CN117132392A - Vehicle loan fraud risk early warning method and system - Google Patents
Vehicle loan fraud risk early warning method and system Download PDFInfo
- Publication number
- CN117132392A CN117132392A CN202311373051.4A CN202311373051A CN117132392A CN 117132392 A CN117132392 A CN 117132392A CN 202311373051 A CN202311373051 A CN 202311373051A CN 117132392 A CN117132392 A CN 117132392A
- Authority
- CN
- China
- Prior art keywords
- call
- vehicle loan
- fraud risk
- fraud
- text
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004891 communication Methods 0.000 claims abstract description 44
- 238000003062 neural network model Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000013461 design Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application discloses a vehicle loan fraud risk early warning method and system, and relates to the technical field of fraud detection. The method comprises the steps of obtaining a calling number in a vehicle loan conversation; acquiring multidimensional communication characteristics of a calling number in a historical time period; the multidimensional communication characteristic is used as input of a neural network model to operate, so that a fraud risk identification result of the vehicle loan conversation is obtained; if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text; identifying whether sensitive words associated with personal privacy information exist in the call text; if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic recognition; if there is an inquiry sentence associated with the sensitive word, the called user is alerted to the risk of vehicle loan fraud. The application can accurately identify the risk of vehicle loan fraud and perform early warning.
Description
Technical Field
The application belongs to the technical field of fraud detection, and particularly relates to a vehicle loan fraud risk early warning method and system.
Background
With the diversity of telecommunication fraud, various kinds of fraud are unqualified, and the economic loss to users is increased. The vehicle loan fraud is one of the fraud modes in telecommunication fraud, and the more common mode in the vehicle loan fraud is to take the user identification card number, the bank card account number and the password, and the transmitted verification information, etc. in the name of the vehicle loan, steal the deposit in the bank card, and take the name of the deceived person or transact various businesses, etc.
At present, for the fraud prevention mode of vehicle loan fraud, the more common mode is to identify the keywords in the sent fraud short messages and intercept the suspected fraud short messages, however, for fraudulent telephones, the telecom operator does not have a more effective method for identifying and timely early warning the calls possibly at risk of vehicle loan fraud.
Therefore, how to provide an effective solution to detect and early warn of calls at risk of vehicle loan fraud has become a major issue in the prior art.
Disclosure of Invention
The application aims to provide a vehicle loan fraud risk early warning method and system, which are used for solving the problems in the prior art.
In order to achieve the above purpose, the present application adopts the following technical scheme:
in a first aspect, the present application provides a vehicle loan fraud risk early warning method, including:
acquiring a calling number in a vehicle loan conversation;
acquiring multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before a current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics;
calculating the multi-dimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk identification result of the vehicle loan call, wherein the fraud risk identification result is obtained by training with the multi-dimensional communication characteristics of a calling number in a historical time period of a specified duration in a sample vehicle loan call as input and the known fraud risk identification result corresponding to the sample vehicle loan call as output;
if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text;
identifying whether sensitive words associated with personal privacy information exist in the call text;
if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic recognition;
and prompting the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists.
Based on the above disclosure, the application obtains the calling number in the vehicle loan conversation; acquiring a multidimensional communication characteristic of a calling number in a historical time period of a designated duration before a current time point; the multidimensional communication characteristic is used as input of a pre-trained neural network model to operate, so that a fraud risk identification result of the vehicle loan conversation is obtained; if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text; identifying whether sensitive words associated with personal privacy information exist in the call text; if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic recognition; if there is an inquiry sentence associated with the sensitive word, the called user is alerted to the risk of vehicle loan fraud. Therefore, whether the vehicle loan call has fraud risk or not can be identified through sensitive word detection and semantic identification, and the called user is prompted when the fraud risk exists, so that the vehicle loan fraud risk can be accurately identified and early warning can be carried out, a good fraud prevention effect is achieved, and economic losses of the user due to fraud are avoided.
Through the design, the application can identify whether the vehicle loan call has fraud risk or not through sensitive word detection and semantic recognition, and prompt a called user when the fraud risk exists, thereby more accurately identifying the vehicle loan fraud risk and carrying out early warning, further achieving better fraud prevention effect, avoiding economic loss of the user caused by fraud, and being convenient for practical application and popularization.
