writing the propagation event into a blockchain network when the nodes determine that the propagation event is not a false event;

a fourth processing unit 143, configured to intercept the propagation event and generate a false event identifier when the nursery rhyme node determines that the propagation event is a false event, and write the false event identifier into a block chain network, where the false event identifier is used to mark the propagation event as a false event.

In some possible embodiments, the verification unit 141 includes:

a sending subunit 1411, configured to send the propagation event to each consensus node;

a predictor 1412, configured to determine fourth probabilities that the propagation event is a false event based on the event content included in the propagation event and the propagation path, and send each fourth probability to the identification node;

a first determining subunit 1413, configured to determine a target consensus node from the respective consensus nodes based on respective fourth probabilities, where the fourth probability sent by the target consensus node is consistent with the first probability;

a second determining subunit 1414, configured to determine the number of the target consensus nodes, and determine that the first false probability is an effective probability when the number of the target consensus nodes is not less than a preset number threshold.

In some feasible embodiments, the text prediction model is obtained by training a propagation network structure feature and a training sample feature, the propagation network structure feature is a structure feature obtained by constructing a feature of a propagation network in which the propagation event is located, and the training sample feature is a training sample keyword obtained by extracting keywords from a dummy event content training sample and a real event content training sample.

In some possible embodiments, the above-mentioned device 1 further comprises:

the verification module 15 is further configured to send the propagation event to each consensus node so that each consensus node verifies the propagation event and generates a signature confirmation message after the verification is passed;

a fourth determining module 16, configured to receive the signature confirmation message sent by each consensus node and determine whether the signature message satisfies a preset consensus policy;

the fifth determining module 17 is further configured to determine that the propagation event is a valid event when the signature confirmation message satisfies the preset consensus policy, and determine that the propagation event is not a valid event when the signature confirmation message does not satisfy the preset consensus policy.

In a specific implementation, the apparatus 1 may execute the implementation manners provided in the steps in fig. 2 through the built-in functional modules, which may specifically refer to the implementation manners provided in the steps, and are not described herein again.

Referring to fig. 11, fig. 11 is a schematic structural diagram of an apparatus provided in an embodiment of the present invention. As shown in fig. 11, the apparatus 1000 in the present embodiment may include: the processor 1001, the network interface 1004, and the memory 1005, and the apparatus 1000 may further include: a user interface 1003, and at least one communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display) and a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a standard wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1004 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 11, a memory 1005, which is a kind of computer-readable storage medium, may include therein an operating system, a network communication module, a user interface module, and a device control application program.

In the device 1000 shown in fig. 11, the network interface 1004 may provide network communication functions; the user interface 1003 is an interface for providing a user with input; and the processor 1001 may be used to invoke a device control application stored in the memory 1005 to implement:

in some possible embodiments, the processor 1001 is configured to:

when a user is detected to generate a propagation behavior, acquiring a propagation event corresponding to the propagation behavior, wherein the propagation event comprises event content, a propagation path and a digital signature of the event content;

determining whether the event content is tampered based on the digital signature, and transmitting the propagation event to an identification node when the propagation event is not tampered;

determining a first probability that the propagated event is a false event based on the event content and the propagation path;

determining whether the propagated event is a spurious event based on the first probability.

In some possible embodiments, the processor 1001 is configured to:

acquiring a public key of the user, and decrypting the digital signature based on the public key to obtain first summary information of the propagation event;

performing hash calculation on the propagation event to obtain second abstract information of the propagation event;

and comparing the first summary information with the second summary information, and if the first summary information is consistent with the second summary information, determining that the propagation event is not tampered.

In some possible embodiments, the processor 1001 is configured to:

validating the first probability, and if the first probability is a valid probability, sending the propagation event to a nursery rhyme node so that the nursery rhyme node determines whether the propagation event is a false event based on the event content;

if the said nodes determine the said event is not false, then writing the said event into block chain network;

if the nodes determine that the propagation event is a false event, intercepting the propagation event and generating a false event identifier, and writing the false event identifier into a block chain network, wherein the false event identifier is used for marking the propagation event as the false event.

In some possible embodiments, the processor 1001 is configured to:

sending the propagation event to each consensus node;

determining fourth probabilities that the propagation events are false events based on the event content and the propagation paths included in the propagation events, and sending the fourth probabilities to the identification node;

determining a target consensus node from the consensus nodes based on fourth probabilities, wherein the fourth probability sent by the target consensus node is consistent with the first probability;

and determining the number of the target consensus nodes, and determining the first false probability as an effective probability when the number of the target consensus nodes is not less than a preset number threshold.

