CN111787159B - Block chain-based crank call identification method and system - Google Patents
Block chain-based crank call identification method and system Download PDFInfo
- Publication number
- CN111787159B CN111787159B CN202010626615.0A CN202010626615A CN111787159B CN 111787159 B CN111787159 B CN 111787159B CN 202010626615 A CN202010626615 A CN 202010626615A CN 111787159 B CN111787159 B CN 111787159B
- Authority
- CN
- China
- Prior art keywords
- harassing
- identification
- harassment
- unfamiliar
- broadcast information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012790 confirmation Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims description 65
- 238000012545 processing Methods 0.000 claims description 13
- 238000012706 support-vector machine Methods 0.000 claims description 12
- 238000007477 logistic regression Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000010365 information processing Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 3
- 238000010295 mobile communication Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a method and a system for identifying crank calls based on a block chain. The method comprises the following steps: receiving strange number broadcast information from a blockchain network; the strange number broadcast information comprises strange telephone numbers; judging whether the unfamiliar telephone number is a harassing number or not based on the first harassing number identification model; the first harassment number identification model is a harassment number identification model stored in the first node; when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information which is generated and sent by a second node according to unfamiliar number broadcast information and a second harassing number identification model from a block chain network; the second node is other nodes except the first node in the block chain network; the identification result broadcast information comprises a confirmation result or a denial result; and when the identification result broadcast information contains a confirmation result, marking the unfamiliar telephone number as a harassing number. The method and the device can improve the accuracy of identifying the harassing numbers and improve the user experience.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a block chain-based crank call identification method and system.
Background
Strange calls answered by mobile communication users are often flooded with a large number of harassing calls, which greatly affects the work and life of the mobile communication users. To protect against nuisance calls, many users choose to reject all strange calls, which in turn may cause the mobile user to miss important calls. In order to facilitate the user to reject the crank call from the strange call without missing the important call, the mobile terminal needs to identify whether the strange call is the crank call.
The method for identifying whether an unfamiliar incoming call is a harassing call by a mobile terminal at present usually identifies through a harassing call number library and a yellow page library which are locally stored, but the method has the defects of long training time and difficulty in real-time sharing, so that the accuracy rate of identifying the harassing call by the mobile terminal is low, and the user experience is poor.
Disclosure of Invention
Therefore, the invention provides a method and a system for identifying crank calls based on a block chain, which are used for solving the problems of low crank call identification accuracy and poor user experience caused by the fact that a mobile terminal identifies crank calls through a locally stored crank call number library and a yellow page library in the prior art.
In order to achieve the above object, a first aspect of the present invention provides a method for identifying a harassing call based on a block chain, where the method includes:
receiving strange number broadcast information from a blockchain network; the unfamiliar number broadcast information comprises unfamiliar telephone numbers;
judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model; the first harassment number identification model is a harassment number identification model stored in the first node;
when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information generated and sent by a second node according to unfamiliar number broadcast information and a second harassing number identification model from a block chain network; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in a second node; the identification result broadcast information comprises a confirmation result or a denial result;
and when the identification result broadcast information contains a confirmation result, marking the unfamiliar telephone number as a harassing number.
Preferably, the step of marking the unfamiliar telephone number as a harassing number when the identification result broadcast message contains a confirmation result includes:
acquiring the number of the identification result broadcast information including the confirmation result received from the blockchain network; the block chain network comprises 2M nodes, wherein M is a positive integer;
and when the number of the identification result broadcast information is not less than M, marking the unfamiliar telephone number as a harassing number.
Preferably, after the step of marking the unfamiliar telephone number as a harassing number, the method further comprises the following steps:
sending the unfamiliar telephone numbers marked as harassing numbers to a harassing number identification library so that the unfamiliar telephone numbers are stored in the harassing number identification library; the harassment number identification library is a number database stored in the block chain network.
Preferably, before the receiving the strange number broadcast information from the blockchain network, the method further includes:
acquiring training data from a harassment number recognition library; the harassment number identification library is a number database stored in the block chain network;
carrying out data preprocessing on the training data to obtain effective training data;
and training a first harassment number learning model based on the effective training data to obtain a first harassment number identification model.
