WO2021184837A1 - Fraudulent call identification method and device, storage medium, and terminal - Google Patents

Fraudulent call identification method and device, storage medium, and terminal Download PDF

Info

Publication number
WO2021184837A1
WO2021184837A1 PCT/CN2020/134094 CN2020134094W WO2021184837A1 WO 2021184837 A1 WO2021184837 A1 WO 2021184837A1 CN 2020134094 W CN2020134094 W CN 2020134094W WO 2021184837 A1 WO2021184837 A1 WO 2021184837A1
Authority
WO
WIPO (PCT)
Prior art keywords
fraud
call
preset
text data
terminal
Prior art date
Application number
PCT/CN2020/134094
Other languages
French (fr)
Chinese (zh)
Inventor
夏桥
Original Assignee
宇龙计算机通信科技(深圳)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 宇龙计算机通信科技(深圳)有限公司 filed Critical 宇龙计算机通信科技(深圳)有限公司
Publication of WO2021184837A1 publication Critical patent/WO2021184837A1/en

Links

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
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/12—Detection or prevention of fraud
    • H04W12/128—Anti-malware arrangements, e.g. protection against SMS fraud or mobile malware
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12—Messaging; Mailboxes; Announcements
    • H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]

Definitions

  • This application relates to the field of computer technology, and in particular to a method, device, storage medium and terminal for identifying fraudulent calls.
  • Phone fraud activities are becoming more and more rampant.
  • related technologies use phone numbers to identify whether a call is a fraudulent call.
  • the terminal obtains the caller number when receiving the call, and then queries the database whether the caller number is marked as If a fraudulent call is marked, the terminal displays a prompt message that the incoming call is suspected of being a fraudulent call on the incoming call interface.
  • fraudsters will constantly change phone numbers to make fraudulent calls. As a result, the incoming call number is not marked in the database, and the risk of users being defrauded is still high.
  • the embodiments of the present application provide a method, device, storage medium, and terminal for identifying fraudulent calls, which can identify fraudulent calls based on the content of the current call to reduce the risk of users being defrauded.
  • the technical solution is as follows:
  • an embodiment of the present application provides a method for identifying fraudulent calls.
  • the method includes:
  • an embodiment of the present application provides a device for identifying fraudulent calls, the device includes:
  • the collection unit is used to collect the voice data of the current call
  • Recognition unit for recognizing whether preset keywords are included in the text data
  • an embodiment of the present application provides a computer storage medium that stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.
  • an embodiment of the present application provides a terminal, which may include a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above method steps.
  • the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are inquired, and the fraud cases are displayed through the display unit. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
  • FIG. 1 is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of the present application
  • Fig. 2 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an example of a user interface provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of an example of a user interface provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram of an example of a user interface provided by an embodiment of the present application.
  • FIG. 6 is a schematic flowchart of a method for identifying fraudulent calls provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a fraudulent phone identification device provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a device for identifying fraudulent calls provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a terminal provided by an embodiment of the present application.
  • the method for identifying fraudulent calls provided in the embodiments of the present application will be described in detail below with reference to FIGS. 1 to 6.
  • the method can be implemented by relying on a computer program, and can be run on a fraud phone identification device based on the von Neumann system.
  • the computer program can be integrated in the application or run as an independent tool application.
  • the device for identifying fraudulent calls in the embodiments of the present application may be a terminal, including but not limited to smart phones, personal computers, tablets, handheld devices, vehicle-mounted devices, wearable devices, computing devices, or other processing connected to wireless modems. Equipment, etc.
  • FIG. 1 is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of this application.
  • the method of the embodiment of the present application may include the following steps:
  • S101 Collect voice data of the current call.
  • the terminal when the terminal receives an incoming call request, it displays the incoming call interface.
  • the incoming call interface includes information such as the incoming call number, attribution, and operator. For example, as shown in Figure 2, the incoming call interface includes the incoming call number: 15888888888, and the attribution is Zhejiang. Quotient is mobile.
  • the incoming call interface also includes an answer button and a reject button. When the user clicks the answer button, the terminal answers the incoming call request; when the user clicks the reject button, the terminal rejects the incoming call request.
  • the terminal displays the call interface, and the terminal collects the voice data of the current call through a voice collection unit (for example: a microphone).
  • the call interface may not only include the information in the incoming call interface, but also include: call duration , Record button, end call button, memo button, contact button, etc.
  • the call duration displayed by the terminal is 34 seconds, and the terminal also displays that the current call is in the recording state.
  • the terminal can preset the setting interface to turn off or on the fraud protection function.
  • the terminal will automatically check the current call when the user answers the current call. Record the call, and save the voice data generated by the recording in the local memory; when the user turns off the fraud protection function through the setting interface, the terminal will not automatically record the current call.
  • the terminal sets the recording button on the call interface. When the recording button is recording the current call, the voice data generated by the recording is saved to the local memory.
  • S102 Convert the voice data into text data according to the voice recognition technology.
  • the speech recognition system construction process as a whole includes two parts: training and recognition. Training is usually done offline. Signal processing and knowledge mining are performed on the massive speech data and language database collected in advance to obtain the "acoustic model” and "language model” required by the speech recognition system; the recognition process is usually completed online , Automatically recognize the user's real-time voice data.
  • the recognition process can usually be divided into two major modules: “front-end” and “back-end”: the main function of the “front-end” module is to perform endpoint detection (remove redundant silence and non-speaking), noise reduction, feature extraction, etc.; The function of the “end” module is to use the trained “acoustic model” and “language model” to perform statistical pattern recognition (also known as “decoding”) on the feature vector of the user’s speech to obtain the text data contained in the voice data.
  • the back-end module There is also an “adaptive” feedback module, which can self-learn the user's voice, so as to make necessary "corrections” to the "acoustic model” and “speech model” to further improve the accuracy of recognition.
  • the terminal can extract preset keywords from multiple fraud cases in advance
  • the algorithm for extracting the preset keywords can be TF-IDF (term frequency-inverse document frequency) algorithm
  • the number of preset keywords can be one or more .
  • the terminal recognizes that the text data in S102 includes preset keywords, it can display fraud cases related to the preset keywords on the call interface through the display unit. The user can identify the tricks of fraudsters by reading the fraud cases, thereby reducing fraud risks of.
  • the preset keywords are "money laundering", “public security organs” and "supervised account”.
  • the terminal recognizes that the text data includes the above preset keywords, it will display " The prompt message of “suspected phone call” and “account money laundering fraud”, account money laundering fraud can be associated with a hyperlink address, and the user clicks on the hyperlink address and the fraud case shown in Figure 5 is displayed.
  • the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
  • FIG. 6 is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of this application.
  • the method for identifying fraudulent calls may include the following steps:
  • S201 Collect voice data of the current call.
  • the terminal collects the voice data of the current call according to the audio collecting unit, and stores the collected voice data in the local memory.
  • the terminal will only temporarily store the voice data of the current call, and after the current call ends, the terminal will delete the voice data of the current call.
  • the acoustic characteristic parameter may be the Mel frequency cepstrum coefficient MFCC, which takes into account the human auditory characteristics, first maps the linear frequency spectrum to the Mel nonlinear frequency spectrum based on auditory perception, and then converts it to the cepstrum. That is, the spectrum passes through a set of Mel filters to obtain the Mel spectrum.
  • cepstrum coefficient h[k] is called the Mel frequency cepstrum coefficient, referred to as MFCC.
  • the spectrogram spectrogram of the original original sound signal will be analyzed by means of pre-emphasis, framing and windowing, short-term FFT, and the MFCC will analyze the sound spectrum signal.
  • the process of extracting MFCC features includes:
  • S203 Obtain text data through an acoustic model and a language model based on the acoustic feature parameters.