In one possible design, the identifying, by semantic recognition, whether there is an inquiry sentence associated with the sensitive word in the call text includes:
and carrying out semantic recognition based on the sentence where the sensitive word is located and the context of the sentence where the sensitive word is located so as to recognize whether an inquiry sentence associated with the sensitive word exists in the call text.
In one possible design, the calling call feature includes average call times and/or average call duration of calls called by the calling number, the traffic feature includes average daily active duration of uplink and downlink traffic and/or average uplink and downlink traffic, and the communication data region feature includes consistency of call roaming, short message and traffic roaming.
In one possible design, the reminding the called user of the risk of vehicle loan fraud includes:
and sending prompt voice to the called user to prompt the called user to have fraud risk.
In one possible design, before obtaining the calling number in the vehicle loan call, the method further comprises:
and carrying out semantic recognition on the voice call in the current call, and recognizing whether the voice call in the current call is a vehicle loan call or not.
In one possible design, the neural network model is a support vector machine model.
In one possible design, the personal privacy information includes an identification card number, a bank card password, and/or a short message authentication code.
In a second aspect, the present application provides a vehicle loan fraud risk warning system, comprising:
the first acquisition unit is used for acquiring a calling number in a vehicle loan conversation;
the second acquisition unit is used for acquiring the multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before the current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics;
the first recognition unit is used for calculating the multidimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk recognition result of the vehicle loan call, wherein the fraud risk recognition result is obtained by training with the multidimensional communication characteristics of a calling number in a historical time period of a designated duration in a sample vehicle loan call as input and the known fraud risk recognition result corresponding to the sample vehicle loan call as output;
the text conversion unit is used for converting the vehicle loan conversation into a text to obtain a conversation text if the fraud risk identification result is that the fraud risk is suspected;
the second recognition unit is used for recognizing whether sensitive words associated with personal privacy information exist in the call text;
a third recognition unit, configured to recognize whether an inquiry sentence associated with a sensitive word exists in the call text through semantic recognition if the sensitive word associated with the personal privacy information exists in the call text;
and the reminding unit is used for reminding the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists.
In a third aspect, the present application provides an electronic device, comprising a memory, a processor and a transceiver, which are communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to send and receive a message, and the processor is configured to read the computer program, and execute the vehicle loan fraud risk early warning method according to the first aspect or any of the possible designs of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the vehicle loan fraud risk warning method of the first aspect or any of the first aspects that may be devised.
In a fifth aspect, the application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the vehicle loan fraud risk warning method of the first aspect or any of the possible designs of the first aspect.
The beneficial effects are that:
the vehicle loan fraud risk early warning method and system provided by the application can identify whether the vehicle loan call has fraud risk or not through sensitive word detection and semantic recognition, and prompt a called user when the fraud risk exists, so that the vehicle loan fraud risk can be accurately identified and early warning is carried out, a good fraud prevention effect is achieved, economic loss of the user caused by fraud is avoided, and the method and system are convenient for practical application and popularization.
Drawings
FIG. 1 is a flow chart of a method for warning of risk of fraud in a vehicle loan, according to an embodiment of the application;
FIG. 2 is a schematic diagram of a vehicle loan fraud risk warning system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the present application will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present application, but is not intended to limit the present application.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present application.
It should be understood that for the term "and/or" that may appear herein, it is merely one association relationship that describes an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a alone, B alone, and both a and B; for the term "/and" that may appear herein, which is descriptive of another associative object relationship, it means that there may be two relationships, e.g., a/and B, it may be expressed that: a alone, a alone and B alone; in addition, for the character "/" that may appear herein, it is generally indicated that the context associated object is an "or" relationship.
In order to detect and early warn a call with a vehicle loan fraud risk, the embodiment of the application provides a vehicle loan fraud risk early warning method and system.
The vehicle loan fraud risk early warning method provided by the embodiment of the application can be applied to a call server of a telecom operator. It will be appreciated that the execution body is not to be construed as limiting the embodiments of the application.
The method for warning the risk of vehicle loan fraud provided by the embodiment of the application is described in detail below.
As shown in fig. 1, a flowchart of a vehicle loan fraud risk warning method provided in the first aspect of the embodiment of the application may include, but is not limited to, the following steps S101-S107.
S101, acquiring a calling number in a vehicle loan conversation.