Preferably, the step of performing data preprocessing on the training data includes:
null processing, outlier processing, and/or training data normalization is performed on the training data using a big data processing tool.
Preferably, the step of training the first disturbance number learning model based on the effective training data includes:
and training a first harassment number learning model based on the effective training data and by adopting a support vector machine algorithm, a logistic regression algorithm or an extreme gradient boosting algorithm.
Preferably, the training data includes nuisance number data and non-nuisance number data.
The invention provides a system for identifying harassing calls based on block chains, which comprises:
the first receiving module is used for receiving strange number broadcast information from the block chain network; the unfamiliar number broadcast information comprises unfamiliar telephone numbers;
the first judgment module is used for judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model; the first harassment number identification model is a harassment number identification model stored in the first node;
the second receiving module is used for receiving identification result broadcast information which is generated and sent by a second node according to the unfamiliar number broadcast information and a second harassing number identification model from a block chain network when the unfamiliar telephone number is a harassing number; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in a second node; the identification result broadcast information comprises a confirmation result or a denial result;
and the first marking module is used for marking the unfamiliar telephone number as a harassing number when the identification result broadcast information contains a confirmation result.
Preferably, the system further comprises:
the first sending module is used for sending the unfamiliar telephone numbers marked as harassing numbers to a harassing number identification library so as to enable the harassing number identification library to store the unfamiliar telephone numbers; the harassment number identification library is a number database stored in the block chain network.
Preferably, the system further comprises:
the first acquisition module is used for acquiring training data from the harassment number recognition library; the harassment number identification library is a number database stored in the block chain network;
the first information processing module is used for carrying out data preprocessing on the training data to obtain effective training data;
and the first training module is used for training a first harassment number learning model based on the effective training data to obtain a first harassment number identification model.
The invention has the following advantages:
the invention provides a harassment number identification method based on a blockchain network. Secondly, judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model, wherein the first harassing number identification model is a harassing number identification model stored in a first node; when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information which is generated and sent by a second node according to unfamiliar number broadcast information and a second harassing number identification model from a block chain network; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in the second node; finally, when the identification result broadcast information contains the confirmation result, the unfamiliar telephone number is marked as the harassing number, and it needs to be stated that when the method judges that the unfamiliar telephone number is the harassing number, the unfamiliar telephone number is not directly marked as the harassing number, but the unfamiliar telephone number is marked as the harassing number through the identification result broadcast information from the second node, so that the identification accuracy of the harassing number is effectively improved, and the user experience is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a flowchart of a method for identifying a harassing call based on a block chain according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for generating a first harassment number identification model according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a block chain-based crank call identification system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a block chain-based crank call identification system according to an embodiment of the present invention.
In the drawings:
31: the first receiving module 32: first judging module
33: the second receiving module 34: first marking module
41: the first obtaining module 42: first information processing module
43: first training module
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Strange calls answered by mobile communication users are often flooded with a large number of harassing calls, which greatly affects the work and life of the mobile communication users. To protect against nuisance calls, many users choose to reject all strange calls, which in turn may cause the mobile user to miss important calls. In order to facilitate the user to reject the crank call from the strange call without missing the important call, the mobile terminal needs to identify whether the strange call is the crank call.
The method for identifying whether an unfamiliar incoming call is a harassing call by a mobile terminal at present usually identifies through a harassing call number library and a yellow page library which are locally stored, but the method has the defects of long training time and difficulty in real-time sharing, so that the accuracy rate of identifying the harassing call by the mobile terminal is low, and the user experience is poor.
In order to solve the above problem, the present embodiment provides a method for identifying a harassing call based on a block chain, as shown in fig. 1, where the method includes the following steps:
step S101, strange number broadcast information is received from the blockchain network.
The unfamiliar number broadcast information is information which is generated according to an unfamiliar call and sent to the blockchain network when any node in the blockchain network receives the unfamiliar call. In one embodiment, the first node receives the unfamiliar number broadcast information in real-time over a blockchain network. The strange number broadcast information comprises strange telephone numbers corresponding to strange calls.