  • the speech recognition system construction process as a whole includes two parts: training and recognition. Training is usually done offline. Signal processing and knowledge mining are performed on the massive speech data and language database collected in advance to obtain the "acoustic model” and "language model” required by the speech recognition system; the recognition process is usually completed online , Automatically recognize the user's real-time voice data.
  • the recognition process can usually be divided into two major modules: “front-end” and “back-end”: the main function of the “front-end” module is to perform endpoint detection (remove redundant silence and non-speaking), noise reduction, feature extraction, etc.; The function of the "end” module is to use the trained “acoustic model” and “language model” to perform statistical pattern recognition (also known as “decoding") on the acoustic feature parameters (feature vectors) of the user's speech to obtain the text data contained in the voice data.
  • the back-end module also has an "adaptive" feedback module that can self-learn the user's voice, so as to make necessary “corrections” to the "acoustic model” and “speech model” to further improve the accuracy of recognition.
  • the terminal may be pre-stored or preset with preset keywords, the number of preset keywords may be one or more, and the terminal recognizes whether the text data in S203 includes the preset keywords.
  • the user may not notice the message displayed on the screen during the call, so when the terminal includes keywords in the text data, the user will be reminded through the preset reminding method, such as vibration or playing the current call through the speaker.
  • the current call is a fraudulent call, and the user will notice what is displayed on the terminal display.
  • S206 Query a fraud case associated with the preset keyword on a server deployed on the Internet.
  • a fraud case related to preset keywords is stored in the server on the Internet.
  • the terminal recognizes the result in S204 as yes, it queries the server for the preset keywords in the analysis carried in the text data, and the server will query based on the preset keywords.
  • the received fraud case is returned to the terminal.
  • S207 Send a fraud prompt message to the terminal corresponding to the phone number pre-stored by the user.
  • the terminal has pre-stored phone numbers, which can be the phone numbers of parents, children or friends.
  • the terminal will send a fraud alert message to the terminal corresponding to the phone number to notify the incoming call of the current call Number, call time, preset keywords, and fraud cases, notify other people that users may encounter fraud, and other people can notify users of fraudulent calls to reduce the possibility of users being defrauded.
  • the fraud alert message can be short message, email, instant messaging message, etc., which is not limited by this application.
  • the terminal can display fraud cases on the call interface of the current call, or display fraud cases on other interfaces.
  • the terminal can use the full-screen fraud case window, which is set with Close button. After the terminal detects the user's click operation on the close button, it can close the window and no longer display the fraud case, so that the user can be more prominently reminded of the content of the fraud case.
  • the terminal may send a fraud reminder message to the fraud center.
  • the fraud reminder message carries information such as the caller number, call time, the preset keywords, and the fraud case, and the fraud reminder center receives the fraud reminder.
  • an anti-fraud reminder text message or an incoming anti-fraud reminder call will be sent to the terminal to increase the credibility that the user believes that he has been defrauded at this time.
  • the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
  • FIG. 7 shows a schematic structural diagram of a fraudulent phone identification device provided by an exemplary embodiment of the present application.
  • the device for identifying fraudulent calls can be implemented as all or a part of the terminal through software, hardware, or a combination of the two.
  • the device 1 includes an acquisition unit 10, a conversion unit 20, and an identification unit 30.
  • the collecting unit 10 is used to collect voice data of the current call
  • the conversion unit 20 is configured to convert the voice data into text data according to the voice recognition technology
  • the recognition unit 30 is configured to recognize whether the text data includes preset keywords
  • the converting the voice data into text data according to a voice recognition technology includes:
  • the text data is obtained through an acoustic model and a language model based on the acoustic feature parameters.
  • the query of the fraud case associated with the preset keyword includes:
  • the displaying the fraud case through the display unit includes:
  • the fraud case is displayed on the display interface of the current call through the display unit.
  • the apparatus 1 further includes:
  • the reminding unit 40 is configured to remind the user that the current call is a fraudulent call through a preset reminding method; wherein, the preset reminding method includes a vibration reminding method.
  • the apparatus 1 further includes:
  • the transceiver unit 50 is configured to send a fraud prompt message to the terminal corresponding to the phone number pre-stored by the user; wherein the fraud prompt message includes the caller number, the call time, the preset keywords, and the fraud case.
  • the transceiver unit 50 is further configured to:
  • the device for identifying fraudulent calls when the device for identifying fraudulent calls provided in the above embodiments executes the method for identifying fraudulent calls, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned function assignments can be divided according to needs.
  • the function module is completed, that is, the internal structure of the device is divided into different function modules to complete all or part of the functions described above.
  • the device for restoring user data provided in the foregoing embodiment and the embodiment of the method for identifying fraudulent calls belong to the same concept. For the implementation process of the method, please refer to the method embodiment, which will not be repeated here.
  • the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
  • the embodiment of the present application also provides a computer storage medium.
  • the computer storage medium may store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps of the embodiments shown in FIGS. 1 to 6 above.
  • the specific execution process please refer to the specific description of the embodiment shown in FIG. 1 to FIG. 6, which will not be repeated here.
  • the terminal 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.
  • the user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • Display display screen
  • Camera Camera
  • the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the processor 1001 may include one or more processing cores.
  • the processor 1001 uses various interfaces and lines to connect various parts of the entire terminal 1000, and executes the terminal by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005.
  • Various functions and processing data of 1000 may use at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). Form to achieve.
  • the processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like.
  • the memory 1005 may include random access memory (Random Access Memory, RAM), and may also include read-only memory (Read-Only Memory).
  • the memory 1005 includes a non-transitory computer-readable storage medium.
  • the memory 1005 may be used to store instructions, programs, codes, code sets or instruction sets.
  • the memory 1005 may include a program storage area and a data storage area, where the program storage area may store instructions for implementing the operating system and instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), Instructions and the like used to implement the above method embodiments; the storage data area can store the data and the like involved in the above method embodiments.
  • the memory 1005 may also be at least one storage device located far away from the foregoing processor 1001. As shown in FIG. 9, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a fraudulent phone identification application program.
  • the user interface 1003 is mainly used to provide an input interface for the user to obtain data input by the user; and the processor 1001 may be used to call the fraudulent phone identification application stored in the memory 1005, and Specifically perform the following operations:
  • the processor 1001 performing the conversion of the voice data into text data according to the voice recognition technology includes:
  • the text data is obtained through an acoustic model and a language model based on the acoustic feature parameters.
  • the processor 1001 executing the query of the fraud case associated with the preset keyword includes:
  • the processor 1001 executing the display of the fraud case through the display unit includes:
  • the fraud case is displayed on the display interface of the current call through the display unit.
  • the processor 1001 is further configured to execute:
  • the user is reminded by a preset reminding method that the current call is a fraudulent call; wherein, the preset reminding method includes a vibration reminding method.
  • the processor 1001 is further configured to execute:
  • the fraud reminder message includes the caller number, the call time, the preset keywords, and the fraud case.
  • the processor 1001 is further configured to execute:
  • the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
  • the program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium can be a magnetic disk, an optical disc, a read-only storage memory, or a random storage memory, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Technology Law (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)
  • Telephone Function (AREA)

Abstract

Disclosed in embodiments of the present application are a fraudulent call identification method and device, a storage medium, and a terminal. The method comprises: acquiring speech data of a current call; converting the speech data into text data according to speech recognition technology; identifying whether the text data comprises a preset keyword; and if yes, querying a fraud case associated with the preset keyword, and displaying the fraud case by means of a display unit. According to the embodiments of the present application, fraudulent calls can be identified by means of the conversation content of calls, thereby reducing the risk of users being defrauded by phone fraud.