In the embodiment of the application, when a voice call occurs, by carrying out semantic recognition on the voice call in the current call, whether the voice call in the current call is a vehicle loan call is recognized, and when the voice call in the current call is the vehicle loan call, the calling number in the vehicle loan call is acquired. The vehicle loan call may refer to a call whose content of the call is related to the vehicle loan.
In the embodiment of the application, whether the voice call in the current call is the vehicle loan call can be identified through semantic identification. It will be appreciated that in other embodiments, it is also possible to identify whether the voice call in the current call is a vehicle loan call by keyword recognition. For example, when keywords such as "car loan", "car loan" are present in the voice call, the voice call in the current call may be determined to be a car loan call.
S102, acquiring multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before a current time point.
The historical time period of the specified duration before the current time point may be within one month before the current time point or within one year before the current time point, which is not particularly limited in the embodiment of the present application. The multi-dimensional communication features may include, but are not limited to, caller identification features, short message frequency features, traffic features, and/or communication data territory features. The calling call feature may include, but is not limited to, an average number of calls (such as daily or every hour) and/or an average call duration of calls called by the calling number, the traffic feature may include, but is not limited to, a daily average active duration including uplink and downlink traffic and/or a daily average uplink and downlink traffic, and the short message frequency feature may refer to an average number of times of sending short messages each day or every hour, where the communication data region feature includes call roaming, short messages, and consistency of traffic roaming. And if the call roaming place, the short message sending place and the flow roaming place are the same, the call roaming, the short message and the flow roaming are considered to be consistent, otherwise, the call roaming, the short message and the flow roaming are considered to be inconsistent.
And S103, calculating the multidimensional communication characteristic as input of a pre-trained neural network model to obtain a fraud risk identification result of the vehicle loan conversation.
Wherein the fraud risk identification result is that there is no fraud risk or there is a suspected fraud risk.
Specifically, in the embodiment of the application, a neural network model for detecting whether fraud risk is suspected to exist is trained in advance, and the neural network model can be obtained by training with the multi-dimensional communication characteristic of the calling number in the sample vehicle loan call in the historical time period of the appointed duration as input and the known fraud risk identification result corresponding to the sample vehicle loan call as output. The neural network model may be, but is not limited to, a support vector machine (support vector machines, SVM) model, a convolutional neural network (Convolutional Neural Networks, CNN) model, or the like.
After the multi-dimensional communication characteristic of the calling number in the historical time period of the appointed duration before the current time point is obtained, the multi-dimensional communication characteristic can be used as input of a pre-trained neural network model to operate, so that a fraud risk identification result of the vehicle loan conversation is obtained, wherein the fraud risk identification result is that no fraud risk exists or the fraud risk is suspected to exist.
And S104, if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text.
The conversion of the vehicle loan call into text may be accomplished by existing text conversion algorithms, such as automatic speech recognition (Automatic Speech Recognition, ASR) to convert the vehicle loan call into text, which will not be described in detail herein.
Step S105, identifying whether sensitive words associated with personal privacy information exist in the call text.
The sensitive words associated with the personal privacy information may include, but are not limited to, an identification card number, a bank card password, and/or a short message authentication code. The sensitive words associated with the personal privacy information can be identified by the existing keyword identification algorithm, and detailed description is omitted in the embodiment of the present application.
And S106, if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic identification.
In one or more embodiments, when recognizing whether an inquiry sentence associated with a sensitive word exists in a call text, semantic recognition may be performed based on the sentence in which the sensitive word exists and the context of the sentence in which the sensitive word exists, so as to recognize whether the inquiry sentence associated with the sensitive word exists in the call text. By combining the context for semantic recognition, whether query sentences associated with sensitive words exist in the call text can be more accurately recognized, and recognition accuracy is ensured.
Step S107, if an inquiry statement associated with the sensitive word exists, reminding the called user of the risk of vehicle loan fraud.
In the embodiment of the application, when reminding the called user of the risk of the fraud in the vehicle loan, the call reminding or the call breaking can be used for reminding the called user of the risk of the fraud in the vehicle loan, prompt voice can be sent to the called user to prompt the called user of the risk of the fraud, a call can be made to the called user through a fixed number to inform the called user of the risk of the fraud, and a short message can be sent to the called user to normally the called user of the risk of the fraud.