It should be noted that, because a harassment number identification library is stored in the blockchain network, the harassment number identification library contains prestored telephone number data, and all nodes in the blockchain network share the prestored telephone number data. Therefore, the strange phone number in the present embodiment refers to a number that is not included in the pre-stored phone number data. It should be noted that the pre-stored phone number data is a tagged phone number data, including a number data with a harassing number tag and a number data with a non-harassing number tag.
And S102, judging whether the unfamiliar telephone number is a harassing number or not based on the first harassing number identification model.
The first harassing number identification model is a harassing number identification model stored in the first node.
In one embodiment, the first harassing number recognition model is generated and stored before the first node receives unfamiliar number broadcast information from the blockchain network. As shown in fig. 2, the method for generating the first harassment number identification model by the first node includes:
step S201, training data are obtained from the harassment number recognition library. The harassment number identification library is a number database stored in the block chain network. The training data acquired by the first node from the harassing number recognition library comprises harassing number data and non-harassing number data.
Step S202, carrying out data preprocessing on the training data to obtain effective training data.
The effective data comprises effective harassing number data and effective non-harassing number data. In one embodiment, the step of the first node performing data preprocessing on the training data comprises: and carrying out null value processing, abnormal value processing and/or training data standardization on the training data by utilizing a big data processing tool, wherein the big data processing tool comprises spark and Flink.
Step S203, training a first harassment number learning model based on the effective training data to obtain a first harassment number recognition model.
And the first harassment number learning model is an initial model constructed by the first node. In one embodiment, the first node trains the first disturbance number learning model based on the effective training data and by using a Support Vector Machine (SVM) algorithm, a logistic regression algorithm, or an eXtreme Gradient Boosting (xgboost) algorithm, so as to obtain a first disturbance number recognition model.
It should be noted that, in this embodiment, after the first node determines whether the unfamiliar phone number is a harassing number based on the first harassing number identification model, the first node does not directly operate the unfamiliar phone number, but continues to perform the following steps to reduce an error of harassing number identification and improve accuracy of harassing number identification.
And step S103, when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information generated and sent by the second node according to unfamiliar number broadcast information and a second harassing number identification model from the block chain network.
The second node is other nodes except the first node in the block chain network; the identification result broadcast information comprises a confirmation result or a denial result; the second disturbance number identification model is a disturbance number identification model stored in the second node.
In one embodiment, the second harassment number identification model is a harassment number identification model obtained and stored by the second node by using a Support Vector Machine (SVM) algorithm, a logistic regression algorithm, or an eXtreme Gradient boost (xgboost) algorithm.
In another embodiment, the second harassing number identification model is a harassing number identification model obtained by the second node by adopting a different algorithm from that of the first node, that is, the harassing number identification models obtained and stored by different nodes have diversity. For example, a first node firstly obtains a first harassment number identification model by using a logistic regression algorithm, and a second node obtains information of the first harassment number identification model obtained by the first node by using the logistic regression algorithm and then selects a terminal gradient extraction algorithm to obtain a second harassment number identification model as all data in a block chain network can be shared. It should be noted that, because the harassing number identification model has diversity, the first node receives the identification result broadcast information generated and sent by the second node according to the unfamiliar number broadcast information and the second harassing number identification model from the blockchain network, so that the error of harassing number identification can be reduced to the maximum extent, and the accuracy of harassing number identification is improved.
And step S104, when the identification result broadcast information contains a confirmation result, marking the unfamiliar telephone number as a harassing number.
In one embodiment, the blockchain network includes 2M nodes, M being a positive integer. When the identification result broadcast information contains the confirmation result, the first node acquires the number of the identification result broadcast information containing the confirmation result received from the blockchain network; and when the number of the identification result broadcast information is not less than M, marking the unfamiliar telephone number as a harassing number. It should be noted that when the number of the identification result broadcast information including the confirmation result acquired by the first node is not less than M, it is indicated that more than half of the nodes in the block chain network determine that the strange phone number is a harassing number, that is, the strange phone number is a harassing number with a very high possibility, and therefore, the identification accuracy of the harassing number can be effectively improved by marking the strange phone number as a harassing number at this time.