Description

诈骗电话的识别方法、装置、存储介质及终端Method, device, storage medium and terminal for identifying fraudulent calls 技术领域Technical field
本申请涉及计算机技术领域，尤其涉及一种诈骗电话的识别方法、装置、存储介质及终端。This application relates to the field of computer technology, and in particular to a method, device, storage medium and terminal for identifying fraudulent calls.
背景技术Background technique
电话诈骗的活动日益猖獗，为了减少用户的财产损失，相关技术中通过电话号码来识别来电是否为诈骗电话，终端在接收到来电时获取来电号码，然后在数据库中查询该来电号码是否被标记为诈骗电话，如果被标记，则终端在来电界面上显示该来电疑似诈骗电话的提示消息。但是，诈骗分子会不停的更换电话号码来拨出诈骗电话，导致来电号码未被标记在数据库中，用户被诈骗的风险仍然很高。Phone fraud activities are becoming more and more rampant. In order to reduce user property losses, related technologies use phone numbers to identify whether a call is a fraudulent call. The terminal obtains the caller number when receiving the call, and then queries the database whether the caller number is marked as If a fraudulent call is marked, the terminal displays a prompt message that the incoming call is suspected of being a fraudulent call on the incoming call interface. However, fraudsters will constantly change phone numbers to make fraudulent calls. As a result, the incoming call number is not marked in the database, and the risk of users being defrauded is still high.
发明内容Summary of the invention
本申请实施例提供了一种诈骗电话的识别方法、装置、存储介质及终端，可以根据当前通话的内容进行诈骗电话识别以减少用户被诈骗的风险。所述技术方案如下：The embodiments of the present application provide a method, device, storage medium, and terminal for identifying fraudulent calls, which can identify fraudulent calls based on the content of the current call to reduce the risk of users being defrauded. The technical solution is as follows:
第一方面，本申请实施例提供了一种诈骗电话的识别方法，所述方法包括：In the first aspect, an embodiment of the present application provides a method for identifying fraudulent calls. The method includes:
采集当前通话的语音数据；Collect the voice data of the current call;
根据语音识别技术将所述语音数据转换为文本数据；Converting the voice data into text data according to the voice recognition technology;
识别所述文本数据中是否包括预设关键词；Identifying whether the text data includes preset keywords;
若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
第二方面，本申请实施例提供了一种诈骗电话的识别装置，所述装置包括：In the second aspect, an embodiment of the present application provides a device for identifying fraudulent calls, the device includes:
采集单元，用于采集当前通话的语音数据；The collection unit is used to collect the voice data of the current call;
转换单元，用于根据语音识别技术将所述语音数据转换为文本数据；A conversion unit for converting the voice data into text data according to the voice recognition technology;
识别单元，用于识别所述文本数据中是否包括预设关键词；Recognition unit for recognizing whether preset keywords are included in the text data;
若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所 述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
第三方面，本申请实施例提供一种计算机存储介质，所述计算机存储介质存储有多条指令，所述指令适于由处理器加载并执行上述的方法步骤。In a third aspect, an embodiment of the present application provides a computer storage medium that stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.
第四方面，本申请实施例提供一种终端，可包括：处理器和存储器；其中，所述存储器存储有计算机程序，所述计算机程序适于由所述处理器加载并执行上述的方法步骤。In a fourth aspect, an embodiment of the present application provides a terminal, which may include a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above method steps.
本申请一些实施例提供的技术方案带来的有益效果至少包括：The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:
采集当前通话的语音数据，将语音数据转换为文本数据，在识别文本数据中包括预设关键词时，查询与预设关键词关联的诈骗案例，以及通过显示单元显示诈骗案例。这样可以通过当前通话的内容识别诈骗电话，以及显示诈骗案例，用户通过阅读诈骗案例的提醒能识破诈骗分子的伎俩，降低被诈骗的风险。The voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are inquired, and the fraud cases are displayed through the display unit. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
附图说明Description of the drawings
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.
图1是本申请实施例提供的一种诈骗电话的识别方法的流程示意图；FIG. 1 is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of the present application;
图2是本申请实施例提供的一种用户界面的示意图；Fig. 2 is a schematic diagram of a user interface provided by an embodiment of the present application;
图3是本申请实施例提供的一种用户界面的举例示意图；FIG. 3 is a schematic diagram of an example of a user interface provided by an embodiment of the present application;
图4是本申请实施例提供的一种用户界面的举例示意图；FIG. 4 is a schematic diagram of an example of a user interface provided by an embodiment of the present application;
图5是本申请实施例提供的一种用户界面的举例示意图；FIG. 5 is a schematic diagram of an example of a user interface provided by an embodiment of the present application;
图6是本申请实施例提供的一种诈骗电话的识别方法的流程示意图；FIG. 6 is a schematic flowchart of a method for identifying fraudulent calls provided by an embodiment of the present application;
图7是本申请实施例提供的一种诈骗电话的识别装置的结构示意图；FIG. 7 is a schematic structural diagram of a fraudulent phone identification device provided by an embodiment of the present application;
图8是本申请实施例提供的一种诈骗电话的识别装置的结构示意图；FIG. 8 is a schematic structural diagram of a device for identifying fraudulent calls provided by an embodiment of the present application;
图9是本申请实施例提供的一种终端的结构示意图。FIG. 9 is a schematic structural diagram of a terminal provided by an embodiment of the present application.
具体实施方式Detailed ways
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请 实施例方式作进一步地详细描述。In order to make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.
下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
在本申请的描述中，需要理解的是，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本申请中的具体含义。此外，在本申请的描述中，除非另有说明，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood under specific circumstances. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects before and after are in an "or" relationship.
下面将结合附图1-附图6，对本申请实施例提供的诈骗电话的识别方法进行详细介绍。该方法可依赖于计算机程序实现，可运行于基于冯诺依曼体系的诈骗电话的识别装置上。该计算机程序可集成在应用中，也可作为独立的工具类应用运行。其中，本申请实施例中的诈骗电话的识别装置可以为终端，包括但不限于智能手机、个人电脑、平板电脑、手持设备、车载设备、可穿戴设备、计算设备或连接到无线调制解调器的其它处理设备等。The method for identifying fraudulent calls provided in the embodiments of the present application will be described in detail below with reference to FIGS. 1 to 6. The method can be implemented by relying on a computer program, and can be run on a fraud phone identification device based on the von Neumann system. The computer program can be integrated in the application or run as an independent tool application. Among them, the device for identifying fraudulent calls in the embodiments of the present application may be a terminal, including but not limited to smart phones, personal computers, tablets, handheld devices, vehicle-mounted devices, wearable devices, computing devices, or other processing connected to wireless modems. Equipment, etc.
请参见图1，为本申请实施例提供的一种诈骗电话的识别方法的流程示意图。如图1所示，本申请实施例的所述方法可以包括以下步骤：Please refer to FIG. 1, which is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of this application. As shown in FIG. 1, the method of the embodiment of the present application may include the following steps:
S101，采集当前通话的语音数据。S101: Collect voice data of the current call.
其中，终端接收到来电请求时，显示来电界面，来电界面上包括来电号码、归属地和运营商等信息，例如：参见图2所示，来电界面包括来电号码：15888888888，归属地为浙江，运营商为移动。来电界面还包括接听按钮和拒接按钮，用户点击接听按钮时，终端接听来电请求；用户点击拒接按钮时，终端拒接来电请求。用户接听来电请求时，终端显示通话界面，以及终端通过语音采集单元(例如：麦克风)采集当前通话的语音数据，通话界面除包括来电界面中的所述的信息之外，还可以包括：通话时长、录音按钮、结束通话按钮、 备忘录按钮和联系人按钮等。Among them, when the terminal receives an incoming call request, it displays the incoming call interface. The incoming call interface includes information such as the incoming call number, attribution, and operator. For example, as shown in Figure 2, the incoming call interface includes the incoming call number: 15888888888, and the attribution is Zhejiang. Quotient is mobile. The incoming call interface also includes an answer button and a reject button. When the user clicks the answer button, the terminal answers the incoming call request; when the user clicks the reject button, the terminal rejects the incoming call request. When the user answers an incoming call request, the terminal displays the call interface, and the terminal collects the voice data of the current call through a voice collection unit (for example: a microphone). The call interface may not only include the information in the incoming call interface, but also include: call duration , Record button, end call button, memo button, contact button, etc.
例如：参见图3所示的通话界面，终端显示的通话时长为34秒，终端还显示当前通话处于录音状态。For example: referring to the call interface shown in Figure 3, the call duration displayed by the terminal is 34 seconds, and the terminal also displays that the current call is in the recording state.