In summary, the method for warning the risk of fraud in vehicle loan provided by the embodiment of the application obtains the calling number in the vehicle loan conversation; acquiring multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before a current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics; calculating the multi-dimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk identification result of the vehicle loan call, wherein the fraud risk identification result is obtained by training with the multi-dimensional communication characteristics of a calling number in a historical time period of a specified duration in a sample vehicle loan call as input and the known fraud risk identification result corresponding to the sample vehicle loan call as output; if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text; identifying whether sensitive words associated with personal privacy information exist in the call text; if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic recognition; and prompting the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists. Therefore, the double recognition can be performed through the sensitive word detection and the semantic recognition, so that whether the vehicle loan call has fraud risk or not is recognized, and the called user is prompted when the fraud risk exists, so that the vehicle loan fraud risk can be accurately recognized and early warning is performed, a good fraud prevention effect is achieved, economic losses of the user due to fraud are avoided, and the vehicle loan call is convenient to apply and popularize practically.
Referring to fig. 2, a second aspect of the embodiment of the present application provides a vehicle loan fraud risk early warning system, which includes:
the first acquisition unit is used for acquiring a calling number in a vehicle loan conversation;
the second acquisition unit is used for acquiring the multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before the current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics;
the first recognition unit is used for calculating the multidimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk recognition result of the vehicle loan call, wherein the fraud risk recognition result is obtained by training with the multidimensional communication characteristics of a calling number in a historical time period of a designated duration in a sample vehicle loan call as input and the known fraud risk recognition result corresponding to the sample vehicle loan call as output;
the text conversion unit is used for converting the vehicle loan conversation into a text to obtain a conversation text if the fraud risk identification result is that the fraud risk is suspected;
the second recognition unit is used for recognizing whether sensitive words associated with personal privacy information exist in the call text;
a third recognition unit, configured to recognize whether an inquiry sentence associated with a sensitive word exists in the call text through semantic recognition if the sensitive word associated with the personal privacy information exists in the call text;
and the reminding unit is used for reminding the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists.
The working process, working details and technical effects of the system provided in the second aspect of the present embodiment may be referred to in the first aspect of the present embodiment, and are not described herein.
As shown in fig. 3, a third aspect of the embodiment of the present application provides an electronic device, including a memory, a processor, and a transceiver, which are sequentially communicatively connected, where the memory is configured to store a computer program, the transceiver is configured to send and receive a message, and the processor is configured to read the computer program, and perform the vehicle loan fraud risk early warning method according to the first aspect of the embodiment.
By way of specific example, the Memory may include, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), flash Memory (Flash Memory), first-in-first-out Memory (FIFO), and/or first-in-last-out Memory (FILO), etc.; the processor may not be limited to a processor adopting architecture such as a microprocessor, ARM (Advanced RISC Machines), X86, etc. of the model STM32F105 series or a processor integrating NPU (neural-network processing units); the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a general packet radio service technology (General Packet Radio Service, GPRS) wireless transceiver, a ZigBee protocol (low power local area network protocol based on the ieee802.15.4 standard), a 3G transceiver, a 4G transceiver, and/or a 5G transceiver, etc.
A fourth aspect of the present embodiment provides a computer readable storage medium storing instructions comprising the vehicle loan fraud risk warning method according to the first aspect of the present embodiment, i.e. the computer readable storage medium has instructions stored thereon, which when executed on a computer, perform the vehicle loan fraud risk warning method according to the first aspect. The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), etc., where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
A fifth aspect of the present embodiment provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the vehicle loan fraud risk warning method of the first aspect of the embodiment, wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
It should be understood that specific details are provided in the following description to provide a thorough understanding of the example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, a system may be shown in block diagrams in order to avoid obscuring the examples with unnecessary detail. In other instances, well-known processes, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the example embodiments.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the application and is not intended to limit the scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (8)
1. A vehicle loan fraud risk warning method, comprising:
acquiring a calling number in a vehicle loan conversation;
acquiring multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before a current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics;
calculating the multi-dimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk identification result of the vehicle loan call, wherein the fraud risk identification result is obtained by training with the multi-dimensional communication characteristics of a calling number in a historical time period of a specified duration in a sample vehicle loan call as input and the known fraud risk identification result corresponding to the sample vehicle loan call as output;
if the fraud risk identification result is that the fraud risk is suspected, converting the vehicle loan call into a text to obtain a call text;
identifying whether sensitive words associated with personal privacy information exist in the call text;
if the sensitive words associated with the personal privacy information exist in the call text, identifying whether query sentences associated with the sensitive words exist in the call text through semantic recognition;
and prompting the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists.