It should be noted that, as can be seen from the foregoing steps S102 to S104, when the first node determines that the unfamiliar telephone number is a harassing number, the unfamiliar telephone number is not directly marked as a harassing number, but the unfamiliar telephone number is marked as a harassing number by the identification result broadcast information from the second node, so that an error in identification of the harassing number is effectively reduced, accuracy in identification of the harassing number is improved, and user experience is improved.
In another embodiment, after the strange telephone number is marked as a harassing number, the first node further sends the strange telephone number marked as the harassing number to a harassing number recognition library so that the harassing number recognition library stores the strange telephone number, wherein the harassing number recognition library is a number database stored in the block chain network. After the harassing number identification library stores the unfamiliar telephone number, all nodes in the block chain network can directly judge that the unfamiliar telephone number is a harassing number through the harassing number identification library, and the harassing number identification efficiency of all nodes in the block chain network is improved.
The embodiment provides a harassment number identification method based on a blockchain network. Secondly, judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model, wherein the first harassing number identification model is a harassing number identification model stored in a first node; when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information which is generated and sent by a second node according to unfamiliar number broadcast information and a second harassing number identification model from a block chain network; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in the second node; finally, when the identification result broadcast information contains the confirmation result, the unfamiliar telephone number is marked as the harassing number, and it needs to be stated that when the method judges that the unfamiliar telephone number is the harassing number, the unfamiliar telephone number is not directly marked as the harassing number, but the unfamiliar telephone number is marked as the harassing number through the identification result broadcast information from the second node, so that the identification accuracy of the harassing number is effectively improved, and the user experience is improved.
The embodiment also provides a block chain-based harassing call identification system, as shown in fig. 3, where the system includes: a first receiving module 31, a first judging module 32, a second receiving module 33 and a first marking module 34.
The first receiving module 31 is configured to receive strange number broadcast information from the blockchain network. Wherein, the strange number broadcast information comprises strange telephone numbers.
The first judging module 32 is configured to judge whether the unfamiliar phone number is a harassing number based on the first harassing number identification model. The first harassing number identification model is a harassing number identification model stored in the first node.
In one embodiment, as shown in fig. 4, the block chain-based harassing call identification system further includes: a first acquisition module 41, a first information processing module 42 and a first training module 43. The harassing call recognition system generates a first harassing number recognition model through a first obtaining module 41, a first information processing module 42 and a first training module 43, and specifically:
first, the first obtaining module 41 obtains training data from the harassment number recognition library. The harassment number identification library is a number database stored in the block chain network. The training data acquired by the first node from the harassing number recognition library comprises harassing number data and non-harassing number data.
Secondly, the first information processing module 42 performs data preprocessing on the training data to obtain effective training data, wherein the effective data includes effective harassing number data and effective non-harassing number data. In one embodiment, the first information processing module performing data preprocessing on the training data comprises: the first information processing module performs null processing, outlier processing, and/or training data normalization on the training data using a big data processing tool, which includes spark and Flink.
Finally, the first training module 43 trains the first disturbance number learning model based on the effective training data to obtain a first disturbance number recognition model. And the first harassment number learning model is an initial model constructed by the first training module. In one embodiment, the first training module trains the first harassment number learning model based on the valid training data and by using a Support Vector Machine (SVM) algorithm, a logistic regression algorithm, or an eXtreme Gradient Boosting (xgboost) algorithm, so as to obtain the first harassment number recognition model.
After the first judging module 32 judges whether the unfamiliar telephone number is a harassing number based on the first harassing number identification model, the second receiving module 33 is configured to receive, from the block chain network, identification result broadcast information generated and sent by the second node according to unfamiliar number broadcast information and the second harassing number identification model when the unfamiliar telephone number is a harassing number.
The second node is other nodes except the first node in the block chain network; the identification result broadcast information comprises a confirmation result or a denial result; the second disturbance number identification model is a disturbance number identification model stored in the second node. In one embodiment, the second harassment number identification model is a harassment number identification model obtained and stored by the second node by using a Support Vector Machine (SVM) algorithm, a logistic regression algorithm, or an eXtreme Gradient boost (xgboost) algorithm.
And the first marking module 34 is used for marking the unfamiliar telephone number as a harassing number when the identification result broadcast information contains a confirmation result.