其中，由于对通话进行录音可能会涉及用户隐私，终端可以预先设置关闭或开启诈骗保护功能的设置界面，用户在通过设置界面开启诈骗保护功能时，终端在用户接听当前来电时，会自动对当前通话进行录音，以及将录音生成的语音数据保存在本地的存储器中；用户在通过设置界面关闭诈骗保护功能时，终端不会自动对当前通话进行录音，终端在通话界面设置录音按钮，在用户通过录音按钮对当前通话进行录音时，将录音生成的语音数据保存到本地的存储器中。Among them, since recording a call may involve user privacy, the terminal can preset the setting interface to turn off or on the fraud protection function. When the user turns on the fraud protection function through the setting interface, the terminal will automatically check the current call when the user answers the current call. Record the call, and save the voice data generated by the recording in the local memory; when the user turns off the fraud protection function through the setting interface, the terminal will not automatically record the current call. The terminal sets the recording button on the call interface. When the recording button is recording the current call, the voice data generated by the recording is saved to the local memory.
S102，根据语音识别技术将所述语音数据转换为文本数据。S102: Convert the voice data into text data according to the voice recognition technology.
其中，语音识别***构建过程整体上包括两大部分：训练和识别。训练通常是离线完成的，对预先收集好的海量语音数据、语言数据库进行信号处理和知识挖掘，获取语音识别***所需要的“声学模型”和“语言模型”；而识别过程通常是在线完成的，对用户实时的语音数据进行自动识别。识别过程通常又可以分为“前端”和“后端”两大模块：“前端”模块主要的作用是进行端点检测(去除多余的静音和非说话声)、降噪、特征提取等；“后端”模块的作用是利用训练好的“声学模型”和“语言模型”对用户说话的特征向量进行统计模式识别(又称“解码”)，得到语音数据包含的文本数据，此外，后端模块还存在一个“自适应”的反馈模块，可以对用户的语音进行自学习，从而对“声学模型”和“语音模型”进行必要的“校正”，进一步提高识别的准确率。Among them, the speech recognition system construction process as a whole includes two parts: training and recognition. Training is usually done offline. Signal processing and knowledge mining are performed on the massive speech data and language database collected in advance to obtain the "acoustic model" and "language model" required by the speech recognition system; the recognition process is usually completed online , Automatically recognize the user's real-time voice data. The recognition process can usually be divided into two major modules: "front-end" and "back-end": the main function of the "front-end" module is to perform endpoint detection (remove redundant silence and non-speaking), noise reduction, feature extraction, etc.; The function of the “end” module is to use the trained “acoustic model” and “language model” to perform statistical pattern recognition (also known as “decoding”) on the feature vector of the user’s speech to obtain the text data contained in the voice data. In addition, the back-end module There is also an "adaptive" feedback module, which can self-learn the user's voice, so as to make necessary "corrections" to the "acoustic model" and "speech model" to further improve the accuracy of recognition.
S103、若识别出所述文本数据中包括预设关键词，查询所述预设关键词的诈骗案例，以及通过显示单元显示所述诈骗案例。S103: If it is recognized that the text data includes a preset keyword, query the fraud case of the preset keyword, and display the fraud case through a display unit.
其中，终端可以预先多个诈骗案例中提取预设关键词，提取预设关键词的算法可以是TF-IDF(term frequency-inverse document frequency)算法，预设关键词的数量可以是一个或多个。终端识别出S102中的文本数据中包括预设关键词时，可以通过显示单元在通话界面上显示预设关键词关联的诈骗案例，用户通过阅读诈骗案例可以识破诈骗分子的伎俩，从而减少被诈骗的风险。Among them, the terminal can extract preset keywords from multiple fraud cases in advance, the algorithm for extracting the preset keywords can be TF-IDF (term frequency-inverse document frequency) algorithm, and the number of preset keywords can be one or more . When the terminal recognizes that the text data in S102 includes preset keywords, it can display fraud cases related to the preset keywords on the call interface through the display unit. The user can identify the tricks of fraudsters by reading the fraud cases, thereby reducing fraud risks of.
例如：参见图4和图5所示，预设关键词为“洗钱”、“公安机关”和“监 管账户”，终端识别出文本数据中包括上述的预设关键词时，在通话界面显示“疑似诈骗电话”和“账户洗钱诈骗”的提示消息，账户洗钱诈骗可以关联一个超链接地址，用户点击该超链接地址后显示如图5所示的诈骗案例。For example: referring to Figures 4 and 5, the preset keywords are "money laundering", "public security organs" and "supervised account". When the terminal recognizes that the text data includes the above preset keywords, it will display " The prompt message of “suspected phone call” and “account money laundering fraud”, account money laundering fraud can be associated with a hyperlink address, and the user clicks on the hyperlink address and the fraud case shown in Figure 5 is displayed.
在本申请实施例中，采集当前通话的语音数据，将语音数据转换为文本数据，在识别文本数据中包括预设关键词时，查询与预设关键词关联的诈骗案例，以及通过显示单元显示诈骗案例。这样可以通过当前通话的内容识别诈骗电话，以及显示诈骗案例，用户通过阅读诈骗案例的提醒能识破诈骗分子的伎俩，降低被诈骗的风险。In the embodiment of the present application, the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
请参见图6，为本申请实施例提供的一种诈骗电话的识别方法的流程示意图。该诈骗电话的识别方法可以包括以下步骤：Please refer to FIG. 6, which is a schematic flowchart of a method for identifying fraudulent calls according to an embodiment of this application. The method for identifying fraudulent calls may include the following steps:
S201，采集当前通话的语音数据。S201: Collect voice data of the current call.
其中，用户接听终端的来电请求时，终端根据音频采集单元采集当前通话的语音数据，将采集到的语音数据存储在本地的存储器中。可选的，为了保护用户的隐私，终端只会临时存储当前通话的语音数据，在当前通话结束之后，终端会删除当前通话的语音数据。Among them, when the user answers the incoming call request of the terminal, the terminal collects the voice data of the current call according to the audio collecting unit, and stores the collected voice data in the local memory. Optionally, in order to protect the privacy of the user, the terminal will only temporarily store the voice data of the current call, and after the current call ends, the terminal will delete the voice data of the current call.
S202、提取所述语音数据的声学特征参数。S202: Extract acoustic feature parameters of the voice data.
其中，声学特征参数可以是梅尔频率倒谱系数MFCC，其考虑到了人类的听觉特征，先将线性频谱映射到基于听觉感知的Mel非线性频谱中，然后转换到倒谱上。即将频谱通过一组Mel滤波器就得到Mel频谱，公式表述就是log X[k]＝log(Mel-Spectrum)，这时候我们再在log X[k]上进行倒谱分析，在Mel频谱上面获得的倒谱系数h[k]就称为Mel频率倒谱系数，简称MFCC。通常，计算MFCC之前，还会通过预加重、分帧和加窗、短时FFT等手段将原始原始声音信号的spectrogram声谱图，MFCC对声谱信号进行分析。Among them, the acoustic characteristic parameter may be the Mel frequency cepstrum coefficient MFCC, which takes into account the human auditory characteristics, first maps the linear frequency spectrum to the Mel nonlinear frequency spectrum based on auditory perception, and then converts it to the cepstrum. That is, the spectrum passes through a set of Mel filters to obtain the Mel spectrum. The formula is log X[k] = log(Mel-Spectrum). At this time, we perform cepstrum analysis on log X[k] and obtain the Mel spectrum. The cepstrum coefficient h[k] is called the Mel frequency cepstrum coefficient, referred to as MFCC. Usually, before calculating the MFCC, the spectrogram spectrogram of the original original sound signal will be analyzed by means of pre-emphasis, framing and windowing, short-term FFT, and the MFCC will analyze the sound spectrum signal.
提取MFCC特征的过程包括：The process of extracting MFCC features includes:
1)先对语音进行预加重、分帧和加窗；1) Perform pre-emphasis, framing and windowing on the voice first;
2)对每一个短时分析窗，通过FFT得到对应的频谱；2) For each short-term analysis window, obtain the corresponding frequency spectrum through FFT;
3)将上面的频谱通过Mel滤波器组得到Mel频谱；3) Pass the above spectrum through the Mel filter bank to obtain the Mel spectrum;
4)在Mel频谱上面进行倒谱分析(取对数，做逆变换，实际逆变换一般 是通过DCT离散余弦变换来代替上文的IDFT，取DCT后的第2个到第13个系数作为MFCC系数)，获得Mel频率倒谱系数MFCC。4) Perform cepstrum analysis on the Mel spectrum (take the logarithm and do the inverse transform. The actual inverse transform is generally through the DCT discrete cosine transform instead of the IDFT above. Take the 2nd to 13th coefficients after DCT as MFCC Coefficient) to obtain the Mel frequency cepstrum coefficient MFCC.
S203、基于所述声学特征参数通过声学模型和语言模型得到文本数据。S203: Obtain text data through an acoustic model and a language model based on the acoustic feature parameters.
其中，语音识别***构建过程整体上包括两大部分：训练和识别。训练通常是离线完成的，对预先收集好的海量语音数据、语言数据库进行信号处理和知识挖掘，获取语音识别***所需要的“声学模型”和“语言模型”；而识别过程通常是在线完成的，对用户实时的语音数据进行自动识别。识别过程通常又可以分为“前端”和“后端”两大模块：“前端”模块主要的作用是进行端点检测(去除多余的静音和非说话声)、降噪、特征提取等；“后端”模块的作用是利用训练好的“声学模型”和“语言模型”对用户说话的声学特征参数(特征向量)进行统计模式识别(又称“解码”)，得到语音数据包含的文本数据，此外，后端模块还存在一个“自适应”的反馈模块，可以对用户的语音进行自学习，从而对“声学模型”和“语音模型”进行必要的“校正”，进一步提高识别的准确率。Among them, the speech recognition system construction process as a whole includes two parts: training and recognition. Training is usually done offline. Signal processing and knowledge mining are performed on the massive speech data and language database collected in advance to obtain the "acoustic model" and "language model" required by the speech recognition system; the recognition process is usually completed online , Automatically recognize the user's real-time voice data. The recognition process can usually be divided into two major modules: "front-end" and "back-end": the main function of the "front-end" module is to perform endpoint detection (remove redundant silence and non-speaking), noise reduction, feature extraction, etc.; The function of the "end" module is to use the trained "acoustic model" and "language model" to perform statistical pattern recognition (also known as "decoding") on the acoustic feature parameters (feature vectors) of the user's speech to obtain the text data contained in the voice data. In addition, the back-end module also has an "adaptive" feedback module that can self-learn the user's voice, so as to make necessary "corrections" to the "acoustic model" and "speech model" to further improve the accuracy of recognition.