2. The vehicle loan fraud risk warning method of claim 1, wherein said semantically identifying whether there is an inquiry sentence associated with the sensitive word in the call text comprises:
and carrying out semantic recognition based on the sentence where the sensitive word is located and the context of the sentence where the sensitive word is located so as to recognize whether an inquiry sentence associated with the sensitive word exists in the call text.
3. The vehicle loan fraud risk warning method according to claim 1, characterized in that the calling call feature comprises an average number of calls and/or an average call duration of calls called by the calling number, the traffic feature comprises a daily active duration of uplink and downlink traffic and/or a daily uplink and downlink traffic, and the communication data region feature comprises consistency of call roaming, short message and traffic roaming.
4. The vehicle loan fraud risk warning method of claim 1, wherein the alerting the called user of the presence of the vehicle loan fraud risk comprises:
and sending prompt voice to the called user to prompt the called user to have fraud risk.
5. The vehicle loan fraud risk warning method of claim 1, wherein prior to obtaining the calling number in the vehicle loan session, the method further comprises:
and carrying out semantic recognition on the voice call in the current call, and recognizing whether the voice call in the current call is a vehicle loan call or not.
6. The vehicle loan fraud risk warning method of claim 1, wherein the neural network model is a support vector machine model.
7. The vehicle loan fraud risk warning method of claim 1, wherein the personal privacy information comprises an identification card number, a bank card password, and/or a short message authentication code.
8. A vehicle loan fraud risk warning system, comprising:
the first acquisition unit is used for acquiring a calling number in a vehicle loan conversation;
the second acquisition unit is used for acquiring the multi-dimensional communication characteristics of the calling number in a historical time period of a designated duration before the current time point, wherein the multi-dimensional communication characteristics comprise calling call characteristics, short message frequency characteristics, flow characteristics and communication data region characteristics;
the first recognition unit is used for calculating the multidimensional communication characteristics as input of a pre-trained neural network model to obtain a fraud risk recognition result of the vehicle loan call, wherein the fraud risk recognition result is obtained by training with the multidimensional communication characteristics of a calling number in a historical time period of a designated duration in a sample vehicle loan call as input and the known fraud risk recognition result corresponding to the sample vehicle loan call as output;
the text conversion unit is used for converting the vehicle loan conversation into a text to obtain a conversation text if the fraud risk identification result is that the fraud risk is suspected;
the second recognition unit is used for recognizing whether sensitive words associated with personal privacy information exist in the call text;
a third recognition unit, configured to recognize whether an inquiry sentence associated with a sensitive word exists in the call text through semantic recognition if the sensitive word associated with the personal privacy information exists in the call text;
and the reminding unit is used for reminding the called user of the risk of vehicle loan fraud if the inquiry statement associated with the sensitive word exists.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373051.4A CN117132392B (en) | 2023-10-23 | 2023-10-23 | Vehicle loan fraud risk early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373051.4A CN117132392B (en) | 2023-10-23 | 2023-10-23 | Vehicle loan fraud risk early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117132392A true CN117132392A (en) | 2023-11-28 |
| CN117132392B CN117132392B (en) | 2024-01-30 |
Family
ID=88858439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311373051.4A Active CN117132392B (en) | 2023-10-23 | 2023-10-23 | Vehicle loan fraud risk early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117132392B (en) |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007139864A (en) * | 2005-11-15 | 2007-06-07 | Nec Corp | Apparatus and method for detecting suspicious conversation, and communication device using the same |
| CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