In one embodiment, the blockchain network includes 2M nodes, M being a positive integer; the block chain network-based harassment number identification system further comprises: and a second obtaining module. When the identification result broadcast information contains the confirmation result, the number of the identification result broadcast information containing the confirmation result received by the second acquisition module from the blockchain network; when the number of the identification result broadcast messages is not less than M, the first marking module 34 marks the unfamiliar telephone number as a harassing number. It should be noted that when the number of the identification result broadcast information including the confirmation result acquired by the second acquisition module is not less than M, it is indicated that more than half of the nodes in the block chain network determine that the strange phone number is a harassing number, that is, the strange phone number is a harassing number with a very high possibility, and therefore, the first marking module 34 marks the strange phone number as a harassing number at this time can effectively improve the accuracy of harassing number identification.
It should be noted that, according to this embodiment, when the first determining module 32 determines that the unfamiliar phone number is a harassing number, the first marking module 34 does not directly mark the unfamiliar phone number as a harassing number, but marks the unfamiliar phone number as a harassing number through the identification result broadcast information from the second node received by the second receiving module 33, so that an error of harassing number identification is effectively reduced, accuracy of harassing number identification is improved, and user experience is improved.
In another embodiment, the block chain network-based harassment number identification system further includes: a first sending module. After the first marking module 34 marks the unfamiliar telephone number as the harassing number, the first sending module sends the unfamiliar telephone number marked as the harassing number to a harassing number identification library so that the harassing number identification library stores the unfamiliar telephone number, wherein the harassing number identification library is a number database stored in the block chain network. After the harassing number identification library stores the unfamiliar telephone number, all nodes in the block chain network can directly judge that the unfamiliar telephone number is a harassing number through the harassing number identification library, and the harassing number identification efficiency of all nodes in the block chain network is improved.
The working modes of the modules in the block chain-based crank call identification system provided by this embodiment correspond to the steps in the block chain-based crank call identification method, and therefore, the detailed working modes of the modules in the block chain-based crank call identification system can be referred to in the block chain-based crank call identification method provided by this embodiment.
The embodiment provides a harassment number identification system based on a blockchain network, which firstly receives strange number broadcast information from the blockchain network through a first receiving module 31, wherein the strange number broadcast information comprises strange telephone numbers. Secondly, the first judging module 32 judges whether the unfamiliar telephone number is a harassing number based on a first harassing number identification model, wherein the first harassing number identification model is a harassing number identification model stored in the first node; when the unfamiliar telephone number is a harassing number, the second receiving module 33 receives identification result broadcast information which is generated and sent by the second node according to unfamiliar number broadcast information and a second harassing number identification model from the block chain network; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in the second node; finally, when the identification result broadcast information contains the confirmation result, the first marking module 34 marks the unfamiliar telephone number as the harassing number, and it should be noted that when the first judging module 32 judges that the unfamiliar telephone number is the harassing number in the system, the first marking module 34 does not directly mark the unfamiliar telephone number as the harassing number, but marks the unfamiliar telephone number as the harassing number through the identification result broadcast information from the second node received by the second receiving module 33, so that the identification accuracy of the harassing number is effectively improved, and the user experience is improved.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (8)
1. A block chain-based crank call identification method is characterized by comprising the following steps:
receiving strange number broadcast information from a blockchain network; the unfamiliar number broadcast information comprises unfamiliar telephone numbers; the unfamiliar telephone number refers to a number which is not contained in telephone number data prestored in a harassment number recognition library of the blockchain network;
judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model; the first harassment number identification model is a harassment number identification model stored in the first node;
when the unfamiliar telephone number is a harassing number, receiving identification result broadcast information generated and sent by a second node according to unfamiliar number broadcast information and a second harassing number identification model from a block chain network; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in a second node; the identification result broadcast information comprises a confirmation result or a denial result;
when the identification result broadcast information contains a confirmation result, marking the unfamiliar telephone number as a harassing number;
before the receiving strange number broadcast information from the blockchain network, the method further comprises the following steps:
acquiring training data from a harassment number recognition library; the harassment number identification library is a number database stored in the block chain network;
carrying out data preprocessing on the training data to obtain effective training data;
training a first harassment number learning model by adopting any one algorithm of a support vector machine algorithm, a logistic regression algorithm or an extreme gradient lifting algorithm based on the effective training data to obtain a first harassment number identification model; and the second harassing number identification model is obtained by the second node by adopting an algorithm different from that of the first node.