S204、识别文本数据中是否包括预设关键词。S204: Identify whether the text data includes preset keywords.
其中，终端可以预存储或预设置有预设关键词，预设关键词的数量可以是一个或多个，终端识别出S203中的文本数据是否包括预设关键词。Among them, the terminal may be pre-stored or preset with preset keywords, the number of preset keywords may be one or more, and the terminal recognizes whether the text data in S203 includes the preset keywords.
S205、在识别结果为是时，通过预设提醒方式提醒用户所述当前通话为诈骗电话。S205: When the recognition result is yes, remind the user that the current call is a fraudulent call through a preset reminding manner.
其中，用户在通话过程中可能不会注意到屏幕上显示的消息，因此终端在文本数据中包括关键词时，通过预设的提醒方式，例如：振动方式或通过扬声器播放当前通话等方式提醒用户当前通话为诈骗电话，用户此时会注意到终端显示屏上显示的内容。Among them, the user may not notice the message displayed on the screen during the call, so when the terminal includes keywords in the text data, the user will be reminded through the preset reminding method, such as vibration or playing the current call through the speaker. The current call is a fraudulent call, and the user will notice what is displayed on the terminal display.
S206、在部署在互联网中的服务器上查询与所述预设关键词关联的诈骗案例。S206: Query a fraud case associated with the preset keyword on a server deployed on the Internet.
其中，互联网的服务器中存储有预设关键词关联的诈骗案例，终端在S204的识别结果为是时，向服务器查询携带文本数据中解析中的预设关键词，服务器将基于预设关键词查询到的诈骗案例返回给终端。Among them, a fraud case related to preset keywords is stored in the server on the Internet. When the terminal recognizes the result in S204 as yes, it queries the server for the preset keywords in the analysis carried in the text data, and the server will query based on the preset keywords. The received fraud case is returned to the terminal.
S207、向所述用户预先存储的电话号码对应的终端发送诈骗提示消息。S207: Send a fraud prompt message to the terminal corresponding to the phone number pre-stored by the user.
其中，终端预先存储有电话号码，电话号码可以是父母、子女或朋友的电话号码，在S204的识别结果为是时，终端会向电话号码对应的终端发送诈骗提示消息，以通知当前通话的来电号码、通话时间、预设关键词和诈骗案例，将用户可能会遭遇诈骗的情况通知给其他人，其他人可以将诈骗电话的情况通知给用户，减少用户被诈骗的可能性。其中，诈骗提示消息可以短消息、邮件、即时通信消息等，本申请不作限制。Among them, the terminal has pre-stored phone numbers, which can be the phone numbers of parents, children or friends. When the recognition result of S204 is yes, the terminal will send a fraud alert message to the terminal corresponding to the phone number to notify the incoming call of the current call Number, call time, preset keywords, and fraud cases, notify other people that users may encounter fraud, and other people can notify users of fraudulent calls to reduce the possibility of users being defrauded. Among them, the fraud alert message can be short message, email, instant messaging message, etc., which is not limited by this application.
S208、通过显示单元显示所述诈骗案例。S208: Display the fraud case through the display unit.
其中，终端可以在当前通话的通话界面上显示诈骗案例，也可以在其他界面上显示诈骗案例，其中，在通话界面上显示诈骗案例时，终端可以使用全屏方式诈骗案例的窗口，窗口上设置有关闭按钮，终端检测到用户对关闭按钮的点击操作后，可以关闭该窗口不再显示诈骗案例，这样可以更显著的提醒用户诈骗案例的内容。Among them, the terminal can display fraud cases on the call interface of the current call, or display fraud cases on other interfaces. Among them, when the fraud case is displayed on the call interface, the terminal can use the full-screen fraud case window, which is set with Close button. After the terminal detects the user's click operation on the close button, it can close the window and no longer display the fraud case, so that the user can be more prominently reminded of the content of the fraud case.
S209、在所述当前通话结束之后，接收防诈骗提醒短信。S209. After the current call ends, receive an anti-fraud reminder short message.
其中，在当前通话结束之后，终端可以向诈骗中心发送诈骗提醒消息，诈骗提醒消息携带来电号码、通话时间、所述预设关键词以及所述诈骗案例等信息，诈骗提醒中心接收到该诈骗提醒消息后，会向终端发送防诈骗提醒短信或防诈骗提醒来电，以增加用户相信此时被诈骗的可信度。Wherein, after the current call ends, the terminal may send a fraud reminder message to the fraud center. The fraud reminder message carries information such as the caller number, call time, the preset keywords, and the fraud case, and the fraud reminder center receives the fraud reminder. After the message, an anti-fraud reminder text message or an incoming anti-fraud reminder call will be sent to the terminal to increase the credibility that the user believes that he has been defrauded at this time.
在本申请实施例中，采集当前通话的语音数据，将语音数据转换为文本数据，在识别文本数据中包括预设关键词时，查询与预设关键词关联的诈骗案例，以及通过显示单元显示诈骗案例。这样可以通过当前通话的内容识别诈骗电话，以及显示诈骗案例，用户通过阅读诈骗案例的提醒能识破诈骗分子的伎俩，降低被诈骗的风险。In the embodiment of the present application, the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
下述为本申请装置实施例，可以用于执行本申请方法实施例。对于本申请装置实施例中未披露的细节，请参照本申请方法实施例。The following are device embodiments of this application, which can be used to implement the method embodiments of this application. For details that are not disclosed in the device embodiments of this application, please refer to the method embodiments of this application.
请参见图7，其示出了本申请一个示例性实施例提供的诈骗电话的识别装置的结构示意图。该诈骗电话的识别装置可以通过软件、硬件或者两者的结合实现成为终端的全部或一部分。该装置1包括采集单元10、转换单元20和识别单元30。Please refer to FIG. 7, which shows a schematic structural diagram of a fraudulent phone identification device provided by an exemplary embodiment of the present application. The device for identifying fraudulent calls can be implemented as all or a part of the terminal through software, hardware, or a combination of the two. The device 1 includes an acquisition unit 10, a conversion unit 20, and an identification unit 30.
采集单元10，用于采集当前通话的语音数据；The collecting unit 10 is used to collect voice data of the current call;
转换单元20，用于根据语音识别技术将所述语音数据转换为文本数据；The conversion unit 20 is configured to convert the voice data into text data according to the voice recognition technology;
识别单元30，用于识别所述文本数据中是否包括预设关键词；The recognition unit 30 is configured to recognize whether the text data includes preset keywords;
若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
在一个或多个实施例中，所述根据语音识别技术将所述语音数据转换为文本数据，包括：In one or more embodiments, the converting the voice data into text data according to a voice recognition technology includes:
提取所述语音数据的声学特征参数；Extracting acoustic feature parameters of the voice data;
基于所述声学特征参数通过声学模型和语言模型得到所述文本数据。The text data is obtained through an acoustic model and a language model based on the acoustic feature parameters.
在一个或多个实施例中，所述查询所述预设关键词关联的诈骗案例，包括：In one or more embodiments, the query of the fraud case associated with the preset keyword includes:
在本地数据库中查询与所述预设关键词关联的诈骗案例；或Query the fraud cases associated with the preset keywords in the local database; or
在部署在互联网中的服务器上查询与所述预设关键词关联的诈骗案例。Inquire about fraud cases associated with the preset keywords on a server deployed on the Internet.
在一个或多个实施例中，所述通过显示单元显示所述诈骗案例，包括：In one or more embodiments, the displaying the fraud case through the display unit includes:
通过显示单元在所述当前通话的显示界面显示所述诈骗案例。The fraud case is displayed on the display interface of the current call through the display unit.
在一个或多个实施例中，参见图8所示，装置1还包括：In one or more embodiments, referring to FIG. 8, the apparatus 1 further includes:
提醒单元40，用于通过预设提醒方式提醒用户所述当前通话为诈骗电话；其中，所述预设提醒方式包括震动提醒方式。The reminding unit 40 is configured to remind the user that the current call is a fraudulent call through a preset reminding method; wherein, the preset reminding method includes a vibration reminding method.
在一个或多个实施例中，参见图8所示，装置1还包括：In one or more embodiments, referring to FIG. 8, the apparatus 1 further includes:
收发单元50，用于向所述用户预先存储的电话号码对应的终端发送诈骗提示消息；其中，所述诈骗提示消息包括来电号码、通话时间、所述预设关键词以及所述诈骗案例。The transceiver unit 50 is configured to send a fraud prompt message to the terminal corresponding to the phone number pre-stored by the user; wherein the fraud prompt message includes the caller number, the call time, the preset keywords, and the fraud case.
在一个或多个实施例中，参见图8所示，收发单元50还用于：In one or more embodiments, referring to FIG. 8, the transceiver unit 50 is further configured to:
在所述当前通话结束之后，接收防诈骗提醒短信。After the current call ends, receive an anti-fraud reminder short message.