| CN103440287A (en) * | 2013-08-14 | 2013-12-11 | 广东工业大学 | Web question-answering retrieval system based on product information structuring |
| CN103685613A (en) * | 2013-12-05 | 2014-03-26 | 江苏大学 | Telephone-fraud-resistant system based on voice recognition and method thereof |
| CN104936182A (en) * | 2015-04-21 | 2015-09-23 | 中国移动通信集团浙江有限公司 | Method of managing and controlling fraud telephones intelligently and system of managing and controlling fraud telephones intelligently |
| CN105930452A (en) * | 2016-04-21 | 2016-09-07 | 北京紫平方信息技术股份有限公司 | Smart answering method capable of identifying natural language |
| CN105989093A (en) * | 2015-02-12 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Automatic discovery method, device and application of sensitive word |
| CN107148024A (en) * | 2017-06-29 | 2017-09-08 | 胡玥莹 | A kind of anti-swindle communication system and method for being used to recognize strange short message |
| JP2017204023A (en) * | 2016-05-09 | 2017-11-16 | トヨタ自動車株式会社 | Conversation processing device |
| CN107360313A (en) * | 2017-06-29 | 2017-11-17 | 胡玥莹 | For identifying anti-the swindle communication system and method for Stranger Calls |
| CN109063000A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海微众银行股份有限公司 | Question sentence recommended method, customer service system and computer readable storage medium |
| CN110070875A (en) * | 2019-04-29 | 2019-07-30 | 深圳市友杰智新科技有限公司 | A kind of anti-telecommunication fraud method based on voice keyword detection and vocal print |
| CN110309299A (en) * | 2018-04-12 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Communicate anti-swindle method, apparatus, computer-readable medium and electronic equipment |
| CN111159364A (en) * | 2018-11-07 | 2020-05-15 | 株式会社东芝 | Dialogue system, dialogue device, dialogue method, and storage medium |
| CN112561684A (en) * | 2020-12-15 | 2021-03-26 | 平安科技（深圳）有限公司 | Financial fraud risk identification method and device, computer equipment and storage medium |
| KR102255598B1 (en) * | 2020-07-08 | 2021-05-25 | 국민대학교산학협력단 | Non-face-to-face online test system and operation method |
| CN114020886A (en) * | 2021-10-29 | 2022-02-08 | 深圳平安综合金融服务有限公司 | Speech intention recognition method, device, equipment and storage medium |
| CN114186026A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Natural language processing method, device, equipment and storage medium |
| CN114579692A (en) * | 2020-12-01 | 2022-06-03 | 三六零智慧科技(天津)有限公司 | Fraud data deep analysis method and system |
| CN114928498A (en) * | 2022-06-15 | 2022-08-19 | 中国联合网络通信集团有限公司 | Fraud information identification method and device and computer readable storage medium |
| CN115130577A (en) * | 2022-06-28 | 2022-09-30 | 中国电信股份有限公司 | Method and device for identifying fraudulent number and electronic equipment |
| CN115344697A (en) * | 2022-08-03 | 2022-11-15 | 南京审计大学 | Method for detecting fraudulent question and answer in on-line question and answer community |
| CN116703325A (en) * | 2023-06-19 | 2023-09-05 | 东亚银行(中国)有限公司 | Quality inspection method, device and medium for chat records |
-
2023
- 2023-10-23 CN CN202311373051.4A patent/CN117132392B/en active Active
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007139864A (en) * | 2005-11-15 | 2007-06-07 | Nec Corp | Apparatus and method for detecting suspicious conversation, and communication device using the same |
| CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
| CN103440287A (en) * | 2013-08-14 | 2013-12-11 | 广东工业大学 | Web question-answering retrieval system based on product information structuring |
| CN103685613A (en) * | 2013-12-05 | 2014-03-26 | 江苏大学 | Telephone-fraud-resistant system based on voice recognition and method thereof |
| CN105989093A (en) * | 2015-02-12 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Automatic discovery method, device and application of sensitive word |
| CN104936182A (en) * | 2015-04-21 | 2015-09-23 | 中国移动通信集团浙江有限公司 | Method of managing and controlling fraud telephones intelligently and system of managing and controlling fraud telephones intelligently |
| CN105930452A (en) * | 2016-04-21 | 2016-09-07 | 北京紫平方信息技术股份有限公司 | Smart answering method capable of identifying natural language |
| JP2017204023A (en) * | 2016-05-09 | 2017-11-16 | トヨタ自動車株式会社 | Conversation processing device |
| CN107148024A (en) * | 2017-06-29 | 2017-09-08 | 胡玥莹 | A kind of anti-swindle communication system and method for being used to recognize strange short message |
| CN107360313A (en) * | 2017-06-29 | 2017-11-17 | 胡玥莹 | For identifying anti-the swindle communication system and method for Stranger Calls |