In some possible embodiments, the processor 1001 is further configured to:

sending the propagation event to each consensus node so that each consensus node verifies the propagation event and generates a signature confirmation message after the verification is passed;

receiving signature confirmation messages sent by all the consensus nodes and determining whether the signature messages meet a preset consensus strategy;

and if the signature confirmation message does not satisfy the preset consensus strategy, determining that the propagation event is not a valid event.

It should be understood that in some possible embodiments, the processor 1001 may be a Central Processing Unit (CPU), and the processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. For example, the memory may also store device type information.

In a specific implementation, the device 1000 may execute the implementation manners provided in the steps in fig. 2 through the built-in functional modules, which may specifically refer to the implementation manners provided in the steps, and are not described herein again.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and is executed by a processor to implement the method provided in each step in fig. 2, which may specifically refer to the implementation manner provided in each step, and is not described herein again.

The computer readable storage medium may be an internal storage unit of the task processing device provided in any of the foregoing embodiments, for example, a hard disk or a memory of an electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) card, a flash card (flash card), and the like, which are provided on the electronic device. The computer readable storage medium may further include a magnetic disk, an optical disk, a read-only memory (ROM), a Random Access Memory (RAM), and the like. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the electronic device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the electronic device. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.

The terms "first", "second", and the like in the claims, in the description and in the drawings of the present invention are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims

1. A false event identification method based on a block chain network is characterized by comprising the following steps:

the forwarding node determines whether the event content is tampered based on the digital signature and sends the propagated event to an identification node when the propagated event is not tampered;

the identifying node determines a first probability that the propagated event is a false event based on the event content and the propagation path;

2. The method of claim 1, wherein the determining a first probability that the propagated event is a spurious event based on the event content and the propagation path comprises:

determining a publishing user of the event content, a forwarding user of the event content and a receiving user of the event content from the propagation path, and determining the false event propagation rate of the publishing user, the forwarding user and the receiving user;

determining a third probability that the propagation path is a false event propagation path based on false event propagation rates of the publishing user, the forwarding user, and the receiving user;

3. The method of claim 1 or 2, wherein the forwarding node determining whether the event content has been tampered with based on the digital signature comprises:

and the forwarding node compares the first abstract information with the second abstract information, and if the first abstract information is consistent with the second abstract information, the forwarding node determines that the propagation event is not tampered.

4. The method of claim 1, wherein the identifying node determining whether the propagated event is a spurious event based on a first probability that the propagated event is a spurious event comprises:

the identification node verifies the validity of the first probability, and if the first probability is a valid probability, the propagation event is sent to the nursery rhyme node so that the nursery rhyme node can determine whether the propagation event is a false event or not based on the event content;

if the said nodes determine the said event is not false, the said identification node writes the said event into block chain network;

if the propagation event is determined to be a false event by the dinning rumor node, the identification node intercepts the propagation event and generates a false event identifier, and writes the false event identifier into a block chain network, wherein the false event identifier is used for marking the propagation event as the false event.

5. The method of claim 4, wherein the identifying the node validating the first probability comprises:

the identification node sends the propagation event to each consensus node;

the common recognition nodes determine fourth probabilities that the propagation events are false events based on the event contents and the propagation paths included in the propagation events, and send the fourth probabilities to the recognition nodes;

the identification node determines a target consensus node from the consensus nodes based on fourth probabilities, wherein the fourth probability sent by the target consensus node is consistent with the first probability;

6. The method according to claim 2, wherein the text prediction model is obtained by training a propagation network structural feature and a training sample feature, the propagation network structural feature is a structural feature obtained by feature construction of a propagation network in which the propagation event is located, and the training sample feature is a training sample keyword obtained by keyword extraction of a false event content training sample and a real event content training sample.

7. The method of claim 1, wherein before the identifying node determines a number of propagations of a target propagated event containing the event content, the method further comprises:

the identification node receives the signature confirmation message sent by each consensus node and determines whether the signature message meets a preset consensus strategy or not;

if the signature confirmation message meets the preset consensus strategy, the identification node determines that the propagation event is an effective event, and if the signature confirmation message does not meet the preset consensus strategy, the identification node determines that the propagation event is not an effective event.

8. An apparatus for identifying false events based on a blockchain network, the apparatus comprising:

the system comprises an acquisition module, a transmission module and a processing module, wherein the acquisition module is used for acquiring a transmission event corresponding to a transmission behavior when detecting that a user generates the transmission behavior, and the transmission event comprises event content, a transmission path and a digital signature of the event content;

a second determining module, configured to determine a propagation time of a target propagation event including the event content, and determine, when the propagation time is greater than a preset propagation time, a first probability that the propagation event is a false event based on the event content and the propagation path;

a third determination module to determine whether the propagated event is a spurious event based on the first probability.

9. A device comprising a processor and a memory, the processor and memory interconnected;

the memory for storing a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method of any one of claims 1 to 7.