需要说明的是，上述实施例提供的诈骗电话的识别装置在执行诈骗电话的识别方法时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的恢复用户数据装置与诈骗电话的识别方法实施例属于同一构思，其体现实现过程详见方法实施例，这里不再赘述。It should be noted that, when the device for identifying fraudulent calls provided in the above embodiments executes the method for identifying fraudulent calls, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned function assignments can be divided according to needs. The function module is completed, that is, the internal structure of the device is divided into different function modules to complete all or part of the functions described above. In addition, the device for restoring user data provided in the foregoing embodiment and the embodiment of the method for identifying fraudulent calls belong to the same concept. For the implementation process of the method, please refer to the method embodiment, which will not be repeated here.
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority or inferiority of the embodiments.
在本申请实施例中，采集当前通话的语音数据，将语音数据转换为文本数据，在识别文本数据中包括预设关键词时，查询与预设关键词关联的诈骗案例，以及通过显示单元显示诈骗案例。这样可以通过当前通话的内容识别诈骗电话，以及显示诈骗案例，用户通过阅读诈骗案例的提醒能识破诈骗分子的伎俩，降低被诈骗的风险。In the embodiment of the present application, the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
本申请实施例还提供了一种计算机存储介质，所述计算机存储介质可以存储有多条指令，所述指令适于由处理器加载并执行如上述图1-图6所示实施例的方法步骤，具体执行过程可以参见图1-图6所示实施例的具体说明，在此不进行赘述。The embodiment of the present application also provides a computer storage medium. The computer storage medium may store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps of the embodiments shown in FIGS. 1 to 6 above. For the specific execution process, please refer to the specific description of the embodiment shown in FIG. 1 to FIG. 6, which will not be repeated here.
请参见图9，为本申请实施例提供了一种终端的结构示意图。如图9所示，所述终端1000可以包括：至少一个处理器1001，至少一个网络接口1004，用户接口1003，存储器1005，至少一个通信总线1002。Refer to FIG. 9, which provides a schematic structural diagram of a terminal according to an embodiment of this application. As shown in FIG. 9, the terminal 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.
其中，通信总线1002用于实现这些组件之间的连接通信。Among them, the communication bus 1002 is used to implement connection and communication between these components.
其中，用户接口1003可以包括显示屏(Display)、摄像头(Camera)，可选用户接口1003还可以包括标准的有线接口、无线接口。The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
其中，网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。Among them, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
其中，处理器1001可以包括一个或者多个处理核心。处理器1001利用各种接口和线路连接整个终端1000内的各个部分，通过运行或执行存储在存储器1005内的指令、程序、代码集或指令集，以及调用存储在存储器1005内的数据，执行终端1000的各种功能和处理数据。可选的，处理器1001可以采用数字信号处理(Digital Signal Processing，DSP)、现场可编程门阵列(Field-Programmable GateArray，FPGA)、可编程逻辑阵列(Programmable LogicArray，PLA)中的至少一种硬件形式来实现。处理器1001可集成中央处理器(Central Processing Unit，CPU)、图像处理器(Graphics Processing Unit，GPU)和调制解调器等中的一种或几种的组合。其中，CPU主要处理操作系 统、用户界面和应用程序等；GPU用于负责显示屏所需要显示的内容的渲染和绘制；调制解调器用于处理无线通信。可以理解的是，上述调制解调器也可以不集成到处理器1001中，单独通过一块芯片进行实现。The processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire terminal 1000, and executes the terminal by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Various functions and processing data of 1000. Optionally, the processor 1001 may use at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). Form to achieve. The processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is used to render and draw the content that needs to be displayed on the display; the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 1001, but may be implemented by a chip alone.
其中，存储器1005可以包括随机存储器(Random Access Memory，RAM)，也可以包括只读存储器(Read-Only Memory)。可选的，该存储器1005包括非瞬时性计算机可读介质(non-transitory computer-readable storage medium)。存储器1005可用于存储指令、程序、代码、代码集或指令集。存储器1005可包括存储程序区和存储数据区，其中，存储程序区可存储用于实现操作***的指令、用于至少一个功能的指令(比如触控功能、声音播放功能、图像播放功能等)、用于实现上述各个方法实施例的指令等；存储数据区可存储上面各个方法实施例中涉及到的数据等。存储器1005可选的还可以是至少一个位于远离前述处理器1001的存储装置。如图9所示，作为一种计算机存储介质的存储器1005中可以包括操作***、网络通信模块、用户接口模块以及诈骗电话的识别应用程序。The memory 1005 may include random access memory (Random Access Memory, RAM), and may also include read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, where the program storage area may store instructions for implementing the operating system and instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), Instructions and the like used to implement the above method embodiments; the storage data area can store the data and the like involved in the above method embodiments. Optionally, the memory 1005 may also be at least one storage device located far away from the foregoing processor 1001. As shown in FIG. 9, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a fraudulent phone identification application program.
在图9所示的终端1000中，用户接口1003主要用于为用户提供输入的接口，获取用户输入的数据；而处理器1001可以用于调用存储器1005中存储的诈骗电话的识别应用程序，并具体执行以下操作：In the terminal 1000 shown in FIG. 9, the user interface 1003 is mainly used to provide an input interface for the user to obtain data input by the user; and the processor 1001 may be used to call the fraudulent phone identification application stored in the memory 1005, and Specifically perform the following operations:
采集当前通话的语音数据；Collect the voice data of the current call;
根据语音识别技术将所述语音数据转换为文本数据；Converting the voice data into text data according to the voice recognition technology;
识别所述文本数据中是否包括预设关键词；Identifying whether the text data includes preset keywords;
若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
在一个或多个实施例中，处理器1001执行所述根据语音识别技术将所述语音数据转换为文本数据，包括：In one or more embodiments, the processor 1001 performing the conversion of the voice data into text data according to the voice recognition technology includes:
提取所述语音数据的声学特征参数；Extracting acoustic feature parameters of the voice data;
基于所述声学特征参数通过声学模型和语言模型得到所述文本数据。The text data is obtained through an acoustic model and a language model based on the acoustic feature parameters.
在一个或多个实施例中，处理器1001执行所述查询所述预设关键词关联的诈骗案例，包括：In one or more embodiments, the processor 1001 executing the query of the fraud case associated with the preset keyword includes:
在本地数据库中查询与所述预设关键词关联的诈骗案例；或Query the fraud cases associated with the preset keywords in the local database; or
在部署在互联网中的服务器上查询与所述预设关键词关联的诈骗案例。Inquire about fraud cases associated with the preset keywords on a server deployed on the Internet.
在一个或多个实施例中，处理器1001执行所述通过显示单元显示所述诈骗案例，包括：In one or more embodiments, the processor 1001 executing the display of the fraud case through the display unit includes:
通过显示单元在所述当前通话的显示界面显示所述诈骗案例。The fraud case is displayed on the display interface of the current call through the display unit.
在一个或多个实施例中，处理器1001还用于执行：In one or more embodiments, the processor 1001 is further configured to execute:
通过预设提醒方式提醒用户所述当前通话为诈骗电话；其中，所述预设提醒方式包括震动提醒方式。The user is reminded by a preset reminding method that the current call is a fraudulent call; wherein, the preset reminding method includes a vibration reminding method.
在一个或多个实施例中，处理器1001还用于执行：In one or more embodiments, the processor 1001 is further configured to execute:
向所述用户预先存储的电话号码对应的终端发送诈骗提示消息；其中，所述诈骗提示消息包括来电号码、通话时间、所述预设关键词以及所述诈骗案例。Send a fraud reminder message to the terminal corresponding to the phone number pre-stored by the user; wherein the fraud reminder message includes the caller number, the call time, the preset keywords, and the fraud case.
在一个或多个实施例中，处理器1001还用于执行：In one or more embodiments, the processor 1001 is further configured to execute:
在所述当前通话结束之后，接收防诈骗提醒短信。After the current call ends, receive an anti-fraud reminder short message.
在本申请实施例中，采集当前通话的语音数据，将语音数据转换为文本数据，在识别文本数据中包括预设关键词时，查询与预设关键词关联的诈骗案例，以及通过显示单元显示诈骗案例。这样可以通过当前通话的内容识别诈骗电话，以及显示诈骗案例，用户通过阅读诈骗案例的提醒能识破诈骗分子的伎俩，降低被诈骗的风险。In the embodiment of the present application, the voice data of the current call is collected, the voice data is converted into text data, and when the preset keywords are included in the recognized text data, the fraud cases associated with the preset keywords are searched and displayed on the display unit Fraud cases. In this way, fraudulent calls can be identified through the content of the current call, and fraud cases can be displayed. Users can see through the tricks of fraudsters by reading the reminders of fraud cases and reduce the risk of being defrauded.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体或随机存储记忆体等。A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through a computer program. The program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments. Wherein, the storage medium can be a magnetic disk, an optical disc, a read-only storage memory, or a random storage memory, etc.
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。The above-disclosed are only preferred embodiments of this application, and of course the scope of rights of this application cannot be limited by this. Therefore, equivalent changes made according to the claims of this application still fall within the scope of this application.