| CN110309299A (en) * | 2018-04-12 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Communicate anti-swindle method, apparatus, computer-readable medium and electronic equipment |
| CN109063000A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海微众银行股份有限公司 | Question sentence recommended method, customer service system and computer readable storage medium |
| CN111159364A (en) * | 2018-11-07 | 2020-05-15 | 株式会社东芝 | Dialogue system, dialogue device, dialogue method, and storage medium |
| CN110070875A (en) * | 2019-04-29 | 2019-07-30 | 深圳市友杰智新科技有限公司 | A kind of anti-telecommunication fraud method based on voice keyword detection and vocal print |
| KR102255598B1 (en) * | 2020-07-08 | 2021-05-25 | 국민대학교산학협력단 | Non-face-to-face online test system and operation method |
| CN114579692A (en) * | 2020-12-01 | 2022-06-03 | 三六零智慧科技(天津)有限公司 | Fraud data deep analysis method and system |
| CN112561684A (en) * | 2020-12-15 | 2021-03-26 | 平安科技（深圳）有限公司 | Financial fraud risk identification method and device, computer equipment and storage medium |
| CN114020886A (en) * | 2021-10-29 | 2022-02-08 | 深圳平安综合金融服务有限公司 | Speech intention recognition method, device, equipment and storage medium |
| CN114186026A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Natural language processing method, device, equipment and storage medium |
| CN114928498A (en) * | 2022-06-15 | 2022-08-19 | 中国联合网络通信集团有限公司 | Fraud information identification method and device and computer readable storage medium |
| CN115130577A (en) * | 2022-06-28 | 2022-09-30 | 中国电信股份有限公司 | Method and device for identifying fraudulent number and electronic equipment |
| CN115344697A (en) * | 2022-08-03 | 2022-11-15 | 南京审计大学 | Method for detecting fraudulent question and answer in on-line question and answer community |
| CN116703325A (en) * | 2023-06-19 | 2023-09-05 | 东亚银行(中国)有限公司 | Quality inspection method, device and medium for chat records |
Non-Patent Citations (3)
| Title |
|---|
| 刘宜昕: "客服机器人拒绝识别任务研究", 中国优秀硕士学位论文全文数据库信息科技辑, no. 1, pages 140 - 345 * |
| 朱太辉: "智能金融发展的潜在风险与监管应对", 国际金融, no. 2, pages 30 * |
| 王攀;刘世栋;: "骚扰欺诈电话的识别及阻断技术研究", 电信快报, no. 04, pages 6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117132392B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200412870A1 (en) | Collaborative Phone Reputation System | |
| CN107306306B (en) | Communication number processing method and device | |
| US20140301218A1 (en) | Statistical analysis and prompting method and system for mobile terminal internet traffic | |
| CN105516989A (en) | Method and device for identifying bad conversation | |
| WO2012031531A1 (en) | Text message processing method and mobile terminal | |
| EP2849474A1 (en) | Information processing method and terminal | |
| US20170064084A1 (en) | Method and Apparatus for Implementing Voice Mailbox | |
| CN109858917A (en) | A kind of anti-fake system and its method based on artificial intelligence | |
| CN106850931A (en) | The method and mobile intelligent terminal of Barassment preventing telephone | |
| CN110705926A (en) | Method, device and system for acquiring logistics object distribution information | |
| CN112995422A (en) | Call control method and device, electronic equipment and storage medium | |
| CN107071126A (en) | A kind of cell phone incoming call call-information precognition display methods and system | |
| CN108965613A (en) | Method, storage medium and application server based on the monitoring of collection system quality | |
| CN117132392B (en) | Vehicle loan fraud risk early warning method and system | |
| CN104869264A (en) | Method of monitoring swindle telephone and joining telephone conference and device of monitoring swindle telephone and joining telephone conference | |
| CN113076533B (en) | Service processing method and device | |
| KR101033870B1 (en) | Method and device for processing spam call | |
| CN111464687A (en) | Strange call request processing method and device | |
| CN108513303B (en) | Abnormity monitoring method and device for same number terminal | |
| CN111343347A (en) | Communication device, communication system and communication control method | |
| CN109192207A (en) | Voice communication assembly, voice communication method and system, equipment, storage medium | |
| CN116915903A (en) | Call voice processing method, device, server and readable storage medium | |
| CN113472686B (en) | Information identification method, device, equipment and storage medium | |
| CN109375963A (en) | Method, storage medium and application server based on the automatic log of collection system | |
| CN116418915A (en) | Abnormal number identification method, device, server 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 |