2. The method according to claim 1, wherein the step of marking the unfamiliar telephone number as a harassing number when the identification broadcast message contains a confirmation, comprises:
acquiring the number of the identification result broadcast information including the confirmation result received from the blockchain network; the block chain network comprises 2M nodes, wherein M is a positive integer;
and when the number of the identification result broadcast information is not less than M, marking the unfamiliar telephone number as a harassing number.
3. The method of claim 1, wherein after said marking said strange phone number as a harassing number, further comprising:
sending the unfamiliar telephone numbers marked as harassing numbers to a harassing number identification library so that the unfamiliar telephone numbers are stored in the harassing number identification library; the harassment number identification library is a number database stored in the block chain network.
4. The method of claim 1, wherein the step of pre-processing the training data comprises:
null processing, outlier processing, and/or training data normalization is performed on the training data using a big data processing tool.
5. The method of claim 1, wherein the step of training a first disturbance number learning model based on the valid training data comprises:
and training a first harassment number learning model based on the effective training data and by adopting a support vector machine algorithm, a logistic regression algorithm or an extreme gradient boosting algorithm.
6. The method of claim 1, wherein the training data comprises nuisance number data and non-nuisance number data.
7. A system for blockchain-based identification of nuisance calls, the system comprising:
the first receiving module is used for receiving strange number broadcast information from the block chain network; the unfamiliar number broadcast information comprises unfamiliar telephone numbers; the unfamiliar telephone number refers to a number which is not contained in telephone number data prestored in a harassment number recognition library of the blockchain network;
the first judgment module is used for judging whether the unfamiliar telephone number is a harassing number or not based on a first harassing number identification model; the first harassment number identification model is a harassment number identification model stored in the first node;
the second receiving module is used for receiving identification result broadcast information which is generated and sent by a second node according to the unfamiliar number broadcast information and a second harassing number identification model from a block chain network when the unfamiliar telephone number is a harassing number; the second node is other nodes except the first node in the block chain network; the second harassment number identification model is a harassment number identification model stored in a second node; the identification result broadcast information comprises a confirmation result or a denial result;
the first marking module is used for marking the unfamiliar telephone number as a harassing number when the identification result broadcast information contains a confirmation result;
the first acquisition module is used for acquiring training data from the harassment number recognition library; the harassment number identification library is a number database stored in the block chain network;
the first information processing module is used for carrying out data preprocessing on the training data to obtain effective training data;
the first training module is used for training a first harassment number learning model by adopting any one algorithm of a support vector machine algorithm, a logistic regression algorithm or an extreme gradient lifting algorithm based on the effective training data to obtain a first harassment number identification model; and the second harassing number identification model is obtained by the second node by adopting an algorithm different from that of the first node.