Claims (10)

  1. 一种诈骗电话的识别方法，其特征在于，所述方法包括：A method for identifying fraudulent calls, which is characterized in that the method includes:
    采集当前通话的语音数据；Collect the voice data of the current call;
    根据语音识别技术将所述语音数据转换为文本数据；Converting the voice data into text data according to the voice recognition technology;
    识别所述文本数据中是否包括预设关键词；Identifying whether the text data includes preset keywords;
    若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
  2. 根据权利要求1所述的方法，其特征在于，所述根据语音识别技术将所述语音数据转换为文本数据，包括：The method according to claim 1, wherein said converting said voice data into text data according to a voice recognition technology comprises:
    提取所述语音数据的声学特征参数；Extracting acoustic feature parameters of the voice data;
    基于所述声学特征参数通过声学模型和语言模型得到所述文本数据。The text data is obtained through an acoustic model and a language model based on the acoustic feature parameters.
  3. 根据权利要求1所述的方法，其特征在于，所述查询所述预设关键词关联的诈骗案例，包括：The method according to claim 1, wherein the querying the fraud case associated with the preset keyword comprises:
    在本地数据库中查询与所述预设关键词关联的诈骗案例；或Query the fraud cases associated with the preset keywords in the local database; or
    在部署在互联网中的服务器上查询与所述预设关键词关联的诈骗案例。Inquire about fraud cases associated with the preset keywords on a server deployed on the Internet.
  4. 根据权利要求1所述的方法，其特征在于，所述通过显示单元显示所述诈骗案例，包括：The method according to claim 1, wherein the displaying the fraud case through a display unit comprises:
    通过显示单元在所述当前通话的显示界面显示所述诈骗案例。The fraud case is displayed on the display interface of the current call through the display unit.
  5. 根据权利要求4所述的方法，其特征在于，所述通过显示单元在所述当前通话的显示界面显示所述诈骗案例之前，还包括：The method according to claim 4, characterized in that, before displaying the fraud case on the display interface of the current call through the display unit, the method further comprises:
    通过预设提醒方式提醒用户所述当前通话为诈骗电话；其中，所述预设提醒方式包括震动提醒方式。The user is reminded by a preset reminding method that the current call is a fraudulent call; wherein, the preset reminding method includes a vibration reminding method.
  6. 根据权利要求1所述的方法，其特征在于，所述方法还包括：The method according to claim 1, wherein the method further comprises:
    向所述用户预先存储的电话号码对应的终端发送诈骗提示消息；其中，所述诈骗提示消息包括来电号码、通话时间、所述预设关键词以及所述诈骗案例。Send a fraud reminder message to the terminal corresponding to the phone number pre-stored by the user; wherein the fraud reminder message includes the caller number, the call time, the preset keywords, and the fraud case.
  7. 根据权利要求1所述的方法，其特征在于，所述方法还包括：The method according to claim 1, wherein the method further comprises:
    在所述当前通话结束之后，接收防诈骗提醒短信。After the current call ends, receive an anti-fraud reminder short message.
  8. 一种诈骗电话的识别装置，其特征在于，所述装置包括：A device for identifying fraudulent calls, which is characterized in that the device comprises:
    采集单元，用于采集当前通话的语音数据；The collection unit is used to collect the voice data of the current call;
    转换单元，用于根据语音识别技术将所述语音数据转换为文本数据；A conversion unit for converting the voice data into text data according to the voice recognition technology;
    识别单元，用于识别所述文本数据中是否包括预设关键词；Recognition unit for recognizing whether preset keywords are included in the text data;
    若为是，查询所述预设关键词关联的诈骗案例，以及通过显示单元显示所述诈骗案例。If yes, query the fraud case associated with the preset keyword, and display the fraud case through the display unit.
  9. 一种计算机存储介质，其特征在于，所述计算机存储介质存储有多条指令，所述指令适于由处理器加载并执行如权利要求1～7任意一项的方法步骤。A computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1-7.
  10. 一种终端，其特征在于，包括：处理器和存储器；其中，所述存储器存储有计算机程序，所述计算机程序适于由所述处理器加载并执行如权利要求1～7任意一项的方法步骤。A terminal, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the method according to any one of claims 1-7 step.
PCT/CN2020/134094 2020-03-16 2020-12-04 Fraudulent call identification method and device, storage medium, and terminal WO2021184837A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010183268.9A CN111447327A (en) 2020-03-16 2020-03-16 Fraud telephone identification method, device, storage medium and terminal
CN202010183268.9 2020-03-16