8. The system of claim 7, further comprising:
the first sending module is used for sending the unfamiliar telephone numbers marked as harassing numbers to a harassing number identification library so as to enable the harassing number identification library to store the unfamiliar telephone numbers; the harassment number identification library is a number database stored in the block chain network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010626615.0A CN111787159B (en) | 2020-07-02 | 2020-07-02 | Block chain-based crank call identification method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010626615.0A CN111787159B (en) | 2020-07-02 | 2020-07-02 | Block chain-based crank call identification method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111787159A CN111787159A (en) | 2020-10-16 |
CN111787159B true CN111787159B (en) | 2022-03-18 |
Family
ID=72758073
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010626615.0A Active CN111787159B (en) | 2020-07-02 | 2020-07-02 | Block chain-based crank call identification method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111787159B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106878528A (en) * | 2017-01-23 | 2017-06-20 | 北京思特奇信息技术股份有限公司 | A kind of disturbance incoming call SMS interception method and system based on block chain technology |
CN108810901A (en) * | 2018-04-17 | 2018-11-13 | 中国地质大学(武汉) | A kind of malice number mark recognition methods based on block chain |
CN109327627A (en) * | 2018-11-27 | 2019-02-12 | 深圳声笑科技有限公司 | Telephone number recognition methods, device and storage medium based on block chain |
CN109728896A (en) * | 2018-12-26 | 2019-05-07 | 广州云趣信息科技有限公司 | A kind of incoming call certification and source tracing method and process based on block chain |
US10477024B1 (en) * | 2017-05-30 | 2019-11-12 | United Services Automobile Association (Usaa) | Dynamic resource allocation |
CN111132172A (en) * | 2019-12-30 | 2020-05-08 | 山东爱城市网信息技术有限公司 | Method, device and medium for preventing telecommunication fraud based on block chain |
CN111327771A (en) * | 2018-12-17 | 2020-06-23 | 中国移动通信集团青海有限公司 | Method and device for identifying crank call number |
-
2020
- 2020-07-02 CN CN202010626615.0A patent/CN111787159B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106878528A (en) * | 2017-01-23 | 2017-06-20 | 北京思特奇信息技术股份有限公司 | A kind of disturbance incoming call SMS interception method and system based on block chain technology |
US10477024B1 (en) * | 2017-05-30 | 2019-11-12 | United Services Automobile Association (Usaa) | Dynamic resource allocation |
CN108810901A (en) * | 2018-04-17 | 2018-11-13 | 中国地质大学(武汉) | A kind of malice number mark recognition methods based on block chain |
CN109327627A (en) * | 2018-11-27 | 2019-02-12 | 深圳声笑科技有限公司 | Telephone number recognition methods, device and storage medium based on block chain |
CN111327771A (en) * | 2018-12-17 | 2020-06-23 | 中国移动通信集团青海有限公司 | Method and device for identifying crank call number |
CN109728896A (en) * | 2018-12-26 | 2019-05-07 | 广州云趣信息科技有限公司 | A kind of incoming call certification and source tracing method and process based on block chain |
CN111132172A (en) * | 2019-12-30 | 2020-05-08 | 山东爱城市网信息技术有限公司 | Method, device and medium for preventing telecommunication fraud based on block chain |
Also Published As
Publication number | Publication date |
---|---|
CN111787159A (en) | 2020-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101753674B (en) | Incoming call processing method and device of a communication terminal | |
CN104349324B (en) | Mobile terminal number intelligent protection system and method | |
CN111104521B (en) | Anti-fraud detection method and detection system based on graph analysis | |
CN112615753B (en) | Link abnormity tracking method, first node, second node and link | |
CN105827787A (en) | Number marking method and number marking device | |
WO2016029781A1 (en) | Method and device for switching sim cards of communication terminal and computer storage medium | |
CN106171019A (en) | Determine the method for terminal roaming status, device, terminal and server | |
CN113840040B (en) | Man-machine cooperation outbound method, device, equipment and storage medium | |
CN104486761A (en) | Terminal communication method and device | |
CN107707723A (en) | The hold-up interception method of harassing call | |
CN105376426A (en) | Information management method based on address book and mobile terminal | |
CN107182078B (en) | Method for analyzing circuit switched fallback test report of terminal, terminal and storage device | |
CN109451564A (en) | Method for searching network, device, computer equipment and storage medium | |
US20090318120A1 (en) | Mobile telephone apparatus and call reception history producing method used by the same | |
CN111787159B (en) | Block chain-based crank call identification method and system | |
CN113055523B (en) | Crank call interception method and device, electronic equipment and storage medium | |
CN107682219B (en) | Android system-based dial testing method and device for testing number | |
CN111343347A (en) | Communication device, communication system and communication control method | |
CN104935736A (en) | Method and device for processing missed calls | |
CN105635497A (en) | Terminal call transfer method and call transfer terminal | |
CN104506743A (en) | Method and device for dynamically intercepting call | |
CN111291123A (en) | Task node management method and device | |
CN103813034B (en) | A kind of method of business realizing, terminal and service server | |
WO2016070638A1 (en) | Method for preventing nuisance calls, and switch | |
CN108174378A (en) | Number identification method, device, terminal and storage medium |
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 |