Publications (1)

Publication Number Publication Date
WO2021184837A1 true WO2021184837A1 (en) 2021-09-23

Family

ID=71654099

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/134094 WO2021184837A1 (en) 2020-03-16 2020-12-04 Fraudulent call identification method and device, storage medium, and terminal

Country Status (2)

Country Link
CN (1) CN111447327A (en)
WO (1) WO2021184837A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115022464A (en) * 2022-05-06 2022-09-06 中国联合网络通信集团有限公司 Number processing method, system, computing device and storage medium

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111447327A (en) * 2020-03-16 2020-07-24 宇龙计算机通信科技(深圳)有限公司 Fraud telephone identification method, device, storage medium and terminal
CN114067834A (en) * 2020-07-30 2022-02-18 ***通信集团有限公司 Bad preamble recognition method and device, storage medium and computer equipment
CN113257250A (en) * 2021-05-11 2021-08-13 歌尔股份有限公司 Fraud behavior detection method, device and storage medium
CN114598777A (en) * 2022-02-25 2022-06-07 马上消费金融股份有限公司 Intention detection method, device, electronic equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104427079A (en) * 2013-09-09 2015-03-18 中兴通讯股份有限公司 Early warning method and device of user voice calls
CN107360576A (en) * 2017-07-25 2017-11-17 上海思依暄机器人科技股份有限公司 A kind of method and system for identifying fraud information, electronic equipment, server
US20190373105A1 (en) * 2018-05-30 2019-12-05 International Business Machines Corporation Cognitive telephone fraud detection
CN110868501A (en) * 2019-11-13 2020-03-06 刘峰刚 Fraud prevention method based on voice recognition and fraud prevention hearing aid
CN111447327A (en) * 2020-03-16 2020-07-24 宇龙计算机通信科技(深圳)有限公司 Fraud telephone identification method, device, storage medium and terminal

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103685613B (en) * 2013-12-05 2016-08-17 江苏大学 A kind of anti-telephone fraud system and method based on speech recognition
JP2015220594A (en) * 2014-05-16 2015-12-07 日本電信電話株式会社 Specific speech notification device and specific speech notification method
CN106412348B (en) * 2016-11-14 2019-04-12 商客通尚景科技（上海）股份有限公司 A kind of telephonograph identification pre-warning and control method
CN108134998A (en) * 2017-12-05 2018-06-08 南京南邮信息产业技术研究院有限公司 Information fraud method for early warning and system based on mobile big data
CN108616890A (en) * 2018-04-16 2018-10-02 中山易美信息技术有限公司 A kind of swindle ticket analysis system
JP6685562B2 (en) * 2018-09-06 2020-04-22 桑原　徹 Telephone fraud reporting device
CN109547651A (en) * 2018-10-22 2019-03-29 北京奇虎科技有限公司 A kind of reminding method, device and computer storage medium
CN110312031A (en) * 2018-12-27 2019-10-08 华为终端有限公司 Incoming number processing method and electronic equipment
CN110381219A (en) * 2019-06-18 2019-10-25 武汉华夏理工学院 A kind of anti-swindle system of communication
CN110738562B (en) * 2019-10-16 2023-04-25 支付宝(杭州)信息技术有限公司 Method, device and equipment for generating risk reminding information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104427079A (en) * 2013-09-09 2015-03-18 中兴通讯股份有限公司 Early warning method and device of user voice calls
CN107360576A (en) * 2017-07-25 2017-11-17 上海思依暄机器人科技股份有限公司 A kind of method and system for identifying fraud information, electronic equipment, server
US20190373105A1 (en) * 2018-05-30 2019-12-05 International Business Machines Corporation Cognitive telephone fraud detection
CN110868501A (en) * 2019-11-13 2020-03-06 刘峰刚 Fraud prevention method based on voice recognition and fraud prevention hearing aid
CN111447327A (en) * 2020-03-16 2020-07-24 宇龙计算机通信科技(深圳)有限公司 Fraud telephone identification method, device, storage medium and terminal

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115022464A (en) * 2022-05-06 2022-09-06 中国联合网络通信集团有限公司 Number processing method, system, computing device and storage medium

Also Published As

Publication number Publication date
CN111447327A (en) 2020-07-24

Similar Documents

Publication Publication Date Title
WO2021184837A1 (en) Fraudulent call identification method and device, storage medium, and terminal
US10810510B2 (en) Conversation and context aware fraud and abuse prevention agent
CN109147770B (en) Voice recognition feature optimization and dynamic registration method, client and server
CN107343077B (en) Method, device and equipment for identifying malicious phone and establishing identification model
TW201905675A (en) Data update method, client and electronic device
JP2020519946A (en) Voice query detection and suppression
CN103190139B (en) For providing the system and method for conferencing information
CN108010513B (en) Voice processing method and device
KR101795593B1 (en) Device and method for protecting phone counselor
WO2020253128A1 (en) Voice recognition-based communication service method, apparatus, computer device, and storage medium
CN111683317B (en) Prompting method and device applied to earphone, terminal and storage medium
WO2014154057A1 (en) Pre-alarming method and device for user voice call and computer storage medium
JP2013206389A (en) Intimacy calculation method, intimacy calculation program and intimacy calculation device
KR20150041592A (en) Method for updating contact information in callee electronic device, and the electronic device
CN111092999A (en) Data request processing method and device
WO2021051504A1 (en) Method for identifying abnormal call party, device, computer apparatus, and storage medium
WO2017084591A1 (en) Identification method and device for malicious call
JP6183841B2 (en) Call center term management system and method for grasping signs of NG word
CN113518075B (en) Phishing warning method, device, electronic equipment and storage medium
JP2010273130A (en) Device for determining progress of fraud, dictionary generator, method for determining progress of fraud, and method for generating dictionary
JP2010002973A (en) Voice data subject estimation device, and call center using the same
CN107154996B (en) Incoming call interception method and device, storage medium and terminal
CN110263135A (en) A kind of data exchange matching process, device, medium and electronic equipment
CN111601000B (en) Communication network fraud identification method and device and electronic equipment
CN109634554A (en) Method and apparatus for output information

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20925193

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20925193

Country of ref document: EP

Kind code of ref document: A1